diff options
Diffstat (limited to 'include/net')
179 files changed, 6899 insertions, 2508 deletions
diff --git a/include/net/9p/client.h b/include/net/9p/client.h index 78ebcf782ce5..4f785098c67a 100644 --- a/include/net/9p/client.h +++ b/include/net/9p/client.h @@ -207,6 +207,8 @@ int p9_client_read(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err int p9_client_read_once(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); +struct netfs_io_subrequest; +void p9_client_write_subreq(struct netfs_io_subrequest *subreq); 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/act_api.h b/include/net/act_api.h index 77ee0c657e2c..404df8557f6a 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -219,7 +219,6 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], int bind, int ref, bool terse); int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int); -int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int); static inline void tcf_action_update_bstats(struct tc_action *a, struct sk_buff *skb) diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 62a407db1bf5..9e5e95988b9e 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -37,10 +37,14 @@ struct prefix_info { struct __packed { #if defined(__BIG_ENDIAN_BITFIELD) __u8 onlink : 1, - autoconf : 1, - reserved : 6; + autoconf : 1, + routeraddr : 1, + preferpd : 1, + reserved : 4; #elif defined(__LITTLE_ENDIAN_BITFIELD) - __u8 reserved : 6, + __u8 reserved : 4, + preferpd : 1, + routeraddr : 1, autoconf : 1, onlink : 1; #else @@ -84,6 +88,23 @@ struct ifa6_config { u16 scope; }; +enum addr_type_t { + UNICAST_ADDR, + MULTICAST_ADDR, + ANYCAST_ADDR, +}; + +struct inet6_fill_args { + u32 portid; + u32 seq; + int event; + unsigned int flags; + int netnsid; + int ifindex; + enum addr_type_t type; + bool force_rt_scope_universe; +}; + int addrconf_init(void); void addrconf_cleanup(void); @@ -183,10 +204,12 @@ static inline int addrconf_ifid_eui48(u8 *eui, struct net_device *dev) return 0; } +#define INFINITY_LIFE_TIME 0xFFFFFFFF + static inline unsigned long addrconf_timeout_fixup(u32 timeout, unsigned int unit) { - if (timeout == 0xffffffff) + if (timeout == INFINITY_LIFE_TIME) return ~0UL; /* @@ -324,10 +347,15 @@ static inline struct inet6_dev *__in6_dev_get(const struct net_device *dev) return rcu_dereference_rtnl(dev->ip6_ptr); } +static inline struct inet6_dev *__in6_dev_get_rtnl_net(const struct net_device *dev) +{ + return rtnl_net_dereference(dev_net(dev), dev->ip6_ptr); +} + /** * __in6_dev_stats_get - get inet6_dev pointer for stats * @dev: network device - * @skb: skb for original incoming interface if neeeded + * @skb: skb for original incoming interface if needed * * Caller must hold rcu_read_lock or RTNL, because this function * does not take a reference on the inet6_dev. @@ -519,4 +547,11 @@ int if6_proc_init(void); void if6_proc_exit(void); #endif +int inet6_fill_ifmcaddr(struct sk_buff *skb, + const struct ifmcaddr6 *ifmca, + struct inet6_fill_args *args); + +int inet6_fill_ifacaddr(struct sk_buff *skb, + const struct ifacaddr6 *ifaca, + struct inet6_fill_args *args); #endif diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index 0754c463224a..0fb4c41c9bbf 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -16,6 +16,7 @@ struct sock; struct socket; struct rxrpc_call; struct rxrpc_peer; +struct krb5_buffer; enum rxrpc_abort_reason; enum rxrpc_interruptibility { @@ -24,23 +25,33 @@ enum rxrpc_interruptibility { RXRPC_UNINTERRUPTIBLE, /* Call should not be interruptible at all */ }; +enum rxrpc_oob_type { + RXRPC_OOB_CHALLENGE, /* Security challenge for a connection */ +}; + /* * Debug ID counter for tracing. */ extern atomic_t rxrpc_debug_id; +/* + * Operations table for rxrpc to call out to a kernel application (e.g. kAFS). + */ +struct rxrpc_kernel_ops { + void (*notify_new_call)(struct sock *sk, struct rxrpc_call *call, + unsigned long user_call_ID); + void (*discard_new_call)(struct rxrpc_call *call, unsigned long user_call_ID); + void (*user_attach_call)(struct rxrpc_call *call, unsigned long user_call_ID); + void (*notify_oob)(struct sock *sk, struct sk_buff *oob); +}; + typedef void (*rxrpc_notify_rx_t)(struct sock *, struct rxrpc_call *, unsigned long); typedef void (*rxrpc_notify_end_tx_t)(struct sock *, struct rxrpc_call *, unsigned long); -typedef void (*rxrpc_notify_new_call_t)(struct sock *, struct rxrpc_call *, - unsigned long); -typedef void (*rxrpc_discard_new_call_t)(struct rxrpc_call *, unsigned long); -typedef void (*rxrpc_user_attach_call_t)(struct rxrpc_call *, unsigned long); -void rxrpc_kernel_new_call_notification(struct socket *, - rxrpc_notify_new_call_t, - rxrpc_discard_new_call_t); +void rxrpc_kernel_set_notifications(struct socket *sock, + const struct rxrpc_kernel_ops *app_ops); struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, struct rxrpc_peer *peer, struct key *key, @@ -69,17 +80,36 @@ struct rxrpc_peer *rxrpc_kernel_get_peer(struct rxrpc_peer *peer); struct rxrpc_peer *rxrpc_kernel_get_call_peer(struct socket *sock, struct rxrpc_call *call); const struct sockaddr_rxrpc *rxrpc_kernel_remote_srx(const struct rxrpc_peer *peer); const struct sockaddr *rxrpc_kernel_remote_addr(const struct rxrpc_peer *peer); +unsigned long rxrpc_kernel_set_peer_data(struct rxrpc_peer *peer, unsigned long app_data); +unsigned long rxrpc_kernel_get_peer_data(const struct rxrpc_peer *peer); unsigned int rxrpc_kernel_get_srtt(const struct rxrpc_peer *); -int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t, - rxrpc_user_attach_call_t, unsigned long, gfp_t, - unsigned int); +int rxrpc_kernel_charge_accept(struct socket *sock, rxrpc_notify_rx_t notify_rx, + unsigned long user_call_ID, gfp_t gfp, + unsigned int debug_id); void rxrpc_kernel_set_tx_length(struct socket *, struct rxrpc_call *, s64); bool rxrpc_kernel_check_life(const struct socket *, const struct rxrpc_call *); -u32 rxrpc_kernel_get_epoch(struct socket *, struct rxrpc_call *); -void rxrpc_kernel_set_max_life(struct socket *, struct rxrpc_call *, - unsigned long); int rxrpc_sock_set_min_security_level(struct sock *sk, unsigned int val); int rxrpc_sock_set_security_keyring(struct sock *, struct key *); +int rxrpc_sock_set_manage_response(struct sock *sk, bool set); + +enum rxrpc_oob_type rxrpc_kernel_query_oob(struct sk_buff *oob, + struct rxrpc_peer **_peer, + unsigned long *_peer_appdata); +struct sk_buff *rxrpc_kernel_dequeue_oob(struct socket *sock, + enum rxrpc_oob_type *_type); +void rxrpc_kernel_free_oob(struct sk_buff *oob); +void rxrpc_kernel_query_challenge(struct sk_buff *challenge, + struct rxrpc_peer **_peer, + unsigned long *_peer_appdata, + u16 *_service_id, u8 *_security_index); +int rxrpc_kernel_reject_challenge(struct sk_buff *challenge, u32 abort_code, + int error, enum rxrpc_abort_reason why); +int rxkad_kernel_respond_to_challenge(struct sk_buff *challenge); +u32 rxgk_kernel_query_challenge(struct sk_buff *challenge); +int rxgk_kernel_respond_to_challenge(struct sk_buff *challenge, + struct krb5_buffer *appdata); +u8 rxrpc_kernel_query_call_security(struct rxrpc_call *call, + u16 *_service_id, u32 *_enctype); #endif /* _NET_RXRPC_H */ diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 3dee0b2721aa..1af1841b7601 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -2,11 +2,15 @@ #ifndef __LINUX_NET_AFUNIX_H #define __LINUX_NET_AFUNIX_H -#include <linux/socket.h> -#include <linux/un.h> +#include <linux/atomic.h> #include <linux/mutex.h> +#include <linux/net.h> +#include <linux/path.h> #include <linux/refcount.h> +#include <linux/spinlock.h> +#include <linux/wait.h> #include <net/sock.h> +#include <uapi/linux/un.h> #if IS_ENABLED(CONFIG_UNIX) struct unix_sock *unix_get_socket(struct file *filp); @@ -17,43 +21,17 @@ static inline struct unix_sock *unix_get_socket(struct file *filp) } #endif -extern spinlock_t unix_gc_lock; -extern unsigned int unix_tot_inflight; - -void unix_inflight(struct user_struct *user, struct file *fp); -void unix_notinflight(struct user_struct *user, struct file *fp); -void unix_gc(void); -void wait_for_unix_gc(struct scm_fp_list *fpl); - -struct sock *unix_peer_get(struct sock *sk); - -#define UNIX_HASH_MOD (256 - 1) -#define UNIX_HASH_SIZE (256 * 2) -#define UNIX_HASH_BITS 8 - struct unix_address { refcount_t refcnt; int len; struct sockaddr_un name[]; }; -struct unix_skb_parms { - struct pid *pid; /* Skb credentials */ - kuid_t uid; - kgid_t gid; - struct scm_fp_list *fp; /* Passed files */ -#ifdef CONFIG_SECURITY_NETWORK - u32 secid; /* Security ID */ -#endif - u32 consumed; -} __randomize_layout; - struct scm_stat { atomic_t nr_fds; + unsigned long nr_unix_fds; }; -#define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb)) - /* The AF_UNIX socket */ struct unix_sock { /* WARNING: sk has to be the first member */ @@ -62,13 +40,11 @@ struct unix_sock { struct path path; struct mutex iolock, bindlock; struct sock *peer; - struct list_head link; - unsigned long inflight; + struct sock *listener; + struct unix_vertex *vertex; spinlock_t lock; - unsigned long gc_flags; -#define UNIX_GC_CANDIDATE 0 -#define UNIX_GC_MAYBE_CYCLE 1 struct socket_wq peer_wq; +#define peer_wait peer_wq.wait wait_queue_entry_t peer_wake; struct scm_stat scm_stat; #if IS_ENABLED(CONFIG_AF_UNIX_OOB) @@ -81,47 +57,5 @@ struct unix_sock { #define unix_state_lock(s) spin_lock(&unix_sk(s)->lock) #define unix_state_unlock(s) spin_unlock(&unix_sk(s)->lock) -enum unix_socket_lock_class { - U_LOCK_NORMAL, - U_LOCK_SECOND, /* for double locking, see unix_state_double_lock(). */ - U_LOCK_DIAG, /* used while dumping icons, see sk_diag_dump_icons(). */ - U_LOCK_GC_LISTENER, /* used for listening socket while determining gc - * candidates to close a small race window. - */ -}; -static inline void unix_state_lock_nested(struct sock *sk, - enum unix_socket_lock_class subclass) -{ - spin_lock_nested(&unix_sk(sk)->lock, subclass); -} - -#define peer_wait peer_wq.wait - -long unix_inq_len(struct sock *sk); -long unix_outq_len(struct sock *sk); - -int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size, - int flags); -int __unix_stream_recvmsg(struct sock *sk, struct msghdr *msg, size_t size, - int flags); -#ifdef CONFIG_SYSCTL -int unix_sysctl_register(struct net *net); -void unix_sysctl_unregister(struct net *net); -#else -static inline int unix_sysctl_register(struct net *net) { return 0; } -static inline void unix_sysctl_unregister(struct net *net) {} -#endif - -#ifdef CONFIG_BPF_SYSCALL -extern struct proto unix_dgram_proto; -extern struct proto unix_stream_proto; - -int unix_dgram_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); -int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); -void __init unix_bpf_build_proto(void); -#else -static inline void __init unix_bpf_build_proto(void) -{} -#endif #endif diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 535701efc1e5..d56e6e135158 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -169,6 +169,9 @@ struct vsock_transport { void (*notify_buffer_size)(struct vsock_sock *, u64 *); int (*notify_set_rcvlowat)(struct vsock_sock *vsk, int val); + /* SIOCOUTQ ioctl */ + ssize_t (*unsent_bytes)(struct vsock_sock *vsk); + /* Shutdown. */ int (*shutdown)(struct vsock_sock *, int); @@ -218,6 +221,7 @@ void vsock_for_each_connected_socket(struct vsock_transport *transport, void (*fn)(struct sock *sk)); int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk); bool vsock_find_cid(unsigned int cid); +void vsock_linger(struct sock *sk); /**** TAP ****/ @@ -230,8 +234,12 @@ struct vsock_tap { int vsock_add_tap(struct vsock_tap *vt); int vsock_remove_tap(struct vsock_tap *vt); void vsock_deliver_tap(struct sk_buff *build_skb(void *opaque), void *opaque); +int __vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags); int vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); +int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags); int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); diff --git a/include/net/ax25.h b/include/net/ax25.h index 0d939e5aee4e..a7bba42dde15 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -139,7 +139,9 @@ enum { AX25_VALUES_N2, /* Default N2 value */ AX25_VALUES_PACLEN, /* AX.25 MTU */ AX25_VALUES_PROTOCOL, /* Std AX.25, DAMA Slave, DAMA Master */ +#ifdef CONFIG_AX25_DAMA_SLAVE AX25_VALUES_DS_TIMEOUT, /* DAMA Slave timeout */ +#endif AX25_MAX_VALUES /* THIS MUST REMAIN THE LAST ENTRY OF THIS LIST */ }; @@ -216,7 +218,7 @@ typedef struct { struct ctl_table; typedef struct ax25_dev { - struct ax25_dev *next; + struct list_head list; struct net_device *dev; netdevice_tracker dev_tracker; @@ -229,6 +231,7 @@ typedef struct ax25_dev { #endif refcount_t refcount; bool device_up; + struct rcu_head rcu; } ax25_dev; typedef struct ax25_cb { @@ -288,9 +291,8 @@ static inline void ax25_dev_hold(ax25_dev *ax25_dev) static inline void ax25_dev_put(ax25_dev *ax25_dev) { - if (refcount_dec_and_test(&ax25_dev->refcount)) { - kfree(ax25_dev); - } + if (refcount_dec_and_test(&ax25_dev->refcount)) + kfree_rcu(ax25_dev, rcu); } static inline __be16 ax25_type_trans(struct sk_buff *skb, struct net_device *dev) { @@ -330,13 +332,12 @@ int ax25_addr_size(const ax25_digi *); void ax25_digi_invert(const ax25_digi *, ax25_digi *); /* ax25_dev.c */ -extern ax25_dev *ax25_dev_list; extern spinlock_t ax25_dev_lock; #if IS_ENABLED(CONFIG_AX25) -static inline ax25_dev *ax25_dev_ax25dev(struct net_device *dev) +static inline ax25_dev *ax25_dev_ax25dev(const struct net_device *dev) { - return dev->ax25_ptr; + return rcu_dereference_rtnl(dev->ax25_ptr); } #endif @@ -417,7 +418,6 @@ void ax25_rt_device_down(struct net_device *); int ax25_rt_ioctl(unsigned int, void __user *); extern const struct seq_operations ax25_rt_seqops; ax25_route *ax25_get_route(ax25_address *addr, struct net_device *dev); -int ax25_rt_autobind(ax25_cb *, ax25_address *); struct sk_buff *ax25_rt_build_path(struct sk_buff *, ax25_address *, ax25_address *, ax25_digi *); void ax25_rt_free(void); diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index eaec5d6caa29..114299bd8b98 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -29,6 +29,7 @@ #include <linux/poll.h> #include <net/sock.h> #include <linux/seq_file.h> +#include <linux/ethtool.h> #define BT_SUBSYS_VERSION 2 #define BT_SUBSYS_REVISION 22 @@ -123,6 +124,7 @@ struct bt_voice { #define BT_VOICE_TRANSPARENT 0x0003 #define BT_VOICE_CVSD_16BIT 0x0060 +#define BT_VOICE_TRANSPARENT_16BIT 0x0063 #define BT_SNDMTU 12 #define BT_RCVMTU 13 @@ -155,6 +157,7 @@ struct bt_voice { #define BT_PKT_STATUS 16 #define BT_SCM_PKT_STATUS 0x03 +#define BT_SCM_ERROR 0x04 #define BT_ISO_QOS 17 @@ -285,7 +288,7 @@ void bt_err_ratelimited(const char *fmt, ...); bt_err_ratelimited("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__) /* Connection and socket states */ -enum { +enum bt_sock_state { BT_CONNECTED = 1, /* Equal to TCP_ESTABLISHED to make net code happy */ BT_OPEN, BT_BOUND, @@ -403,6 +406,7 @@ 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); +bool bt_sock_linked(struct bt_sock_list *l, struct sock *s); struct sock *bt_sock_alloc(struct net *net, struct socket *sock, struct proto *prot, int proto, gfp_t prio, int kern); int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, @@ -441,6 +445,13 @@ typedef void (*hci_req_complete_t)(struct hci_dev *hdev, u8 status, u16 opcode); typedef void (*hci_req_complete_skb_t)(struct hci_dev *hdev, u8 status, u16 opcode, struct sk_buff *skb); +void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status, + hci_req_complete_t *req_complete, + hci_req_complete_skb_t *req_complete_skb); + +int hci_ethtool_ts_info(unsigned int index, int sk_proto, + struct kernel_ethtool_ts_info *ts_info); + #define HCI_REQ_START BIT(0) #define HCI_REQ_SKB BIT(1) @@ -585,15 +596,6 @@ static inline struct sk_buff *bt_skb_sendmmsg(struct sock *sk, return skb; } -static inline int bt_copy_from_sockptr(void *dst, size_t dst_size, - sockptr_t src, size_t src_size) -{ - if (dst_size > src_size) - return -EINVAL; - - return copy_from_sockptr(dst, src, dst_size); -} - int bt_to_errno(u16 code); __u8 bt_status(int err); diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 5c12761cbc0e..82cbd54443ac 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -1,7 +1,7 @@ /* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2000-2001 Qualcomm Incorporated - Copyright 2023 NXP + Copyright 2023-2024 NXP Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> @@ -29,13 +29,11 @@ #define HCI_MAX_ACL_SIZE 1024 #define HCI_MAX_SCO_SIZE 255 #define HCI_MAX_ISO_SIZE 251 +#define HCI_MAX_ISO_BIS 31 #define HCI_MAX_EVENT_SIZE 260 #define HCI_MAX_FRAME_SIZE (HCI_MAX_ACL_SIZE + 4) #define HCI_LINK_KEY_SIZE 16 -#define HCI_AMP_LINK_KEY_SIZE (2 * HCI_LINK_KEY_SIZE) - -#define HCI_MAX_AMP_ASSOC_SIZE 672 #define HCI_MAX_CPB_DATA_SIZE 252 @@ -70,26 +68,7 @@ #define HCI_I2C 8 #define HCI_SMD 9 #define HCI_VIRTIO 10 - -/* HCI controller types */ -#define HCI_PRIMARY 0x00 -#define HCI_AMP 0x01 - -/* First BR/EDR Controller shall have ID = 0 */ -#define AMP_ID_BREDR 0x00 - -/* AMP controller types */ -#define AMP_TYPE_BREDR 0x00 -#define AMP_TYPE_80211 0x01 - -/* AMP controller status */ -#define AMP_STATUS_POWERED_DOWN 0x00 -#define AMP_STATUS_BLUETOOTH_ONLY 0x01 -#define AMP_STATUS_NO_CAPACITY 0x02 -#define AMP_STATUS_LOW_CAPACITY 0x03 -#define AMP_STATUS_MEDIUM_CAPACITY 0x04 -#define AMP_STATUS_HIGH_CAPACITY 0x05 -#define AMP_STATUS_FULL_CAPACITY 0x06 +#define HCI_IPC 11 /* HCI device quirks */ enum { @@ -229,14 +208,24 @@ enum { */ HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, - /* When this quirk is set, the controller has validated that - * LE states reported through the HCI_LE_READ_SUPPORTED_STATES are - * valid. This mechanism is necessary as many controllers have - * been seen has having trouble initiating a connectable - * advertisement despite the state combination being reported as - * supported. + /* When this quirk is set consider Sync Flow Control as supported by + * the driver. + * + * This quirk must be set before hci_register_dev is called. */ - HCI_QUIRK_VALID_LE_STATES, + HCI_QUIRK_SYNC_FLOWCTL_SUPPORTED, + + /* When this quirk is set, the LE states reported through the + * HCI_LE_READ_SUPPORTED_STATES are invalid/broken. + * + * This mechanism is necessary as many controllers have been seen has + * having trouble initiating a connectable advertisement despite the + * state combination being reported as supported. + * + * This quirk can be set before hci_register_dev is called or + * during the hdev->setup vendor callback. + */ + HCI_QUIRK_BROKEN_LE_STATES, /* When this quirk is set, then erroneous data reporting * is ignored. This is mainly due to the fact that the HCI @@ -320,6 +309,20 @@ enum { */ HCI_QUIRK_BROKEN_SET_RPA_TIMEOUT, + /* + * When this quirk is set, the HCI_OP_LE_EXT_CREATE_CONN command is + * disabled. This is required for the Actions Semiconductor ATS2851 + * based controllers, which erroneously claims to support it. + */ + HCI_QUIRK_BROKEN_EXT_CREATE_CONN, + + /* + * When this quirk is set, the command WRITE_AUTH_PAYLOAD_TIMEOUT is + * skipped. This is required for the Actions Semiconductor ATS2851 + * based controllers, due to a race condition in pairing process. + */ + HCI_QUIRK_BROKEN_WRITE_AUTH_PAYLOAD_TIMEOUT, + /* When this quirk is set, MSFT extension monitor tracking by * address filter is supported. Since tracking quantity of each * pattern is limited, this feature supports tracking multiple @@ -347,6 +350,33 @@ enum { * claim to support it. */ HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE, + + /* + * When this quirk is set, the reserved bits of Primary/Secondary_PHY + * inside the LE Extended Advertising Report events are discarded. + * This is required for some Apple/Broadcom controllers which + * abuse these reserved bits for unrelated flags. + * + * This quirk can be set before hci_register_dev is called or + * during the hdev->setup vendor callback. + */ + HCI_QUIRK_FIXUP_LE_EXT_ADV_REPORT_PHY, + + /* When this quirk is set, the HCI_OP_READ_VOICE_SETTING command is + * skipped. This is required for a subset of the CSR controller clones + * which erroneously claim to support it. + * + * This quirk must be set before hci_register_dev is called. + */ + HCI_QUIRK_BROKEN_READ_VOICE_SETTING, + + /* When this quirk is set, the HCI_OP_READ_PAGE_SCAN_TYPE command is + * skipped. This is required for a subset of the CSR controller clones + * which erroneously claim to support it. + * + * This quirk must be set before hci_register_dev is called. + */ + HCI_QUIRK_BROKEN_READ_PAGE_SCAN_TYPE, }; /* HCI device flags */ @@ -425,13 +455,13 @@ enum { HCI_WIDEBAND_SPEECH_ENABLED, HCI_EVENT_FILTER_CONFIGURED, HCI_PA_SYNC, + HCI_SCO_FLOWCTL, HCI_DUT_MODE, HCI_VENDOR_DIAG, HCI_FORCE_BREDR_SMP, HCI_FORCE_STATIC_ADDR, HCI_LL_RPA_RESOLUTION, - HCI_ENABLE_LL_PRIVACY, HCI_CMD_PENDING, HCI_FORCE_NO_MITM, HCI_QUALITY_REPORT, @@ -456,7 +486,6 @@ enum { #define HCI_AUTO_OFF_TIMEOUT msecs_to_jiffies(2000) /* 2 seconds */ #define HCI_ACL_CONN_TIMEOUT msecs_to_jiffies(20000) /* 20 seconds */ #define HCI_LE_CONN_TIMEOUT msecs_to_jiffies(20000) /* 20 seconds */ -#define HCI_LE_AUTOCONN_TIMEOUT msecs_to_jiffies(4000) /* 4 seconds */ /* HCI data types */ #define HCI_COMMAND_PKT 0x01 @@ -465,6 +494,7 @@ enum { #define HCI_EVENT_PKT 0x04 #define HCI_ISODATA_PKT 0x05 #define HCI_DIAG_PKT 0xf0 +#define HCI_DRV_PKT 0xf1 #define HCI_VENDOR_PKT 0xff /* HCI packet types */ @@ -528,8 +558,8 @@ enum { #define ESCO_LINK 0x02 /* Low Energy links do not have defined link type. Use invented one */ #define LE_LINK 0x80 -#define AMP_LINK 0x81 -#define ISO_LINK 0x82 +#define CIS_LINK 0x82 +#define BIS_LINK 0x83 #define INVALID_LINK 0xff /* LMP features */ @@ -679,7 +709,7 @@ enum { #define HCI_ERROR_REMOTE_POWER_OFF 0x15 #define HCI_ERROR_LOCAL_HOST_TERM 0x16 #define HCI_ERROR_PAIRING_NOT_ALLOWED 0x18 -#define HCI_ERROR_UNSUPPORTED_REMOTE_FEATURE 0x1e +#define HCI_ERROR_UNSUPPORTED_REMOTE_FEATURE 0x1a #define HCI_ERROR_INVALID_LL_PARAMS 0x1e #define HCI_ERROR_UNSPECIFIED 0x1f #define HCI_ERROR_ADVERTISING_TIMEOUT 0x3c @@ -694,6 +724,7 @@ enum { #define HCI_RSSI_INVALID 127 #define HCI_SYNC_HANDLE_INVALID 0xffff +#define HCI_SID_INVALID 0xff #define HCI_ROLE_MASTER 0x00 #define HCI_ROLE_SLAVE 0x01 @@ -850,6 +881,11 @@ struct hci_cp_remote_name_req_cancel { bdaddr_t bdaddr; } __packed; +struct hci_rp_remote_name_req_cancel { + __u8 status; + bdaddr_t bdaddr; +} __packed; + #define HCI_OP_READ_REMOTE_FEATURES 0x041b struct hci_cp_read_remote_features { __le16 handle; @@ -944,56 +980,6 @@ struct hci_cp_io_capability_neg_reply { __u8 reason; } __packed; -#define HCI_OP_CREATE_PHY_LINK 0x0435 -struct hci_cp_create_phy_link { - __u8 phy_handle; - __u8 key_len; - __u8 key_type; - __u8 key[HCI_AMP_LINK_KEY_SIZE]; -} __packed; - -#define HCI_OP_ACCEPT_PHY_LINK 0x0436 -struct hci_cp_accept_phy_link { - __u8 phy_handle; - __u8 key_len; - __u8 key_type; - __u8 key[HCI_AMP_LINK_KEY_SIZE]; -} __packed; - -#define HCI_OP_DISCONN_PHY_LINK 0x0437 -struct hci_cp_disconn_phy_link { - __u8 phy_handle; - __u8 reason; -} __packed; - -struct ext_flow_spec { - __u8 id; - __u8 stype; - __le16 msdu; - __le32 sdu_itime; - __le32 acc_lat; - __le32 flush_to; -} __packed; - -#define HCI_OP_CREATE_LOGICAL_LINK 0x0438 -#define HCI_OP_ACCEPT_LOGICAL_LINK 0x0439 -struct hci_cp_create_accept_logical_link { - __u8 phy_handle; - struct ext_flow_spec tx_flow_spec; - struct ext_flow_spec rx_flow_spec; -} __packed; - -#define HCI_OP_DISCONN_LOGICAL_LINK 0x043a -struct hci_cp_disconn_logical_link { - __le16 log_handle; -} __packed; - -#define HCI_OP_LOGICAL_LINK_CANCEL 0x043b -struct hci_cp_logical_link_cancel { - __u8 phy_handle; - __u8 flow_spec_id; -} __packed; - #define HCI_OP_ENHANCED_SETUP_SYNC_CONN 0x043d struct hci_coding_format { __u8 id; @@ -1573,6 +1559,11 @@ struct hci_rp_read_tx_power { __s8 tx_power; } __packed; +#define HCI_OP_WRITE_SYNC_FLOWCTL 0x0c2f +struct hci_cp_write_sync_flowctl { + __u8 enable; +} __packed; + #define HCI_OP_READ_PAGE_SCAN_TYPE 0x0c46 struct hci_rp_read_page_scan_type { __u8 status; @@ -1615,46 +1606,6 @@ struct hci_rp_read_enc_key_size { __u8 key_size; } __packed; -#define HCI_OP_READ_LOCAL_AMP_INFO 0x1409 -struct hci_rp_read_local_amp_info { - __u8 status; - __u8 amp_status; - __le32 total_bw; - __le32 max_bw; - __le32 min_latency; - __le32 max_pdu; - __u8 amp_type; - __le16 pal_cap; - __le16 max_assoc_size; - __le32 max_flush_to; - __le32 be_flush_to; -} __packed; - -#define HCI_OP_READ_LOCAL_AMP_ASSOC 0x140a -struct hci_cp_read_local_amp_assoc { - __u8 phy_handle; - __le16 len_so_far; - __le16 max_len; -} __packed; -struct hci_rp_read_local_amp_assoc { - __u8 status; - __u8 phy_handle; - __le16 rem_len; - __u8 frag[]; -} __packed; - -#define HCI_OP_WRITE_REMOTE_AMP_ASSOC 0x140b -struct hci_cp_write_remote_amp_assoc { - __u8 phy_handle; - __le16 len_so_far; - __le16 rem_len; - __u8 frag[]; -} __packed; -struct hci_rp_write_remote_amp_assoc { - __u8 status; - __u8 phy_handle; -} __packed; - #define HCI_OP_GET_MWS_TRANSPORT_CONFIG 0x140c #define HCI_OP_ENABLE_DUT_MODE 0x1803 @@ -1666,6 +1617,15 @@ struct hci_cp_le_set_event_mask { __u8 mask[8]; } __packed; +/* BLUETOOTH CORE SPECIFICATION Version 5.4 | Vol 4, Part E + * 7.8.2 LE Read Buffer Size command + * MAX_LE_MTU is 0xffff. + * 0 is also valid. It means that no dedicated LE Buffer exists. + * It should use the HCI_Read_Buffer_Size command and mtu is shared + * between BR/EDR and LE. + */ +#define HCI_MIN_LE_MTU 0x001b + #define HCI_OP_LE_READ_BUFFER_SIZE 0x2002 struct hci_rp_le_read_buffer_size { __u8 status; @@ -1973,6 +1933,8 @@ struct hci_cp_le_pa_create_sync { __u8 sync_cte_type; } __packed; +#define HCI_OP_LE_PA_CREATE_SYNC_CANCEL 0x2045 + #define HCI_OP_LE_PA_TERM_SYNC 0x2046 struct hci_cp_le_pa_term_sync { __le16 handle; @@ -2026,7 +1988,7 @@ struct hci_cp_le_set_ext_adv_data { __u8 operation; __u8 frag_pref; __u8 length; - __u8 data[]; + __u8 data[] __counted_by(length); } __packed; #define HCI_OP_LE_SET_EXT_SCAN_RSP_DATA 0x2038 @@ -2035,7 +1997,7 @@ struct hci_cp_le_set_ext_scan_rsp_data { __u8 operation; __u8 frag_pref; __u8 length; - __u8 data[]; + __u8 data[] __counted_by(length); } __packed; #define HCI_OP_LE_SET_EXT_ADV_ENABLE 0x2039 @@ -2061,7 +2023,7 @@ struct hci_cp_le_set_per_adv_data { __u8 handle; __u8 operation; __u8 length; - __u8 data[]; + __u8 data[] __counted_by(length); } __packed; #define HCI_OP_LE_SET_PER_ADV_ENABLE 0x2040 @@ -2144,7 +2106,7 @@ struct hci_cp_le_set_cig_params { __le16 c_latency; __le16 p_latency; __u8 num_cis; - struct hci_cis_params cis[]; + struct hci_cis_params cis[] __counted_by(num_cis); } __packed; struct hci_rp_le_set_cig_params { @@ -2162,7 +2124,7 @@ struct hci_cis { struct hci_cp_le_create_cis { __u8 num_cis; - struct hci_cis cis[]; + struct hci_cis cis[] __counted_by(num_cis); } __packed; #define HCI_OP_LE_REMOVE_CIG 0x2065 @@ -2216,7 +2178,7 @@ struct hci_cp_le_big_create_sync { __u8 mse; __le16 timeout; __u8 num_bis; - __u8 bis[]; + __u8 bis[] __counted_by(num_bis); } __packed; #define HCI_OP_LE_BIG_TERM_SYNC 0x206c @@ -2872,7 +2834,7 @@ struct hci_evt_le_create_big_complete { __le16 bis_handle[]; } __packed; -#define HCI_EVT_LE_BIG_SYNC_ESTABILISHED 0x1d +#define HCI_EVT_LE_BIG_SYNC_ESTABLISHED 0x1d struct hci_evt_le_big_sync_estabilished { __u8 status; __u8 handle; @@ -2993,6 +2955,11 @@ static inline struct hci_sco_hdr *hci_sco_hdr(const struct sk_buff *skb) return (struct hci_sco_hdr *) skb->data; } +static inline struct hci_iso_hdr *hci_iso_hdr(const struct sk_buff *skb) +{ + return (struct hci_iso_hdr *)skb->data; +} + /* Command opcode pack/unpack */ #define hci_opcode_pack(ogf, ocf) ((__u16) ((ocf & 0x03ff)|(ogf << 10))) #define hci_opcode_ogf(op) (op >> 10) diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index e8f581f3f3ce..2b261e74e2c4 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -31,6 +31,7 @@ #include <linux/rculist.h> #include <net/bluetooth/hci.h> +#include <net/bluetooth/hci_drv.h> #include <net/bluetooth/hci_sync.h> #include <net/bluetooth/hci_sock.h> #include <net/bluetooth/coredump.h> @@ -91,8 +92,6 @@ struct discovery_state { s8 rssi; u16 uuid_count; u8 (*uuids)[16]; - unsigned long scan_start; - unsigned long scan_duration; unsigned long name_resolve_timeout; }; @@ -126,7 +125,6 @@ enum suspended_state { struct hci_conn_hash { struct list_head list; unsigned int acl_num; - unsigned int amp_num; unsigned int sco_num; unsigned int iso_num; unsigned int le_num; @@ -160,8 +158,9 @@ struct bdaddr_list_with_irk { /* Bitmask of connection flags */ enum hci_conn_flags { - HCI_CONN_FLAG_REMOTE_WAKEUP = 1, - HCI_CONN_FLAG_DEVICE_PRIVACY = 2, + HCI_CONN_FLAG_REMOTE_WAKEUP = BIT(0), + HCI_CONN_FLAG_DEVICE_PRIVACY = BIT(1), + HCI_CONN_FLAG_ADDRESS_RESOLUTION = BIT(2), }; typedef u8 hci_conn_flags_t; @@ -189,7 +188,6 @@ struct blocked_key { struct smp_csrk { bdaddr_t bdaddr; u8 bdaddr_type; - u8 link_type; u8 type; u8 val[16]; }; @@ -199,7 +197,6 @@ struct smp_ltk { struct rcu_head rcu; bdaddr_t bdaddr; u8 bdaddr_type; - u8 link_type; u8 authenticated; u8 type; u8 enc_size; @@ -214,7 +211,6 @@ struct smp_irk { bdaddr_t rpa; bdaddr_t bdaddr; u8 addr_type; - u8 link_type; u8 val[16]; }; @@ -222,8 +218,6 @@ struct link_key { struct list_head list; struct rcu_head rcu; bdaddr_t bdaddr; - u8 bdaddr_type; - u8 link_type; u8 type; u8 val[HCI_LINK_KEY_SIZE]; u8 pin_len; @@ -247,6 +241,7 @@ struct adv_info { bool periodic; __u8 mesh; __u8 instance; + __u8 handle; __u32 flags; __u16 timeout; __u16 remaining_time; @@ -267,6 +262,12 @@ struct adv_info { struct delayed_work rpa_expired_cb; }; +struct tx_queue { + struct sk_buff_head queue; + unsigned int extra; + unsigned int tracked; +}; + #define HCI_MAX_ADV_INSTANCES 5 #define HCI_DEFAULT_ADV_DURATION 2 @@ -341,14 +342,6 @@ struct adv_monitor { /* Default authenticated payload timeout 30s */ #define DEFAULT_AUTH_PAYLOAD_TIMEOUT 0x0bb8 -struct amp_assoc { - __u16 len; - __u16 offset; - __u16 rem_len; - __u16 len_so_far; - __u8 data[HCI_MAX_AMP_ASSOC_SIZE]; -}; - #define HCI_MAX_PAGES 3 struct hci_dev { @@ -361,7 +354,6 @@ struct hci_dev { unsigned long flags; __u16 id; __u8 bus; - __u8 dev_type; bdaddr_t bdaddr; bdaddr_t setup_addr; bdaddr_t public_addr; @@ -467,21 +459,6 @@ struct hci_dev { __u16 sniff_min_interval; __u16 sniff_max_interval; - __u8 amp_status; - __u32 amp_total_bw; - __u32 amp_max_bw; - __u32 amp_min_latency; - __u32 amp_max_pdu; - __u8 amp_type; - __u16 amp_pal_cap; - __u16 amp_assoc_size; - __u32 amp_max_flush_to; - __u32 amp_be_flush_to; - - struct amp_assoc loc_assoc; - - __u8 flow_ctl_mode; - unsigned int auto_accept_delay; unsigned long quirks; @@ -501,13 +478,7 @@ struct hci_dev { unsigned int le_pkts; unsigned int iso_pkts; - __u16 block_len; - __u16 block_mtu; - __u16 num_blocks; - __u16 block_cnt; - unsigned long acl_last_tx; - unsigned long sco_last_tx; unsigned long le_last_tx; __u8 le_tx_def_phys; @@ -559,7 +530,6 @@ struct hci_dev { struct discovery_state discovery; - int discovery_old_state; bool discovery_paused; int advertising_old_state; bool advertising_paused; @@ -644,6 +614,8 @@ struct hci_dev { struct list_head monitored_devices; bool advmon_pend_notify; + struct hci_drv *hci_drv; + #if IS_ENABLED(CONFIG_BT_LEDS) struct led_trigger *power_led; #endif @@ -670,7 +642,6 @@ struct hci_dev { int (*post_init)(struct hci_dev *hdev); int (*set_diag)(struct hci_dev *hdev, bool enable); int (*set_bdaddr)(struct hci_dev *hdev, const bdaddr_t *bdaddr); - void (*cmd_timeout)(struct hci_dev *hdev); void (*reset)(struct hci_dev *hdev); bool (*wakeup)(struct hci_dev *hdev); int (*set_quality_report)(struct hci_dev *hdev, bool enable); @@ -678,6 +649,7 @@ struct hci_dev { int (*get_codec_config_data)(struct hci_dev *hdev, __u8 type, struct bt_codec *codec, __u8 *vnd_len, __u8 **vnd_data); + u8 (*classify_pkt_type)(struct hci_dev *hdev, struct sk_buff *skb); }; #define HCI_PHY_HANDLE(handle) (handle & 0xff) @@ -705,7 +677,9 @@ struct hci_conn { __u8 adv_instance; __u16 handle; __u16 sync_handle; + __u8 sid; __u16 state; + __u16 mtu; __u8 mode; __u8 type; __u8 role; @@ -746,6 +720,9 @@ struct hci_conn { __s8 tx_power; __s8 max_tx_power; struct bt_iso_qos iso_qos; + __u8 num_bis; + __u8 bis[HCI_MAX_ISO_BIS]; + unsigned long flags; enum conn_reasons conn_reason; @@ -765,6 +742,8 @@ struct hci_conn { struct sk_buff_head data_q; struct list_head chan_list; + struct tx_queue tx_q; + struct delayed_work disc_work; struct delayed_work auto_accept_work; struct delayed_work idle_work; @@ -777,7 +756,6 @@ struct hci_conn { void *l2cap_data; void *sco_data; void *iso_data; - struct amp_mgr *amp_mgr; struct list_head link_list; struct hci_conn *parent; @@ -804,7 +782,6 @@ struct hci_chan { struct sk_buff_head data_q; unsigned int sent; __u8 state; - bool amp; }; struct hci_conn_params { @@ -858,7 +835,7 @@ extern struct mutex hci_cb_list_lock; } while (0) #define hci_dev_le_state_simultaneous(hdev) \ - (test_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks) && \ + (!test_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks) && \ (hdev->le_states[4] & 0x08) && /* Central */ \ (hdev->le_states[4] & 0x40) && /* Peripheral */ \ (hdev->le_states[3] & 0x10)) /* Simultaneous */ @@ -920,8 +897,6 @@ static inline void hci_discovery_filter_clear(struct hci_dev *hdev) hdev->discovery.uuid_count = 0; kfree(hdev->discovery.uuids); hdev->discovery.uuids = NULL; - hdev->discovery.scan_start = 0; - hdev->discovery.scan_duration = 0; } bool hci_discovery_active(struct hci_dev *hdev); @@ -985,8 +960,10 @@ enum { HCI_CONN_PER_ADV, HCI_CONN_BIG_CREATED, HCI_CONN_CREATE_CIS, + HCI_CONN_CREATE_BIG_SYNC, HCI_CONN_BIG_SYNC, HCI_CONN_BIG_SYNC_FAILED, + HCI_CONN_CREATE_PA_SYNC, HCI_CONN_PA_SYNC, HCI_CONN_PA_SYNC_FAILED, }; @@ -1013,9 +990,6 @@ static inline void hci_conn_hash_add(struct hci_dev *hdev, struct hci_conn *c) case ACL_LINK: h->acl_num++; break; - case AMP_LINK: - h->amp_num++; - break; case LE_LINK: h->le_num++; if (c->role == HCI_ROLE_SLAVE) @@ -1025,7 +999,8 @@ static inline void hci_conn_hash_add(struct hci_dev *hdev, struct hci_conn *c) case ESCO_LINK: h->sco_num++; break; - case ISO_LINK: + case CIS_LINK: + case BIS_LINK: h->iso_num++; break; } @@ -1042,9 +1017,6 @@ static inline void hci_conn_hash_del(struct hci_dev *hdev, struct hci_conn *c) case ACL_LINK: h->acl_num--; break; - case AMP_LINK: - h->amp_num--; - break; case LE_LINK: h->le_num--; if (c->role == HCI_ROLE_SLAVE) @@ -1054,7 +1026,8 @@ static inline void hci_conn_hash_del(struct hci_dev *hdev, struct hci_conn *c) case ESCO_LINK: h->sco_num--; break; - case ISO_LINK: + case CIS_LINK: + case BIS_LINK: h->iso_num--; break; } @@ -1066,14 +1039,13 @@ static inline unsigned int hci_conn_num(struct hci_dev *hdev, __u8 type) switch (type) { case ACL_LINK: return h->acl_num; - case AMP_LINK: - return h->amp_num; case LE_LINK: return h->le_num; case SCO_LINK: case ESCO_LINK: return h->sco_num; - case ISO_LINK: + case CIS_LINK: + case BIS_LINK: return h->iso_num; default: return 0; @@ -1084,7 +1056,7 @@ static inline unsigned int hci_conn_count(struct hci_dev *hdev) { struct hci_conn_hash *c = &hdev->conn_hash; - return c->acl_num + c->amp_num + c->sco_num + c->le_num + c->iso_num; + return c->acl_num + c->sco_num + c->le_num + c->iso_num; } static inline bool hci_conn_valid(struct hci_dev *hdev, struct hci_conn *conn) @@ -1134,7 +1106,7 @@ static inline struct hci_conn *hci_conn_hash_lookup_bis(struct hci_dev *hdev, rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { - if (bacmp(&c->dst, ba) || c->type != ISO_LINK) + if (bacmp(&c->dst, ba) || c->type != BIS_LINK) continue; if (c->iso_qos.bcast.bis == bis) { @@ -1148,6 +1120,30 @@ static inline struct hci_conn *hci_conn_hash_lookup_bis(struct hci_dev *hdev, } static inline struct hci_conn * +hci_conn_hash_lookup_create_pa_sync(struct hci_dev *hdev) +{ + struct hci_conn_hash *h = &hdev->conn_hash; + struct hci_conn *c; + + rcu_read_lock(); + + list_for_each_entry_rcu(c, &h->list, list) { + if (c->type != BIS_LINK) + continue; + + if (!test_bit(HCI_CONN_CREATE_PA_SYNC, &c->flags)) + continue; + + rcu_read_unlock(); + return c; + } + + rcu_read_unlock(); + + return NULL; +} + +static inline struct hci_conn * hci_conn_hash_lookup_per_adv_bis(struct hci_dev *hdev, bdaddr_t *ba, __u8 big, __u8 bis) @@ -1158,8 +1154,8 @@ hci_conn_hash_lookup_per_adv_bis(struct hci_dev *hdev, rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { - if (bacmp(&c->dst, ba) || c->type != ISO_LINK || - !test_bit(HCI_CONN_PER_ADV, &c->flags)) + if (bacmp(&c->dst, ba) || c->type != BIS_LINK || + !test_bit(HCI_CONN_PER_ADV, &c->flags)) continue; if (c->iso_qos.bcast.big == big && @@ -1248,7 +1244,7 @@ static inline struct hci_conn *hci_conn_hash_lookup_cis(struct hci_dev *hdev, rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { - if (c->type != ISO_LINK || !bacmp(&c->dst, BDADDR_ANY)) + if (c->type != CIS_LINK) continue; /* Match CIG ID if set */ @@ -1280,7 +1276,7 @@ static inline struct hci_conn *hci_conn_hash_lookup_cig(struct hci_dev *hdev, rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { - if (c->type != ISO_LINK || !bacmp(&c->dst, BDADDR_ANY)) + if (c->type != CIS_LINK) continue; if (handle == c->iso_qos.ucast.cig) { @@ -1303,7 +1299,7 @@ static inline struct hci_conn *hci_conn_hash_lookup_big(struct hci_dev *hdev, rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { - if (bacmp(&c->dst, BDADDR_ANY) || c->type != ISO_LINK) + if (c->type != BIS_LINK) continue; if (handle == c->iso_qos.bcast.big) { @@ -1318,6 +1314,30 @@ static inline struct hci_conn *hci_conn_hash_lookup_big(struct hci_dev *hdev, } static inline struct hci_conn * +hci_conn_hash_lookup_big_sync_pend(struct hci_dev *hdev, + __u8 handle, __u8 num_bis) +{ + struct hci_conn_hash *h = &hdev->conn_hash; + struct hci_conn *c; + + rcu_read_lock(); + + list_for_each_entry_rcu(c, &h->list, list) { + if (c->type != BIS_LINK) + continue; + + if (handle == c->iso_qos.bcast.big && num_bis == c->num_bis) { + rcu_read_unlock(); + return c; + } + } + + rcu_read_unlock(); + + return NULL; +} + +static inline struct hci_conn * hci_conn_hash_lookup_big_state(struct hci_dev *hdev, __u8 handle, __u16 state) { struct hci_conn_hash *h = &hdev->conn_hash; @@ -1326,8 +1346,8 @@ hci_conn_hash_lookup_big_state(struct hci_dev *hdev, __u8 handle, __u16 state) rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { - if (bacmp(&c->dst, BDADDR_ANY) || c->type != ISO_LINK || - c->state != state) + if (c->type != BIS_LINK || bacmp(&c->dst, BDADDR_ANY) || + c->state != state) continue; if (handle == c->iso_qos.bcast.big) { @@ -1350,8 +1370,8 @@ hci_conn_hash_lookup_pa_sync_big_handle(struct hci_dev *hdev, __u8 big) rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { - if (c->type != ISO_LINK || - !test_bit(HCI_CONN_PA_SYNC, &c->flags)) + if (c->type != BIS_LINK || + !test_bit(HCI_CONN_PA_SYNC, &c->flags)) continue; if (c->iso_qos.bcast.big == big) { @@ -1373,8 +1393,14 @@ hci_conn_hash_lookup_pa_sync_handle(struct hci_dev *hdev, __u16 sync_handle) rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { - if (c->type != ISO_LINK || - !test_bit(HCI_CONN_PA_SYNC, &c->flags)) + if (c->type != BIS_LINK) + continue; + + /* Ignore the listen hcon, we are looking + * for the child hcon that was created as + * a result of the PA sync established event. + */ + if (c->state == BT_LISTEN) continue; if (c->sync_handle == sync_handle) { @@ -1534,9 +1560,9 @@ struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst, __u8 data_len, __u8 *data); struct hci_conn *hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, __u8 sid, struct bt_iso_qos *qos); -int hci_le_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon, - struct bt_iso_qos *qos, - __u16 sync_handle, __u8 num_bis, __u8 bis[]); +int hci_conn_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon, + struct bt_iso_qos *qos, __u16 sync_handle, + __u8 num_bis, __u8 bis[]); int hci_conn_check_link_mode(struct hci_conn *conn); int hci_conn_check_secure(struct hci_conn *conn, __u8 sec_level); int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type, @@ -1548,6 +1574,18 @@ void hci_conn_enter_active_mode(struct hci_conn *conn, __u8 force_active); void hci_conn_failed(struct hci_conn *conn, u8 status); u8 hci_conn_set_handle(struct hci_conn *conn, u16 handle); +void hci_conn_tx_queue(struct hci_conn *conn, struct sk_buff *skb); +void hci_conn_tx_dequeue(struct hci_conn *conn); +void hci_setup_tx_timestamp(struct sk_buff *skb, size_t key_offset, + const struct sockcm_cookie *sockc); + +static inline void hci_sockcm_init(struct sockcm_cookie *sockc, struct sock *sk) +{ + *sockc = (struct sockcm_cookie) { + .tsflags = READ_ONCE(sk->sk_tsflags), + }; +} + /* * hci_conn_get() and hci_conn_put() are used to control the life-time of an * "hci_conn" object. They do not guarantee that the hci_conn object is running, @@ -1610,10 +1648,6 @@ static inline void hci_conn_drop(struct hci_conn *conn) } break; - case AMP_LINK: - timeo = conn->disc_timeout; - break; - default: timeo = 0; break; @@ -1740,8 +1774,6 @@ int hci_bdaddr_list_add_with_flags(struct list_head *list, bdaddr_t *bdaddr, int hci_bdaddr_list_del(struct list_head *list, bdaddr_t *bdaddr, u8 type); int hci_bdaddr_list_del_with_irk(struct list_head *list, bdaddr_t *bdaddr, u8 type); -int hci_bdaddr_list_del_with_flags(struct list_head *list, bdaddr_t *bdaddr, - u8 type); void hci_bdaddr_list_clear(struct list_head *list); struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev, @@ -1762,6 +1794,7 @@ struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list, void hci_uuids_clear(struct hci_dev *hdev); void hci_link_keys_clear(struct hci_dev *hdev); +u8 *hci_conn_key_enc_size(struct hci_conn *conn); struct link_key *hci_find_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr); struct link_key *hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, bdaddr_t *bdaddr, u8 *val, u8 type, @@ -1840,6 +1873,7 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define lmp_hold_capable(dev) ((dev)->features[0][0] & LMP_HOLD) #define lmp_sniff_capable(dev) ((dev)->features[0][0] & LMP_SNIFF) #define lmp_park_capable(dev) ((dev)->features[0][1] & LMP_PARK) +#define lmp_sco_capable(dev) ((dev)->features[0][1] & LMP_SCO) #define lmp_inq_rssi_capable(dev) ((dev)->features[0][3] & LMP_RSSI_INQ) #define lmp_esco_capable(dev) ((dev)->features[0][3] & LMP_ESCO) #define lmp_bredr_capable(dev) (!((dev)->features[0][4] & LMP_NO_BREDR)) @@ -1900,17 +1934,17 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define ll_privacy_capable(dev) ((dev)->le_features[0] & HCI_LE_LL_PRIVACY) -/* Use LL Privacy based address resolution if supported */ -#define use_ll_privacy(dev) (ll_privacy_capable(dev) && \ - hci_dev_test_flag(dev, HCI_ENABLE_LL_PRIVACY)) - -#define privacy_mode_capable(dev) (use_ll_privacy(dev) && \ +#define privacy_mode_capable(dev) (ll_privacy_capable(dev) && \ (hdev->commands[39] & 0x04)) #define read_key_size_capable(dev) \ ((dev)->commands[20] & 0x10 && \ !test_bit(HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE, &hdev->quirks)) +#define read_voice_setting_capable(dev) \ + ((dev)->commands[9] & 0x04 && \ + !test_bit(HCI_QUIRK_BROKEN_READ_VOICE_SETTING, &(dev)->quirks)) + /* Use enhanced synchronous connection if command is supported and its quirk * has not been set. */ @@ -1924,8 +1958,8 @@ void hci_conn_del_sysfs(struct hci_conn *conn); !test_bit(HCI_QUIRK_BROKEN_EXT_SCAN, &(dev)->quirks)) /* Use ext create connection if command is supported */ -#define use_ext_conn(dev) ((dev)->commands[37] & 0x80) - +#define use_ext_conn(dev) (((dev)->commands[37] & 0x80) && \ + !test_bit(HCI_QUIRK_BROKEN_EXT_CREATE_CONN, &(dev)->quirks)) /* Extended advertising support */ #define ext_adv_capable(dev) (((dev)->le_features[1] & HCI_LE_EXT_ADV)) @@ -1938,8 +1972,10 @@ void hci_conn_del_sysfs(struct hci_conn *conn); * C24: Mandatory if the LE Controller supports Connection State and either * LE Feature (LL Privacy) or LE Feature (Extended Advertising) is supported */ -#define use_enhanced_conn_complete(dev) (ll_privacy_capable(dev) || \ - ext_adv_capable(dev)) +#define use_enhanced_conn_complete(dev) ((ll_privacy_capable(dev) || \ + ext_adv_capable(dev)) && \ + !test_bit(HCI_QUIRK_BROKEN_EXT_CREATE_CONN, \ + &(dev)->quirks)) /* Periodic advertising support */ #define per_adv_capable(dev) (((dev)->le_features[1] & HCI_LE_PERIODIC_ADV)) @@ -1972,7 +2008,8 @@ static inline int hci_proto_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, case ESCO_LINK: return sco_connect_ind(hdev, bdaddr, flags); - case ISO_LINK: + case CIS_LINK: + case BIS_LINK: return iso_connect_ind(hdev, bdaddr, flags); default: @@ -2156,18 +2193,46 @@ static inline int hci_check_conn_params(u16 min, u16 max, u16 latency, { u16 max_latency; - if (min > max || min < 6 || max > 3200) + if (min > max) { + BT_WARN("min %d > max %d", min, max); + return -EINVAL; + } + + if (min < 6) { + BT_WARN("min %d < 6", min); + return -EINVAL; + } + + if (max > 3200) { + BT_WARN("max %d > 3200", max); return -EINVAL; + } - if (to_multiplier < 10 || to_multiplier > 3200) + if (to_multiplier < 10) { + BT_WARN("to_multiplier %d < 10", to_multiplier); return -EINVAL; + } + + if (to_multiplier > 3200) { + BT_WARN("to_multiplier %d > 3200", to_multiplier); + return -EINVAL; + } - if (max >= to_multiplier * 8) + if (max >= to_multiplier * 8) { + BT_WARN("max %d >= to_multiplier %d * 8", max, to_multiplier); return -EINVAL; + } max_latency = (to_multiplier * 4 / max) - 1; - if (latency > 499 || latency > max_latency) + if (latency > 499) { + BT_WARN("latency %d > 499", latency); return -EINVAL; + } + + if (latency > max_latency) { + BT_WARN("latency %d > max_latency %d", latency, max_latency); + return -EINVAL; + } return 0; } @@ -2235,8 +2300,22 @@ void hci_mgmt_chan_unregister(struct hci_mgmt_chan *c); /* These LE scan and inquiry parameters were chosen according to LE General * Discovery Procedure specification. */ -#define DISCOV_LE_SCAN_WIN 0x12 -#define DISCOV_LE_SCAN_INT 0x12 +#define DISCOV_LE_SCAN_WIN 0x0012 /* 11.25 msec */ +#define DISCOV_LE_SCAN_INT 0x0012 /* 11.25 msec */ +#define DISCOV_LE_SCAN_INT_FAST 0x0060 /* 60 msec */ +#define DISCOV_LE_SCAN_WIN_FAST 0x0030 /* 30 msec */ +#define DISCOV_LE_SCAN_INT_CONN 0x0060 /* 60 msec */ +#define DISCOV_LE_SCAN_WIN_CONN 0x0060 /* 60 msec */ +#define DISCOV_LE_SCAN_INT_SLOW1 0x0800 /* 1.28 sec */ +#define DISCOV_LE_SCAN_WIN_SLOW1 0x0012 /* 11.25 msec */ +#define DISCOV_LE_SCAN_INT_SLOW2 0x1000 /* 2.56 sec */ +#define DISCOV_LE_SCAN_WIN_SLOW2 0x0024 /* 22.5 msec */ +#define DISCOV_CODED_SCAN_INT_FAST 0x0120 /* 180 msec */ +#define DISCOV_CODED_SCAN_WIN_FAST 0x0090 /* 90 msec */ +#define DISCOV_CODED_SCAN_INT_SLOW1 0x1800 /* 3.84 sec */ +#define DISCOV_CODED_SCAN_WIN_SLOW1 0x0036 /* 33.75 msec */ +#define DISCOV_CODED_SCAN_INT_SLOW2 0x3000 /* 7.68 sec */ +#define DISCOV_CODED_SCAN_WIN_SLOW2 0x006c /* 67.5 msec */ #define DISCOV_LE_TIMEOUT 10240 /* msec */ #define DISCOV_INTERLEAVED_TIMEOUT 5120 /* msec */ #define DISCOV_INTERLEAVED_INQUIRY_LEN 0x04 @@ -2268,8 +2347,8 @@ void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr, bool mgmt_connected); void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 status); -void mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, - u8 addr_type, u8 status); +void mgmt_connect_failed(struct hci_dev *hdev, struct hci_conn *conn, + u8 status); void mgmt_pin_code_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 secure); void mgmt_pin_code_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 status); @@ -2296,8 +2375,6 @@ void mgmt_auth_enable_complete(struct hci_dev *hdev, 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_start_discovery_complete(struct hci_dev *hdev, u8 status); -void mgmt_stop_discovery_complete(struct hci_dev *hdev, u8 status); void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 *dev_class, s8 rssi, u32 flags, u8 *eir, u16 eir_len, u8 *scan_rsp, u8 scan_rsp_len, diff --git a/include/net/bluetooth/hci_drv.h b/include/net/bluetooth/hci_drv.h new file mode 100644 index 000000000000..2f01c44f05ec --- /dev/null +++ b/include/net/bluetooth/hci_drv.h @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2025 Google Corporation + */ + +#ifndef __HCI_DRV_H +#define __HCI_DRV_H + +#include <linux/types.h> + +#include <net/bluetooth/bluetooth.h> +#include <net/bluetooth/hci.h> + +struct hci_drv_cmd_hdr { + __le16 opcode; + __le16 len; +} __packed; + +struct hci_drv_ev_hdr { + __le16 opcode; + __le16 len; +} __packed; + +#define HCI_DRV_EV_CMD_STATUS 0x0000 +struct hci_drv_ev_cmd_status { + __le16 opcode; + __u8 status; +} __packed; + +#define HCI_DRV_EV_CMD_COMPLETE 0x0001 +struct hci_drv_ev_cmd_complete { + __le16 opcode; + __u8 status; + __u8 data[]; +} __packed; + +#define HCI_DRV_STATUS_SUCCESS 0x00 +#define HCI_DRV_STATUS_UNSPECIFIED_ERROR 0x01 +#define HCI_DRV_STATUS_UNKNOWN_COMMAND 0x02 +#define HCI_DRV_STATUS_INVALID_PARAMETERS 0x03 + +#define HCI_DRV_MAX_DRIVER_NAME_LENGTH 32 + +/* Common commands that make sense on all drivers start from 0x0000 */ +#define HCI_DRV_OP_READ_INFO 0x0000 +#define HCI_DRV_READ_INFO_SIZE 0 +struct hci_drv_rp_read_info { + __u8 driver_name[HCI_DRV_MAX_DRIVER_NAME_LENGTH]; + __le16 num_supported_commands; + __le16 supported_commands[]; +} __packed; + +/* Driver specific OGF (Opcode Group Field) + * Commands in this group may have different meanings across different drivers. + */ +#define HCI_DRV_OGF_DRIVER_SPECIFIC 0x01 + +int hci_drv_cmd_status(struct hci_dev *hdev, u16 cmd, u8 status); +int hci_drv_cmd_complete(struct hci_dev *hdev, u16 cmd, u8 status, void *rp, + size_t rp_len); +int hci_drv_process_cmd(struct hci_dev *hdev, struct sk_buff *cmd_skb); + +struct hci_drv_handler { + int (*func)(struct hci_dev *hdev, void *data, u16 data_len); + size_t data_len; +}; + +struct hci_drv { + size_t common_handler_count; + const struct hci_drv_handler *common_handlers; + + size_t specific_handler_count; + const struct hci_drv_handler *specific_handlers; +}; + +#endif /* __HCI_DRV_H */ diff --git a/include/net/bluetooth/hci_mon.h b/include/net/bluetooth/hci_mon.h index 082f89531b88..bbd752494ef9 100644 --- a/include/net/bluetooth/hci_mon.h +++ b/include/net/bluetooth/hci_mon.h @@ -51,6 +51,8 @@ struct hci_mon_hdr { #define HCI_MON_CTRL_EVENT 17 #define HCI_MON_ISO_TX_PKT 18 #define HCI_MON_ISO_RX_PKT 19 +#define HCI_MON_DRV_TX_PKT 20 +#define HCI_MON_DRV_RX_PKT 21 struct hci_mon_new_index { __u8 type; diff --git a/include/net/bluetooth/hci_sock.h b/include/net/bluetooth/hci_sock.h index 9949870f7d78..13e8cd4414a1 100644 --- a/include/net/bluetooth/hci_sock.h +++ b/include/net/bluetooth/hci_sock.h @@ -144,7 +144,7 @@ struct hci_dev_req { struct hci_dev_list_req { __u16 dev_num; - struct hci_dev_req dev_req[]; /* hci_dev_req structures */ + struct hci_dev_req dev_req[] __counted_by(dev_num); }; struct hci_conn_list_req { diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h index 6a9d063e9f47..72558c826aa1 100644 --- a/include/net/bluetooth/hci_sync.h +++ b/include/net/bluetooth/hci_sync.h @@ -8,6 +8,23 @@ #define UINT_PTR(_handle) ((void *)((uintptr_t)_handle)) #define PTR_UINT(_ptr) ((uintptr_t)((void *)_ptr)) +#define HCI_REQ_DONE 0 +#define HCI_REQ_PEND 1 +#define HCI_REQ_CANCELED 2 + +#define hci_req_sync_lock(hdev) mutex_lock(&hdev->req_lock) +#define hci_req_sync_unlock(hdev) mutex_unlock(&hdev->req_lock) + +struct hci_request { + struct hci_dev *hdev; + struct sk_buff_head cmd_q; + + /* If something goes wrong when building the HCI request, the error + * value is stored in this field. + */ + int err; +}; + typedef int (*hci_cmd_sync_work_func_t)(struct hci_dev *hdev, void *data); typedef void (*hci_cmd_sync_work_destroy_t)(struct hci_dev *hdev, void *data, int err); @@ -20,6 +37,10 @@ struct hci_cmd_sync_work_entry { }; struct adv_info; + +struct sk_buff *hci_cmd_sync_alloc(struct hci_dev *hdev, u16 opcode, u32 plen, + const void *param, struct sock *sk); + /* Function with sync suffix shall not be called with hdev->lock held as they * wait the command to complete and in the meantime an event could be received * which could attempt to acquire hdev->lock causing a deadlock. @@ -38,6 +59,8 @@ int __hci_cmd_sync_status(struct hci_dev *hdev, u16 opcode, u32 plen, int __hci_cmd_sync_status_sk(struct hci_dev *hdev, u16 opcode, u32 plen, const void *param, u8 event, u32 timeout, struct sock *sk); +int hci_cmd_sync_status(struct hci_dev *hdev, u16 opcode, u32 plen, + const void *param, u32 timeout); void hci_cmd_sync_init(struct hci_dev *hdev); void hci_cmd_sync_clear(struct hci_dev *hdev); @@ -50,6 +73,10 @@ int hci_cmd_sync_queue(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, void *data, hci_cmd_sync_work_destroy_t destroy); int hci_cmd_sync_queue_once(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, void *data, hci_cmd_sync_work_destroy_t destroy); +int hci_cmd_sync_run(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy); +int hci_cmd_sync_run_once(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy); struct hci_cmd_sync_work_entry * hci_cmd_sync_lookup_entry(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, void *data, hci_cmd_sync_work_destroy_t destroy); @@ -113,7 +140,6 @@ int hci_update_scan(struct hci_dev *hdev); int hci_write_le_host_supported_sync(struct hci_dev *hdev, u8 le, u8 simul); int hci_remove_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance, struct sock *sk); -int hci_remove_ext_adv_instance(struct hci_dev *hdev, u8 instance); struct sk_buff *hci_read_local_oob_data_sync(struct hci_dev *hdev, bool ext, struct sock *sk); @@ -129,6 +155,8 @@ int hci_update_discoverable(struct hci_dev *hdev); int hci_update_connectable_sync(struct hci_dev *hdev); +int hci_inquiry_sync(struct hci_dev *hdev, u8 length, u8 num_rsp); + int hci_start_discovery_sync(struct hci_dev *hdev); int hci_stop_discovery_sync(struct hci_dev *hdev); @@ -136,6 +164,7 @@ int hci_suspend_sync(struct hci_dev *hdev); int hci_resume_sync(struct hci_dev *hdev); struct hci_conn; +struct hci_conn_params; int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason); @@ -154,3 +183,8 @@ int hci_connect_acl_sync(struct hci_dev *hdev, struct hci_conn *conn); int hci_connect_le_sync(struct hci_dev *hdev, struct hci_conn *conn); int hci_cancel_connect_sync(struct hci_dev *hdev, struct hci_conn *conn); +int hci_le_conn_update_sync(struct hci_dev *hdev, struct hci_conn *conn, + struct hci_conn_params *params); + +int hci_connect_pa_sync(struct hci_dev *hdev, struct hci_conn *conn); +int hci_connect_big_sync(struct hci_dev *hdev, struct hci_conn *conn); diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index a4278aa618ab..4bb0eaedda18 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -27,7 +27,7 @@ #ifndef __L2CAP_H #define __L2CAP_H -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/atomic.h> /* L2CAP defaults */ @@ -38,8 +38,8 @@ #define L2CAP_DEFAULT_TX_WINDOW 63 #define L2CAP_DEFAULT_EXT_WINDOW 0x3FFF #define L2CAP_DEFAULT_MAX_TX 3 -#define L2CAP_DEFAULT_RETRANS_TO 2000 /* 2 seconds */ -#define L2CAP_DEFAULT_MONITOR_TO 12000 /* 12 seconds */ +#define L2CAP_DEFAULT_RETRANS_TO 2 /* seconds */ +#define L2CAP_DEFAULT_MONITOR_TO 12 /* seconds */ #define L2CAP_DEFAULT_MAX_PDU_SIZE 1492 /* Sized for AMP packet */ #define L2CAP_DEFAULT_ACK_TO 200 #define L2CAP_DEFAULT_MAX_SDU_SIZE 0xFFFF @@ -463,18 +463,24 @@ struct l2cap_le_credits { #define L2CAP_ECRED_MAX_CID 5 struct l2cap_ecred_conn_req { - __le16 psm; - __le16 mtu; - __le16 mps; - __le16 credits; + /* New members must be added within the struct_group() macro below. */ + __struct_group(l2cap_ecred_conn_req_hdr, hdr, __packed, + __le16 psm; + __le16 mtu; + __le16 mps; + __le16 credits; + ); __le16 scid[]; } __packed; struct l2cap_ecred_conn_rsp { - __le16 mtu; - __le16 mps; - __le16 credits; - __le16 result; + /* New members must be added within the struct_group() macro below. */ + struct_group_tagged(l2cap_ecred_conn_rsp_hdr, hdr, + __le16 mtu; + __le16 mps; + __le16 credits; + __le16 result; + ); __le16 dcid[]; }; @@ -548,6 +554,9 @@ struct l2cap_chan { __u16 tx_credits; __u16 rx_credits; + /* estimated available receive buffer space or -1 if unknown */ + ssize_t rx_avail; + __u8 tx_state; __u8 rx_state; @@ -659,7 +668,7 @@ struct l2cap_conn { struct l2cap_chan *smp; struct list_head chan_l; - struct mutex chan_lock; + struct mutex lock; struct kref ref; struct list_head users; }; @@ -682,10 +691,15 @@ struct l2cap_user { /* ----- L2CAP socket info ----- */ #define l2cap_pi(sk) ((struct l2cap_pinfo *) sk) +struct l2cap_rx_busy { + struct list_head list; + struct sk_buff *skb; +}; + struct l2cap_pinfo { struct bt_sock bt; struct l2cap_chan *chan; - struct sk_buff *rx_busy_skb; + struct list_head rx_busy; }; enum { @@ -941,8 +955,10 @@ void l2cap_chan_close(struct l2cap_chan *chan, int reason); int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, bdaddr_t *dst, u8 dst_type, u16 timeout); int l2cap_chan_reconfigure(struct l2cap_chan *chan, __u16 mtu); -int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len); +int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len, + const struct sockcm_cookie *sockc); void l2cap_chan_busy(struct l2cap_chan *chan, int busy); +void l2cap_chan_rx_avail(struct l2cap_chan *chan, ssize_t rx_avail); int l2cap_chan_check_security(struct l2cap_chan *chan, bool initiator); void l2cap_chan_set_defaults(struct l2cap_chan *chan); int l2cap_ertm_init(struct l2cap_chan *chan); @@ -953,12 +969,9 @@ void l2cap_chan_list(struct l2cap_conn *conn, l2cap_chan_func_t func, void *data); void l2cap_chan_del(struct l2cap_chan *chan, int err); void l2cap_send_conn_req(struct l2cap_chan *chan); -void l2cap_move_start(struct l2cap_chan *chan); -void l2cap_logical_cfm(struct l2cap_chan *chan, struct hci_chan *hchan, - u8 status); -void __l2cap_physical_cfm(struct l2cap_chan *chan, int result); struct l2cap_conn *l2cap_conn_get(struct l2cap_conn *conn); +struct l2cap_conn *l2cap_conn_hold_unless_zero(struct l2cap_conn *conn); void l2cap_conn_put(struct l2cap_conn *conn); int l2cap_register_user(struct l2cap_conn *conn, struct l2cap_user *user); diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index d382679efd2b..3575cd16049a 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -113,6 +113,7 @@ struct mgmt_rp_read_index_list { #define MGMT_SETTING_CIS_PERIPHERAL BIT(19) #define MGMT_SETTING_ISO_BROADCASTER BIT(20) #define MGMT_SETTING_ISO_SYNC_RECEIVER BIT(21) +#define MGMT_SETTING_LL_PRIVACY BIT(22) #define MGMT_OP_READ_INFO 0x0004 #define MGMT_READ_INFO_SIZE 0 @@ -878,6 +879,16 @@ struct mgmt_cp_mesh_send_cancel { } __packed; #define MGMT_MESH_SEND_CANCEL_SIZE 1 +#define MGMT_OP_HCI_CMD_SYNC 0x005B +struct mgmt_cp_hci_cmd_sync { + __le16 opcode; + __u8 event; + __u8 timeout; + __le16 params_len; + __u8 params[]; +} __packed; +#define MGMT_HCI_CMD_SYNC_SIZE 6 + #define MGMT_EV_CMD_COMPLETE 0x0001 struct mgmt_ev_cmd_complete { __le16 opcode; diff --git a/include/net/bluetooth/rfcomm.h b/include/net/bluetooth/rfcomm.h index 99d26879b02a..c05882476900 100644 --- a/include/net/bluetooth/rfcomm.h +++ b/include/net/bluetooth/rfcomm.h @@ -355,7 +355,7 @@ struct rfcomm_dev_info { struct rfcomm_dev_list_req { u16 dev_num; - struct rfcomm_dev_info dev_info[]; + struct rfcomm_dev_info dev_info[] __counted_by(dev_num); }; int rfcomm_dev_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index 9ce5ac2bfbad..2053cd8e788a 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -231,7 +231,10 @@ typedef struct port { mux_states_t sm_mux_state; /* state machine mux state */ 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_tx_timer_counter; /* state machine tx timer counter + * (always 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; diff --git a/include/net/bond_alb.h b/include/net/bond_alb.h index 9dc082b2d543..e5945427f38d 100644 --- a/include/net/bond_alb.h +++ b/include/net/bond_alb.h @@ -53,7 +53,7 @@ struct slave; struct tlb_client_info { - struct slave *tx_slave; /* A pointer to slave used for transmiting + struct slave *tx_slave; /* A pointer to slave used for transmitting * packets to a Client that the Hash function * gave this entry index. */ diff --git a/include/net/bond_options.h b/include/net/bond_options.h index 473a0147769e..18687ccf0638 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -161,5 +161,7 @@ void bond_option_arp_ip_targets_clear(struct bonding *bond); #if IS_ENABLED(CONFIG_IPV6) void bond_option_ns_ip6_targets_clear(struct bonding *bond); #endif +void bond_slave_ns_maddrs_add(struct bonding *bond, struct slave *slave); +void bond_slave_ns_maddrs_del(struct bonding *bond, struct slave *slave); #endif /* _NET_BOND_OPTIONS_H */ diff --git a/include/net/bonding.h b/include/net/bonding.h index b61fb1aa3a56..95f67b308c19 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -260,7 +260,7 @@ struct bonding { #ifdef CONFIG_XFRM_OFFLOAD struct list_head ipsec_list; /* protecting ipsec_list */ - spinlock_t ipsec_lock; + struct mutex ipsec_lock; #endif /* CONFIG_XFRM_OFFLOAD */ struct bpf_prog *xdp_prog; }; @@ -695,6 +695,7 @@ void bond_debug_register(struct bonding *bond); void bond_debug_unregister(struct bonding *bond); void bond_debug_reregister(struct bonding *bond); const char *bond_mode_name(int mode); +bool bond_xdp_check(struct bonding *bond, int mode); void bond_setup(struct net_device *bond_dev); unsigned int bond_get_num_tx_queues(void); int bond_netlink_init(void); diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 9b09acac538e..6e172d0f6ef5 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -24,6 +24,11 @@ */ #define MIN_NAPI_ID ((unsigned int)(NR_CPUS + 1)) +static inline bool napi_id_valid(unsigned int napi_id) +{ + return napi_id >= MIN_NAPI_ID; +} + #define BUSY_POLL_BUDGET 8 #ifdef CONFIG_NET_RX_BUSY_POLL @@ -52,6 +57,9 @@ void napi_busy_loop_rcu(unsigned int napi_id, bool (*loop_end)(void *, unsigned long), void *loop_end_arg, bool prefer_busy_poll, u16 budget); +void napi_suspend_irqs(unsigned int napi_id); +void napi_resume_irqs(unsigned int napi_id); + #else /* CONFIG_NET_RX_BUSY_POLL */ static inline unsigned long net_busy_loop_on(void) { @@ -68,7 +76,7 @@ static inline bool sk_can_busy_loop(struct sock *sk) static inline unsigned long busy_loop_current_time(void) { #ifdef CONFIG_NET_RX_BUSY_POLL - return (unsigned long)(local_clock() >> 10); + return (unsigned long)(ktime_get_ns() >> 10); #else return 0; #endif @@ -111,7 +119,7 @@ static inline void sk_busy_loop(struct sock *sk, int nonblock) #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int napi_id = READ_ONCE(sk->sk_napi_id); - if (napi_id >= MIN_NAPI_ID) + if (napi_id_valid(napi_id)) napi_busy_loop(napi_id, nonblock ? NULL : sk_busy_loop_end, sk, READ_ONCE(sk->sk_prefer_busy_poll), READ_ONCE(sk->sk_busy_poll_budget) ?: BUSY_POLL_BUDGET); @@ -119,19 +127,25 @@ static inline void sk_busy_loop(struct sock *sk, int nonblock) } /* used in the NIC receive handler to mark the skb */ -static inline void skb_mark_napi_id(struct sk_buff *skb, - struct napi_struct *napi) +static inline void __skb_mark_napi_id(struct sk_buff *skb, + const struct gro_node *gro) { #ifdef CONFIG_NET_RX_BUSY_POLL /* If the skb was already marked with a valid NAPI ID, avoid overwriting * it. */ - if (skb->napi_id < MIN_NAPI_ID) - skb->napi_id = napi->napi_id; + if (!napi_id_valid(skb->napi_id)) + skb->napi_id = gro->cached_napi_id; #endif } -/* used in the protocol hanlder to propagate the napi_id to the socket */ +static inline void skb_mark_napi_id(struct sk_buff *skb, + const struct napi_struct *napi) +{ + __skb_mark_napi_id(skb, &napi->gro); +} + +/* used in the protocol handler to propagate the napi_id to the socket */ static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL @@ -171,12 +185,4 @@ static inline void sk_mark_napi_id_once(struct sock *sk, #endif } -static inline void sk_mark_napi_id_once_xdp(struct sock *sk, - const struct xdp_buff *xdp) -{ -#ifdef CONFIG_NET_RX_BUSY_POLL - __sk_mark_napi_id_once(sk, xdp->rxq->napi_id); -#endif -} - #endif /* _LINUX_NET_BUSY_POLL_H */ diff --git a/include/net/caif/caif_layer.h b/include/net/caif/caif_layer.h index 51f7bb42a936..053e7c6a6a66 100644 --- a/include/net/caif/caif_layer.h +++ b/include/net/caif/caif_layer.h @@ -11,9 +11,7 @@ struct cflayer; struct cfpkt; -struct cfpktq; struct caif_payload_info; -struct caif_packet_funcs; #define CAIF_LAYER_NAME_SZ 16 @@ -22,7 +20,7 @@ struct caif_packet_funcs; * @assert: expression to evaluate. * * This function will print a error message and a do WARN_ON if the - * assertion failes. Normally this will do a stack up at the current location. + * assertion fails. Normally this will do a stack up at the current location. */ #define caif_assert(assert) \ do { \ @@ -118,7 +116,7 @@ enum caif_direction { * @dn: Pointer down to the layer below. * @node: List node used when layer participate in a list. * @receive: Packet receive function. - * @transmit: Packet transmit funciton. + * @transmit: Packet transmit function. * @ctrlcmd: Used for control signalling upwards in the stack. * @modemcmd: Used for control signaling downwards in the stack. * @id: The identity of this layer diff --git a/include/net/caif/cfpkt.h b/include/net/caif/cfpkt.h index 44d914a50369..acf664227d96 100644 --- a/include/net/caif/cfpkt.h +++ b/include/net/caif/cfpkt.h @@ -18,7 +18,7 @@ struct cfpkt *cfpkt_create(u16 len); /* * Destroy a CAIF Packet. - * pkt Packet to be destoyed. + * pkt Packet to be destroyed. */ void cfpkt_destroy(struct cfpkt *pkt); diff --git a/include/net/caif/cfsrvl.h b/include/net/caif/cfsrvl.h index 5ee7b322e18b..a000dc45f966 100644 --- a/include/net/caif/cfsrvl.h +++ b/include/net/caif/cfsrvl.h @@ -40,7 +40,6 @@ void cfsrvl_init(struct cfsrvl *service, struct dev_info *dev_info, bool supports_flowctrl); bool cfsrvl_ready(struct cfsrvl *service, int *err); -u8 cfsrvl_getphyid(struct cflayer *layer); static inline void cfsrvl_get(struct cflayer *layr) { diff --git a/include/net/calipso.h b/include/net/calipso.h index f8667a3fda9e..76b9e08c10c2 100644 --- a/include/net/calipso.h +++ b/include/net/calipso.h @@ -25,7 +25,7 @@ #include <net/netlabel.h> #include <net/request_sock.h> #include <linux/refcount.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* known doi values */ #define CALIPSO_DOI_UNKNOWN 0x00000000 diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 1e09329acc42..d1848dc8ec99 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -7,7 +7,7 @@ * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2024 Intel Corporation + * Copyright (C) 2018-2025 Intel Corporation */ #include <linux/ethtool.h> @@ -125,33 +125,39 @@ struct wiphy; * @IEEE80211_CHAN_CAN_MONITOR: This channel can be used for monitor * mode even in the presence of other (regulatory) restrictions, * even if it is otherwise disabled. + * @IEEE80211_CHAN_ALLOW_6GHZ_VLP_AP: Allow using this channel for AP operation + * with very low power (VLP), even if otherwise set to NO_IR. + * @IEEE80211_CHAN_ALLOW_20MHZ_ACTIVITY: Allow activity on a 20 MHz channel, + * even if otherwise set to NO_IR. */ enum ieee80211_channel_flags { - IEEE80211_CHAN_DISABLED = 1<<0, - IEEE80211_CHAN_NO_IR = 1<<1, - IEEE80211_CHAN_PSD = 1<<2, - IEEE80211_CHAN_RADAR = 1<<3, - IEEE80211_CHAN_NO_HT40PLUS = 1<<4, - IEEE80211_CHAN_NO_HT40MINUS = 1<<5, - IEEE80211_CHAN_NO_OFDM = 1<<6, - IEEE80211_CHAN_NO_80MHZ = 1<<7, - IEEE80211_CHAN_NO_160MHZ = 1<<8, - IEEE80211_CHAN_INDOOR_ONLY = 1<<9, - IEEE80211_CHAN_IR_CONCURRENT = 1<<10, - IEEE80211_CHAN_NO_20MHZ = 1<<11, - IEEE80211_CHAN_NO_10MHZ = 1<<12, - IEEE80211_CHAN_NO_HE = 1<<13, - IEEE80211_CHAN_1MHZ = 1<<14, - IEEE80211_CHAN_2MHZ = 1<<15, - IEEE80211_CHAN_4MHZ = 1<<16, - IEEE80211_CHAN_8MHZ = 1<<17, - IEEE80211_CHAN_16MHZ = 1<<18, - IEEE80211_CHAN_NO_320MHZ = 1<<19, - IEEE80211_CHAN_NO_EHT = 1<<20, - IEEE80211_CHAN_DFS_CONCURRENT = 1<<21, - IEEE80211_CHAN_NO_6GHZ_VLP_CLIENT = 1<<22, - IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT = 1<<23, - IEEE80211_CHAN_CAN_MONITOR = 1<<24, + IEEE80211_CHAN_DISABLED = BIT(0), + IEEE80211_CHAN_NO_IR = BIT(1), + IEEE80211_CHAN_PSD = BIT(2), + IEEE80211_CHAN_RADAR = BIT(3), + IEEE80211_CHAN_NO_HT40PLUS = BIT(4), + IEEE80211_CHAN_NO_HT40MINUS = BIT(5), + IEEE80211_CHAN_NO_OFDM = BIT(6), + IEEE80211_CHAN_NO_80MHZ = BIT(7), + IEEE80211_CHAN_NO_160MHZ = BIT(8), + IEEE80211_CHAN_INDOOR_ONLY = BIT(9), + IEEE80211_CHAN_IR_CONCURRENT = BIT(10), + IEEE80211_CHAN_NO_20MHZ = BIT(11), + IEEE80211_CHAN_NO_10MHZ = BIT(12), + IEEE80211_CHAN_NO_HE = BIT(13), + IEEE80211_CHAN_1MHZ = BIT(14), + IEEE80211_CHAN_2MHZ = BIT(15), + IEEE80211_CHAN_4MHZ = BIT(16), + IEEE80211_CHAN_8MHZ = BIT(17), + IEEE80211_CHAN_16MHZ = BIT(18), + IEEE80211_CHAN_NO_320MHZ = BIT(19), + IEEE80211_CHAN_NO_EHT = BIT(20), + IEEE80211_CHAN_DFS_CONCURRENT = BIT(21), + IEEE80211_CHAN_NO_6GHZ_VLP_CLIENT = BIT(22), + IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT = BIT(23), + IEEE80211_CHAN_CAN_MONITOR = BIT(24), + IEEE80211_CHAN_ALLOW_6GHZ_VLP_AP = BIT(25), + IEEE80211_CHAN_ALLOW_20MHZ_ACTIVITY = BIT(26), }; #define IEEE80211_CHAN_NO_HT40 \ @@ -229,13 +235,13 @@ struct ieee80211_channel { * @IEEE80211_RATE_SUPPORTS_10MHZ: Rate can be used in 10 MHz mode */ enum ieee80211_rate_flags { - IEEE80211_RATE_SHORT_PREAMBLE = 1<<0, - IEEE80211_RATE_MANDATORY_A = 1<<1, - IEEE80211_RATE_MANDATORY_B = 1<<2, - IEEE80211_RATE_MANDATORY_G = 1<<3, - IEEE80211_RATE_ERP_G = 1<<4, - IEEE80211_RATE_SUPPORTS_5MHZ = 1<<5, - IEEE80211_RATE_SUPPORTS_10MHZ = 1<<6, + IEEE80211_RATE_SHORT_PREAMBLE = BIT(0), + IEEE80211_RATE_MANDATORY_A = BIT(1), + IEEE80211_RATE_MANDATORY_B = BIT(2), + IEEE80211_RATE_MANDATORY_G = BIT(3), + IEEE80211_RATE_ERP_G = BIT(4), + IEEE80211_RATE_SUPPORTS_5MHZ = BIT(5), + IEEE80211_RATE_SUPPORTS_10MHZ = BIT(6), }; /** @@ -1003,6 +1009,17 @@ cfg80211_chandef_compatible(const struct cfg80211_chan_def *chandef1, int nl80211_chan_width_to_mhz(enum nl80211_chan_width chan_width); /** + * cfg80211_chandef_get_width - return chandef width in MHz + * @c: chandef to return bandwidth for + * Return: channel width in MHz for the given chandef; note that it returns + * 80 for 80+80 configurations + */ +static inline int cfg80211_chandef_get_width(const struct cfg80211_chan_def *c) +{ + return nl80211_chan_width_to_mhz(c->width); +} + +/** * cfg80211_chandef_valid - check if a channel definition is valid * @chandef: the channel definition to check * Return: %true if the channel definition is valid. %false otherwise. @@ -1080,43 +1097,6 @@ int cfg80211_chandef_primary(const struct cfg80211_chan_def *chandef, int nl80211_send_chandef(struct sk_buff *msg, const struct cfg80211_chan_def *chandef); /** - * ieee80211_chanwidth_rate_flags - return rate flags for channel width - * @width: the channel width of the channel - * - * In some channel types, not all rates may be used - for example CCK - * rates may not be used in 5/10 MHz channels. - * - * Returns: rate flags which apply for this channel width - */ -static inline enum ieee80211_rate_flags -ieee80211_chanwidth_rate_flags(enum nl80211_chan_width width) -{ - switch (width) { - case NL80211_CHAN_WIDTH_5: - return IEEE80211_RATE_SUPPORTS_5MHZ; - case NL80211_CHAN_WIDTH_10: - return IEEE80211_RATE_SUPPORTS_10MHZ; - default: - break; - } - return 0; -} - -/** - * ieee80211_chandef_rate_flags - returns rate flags for a channel - * @chandef: channel definition for the channel - * - * See ieee80211_chanwidth_rate_flags(). - * - * Returns: rate flags which apply for this channel - */ -static inline enum ieee80211_rate_flags -ieee80211_chandef_rate_flags(struct cfg80211_chan_def *chandef) -{ - return ieee80211_chanwidth_rate_flags(chandef->width); -} - -/** * ieee80211_chandef_max_power - maximum transmission power for the chandef * * In some regulations, the transmit power may depend on the configured channel @@ -1149,6 +1129,8 @@ ieee80211_chandef_max_power(struct cfg80211_chan_def *chandef) * @band_mask: which bands to check on * @prohibited_flags: which channels to not consider usable, * %IEEE80211_CHAN_DISABLED is always taken into account + * + * Return: %true if usable channels found, %false otherwise */ bool cfg80211_any_usable_channels(struct wiphy *wiphy, unsigned long band_mask, @@ -1281,11 +1263,13 @@ struct cfg80211_crypto_settings { * struct cfg80211_mbssid_config - AP settings for multi bssid * * @tx_wdev: pointer to the transmitted interface in the MBSSID set + * @tx_link_id: link ID of the transmitted profile in an MLD. * @index: index of this AP in the multi bssid group. * @ema: set to true if the beacons should be sent out in EMA mode. */ struct cfg80211_mbssid_config { struct wireless_dev *tx_wdev; + u8 tx_link_id; u8 index; bool ema; }; @@ -1455,7 +1439,6 @@ struct cfg80211_unsol_bcast_probe_resp { * @crypto: crypto settings * @privacy: the BSS uses privacy * @auth_type: Authentication type (algorithm) - * @smps_mode: SMPS mode * @inactivity_timeout: time in seconds to determine station's inactivity. * @p2p_ctwindow: P2P CT Window * @p2p_opp_ps: P2P opportunistic PS @@ -1493,7 +1476,6 @@ struct cfg80211_ap_settings { struct cfg80211_crypto_settings crypto; bool privacy; enum nl80211_auth_type auth_type; - enum nl80211_smps_mode smps_mode; int inactivity_timeout; u8 p2p_ctwindow; bool p2p_opp_ps; @@ -1575,6 +1557,8 @@ struct cfg80211_csa_settings { * @beacon_next: beacon data to be used after the color change * @count: number of beacons until the color change * @color: the color used after the change + * @link_id: defines the link on which color change is expected during MLO. + * 0 in case of non-MLO. */ struct cfg80211_color_change_settings { struct cfg80211_beacon_data beacon_color_change; @@ -1583,6 +1567,7 @@ struct cfg80211_color_change_settings { struct cfg80211_beacon_data beacon_next; u8 count; u8 color; + u8 link_id; }; /** @@ -1590,6 +1575,7 @@ struct cfg80211_color_change_settings { * * Used to pass interface combination parameters * + * @radio_idx: wiphy radio index or -1 for global * @num_different_channels: the number of different channels we want * to use for verification * @radar_detect: a bitmap where each bit corresponds to a channel @@ -1603,6 +1589,7 @@ struct cfg80211_color_change_settings { * the verification */ struct iface_combination_params { + int radio_idx; int num_different_channels; u8 radar_detect; int iftype_num[NUM_NL80211_IFTYPES]; @@ -1748,6 +1735,9 @@ struct cfg80211_ttlm_params { * @supported_oper_classes_len: number of supported operating classes * @support_p2p_ps: information if station supports P2P PS mechanism * @airtime_weight: airtime scheduler weight for this station + * @eml_cap_present: Specifies if EML capabilities field (@eml_cap) is + * present/updated + * @eml_cap: EML capabilities of this station * @link_sta_params: link related params. */ struct station_parameters { @@ -1772,6 +1762,8 @@ struct station_parameters { u8 supported_oper_classes_len; int support_p2p_ps; u16 airtime_weight; + bool eml_cap_present; + u16 eml_cap; struct link_station_parameters link_sta_params; }; @@ -1833,9 +1825,11 @@ enum cfg80211_station_type { * * Utility function for the @change_station driver method. Call this function * with the appropriate station type looking up the station (and checking that - * it exists). It will verify whether the station change is acceptable, and if - * not will return an error code. Note that it may modify the parameters for - * backward compatibility reasons, so don't use them before calling this. + * it exists). It will verify whether the station change is acceptable. + * + * Return: 0 if the change is acceptable, otherwise an error code. Note that + * it may modify the parameters for backward compatibility reasons, so don't + * use them before calling this. */ int cfg80211_check_station_change(struct wiphy *wiphy, struct station_parameters *params, @@ -1950,9 +1944,9 @@ struct rate_info { * @BSS_PARAM_FLAGS_SHORT_SLOT_TIME: whether short slot time is enabled */ enum bss_param_flags { - BSS_PARAM_FLAGS_CTS_PROT = 1<<0, - BSS_PARAM_FLAGS_SHORT_PREAMBLE = 1<<1, - BSS_PARAM_FLAGS_SHORT_SLOT_TIME = 1<<2, + BSS_PARAM_FLAGS_CTS_PROT = BIT(0), + BSS_PARAM_FLAGS_SHORT_PREAMBLE = BIT(1), + BSS_PARAM_FLAGS_SHORT_SLOT_TIME = BIT(2), }; /** @@ -2035,9 +2029,6 @@ struct cfg80211_tid_stats { * @assoc_at: bootime (ns) of the last association * @rx_bytes: bytes (size of MPDUs) received from this station * @tx_bytes: bytes (size of MPDUs) transmitted to this station - * @llid: mesh local link id - * @plid: mesh peer link id - * @plink_state: mesh peer link state * @signal: The signal strength, type depends on the wiphy's signal_type. * For CFG80211_SIGNAL_TYPE_MBM, value is expressed in _dBm_. * @signal_avg: Average signal strength, type depends on the wiphy's signal_type. @@ -2057,14 +2048,20 @@ struct cfg80211_tid_stats { * This number should increase every time the list of stations * changes, i.e. when a station is added or removed, so that * userspace can tell whether it got a consistent snapshot. + * @beacon_loss_count: Number of times beacon loss event has triggered. * @assoc_req_ies: IEs from (Re)Association Request. * This is used only when in AP mode with drivers that do not use * user space MLME/SME implementation. The information is provided for * the cfg80211_new_sta() calls to notify user space of the IEs. * @assoc_req_ies_len: Length of assoc_req_ies buffer in octets. * @sta_flags: station flags mask & values - * @beacon_loss_count: Number of times beacon loss event has triggered. * @t_offset: Time offset of the station relative to this host. + * @llid: mesh local link id + * @plid: mesh peer link id + * @plink_state: mesh peer link state + * @connected_to_gate: true if mesh STA has a path to mesh gate + * @connected_to_as: true if mesh STA has a path to authentication server + * @airtime_link_metric: mesh airtime link metric. * @local_pm: local mesh STA power save mode * @peer_pm: peer mesh STA power save mode * @nonpeer_pm: non-peer mesh STA power save mode @@ -2073,7 +2070,6 @@ struct cfg80211_tid_stats { * @rx_beacon: number of beacons received from this peer * @rx_beacon_signal_avg: signal strength average (in dBm) for beacons received * from this peer - * @connected_to_gate: true if mesh STA has a path to mesh gate * @rx_duration: aggregate PPDU duration(usecs) for all the frames from a peer * @tx_duration: aggregate PPDU duration(usecs) for all the frames to a peer * @airtime_weight: current airtime scheduling weight @@ -2087,8 +2083,6 @@ struct cfg80211_tid_stats { * @fcs_err_count: number of packets (MPDUs) received from this station with * an FCS error. This counter should be incremented only when TA of the * received packet with an FCS error matches the peer MAC address. - * @airtime_link_metric: mesh airtime link metric. - * @connected_to_as: true if mesh STA has a path to authentication server * @mlo_params_valid: Indicates @assoc_link_id and @mld_addr fields are filled * by driver. Drivers use this only in cfg80211_new_sta() calls when AP * MLD's MLME/SME is offload to driver. Drivers won't fill this @@ -2115,9 +2109,6 @@ struct station_info { u64 assoc_at; u64 rx_bytes; u64 tx_bytes; - u16 llid; - u16 plid; - u8 plink_state; s8 signal; s8 signal_avg; @@ -2137,36 +2128,38 @@ struct station_info { int generation; + u32 beacon_loss_count; + const u8 *assoc_req_ies; size_t assoc_req_ies_len; - u32 beacon_loss_count; s64 t_offset; + u16 llid; + u16 plid; + u8 plink_state; + u8 connected_to_gate; + u8 connected_to_as; + u32 airtime_link_metric; enum nl80211_mesh_power_mode local_pm; enum nl80211_mesh_power_mode peer_pm; enum nl80211_mesh_power_mode nonpeer_pm; u32 expected_throughput; - u64 tx_duration; - u64 rx_duration; - u64 rx_beacon; - u8 rx_beacon_signal_avg; - u8 connected_to_gate; + u16 airtime_weight; - struct cfg80211_tid_stats *pertid; s8 ack_signal; s8 avg_ack_signal; + struct cfg80211_tid_stats *pertid; - u16 airtime_weight; + u64 tx_duration; + u64 rx_duration; + u64 rx_beacon; + u8 rx_beacon_signal_avg; u32 rx_mpdu_count; u32 fcs_err_count; - u32 airtime_link_metric; - - u8 connected_to_as; - bool mlo_params_valid; u8 assoc_link_id; u8 mld_addr[ETH_ALEN] __aligned(2); @@ -2193,7 +2186,7 @@ struct cfg80211_sar_sub_specs { struct cfg80211_sar_specs { enum nl80211_sar_type type; u32 num_sub_specs; - struct cfg80211_sar_sub_specs sub_specs[]; + struct cfg80211_sar_sub_specs sub_specs[] __counted_by(num_sub_specs); }; @@ -2229,7 +2222,7 @@ struct cfg80211_sar_capa { * @mac_addr: the mac address of the station of interest * @sinfo: pointer to the structure to fill with the information * - * Returns 0 on success and sinfo is filled with the available information + * Return: 0 on success and sinfo is filled with the available information * otherwise returns a negative error code and the content of sinfo has to be * considered undefined. */ @@ -2255,17 +2248,19 @@ static inline int cfg80211_get_station(struct net_device *dev, * @MONITOR_FLAG_PLCPFAIL: pass frames with bad PLCP * @MONITOR_FLAG_CONTROL: pass control frames * @MONITOR_FLAG_OTHER_BSS: disable BSSID filtering - * @MONITOR_FLAG_COOK_FRAMES: report frames after processing + * @MONITOR_FLAG_COOK_FRAMES: deprecated, will unconditionally be refused * @MONITOR_FLAG_ACTIVE: active monitor, ACKs frames on its MAC address + * @MONITOR_FLAG_SKIP_TX: do not pass locally transmitted frames */ enum monitor_flags { - MONITOR_FLAG_CHANGED = 1<<__NL80211_MNTR_FLAG_INVALID, - MONITOR_FLAG_FCSFAIL = 1<<NL80211_MNTR_FLAG_FCSFAIL, - MONITOR_FLAG_PLCPFAIL = 1<<NL80211_MNTR_FLAG_PLCPFAIL, - MONITOR_FLAG_CONTROL = 1<<NL80211_MNTR_FLAG_CONTROL, - MONITOR_FLAG_OTHER_BSS = 1<<NL80211_MNTR_FLAG_OTHER_BSS, - MONITOR_FLAG_COOK_FRAMES = 1<<NL80211_MNTR_FLAG_COOK_FRAMES, - MONITOR_FLAG_ACTIVE = 1<<NL80211_MNTR_FLAG_ACTIVE, + MONITOR_FLAG_CHANGED = BIT(__NL80211_MNTR_FLAG_INVALID), + MONITOR_FLAG_FCSFAIL = BIT(NL80211_MNTR_FLAG_FCSFAIL), + MONITOR_FLAG_PLCPFAIL = BIT(NL80211_MNTR_FLAG_PLCPFAIL), + MONITOR_FLAG_CONTROL = BIT(NL80211_MNTR_FLAG_CONTROL), + MONITOR_FLAG_OTHER_BSS = BIT(NL80211_MNTR_FLAG_OTHER_BSS), + MONITOR_FLAG_COOK_FRAMES = BIT(NL80211_MNTR_FLAG_COOK_FRAMES), + MONITOR_FLAG_ACTIVE = BIT(NL80211_MNTR_FLAG_ACTIVE), + MONITOR_FLAG_SKIP_TX = BIT(NL80211_MNTR_FLAG_SKIP_TX), }; /** @@ -2831,7 +2826,7 @@ struct cfg80211_sched_scan_request { struct list_head list; /* keep last */ - struct ieee80211_channel *channels[]; + struct ieee80211_channel *channels[] __counted_by(n_channels); }; /** @@ -2935,6 +2930,7 @@ struct cfg80211_bss_ies { * @nontrans_list: list of non-transmitted BSS, if this is a transmitted one * (multi-BSSID support) * @signal: signal strength value (type depends on the wiphy's signal_type) + * @ts_boottime: timestamp of the last BSS update in nanoseconds since boot * @chains: bitmask for filled values in @chain_signal. * @chain_signal: per-chain signal strength of last received BSS in dBm. * @bssid_index: index in the multiple BSS set @@ -2959,6 +2955,8 @@ struct cfg80211_bss { s32 signal; + u64 ts_boottime; + u16 beacon_interval; u16 capability; @@ -3011,6 +3009,10 @@ static inline const u8 *ieee80211_bss_get_ie(struct cfg80211_bss *bss, u8 id) * * @bss: The BSS to authenticate with, the callee must obtain a reference * to it if it needs to keep it. + * @supported_selectors: List of selectors that should be assumed to be + * supported by the station. + * SAE_H2E must be assumed supported if set to %NULL. + * @supported_selectors_len: Length of supported_selectors in octets. * @auth_type: Authentication type (algorithm) * @ie: Extra IEs to add to Authentication frame or %NULL * @ie_len: Length of ie buffer in octets @@ -3033,6 +3035,8 @@ struct cfg80211_auth_request { struct cfg80211_bss *bss; const u8 *ie; size_t ie_len; + const u8 *supported_selectors; + u8 supported_selectors_len; enum nl80211_auth_type auth_type; const u8 *key; u8 key_len; @@ -3063,6 +3067,19 @@ struct cfg80211_assoc_link { }; /** + * struct cfg80211_ml_reconf_req - MLO link reconfiguration request + * @add_links: data for links to add, see &struct cfg80211_assoc_link + * @rem_links: bitmap of links to remove + * @ext_mld_capa_ops: extended MLD capabilities and operations set by + * userspace for the ML reconfiguration action frame + */ +struct cfg80211_ml_reconf_req { + struct cfg80211_assoc_link add_links[IEEE80211_MLD_MAX_NUM_LINKS]; + u16 rem_links; + u16 ext_mld_capa_ops; +}; + +/** * enum cfg80211_assoc_req_flags - Over-ride default behaviour in association. * * @ASSOC_REQ_DISABLE_HT: Disable HT (802.11n) @@ -3112,6 +3129,10 @@ enum cfg80211_assoc_req_flags { * included in the Current AP address field of the Reassociation Request * frame. * @flags: See &enum cfg80211_assoc_req_flags + * @supported_selectors: supported BSS selectors in IEEE 802.11 format + * (or %NULL for no change). + * If %NULL, then support for SAE_H2E should be assumed. + * @supported_selectors_len: number of supported BSS selectors * @ht_capa: HT Capabilities over-rides. Values set in ht_capa_mask * will be used in ht_capa. Un-supported values will be ignored. * @ht_capa_mask: The bits of ht_capa which are to be used. @@ -3130,6 +3151,8 @@ enum cfg80211_assoc_req_flags { * the link on which the association request should be sent * @ap_mld_addr: AP MLD address in case of MLO association request, * valid iff @link_id >= 0 + * @ext_mld_capa_ops: extended MLD capabilities and operations set by + * userspace for the association */ struct cfg80211_assoc_request { struct cfg80211_bss *bss; @@ -3138,6 +3161,8 @@ struct cfg80211_assoc_request { struct cfg80211_crypto_settings crypto; bool use_mfp; u32 flags; + const u8 *supported_selectors; + u8 supported_selectors_len; struct ieee80211_ht_cap ht_capa; struct ieee80211_ht_cap ht_capa_mask; struct ieee80211_vht_cap vht_capa, vht_capa_mask; @@ -3148,6 +3173,7 @@ struct cfg80211_assoc_request { struct cfg80211_assoc_link links[IEEE80211_MLD_MAX_NUM_LINKS]; const u8 *ap_mld_addr; s8 link_id; + u16 ext_mld_capa_ops; }; /** @@ -3392,15 +3418,15 @@ enum cfg80211_connect_params_changed { * @WIPHY_PARAM_TXQ_QUANTUM: TXQ scheduler quantum */ enum wiphy_params_flags { - WIPHY_PARAM_RETRY_SHORT = 1 << 0, - WIPHY_PARAM_RETRY_LONG = 1 << 1, - WIPHY_PARAM_FRAG_THRESHOLD = 1 << 2, - WIPHY_PARAM_RTS_THRESHOLD = 1 << 3, - WIPHY_PARAM_COVERAGE_CLASS = 1 << 4, - WIPHY_PARAM_DYN_ACK = 1 << 5, - WIPHY_PARAM_TXQ_LIMIT = 1 << 6, - WIPHY_PARAM_TXQ_MEMORY_LIMIT = 1 << 7, - WIPHY_PARAM_TXQ_QUANTUM = 1 << 8, + WIPHY_PARAM_RETRY_SHORT = BIT(0), + WIPHY_PARAM_RETRY_LONG = BIT(1), + WIPHY_PARAM_FRAG_THRESHOLD = BIT(2), + WIPHY_PARAM_RTS_THRESHOLD = BIT(3), + WIPHY_PARAM_COVERAGE_CLASS = BIT(4), + WIPHY_PARAM_DYN_ACK = BIT(5), + WIPHY_PARAM_TXQ_LIMIT = BIT(6), + WIPHY_PARAM_TXQ_MEMORY_LIMIT = BIT(7), + WIPHY_PARAM_TXQ_QUANTUM = BIT(8), }; #define IEEE80211_DEFAULT_AIRTIME_WEIGHT 256 @@ -3559,8 +3585,8 @@ struct cfg80211_coalesce_rules { * @n_rules: number of rules */ struct cfg80211_coalesce { - struct cfg80211_coalesce_rules *rules; int n_rules; + struct cfg80211_coalesce_rules rules[] __counted_by(n_rules); }; /** @@ -3575,7 +3601,7 @@ struct cfg80211_coalesce { struct cfg80211_wowlan_nd_match { struct cfg80211_ssid ssid; int n_channels; - u32 channels[]; + u32 channels[] __counted_by(n_channels); }; /** @@ -3589,7 +3615,7 @@ struct cfg80211_wowlan_nd_match { */ struct cfg80211_wowlan_nd_info { int n_matches; - struct cfg80211_wowlan_nd_match *matches[]; + struct cfg80211_wowlan_nd_match *matches[] __counted_by(n_matches); }; /** @@ -4570,6 +4596,18 @@ struct mgmt_frame_regs { * * @set_hw_timestamp: Enable/disable HW timestamping of TM/FTM frames. * @set_ttlm: set the TID to link mapping. + * @set_epcs: Enable/Disable EPCS for station mode. + * @get_radio_mask: get bitmask of radios in use. + * (invoked with the wiphy mutex held) + * @assoc_ml_reconf: Request a non-AP MLO connection to perform ML + * reconfiguration, i.e., add and/or remove links to/from the + * association using ML reconfiguration action frames. Successfully added + * links will be added to the set of valid links. Successfully removed + * links will be removed from the set of valid links. The driver must + * indicate removed links by calling cfg80211_links_removed() and added + * links by calling cfg80211_mlo_reconf_add_done(). When calling + * cfg80211_mlo_reconf_add_done() the bss pointer must be given for each + * link for which MLO reconfiguration 'add' operation was requested. */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -4682,6 +4720,7 @@ struct cfg80211_ops { struct ieee80211_channel *chan); int (*set_monitor_channel)(struct wiphy *wiphy, + struct net_device *dev, struct cfg80211_chan_def *chandef); int (*scan)(struct wiphy *wiphy, @@ -4718,7 +4757,7 @@ struct cfg80211_ops { int (*set_tx_power)(struct wiphy *wiphy, struct wireless_dev *wdev, enum nl80211_tx_power_setting type, int mbm); int (*get_tx_power)(struct wiphy *wiphy, struct wireless_dev *wdev, - int *dbm); + unsigned int link_id, int *dbm); void (*rfkill_poll)(struct wiphy *wiphy); @@ -4823,9 +4862,9 @@ struct cfg80211_ops { int (*start_radar_detection)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_chan_def *chandef, - u32 cac_time_ms); + u32 cac_time_ms, int link_id); void (*end_cac)(struct wiphy *wiphy, - struct net_device *dev); + struct net_device *dev, unsigned int link_id); int (*update_ft_ies)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_update_ft_ies_params *ftie); int (*crit_proto_start)(struct wiphy *wiphy, @@ -4931,6 +4970,11 @@ struct cfg80211_ops { struct cfg80211_set_hw_timestamp *hwts); int (*set_ttlm)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ttlm_params *params); + u32 (*get_radio_mask)(struct wiphy *wiphy, struct net_device *dev); + int (*assoc_ml_reconf)(struct wiphy *wiphy, struct net_device *dev, + struct cfg80211_ml_reconf_req *req); + int (*set_epcs)(struct wiphy *wiphy, struct net_device *dev, + bool val); }; /* @@ -5036,7 +5080,9 @@ struct ieee80211_iface_limit { * struct ieee80211_iface_combination - possible interface combination * * With this structure the driver can describe which interface - * combinations it supports concurrently. + * combinations it supports concurrently. When set in a struct wiphy_radio, + * the combinations refer to combinations of interfaces currently active on + * that radio. * * Examples: * @@ -5334,6 +5380,8 @@ struct wiphy_iftype_ext_capab { * cfg80211_get_iftype_ext_capa - lookup interface type extended capability * @wiphy: the wiphy to look up from * @type: the interface type to look up + * + * Return: The extended capability for the given interface @type, may be %NULL */ const struct wiphy_iftype_ext_capab * cfg80211_get_iftype_ext_capa(struct wiphy *wiphy, enum nl80211_iftype type); @@ -5394,6 +5442,42 @@ struct wiphy_iftype_akm_suites { int n_akm_suites; }; +/** + * struct wiphy_radio_freq_range - wiphy frequency range + * @start_freq: start range edge frequency (kHz) + * @end_freq: end range edge frequency (kHz) + */ +struct wiphy_radio_freq_range { + u32 start_freq; + u32 end_freq; +}; + + +/** + * struct wiphy_radio - physical radio of a wiphy + * This structure describes a physical radio belonging to a wiphy. + * It is used to describe concurrent-channel capabilities. Only one channel + * can be active on the radio described by struct wiphy_radio. + * + * @freq_range: frequency range that the radio can operate on. + * @n_freq_range: number of elements in @freq_range + * + * @iface_combinations: Valid interface combinations array, should not + * list single interface types. + * @n_iface_combinations: number of entries in @iface_combinations array. + * + * @antenna_mask: bitmask of antennas connected to this radio. + */ +struct wiphy_radio { + const struct wiphy_radio_freq_range *freq_range; + int n_freq_range; + + const struct ieee80211_iface_combination *iface_combinations; + int n_iface_combinations; + + u32 antenna_mask; +}; + #define CFG80211_HW_TIMESTAMP_ALL_PEERS 0xffff /** @@ -5612,6 +5696,9 @@ struct wiphy_iftype_akm_suites { * A value of %CFG80211_HW_TIMESTAMP_ALL_PEERS indicates the driver * supports enabling HW timestamping for all peers (i.e. no need to * specify a mac address). + * + * @radio: radios belonging to this wiphy + * @n_radio: number of radios */ struct wiphy { struct mutex mtx; @@ -5762,6 +5849,9 @@ struct wiphy { u16 hw_timestamp_max_peers; + int n_radio; + const struct wiphy_radio *radio; + char priv[] __aligned(NETDEV_ALIGN); }; @@ -5895,7 +5985,7 @@ int wiphy_register(struct wiphy *wiphy); * @wiphy: the wiphy to check the locking on * @p: The pointer to read, prior to dereferencing * - * Return the value of the specified RCU-protected pointer, but omit the + * Return: the value of the specified RCU-protected pointer, but omit the * READ_ONCE(), because caller holds the wiphy mutex used for updates. */ #define wiphy_dereference(wiphy, p) \ @@ -5904,6 +5994,10 @@ int wiphy_register(struct wiphy *wiphy); /** * get_wiphy_regdom - get custom regdomain for the given wiphy * @wiphy: the wiphy to get the regdomain from + * + * Context: Requires any of RTNL, wiphy mutex or RCU protection. + * + * Return: pointer to the regulatory domain associated with the wiphy */ const struct ieee80211_regdomain *get_wiphy_regdom(struct wiphy *wiphy); @@ -5965,6 +6059,10 @@ static inline void wiphy_unlock(struct wiphy *wiphy) mutex_unlock(&wiphy->mtx); } +DEFINE_GUARD(wiphy, struct wiphy *, + mutex_lock(&_T->mtx), + mutex_unlock(&_T->mtx)) + struct wiphy_work; typedef void (*wiphy_work_func_t)(struct wiphy *, struct wiphy_work *); @@ -6069,6 +6167,65 @@ void wiphy_delayed_work_flush(struct wiphy *wiphy, struct wiphy_delayed_work *dwork); /** + * wiphy_delayed_work_pending - Find out whether a wiphy delayable + * work item is currently pending. + * + * @wiphy: the wiphy, for debug purposes + * @dwork: the delayed work in question + * + * Return: true if timer is pending, false otherwise + * + * How wiphy_delayed_work_queue() works is by setting a timer which + * when it expires calls wiphy_work_queue() to queue the wiphy work. + * Because wiphy_delayed_work_queue() uses mod_timer(), if it is + * called twice and the second call happens before the first call + * deadline, the work will rescheduled for the second deadline and + * won't run before that. + * + * wiphy_delayed_work_pending() can be used to detect if calling + * wiphy_work_delayed_work_queue() would start a new work schedule + * or delayed a previous one. As seen below it cannot be used to + * detect precisely if the work has finished to execute nor if it + * is currently executing. + * + * CPU0 CPU1 + * wiphy_delayed_work_queue(wk) + * mod_timer(wk->timer) + * wiphy_delayed_work_pending(wk) -> true + * + * [...] + * expire_timers(wk->timer) + * detach_timer(wk->timer) + * wiphy_delayed_work_pending(wk) -> false + * wk->timer->function() | + * wiphy_work_queue(wk) | delayed work pending + * list_add_tail() | returns false but + * queue_work(cfg80211_wiphy_work) | wk->func() has not + * | been run yet + * [...] | + * cfg80211_wiphy_work() | + * wk->func() V + * + */ +bool wiphy_delayed_work_pending(struct wiphy *wiphy, + struct wiphy_delayed_work *dwork); + +/** + * enum ieee80211_ap_reg_power - regulatory power for an Access Point + * + * @IEEE80211_REG_UNSET_AP: Access Point has no regulatory power mode + * @IEEE80211_REG_LPI_AP: Indoor Access Point + * @IEEE80211_REG_SP_AP: Standard power Access Point + * @IEEE80211_REG_VLP_AP: Very low power Access Point + */ +enum ieee80211_ap_reg_power { + IEEE80211_REG_UNSET_AP, + IEEE80211_REG_LPI_AP, + IEEE80211_REG_SP_AP, + IEEE80211_REG_VLP_AP, +}; + +/** * struct wireless_dev - wireless device state * * For netdevs, this structure must be allocated by the driver @@ -6118,9 +6275,6 @@ void wiphy_delayed_work_flush(struct wiphy *wiphy, * @address: The address for this device, valid only if @netdev is %NULL * @is_running: true if this is a non-netdev device that has been started, e.g. * the P2P Device. - * @cac_started: true if DFS channel availability check has been started - * @cac_start_time: timestamp (jiffies) when the dfs state was entered. - * @cac_time_ms: CAC time in ms * @ps: powersave mode is enabled * @ps_timeout: dynamic powersave timeout * @ap_unexpected_nlportid: (private) netlink port ID of application @@ -6144,7 +6298,13 @@ void wiphy_delayed_work_flush(struct wiphy *wiphy, * unprotected beacon report * @links: array of %IEEE80211_MLD_MAX_NUM_LINKS elements containing @addr * @ap and @client for each link + * @links.cac_started: true if DFS channel availability check has been + * started + * @links.cac_start_time: timestamp (jiffies) when the dfs state was + * entered. + * @links.cac_time_ms: CAC time in ms * @valid_links: bitmap describing what elements of @links are valid + * @radio_mask: Bitmask of radios that this interface is allowed to operate on. */ struct wireless_dev { struct wiphy *wiphy; @@ -6185,11 +6345,6 @@ struct wireless_dev { u32 owner_nlportid; bool nl_owner_dead; - /* FIXME: need to rework radar detection for MLO */ - bool cac_started; - unsigned long cac_start_time; - unsigned int cac_time_ms; - #ifdef CONFIG_CFG80211_WEXT /* wext data */ struct { @@ -6256,8 +6411,14 @@ struct wireless_dev { struct cfg80211_internal_bss *current_bss; } client; }; + + bool cac_started; + unsigned long cac_start_time; + unsigned int cac_time_ms; } links[IEEE80211_MLD_MAX_NUM_LINKS]; u16 valid_links; + + u32 radio_mask; }; static inline const u8 *wdev_address(struct wireless_dev *wdev) @@ -6421,6 +6582,8 @@ ieee80211_get_channel(struct wiphy *wiphy, int freq) * * The Preferred Scanning Channels (PSC) are defined in * Draft IEEE P802.11ax/D5.0, 26.17.2.3.3 + * + * Return: %true if channel is a PSC, %false otherwise */ static inline bool cfg80211_channel_is_psc(struct ieee80211_channel *chan) { @@ -6431,6 +6594,28 @@ static inline bool cfg80211_channel_is_psc(struct ieee80211_channel *chan) } /** + * cfg80211_radio_chandef_valid - Check if the radio supports the chandef + * + * @radio: wiphy radio + * @chandef: chandef for current channel + * + * Return: whether or not the given chandef is valid for the given radio + */ +bool cfg80211_radio_chandef_valid(const struct wiphy_radio *radio, + const struct cfg80211_chan_def *chandef); + +/** + * cfg80211_wdev_channel_allowed - Check if the wdev may use the channel + * + * @wdev: the wireless device + * @chan: channel to check + * + * Return: whether or not the wdev may use the channel + */ +bool cfg80211_wdev_channel_allowed(struct wireless_dev *wdev, + struct ieee80211_channel *chan); + +/** * ieee80211_get_response_rate - get basic rate for a given rate * * @sband: the band to look for rates in @@ -6450,8 +6635,8 @@ ieee80211_get_response_rate(struct ieee80211_supported_band *sband, * ieee80211_mandatory_rates - get mandatory rates for a given band * @sband: the band to look for rates in * - * This function returns a bitmap of the mandatory rates for the given - * band, bits are set according to the rate position in the bitrates array. + * Return: a bitmap of the mandatory rates for the given band, bits + * are set according to the rate position in the bitrates array. */ u32 ieee80211_mandatory_rates(struct ieee80211_supported_band *sband); @@ -6665,6 +6850,8 @@ bool ieee80211_get_8023_tunnel_proto(const void *hdr, __be16 *proto); * header to the ethernet header (if present). * * @skb: The 802.3 frame with embedded mesh header + * + * Return: 0 on success. Non-zero on error. */ int ieee80211_strip_8023_mesh_hdr(struct sk_buff *skb); @@ -7043,6 +7230,8 @@ const struct ieee80211_reg_rule *freq_reg_info(struct wiphy *wiphy, * * You can use this to map the regulatory request initiator enum to a * proper string representation. + * + * Return: pointer to string representation of the initiator */ const char *reg_initiator_name(enum nl80211_reg_initiator initiator); @@ -7051,6 +7240,8 @@ const char *reg_initiator_name(enum nl80211_reg_initiator initiator); * @wiphy: wiphy for which pre-CAC capability is checked. * * Pre-CAC is allowed only in some regdomains (notable ETSI). + * + * Return: %true if allowed, %false otherwise */ bool regulatory_pre_cac_allowed(struct wiphy *wiphy); @@ -7185,6 +7376,8 @@ static inline void cfg80211_gen_new_bssid(const u8 *bssid, u8 max_bssid, * cfg80211_is_element_inherited - returns if element ID should be inherited * @element: element to check * @non_inherit_element: non inheritance element + * + * Return: %true if should be inherited, %false otherwise */ bool cfg80211_is_element_inherited(const struct element *element, const struct element *non_inherit_element); @@ -7197,6 +7390,8 @@ bool cfg80211_is_element_inherited(const struct element *element, * @sub_elem: current MBSSID subelement (profile) * @merged_ie: location of the merged profile * @max_copy_len: max merged profile length + * + * Return: the number of bytes merged */ size_t cfg80211_merge_profile(const u8 *ie, size_t ielen, const struct element *mbssid_elem, @@ -7224,7 +7419,7 @@ enum cfg80211_bss_frame_type { * @ielen: length of IEs * @band: enum nl80211_band of the channel * - * Returns the channel number, or -1 if none could be determined. + * Return: the channel number, or -1 if none could be determined. */ int cfg80211_get_ies_channel_number(const u8 *ie, size_t ielen, enum nl80211_band band); @@ -7302,6 +7497,8 @@ cfg80211_inform_bss(struct wiphy *wiphy, * @bss_type: type of BSS, see &enum ieee80211_bss_type * @privacy: privacy filter, see &enum ieee80211_privacy * @use_for: indicates which use is intended + * + * Return: Reference-counted BSS on success. %NULL on error. */ struct cfg80211_bss *__cfg80211_get_bss(struct wiphy *wiphy, struct ieee80211_channel *channel, @@ -7322,6 +7519,8 @@ struct cfg80211_bss *__cfg80211_get_bss(struct wiphy *wiphy, * @privacy: privacy filter, see &enum ieee80211_privacy * * This version implies regular usage, %NL80211_BSS_USE_FOR_NORMAL. + * + * Return: Reference-counted BSS on success. %NULL on error. */ static inline struct cfg80211_bss * cfg80211_get_bss(struct wiphy *wiphy, struct ieee80211_channel *channel, @@ -7706,8 +7905,9 @@ int cfg80211_vendor_cmd_reply(struct sk_buff *skb); * cfg80211_vendor_cmd_get_sender - get the current sender netlink ID * @wiphy: the wiphy * - * Return the current netlink port ID in a vendor command handler. - * Valid to call only there. + * Return: the current netlink port ID in a vendor command handler. + * + * Context: May only be called from a vendor command handler */ unsigned int cfg80211_vendor_cmd_get_sender(struct wiphy *wiphy); @@ -8260,6 +8460,8 @@ void cfg80211_tx_mgmt_expired(struct wireless_dev *wdev, u64 cookie, * * @sinfo: the station information * @gfp: allocation flags + * + * Return: 0 on success. Non-zero on error. */ int cfg80211_sinfo_alloc_tid_stats(struct station_info *sinfo, gfp_t gfp); @@ -8634,6 +8836,7 @@ void cfg80211_sta_opmode_change_notify(struct net_device *dev, const u8 *mac, * @chandef: chandef for the current channel * @event: type of event * @gfp: context flags + * @link_id: valid link_id for MLO operation or 0 otherwise. * * This function is called when a Channel availability check (CAC) is finished * or aborted. This must be called to notify the completion of a CAC process, @@ -8641,7 +8844,8 @@ void cfg80211_sta_opmode_change_notify(struct net_device *dev, const u8 *mac, */ void cfg80211_cac_event(struct net_device *netdev, const struct cfg80211_chan_def *chandef, - enum nl80211_radar_event event, gfp_t gfp); + enum nl80211_radar_event event, gfp_t gfp, + unsigned int link_id); /** * cfg80211_background_cac_abort - Channel Availability Check offchan abort event @@ -8754,6 +8958,34 @@ static inline void cfg80211_report_obss_beacon(struct wiphy *wiphy, } /** + * struct cfg80211_beaconing_check_config - beacon check configuration + * @iftype: the interface type to check for + * @relax: allow IR-relaxation conditions to apply (e.g. another + * interface connected already on the same channel) + * NOTE: If this is set, wiphy mutex must be held. + * @reg_power: &enum ieee80211_ap_reg_power value indicating the + * advertised/used 6 GHz regulatory power setting + */ +struct cfg80211_beaconing_check_config { + enum nl80211_iftype iftype; + enum ieee80211_ap_reg_power reg_power; + bool relax; +}; + +/** + * cfg80211_reg_check_beaconing - check if beaconing is allowed + * @wiphy: the wiphy + * @chandef: the channel definition + * @cfg: additional parameters for the checking + * + * Return: %true if there is no secondary channel or the secondary channel(s) + * can be used for beaconing (i.e. is not a radar channel etc.) + */ +bool cfg80211_reg_check_beaconing(struct wiphy *wiphy, + struct cfg80211_chan_def *chandef, + struct cfg80211_beaconing_check_config *cfg); + +/** * cfg80211_reg_can_beacon - check if beaconing is allowed * @wiphy: the wiphy * @chandef: the channel definition @@ -8762,9 +8994,17 @@ static inline void cfg80211_report_obss_beacon(struct wiphy *wiphy, * Return: %true if there is no secondary channel or the secondary channel(s) * can be used for beaconing (i.e. is not a radar channel etc.) */ -bool cfg80211_reg_can_beacon(struct wiphy *wiphy, - struct cfg80211_chan_def *chandef, - enum nl80211_iftype iftype); +static inline bool +cfg80211_reg_can_beacon(struct wiphy *wiphy, + struct cfg80211_chan_def *chandef, + enum nl80211_iftype iftype) +{ + struct cfg80211_beaconing_check_config config = { + .iftype = iftype, + }; + + return cfg80211_reg_check_beaconing(wiphy, chandef, &config); +} /** * cfg80211_reg_can_beacon_relax - check if beaconing is allowed with relaxation @@ -8777,13 +9017,22 @@ bool cfg80211_reg_can_beacon(struct wiphy *wiphy, * also checks if IR-relaxation conditions apply, to allow beaconing under * more permissive conditions. * - * Requires the wiphy mutex to be held. + * Context: Requires the wiphy mutex to be held. */ -bool cfg80211_reg_can_beacon_relax(struct wiphy *wiphy, - struct cfg80211_chan_def *chandef, - enum nl80211_iftype iftype); +static inline bool +cfg80211_reg_can_beacon_relax(struct wiphy *wiphy, + struct cfg80211_chan_def *chandef, + enum nl80211_iftype iftype) +{ + struct cfg80211_beaconing_check_config config = { + .iftype = iftype, + .relax = true, + }; -/* + return cfg80211_reg_check_beaconing(wiphy, chandef, &config); +} + +/** * cfg80211_ch_switch_notify - update wdev channel and notify userspace * @dev: the device which switched channels * @chandef: the new channel definition @@ -8796,7 +9045,7 @@ void cfg80211_ch_switch_notify(struct net_device *dev, struct cfg80211_chan_def *chandef, unsigned int link_id); -/* +/** * cfg80211_ch_switch_started_notify - notify channel switch start * @dev: the device on which the channel switch started * @chandef: the future channel definition @@ -8819,7 +9068,7 @@ void cfg80211_ch_switch_started_notify(struct net_device *dev, * @operating_class: the operating class to convert * @band: band pointer to fill * - * Returns %true if the conversion was successful, %false otherwise. + * Return: %true if the conversion was successful, %false otherwise. */ bool ieee80211_operating_class_to_band(u8 operating_class, enum nl80211_band *band); @@ -8831,7 +9080,7 @@ bool ieee80211_operating_class_to_band(u8 operating_class, * @chan: the ieee80211_channel to convert * @chandef: a pointer to the resulting chandef * - * Returns %true if the conversion was successful, %false otherwise. + * Return: %true if the conversion was successful, %false otherwise. */ bool ieee80211_operating_class_to_chandef(u8 operating_class, struct ieee80211_channel *chan, @@ -8843,7 +9092,7 @@ bool ieee80211_operating_class_to_chandef(u8 operating_class, * @chandef: the chandef to convert * @op_class: a pointer to the resulting operating class * - * Returns %true if the conversion was successful, %false otherwise. + * Return: %true if the conversion was successful, %false otherwise. */ bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef, u8 *op_class); @@ -8853,7 +9102,7 @@ bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef, * * @chandef: the chandef to convert * - * Returns the center frequency of chandef (1st segment) in KHz. + * Return: the center frequency of chandef (1st segment) in KHz. */ static inline u32 ieee80211_chandef_to_khz(const struct cfg80211_chan_def *chandef) @@ -8861,7 +9110,7 @@ ieee80211_chandef_to_khz(const struct cfg80211_chan_def *chandef) return MHZ_TO_KHZ(chandef->center_freq1) + chandef->freq1_offset; } -/* +/** * cfg80211_tdls_oper_request - request userspace to perform TDLS operation * @dev: the device on which the operation is requested * @peer: the MAC address of the peer device @@ -8880,11 +9129,11 @@ void cfg80211_tdls_oper_request(struct net_device *dev, const u8 *peer, enum nl80211_tdls_operation oper, u16 reason_code, gfp_t gfp); -/* +/** * cfg80211_calculate_bitrate - calculate actual bitrate (in 100Kbps units) * @rate: given rate_info to calculate bitrate from * - * return 0 if MCS index >= 32 + * Return: calculated bitrate */ u32 cfg80211_calculate_bitrate(struct rate_info *rate); @@ -8898,7 +9147,7 @@ u32 cfg80211_calculate_bitrate(struct rate_info *rate); * when the driver wishes to unregister the wdev, e.g. when the hardware device * is unbound from the driver. * - * Requires the RTNL and wiphy mutex to be held. + * Context: Requires the RTNL and wiphy mutex to be held. */ void cfg80211_unregister_wdev(struct wireless_dev *wdev); @@ -8911,7 +9160,9 @@ void cfg80211_unregister_wdev(struct wireless_dev *wdev); * held. Otherwise, both register_netdevice() and register_netdev() are usable * instead as well. * - * Requires the RTNL and wiphy mutex to be held. + * Context: Requires the RTNL and wiphy mutex to be held. + * + * Return: 0 on success. Non-zero on error. */ int cfg80211_register_netdevice(struct net_device *dev); @@ -8924,7 +9175,7 @@ int cfg80211_register_netdevice(struct net_device *dev); * is held. Otherwise, both unregister_netdevice() and unregister_netdev() are * usable instead as well. * - * Requires the RTNL and wiphy mutex to be held. + * Context: Requires the RTNL and wiphy mutex to be held. */ static inline void cfg80211_unregister_netdevice(struct net_device *dev) { @@ -9000,9 +9251,9 @@ int cfg80211_get_p2p_attr(const u8 *ies, unsigned int len, * 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. + * Return: 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, @@ -9030,9 +9281,9 @@ size_t ieee80211_ie_split_ric(const u8 *ies, size_t ielen, * 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. + * Return: The offset where the next part of the buffer starts, which + * may be @ielen if the entire (remainder) of the buffer should be + * used. */ static inline size_t ieee80211_ie_split(const u8 *ies, size_t ielen, const u8 *ids, int n_ids, size_t offset) @@ -9096,6 +9347,8 @@ unsigned int ieee80211_get_num_supported_channels(struct wiphy *wiphy); * This function can be called by the driver to check whether a * combination of interfaces and their types are allowed according to * the interface combinations. + * + * Return: 0 if combinations are allowed. Non-zero on error. */ int cfg80211_check_combinations(struct wiphy *wiphy, struct iface_combination_params *params); @@ -9111,6 +9364,8 @@ int cfg80211_check_combinations(struct wiphy *wiphy, * This function can be called by the driver to check what possible * combinations it fits in at a given moment, e.g. for channel switching * purposes. + * + * Return: 0 on success. Non-zero on error. */ int cfg80211_iter_combinations(struct wiphy *wiphy, struct iface_combination_params *params, @@ -9118,7 +9373,7 @@ int cfg80211_iter_combinations(struct wiphy *wiphy, void *data), void *data); -/* +/** * cfg80211_stop_iface - trigger interface disconnection * * @wiphy: the wiphy @@ -9173,6 +9428,8 @@ static inline void wiphy_ext_feature_set(struct wiphy *wiphy, * * The extended features are flagged in multiple bytes (see * &struct wiphy.@ext_features) + * + * Return: %true if extended feature flag is set, %false otherwise */ static inline bool wiphy_ext_feature_isset(struct wiphy *wiphy, @@ -9294,6 +9551,8 @@ void cfg80211_pmsr_complete(struct wireless_dev *wdev, * Check whether the interface is allowed to operate; additionally, this API * can be used to check iftype against the software interfaces when * check_swif is '1'. + * + * Return: %true if allowed, %false otherwise */ bool cfg80211_iftype_allowed(struct wiphy *wiphy, enum nl80211_iftype iftype, bool is_4addr, u8 check_swif); @@ -9386,60 +9645,78 @@ void cfg80211_bss_flush(struct wiphy *wiphy); * @cmd: the actual event we want to notify * @count: the number of TBTTs until the color change happens * @color_bitmap: representations of the colors that the local BSS is aware of + * @link_id: valid link_id in case of MLO or 0 for non-MLO. + * + * Return: 0 on success. Non-zero on error. */ int cfg80211_bss_color_notify(struct net_device *dev, enum nl80211_commands cmd, u8 count, - u64 color_bitmap); + u64 color_bitmap, u8 link_id); /** * cfg80211_obss_color_collision_notify - notify about bss color collision * @dev: network device * @color_bitmap: representations of the colors that the local BSS is aware of + * @link_id: valid link_id in case of MLO or 0 for non-MLO. + * + * Return: 0 on success. Non-zero on error. */ static inline int cfg80211_obss_color_collision_notify(struct net_device *dev, - u64 color_bitmap) + u64 color_bitmap, + u8 link_id) { return cfg80211_bss_color_notify(dev, NL80211_CMD_OBSS_COLOR_COLLISION, - 0, color_bitmap); + 0, color_bitmap, link_id); } /** * cfg80211_color_change_started_notify - notify color change start * @dev: the device on which the color is switched * @count: the number of TBTTs until the color change happens + * @link_id: valid link_id in case of MLO or 0 for non-MLO. * * Inform the userspace about the color change that has started. + * + * Return: 0 on success. Non-zero on error. */ static inline int cfg80211_color_change_started_notify(struct net_device *dev, - u8 count) + u8 count, u8 link_id) { return cfg80211_bss_color_notify(dev, NL80211_CMD_COLOR_CHANGE_STARTED, - count, 0); + count, 0, link_id); } /** * cfg80211_color_change_aborted_notify - notify color change abort * @dev: the device on which the color is switched + * @link_id: valid link_id in case of MLO or 0 for non-MLO. * * Inform the userspace about the color change that has aborted. + * + * Return: 0 on success. Non-zero on error. */ -static inline int cfg80211_color_change_aborted_notify(struct net_device *dev) +static inline int cfg80211_color_change_aborted_notify(struct net_device *dev, + u8 link_id) { return cfg80211_bss_color_notify(dev, NL80211_CMD_COLOR_CHANGE_ABORTED, - 0, 0); + 0, 0, link_id); } /** * cfg80211_color_change_notify - notify color change completion * @dev: the device on which the color was switched + * @link_id: valid link_id in case of MLO or 0 for non-MLO. * * Inform the userspace about the color change that has completed. + * + * Return: 0 on success. Non-zero on error. */ -static inline int cfg80211_color_change_notify(struct net_device *dev) +static inline int cfg80211_color_change_notify(struct net_device *dev, + u8 link_id) { return cfg80211_bss_color_notify(dev, NL80211_CMD_COLOR_CHANGE_COMPLETED, - 0, 0); + 0, 0, link_id); } /** @@ -9456,6 +9733,40 @@ static inline int cfg80211_color_change_notify(struct net_device *dev) void cfg80211_links_removed(struct net_device *dev, u16 link_mask); /** + * struct cfg80211_mlo_reconf_done_data - MLO reconfiguration data + * @buf: MLO Reconfiguration Response frame (header + body) + * @len: length of the frame data + * @added_links: BIT mask of links successfully added to the association + * @links: per-link information indexed by link ID + * @links.bss: the BSS that MLO reconfiguration was requested for, ownership of + * the pointer moves to cfg80211 in the call to + * cfg80211_mlo_reconf_add_done(). + * + * The BSS pointer must be set for each link for which 'add' operation was + * requested in the assoc_ml_reconf callback. + */ +struct cfg80211_mlo_reconf_done_data { + const u8 *buf; + size_t len; + u16 added_links; + struct { + struct cfg80211_bss *bss; + u8 *addr; + } links[IEEE80211_MLD_MAX_NUM_LINKS]; +}; + +/** + * cfg80211_mlo_reconf_add_done - Notify about MLO reconfiguration result + * @dev: network device. + * @data: MLO reconfiguration done data, &struct cfg80211_mlo_reconf_done_data + * + * Inform cfg80211 and the userspace that processing of ML reconfiguration + * request to add links to the association is done. + */ +void cfg80211_mlo_reconf_add_done(struct net_device *dev, + struct cfg80211_mlo_reconf_done_data *data); + +/** * cfg80211_schedule_channels_check - schedule regulatory check if needed * @wdev: the wireless device to check * @@ -9465,6 +9776,13 @@ void cfg80211_links_removed(struct net_device *dev, u16 link_mask); */ void cfg80211_schedule_channels_check(struct wireless_dev *wdev); +/** + * cfg80211_epcs_changed - Notify about a change in EPCS state + * @netdev: the wireless device whose EPCS state changed + * @enabled: set to true if EPCS was enabled, otherwise set to false. + */ +void cfg80211_epcs_changed(struct net_device *netdev, bool enabled); + #ifdef CONFIG_CFG80211_DEBUGFS /** * wiphy_locked_debugfs_read - do a locked read in debugfs @@ -9477,6 +9795,8 @@ void cfg80211_schedule_channels_check(struct wireless_dev *wdev); * @ppos: read position * @handler: the read handler to call (under wiphy lock) * @data: additional data to pass to the read handler + * + * Return: the number of characters read, or a negative errno */ ssize_t wiphy_locked_debugfs_read(struct wiphy *wiphy, struct file *file, char *buf, size_t bufsize, @@ -9499,6 +9819,8 @@ ssize_t wiphy_locked_debugfs_read(struct wiphy *wiphy, struct file *file, * @count: read count * @handler: the write handler to call (under wiphy lock) * @data: additional data to pass to the write handler + * + * Return: the number of characters written, or a negative errno */ ssize_t wiphy_locked_debugfs_write(struct wiphy *wiphy, struct file *file, char *buf, size_t bufsize, diff --git a/include/net/checksum.h b/include/net/checksum.h index 1338cb92c8e7..e57986b173f8 100644 --- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -99,12 +99,6 @@ csum_block_add(__wsum csum, __wsum csum2, int offset) } static __always_inline __wsum -csum_block_add_ext(__wsum csum, __wsum csum2, int offset, int len) -{ - return csum_block_add(csum, csum2, offset); -} - -static __always_inline __wsum csum_block_sub(__wsum csum, __wsum csum2, int offset) { return csum_block_add(csum, ~csum2, offset); @@ -115,12 +109,6 @@ static __always_inline __wsum csum_unfold(__sum16 n) return (__force __wsum)n; } -static __always_inline -__wsum csum_partial_ext(const void *buff, int len, __wsum sum) -{ - return csum_partial(buff, len, sum); -} - #define CSUM_MANGLED_0 ((__force __sum16)0xffff) static __always_inline void csum_replace_by_diff(__sum16 *sum, __wsum diff) @@ -151,6 +139,12 @@ static inline void csum_replace(__wsum *csum, __wsum old, __wsum new) *csum = csum_add(csum_sub(*csum, old), new); } +static inline unsigned short csum_from32to16(unsigned int sum) +{ + sum += (sum >> 16) | (sum << 16); + return (unsigned short)(sum >> 16); +} + struct sk_buff; void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, __be32 from, __be32 to, bool pseudohdr); diff --git a/include/net/cipso_ipv4.h b/include/net/cipso_ipv4.h index 53dd7d988a2d..d6780d7903f4 100644 --- a/include/net/cipso_ipv4.h +++ b/include/net/cipso_ipv4.h @@ -28,7 +28,7 @@ #include <net/request_sock.h> #include <linux/atomic.h> #include <linux/refcount.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* known doi values */ #define CIPSO_V4_DOI_UNKNOWN 0x00000000 @@ -183,7 +183,8 @@ int cipso_v4_getattr(const unsigned char *cipso, struct netlbl_lsm_secattr *secattr); int cipso_v4_sock_setattr(struct sock *sk, const struct cipso_v4_doi *doi_def, - const struct netlbl_lsm_secattr *secattr); + const struct netlbl_lsm_secattr *secattr, + bool sk_locked); void cipso_v4_sock_delattr(struct sock *sk); int cipso_v4_sock_getattr(struct sock *sk, struct netlbl_lsm_secattr *secattr); int cipso_v4_req_setattr(struct request_sock *req, @@ -214,7 +215,8 @@ static inline int cipso_v4_getattr(const unsigned char *cipso, static inline int cipso_v4_sock_setattr(struct sock *sk, const struct cipso_v4_doi *doi_def, - const struct netlbl_lsm_secattr *secattr) + const struct netlbl_lsm_secattr *secattr, + bool sk_locked) { return -ENOSYS; } diff --git a/include/net/devlink.h b/include/net/devlink.h index 9ac394bdfbe4..0091f23a40f7 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -35,7 +35,7 @@ struct devlink_port_phys_attrs { /** * struct devlink_port_pci_pf_attrs - devlink port's PCI PF attributes * @controller: Associated controller number - * @pf: Associated PCI PF number for this port. + * @pf: associated PCI function number for the devlink port instance * @external: when set, indicates if a port is for an external controller */ struct devlink_port_pci_pf_attrs { @@ -47,8 +47,9 @@ struct devlink_port_pci_pf_attrs { /** * struct devlink_port_pci_vf_attrs - devlink port's PCI VF attributes * @controller: Associated controller number - * @pf: Associated PCI PF number for this port. - * @vf: Associated PCI VF for of the PCI PF for this port. + * @pf: associated PCI function number for the devlink port instance + * @vf: associated PCI VF number of a PF for the devlink port instance; + * VF number starts from 0 for the first PCI virtual function * @external: when set, indicates if a port is for an external controller */ struct devlink_port_pci_vf_attrs { @@ -61,8 +62,8 @@ struct devlink_port_pci_vf_attrs { /** * struct devlink_port_pci_sf_attrs - devlink port's PCI SF attributes * @controller: Associated controller number - * @sf: Associated PCI SF for of the PCI PF for this port. - * @pf: Associated PCI PF number for this port. + * @sf: associated SF number of a PF for the devlink port instance + * @pf: associated PCI function number for the devlink port instance * @external: when set, indicates if a port is for an external controller */ struct devlink_port_pci_sf_attrs { @@ -352,7 +353,7 @@ struct devlink_dpipe_table { bool resource_valid; u64 resource_id; u64 resource_units; - struct devlink_dpipe_table_ops *table_ops; + const struct devlink_dpipe_table_ops *table_ops; struct rcu_head rcu; }; @@ -419,11 +420,11 @@ typedef u64 devlink_resource_occ_get_t(void *priv); #define __DEVLINK_PARAM_MAX_STRING_VALUE 32 enum devlink_param_type { - DEVLINK_PARAM_TYPE_U8, - DEVLINK_PARAM_TYPE_U16, - DEVLINK_PARAM_TYPE_U32, - DEVLINK_PARAM_TYPE_STRING, - DEVLINK_PARAM_TYPE_BOOL, + DEVLINK_PARAM_TYPE_U8 = DEVLINK_VAR_ATTR_TYPE_U8, + DEVLINK_PARAM_TYPE_U16 = DEVLINK_VAR_ATTR_TYPE_U16, + DEVLINK_PARAM_TYPE_U32 = DEVLINK_VAR_ATTR_TYPE_U32, + DEVLINK_PARAM_TYPE_STRING = DEVLINK_VAR_ATTR_TYPE_STRING, + DEVLINK_PARAM_TYPE_BOOL = DEVLINK_VAR_ATTR_TYPE_FLAG, }; union devlink_param_value { @@ -483,7 +484,8 @@ struct devlink_param { int (*get)(struct devlink *devlink, u32 id, struct devlink_param_gset_ctx *ctx); int (*set)(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx); + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack); int (*validate)(struct devlink *devlink, u32 id, union devlink_param_value val, struct netlink_ext_ack *extack); @@ -599,12 +601,14 @@ enum devlink_param_generic_id { .validate = _validate, \ } -/* Part number, identifier of board design */ +/* Identifier of board design */ #define DEVLINK_INFO_VERSION_GENERIC_BOARD_ID "board.id" /* Revision of board design */ #define DEVLINK_INFO_VERSION_GENERIC_BOARD_REV "board.rev" /* Maker of the board */ #define DEVLINK_INFO_VERSION_GENERIC_BOARD_MANUFACTURE "board.manufacture" +/* Part number of the board and its components */ +#define DEVLINK_INFO_VERSION_GENERIC_BOARD_PART_NUMBER "board.part_number" /* Part number, identifier of asic design */ #define DEVLINK_INFO_VERSION_GENERIC_ASIC_ID "asic.id" @@ -1258,6 +1262,18 @@ enum devlink_trap_group_generic_id { .min_burst = _min_burst, \ } +#define devlink_fmsg_put(fmsg, name, value) ( \ + _Generic((value), \ + bool : devlink_fmsg_bool_pair_put, \ + u8 : devlink_fmsg_u8_pair_put, \ + u16 : devlink_fmsg_u32_pair_put, \ + u32 : devlink_fmsg_u32_pair_put, \ + u64 : devlink_fmsg_u64_pair_put, \ + int : devlink_fmsg_u32_pair_put, \ + char * : devlink_fmsg_string_pair_put, \ + const char * : devlink_fmsg_string_pair_put) \ + (fmsg, name, (value))) + enum { /* device supports reload operations */ DEVLINK_F_RELOAD = 1UL << 0, @@ -1519,6 +1535,7 @@ int devl_trylock(struct devlink *devlink); void devl_unlock(struct devlink *devlink); void devl_assert_locked(struct devlink *devlink); bool devl_lock_is_held(struct devlink *devlink); +DEFINE_GUARD(devl, struct devlink *, devl_lock(_T), devl_unlock(_T)); struct ib_device; @@ -1602,6 +1619,14 @@ void devlink_free(struct devlink *devlink); * capability. Should be used by device drivers to * enable/disable ipsec_packet capability of a * function managed by the devlink port. + * @port_fn_max_io_eqs_get: Callback used to get port function's maximum number + * of event queues. Should be used by device drivers to + * report the maximum event queues of a function + * managed by the devlink port. + * @port_fn_max_io_eqs_set: Callback used to set port function's maximum number + * of event queues. Should be used by device drivers to + * configure maximum number of event queues + * of a function managed by the devlink port. * * Note: Driver should return -EOPNOTSUPP if it doesn't support * port function (@port_fn_*) handling for a particular port. @@ -1651,6 +1676,12 @@ struct devlink_port_ops { int (*port_fn_ipsec_packet_set)(struct devlink_port *devlink_port, bool enable, struct netlink_ext_ack *extack); + int (*port_fn_max_io_eqs_get)(struct devlink_port *devlink_port, + u32 *max_eqs, + struct netlink_ext_ack *extack); + int (*port_fn_max_io_eqs_set)(struct devlink_port *devlink_port, + u32 max_eqs, + struct netlink_ext_ack *extack); }; void devlink_port_init(struct devlink *devlink, @@ -1734,7 +1765,7 @@ void devl_sb_unregister(struct devlink *devlink, unsigned int sb_index); void devlink_sb_unregister(struct devlink *devlink, unsigned int sb_index); int devl_dpipe_table_register(struct devlink *devlink, const char *table_name, - struct devlink_dpipe_table_ops *table_ops, + const struct devlink_dpipe_table_ops *table_ops, void *priv, bool counter_control_extern); void devl_dpipe_table_unregister(struct devlink *devlink, const char *table_name); @@ -1762,12 +1793,6 @@ int devl_resource_register(struct devlink *devlink, u64 resource_id, u64 parent_resource_id, const struct devlink_resource_size_params *size_params); -int devlink_resource_register(struct devlink *devlink, - const char *resource_name, - u64 resource_size, - u64 resource_id, - u64 parent_resource_id, - const struct devlink_resource_size_params *size_params); void devl_resources_unregister(struct devlink *devlink); void devlink_resources_unregister(struct devlink *devlink); int devl_resource_size_get(struct devlink *devlink, @@ -1780,15 +1805,8 @@ void devl_resource_occ_get_register(struct devlink *devlink, u64 resource_id, devlink_resource_occ_get_t *occ_get, void *occ_get_priv); -void devlink_resource_occ_get_register(struct devlink *devlink, - u64 resource_id, - devlink_resource_occ_get_t *occ_get, - void *occ_get_priv); void devl_resource_occ_get_unregister(struct devlink *devlink, u64 resource_id); - -void devlink_resource_occ_get_unregister(struct devlink *devlink, - u64 resource_id); int devl_params_register(struct devlink *devlink, const struct devlink_param *params, size_t params_count); @@ -1990,6 +2008,7 @@ int devlink_compat_switch_id_get(struct net_device *dev, int devlink_nl_port_handle_fill(struct sk_buff *msg, struct devlink_port *devlink_port); size_t devlink_nl_port_handle_size(struct devlink_port *devlink_port); +void devlink_fmsg_dump_skb(struct devlink_fmsg *fmsg, const struct sk_buff *skb); #else diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h index 9707ab54fdd5..bcf9d7467e1a 100644 --- a/include/net/dropreason-core.h +++ b/include/net/dropreason-core.h @@ -6,9 +6,13 @@ #define DEFINE_DROP_REASON(FN, FNe) \ FN(NOT_SPECIFIED) \ FN(NO_SOCKET) \ + FN(SOCKET_CLOSE) \ + FN(SOCKET_FILTER) \ + FN(SOCKET_RCVBUFF) \ + FN(UNIX_DISCONNECT) \ + FN(UNIX_SKIP_OOB) \ FN(PKT_TOO_SMALL) \ FN(TCP_CSUM) \ - FN(SOCKET_FILTER) \ FN(UDP_CSUM) \ FN(NETFILTER_DROP) \ FN(OTHERHOST) \ @@ -18,7 +22,6 @@ FN(UNICAST_IN_L2_MULTICAST) \ FN(XFRM_POLICY) \ FN(IP_NOPROTO) \ - FN(SOCKET_RCVBUFF) \ FN(PROTO_MEM) \ FN(TCP_AUTH_HDR) \ FN(TCP_MD5NOTFOUND) \ @@ -36,6 +39,10 @@ FN(TCP_OVERWINDOW) \ FN(TCP_OFOMERGE) \ FN(TCP_RFC7323_PAWS) \ + FN(TCP_RFC7323_PAWS_ACK) \ + FN(TCP_RFC7323_TW_PAWS) \ + FN(TCP_RFC7323_TSECR) \ + FN(TCP_LISTEN_OVERFLOW) \ FN(TCP_OLD_SEQUENCE) \ FN(TCP_INVALID_SEQUENCE) \ FN(TCP_INVALID_ACK_SEQUENCE) \ @@ -55,9 +62,16 @@ FN(NEIGH_FAILED) \ FN(NEIGH_QUEUEFULL) \ FN(NEIGH_DEAD) \ + FN(NEIGH_HH_FILLFAIL) \ FN(TC_EGRESS) \ FN(SECURITY_HOOK) \ FN(QDISC_DROP) \ + FN(QDISC_OVERLIMIT) \ + FN(QDISC_CONGESTED) \ + FN(CAKE_FLOOD) \ + FN(FQ_BAND_LIMIT) \ + FN(FQ_HORIZON_LIMIT) \ + FN(FQ_FLOW_LIMIT) \ FN(CPU_BACKLOG) \ FN(XDP) \ FN(TC_INGRESS) \ @@ -76,6 +90,10 @@ FN(INVALID_PROTO) \ FN(IP_INADDRERRORS) \ FN(IP_INNOROUTES) \ + FN(IP_LOCAL_SOURCE) \ + FN(IP_INVALID_SOURCE) \ + FN(IP_LOCALNET) \ + FN(IP_INVALID_DEST) \ FN(PKT_TOO_BIG) \ FN(DUP_FRAG) \ FN(FRAG_REASM_TIMEOUT) \ @@ -92,6 +110,17 @@ FN(PACKET_SOCK_ERROR) \ FN(TC_CHAIN_NOTFOUND) \ FN(TC_RECLASSIFY_LOOP) \ + FN(VXLAN_INVALID_HDR) \ + FN(VXLAN_VNI_NOT_FOUND) \ + FN(MAC_INVALID_SOURCE) \ + FN(VXLAN_ENTRY_EXISTS) \ + FN(NO_TX_TARGET) \ + FN(IP_TUNNEL_ECN) \ + FN(TUNNEL_TXINFO) \ + FN(LOCAL_MAC) \ + FN(ARP_PVLAN_DISABLE) \ + FN(MAC_IEEE_MAC_CONTROL) \ + FN(BRIDGE_INGRESS_STP_STATE) \ FNe(MAX) /** @@ -116,12 +145,27 @@ enum skb_drop_reason { * 3) no valid child socket during 3WHS process */ SKB_DROP_REASON_NO_SOCKET, + /** @SKB_DROP_REASON_SOCKET_CLOSE: socket is close()d */ + SKB_DROP_REASON_SOCKET_CLOSE, + /** @SKB_DROP_REASON_SOCKET_FILTER: dropped by socket filter */ + SKB_DROP_REASON_SOCKET_FILTER, + /** @SKB_DROP_REASON_SOCKET_RCVBUFF: socket receive buff is full */ + SKB_DROP_REASON_SOCKET_RCVBUFF, + /** + * @SKB_DROP_REASON_UNIX_DISCONNECT: recv queue is purged when SOCK_DGRAM + * or SOCK_SEQPACKET socket re-connect()s to another socket or notices + * during send() that the peer has been close()d. + */ + SKB_DROP_REASON_UNIX_DISCONNECT, + /** + * @SKB_DROP_REASON_UNIX_SKIP_OOB: Out-Of-Band data is skipped by + * recv() without MSG_OOB so dropped. + */ + SKB_DROP_REASON_UNIX_SKIP_OOB, /** @SKB_DROP_REASON_PKT_TOO_SMALL: packet size is too small */ SKB_DROP_REASON_PKT_TOO_SMALL, /** @SKB_DROP_REASON_TCP_CSUM: TCP checksum error */ SKB_DROP_REASON_TCP_CSUM, - /** @SKB_DROP_REASON_SOCKET_FILTER: dropped by socket filter */ - SKB_DROP_REASON_SOCKET_FILTER, /** @SKB_DROP_REASON_UDP_CSUM: UDP checksum error */ SKB_DROP_REASON_UDP_CSUM, /** @SKB_DROP_REASON_NETFILTER_DROP: dropped by netfilter */ @@ -152,11 +196,9 @@ enum skb_drop_reason { SKB_DROP_REASON_XFRM_POLICY, /** @SKB_DROP_REASON_IP_NOPROTO: no support for IP protocol */ SKB_DROP_REASON_IP_NOPROTO, - /** @SKB_DROP_REASON_SOCKET_RCVBUFF: socket receive buff is full */ - SKB_DROP_REASON_SOCKET_RCVBUFF, /** - * @SKB_DROP_REASON_PROTO_MEM: proto memory limition, such as udp packet - * drop out of udp_memory_allocated. + * @SKB_DROP_REASON_PROTO_MEM: proto memory limitation, such as + * udp packet drop out of udp_memory_allocated. */ SKB_DROP_REASON_PROTO_MEM, /** @@ -217,7 +259,7 @@ enum skb_drop_reason { */ SKB_DROP_REASON_TCP_ZEROWINDOW, /** - * @SKB_DROP_REASON_TCP_OLD_DATA: the TCP data reveived is already + * @SKB_DROP_REASON_TCP_OLD_DATA: the TCP data received is already * received before (spurious retrans may happened), see * LINUX_MIB_DELAYEDACKLOST */ @@ -238,6 +280,24 @@ enum skb_drop_reason { * LINUX_MIB_PAWSESTABREJECTED, LINUX_MIB_PAWSACTIVEREJECTED */ SKB_DROP_REASON_TCP_RFC7323_PAWS, + /** + * @SKB_DROP_REASON_TCP_RFC7323_PAWS_ACK: PAWS check, old ACK packet. + * Corresponds to LINUX_MIB_PAWS_OLD_ACK. + */ + SKB_DROP_REASON_TCP_RFC7323_PAWS_ACK, + /** + * @SKB_DROP_REASON_TCP_RFC7323_TW_PAWS: PAWS check, socket is in + * TIME_WAIT state. + * Corresponds to LINUX_MIB_PAWS_TW_REJECTED. + */ + SKB_DROP_REASON_TCP_RFC7323_TW_PAWS, + /** + * @SKB_DROP_REASON_TCP_RFC7323_TSECR: PAWS check, invalid TSEcr. + * Corresponds to LINUX_MIB_TSECRREJECTED. + */ + SKB_DROP_REASON_TCP_RFC7323_TSECR, + /** @SKB_DROP_REASON_TCP_LISTEN_OVERFLOW: listener queue full. */ + SKB_DROP_REASON_TCP_LISTEN_OVERFLOW, /** @SKB_DROP_REASON_TCP_OLD_SEQUENCE: Old SEQ field (duplicate packet) */ SKB_DROP_REASON_TCP_OLD_SEQUENCE, /** @SKB_DROP_REASON_TCP_INVALID_SEQUENCE: Not acceptable SEQ field */ @@ -289,6 +349,8 @@ enum skb_drop_reason { SKB_DROP_REASON_NEIGH_QUEUEFULL, /** @SKB_DROP_REASON_NEIGH_DEAD: neigh entry is dead */ SKB_DROP_REASON_NEIGH_DEAD, + /** @SKB_DROP_REASON_NEIGH_HH_FILLFAIL: failed to fill the device hard header */ + SKB_DROP_REASON_NEIGH_HH_FILLFAIL, /** @SKB_DROP_REASON_TC_EGRESS: dropped in TC egress HOOK */ SKB_DROP_REASON_TC_EGRESS, /** @SKB_DROP_REASON_SECURITY_HOOK: dropped due to security HOOK */ @@ -299,6 +361,36 @@ enum skb_drop_reason { */ SKB_DROP_REASON_QDISC_DROP, /** + * @SKB_DROP_REASON_QDISC_OVERLIMIT: dropped by qdisc when a qdisc + * instance exceeds its total buffer size limit. + */ + SKB_DROP_REASON_QDISC_OVERLIMIT, + /** + * @SKB_DROP_REASON_QDISC_CONGESTED: dropped by a qdisc AQM algorithm + * due to congestion. + */ + SKB_DROP_REASON_QDISC_CONGESTED, + /** + * @SKB_DROP_REASON_CAKE_FLOOD: dropped by the flood protection part of + * CAKE qdisc AQM algorithm (BLUE). + */ + SKB_DROP_REASON_CAKE_FLOOD, + /** + * @SKB_DROP_REASON_FQ_BAND_LIMIT: dropped by fq qdisc when per band + * limit is reached. + */ + SKB_DROP_REASON_FQ_BAND_LIMIT, + /** + * @SKB_DROP_REASON_FQ_HORIZON_LIMIT: dropped by fq qdisc when packet + * timestamp is too far in the future. + */ + SKB_DROP_REASON_FQ_HORIZON_LIMIT, + /** + * @SKB_DROP_REASON_FQ_FLOW_LIMIT: dropped by fq qdisc when a flow + * exceeds its limits. + */ + SKB_DROP_REASON_FQ_FLOW_LIMIT, + /** * @SKB_DROP_REASON_CPU_BACKLOG: failed to enqueue the skb to the per CPU * backlog queue. This can be caused by backlog queue full (see * netdev_max_backlog in net.rst) or RPS flow limit @@ -365,6 +457,21 @@ enum skb_drop_reason { * IPSTATS_MIB_INADDRERRORS */ SKB_DROP_REASON_IP_INNOROUTES, + /** @SKB_DROP_REASON_IP_LOCAL_SOURCE: the source ip is local */ + SKB_DROP_REASON_IP_LOCAL_SOURCE, + /** + * @SKB_DROP_REASON_IP_INVALID_SOURCE: the source ip is invalid: + * 1) source ip is multicast or limited broadcast + * 2) source ip is zero and not IGMP + */ + SKB_DROP_REASON_IP_INVALID_SOURCE, + /** @SKB_DROP_REASON_IP_LOCALNET: source or dest ip is local net */ + SKB_DROP_REASON_IP_LOCALNET, + /** + * @SKB_DROP_REASON_IP_INVALID_DEST: the dest ip is invalid: + * 1) dest ip is 0 + */ + SKB_DROP_REASON_IP_INVALID_DEST, /** * @SKB_DROP_REASON_PKT_TOO_BIG: packet size is too big (maybe exceed the * MTU) @@ -419,6 +526,54 @@ enum skb_drop_reason { */ SKB_DROP_REASON_TC_RECLASSIFY_LOOP, /** + * @SKB_DROP_REASON_VXLAN_INVALID_HDR: VXLAN header is invalid. E.g.: + * 1) reserved fields are not zero + * 2) "I" flag is not set + */ + SKB_DROP_REASON_VXLAN_INVALID_HDR, + /** @SKB_DROP_REASON_VXLAN_VNI_NOT_FOUND: no VXLAN device found for VNI */ + SKB_DROP_REASON_VXLAN_VNI_NOT_FOUND, + /** @SKB_DROP_REASON_MAC_INVALID_SOURCE: source mac is invalid */ + SKB_DROP_REASON_MAC_INVALID_SOURCE, + /** + * @SKB_DROP_REASON_VXLAN_ENTRY_EXISTS: trying to migrate a static + * entry or an entry pointing to a nexthop. + */ + SKB_DROP_REASON_VXLAN_ENTRY_EXISTS, + /** @SKB_DROP_REASON_NO_TX_TARGET: no target found for xmit */ + SKB_DROP_REASON_NO_TX_TARGET, + /** + * @SKB_DROP_REASON_IP_TUNNEL_ECN: skb is dropped according to + * RFC 6040 4.2, see __INET_ECN_decapsulate() for detail. + */ + SKB_DROP_REASON_IP_TUNNEL_ECN, + /** + * @SKB_DROP_REASON_TUNNEL_TXINFO: packet without necessary metadata + * reached a device which is in "external" mode. + */ + SKB_DROP_REASON_TUNNEL_TXINFO, + /** + * @SKB_DROP_REASON_LOCAL_MAC: the source MAC address is equal to + * the MAC address of the local netdev. + */ + SKB_DROP_REASON_LOCAL_MAC, + /** + * @SKB_DROP_REASON_ARP_PVLAN_DISABLE: packet which is not IP is + * forwarded to the in_dev, and the proxy_arp_pvlan is not + * enabled. + */ + SKB_DROP_REASON_ARP_PVLAN_DISABLE, + /** + * @SKB_DROP_REASON_MAC_IEEE_MAC_CONTROL: the destination MAC address + * is an IEEE MAC Control address. + */ + SKB_DROP_REASON_MAC_IEEE_MAC_CONTROL, + /** + * @SKB_DROP_REASON_BRIDGE_INGRESS_STP_STATE: the STP state of the + * ingress bridge port does not allow frames to be forwarded. + */ + SKB_DROP_REASON_BRIDGE_INGRESS_STP_STATE, + /** * @SKB_DROP_REASON_MAX: the maximum of core drop reasons, which * shouldn't be used as a real 'reason' - only for tracing code gen */ diff --git a/include/net/dropreason.h b/include/net/dropreason.h index 56cb7be92244..7d3b1a2a6fec 100644 --- a/include/net/dropreason.h +++ b/include/net/dropreason.h @@ -18,12 +18,6 @@ enum skb_drop_reason_subsys { SKB_DROP_REASON_SUBSYS_MAC80211_UNUSABLE, /** - * @SKB_DROP_REASON_SUBSYS_MAC80211_MONITOR: mac80211 drop reasons - * for frames still going to monitor, see net/mac80211/drop.h - */ - SKB_DROP_REASON_SUBSYS_MAC80211_MONITOR, - - /** * @SKB_DROP_REASON_SUBSYS_OPENVSWITCH: openvswitch drop reasons, * see net/openvswitch/drop.h */ diff --git a/include/net/dsa.h b/include/net/dsa.h index 7c0da9effe4e..55e2d97f247e 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -24,9 +24,6 @@ struct dsa_8021q_context; struct tc_action; -struct phy_device; -struct fixed_phy_status; -struct phylink_link_state; #define DSA_TAG_PROTO_NONE_VALUE 0 #define DSA_TAG_PROTO_BRCM_VALUE 1 @@ -56,6 +53,7 @@ struct phylink_link_state; #define DSA_TAG_PROTO_RTL8_4T_VALUE 25 #define DSA_TAG_PROTO_RZN1_A5PSW_VALUE 26 #define DSA_TAG_PROTO_LAN937X_VALUE 27 +#define DSA_TAG_PROTO_VSC73XX_8021Q_VALUE 28 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -86,6 +84,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_RTL8_4T = DSA_TAG_PROTO_RTL8_4T_VALUE, DSA_TAG_PROTO_RZN1_A5PSW = DSA_TAG_PROTO_RZN1_A5PSW_VALUE, DSA_TAG_PROTO_LAN937X = DSA_TAG_PROTO_LAN937X_VALUE, + DSA_TAG_PROTO_VSC73XX_8021Q = DSA_TAG_PROTO_VSC73XX_8021Q_VALUE, }; struct dsa_switch; @@ -327,6 +326,12 @@ struct dsa_port { }; }; +static inline struct dsa_port * +dsa_phylink_to_port(struct phylink_config *config) +{ + return container_of(config, struct dsa_port, pl_config); +} + /* TODO: ideally DSA ports would have a single dp->link_dp member, * and no dst->rtable nor this struct dsa_link would be needed, * but this would require some more complex tree walking, @@ -398,14 +403,18 @@ struct dsa_switch { */ u32 configure_vlan_while_not_filtering:1; - /* If the switch driver always programs the CPU port as egress tagged - * despite the VLAN configuration indicating otherwise, then setting - * @untag_bridge_pvid will force the DSA receive path to pop the - * bridge's default_pvid VLAN tagged frames to offer a consistent - * behavior between a vlan_filtering=0 and vlan_filtering=1 bridge - * device. + /* Pop the default_pvid of VLAN-unaware bridge ports from tagged frames. + * DEPRECATED: Do NOT set this field in new drivers. Instead look at + * the dsa_software_vlan_untag() comments. */ u32 untag_bridge_pvid:1; + /* Pop the default_pvid of VLAN-aware bridge ports from tagged frames. + * Useful if the switch cannot preserve the VLAN tag as seen on the + * wire for user port ingress, and chooses to send all frames as + * VLAN-tagged to the CPU, including those which were originally + * untagged. + */ + u32 untag_vlan_aware_bridge_pvid:1; /* Let DSA manage the FDB entries towards the * CPU, based on the software bridge database. @@ -430,6 +439,11 @@ struct dsa_switch { */ u32 fdb_isolation:1; + /* Drivers that have global DSCP mapping settings must set this to + * true to automatically apply the settings to all ports. + */ + u32 dscp_prio_mapping_is_global:1; + /* Listener for switch fabric events */ struct notifier_block nb; @@ -452,6 +466,11 @@ struct dsa_switch { const struct dsa_switch_ops *ops; /* + * Allow a DSA switch driver to override the phylink MAC ops + */ + const struct phylink_mac_ops *phylink_mac_ops; + + /* * User mii_bus and devices for the individual ports. */ u32 phys_mii_mask; @@ -578,6 +597,10 @@ static inline bool dsa_is_user_port(struct dsa_switch *ds, int p) dsa_switch_for_each_port((_dp), (_ds)) \ if (dsa_port_is_user((_dp))) +#define dsa_switch_for_each_user_port_continue_reverse(_dp, _ds) \ + dsa_switch_for_each_port_continue_reverse((_dp), (_ds)) \ + if (dsa_port_is_user((_dp))) + #define dsa_switch_for_each_cpu_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (dsa_port_is_cpu((_dp))) @@ -858,39 +881,10 @@ struct dsa_switch_ops { int regnum, u16 val); /* - * Link state adjustment (called from libphy) - */ - void (*adjust_link)(struct dsa_switch *ds, int port, - struct phy_device *phydev); - void (*fixed_link_update)(struct dsa_switch *ds, int port, - struct fixed_phy_status *st); - - /* * PHYLINK integration */ void (*phylink_get_caps)(struct dsa_switch *ds, int port, struct phylink_config *config); - struct phylink_pcs *(*phylink_mac_select_pcs)(struct dsa_switch *ds, - int port, - phy_interface_t iface); - int (*phylink_mac_prepare)(struct dsa_switch *ds, int port, - unsigned int mode, - phy_interface_t interface); - void (*phylink_mac_config)(struct dsa_switch *ds, int port, - unsigned int mode, - const struct phylink_link_state *state); - int (*phylink_mac_finish)(struct dsa_switch *ds, int port, - unsigned int mode, - phy_interface_t interface); - void (*phylink_mac_link_down)(struct dsa_switch *ds, int port, - unsigned int mode, - phy_interface_t interface); - void (*phylink_mac_link_up)(struct dsa_switch *ds, int port, - unsigned int mode, - phy_interface_t interface, - struct phy_device *phydev, - int speed, int duplex, - bool tx_pause, bool rx_pause); void (*phylink_fixed_state)(struct dsa_switch *ds, int port, struct phylink_link_state *state); /* @@ -912,6 +906,8 @@ struct dsa_switch_ops { void (*get_rmon_stats)(struct dsa_switch *ds, int port, struct ethtool_rmon_stats *rmon_stats, const struct ethtool_rmon_hist_range **ranges); + void (*get_ts_stats)(struct dsa_switch *ds, int port, + struct ethtool_ts_stats *ts_stats); void (*get_stats64)(struct dsa_switch *ds, int port, struct rtnl_link_stats64 *s); void (*get_pause_stats)(struct dsa_switch *ds, int port, @@ -931,7 +927,7 @@ struct dsa_switch_ops { * ethtool timestamp info */ int (*get_ts_info)(struct dsa_switch *ds, int port, - struct ethtool_ts_info *ts); + struct kernel_ethtool_ts_info *ts); /* * ethtool MAC merge layer @@ -955,6 +951,10 @@ struct dsa_switch_ops { u8 prio); int (*port_del_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp, u8 prio); + int (*port_set_apptrust)(struct dsa_switch *ds, int port, + const u8 *sel, int nsel); + int (*port_get_apptrust)(struct dsa_switch *ds, int port, u8 *sel, + int *nsel); /* * Suspend and resume @@ -990,10 +990,9 @@ struct dsa_switch_ops { /* * Port's MAC EEE settings */ + bool (*support_eee)(struct dsa_switch *ds, int port); int (*set_mac_eee)(struct dsa_switch *ds, int port, struct ethtool_keee *e); - int (*get_mac_eee)(struct dsa_switch *ds, int port, - struct ethtool_keee *e); /* EEPROM access */ int (*get_eeprom_len)(struct dsa_switch *ds); @@ -1132,9 +1131,10 @@ struct dsa_switch_ops { * PTP functionality */ int (*port_hwtstamp_get)(struct dsa_switch *ds, int port, - struct ifreq *ifr); + struct kernel_hwtstamp_config *config); int (*port_hwtstamp_set)(struct dsa_switch *ds, int port, - struct ifreq *ifr); + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack); void (*port_txtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb); bool (*port_rxtstamp)(struct dsa_switch *ds, int port, @@ -1247,7 +1247,8 @@ struct dsa_switch_ops { int dsa_devlink_param_get(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx); int dsa_devlink_param_set(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx); + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack); int dsa_devlink_params_register(struct dsa_switch *ds, const struct devlink_param *params, size_t params_count); @@ -1384,5 +1385,6 @@ static inline bool dsa_user_dev_check(const struct net_device *dev) netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev); void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up); +bool dsa_supports_eee(struct dsa_switch *ds, int port); #endif diff --git a/include/net/dscp.h b/include/net/dscp.h new file mode 100644 index 000000000000..ba40540868c9 --- /dev/null +++ b/include/net/dscp.h @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024 Pengutronix, Oleksij Rempel <kernel@pengutronix.de> */ + +#ifndef __DSCP_H__ +#define __DSCP_H__ + +/* + * DSCP Pools and Codepoint Space Division: + * + * The Differentiated Services (Diffserv) architecture defines a method for + * classifying and managing network traffic using the DS field in IPv4 and IPv6 + * packet headers. This field can carry one of 64 distinct DSCP (Differentiated + * Services Code Point) values, which are divided into three pools based on + * their Least Significant Bits (LSB) patterns and intended usage. Each pool has + * a specific registration procedure for assigning DSCP values: + * + * Pool 1 (Standards Action Pool): + * - Codepoint Space: xxxxx0 + * This pool includes DSCP values ending in '0' (binary), allocated via + * Standards Action. It is intended for globally recognized traffic classes, + * ensuring interoperability across the internet. This pool encompasses + * well-known DSCP values such as CS0-CS7, AFxx, EF, and VOICE-ADMIT. + * + * Pool 2 (Experimental/Local Use Pool): + * - Codepoint Space: xxxx11 + * Reserved for DSCP values ending in '11' (binary), this pool is designated + * for Experimental or Local Use. It allows for private or temporary traffic + * marking schemes not intended for standardized global use, facilitating + * testing and network-specific configurations without impacting + * interoperability. + * + * Pool 3 (Preferential Standardization Pool): + * - Codepoint Space: xxxx01 + * Initially reserved for experimental or local use, this pool now serves as + * a secondary standardization resource should Pool 1 become exhausted. DSCP + * values ending in '01' (binary) are assigned via Standards Action, with a + * focus on adopting new, standardized traffic classes as the need arises. + * + * For pool updates see: + * https://www.iana.org/assignments/dscp-registry/dscp-registry.xhtml + */ + +/* Pool 1: Standardized DSCP values as per [RFC8126] */ +#define DSCP_CS0 0 /* 000000, [RFC2474] */ +/* CS0 is some times called default (DF) */ +#define DSCP_DF 0 /* 000000, [RFC2474] */ +#define DSCP_CS1 8 /* 001000, [RFC2474] */ +#define DSCP_CS2 16 /* 010000, [RFC2474] */ +#define DSCP_CS3 24 /* 011000, [RFC2474] */ +#define DSCP_CS4 32 /* 100000, [RFC2474] */ +#define DSCP_CS5 40 /* 101000, [RFC2474] */ +#define DSCP_CS6 48 /* 110000, [RFC2474] */ +#define DSCP_CS7 56 /* 111000, [RFC2474] */ +#define DSCP_AF11 10 /* 001010, [RFC2597] */ +#define DSCP_AF12 12 /* 001100, [RFC2597] */ +#define DSCP_AF13 14 /* 001110, [RFC2597] */ +#define DSCP_AF21 18 /* 010010, [RFC2597] */ +#define DSCP_AF22 20 /* 010100, [RFC2597] */ +#define DSCP_AF23 22 /* 010110, [RFC2597] */ +#define DSCP_AF31 26 /* 011010, [RFC2597] */ +#define DSCP_AF32 28 /* 011100, [RFC2597] */ +#define DSCP_AF33 30 /* 011110, [RFC2597] */ +#define DSCP_AF41 34 /* 100010, [RFC2597] */ +#define DSCP_AF42 36 /* 100100, [RFC2597] */ +#define DSCP_AF43 38 /* 100110, [RFC2597] */ +#define DSCP_EF 46 /* 101110, [RFC3246] */ +#define DSCP_VOICE_ADMIT 44 /* 101100, [RFC5865] */ + +/* Pool 3: Standardized assignments, previously available for experimental/local + * use + */ +#define DSCP_LE 1 /* 000001, [RFC8622] */ + +#define DSCP_MAX 64 + +#endif /* __DSCP_H__ */ diff --git a/include/net/dst.h b/include/net/dst.h index 0aa331bd2fdb..78c78cdce0e9 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -307,7 +307,7 @@ static inline bool dst_hold_safe(struct dst_entry *dst) * @skb: buffer * * If dst is not yet refcounted and not destroyed, grab a ref on it. - * Returns true if dst is refcounted. + * Returns: true if dst is refcounted. */ static inline bool skb_dst_force(struct sk_buff *skb) { @@ -341,7 +341,7 @@ static inline void __skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, skb->dev = dev; /* - * Clear hash so that we can recalulate the hash for the + * Clear hash so that we can recalculate the hash for the * encapsulated packet, unless we have already determine the hash * over the L4 4-tuple. */ @@ -440,6 +440,15 @@ static inline void dst_set_expires(struct dst_entry *dst, int timeout) dst->expires = expires; } +static inline unsigned int dst_dev_overhead(struct dst_entry *dst, + struct sk_buff *skb) +{ + if (likely(dst)) + return LL_RESERVED_SPACE(dst->dev); + + return skb->mac_len; +} + INDIRECT_CALLABLE_DECLARE(int ip6_output(struct net *, struct sock *, struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int ip_output(struct net *, struct sock *, diff --git a/include/net/dst_cache.h b/include/net/dst_cache.h index df6622a5fe98..1961699598e2 100644 --- a/include/net/dst_cache.h +++ b/include/net/dst_cache.h @@ -76,7 +76,7 @@ struct dst_entry *dst_cache_get_ip6(struct dst_cache *dst_cache, */ static inline void dst_cache_reset(struct dst_cache *dst_cache) { - dst_cache->reset_ts = jiffies; + WRITE_ONCE(dst_cache->reset_ts, jiffies); } /** @@ -102,7 +102,7 @@ int dst_cache_init(struct dst_cache *dst_cache, gfp_t gfp); * @dst_cache: the cache * * No synchronization is enforced: it must be called only when the cache - * is unsed. + * is unused. */ void dst_cache_destroy(struct dst_cache *dst_cache); diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 1b7fae4c6b24..4160731dcb6e 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -198,7 +198,7 @@ static inline struct metadata_dst *__ip_tun_set_dst(__be32 saddr, __be32 daddr, __u8 tos, __u8 ttl, __be16 tp_dst, - __be16 flags, + const unsigned long *flags, __be64 tunnel_id, int md_size) { @@ -215,7 +215,7 @@ static inline struct metadata_dst *__ip_tun_set_dst(__be32 saddr, } static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb, - __be16 flags, + const unsigned long *flags, __be64 tunnel_id, int md_size) { @@ -230,7 +230,7 @@ static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *sad __u8 tos, __u8 ttl, __be16 tp_dst, __be32 label, - __be16 flags, + const unsigned long *flags, __be64 tunnel_id, int md_size) { @@ -243,7 +243,7 @@ static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *sad info = &tun_dst->u.tun_info; info->mode = IP_TUNNEL_INFO_IPV6; - info->key.tun_flags = flags; + ip_tunnel_flags_copy(info->key.tun_flags, flags); info->key.tun_id = tunnel_id; info->key.tp_src = 0; info->key.tp_dst = tp_dst; @@ -259,7 +259,7 @@ static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *sad } static inline struct metadata_dst *ipv6_tun_rx_dst(struct sk_buff *skb, - __be16 flags, + const unsigned long *flags, __be64 tunnel_id, int md_size) { diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 6d1c8541183d..3a9001a042a5 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -24,7 +24,7 @@ struct dst_ops { void (*destroy)(struct dst_entry *); void (*ifdown)(struct dst_entry *, struct net_device *dev); - struct dst_entry * (*negative_advice)(struct dst_entry *); + void (*negative_advice)(struct sock *sk, struct dst_entry *); void (*link_failure)(struct sk_buff *); void (*update_pmtu)(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, diff --git a/include/net/eee.h b/include/net/eee.h index 84837aba3cd9..cfab1b8bc46a 100644 --- a/include/net/eee.h +++ b/include/net/eee.h @@ -13,10 +13,7 @@ struct eee_config { static inline bool eeecfg_mac_can_tx_lpi(const struct eee_config *eeecfg) { /* eee_enabled is the master on/off */ - if (!eeecfg->eee_enabled || !eeecfg->tx_lpi_enabled) - return false; - - return true; + return eeecfg->eee_enabled && eeecfg->tx_lpi_enabled; } static inline void eeecfg_to_eee(struct ethtool_keee *eee, diff --git a/include/net/erspan.h b/include/net/erspan.h index 6cb4cbd6a48f..c6209e7b6c96 100644 --- a/include/net/erspan.h +++ b/include/net/erspan.h @@ -89,7 +89,7 @@ enum erspan_encap_type { ERSPAN_ENCAP_NOVLAN = 0x0, /* originally without VLAN tag */ ERSPAN_ENCAP_ISL = 0x1, /* originally ISL encapsulated */ ERSPAN_ENCAP_8021Q = 0x2, /* originally 802.1Q encapsulated */ - ERSPAN_ENCAP_INFRAME = 0x3, /* VLAN tag perserved in frame */ + ERSPAN_ENCAP_INFRAME = 0x3, /* VLAN tag preserved in frame */ }; #define ERSPAN_V1_MDSIZE 4 @@ -192,7 +192,7 @@ static inline void erspan_build_header(struct sk_buff *skb, enc_type = ERSPAN_ENCAP_NOVLAN; /* If mirrored packet has vlan tag, extract tci and - * perserve vlan header in the mirrored frame. + * preserve vlan header in the mirrored frame. */ if (eth->h_proto == htons(ETH_P_8021Q)) { qp = (struct qtag_prefix *)(skb->data + 2 * ETH_ALEN); diff --git a/include/net/espintcp.h b/include/net/espintcp.h index 0335bbd76552..c70efd704b6d 100644 --- a/include/net/espintcp.h +++ b/include/net/espintcp.h @@ -32,7 +32,7 @@ struct espintcp_ctx { static inline struct espintcp_ctx *espintcp_getctx(const struct sock *sk) { - struct inet_connection_sock *icsk = inet_csk(sk); + const struct inet_connection_sock *icsk = inet_csk(sk); /* RCU is only needed for diag */ return (__force void *)icsk->icsk_ulp_data; diff --git a/include/net/fib_notifier.h b/include/net/fib_notifier.h index 6d59221ff05a..48aad6128fea 100644 --- a/include/net/fib_notifier.h +++ b/include/net/fib_notifier.h @@ -28,7 +28,7 @@ enum fib_event_type { struct fib_notifier_ops { int family; struct list_head list; - unsigned int (*fib_seq_read)(struct net *net); + unsigned int (*fib_seq_read)(const struct net *net); int (*fib_dump)(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); struct module *owner; diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index d17855c52ef9..6e68e359ad18 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -43,6 +43,10 @@ struct fib_rule { struct fib_kuid_range uid_range; struct fib_rule_port_range sport_range; struct fib_rule_port_range dport_range; + u16 sport_mask; + u16 dport_mask; + u8 iif_is_l3_master; + u8 oif_is_l3_master; struct rcu_head rcu; }; @@ -146,6 +150,17 @@ static inline bool fib_rule_port_inrange(const struct fib_rule_port_range *a, ntohs(port) <= a->end; } +static inline bool fib_rule_port_match(const struct fib_rule_port_range *range, + u16 port_mask, __be16 port) +{ + if ((range->start ^ ntohs(port)) & port_mask) + return false; + if (!port_mask && fib_rule_port_range_set(range) && + !fib_rule_port_inrange(range, port)) + return false; + return true; +} + static inline bool fib_rule_port_range_valid(const struct fib_rule_port_range *a) { return a->start != 0 && a->end != 0 && a->end < 0xffff && @@ -159,6 +174,12 @@ static inline bool fib_rule_port_range_compare(struct fib_rule_port_range *a, a->end == b->end; } +static inline bool +fib_rule_port_is_range(const struct fib_rule_port_range *range) +{ + return range->start != range->end; +} + static inline bool fib_rule_requires_fldissect(struct fib_rule *rule) { return rule->iifindex != LOOPBACK_IFINDEX && (rule->ip_proto || @@ -176,12 +197,12 @@ int fib_default_rule_add(struct fib_rules_ops *, u32 pref, u32 table); bool fib_rule_matchall(const struct fib_rule *rule); int fib_rules_dump(struct net *net, struct notifier_block *nb, int family, struct netlink_ext_ack *extack); -unsigned int fib_rules_seq_read(struct net *net, int family); +unsigned int fib_rules_seq_read(const struct net *net, int family); -int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, - struct netlink_ext_ack *extack); -int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, - struct netlink_ext_ack *extack); +int fib_newrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack, bool rtnl_held); +int fib_delrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack, bool rtnl_held); INDIRECT_CALLABLE_DECLARE(int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags)); diff --git a/include/net/flow.h b/include/net/flow.h index 335bbc52171c..a1839c278d87 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -38,6 +38,8 @@ struct flowi_common { __u8 flowic_flags; #define FLOWI_FLAG_ANYSRC 0x01 #define FLOWI_FLAG_KNOWN_NH 0x02 +#define FLOWI_FLAG_L3MDEV_OIF 0x04 +#define FLOWI_FLAG_ANY_SPORT 0x08 __u32 flowic_secid; kuid_t flowic_uid; __u32 flowic_multipath_hash; diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 1a7131d6cb0e..ced79dc8e856 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -7,6 +7,7 @@ #include <linux/siphash.h> #include <linux/string.h> #include <uapi/linux/if_ether.h> +#include <uapi/linux/pkt_cls.h> struct bpf_prog; struct net; @@ -16,7 +17,8 @@ struct sk_buff; * struct flow_dissector_key_control: * @thoff: Transport header offset * @addr_type: Type of key. One of FLOW_DISSECTOR_KEY_* - * @flags: Key flags. Any of FLOW_DIS_(IS_FRAGMENT|FIRST_FRAGENCAPSULATION) + * @flags: Key flags. + * Any of FLOW_DIS_(IS_FRAGMENT|FIRST_FRAG|ENCAPSULATION|F_*) */ struct flow_dissector_key_control { u16 thoff; @@ -24,9 +26,20 @@ struct flow_dissector_key_control { u32 flags; }; -#define FLOW_DIS_IS_FRAGMENT BIT(0) -#define FLOW_DIS_FIRST_FRAG BIT(1) -#define FLOW_DIS_ENCAPSULATION BIT(2) +/* The control flags are kept in sync with TCA_FLOWER_KEY_FLAGS_*, as those + * flags are exposed to userspace in some error paths, ie. unsupported flags. + */ +enum flow_dissector_ctrl_flags { + FLOW_DIS_IS_FRAGMENT = TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT, + FLOW_DIS_FIRST_FRAG = TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST, + FLOW_DIS_F_TUNNEL_CSUM = TCA_FLOWER_KEY_FLAGS_TUNNEL_CSUM, + FLOW_DIS_F_TUNNEL_DONT_FRAGMENT = TCA_FLOWER_KEY_FLAGS_TUNNEL_DONT_FRAGMENT, + FLOW_DIS_F_TUNNEL_OAM = TCA_FLOWER_KEY_FLAGS_TUNNEL_OAM, + FLOW_DIS_F_TUNNEL_CRIT_OPT = TCA_FLOWER_KEY_FLAGS_TUNNEL_CRIT_OPT, + + /* These flags are internal to the kernel */ + FLOW_DIS_ENCAPSULATION = (TCA_FLOWER_KEY_FLAGS_MAX << 1), +}; enum flow_dissect_ret { FLOW_DISSECT_RET_OUT_GOOD, @@ -97,7 +110,7 @@ struct flow_dissector_key_enc_opts { * here but seems difficult to #include */ u8 len; - __be16 dst_opt_type; + u32 dst_opt_type; }; struct flow_dissector_key_keyid { @@ -433,6 +446,8 @@ static inline bool flow_keys_have_l4(const struct flow_keys *keys) } u32 flow_hash_from_keys(struct flow_keys *keys); +u32 flow_hash_from_keys_seed(struct flow_keys *keys, + const siphash_key_t *keyval); void skb_flow_get_icmp_tci(const struct sk_buff *skb, struct flow_dissector_key_icmp *key_icmp, const void *data, int thoff, int hlen); diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 314087a5e181..596ab9791e4d 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -345,7 +345,7 @@ static inline bool flow_action_has_entries(const struct flow_action *action) * flow_offload_has_one_action() - check if exactly one action is present * @action: tc filter flow offload action * - * Returns true if exactly one action is present. + * Return: true if exactly one action is present. */ static inline bool flow_offload_has_one_action(const struct flow_action *action) { @@ -449,6 +449,96 @@ static inline bool flow_rule_match_key(const struct flow_rule *rule, return dissector_uses_key(rule->match.dissector, key); } +/** + * flow_rule_is_supp_control_flags() - check for supported control flags + * @supp_flags: control flags supported by driver + * @ctrl_flags: control flags present in rule + * @extack: The netlink extended ACK for reporting errors. + * + * Return: true if only supported control flags are set, false otherwise. + */ +static inline bool flow_rule_is_supp_control_flags(const u32 supp_flags, + const u32 ctrl_flags, + struct netlink_ext_ack *extack) +{ + if (likely((ctrl_flags & ~supp_flags) == 0)) + return true; + + NL_SET_ERR_MSG_FMT_MOD(extack, + "Unsupported match on control.flags %#x", + ctrl_flags); + + return false; +} + +/** + * flow_rule_is_supp_enc_control_flags() - check for supported control flags + * @supp_enc_flags: encapsulation control flags supported by driver + * @enc_ctrl_flags: encapsulation control flags present in rule + * @extack: The netlink extended ACK for reporting errors. + * + * Return: true if only supported control flags are set, false otherwise. + */ +static inline bool flow_rule_is_supp_enc_control_flags(const u32 supp_enc_flags, + const u32 enc_ctrl_flags, + struct netlink_ext_ack *extack) +{ + if (likely((enc_ctrl_flags & ~supp_enc_flags) == 0)) + return true; + + NL_SET_ERR_MSG_FMT_MOD(extack, + "Unsupported match on enc_control.flags %#x", + enc_ctrl_flags); + + return false; +} + +/** + * flow_rule_has_control_flags() - check for presence of any control flags + * @ctrl_flags: control flags present in rule + * @extack: The netlink extended ACK for reporting errors. + * + * Return: true if control flags are set, false otherwise. + */ +static inline bool flow_rule_has_control_flags(const u32 ctrl_flags, + struct netlink_ext_ack *extack) +{ + return !flow_rule_is_supp_control_flags(0, ctrl_flags, extack); +} + +/** + * flow_rule_has_enc_control_flags() - check for presence of any control flags + * @enc_ctrl_flags: encapsulation control flags present in rule + * @extack: The netlink extended ACK for reporting errors. + * + * Return: true if control flags are set, false otherwise. + */ +static inline bool flow_rule_has_enc_control_flags(const u32 enc_ctrl_flags, + struct netlink_ext_ack *extack) +{ + return !flow_rule_is_supp_enc_control_flags(0, enc_ctrl_flags, extack); +} + +/** + * flow_rule_match_has_control_flags() - match and check for any control flags + * @rule: The flow_rule under evaluation. + * @extack: The netlink extended ACK for reporting errors. + * + * Return: true if control flags are set, false otherwise. + */ +static inline bool flow_rule_match_has_control_flags(struct flow_rule *rule, + struct netlink_ext_ack *extack) +{ + struct flow_match_control match; + + if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) + return false; + + flow_rule_match_control(rule, &match); + + return flow_rule_has_control_flags(match.mask->flags, extack); +} + struct flow_stats { u64 pkts; u64 bytes; @@ -595,6 +685,7 @@ struct flow_cls_common_offload { u32 chain_index; __be16 protocol; u32 prio; + bool skip_sw; struct netlink_ext_ack *extack; }; diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 9ece6e5a3ea8..a03d56765832 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -2,12 +2,20 @@ #ifndef __NET_GENERIC_NETLINK_H #define __NET_GENERIC_NETLINK_H -#include <linux/genetlink.h> +#include <linux/net.h> #include <net/netlink.h> #include <net/net_namespace.h> +#include <uapi/linux/genetlink.h> #define GENLMSG_DEFAULT_SIZE (NLMSG_DEFAULT_SIZE - GENL_HDRLEN) +/* Non-parallel generic netlink requests are serialized by a global lock. */ +void genl_lock(void); +void genl_unlock(void); + +#define MODULE_ALIAS_GENL_FAMILY(family) \ + MODULE_ALIAS_NET_PF_PROTO_NAME(PF_NETLINK, NETLINK_GENERIC, "-family-" family) + /* Binding to multicast group requires %CAP_NET_ADMIN */ #define GENL_MCAST_CAP_NET_ADMIN BIT(0) /* Binding to multicast group requires %CAP_SYS_ADMIN */ @@ -116,7 +124,8 @@ struct genl_family { * @genlhdr: generic netlink message header * @attrs: netlink attributes * @_net: network namespace - * @user_ptr: user pointers + * @ctx: storage space for the use by the family + * @user_ptr: user pointers (deprecated, use ctx instead) * @extack: extended ACK report struct */ struct genl_info { @@ -127,7 +136,10 @@ struct genl_info { struct genlmsghdr * genlhdr; struct nlattr ** attrs; possible_net_t _net; - void * user_ptr[2]; + union { + u8 ctx[NETLINK_CTX_SIZE]; + void * user_ptr[2]; + }; struct netlink_ext_ack *extack; }; @@ -342,7 +354,7 @@ __genlmsg_iput(struct sk_buff *skb, const struct genl_info *info, int flags) * such requests) or a struct initialized by genl_info_init_ntf() * when constructing notifications. * - * Returns pointer to new genetlink header. + * Returns: pointer to new genetlink header. */ static inline void * genlmsg_iput(struct sk_buff *skb, const struct genl_info *info) @@ -354,7 +366,7 @@ genlmsg_iput(struct sk_buff *skb, const struct genl_info *info) * genlmsg_nlhdr - Obtain netlink header from user specified header * @user_hdr: user header as returned from genlmsg_put() * - * Returns pointer to netlink header. + * Returns: pointer to netlink header. */ static inline struct nlmsghdr *genlmsg_nlhdr(void *user_hdr) { @@ -423,7 +435,7 @@ static inline void genl_dump_check_consistent(struct netlink_callback *cb, * @flags: netlink message flags * @cmd: generic netlink command * - * Returns pointer to user specific header + * Returns: pointer to user specific header */ static inline void *genlmsg_put_reply(struct sk_buff *skb, struct genl_info *info, @@ -523,13 +535,12 @@ static inline int genlmsg_multicast(const struct genl_family *family, * @skb: netlink message as socket buffer * @portid: own netlink portid to avoid sending to yourself * @group: offset of multicast group in groups array - * @flags: allocation flags * * This function must hold the RTNL or rcu_read_lock(). */ int genlmsg_multicast_allns(const struct genl_family *family, struct sk_buff *skb, u32 portid, - unsigned int group, gfp_t flags); + unsigned int group); /** * genlmsg_unicast - unicast a netlink message diff --git a/include/net/gre.h b/include/net/gre.h index 4e209708b754..ccd293203284 100644 --- a/include/net/gre.h +++ b/include/net/gre.h @@ -49,67 +49,61 @@ static inline bool netif_is_ip6gretap(const struct net_device *dev) !strcmp(dev->rtnl_link_ops->kind, "ip6gretap"); } -static inline int gre_calc_hlen(__be16 o_flags) +static inline int gre_calc_hlen(const unsigned long *o_flags) { int addend = 4; - if (o_flags & TUNNEL_CSUM) + if (test_bit(IP_TUNNEL_CSUM_BIT, o_flags)) addend += 4; - if (o_flags & TUNNEL_KEY) + if (test_bit(IP_TUNNEL_KEY_BIT, o_flags)) addend += 4; - if (o_flags & TUNNEL_SEQ) + if (test_bit(IP_TUNNEL_SEQ_BIT, o_flags)) addend += 4; return addend; } -static inline __be16 gre_flags_to_tnl_flags(__be16 flags) +static inline void gre_flags_to_tnl_flags(unsigned long *dst, __be16 flags) { - __be16 tflags = 0; - - if (flags & GRE_CSUM) - tflags |= TUNNEL_CSUM; - if (flags & GRE_ROUTING) - tflags |= TUNNEL_ROUTING; - if (flags & GRE_KEY) - tflags |= TUNNEL_KEY; - if (flags & GRE_SEQ) - tflags |= TUNNEL_SEQ; - if (flags & GRE_STRICT) - tflags |= TUNNEL_STRICT; - if (flags & GRE_REC) - tflags |= TUNNEL_REC; - if (flags & GRE_VERSION) - tflags |= TUNNEL_VERSION; - - return tflags; + IP_TUNNEL_DECLARE_FLAGS(res) = { }; + + __assign_bit(IP_TUNNEL_CSUM_BIT, res, flags & GRE_CSUM); + __assign_bit(IP_TUNNEL_ROUTING_BIT, res, flags & GRE_ROUTING); + __assign_bit(IP_TUNNEL_KEY_BIT, res, flags & GRE_KEY); + __assign_bit(IP_TUNNEL_SEQ_BIT, res, flags & GRE_SEQ); + __assign_bit(IP_TUNNEL_STRICT_BIT, res, flags & GRE_STRICT); + __assign_bit(IP_TUNNEL_REC_BIT, res, flags & GRE_REC); + __assign_bit(IP_TUNNEL_VERSION_BIT, res, flags & GRE_VERSION); + + ip_tunnel_flags_copy(dst, res); } -static inline __be16 gre_tnl_flags_to_gre_flags(__be16 tflags) +static inline __be16 gre_tnl_flags_to_gre_flags(const unsigned long *tflags) { __be16 flags = 0; - if (tflags & TUNNEL_CSUM) + if (test_bit(IP_TUNNEL_CSUM_BIT, tflags)) flags |= GRE_CSUM; - if (tflags & TUNNEL_ROUTING) + if (test_bit(IP_TUNNEL_ROUTING_BIT, tflags)) flags |= GRE_ROUTING; - if (tflags & TUNNEL_KEY) + if (test_bit(IP_TUNNEL_KEY_BIT, tflags)) flags |= GRE_KEY; - if (tflags & TUNNEL_SEQ) + if (test_bit(IP_TUNNEL_SEQ_BIT, tflags)) flags |= GRE_SEQ; - if (tflags & TUNNEL_STRICT) + if (test_bit(IP_TUNNEL_STRICT_BIT, tflags)) flags |= GRE_STRICT; - if (tflags & TUNNEL_REC) + if (test_bit(IP_TUNNEL_REC_BIT, tflags)) flags |= GRE_REC; - if (tflags & TUNNEL_VERSION) + if (test_bit(IP_TUNNEL_VERSION_BIT, tflags)) flags |= GRE_VERSION; return flags; } static inline void gre_build_header(struct sk_buff *skb, int hdr_len, - __be16 flags, __be16 proto, + const unsigned long *flags, __be16 proto, __be32 key, __be32 seq) { + IP_TUNNEL_DECLARE_FLAGS(cond) = { }; struct gre_base_hdr *greh; skb_push(skb, hdr_len); @@ -120,18 +114,22 @@ static inline void gre_build_header(struct sk_buff *skb, int hdr_len, greh->flags = gre_tnl_flags_to_gre_flags(flags); greh->protocol = proto; - if (flags & (TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_SEQ)) { + __set_bit(IP_TUNNEL_KEY_BIT, cond); + __set_bit(IP_TUNNEL_CSUM_BIT, cond); + __set_bit(IP_TUNNEL_SEQ_BIT, cond); + + if (ip_tunnel_flags_intersect(flags, cond)) { __be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4); - if (flags & TUNNEL_SEQ) { + if (test_bit(IP_TUNNEL_SEQ_BIT, flags)) { *ptr = seq; ptr--; } - if (flags & TUNNEL_KEY) { + if (test_bit(IP_TUNNEL_KEY_BIT, flags)) { *ptr = key; ptr--; } - if (flags & TUNNEL_CSUM && + if (test_bit(IP_TUNNEL_CSUM_BIT, flags) && !(skb_shinfo(skb)->gso_type & (SKB_GSO_GRE | SKB_GSO_GRE_CSUM))) { *ptr = 0; diff --git a/include/net/gro.h b/include/net/gro.h index 50f1e403dbbb..22d3a69e4404 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -11,6 +11,9 @@ #include <net/udp.h> #include <net/hotdata.h> +/* This should be increased if a protocol with a bigger head is added. */ +#define GRO_MAX_HEAD (MAX_HEADER + 128) + struct napi_gro_cb { union { struct { @@ -36,15 +39,14 @@ struct napi_gro_cb { /* This is non-zero if the packet cannot be merged with the new skb. */ u16 flush; - /* Save the IP ID here and check when we get to the transport layer */ - u16 flush_id; - /* Number of segments aggregated. */ u16 count; /* Used in ipv6_gro_receive() and foo-over-udp and esp-in-udp */ u16 proto; + u16 pad; + /* Used in napi_gro_cb::free */ #define NAPI_GRO_FREE 1 #define NAPI_GRO_FREE_STOLEN_HEAD 2 @@ -75,8 +77,8 @@ struct napi_gro_cb { /* Used in GRE, set in fou/gue_gro_receive */ u8 is_fou:1; - /* Used to determine if flush_id can be ignored */ - u8 is_atomic:1; + /* Used to determine if ipid_offset can be ignored */ + u8 ip_fixedid:1; /* Number of gro_receive callbacks this packet already went through */ u8 recursion_counter:4; @@ -87,6 +89,15 @@ struct napi_gro_cb { /* used to support CHECKSUM_COMPLETE for tunneling protocols */ __wsum csum; + + /* L3 offsets */ + union { + struct { + u16 network_offset; + u16 inner_network_offset; + }; + u16 network_offsets[2]; + }; }; #define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb) @@ -172,12 +183,17 @@ static inline void *skb_gro_header(struct sk_buff *skb, unsigned int hlen, return ptr; } +static inline int skb_gro_receive_network_offset(const struct sk_buff *skb) +{ + return NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark]; +} + static inline void *skb_gro_network_header(const struct sk_buff *skb) { if (skb_gro_may_pull(skb, skb_gro_offset(skb))) - return skb_gro_header_fast(skb, skb_network_offset(skb)); + return skb_gro_header_fast(skb, skb_gro_receive_network_offset(skb)); - return skb_network_header(skb); + return skb->data + skb_gro_receive_network_offset(skb); } static inline __wsum inet_gro_compute_pseudo(const struct sk_buff *skb, @@ -428,29 +444,111 @@ static inline __wsum ip6_gro_compute_pseudo(const struct sk_buff *skb, skb_gro_len(skb), proto, 0)); } +static inline int inet_gro_flush(const struct iphdr *iph, const struct iphdr *iph2, + struct sk_buff *p, bool outer) +{ + const u32 id = ntohl(*(__be32 *)&iph->id); + const u32 id2 = ntohl(*(__be32 *)&iph2->id); + const u16 ipid_offset = (id >> 16) - (id2 >> 16); + const u16 count = NAPI_GRO_CB(p)->count; + const u32 df = id & IP_DF; + int flush; + + /* All fields must match except length and checksum. */ + flush = (iph->ttl ^ iph2->ttl) | (iph->tos ^ iph2->tos) | (df ^ (id2 & IP_DF)); + + if (flush | (outer && df)) + return flush; + + /* When we receive our second frame we can make a decision on if we + * continue this flow as an atomic flow with a fixed ID or if we use + * an incrementing ID. + */ + if (count == 1 && df && !ipid_offset) + NAPI_GRO_CB(p)->ip_fixedid = true; + + return ipid_offset ^ (count * !NAPI_GRO_CB(p)->ip_fixedid); +} + +static inline int ipv6_gro_flush(const struct ipv6hdr *iph, const struct ipv6hdr *iph2) +{ + /* <Version:4><Traffic_Class:8><Flow_Label:20> */ + __be32 first_word = *(__be32 *)iph ^ *(__be32 *)iph2; + + /* Flush if Traffic Class fields are different. */ + return !!((first_word & htonl(0x0FF00000)) | + (__force __be32)(iph->hop_limit ^ iph2->hop_limit)); +} + +static inline int __gro_receive_network_flush(const void *th, const void *th2, + struct sk_buff *p, const u16 diff, + bool outer) +{ + const void *nh = th - diff; + const void *nh2 = th2 - diff; + + if (((struct iphdr *)nh)->version == 6) + return ipv6_gro_flush(nh, nh2); + else + return inet_gro_flush(nh, nh2, p, outer); +} + +static inline int gro_receive_network_flush(const void *th, const void *th2, + struct sk_buff *p) +{ + const bool encap_mark = NAPI_GRO_CB(p)->encap_mark; + int off = skb_transport_offset(p); + int flush; + + flush = __gro_receive_network_flush(th, th2, p, off - NAPI_GRO_CB(p)->network_offset, encap_mark); + if (encap_mark) + flush |= __gro_receive_network_flush(th, th2, p, off - NAPI_GRO_CB(p)->inner_network_offset, false); + + return flush; +} + int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb); +int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb); +void __gro_flush(struct gro_node *gro, bool flush_old); + +static inline void gro_flush(struct gro_node *gro, bool flush_old) +{ + if (!gro->bitmask) + return; + + __gro_flush(gro, flush_old); +} + +static inline void napi_gro_flush(struct napi_struct *napi, bool flush_old) +{ + gro_flush(&napi->gro, flush_old); +} /* Pass the currently batched GRO_NORMAL SKBs up to the stack. */ -static inline void gro_normal_list(struct napi_struct *napi) +static inline void gro_normal_list(struct gro_node *gro) { - if (!napi->rx_count) + if (!gro->rx_count) return; - netif_receive_skb_list_internal(&napi->rx_list); - INIT_LIST_HEAD(&napi->rx_list); - napi->rx_count = 0; + netif_receive_skb_list_internal(&gro->rx_list); + INIT_LIST_HEAD(&gro->rx_list); + gro->rx_count = 0; } /* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded, * pass the whole batch up to the stack. */ -static inline void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb, int segs) +static inline void gro_normal_one(struct gro_node *gro, struct sk_buff *skb, + int segs) { - list_add_tail(&skb->list, &napi->rx_list); - napi->rx_count += segs; - if (napi->rx_count >= READ_ONCE(net_hotdata.gro_normal_batch)) - gro_normal_list(napi); + list_add_tail(&skb->list, &gro->rx_list); + gro->rx_count += segs; + if (gro->rx_count >= READ_ONCE(net_hotdata.gro_normal_batch)) + gro_normal_list(gro); } +void gro_init(struct gro_node *gro); +void gro_cleanup(struct gro_node *gro); + /* This function is the alternative of 'inet_iif' and 'inet_sdif' * functions in case we can not rely on fields of IPCB. * diff --git a/include/net/gtp.h b/include/net/gtp.h index 2a503f035d18..c0253c8702d0 100644 --- a/include/net/gtp.h +++ b/include/net/gtp.h @@ -78,4 +78,9 @@ static inline bool netif_is_gtp(const struct net_device *dev) #define GTP1_F_EXTHDR 0x04 #define GTP1_F_MASK 0x07 +struct gtp_ext_hdr { + __u8 len; + __u8 data[]; +}; + #endif diff --git a/include/net/hotdata.h b/include/net/hotdata.h index 003667a1efd6..fda94b2647ff 100644 --- a/include/net/hotdata.h +++ b/include/net/hotdata.h @@ -23,7 +23,6 @@ struct net_hotdata { struct net_offload udpv6_offload; #endif struct list_head offload_base; - struct list_head ptype_all; struct kmem_cache *skbuff_cache; struct kmem_cache *skbuff_fclone_cache; struct kmem_cache *skb_small_head_cache; @@ -38,6 +37,9 @@ struct net_hotdata { int max_backlog; int dev_tx_weight; int dev_rx_weight; + int sysctl_max_skb_frags; + int sysctl_skb_defer_max; + int sysctl_mem_pcpu_rsv; }; #define inet_ehash_secret net_hotdata.tcp_protocol.secret diff --git a/include/net/hwbm.h b/include/net/hwbm.h index aa495decec35..bdbe91c609ff 100644 --- a/include/net/hwbm.h +++ b/include/net/hwbm.h @@ -11,9 +11,9 @@ struct hwbm_pool { int frag_size; /* Number of buffers currently used by this pool */ int buf_num; - /* constructor called during alocation */ + /* constructor called during allocation */ int (*construct)(struct hwbm_pool *bm_pool, void *buf); - /* protect acces to the buffer counter*/ + /* protect access to the buffer counter*/ struct mutex buf_lock; /* private data */ void *priv; diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h index 925bac726a92..813e163ce27c 100644 --- a/include/net/ieee80211_radiotap.h +++ b/include/net/ieee80211_radiotap.h @@ -18,31 +18,33 @@ #define __RADIOTAP_H #include <linux/kernel.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /** * struct ieee80211_radiotap_header - base radiotap header */ struct ieee80211_radiotap_header { - /** - * @it_version: radiotap version, always 0 - */ - uint8_t it_version; - - /** - * @it_pad: padding (or alignment) - */ - uint8_t it_pad; - - /** - * @it_len: overall radiotap header length - */ - __le16 it_len; - - /** - * @it_present: (first) present word - */ - __le32 it_present; + __struct_group(ieee80211_radiotap_header_fixed, hdr, __packed, + /** + * @it_version: radiotap version, always 0 + */ + uint8_t it_version; + + /** + * @it_pad: padding (or alignment) + */ + uint8_t it_pad; + + /** + * @it_len: overall radiotap header length + */ + __le16 it_len; + + /** + * @it_present: (first) present word + */ + __le32 it_present; + ); /** * @it_optional: all remaining presence bitmaps @@ -50,6 +52,9 @@ struct ieee80211_radiotap_header { __le32 it_optional[]; } __packed; +static_assert(offsetof(struct ieee80211_radiotap_header, it_optional) == sizeof(struct ieee80211_radiotap_header_fixed), + "struct member likely outside of __struct_group()"); + /* version is always 0 */ #define PKTHDR_RADIOTAP_VERSION 0 @@ -582,6 +587,7 @@ enum ieee80211_radiotap_eht_usig_tb { /** * ieee80211_get_radiotap_len - get radiotap header length * @data: pointer to the header + * Return: the radiotap header length */ static inline u16 ieee80211_get_radiotap_len(const char *data) { diff --git a/include/net/ieee8021q.h b/include/net/ieee8021q.h new file mode 100644 index 000000000000..8bfe903dd3d0 --- /dev/null +++ b/include/net/ieee8021q.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024 Pengutronix, Oleksij Rempel <kernel@pengutronix.de> */ + +#ifndef _NET_IEEE8021Q_H +#define _NET_IEEE8021Q_H + +#include <linux/errno.h> + +/** + * enum ieee8021q_traffic_type - 802.1Q traffic type priority values (802.1Q-2022) + * + * @IEEE8021Q_TT_BK: Background + * @IEEE8021Q_TT_BE: Best Effort (default). According to 802.1Q-2022, BE is 0 + * but has higher priority than BK which is 1. + * @IEEE8021Q_TT_EE: Excellent Effort + * @IEEE8021Q_TT_CA: Critical Applications + * @IEEE8021Q_TT_VI: Video, < 100 ms latency and jitter + * @IEEE8021Q_TT_VO: Voice, < 10 ms latency and jitter + * @IEEE8021Q_TT_IC: Internetwork Control + * @IEEE8021Q_TT_NC: Network Control + */ +enum ieee8021q_traffic_type { + IEEE8021Q_TT_BK = 0, + IEEE8021Q_TT_BE = 1, + IEEE8021Q_TT_EE = 2, + IEEE8021Q_TT_CA = 3, + IEEE8021Q_TT_VI = 4, + IEEE8021Q_TT_VO = 5, + IEEE8021Q_TT_IC = 6, + IEEE8021Q_TT_NC = 7, + + /* private: */ + IEEE8021Q_TT_MAX, +}; + +#define SIMPLE_IETF_DSCP_TO_IEEE8021Q_TT(dscp) ((dscp >> 3) & 0x7) + +#if IS_ENABLED(CONFIG_NET_IEEE8021Q_HELPERS) + +int ietf_dscp_to_ieee8021q_tt(u8 dscp); +int ieee8021q_tt_to_tc(enum ieee8021q_traffic_type tt, unsigned int num_queues); + +#else + +static inline int ietf_dscp_to_ieee8021q_tt(u8 dscp) +{ + return -EOPNOTSUPP; +} + +static inline int ieee8021q_tt_to_tc(enum ieee8021q_traffic_type tt, + unsigned int num_queues) +{ + return -EOPNOTSUPP; +} + +#endif +#endif /* _NET_IEEE8021Q_H */ diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h index 025bd8d3c769..745891d2e113 100644 --- a/include/net/inet6_connection_sock.h +++ b/include/net/inet6_connection_sock.h @@ -21,8 +21,6 @@ struct sockaddr; struct dst_entry *inet6_csk_route_req(const struct sock *sk, struct flowi6 *fl6, const struct request_sock *req, u8 proto); -void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr); - int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl); struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu); diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 533a7337865a..c32878c69179 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -40,7 +40,7 @@ static inline unsigned int __inet6_ehashfn(const u32 lhash, * * The sockhash lock must be held as a reader here. */ -struct sock *__inet6_lookup_established(struct net *net, +struct sock *__inet6_lookup_established(const struct net *net, struct inet_hashinfo *hashinfo, const struct in6_addr *saddr, const __be16 sport, @@ -56,7 +56,7 @@ inet6_ehashfn_t inet6_ehashfn; INDIRECT_CALLABLE_DECLARE(inet6_ehashfn_t udp6_ehashfn); -struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, +struct sock *inet6_lookup_reuseport(const struct net *net, struct sock *sk, struct sk_buff *skb, int doff, const struct in6_addr *saddr, __be16 sport, @@ -64,7 +64,7 @@ struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, unsigned short hnum, inet6_ehashfn_t *ehashfn); -struct sock *inet6_lookup_listener(struct net *net, +struct sock *inet6_lookup_listener(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -73,7 +73,7 @@ struct sock *inet6_lookup_listener(struct net *net, const unsigned short hnum, const int dif, const int sdif); -struct sock *inet6_lookup_run_sk_lookup(struct net *net, +struct sock *inet6_lookup_run_sk_lookup(const struct net *net, int protocol, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -82,7 +82,7 @@ struct sock *inet6_lookup_run_sk_lookup(struct net *net, const u16 hnum, const int dif, inet6_ehashfn_t *ehashfn); -static inline struct sock *__inet6_lookup(struct net *net, +static inline struct sock *__inet6_lookup(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -150,7 +150,7 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo, int iif, int sdif, bool *refcounted) { - struct net *net = dev_net(skb_dst(skb)->dev); + struct net *net = dev_net_rcu(skb_dst(skb)->dev); const struct ipv6hdr *ip6h = ipv6_hdr(skb); struct sock *sk; @@ -167,7 +167,7 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo, iif, sdif, refcounted); } -struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, +struct sock *inet6_lookup(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const __be16 dport, @@ -175,7 +175,7 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, int inet6_hash(struct sock *sk); -static inline bool inet6_match(struct net *net, const struct sock *sk, +static inline bool inet6_match(const struct net *net, const struct sock *sk, const struct in6_addr *saddr, const struct in6_addr *daddr, const __portpair ports, diff --git a/include/net/inet_common.h b/include/net/inet_common.h index f50a644d87a9..c17a6585d0b0 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -29,8 +29,8 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags, int is_sendmsg); 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, - bool kern); +int inet_accept(struct socket *sock, struct socket *newsock, + struct proto_accept_arg *arg); void __inet_accept(struct socket *sock, struct socket *newsock, struct sock *newsk); int inet_send_prepare(struct sock *sk); diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index ccf171f7eb60..1735db332aab 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -44,12 +44,10 @@ struct inet_connection_sock_af_ops { struct request_sock *req_unhash, bool *own_req); u16 net_header_len; - u16 sockaddr_len; int (*setsockopt)(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int (*getsockopt)(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); - void (*addr2sockaddr)(struct sock *sk, struct sockaddr *); void (*mtu_reduced)(struct sock *sk); }; @@ -58,7 +56,6 @@ struct inet_connection_sock_af_ops { * @icsk_accept_queue: FIFO of established children * @icsk_bind_hash: Bind node * @icsk_bind2_hash: Bind node in the bhash2 table - * @icsk_timeout: Timeout * @icsk_retransmit_timer: Resend (no ack) * @icsk_rto: Retransmit timeout * @icsk_pmtu_cookie Last pmtu seen by socket @@ -66,7 +63,6 @@ struct inet_connection_sock_af_ops { * @icsk_af_ops Operations which are AF_INET{4,6} specific * @icsk_ulp_ops Pluggable ULP control hook * @icsk_ulp_data ULP private data - * @icsk_clean_acked Clean acked data hook * @icsk_ca_state: Congestion control state * @icsk_retransmits: Number of unrecovered [RTO] timeouts * @icsk_pending: Scheduled timer event @@ -85,18 +81,17 @@ struct inet_connection_sock { struct request_sock_queue icsk_accept_queue; struct inet_bind_bucket *icsk_bind_hash; struct inet_bind2_bucket *icsk_bind2_hash; - unsigned long icsk_timeout; struct timer_list icsk_retransmit_timer; struct timer_list icsk_delack_timer; __u32 icsk_rto; __u32 icsk_rto_min; + u32 icsk_rto_max; __u32 icsk_delack_max; __u32 icsk_pmtu_cookie; const struct tcp_congestion_ops *icsk_ca_ops; const struct inet_connection_sock_af_ops *icsk_af_ops; const struct tcp_ulp_ops *icsk_ulp_ops; void __rcu *icsk_ulp_data; - void (*icsk_clean_acked)(struct sock *sk, u32 acked_seq); unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu); __u8 icsk_ca_state:5, icsk_ca_initialized:1, @@ -116,8 +111,8 @@ struct inet_connection_sock { #define ATO_BITS 8 __u32 ato:ATO_BITS, /* Predicted tick of soft clock */ lrcv_flowlabel:20, /* last received ipv6 flowlabel */ - unused:4; - unsigned long timeout; /* Currently scheduled timeout */ + dst_quick_ack:1, /* cache dst RTAX_QUICKACK */ + unused:3; __u32 lrcvtime; /* timestamp of last received data packet */ __u16 last_seg_size; /* Size of last incoming segment */ __u16 rcv_mss; /* MSS used for delayed ACK decisions */ @@ -147,10 +142,7 @@ struct inet_connection_sock { #define ICSK_TIME_LOSS_PROBE 5 /* Tail loss probe timer */ #define ICSK_TIME_REO_TIMEOUT 6 /* Reordering timer */ -static inline struct inet_connection_sock *inet_csk(const struct sock *sk) -{ - return (struct inet_connection_sock *)sk; -} +#define inet_csk(ptr) container_of_const(ptr, struct inet_connection_sock, icsk_inet.sk) static inline void *inet_csk_ca(const struct sock *sk) { @@ -192,20 +184,29 @@ static inline void inet_csk_delack_init(struct sock *sk) memset(&inet_csk(sk)->icsk_ack, 0, sizeof(inet_csk(sk)->icsk_ack)); } -void inet_csk_delete_keepalive_timer(struct sock *sk); -void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long timeout); +static inline unsigned long +icsk_timeout(const struct inet_connection_sock *icsk) +{ + return READ_ONCE(icsk->icsk_retransmit_timer.expires); +} + +static inline unsigned long +icsk_delack_timeout(const struct inet_connection_sock *icsk) +{ + return READ_ONCE(icsk->icsk_delack_timer.expires); +} static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what) { struct inet_connection_sock *icsk = inet_csk(sk); if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) { - icsk->icsk_pending = 0; + smp_store_release(&icsk->icsk_pending, 0); #ifdef INET_CSK_CLEAR_TIMERS sk_stop_timer(sk, &icsk->icsk_retransmit_timer); #endif } else if (what == ICSK_TIME_DACK) { - icsk->icsk_ack.pending = 0; + smp_store_release(&icsk->icsk_ack.pending, 0); icsk->icsk_ack.retry = 0; #ifdef INET_CSK_CLEAR_TIMERS sk_stop_timer(sk, &icsk->icsk_delack_timer); @@ -230,15 +231,15 @@ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what, when = max_when; } + when += jiffies; if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0 || what == ICSK_TIME_LOSS_PROBE || what == ICSK_TIME_REO_TIMEOUT) { - icsk->icsk_pending = what; - icsk->icsk_timeout = jiffies + when; - sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout); + smp_store_release(&icsk->icsk_pending, what); + sk_reset_timer(sk, &icsk->icsk_retransmit_timer, when); } else if (what == ICSK_TIME_DACK) { - icsk->icsk_ack.pending |= ICSK_ACK_TIMER; - icsk->icsk_ack.timeout = jiffies + when; - sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout); + smp_store_release(&icsk->icsk_ack.pending, + icsk->icsk_ack.pending | ICSK_ACK_TIMER); + sk_reset_timer(sk, &icsk->icsk_delack_timer, when); } else { pr_debug("inet_csk BUG: unknown timer value\n"); } @@ -253,7 +254,7 @@ inet_csk_rto_backoff(const struct inet_connection_sock *icsk, return (unsigned long)min_t(u64, when, max_when); } -struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern); +struct sock *inet_csk_accept(struct sock *sk, struct proto_accept_arg *arg); int inet_csk_get_port(struct sock *sk, unsigned short snum); @@ -266,7 +267,7 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, struct sock *inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, struct sock *child); -void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, +bool inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, unsigned long timeout); struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child, struct request_sock *req, @@ -284,7 +285,7 @@ static inline int inet_csk_reqsk_queue_len(const struct sock *sk) static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) { - return inet_csk_reqsk_queue_len(sk) >= sk->sk_max_ack_backlog; + return inet_csk_reqsk_queue_len(sk) > READ_ONCE(sk->sk_max_ack_backlog); } bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); @@ -320,8 +321,6 @@ static inline __poll_t inet_csk_listen_poll(const struct sock *sk) int inet_csk_listen_start(struct sock *sk); void inet_csk_listen_stop(struct sock *sk); -void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr); - /* update the fast reuse flag when adding a socket */ void inet_csk_update_fastreuse(struct inet_bind_bucket *tb, struct sock *sk); diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 153960663ce4..0eccd9c3a883 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -76,7 +76,7 @@ struct frag_v6_compare_key { * @stamp: timestamp of the last received fragment * @len: total length of the original datagram * @meat: length of received fragments so far - * @mono_delivery_time: stamp has a mono delivery time (EDT) + * @tstamp_type: stamp has a mono delivery time (EDT) * @flags: fragment queue flags * @max_size: maximum received fragment size * @fqdir: pointer to struct fqdir @@ -97,7 +97,7 @@ struct inet_frag_queue { ktime_t stamp; int len; int meat; - u8 mono_delivery_time; + u8 tstamp_type; __u8 flags; u16 max_size; struct fqdir *fqdir; @@ -137,7 +137,7 @@ static inline void fqdir_pre_exit(struct fqdir *fqdir) } void fqdir_exit(struct fqdir *fqdir); -void inet_frag_kill(struct inet_frag_queue *q); +void inet_frag_kill(struct inet_frag_queue *q, int *refs); void inet_frag_destroy(struct inet_frag_queue *q); struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key); @@ -145,9 +145,9 @@ struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key); unsigned int inet_frag_rbtree_purge(struct rb_root *root, enum skb_drop_reason reason); -static inline void inet_frag_put(struct inet_frag_queue *q) +static inline void inet_frag_putn(struct inet_frag_queue *q, int refs) { - if (refcount_dec_and_test(&q->refcnt)) + if (refs && refcount_sub_and_test(refs, &q->refcnt)) inet_frag_destroy(q); } diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 7f1b38458743..4564b5d348b1 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -89,6 +89,7 @@ struct inet_bind_bucket { bool fast_ipv6_only; struct hlist_node node; struct hlist_head bhash2; + struct rcu_head rcu; }; struct inet_bind2_bucket { @@ -174,14 +175,9 @@ struct inet_hashinfo { bool pernet; } ____cacheline_aligned_in_smp; -static inline struct inet_hashinfo *tcp_or_dccp_get_hashinfo(const struct sock *sk) +static inline struct inet_hashinfo *tcp_get_hashinfo(const struct sock *sk) { -#if IS_ENABLED(CONFIG_IP_DCCP) - return sk->sk_prot->h.hashinfo ? : - sock_net(sk)->ipv4.tcp_death_row.hashinfo; -#else return sock_net(sk)->ipv4.tcp_death_row.hashinfo; -#endif } static inline struct inet_listen_hashbucket * @@ -226,8 +222,7 @@ struct inet_bind_bucket * inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net, struct inet_bind_hashbucket *head, const unsigned short snum, int l3mdev); -void inet_bind_bucket_destroy(struct kmem_cache *cachep, - struct inet_bind_bucket *tb); +void inet_bind_bucket_destroy(struct inet_bind_bucket *tb); bool inet_bind_bucket_match(const struct inet_bind_bucket *tb, const struct net *net, unsigned short port, @@ -304,7 +299,7 @@ int __inet_hash(struct sock *sk, struct sock *osk); int inet_hash(struct sock *sk); void inet_unhash(struct sock *sk); -struct sock *__inet_lookup_listener(struct net *net, +struct sock *__inet_lookup_listener(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const __be32 saddr, const __be16 sport, @@ -351,7 +346,7 @@ static inline struct sock *inet_lookup_listener(struct net *net, ((__force __u64)(__be32)(__saddr))) #endif /* __BIG_ENDIAN */ -static inline bool inet_match(struct net *net, const struct sock *sk, +static inline bool inet_match(const struct net *net, const struct sock *sk, const __addrpair cookie, const __portpair ports, int dif, int sdif) { @@ -368,7 +363,7 @@ static inline bool inet_match(struct net *net, const struct sock *sk, /* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need * not check it for lookups anymore, thanks Alexey. -DaveM */ -struct sock *__inet_lookup_established(struct net *net, +struct sock *__inet_lookup_established(const struct net *net, struct inet_hashinfo *hashinfo, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 hnum, @@ -382,13 +377,13 @@ inet_ehashfn_t inet_ehashfn; INDIRECT_CALLABLE_DECLARE(inet_ehashfn_t udp_ehashfn); -struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk, +struct sock *inet_lookup_reuseport(const struct net *net, struct sock *sk, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, __be32 daddr, unsigned short hnum, inet_ehashfn_t *ehashfn); -struct sock *inet_lookup_run_sk_lookup(struct net *net, +struct sock *inet_lookup_run_sk_lookup(const struct net *net, int protocol, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, @@ -492,7 +487,7 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo, const int sdif, bool *refcounted) { - struct net *net = dev_net(skb_dst(skb)->dev); + struct net *net = dev_net_rcu(skb_dst(skb)->dev); const struct iphdr *iph = ip_hdr(skb); struct sock *sk; @@ -527,9 +522,12 @@ static inline void sk_rcv_saddr_set(struct sock *sk, __be32 addr) int __inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk, u64 port_offset, + u32 hash_port0, int (*check_established)(struct inet_timewait_death_row *, struct sock *, __u16, - struct inet_timewait_sock **)); + struct inet_timewait_sock **, + bool rcu_lookup, + u32 hash)); 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 f9ddd47dc4f8..1086256549fa 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -19,6 +19,7 @@ #include <linux/netdevice.h> #include <net/flow.h> +#include <net/inet_dscp.h> #include <net/sock.h> #include <net/request_sock.h> #include <net/netns/hash.h> @@ -150,7 +151,8 @@ static inline bool inet_bound_dev_eq(bool l3mdev_accept, int bound_dev_if, return bound_dev_if == dif || bound_dev_if == sdif; } -static inline bool inet_sk_bound_dev_eq(struct net *net, int bound_dev_if, +static inline bool inet_sk_bound_dev_eq(const struct net *net, + int bound_dev_if, int dif, int sdif) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) @@ -171,8 +173,9 @@ struct inet_cork { u8 tx_flags; __u8 ttl; __s16 tos; - char priority; + u32 priority; __u16 gso_size; + u32 ts_opt_id; u64 transmit_time; u32 mark; }; @@ -240,7 +243,8 @@ struct inet_sock { struct inet_cork_full cork; }; -#define IPCORK_OPT 1 /* ip-options has been held in ipcork.opt */ +#define IPCORK_OPT 1 /* ip-options has been held in ipcork.opt */ +#define IPCORK_TS_OPT_ID 2 /* ts_opt_id field is valid, overriding sk_tskey */ enum { INET_FLAGS_PKTINFO = 0, @@ -299,6 +303,11 @@ static inline unsigned long inet_cmsg_flags(const struct inet_sock *inet) return READ_ONCE(inet->inet_flags) & IP_CMSG_ALL; } +static inline dscp_t inet_sk_dscp(const struct inet_sock *inet) +{ + return inet_dsfield_to_dscp(READ_ONCE(inet->tos)); +} + #define inet_test_bit(nr, sk) \ test_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) #define inet_set_bit(nr, sk) \ @@ -318,8 +327,10 @@ static inline unsigned long inet_cmsg_flags(const struct inet_sock *inet) static inline struct sock *sk_to_full_sk(struct sock *sk) { #ifdef CONFIG_INET - if (sk && sk->sk_state == TCP_NEW_SYN_RECV) + if (sk && READ_ONCE(sk->sk_state) == TCP_NEW_SYN_RECV) sk = inet_reqsk(sk)->rsk_listener; + if (sk && READ_ONCE(sk->sk_state) == TCP_TIME_WAIT) + sk = NULL; #endif return sk; } @@ -328,8 +339,10 @@ static inline struct sock *sk_to_full_sk(struct sock *sk) static inline const struct sock *sk_const_to_full_sk(const struct sock *sk) { #ifdef CONFIG_INET - if (sk && sk->sk_state == TCP_NEW_SYN_RECV) + if (sk && READ_ONCE(sk->sk_state) == TCP_NEW_SYN_RECV) sk = ((const struct request_sock *)sk)->rsk_listener; + if (sk && READ_ONCE(sk->sk_state) == TCP_TIME_WAIT) + sk = NULL; #endif return sk; } diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index f28da08a37b4..67a313575780 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -45,6 +45,8 @@ struct inet_timewait_sock { #define tw_node __tw_common.skc_nulls_node #define tw_bind_node __tw_common.skc_bind_node #define tw_refcnt __tw_common.skc_refcnt +#define tw_tx_queue_mapping __tw_common.skc_tx_queue_mapping +#define tw_rx_queue_mapping __tw_common.skc_rx_queue_mapping #define tw_hash __tw_common.skc_hash #define tw_prot __tw_common.skc_prot #define tw_net __tw_common.skc_net @@ -58,7 +60,7 @@ struct inet_timewait_sock { #define tw_dr __tw_common.skc_tw_dr __u32 tw_mark; - volatile unsigned char tw_substate; + unsigned char tw_substate; unsigned char tw_rcv_wscale; /* Socket demultiplex comparisons on incoming packets. */ @@ -72,6 +74,10 @@ struct inet_timewait_sock { tw_tos : 8; u32 tw_txhash; u32 tw_priority; + /** + * @tw_reuse_stamp: Time of entry into %TCP_TIME_WAIT state in msec. + */ + u32 tw_entry_stamp; struct timer_list tw_timer; struct inet_bind_bucket *tw_tb; struct inet_bind2_bucket *tw_tb2; @@ -93,17 +99,14 @@ 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_hashdance_schedule(struct inet_timewait_sock *tw, + struct sock *sk, + struct inet_hashinfo *hashinfo, + int timeo); void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm); -static inline void inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo) -{ - __inet_twsk_schedule(tw, timeo, false); -} - static inline void inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo) { __inet_twsk_schedule(tw, timeo, true); @@ -111,7 +114,7 @@ static inline void inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo void inet_twsk_deschedule_put(struct inet_timewait_sock *tw); -void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family); +void inet_twsk_purge(struct inet_hashinfo *hashinfo); static inline struct net *twsk_net(const struct inet_timewait_sock *twsk) diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 74ff688568a0..f475757daafb 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -96,30 +96,28 @@ static inline struct in6_addr *inetpeer_get_addr_v6(struct inetpeer_addr *iaddr) /* can be called with or without local BH being disabled */ struct inet_peer *inet_getpeer(struct inet_peer_base *base, - const struct inetpeer_addr *daddr, - int create); + const struct inetpeer_addr *daddr); static inline struct inet_peer *inet_getpeer_v4(struct inet_peer_base *base, __be32 v4daddr, - int vif, int create) + int vif) { struct inetpeer_addr daddr; daddr.a4.addr = v4daddr; daddr.a4.vif = vif; daddr.family = AF_INET; - return inet_getpeer(base, &daddr, create); + return inet_getpeer(base, &daddr); } static inline struct inet_peer *inet_getpeer_v6(struct inet_peer_base *base, - const struct in6_addr *v6daddr, - int create) + const struct in6_addr *v6daddr) { struct inetpeer_addr daddr; daddr.a6 = *v6daddr; daddr.family = AF_INET6; - return inet_getpeer(base, &daddr, create); + return inet_getpeer(base, &daddr); } static inline int inetpeer_addr_cmp(const struct inetpeer_addr *a, diff --git a/include/net/ip.h b/include/net/ip.h index 25cb688bdc62..47ed6d23853d 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -33,6 +33,7 @@ #include <net/flow_dissector.h> #include <net/netns/hash.h> #include <net/lwtunnel.h> +#include <net/inet_dscp.h> #define IPV4_MAX_PMTU 65535U /* RFC 2675, Section 5.1 */ #define IPV4_MIN_MTU 68 /* RFC 791 */ @@ -80,7 +81,6 @@ struct ipcm_cookie { __u8 protocol; __u8 ttl; __s16 tos; - char priority; __u16 gso_size; }; @@ -92,10 +92,12 @@ static inline void ipcm_init(struct ipcm_cookie *ipcm) static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, const struct inet_sock *inet) { - ipcm_init(ipcm); + *ipcm = (struct ipcm_cookie) { + .tos = READ_ONCE(inet->tos), + }; + + sockcm_init(&ipcm->sockc, &inet->sk); - ipcm->sockc.mark = READ_ONCE(inet->sk.sk_mark); - ipcm->sockc.tsflags = READ_ONCE(inet->sk.sk_tsflags); ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if); ipcm->addr = inet->inet_saddr; ipcm->protocol = inet->inet_num; @@ -256,11 +258,6 @@ static inline u8 ip_sendmsg_scope(const struct inet_sock *inet, return RT_SCOPE_UNIVERSE; } -static inline __u8 get_rttos(struct ipcm_cookie* ipc, struct inet_sock *inet) -{ - return (ipc->tos != -1) ? RT_TOS(ipc->tos) : RT_TOS(READ_ONCE(inet->tos)); -} - /* datagram.c */ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); @@ -285,7 +282,8 @@ static inline __u8 ip_reply_arg_flowi_flags(const struct ip_reply_arg *arg) return (arg->flags & IP_REPLY_ARG_NOSRCCHECK) ? FLOWI_FLAG_ANYSRC : 0; } -void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, +void ip_send_unicast_reply(struct sock *sk, const struct sock *orig_sk, + struct sk_buff *skb, const struct ip_options *sopt, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, @@ -359,7 +357,7 @@ static inline void inet_get_local_port_range(const struct net *net, int *low, in bool inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high); #ifdef CONFIG_SYSCTL -static inline bool inet_is_local_reserved_port(struct net *net, unsigned short port) +static inline bool inet_is_local_reserved_port(const struct net *net, unsigned short port) { if (!net->ipv4.sysctl_local_reserved_ports) return false; @@ -421,9 +419,14 @@ int ip_decrease_ttl(struct iphdr *iph) return --iph->ttl; } +static inline dscp_t ip4h_dscp(const struct iphdr *ip4h) +{ + return inet_dsfield_to_dscp(ip4h->tos); +} + static inline int ip_mtu_locked(const struct dst_entry *dst) { - const struct rtable *rt = (const struct rtable *)dst; + const struct rtable *rt = dst_rtable(dst); return rt->rt_mtu_locked || dst_metric_locked(dst, RTAX_MTU); } @@ -461,10 +464,13 @@ static inline bool ip_sk_ignore_df(const struct sock *sk) static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, bool forwarding) { - const struct rtable *rt = container_of(dst, struct rtable, dst); - struct net *net = dev_net(dst->dev); - unsigned int mtu; + const struct rtable *rt = dst_rtable(dst); + unsigned int mtu, res; + struct net *net; + rcu_read_lock(); + + net = dev_net_rcu(dst->dev); if (READ_ONCE(net->ipv4.sysctl_ip_fwd_use_pmtu) || ip_mtu_locked(dst) || !forwarding) { @@ -488,7 +494,11 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, out: mtu = min_t(unsigned int, mtu, IP_MAX_MTU); - return mtu - lwtunnel_headroom(dst->lwtstate, mtu); + res = mtu - lwtunnel_headroom(dst->lwtstate, mtu); + + rcu_read_unlock(); + + return res; } static inline unsigned int ip_skb_dst_mtu(struct sock *sk, @@ -506,8 +516,7 @@ static inline unsigned int ip_skb_dst_mtu(struct sock *sk, return mtu - lwtunnel_headroom(skb_dst(skb)->lwtstate, mtu); } -struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx, - int fc_mx_len, +struct dst_metrics *ip_fib_metrics_init(struct nlattr *fc_mx, int fc_mx_len, struct netlink_ext_ack *extack); static inline void ip_fib_metrics_put(struct dst_metrics *fib_metrics) { @@ -677,11 +686,24 @@ static __inline__ void inet_reset_saddr(struct sock *sk) #endif +#if IS_MODULE(CONFIG_IPV6) +#define EXPORT_IPV6_MOD(X) EXPORT_SYMBOL(X) +#define EXPORT_IPV6_MOD_GPL(X) EXPORT_SYMBOL_GPL(X) +#else +#define EXPORT_IPV6_MOD(X) +#define EXPORT_IPV6_MOD_GPL(X) +#endif + static inline unsigned int ipv4_addr_hash(__be32 ip) { return (__force unsigned int) ip; } +static inline u32 __ipv4_addr_hash(const __be32 ip, const u32 initval) +{ + return jhash_1word((__force u32)ip, initval); +} + static inline u32 ipv4_portaddr_hash(const struct net *net, __be32 saddr, unsigned int port) @@ -795,9 +817,8 @@ static inline void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb) ip_cmsg_recv_offset(msg, skb->sk, skb, 0, 0); } -bool icmp_global_allow(void); -extern int sysctl_icmp_msgs_per_sec; -extern int sysctl_icmp_msgs_burst; +bool icmp_global_allow(struct net *net); +void icmp_global_consume(struct net *net); #ifdef CONFIG_PROC_FS int ip_misc_proc_init(void); diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 323c94f1845b..88b0dd4d8e09 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -198,6 +198,7 @@ struct fib6_info { fib6_destroying:1, unused:4; + struct list_head purge_link; struct rcu_head rcu; struct nexthop *nh; struct fib6_nh fib6_nh[]; @@ -234,9 +235,11 @@ struct fib6_result { for (rt = (w)->leaf; rt; \ rt = rcu_dereference_protected(rt->fib6_next, 1)) -static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst) +#define dst_rt6_info(_ptr) container_of_const(_ptr, struct rt6_info, dst) + +static inline struct inet6_dev *ip6_dst_idev(const struct dst_entry *dst) { - return ((struct rt6_info *)dst)->rt6i_idev; + return dst_rt6_info(dst)->rt6i_idev; } static inline bool fib6_requires_src(const struct fib6_info *rt) @@ -338,7 +341,7 @@ static inline void fib6_info_release(struct fib6_info *f6i) { if (f6i && refcount_dec_and_test(&f6i->fib6_ref)) { DEBUG_NET_WARN_ON_ONCE(!hlist_unhashed(&f6i->gc_link)); - call_rcu(&f6i->rcu, fib6_info_destroy_rcu); + call_rcu_hurry(&f6i->rcu, fib6_info_destroy_rcu); } } @@ -392,7 +395,7 @@ struct fib6_table { struct fib6_node tb6_root; struct inet_peer_base tb6_peers; unsigned int flags; - unsigned int fib_seq; + unsigned int fib_seq; /* writes protected by rtnl_mutex */ struct hlist_head tb6_gc_hlist; /* GC candidates */ #define RT6_TABLE_HAS_DFLT_ROUTER BIT(0) }; @@ -561,7 +564,7 @@ int call_fib6_notifiers(struct net *net, enum fib_event_type event_type, int __net_init fib6_notifier_init(struct net *net); void __net_exit fib6_notifier_exit(struct net *net); -unsigned int fib6_tables_seq_read(struct net *net); +unsigned int fib6_tables_seq_read(const struct net *net); int fib6_tables_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); @@ -630,7 +633,7 @@ void fib6_rules_cleanup(void); bool fib6_rule_default(const struct fib_rule *rule); int fib6_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); -unsigned int fib6_rules_seq_read(struct net *net); +unsigned int fib6_rules_seq_read(const struct net *net); static inline bool fib6_rules_early_flow_dissect(struct net *net, struct sk_buff *skb, @@ -674,7 +677,7 @@ static inline int fib6_rules_dump(struct net *net, struct notifier_block *nb, { return 0; } -static inline unsigned int fib6_rules_seq_read(struct net *net) +static inline unsigned int fib6_rules_seq_read(const struct net *net) { return 0; } diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index a30c6aa9e5cf..6dbdf60b342f 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -127,18 +127,26 @@ void rt6_age_exceptions(struct fib6_info *f6i, struct fib6_gc_args *gc_args, static inline int ip6_route_get_saddr(struct net *net, struct fib6_info *f6i, const struct in6_addr *daddr, - unsigned int prefs, + unsigned int prefs, int l3mdev_index, struct in6_addr *saddr) { + struct net_device *l3mdev; + struct net_device *dev; + bool same_vrf; int err = 0; - if (f6i && f6i->fib6_prefsrc.plen) { + rcu_read_lock(); + + l3mdev = dev_get_by_index_rcu(net, l3mdev_index); + if (!f6i || !f6i->fib6_prefsrc.plen || l3mdev) + dev = f6i ? fib6_info_nh_dev(f6i) : NULL; + same_vrf = !l3mdev || l3mdev_master_dev_rcu(dev) == l3mdev; + if (f6i && f6i->fib6_prefsrc.plen && same_vrf) *saddr = f6i->fib6_prefsrc.addr; - } else { - struct net_device *dev = f6i ? fib6_info_nh_dev(f6i) : NULL; + else + err = ipv6_dev_get_saddr(net, same_vrf ? dev : l3mdev, daddr, prefs, saddr); - err = ipv6_dev_get_saddr(net, dev, daddr, prefs, saddr); - } + rcu_read_unlock(); return err; } @@ -210,12 +218,11 @@ void rt6_uncached_list_del(struct rt6_info *rt); static inline const struct rt6_info *skb_rt6_info(const struct sk_buff *skb) { const struct dst_entry *dst = skb_dst(skb); - const struct rt6_info *rt6 = NULL; if (dst) - rt6 = container_of(dst, struct rt6_info, dst); + return dst_rt6_info(dst); - return rt6; + return NULL; } /* @@ -227,7 +234,7 @@ static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst, { struct ipv6_pinfo *np = inet6_sk(sk); - np->dst_cookie = rt6_get_cookie((struct rt6_info *)dst); + np->dst_cookie = rt6_get_cookie(dst_rt6_info(dst)); sk_setup_caps(sk, dst); np->daddr_cache = daddr; #ifdef CONFIG_IPV6_SUBTREES @@ -240,7 +247,7 @@ void ip6_sk_dst_store_flow(struct sock *sk, struct dst_entry *dst, static inline bool ipv6_unicast_destination(const struct sk_buff *skb) { - struct rt6_info *rt = (struct rt6_info *) skb_dst(skb); + const struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); return rt->rt6i_flags & RTF_LOCAL; } @@ -248,7 +255,7 @@ static inline bool ipv6_unicast_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 *)dst; + const struct rt6_info *rt = dst_rt6_info(dst); return rt->rt6i_flags & RTF_ANYCAST || (rt->rt6i_dst.plen < 127 && diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 74b369bddf49..399592405c72 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -30,8 +30,8 @@ struct __ip6_tnl_parm { struct in6_addr laddr; /* local tunnel end-point address */ struct in6_addr raddr; /* remote tunnel end-point address */ - __be16 i_flags; - __be16 o_flags; + IP_TUNNEL_DECLARE_FLAGS(i_flags); + IP_TUNNEL_DECLARE_FLAGS(o_flags); __be32 i_key; __be32 o_key; diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 9b2f69ba5e49..48bb3cf41469 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -22,6 +22,8 @@ #include <linux/percpu.h> #include <linux/notifier.h> #include <linux/refcount.h> +#include <linux/ip.h> +#include <linux/in_route.h> struct fib_config { u8 fc_dst_len; @@ -160,6 +162,8 @@ struct fib_info { struct fib_nh fib_nh[] __counted_by(fib_nhs); }; +int __net_init fib4_semantics_init(struct net *net); +void __net_exit fib4_semantics_exit(struct net *net); #ifdef CONFIG_IP_MULTIPLE_TABLES struct fib_rule; @@ -173,6 +177,7 @@ struct fib_result { unsigned char type; unsigned char scope; u32 tclassid; + dscp_t dscp; struct fib_nh_common *nhc; struct fib_info *fi; struct fib_table *table; @@ -344,7 +349,7 @@ static inline int fib4_rules_dump(struct net *net, struct notifier_block *nb, return 0; } -static inline unsigned int fib4_rules_seq_read(struct net *net) +static inline unsigned int fib4_rules_seq_read(const struct net *net) { return 0; } @@ -408,7 +413,7 @@ static inline bool fib4_has_custom_rules(const struct net *net) bool fib4_rule_default(const struct fib_rule *rule); int fib4_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); -unsigned int fib4_rules_seq_read(struct net *net); +unsigned int fib4_rules_seq_read(const struct net *net); static inline bool fib4_rules_early_flow_dissect(struct net *net, struct sk_buff *skb, @@ -433,6 +438,11 @@ static inline bool fib4_rules_early_flow_dissect(struct net *net, #endif /* CONFIG_IP_MULTIPLE_TABLES */ +static inline bool fib_dscp_masked_match(dscp_t dscp, const struct flowi4 *fl4) +{ + return dscp == inet_dsfield_to_dscp(RT_TOS(fl4->flowi4_tos)); +} + /* Exported by fib_frontend.c */ extern const struct nla_policy rtm_ipv4_policy[]; void ip_fib_init(void); @@ -441,8 +451,21 @@ int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla, __be32 fib_compute_spec_dst(struct sk_buff *skb); bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev); int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, - u8 tos, int oif, struct net_device *dev, + dscp_t dscp, int oif, struct net_device *dev, struct in_device *idev, u32 *itag); + +static inline enum skb_drop_reason +fib_validate_source_reason(struct sk_buff *skb, __be32 src, __be32 dst, + dscp_t dscp, int oif, struct net_device *dev, + struct in_device *idev, u32 *itag) +{ + int err = fib_validate_source(skb, src, dst, dscp, oif, dev, idev, + itag); + if (err < 0) + return -err; + return SKB_NOT_DROPPED_YET; +} + #ifdef CONFIG_IP_ROUTE_CLASSID static inline int fib_num_tclassid_users(struct net *net) { @@ -520,10 +543,39 @@ void fib_nhc_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig); #ifdef CONFIG_IP_ROUTE_MULTIPATH int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, const struct sk_buff *skb, struct flow_keys *flkeys); + +static void +fib_multipath_hash_construct_key(siphash_key_t *key, u32 mp_seed) +{ + u64 mp_seed_64 = mp_seed; + + key->key[0] = (mp_seed_64 << 32) | mp_seed_64; + key->key[1] = key->key[0]; +} + +static inline u32 fib_multipath_hash_from_keys(const struct net *net, + struct flow_keys *keys) +{ + siphash_aligned_key_t hash_key; + u32 mp_seed; + + mp_seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed).mp_seed; + fib_multipath_hash_construct_key(&hash_key, mp_seed); + + return flow_hash_from_keys_seed(keys, &hash_key); +} +#else +static inline u32 fib_multipath_hash_from_keys(const struct net *net, + struct flow_keys *keys) +{ + return flow_hash_from_keys(keys); +} #endif + int fib_check_nh(struct net *net, struct fib_nh *nh, u32 table, u8 scope, struct netlink_ext_ack *extack); -void fib_select_multipath(struct fib_result *res, int hash); +void fib_select_multipath(struct fib_result *res, int hash, + const struct flowi4 *fl4); void fib_select_path(struct net *net, struct fib_result *res, struct flowi4 *fl4, const struct sk_buff *skb); diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index c286cc2e766e..0c3d571a04a1 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -36,6 +36,24 @@ (sizeof_field(struct ip_tunnel_key, u) - \ sizeof_field(struct ip_tunnel_key, u.ipv4)) +#define __ipt_flag_op(op, ...) \ + op(__VA_ARGS__, __IP_TUNNEL_FLAG_NUM) + +#define IP_TUNNEL_DECLARE_FLAGS(...) \ + __ipt_flag_op(DECLARE_BITMAP, __VA_ARGS__) + +#define ip_tunnel_flags_zero(...) __ipt_flag_op(bitmap_zero, __VA_ARGS__) +#define ip_tunnel_flags_copy(...) __ipt_flag_op(bitmap_copy, __VA_ARGS__) +#define ip_tunnel_flags_and(...) __ipt_flag_op(bitmap_and, __VA_ARGS__) +#define ip_tunnel_flags_or(...) __ipt_flag_op(bitmap_or, __VA_ARGS__) + +#define ip_tunnel_flags_empty(...) \ + __ipt_flag_op(bitmap_empty, __VA_ARGS__) +#define ip_tunnel_flags_intersect(...) \ + __ipt_flag_op(bitmap_intersects, __VA_ARGS__) +#define ip_tunnel_flags_subset(...) \ + __ipt_flag_op(bitmap_subset, __VA_ARGS__) + struct ip_tunnel_key { __be64 tun_id; union { @@ -48,11 +66,11 @@ struct ip_tunnel_key { struct in6_addr dst; } ipv6; } u; - __be16 tun_flags; - u8 tos; /* TOS for IPv4, TC for IPv6 */ - u8 ttl; /* TTL for IPv4, HL for IPv6 */ + IP_TUNNEL_DECLARE_FLAGS(tun_flags); __be32 label; /* Flow Label for IPv6 */ u32 nhid; + u8 tos; /* TOS for IPv4, TC for IPv6 */ + u8 ttl; /* TTL for IPv4, HL for IPv6 */ __be16 tp_src; __be16 tp_dst; __u8 flow_flags; @@ -77,8 +95,8 @@ struct ip_tunnel_encap { #define ip_tunnel_info_opts(info) \ _Generic(info, \ - const struct ip_tunnel_info * : ((const void *)((info) + 1)),\ - struct ip_tunnel_info * : ((void *)((info) + 1))\ + const struct ip_tunnel_info * : ((const void *)(info)->options),\ + struct ip_tunnel_info * : ((void *)(info)->options)\ ) struct ip_tunnel_info { @@ -89,6 +107,7 @@ struct ip_tunnel_info { #endif u8 options_len; u8 mode; + u8 options[] __aligned_largest __counted_by(options_len); }; /* 6rd prefix/relay information */ @@ -110,6 +129,17 @@ struct ip_tunnel_prl_entry { struct metadata_dst; +/* Kernel-side variant of ip_tunnel_parm */ +struct ip_tunnel_parm_kern { + char name[IFNAMSIZ]; + IP_TUNNEL_DECLARE_FLAGS(i_flags); + IP_TUNNEL_DECLARE_FLAGS(o_flags); + __be32 i_key; + __be32 o_key; + int link; + struct iphdr iph; +}; + struct ip_tunnel { struct ip_tunnel __rcu *next; struct hlist_node hash_node; @@ -136,7 +166,7 @@ struct ip_tunnel { struct dst_cache dst_cache; - struct ip_tunnel_parm parms; + struct ip_tunnel_parm_kern parms; int mlink; int encap_hlen; /* Encap header length (FOU,GUE) */ @@ -157,7 +187,7 @@ struct ip_tunnel { }; struct tnl_ptk_info { - __be16 flags; + IP_TUNNEL_DECLARE_FLAGS(flags); __be16 proto; __be32 key; __be32 seq; @@ -179,11 +209,80 @@ struct ip_tunnel_net { int type; }; +static inline void ip_tunnel_set_options_present(unsigned long *flags) +{ + IP_TUNNEL_DECLARE_FLAGS(present) = { }; + + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, present); + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, present); + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, present); + __set_bit(IP_TUNNEL_GTP_OPT_BIT, present); + __set_bit(IP_TUNNEL_PFCP_OPT_BIT, present); + + ip_tunnel_flags_or(flags, flags, present); +} + +static inline void ip_tunnel_clear_options_present(unsigned long *flags) +{ + IP_TUNNEL_DECLARE_FLAGS(present) = { }; + + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, present); + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, present); + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, present); + __set_bit(IP_TUNNEL_GTP_OPT_BIT, present); + __set_bit(IP_TUNNEL_PFCP_OPT_BIT, present); + + __ipt_flag_op(bitmap_andnot, flags, flags, present); +} + +static inline bool ip_tunnel_is_options_present(const unsigned long *flags) +{ + IP_TUNNEL_DECLARE_FLAGS(present) = { }; + + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, present); + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, present); + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, present); + __set_bit(IP_TUNNEL_GTP_OPT_BIT, present); + __set_bit(IP_TUNNEL_PFCP_OPT_BIT, present); + + return ip_tunnel_flags_intersect(flags, present); +} + +static inline bool ip_tunnel_flags_is_be16_compat(const unsigned long *flags) +{ + IP_TUNNEL_DECLARE_FLAGS(supp) = { }; + + bitmap_set(supp, 0, BITS_PER_TYPE(__be16)); + __set_bit(IP_TUNNEL_VTI_BIT, supp); + + return ip_tunnel_flags_subset(flags, supp); +} + +static inline void ip_tunnel_flags_from_be16(unsigned long *dst, __be16 flags) +{ + ip_tunnel_flags_zero(dst); + + bitmap_write(dst, be16_to_cpu(flags), 0, BITS_PER_TYPE(__be16)); + __assign_bit(IP_TUNNEL_VTI_BIT, dst, flags & VTI_ISVTI); +} + +static inline __be16 ip_tunnel_flags_to_be16(const unsigned long *flags) +{ + __be16 ret; + + ret = cpu_to_be16(bitmap_read(flags, 0, BITS_PER_TYPE(__be16))); + if (test_bit(IP_TUNNEL_VTI_BIT, flags)) + ret |= VTI_ISVTI; + + return ret; +} + static inline void ip_tunnel_key_init(struct ip_tunnel_key *key, __be32 saddr, __be32 daddr, u8 tos, u8 ttl, __be32 label, __be16 tp_src, __be16 tp_dst, - __be64 tun_id, __be16 tun_flags) + __be64 tun_id, + const unsigned long *tun_flags) { key->tun_id = tun_id; key->u.ipv4.src = saddr; @@ -193,7 +292,7 @@ static inline void ip_tunnel_key_init(struct ip_tunnel_key *key, key->tos = tos; key->ttl = ttl; key->label = label; - key->tun_flags = tun_flags; + ip_tunnel_flags_copy(key->tun_flags, tun_flags); /* For the tunnel types on the top of IPsec, the tp_src and tp_dst of * the upper tunnel are used. @@ -214,12 +313,8 @@ ip_tunnel_dst_cache_usable(const struct sk_buff *skb, { if (skb->mark) return false; - if (!info) - return true; - if (info->key.tun_flags & TUNNEL_NOCACHE) - return false; - return true; + return !info || !test_bit(IP_TUNNEL_NOCACHE_BIT, info->key.tun_flags); } static inline unsigned short ip_tunnel_info_af(const struct ip_tunnel_info @@ -260,7 +355,7 @@ static inline void ip_tunnel_init_flow(struct flowi4 *fl4, memset(fl4, 0, sizeof(*fl4)); if (oif) { - fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index_rcu(net, oif); + fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index(net, oif); /* Legacy VRF/l3mdev use case */ fl4->flowi4_oif = fl4->flowi4_l3mdev ? 0 : oif; } @@ -282,23 +377,26 @@ 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, unsigned int ip_tnl_net_id, struct rtnl_link_ops *ops, char *devname); - -void ip_tunnel_delete_nets(struct list_head *list_net, unsigned int id, - struct rtnl_link_ops *ops, - struct list_head *dev_to_kill); +void ip_tunnel_delete_net(struct net *net, unsigned int id, + struct rtnl_link_ops *ops, + struct list_head *dev_to_kill); void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, const u8 protocol); void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const u8 proto, int tunnel_hlen); -int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd); +int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, + int cmd); +bool ip_tunnel_parm_from_user(struct ip_tunnel_parm_kern *kp, + const void __user *data); +bool ip_tunnel_parm_to_user(void __user *data, struct ip_tunnel_parm_kern *kp); int ip_tunnel_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd); int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict); int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu); struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, - int link, __be16 flags, + int link, const unsigned long *flags, __be32 remote, __be32 local, __be32 key); @@ -307,16 +405,17 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst, bool log_ecn_error); int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[], - struct ip_tunnel_parm *p, __u32 fwmark); -int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], - struct ip_tunnel_parm *p, __u32 fwmark); + struct ip_tunnel_parm_kern *p, __u32 fwmark); +int ip_tunnel_newlink(struct net *net, struct net_device *dev, + struct nlattr *tb[], struct ip_tunnel_parm_kern *p, + __u32 fwmark); void ip_tunnel_setup(struct net_device *dev, unsigned int net_id); bool ip_tunnel_netlink_encap_parms(struct nlattr *data[], struct ip_tunnel_encap *encap); void ip_tunnel_netlink_parms(struct nlattr *data[], - struct ip_tunnel_parm *parms); + struct ip_tunnel_parm_kern *parms); extern const struct header_ops ip_tunnel_header_ops; __be16 ip_tunnel_parse_protocol(const struct sk_buff *skb); @@ -341,7 +440,8 @@ int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op, int ip_tunnel_encap_setup(struct ip_tunnel *t, struct ip_tunnel_encap *ipencap); -static inline bool pskb_inet_may_pull(struct sk_buff *skb) +static inline enum skb_drop_reason +pskb_inet_may_pull_reason(struct sk_buff *skb) { int nhlen; @@ -358,15 +458,22 @@ static inline bool pskb_inet_may_pull(struct sk_buff *skb) nhlen = 0; } - return pskb_network_may_pull(skb, nhlen); + return pskb_network_may_pull_reason(skb, nhlen); +} + +static inline bool pskb_inet_may_pull(struct sk_buff *skb) +{ + return pskb_inet_may_pull_reason(skb) == SKB_NOT_DROPPED_YET; } /* Variant of pskb_inet_may_pull(). */ -static inline bool skb_vlan_inet_prepare(struct sk_buff *skb) +static inline enum skb_drop_reason +skb_vlan_inet_prepare(struct sk_buff *skb, bool inner_proto_inherit) { - int nhlen = 0, maclen = ETH_HLEN; + int nhlen = 0, maclen = inner_proto_inherit ? 0 : ETH_HLEN; __be16 type = skb->protocol; + enum skb_drop_reason reason; /* Essentially this is skb_protocol(skb, true) * And we get MAC len. @@ -387,11 +494,13 @@ static inline bool skb_vlan_inet_prepare(struct sk_buff *skb) /* For ETH_P_IPV6/ETH_P_IP we make sure to pull * a base network header in skb->head. */ - if (!pskb_may_pull(skb, maclen + nhlen)) - return false; + reason = pskb_may_pull_reason(skb, maclen + nhlen); + if (reason) + return reason; skb_set_network_header(skb, maclen); - return true; + + return SKB_NOT_DROPPED_YET; } static inline int ip_encap_hlen(struct ip_tunnel_encap *e) @@ -474,7 +583,7 @@ static inline u8 ip_tunnel_get_ttl(const struct iphdr *iph, return 0; } -/* Propogate ECN bits out */ +/* Propagate ECN bits out */ static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph, const struct sk_buff *skb) { @@ -542,17 +651,18 @@ static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len) static inline void ip_tunnel_info_opts_get(void *to, const struct ip_tunnel_info *info) { - memcpy(to, info + 1, info->options_len); + memcpy(to, ip_tunnel_info_opts(info), info->options_len); } static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, const void *from, int len, - __be16 flags) + const unsigned long *flags) { info->options_len = len; if (len > 0) { memcpy(ip_tunnel_info_opts(info), from, len); - info->key.tun_flags |= flags; + ip_tunnel_flags_or(info->key.tun_flags, info->key.tun_flags, + flags); } } @@ -596,7 +706,7 @@ static inline void ip_tunnel_info_opts_get(void *to, static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, const void *from, int len, - __be16 flags) + const unsigned long *flags) { info->options_len = 0; } diff --git a/include/net/ipcomp.h b/include/net/ipcomp.h index 8660a2a6d1fc..51401f01e2a5 100644 --- a/include/net/ipcomp.h +++ b/include/net/ipcomp.h @@ -3,20 +3,9 @@ #define _NET_IPCOMP_H #include <linux/skbuff.h> -#include <linux/types.h> - -#define IPCOMP_SCRATCH_SIZE 65400 - -struct crypto_comp; -struct ip_comp_hdr; - -struct ipcomp_data { - u16 threshold; - struct crypto_comp * __percpu *tfms; -}; struct ip_comp_hdr; -struct sk_buff; +struct netlink_ext_ack; struct xfrm_state; int ipcomp_input(struct xfrm_state *x, struct sk_buff *skb); diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 88a8e554f7a1..2ccdf85f34f1 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -246,17 +246,20 @@ extern int sysctl_mld_qrv; #define _DEVADD(net, statname, mod, idev, field, val) \ ({ \ struct inet6_dev *_idev = (idev); \ + unsigned long _field = (field); \ + unsigned long _val = (val); \ if (likely(_idev != NULL)) \ - mod##SNMP_ADD_STATS((_idev)->stats.statname, (field), (val)); \ - mod##SNMP_ADD_STATS((net)->mib.statname##_statistics, (field), (val));\ + mod##SNMP_ADD_STATS((_idev)->stats.statname, _field, _val); \ + mod##SNMP_ADD_STATS((net)->mib.statname##_statistics, _field, _val);\ }) #define _DEVUPD(net, statname, mod, idev, field, val) \ ({ \ struct inet6_dev *_idev = (idev); \ + unsigned long _val = (val); \ if (likely(_idev != NULL)) \ - mod##SNMP_UPD_PO_STATS((_idev)->stats.statname, field, (val)); \ - mod##SNMP_UPD_PO_STATS((net)->mib.statname##_statistics, field, (val));\ + mod##SNMP_UPD_PO_STATS((_idev)->stats.statname, field, _val); \ + mod##SNMP_UPD_PO_STATS((net)->mib.statname##_statistics, field, _val);\ }) /* MIBs */ @@ -363,15 +366,6 @@ struct ipcm6_cookie { struct ipv6_txoptions *opt; }; -static inline void ipcm6_init(struct ipcm6_cookie *ipc6) -{ - *ipc6 = (struct ipcm6_cookie) { - .hlimit = -1, - .tclass = -1, - .dontfrag = -1, - }; -} - static inline void ipcm6_init_sk(struct ipcm6_cookie *ipc6, const struct sock *sk) { @@ -380,6 +374,8 @@ static inline void ipcm6_init_sk(struct ipcm6_cookie *ipc6, .tclass = inet6_sk(sk)->tclass, .dontfrag = inet6_test_bit(DONTFRAG, sk), }; + + sockcm_init(&ipc6->sockc, sk); } static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np) @@ -471,7 +467,7 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk, /* This helper is specialized for BIG TCP needs. * It assumes the hop_jumbo_hdr will immediately follow the IPV6 header. * It assumes headers are already in skb->head. - * Returns 0, or IPPROTO_TCP if a BIG TCP packet is there. + * Returns: 0, or IPPROTO_TCP if a BIG TCP packet is there. */ static inline int ipv6_has_hopopt_jumbo(const struct sk_buff *skb) { @@ -851,7 +847,7 @@ static inline int __ipv6_addr_diff32(const void *token1, const void *token2, int * we should *never* get to this point since that * would mean the addrs are equal * - * However, we do get to it 8) And exacly, when + * However, we do get to it 8) And exactly, when * addresses are equal 8) * * ip route add 1111::/128 via ... @@ -973,7 +969,7 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, hash = skb_get_hash_flowi6(skb, fl6); /* Since this is being sent on the wire obfuscate hash a bit - * to minimize possbility that any useful information to an + * to minimize possibility that any useful information to an * attacker is leaked. Only lower 20 bits are relevant. */ hash = rol32(hash, 16); @@ -1365,4 +1361,16 @@ static inline void ip6_sock_set_recvpktinfo(struct sock *sk) release_sock(sk); } +#define IPV6_ADDR_WORDS 4 + +static inline void ipv6_addr_cpu_to_be32(__be32 *dst, const u32 *src) +{ + cpu_to_be32_array(dst, src, IPV6_ADDR_WORDS); +} + +static inline void ipv6_addr_be32_to_cpu(u32 *dst, const __be32 *src) +{ + be32_to_cpu_array(dst, src, IPV6_ADDR_WORDS); +} + #endif /* _NET_IPV6_H */ diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h index 7321ffe3a108..38ef66826939 100644 --- a/include/net/ipv6_frag.h +++ b/include/net/ipv6_frag.h @@ -66,6 +66,7 @@ ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq) { struct net_device *dev = NULL; struct sk_buff *head; + int refs = 1; rcu_read_lock(); /* Paired with the WRITE_ONCE() in fqdir_pre_exit(). */ @@ -77,7 +78,7 @@ ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq) goto out; fq->q.flags |= INET_FRAG_DROP; - inet_frag_kill(&fq->q); + inet_frag_kill(&fq->q, &refs); dev = dev_get_by_index_rcu(net, fq->iif); if (!dev) @@ -109,7 +110,7 @@ out: spin_unlock(&fq->q.lock); out_rcu_unlock: rcu_read_unlock(); - inet_frag_put(&fq->q); + inet_frag_putn(&fq->q, refs); } /* Check if the upper layer header is truncated in the first fragment. */ diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index 485c39a89866..8a3465c8c2c5 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -9,6 +9,7 @@ #include <net/flow.h> #include <net/neighbour.h> #include <net/sock.h> +#include <net/ipv6.h> /* structs from net/ip6_fib.h */ struct fib6_info; @@ -72,6 +73,8 @@ struct ipv6_stub { int (*output)(struct net *, struct sock *, struct sk_buff *)); struct net_device *(*ipv6_dev_find)(struct net *net, const struct in6_addr *addr, struct net_device *dev); + int (*ip6_xmit)(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, + __u32 mark, struct ipv6_txoptions *opt, int tclass, u32 priority); }; extern const struct ipv6_stub *ipv6_stub __read_mostly; @@ -79,7 +82,7 @@ extern const struct ipv6_stub *ipv6_stub __read_mostly; struct ipv6_bpf_stub { int (*inet6_bind)(struct sock *sk, struct sockaddr *uaddr, int addr_len, u32 flags); - struct sock *(*udp6_lib_lookup)(struct net *net, + struct sock *(*udp6_lib_lookup)(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif, int sdif, struct udp_table *tbl, diff --git a/include/net/iucv/iucv.h b/include/net/iucv/iucv.h index 5cd7871127c9..9804fa5d9c67 100644 --- a/include/net/iucv/iucv.h +++ b/include/net/iucv/iucv.h @@ -15,7 +15,7 @@ * To explore any of the IUCV functions, one must first register their * program using iucv_register(). Once your program has successfully * completed a register, it can exploit the other functions. - * For furthur reference on all IUCV functionality, refer to the + * For further reference on all IUCV functionality, refer to the * CP Programming Services book, also available on the web thru * www.vm.ibm.com/pubs, manual # SC24-6084 * @@ -82,7 +82,12 @@ struct iucv_array { } __attribute__ ((aligned (8))); extern const struct bus_type iucv_bus; -extern struct device *iucv_root; + +struct device_driver; + +struct device *iucv_alloc_device(const struct attribute_group **attrs, + struct device_driver *driver, void *priv, + const char *fmt, ...) __printf(4, 5); /* * struct iucv_path @@ -197,7 +202,7 @@ struct iucv_handler { * * Registers a driver with IUCV. * - * Returns 0 on success, -ENOMEM if the memory allocation for the pathid + * Returns: 0 on success, -ENOMEM if the memory allocation for the pathid * table failed, or -EIO if IUCV_DECLARE_BUFFER failed on all cpus. */ int iucv_register(struct iucv_handler *handler, int smp); @@ -219,7 +224,7 @@ void iucv_unregister(struct iucv_handler *handle, int smp); * * Allocate a new path structure for use with iucv_connect. * - * Returns NULL if the memory allocation failed or a pointer to the + * Returns: NULL if the memory allocation failed or a pointer to the * path structure. */ static inline struct iucv_path *iucv_path_alloc(u16 msglim, u8 flags, gfp_t gfp) @@ -255,7 +260,7 @@ static inline void iucv_path_free(struct iucv_path *path) * This function is issued after the user received a connection pending * external interrupt and now wishes to complete the IUCV communication path. * - * Returns the result of the CP IUCV call. + * Returns: the result of the CP IUCV call. */ int iucv_path_accept(struct iucv_path *path, struct iucv_handler *handler, u8 *userdata, void *private); @@ -273,7 +278,7 @@ int iucv_path_accept(struct iucv_path *path, struct iucv_handler *handler, * successfully, you are not able to use the path until you receive an IUCV * Connection Complete external interrupt. * - * Returns the result of the CP IUCV call. + * Returns: the result of the CP IUCV call. */ int iucv_path_connect(struct iucv_path *path, struct iucv_handler *handler, u8 *userid, u8 *system, u8 *userdata, @@ -287,7 +292,7 @@ int iucv_path_connect(struct iucv_path *path, struct iucv_handler *handler, * This function temporarily suspends incoming messages on an IUCV path. * You can later reactivate the path by invoking the iucv_resume function. * - * Returns the result from the CP IUCV call. + * Returns: the result from the CP IUCV call. */ int iucv_path_quiesce(struct iucv_path *path, u8 *userdata); @@ -299,7 +304,7 @@ int iucv_path_quiesce(struct iucv_path *path, u8 *userdata); * This function resumes incoming messages on an IUCV path that has * been stopped with iucv_path_quiesce. * - * Returns the result from the CP IUCV call. + * Returns: the result from the CP IUCV call. */ int iucv_path_resume(struct iucv_path *path, u8 *userdata); @@ -310,7 +315,7 @@ int iucv_path_resume(struct iucv_path *path, u8 *userdata); * * This function terminates an IUCV path. * - * Returns the result from the CP IUCV call. + * Returns: the result from the CP IUCV call. */ int iucv_path_sever(struct iucv_path *path, u8 *userdata); @@ -322,7 +327,7 @@ int iucv_path_sever(struct iucv_path *path, u8 *userdata); * * Cancels a message you have sent. * - * Returns the result from the CP IUCV call. + * Returns: the result from the CP IUCV call. */ int iucv_message_purge(struct iucv_path *path, struct iucv_message *msg, u32 srccls); @@ -342,7 +347,7 @@ int iucv_message_purge(struct iucv_path *path, struct iucv_message *msg, * * Locking: local_bh_enable/local_bh_disable * - * Returns the result from the CP IUCV call. + * Returns: the result from the CP IUCV call. */ int iucv_message_receive(struct iucv_path *path, struct iucv_message *msg, u8 flags, void *buffer, size_t size, size_t *residual); @@ -362,7 +367,7 @@ int iucv_message_receive(struct iucv_path *path, struct iucv_message *msg, * * Locking: no locking. * - * Returns the result from the CP IUCV call. + * Returns: the result from the CP IUCV call. */ int __iucv_message_receive(struct iucv_path *path, struct iucv_message *msg, u8 flags, void *buffer, size_t size, @@ -377,7 +382,7 @@ int __iucv_message_receive(struct iucv_path *path, struct iucv_message *msg, * are notified of a message and the time that you complete the message, * the message may be rejected. * - * Returns the result from the CP IUCV call. + * Returns: the result from the CP IUCV call. */ int iucv_message_reject(struct iucv_path *path, struct iucv_message *msg); @@ -394,7 +399,7 @@ int iucv_message_reject(struct iucv_path *path, struct iucv_message *msg); * pathid, msgid, and trgcls. Prmmsg signifies the data is moved into * the parameter list. * - * Returns the result from the CP IUCV call. + * Returns: the result from the CP IUCV call. */ int iucv_message_reply(struct iucv_path *path, struct iucv_message *msg, u8 flags, void *reply, size_t size); @@ -414,7 +419,7 @@ int iucv_message_reply(struct iucv_path *path, struct iucv_message *msg, * * Locking: local_bh_enable/local_bh_disable * - * Returns the result from the CP IUCV call. + * Returns: the result from the CP IUCV call. */ int iucv_message_send(struct iucv_path *path, struct iucv_message *msg, u8 flags, u32 srccls, void *buffer, size_t size); @@ -434,7 +439,7 @@ int iucv_message_send(struct iucv_path *path, struct iucv_message *msg, * * Locking: no locking. * - * Returns the result from the CP IUCV call. + * Returns: the result from the CP IUCV call. */ int __iucv_message_send(struct iucv_path *path, struct iucv_message *msg, u8 flags, u32 srccls, void *buffer, size_t size); @@ -456,7 +461,7 @@ int __iucv_message_send(struct iucv_path *path, struct iucv_message *msg, * reply to the message and a buffer is provided into which IUCV moves * the reply to this message. * - * Returns the result from the CP IUCV call. + * Returns: the result from the CP IUCV call. */ int iucv_message_send2way(struct iucv_path *path, struct iucv_message *msg, u8 flags, u32 srccls, void *buffer, size_t size, diff --git a/include/net/iw_handler.h b/include/net/iw_handler.h index b2cf243ebe44..b80e474cb0aa 100644 --- a/include/net/iw_handler.h +++ b/include/net/iw_handler.h @@ -23,7 +23,7 @@ * to handle wireless statistics. * * The initial APIs served us well and has proven a reasonably good design. - * However, there is a few shortcommings : + * However, there are a few shortcomings : * o No events, everything is a request to the driver. * o Large ioctl function in driver with gigantic switch statement * (i.e. spaghetti code). @@ -38,13 +38,13 @@ * ------------------------------- * The new driver API is just a bunch of standard functions (handlers), * each handling a specific Wireless Extension. The driver just export - * the list of handler it supports, and those will be called apropriately. + * the list of handler it supports, and those will be called appropriately. * * I tried to keep the main advantage of the previous API (simplicity, * efficiency and light weight), and also I provide a good dose of backward * compatibility (most structures are the same, driver can use both API * simultaneously, ...). - * Hopefully, I've also addressed the shortcomming of the initial API. + * Hopefully, I've also addressed the shortcoming of the initial API. * * The advantage of the new API are : * o Handling of Extensions in driver broken in small contained functions @@ -84,7 +84,7 @@ /* ---------------------- THE IMPLEMENTATION ---------------------- */ /* - * Some of the choice I've made are pretty controversials. Defining an + * Some of the choice I've made are pretty controversial. Defining an * API is very much weighting compromises. This goes into some of the * details and the thinking behind the implementation. * @@ -140,7 +140,7 @@ * example to distinguish setting max rate and basic rate), I would * break the prototype. Using iwreq_data is more flexible. * 3) Also, the above form is not generic (see above). - * 4) I don't expect driver developper using the wrong field of the + * 4) I don't expect driver developer using the wrong field of the * union (Doh !), so static typechecking doesn't add much value. * 5) Lastly, you can skip the union by doing : * static int mydriver_ioctl_setrate(struct net_device *dev, @@ -279,8 +279,6 @@ #define IW_DESCR_FLAG_RESTRICT 0x0004 /* GET : request is ROOT only */ /* SET : Omit payload from generated iwevent */ #define IW_DESCR_FLAG_NOMAX 0x0008 /* GET : no limit on request size */ -/* Driver level flags */ -#define IW_DESCR_FLAG_WAIT 0x0100 /* Wait for driver event */ /****************************** TYPES ******************************/ @@ -373,11 +371,10 @@ struct iw_handler_def { */ struct iw_ioctl_description { __u8 header_type; /* NULL, iw_point or other */ - __u8 token_type; /* Future */ + __u8 flags; /* Special handling of the request */ __u16 token_size; /* Granularity of payload */ __u16 min_tokens; /* Min acceptable token number */ __u16 max_tokens; /* Max acceptable token number */ - __u32 flags; /* Special handling of the request */ }; /* Need to think of short header translation table. Later. */ @@ -404,26 +401,6 @@ struct iw_spy_data { u_char spy_thr_under[IW_MAX_SPY]; }; -/* --------------------- DEVICE WIRELESS DATA --------------------- */ -/* - * This is all the wireless data specific to a device instance that - * is managed by the core of Wireless Extensions or the 802.11 layer. - * We only keep pointer to those structures, so that a driver is free - * to share them between instances. - * This structure should be initialised before registering the device. - * Access to this data follow the same rules as any other struct net_device - * data (i.e. valid as long as struct net_device exist, same locking rules). - */ -/* Forward declaration */ -struct libipw_device; -/* The struct */ -struct iw_public_data { - /* Driver enhanced spy support */ - struct iw_spy_data * spy_data; - /* Legacy structure managed by the ipw2x00-specific IEEE 802.11 layer */ - struct libipw_device * libipw; -}; - /**************************** PROTOTYPES ****************************/ /* * Functions part of the Wireless Extensions (defined in net/wireless/wext-core.c). @@ -443,23 +420,7 @@ static inline void wireless_nlevent_flush(void) {} /* We may need a function to send a stream of events to user space. * More on that later... */ -/* Standard handler for SIOCSIWSPY */ -int iw_handler_set_spy(struct net_device *dev, struct iw_request_info *info, - union iwreq_data *wrqu, char *extra); -/* Standard handler for SIOCGIWSPY */ -int iw_handler_get_spy(struct net_device *dev, struct iw_request_info *info, - union iwreq_data *wrqu, char *extra); -/* Standard handler for SIOCSIWTHRSPY */ -int iw_handler_set_thrspy(struct net_device *dev, struct iw_request_info *info, - union iwreq_data *wrqu, char *extra); -/* Standard handler for SIOCGIWTHRSPY */ -int iw_handler_get_thrspy(struct net_device *dev, struct iw_request_info *info, - union iwreq_data *wrqu, char *extra); -/* Driver call to update spy records */ -void wireless_spy_update(struct net_device *dev, unsigned char *address, - struct iw_quality *wstats); - -/************************* INLINE FUNTIONS *************************/ +/************************* INLINE FUNCTIONS *************************/ /* * Function that are so simple that it's more efficient inlining them */ diff --git a/include/net/kcm.h b/include/net/kcm.h index 90279e5e09a5..441e993be634 100644 --- a/include/net/kcm.h +++ b/include/net/kcm.h @@ -70,6 +70,7 @@ struct kcm_sock { struct work_struct tx_work; struct list_head wait_psock_list; struct sk_buff *seq_skb; + struct mutex tx_mutex; u32 tx_stopped : 1; /* Don't use bit fields here, these are set under different locks */ diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index 031c661aa14d..1eb8dad18f7e 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -59,6 +59,20 @@ int l3mdev_ifindex_lookup_by_table_id(enum l3mdev_type l3type, struct net *net, int l3mdev_fib_rule_match(struct net *net, struct flowi *fl, struct fib_lookup_arg *arg); +static inline +bool l3mdev_fib_rule_iif_match(const struct flowi *fl, int iifindex) +{ + return !(fl->flowi_flags & FLOWI_FLAG_L3MDEV_OIF) && + fl->flowi_l3mdev == iifindex; +} + +static inline +bool l3mdev_fib_rule_oif_match(const struct flowi *fl, int oifindex) +{ + return fl->flowi_flags & FLOWI_FLAG_L3MDEV_OIF && + fl->flowi_l3mdev == oifindex; +} + void l3mdev_update_flow(struct net *net, struct flowi *fl); int l3mdev_master_ifindex_rcu(const struct net_device *dev); @@ -78,7 +92,7 @@ static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex) struct net_device *dev; int rc = 0; - if (likely(ifindex)) { + if (ifindex) { rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); @@ -198,10 +212,12 @@ struct sk_buff *l3mdev_l3_out(struct sock *sk, struct sk_buff *skb, u16 proto) if (netif_is_l3_slave(dev)) { struct net_device *master; + rcu_read_lock(); master = netdev_master_upper_dev_get_rcu(dev); if (master && master->l3mdev_ops->l3mdev_l3_out) skb = master->l3mdev_ops->l3mdev_l3_out(master, sk, skb, proto); + rcu_read_unlock(); } return skb; @@ -325,6 +341,19 @@ int l3mdev_fib_rule_match(struct net *net, struct flowi *fl, { return 1; } + +static inline +bool l3mdev_fib_rule_iif_match(const struct flowi *fl, int iifindex) +{ + return false; +} + +static inline +bool l3mdev_fib_rule_oif_match(const struct flowi *fl, int oifindex) +{ + return false; +} + static inline void l3mdev_update_flow(struct net *net, struct flowi *fl) { diff --git a/include/net/lapb.h b/include/net/lapb.h index 124ee122f2c8..6c07420644e4 100644 --- a/include/net/lapb.h +++ b/include/net/lapb.h @@ -4,7 +4,7 @@ #include <linux/lapb.h> #include <linux/refcount.h> -#define LAPB_HEADER_LEN 20 /* LAPB over Ethernet + a bit more */ +#define LAPB_HEADER_LEN MAX_HEADER /* LAPB over Ethernet + a bit more */ #define LAPB_ACK_PENDING_CONDITION 0x01 #define LAPB_REJECT_CONDITION 0x02 diff --git a/include/net/lib80211.h b/include/net/lib80211.h deleted file mode 100644 index 8b47d3a51cf8..000000000000 --- a/include/net/lib80211.h +++ /dev/null @@ -1,122 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * lib80211.h -- common bits for IEEE802.11 wireless drivers - * - * Copyright (c) 2008, John W. Linville <linville@tuxdriver.com> - * - * Some bits copied from old ieee80211 component, w/ original copyright - * notices below: - * - * Original code based on Host AP (software wireless LAN access point) driver - * for Intersil Prism2/2.5/3. - * - * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen - * <j@w1.fi> - * Copyright (c) 2002-2003, Jouni Malinen <j@w1.fi> - * - * Adaption to a generic IEEE 802.11 stack by James Ketrenos - * <jketreno@linux.intel.com> - * - * Copyright (c) 2004, Intel Corporation - * - */ - -#ifndef LIB80211_H -#define LIB80211_H - -#include <linux/types.h> -#include <linux/list.h> -#include <linux/atomic.h> -#include <linux/if.h> -#include <linux/skbuff.h> -#include <linux/ieee80211.h> -#include <linux/timer.h> -#include <linux/seq_file.h> - -#define NUM_WEP_KEYS 4 - -enum { - IEEE80211_CRYPTO_TKIP_COUNTERMEASURES = (1 << 0), -}; - -struct module; - -struct lib80211_crypto_ops { - const char *name; - struct list_head list; - - /* init new crypto context (e.g., allocate private data space, - * select IV, etc.); returns NULL on failure or pointer to allocated - * private data on success */ - void *(*init) (int keyidx); - - /* deinitialize crypto context and free allocated private data */ - void (*deinit) (void *priv); - - /* encrypt/decrypt return < 0 on error or >= 0 on success. The return - * value from decrypt_mpdu is passed as the keyidx value for - * decrypt_msdu. skb must have enough head and tail room for the - * encryption; if not, error will be returned; these functions are - * called for all MPDUs (i.e., fragments). - */ - int (*encrypt_mpdu) (struct sk_buff * skb, int hdr_len, void *priv); - int (*decrypt_mpdu) (struct sk_buff * skb, int hdr_len, void *priv); - - /* These functions are called for full MSDUs, i.e. full frames. - * These can be NULL if full MSDU operations are not needed. */ - int (*encrypt_msdu) (struct sk_buff * skb, int hdr_len, void *priv); - int (*decrypt_msdu) (struct sk_buff * skb, int keyidx, int hdr_len, - void *priv); - - int (*set_key) (void *key, int len, u8 * seq, void *priv); - int (*get_key) (void *key, int len, u8 * seq, void *priv); - - /* procfs handler for printing out key information and possible - * statistics */ - void (*print_stats) (struct seq_file *m, void *priv); - - /* Crypto specific flag get/set for configuration settings */ - unsigned long (*get_flags) (void *priv); - unsigned long (*set_flags) (unsigned long flags, void *priv); - - /* maximum number of bytes added by encryption; encrypt buf is - * allocated with extra_prefix_len bytes, copy of in_buf, and - * extra_postfix_len; encrypt need not use all this space, but - * the result must start at the beginning of the buffer and correct - * length must be returned */ - int extra_mpdu_prefix_len, extra_mpdu_postfix_len; - int extra_msdu_prefix_len, extra_msdu_postfix_len; - - struct module *owner; -}; - -struct lib80211_crypt_data { - struct list_head list; /* delayed deletion list */ - struct lib80211_crypto_ops *ops; - void *priv; - atomic_t refcnt; -}; - -struct lib80211_crypt_info { - char *name; - /* Most clients will already have a lock, - so just point to that. */ - spinlock_t *lock; - - struct lib80211_crypt_data *crypt[NUM_WEP_KEYS]; - int tx_keyidx; /* default TX key index (crypt[tx_keyidx]) */ - struct list_head crypt_deinit_list; - struct timer_list crypt_deinit_timer; - int crypt_quiesced; -}; - -int lib80211_crypt_info_init(struct lib80211_crypt_info *info, char *name, - spinlock_t *lock); -void lib80211_crypt_info_free(struct lib80211_crypt_info *info); -int lib80211_register_crypto_ops(struct lib80211_crypto_ops *ops); -int lib80211_unregister_crypto_ops(struct lib80211_crypto_ops *ops); -struct lib80211_crypto_ops *lib80211_get_crypto_ops(const char *name); -void lib80211_crypt_delayed_deinit(struct lib80211_crypt_info *info, - struct lib80211_crypt_data **crypt); - -#endif /* LIB80211_H */ diff --git a/include/net/libeth/cache.h b/include/net/libeth/cache.h new file mode 100644 index 000000000000..bdb0c043ce61 --- /dev/null +++ b/include/net/libeth/cache.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2024 Intel Corporation */ + +#ifndef __LIBETH_CACHE_H +#define __LIBETH_CACHE_H + +#include <linux/cache.h> + +/** + * libeth_cacheline_group_assert - make sure cacheline group size is expected + * @type: type of the structure containing the group + * @grp: group name inside the struct + * @sz: expected group size + */ +#if defined(CONFIG_64BIT) && SMP_CACHE_BYTES == 64 +#define libeth_cacheline_group_assert(type, grp, sz) \ + static_assert(offsetof(type, __cacheline_group_end__##grp) - \ + offsetofend(type, __cacheline_group_begin__##grp) == \ + (sz)) +#define __libeth_cacheline_struct_assert(type, sz) \ + static_assert(sizeof(type) == (sz)) +#else /* !CONFIG_64BIT || SMP_CACHE_BYTES != 64 */ +#define libeth_cacheline_group_assert(type, grp, sz) \ + static_assert(offsetof(type, __cacheline_group_end__##grp) - \ + offsetofend(type, __cacheline_group_begin__##grp) <= \ + (sz)) +#define __libeth_cacheline_struct_assert(type, sz) \ + static_assert(sizeof(type) <= (sz)) +#endif /* !CONFIG_64BIT || SMP_CACHE_BYTES != 64 */ + +#define __libeth_cls1(sz1) SMP_CACHE_ALIGN(sz1) +#define __libeth_cls2(sz1, sz2) (SMP_CACHE_ALIGN(sz1) + SMP_CACHE_ALIGN(sz2)) +#define __libeth_cls3(sz1, sz2, sz3) \ + (SMP_CACHE_ALIGN(sz1) + SMP_CACHE_ALIGN(sz2) + SMP_CACHE_ALIGN(sz3)) +#define __libeth_cls(...) \ + CONCATENATE(__libeth_cls, COUNT_ARGS(__VA_ARGS__))(__VA_ARGS__) + +/** + * libeth_cacheline_struct_assert - make sure CL-based struct size is expected + * @type: type of the struct + * @...: from 1 to 3 CL group sizes (read-mostly, read-write, cold) + * + * When a struct contains several CL groups, it's difficult to predict its size + * on different architectures. The macro instead takes sizes of all of the + * groups the structure contains and generates the final struct size. + */ +#define libeth_cacheline_struct_assert(type, ...) \ + __libeth_cacheline_struct_assert(type, __libeth_cls(__VA_ARGS__)); \ + static_assert(__alignof(type) >= SMP_CACHE_BYTES) + +/** + * libeth_cacheline_set_assert - make sure CL-based struct layout is expected + * @type: type of the struct + * @ro: expected size of the read-mostly group + * @rw: expected size of the read-write group + * @c: expected size of the cold group + * + * Check that each group size is expected and then do final struct size check. + */ +#define libeth_cacheline_set_assert(type, ro, rw, c) \ + libeth_cacheline_group_assert(type, read_mostly, ro); \ + libeth_cacheline_group_assert(type, read_write, rw); \ + libeth_cacheline_group_assert(type, cold, c); \ + libeth_cacheline_struct_assert(type, ro, rw, c) + +#endif /* __LIBETH_CACHE_H */ diff --git a/include/net/libeth/rx.h b/include/net/libeth/rx.h new file mode 100644 index 000000000000..ab05024be518 --- /dev/null +++ b/include/net/libeth/rx.h @@ -0,0 +1,308 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2024 Intel Corporation */ + +#ifndef __LIBETH_RX_H +#define __LIBETH_RX_H + +#include <linux/if_vlan.h> + +#include <net/page_pool/helpers.h> +#include <net/xdp.h> + +/* Rx buffer management */ + +/* Space reserved in front of each frame */ +#define LIBETH_SKB_HEADROOM (NET_SKB_PAD + NET_IP_ALIGN) +/* Maximum headroom for worst-case calculations */ +#define LIBETH_MAX_HEADROOM LIBETH_SKB_HEADROOM +/* Link layer / L2 overhead: Ethernet, 2 VLAN tags (C + S), FCS */ +#define LIBETH_RX_LL_LEN (ETH_HLEN + 2 * VLAN_HLEN + ETH_FCS_LEN) +/* Maximum supported L2-L4 header length */ +#define LIBETH_MAX_HEAD roundup_pow_of_two(max(MAX_HEADER, 256)) + +/* Always use order-0 pages */ +#define LIBETH_RX_PAGE_ORDER 0 +/* Pick a sane buffer stride and align to a cacheline boundary */ +#define LIBETH_RX_BUF_STRIDE SKB_DATA_ALIGN(128) +/* HW-writeable space in one buffer: truesize - headroom/tailroom, aligned */ +#define LIBETH_RX_PAGE_LEN(hr) \ + ALIGN_DOWN(SKB_MAX_ORDER(hr, LIBETH_RX_PAGE_ORDER), \ + LIBETH_RX_BUF_STRIDE) + +/** + * struct libeth_fqe - structure representing an Rx buffer (fill queue element) + * @page: page holding the buffer + * @offset: offset from the page start (to the headroom) + * @truesize: total space occupied by the buffer (w/ headroom and tailroom) + * + * Depending on the MTU, API switches between one-page-per-frame and shared + * page model (to conserve memory on bigger-page platforms). In case of the + * former, @offset is always 0 and @truesize is always ```PAGE_SIZE```. + */ +struct libeth_fqe { + struct page *page; + u32 offset; + u32 truesize; +} __aligned_largest; + +/** + * enum libeth_fqe_type - enum representing types of Rx buffers + * @LIBETH_FQE_MTU: buffer size is determined by MTU + * @LIBETH_FQE_SHORT: buffer size is smaller than MTU, for short frames + * @LIBETH_FQE_HDR: buffer size is ```LIBETH_MAX_HEAD```-sized, for headers + */ +enum libeth_fqe_type { + LIBETH_FQE_MTU = 0U, + LIBETH_FQE_SHORT, + LIBETH_FQE_HDR, +}; + +/** + * struct libeth_fq - structure representing a buffer (fill) queue + * @fp: hotpath part of the structure + * @pp: &page_pool for buffer management + * @fqes: array of Rx buffers + * @truesize: size to allocate per buffer, w/overhead + * @count: number of descriptors/buffers the queue has + * @type: type of the buffers this queue has + * @hsplit: flag whether header split is enabled + * @buf_len: HW-writeable length per each buffer + * @nid: ID of the closest NUMA node with memory + */ +struct libeth_fq { + struct_group_tagged(libeth_fq_fp, fp, + struct page_pool *pp; + struct libeth_fqe *fqes; + + u32 truesize; + u32 count; + ); + + /* Cold fields */ + enum libeth_fqe_type type:2; + bool hsplit:1; + + u32 buf_len; + int nid; +}; + +int libeth_rx_fq_create(struct libeth_fq *fq, struct napi_struct *napi); +void libeth_rx_fq_destroy(struct libeth_fq *fq); + +/** + * libeth_rx_alloc - allocate a new Rx buffer + * @fq: fill queue to allocate for + * @i: index of the buffer within the queue + * + * Return: DMA address to be passed to HW for Rx on successful allocation, + * ```DMA_MAPPING_ERROR``` otherwise. + */ +static inline dma_addr_t libeth_rx_alloc(const struct libeth_fq_fp *fq, u32 i) +{ + struct libeth_fqe *buf = &fq->fqes[i]; + + buf->truesize = fq->truesize; + buf->page = page_pool_dev_alloc(fq->pp, &buf->offset, &buf->truesize); + if (unlikely(!buf->page)) + return DMA_MAPPING_ERROR; + + return page_pool_get_dma_addr(buf->page) + buf->offset + + fq->pp->p.offset; +} + +void libeth_rx_recycle_slow(struct page *page); + +/** + * libeth_rx_sync_for_cpu - synchronize or recycle buffer post DMA + * @fqe: buffer to process + * @len: frame length from the descriptor + * + * Process the buffer after it's written by HW. The regular path is to + * synchronize DMA for CPU, but in case of no data it will be immediately + * recycled back to its PP. + * + * Return: true when there's data to process, false otherwise. + */ +static inline bool libeth_rx_sync_for_cpu(const struct libeth_fqe *fqe, + u32 len) +{ + struct page *page = fqe->page; + + /* Very rare, but possible case. The most common reason: + * the last fragment contained FCS only, which was then + * stripped by the HW. + */ + if (unlikely(!len)) { + libeth_rx_recycle_slow(page); + return false; + } + + page_pool_dma_sync_for_cpu(page->pp, page, fqe->offset, len); + + return true; +} + +/* Converting abstract packet type numbers into a software structure with + * the packet parameters to do O(1) lookup on Rx. + */ + +enum { + LIBETH_RX_PT_OUTER_L2 = 0U, + LIBETH_RX_PT_OUTER_IPV4, + LIBETH_RX_PT_OUTER_IPV6, +}; + +enum { + LIBETH_RX_PT_NOT_FRAG = 0U, + LIBETH_RX_PT_FRAG, +}; + +enum { + LIBETH_RX_PT_TUNNEL_IP_NONE = 0U, + LIBETH_RX_PT_TUNNEL_IP_IP, + LIBETH_RX_PT_TUNNEL_IP_GRENAT, + LIBETH_RX_PT_TUNNEL_IP_GRENAT_MAC, + LIBETH_RX_PT_TUNNEL_IP_GRENAT_MAC_VLAN, +}; + +enum { + LIBETH_RX_PT_TUNNEL_END_NONE = 0U, + LIBETH_RX_PT_TUNNEL_END_IPV4, + LIBETH_RX_PT_TUNNEL_END_IPV6, +}; + +enum { + LIBETH_RX_PT_INNER_NONE = 0U, + LIBETH_RX_PT_INNER_UDP, + LIBETH_RX_PT_INNER_TCP, + LIBETH_RX_PT_INNER_SCTP, + LIBETH_RX_PT_INNER_ICMP, + LIBETH_RX_PT_INNER_TIMESYNC, +}; + +#define LIBETH_RX_PT_PAYLOAD_NONE PKT_HASH_TYPE_NONE +#define LIBETH_RX_PT_PAYLOAD_L2 PKT_HASH_TYPE_L2 +#define LIBETH_RX_PT_PAYLOAD_L3 PKT_HASH_TYPE_L3 +#define LIBETH_RX_PT_PAYLOAD_L4 PKT_HASH_TYPE_L4 + +struct libeth_rx_pt { + u32 outer_ip:2; + u32 outer_frag:1; + u32 tunnel_type:3; + u32 tunnel_end_prot:2; + u32 tunnel_end_frag:1; + u32 inner_prot:3; + enum pkt_hash_types payload_layer:2; + + u32 pad:2; + enum xdp_rss_hash_type hash_type:16; +}; + +/** + * struct libeth_rx_csum - checksum offload bits decoded from the Rx descriptor + * @l3l4p: detectable L3 and L4 integrity check is processed by the hardware + * @ipe: IP checksum error + * @eipe: external (outermost) IP header (only for tunels) + * @eudpe: external (outermost) UDP checksum error (only for tunels) + * @ipv6exadd: IPv6 header with extension headers + * @l4e: L4 integrity error + * @pprs: set for packets that skip checksum calculation in the HW pre parser + * @nat: the packet is a UDP tunneled packet + * @raw_csum_valid: set if raw checksum is valid + * @pad: padding to naturally align raw_csum field + * @raw_csum: raw checksum + */ +struct libeth_rx_csum { + u32 l3l4p:1; + u32 ipe:1; + u32 eipe:1; + u32 eudpe:1; + u32 ipv6exadd:1; + u32 l4e:1; + u32 pprs:1; + u32 nat:1; + + u32 raw_csum_valid:1; + u32 pad:7; + u32 raw_csum:16; +}; + +/** + * struct libeth_rqe_info - receive queue element info + * @len: packet length + * @ptype: packet type based on types programmed into the device + * @eop: whether it's the last fragment of the packet + * @rxe: MAC errors: CRC, Alignment, Oversize, Undersizes, Length error + * @vlan: C-VLAN or S-VLAN tag depending on the VLAN offload configuration + */ +struct libeth_rqe_info { + u32 len; + + u32 ptype:14; + u32 eop:1; + u32 rxe:1; + + u32 vlan:16; +}; + +void libeth_rx_pt_gen_hash_type(struct libeth_rx_pt *pt); + +/** + * libeth_rx_pt_get_ip_ver - get IP version from a packet type structure + * @pt: packet type params + * + * Wrapper to compile out the IPv6 code from the drivers when not supported + * by the kernel. + * + * Return: @pt.outer_ip or stub for IPv6 when not compiled-in. + */ +static inline u32 libeth_rx_pt_get_ip_ver(struct libeth_rx_pt pt) +{ +#if !IS_ENABLED(CONFIG_IPV6) + switch (pt.outer_ip) { + case LIBETH_RX_PT_OUTER_IPV4: + return LIBETH_RX_PT_OUTER_IPV4; + default: + return LIBETH_RX_PT_OUTER_L2; + } +#else + return pt.outer_ip; +#endif +} + +/* libeth_has_*() can be used to quickly check whether the HW metadata is + * available to avoid further expensive processing such as descriptor reads. + * They already check for the corresponding netdev feature to be enabled, + * thus can be used as drop-in replacements. + */ + +static inline bool libeth_rx_pt_has_checksum(const struct net_device *dev, + struct libeth_rx_pt pt) +{ + /* Non-zero _INNER* is only possible when _OUTER_IPV* is set, + * it is enough to check only for the L4 type. + */ + return likely(pt.inner_prot > LIBETH_RX_PT_INNER_NONE && + (dev->features & NETIF_F_RXCSUM)); +} + +static inline bool libeth_rx_pt_has_hash(const struct net_device *dev, + struct libeth_rx_pt pt) +{ + return likely(pt.payload_layer > LIBETH_RX_PT_PAYLOAD_NONE && + (dev->features & NETIF_F_RXHASH)); +} + +/** + * libeth_rx_pt_set_hash - fill in skb hash value basing on the PT + * @skb: skb to fill the hash in + * @hash: 32-bit hash value from the descriptor + * @pt: packet type + */ +static inline void libeth_rx_pt_set_hash(struct sk_buff *skb, u32 hash, + struct libeth_rx_pt pt) +{ + skb_set_hash(skb, hash, pt.payload_layer); +} + +#endif /* __LIBETH_RX_H */ diff --git a/include/net/libeth/tx.h b/include/net/libeth/tx.h new file mode 100644 index 000000000000..35614f9523f6 --- /dev/null +++ b/include/net/libeth/tx.h @@ -0,0 +1,129 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2024 Intel Corporation */ + +#ifndef __LIBETH_TX_H +#define __LIBETH_TX_H + +#include <linux/skbuff.h> + +#include <net/libeth/types.h> + +/* Tx buffer completion */ + +/** + * enum libeth_sqe_type - type of &libeth_sqe to act on Tx completion + * @LIBETH_SQE_EMPTY: unused/empty, no action required + * @LIBETH_SQE_CTX: context descriptor with empty SQE, no action required + * @LIBETH_SQE_SLAB: kmalloc-allocated buffer, unmap and kfree() + * @LIBETH_SQE_FRAG: mapped skb frag, only unmap DMA + * @LIBETH_SQE_SKB: &sk_buff, unmap and napi_consume_skb(), update stats + */ +enum libeth_sqe_type { + LIBETH_SQE_EMPTY = 0U, + LIBETH_SQE_CTX, + LIBETH_SQE_SLAB, + LIBETH_SQE_FRAG, + LIBETH_SQE_SKB, +}; + +/** + * struct libeth_sqe - represents a Send Queue Element / Tx buffer + * @type: type of the buffer, see the enum above + * @rs_idx: index of the last buffer from the batch this one was sent in + * @raw: slab buffer to free via kfree() + * @skb: &sk_buff to consume + * @dma: DMA address to unmap + * @len: length of the mapped region to unmap + * @nr_frags: number of frags in the frame this buffer belongs to + * @packets: number of physical packets sent for this frame + * @bytes: number of physical bytes sent for this frame + * @priv: driver-private scratchpad + */ +struct libeth_sqe { + enum libeth_sqe_type type:32; + u32 rs_idx; + + union { + void *raw; + struct sk_buff *skb; + }; + + DEFINE_DMA_UNMAP_ADDR(dma); + DEFINE_DMA_UNMAP_LEN(len); + + u32 nr_frags; + u32 packets; + u32 bytes; + + unsigned long priv; +} __aligned_largest; + +/** + * LIBETH_SQE_CHECK_PRIV - check the driver's private SQE data + * @p: type or name of the object the driver wants to fit into &libeth_sqe + * + * Make sure the driver's private data fits into libeth_sqe::priv. To be used + * right after its declaration. + */ +#define LIBETH_SQE_CHECK_PRIV(p) \ + static_assert(sizeof(p) <= sizeof_field(struct libeth_sqe, priv)) + +/** + * struct libeth_cq_pp - completion queue poll params + * @dev: &device to perform DMA unmapping + * @ss: onstack NAPI stats to fill + * @napi: whether it's called from the NAPI context + * + * libeth uses this structure to access objects needed for performing full + * Tx complete operation without passing lots of arguments and change the + * prototypes each time a new one is added. + */ +struct libeth_cq_pp { + struct device *dev; + struct libeth_sq_napi_stats *ss; + + bool napi; +}; + +/** + * libeth_tx_complete - perform Tx completion for one SQE + * @sqe: SQE to complete + * @cp: poll params + * + * Do Tx complete for all the types of buffers, incl. freeing, unmapping, + * updating the stats etc. + */ +static inline void libeth_tx_complete(struct libeth_sqe *sqe, + const struct libeth_cq_pp *cp) +{ + switch (sqe->type) { + case LIBETH_SQE_EMPTY: + return; + case LIBETH_SQE_SKB: + case LIBETH_SQE_FRAG: + case LIBETH_SQE_SLAB: + dma_unmap_page(cp->dev, dma_unmap_addr(sqe, dma), + dma_unmap_len(sqe, len), DMA_TO_DEVICE); + break; + default: + break; + } + + switch (sqe->type) { + case LIBETH_SQE_SKB: + cp->ss->packets += sqe->packets; + cp->ss->bytes += sqe->bytes; + + napi_consume_skb(sqe->skb, cp->napi); + break; + case LIBETH_SQE_SLAB: + kfree(sqe->raw); + break; + default: + break; + } + + sqe->type = LIBETH_SQE_EMPTY; +} + +#endif /* __LIBETH_TX_H */ diff --git a/include/net/libeth/types.h b/include/net/libeth/types.h new file mode 100644 index 000000000000..603825e45133 --- /dev/null +++ b/include/net/libeth/types.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2024 Intel Corporation */ + +#ifndef __LIBETH_TYPES_H +#define __LIBETH_TYPES_H + +#include <linux/types.h> + +/** + * struct libeth_sq_napi_stats - "hot" counters to update in Tx completion loop + * @packets: completed frames counter + * @bytes: sum of bytes of completed frames above + * @raw: alias to access all the fields as an array + */ +struct libeth_sq_napi_stats { + union { + struct { + u32 packets; + u32 bytes; + }; + DECLARE_FLEX_ARRAY(u32, raw); + }; +}; + +#endif /* __LIBETH_TYPES_H */ diff --git a/include/net/llc_c_st.h b/include/net/llc_c_st.h index 53823d61d8b6..a4bea0f33188 100644 --- a/include/net/llc_c_st.h +++ b/include/net/llc_c_st.h @@ -44,8 +44,8 @@ struct llc_conn_state_trans { }; struct llc_conn_state { - u8 current_state; - struct llc_conn_state_trans **transitions; + u8 current_state; + const struct llc_conn_state_trans **transitions; }; extern struct llc_conn_state llc_conn_state_table[]; diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h index 1d55ba7c45be..86681f29bda7 100644 --- a/include/net/llc_pdu.h +++ b/include/net/llc_pdu.h @@ -254,7 +254,7 @@ static inline void llc_pdu_header_init(struct sk_buff *skb, u8 type, } /** - * llc_pdu_decode_sa - extracs source address (MAC) of input frame + * llc_pdu_decode_sa - extracts, source address (MAC) of input frame * @skb: input skb that source address must be extracted from it. * @sa: pointer to source address (6 byte array). * diff --git a/include/net/llc_s_st.h b/include/net/llc_s_st.h index ed5b2fa40d32..fca49d483d20 100644 --- a/include/net/llc_s_st.h +++ b/include/net/llc_s_st.h @@ -29,8 +29,8 @@ struct llc_sap_state_trans { }; struct llc_sap_state { - u8 curr_state; - struct llc_sap_state_trans **transitions; + u8 curr_state; + const struct llc_sap_state_trans **transitions; }; /* only access to SAP state table */ diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index 53bd2d02a4f0..c306ebe379a0 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -206,6 +206,7 @@ static inline int lwtunnel_valid_encap_type(u16 encap_type, NL_SET_ERR_MSG(extack, "CONFIG_LWTUNNEL is not enabled in this kernel"); return -EOPNOTSUPP; } + static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len, struct netlink_ext_ack *extack) { diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 2d7f87bc5324..82617579d910 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -7,7 +7,7 @@ * Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018 - 2024 Intel Corporation + * Copyright (C) 2018 - 2025 Intel Corporation */ #ifndef MAC80211_H @@ -22,7 +22,7 @@ #include <net/cfg80211.h> #include <net/codel.h> #include <net/ieee80211_radiotap.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /** * DOC: Introduction @@ -213,7 +213,7 @@ struct ieee80211_low_level_stats { * @IEEE80211_CHANCTX_CHANGE_RADAR: radar detection flag changed * @IEEE80211_CHANCTX_CHANGE_CHANNEL: switched to another operating channel, * this is used only with channel switching with CSA - * @IEEE80211_CHANCTX_CHANGE_MIN_WIDTH: The min required channel width changed + * @IEEE80211_CHANCTX_CHANGE_MIN_DEF: The min chandef changed * @IEEE80211_CHANCTX_CHANGE_AP: The AP channel definition changed, so (wider * bandwidth) OFDMA settings need to be changed * @IEEE80211_CHANCTX_CHANGE_PUNCTURING: The punctured channel(s) bitmap @@ -224,7 +224,7 @@ enum ieee80211_chanctx_change { IEEE80211_CHANCTX_CHANGE_RX_CHAINS = BIT(1), IEEE80211_CHANCTX_CHANGE_RADAR = BIT(2), IEEE80211_CHANCTX_CHANGE_CHANNEL = BIT(3), - IEEE80211_CHANCTX_CHANGE_MIN_WIDTH = BIT(4), + IEEE80211_CHANCTX_CHANGE_MIN_DEF = BIT(4), IEEE80211_CHANCTX_CHANGE_AP = BIT(5), IEEE80211_CHANCTX_CHANGE_PUNCTURING = BIT(6), }; @@ -250,6 +250,7 @@ struct ieee80211_chan_req { * @min_def: the minimum channel definition currently required. * @ap: the channel definition the AP actually is operating as, * for use with (wider bandwidth) OFDMA + * @radio_idx: index of the wiphy radio used used for this channel * @rx_chains_static: The number of RX chains that must always be * active on the channel to receive MIMO transmissions * @rx_chains_dynamic: The number of RX chains that must be enabled @@ -264,6 +265,7 @@ struct ieee80211_chanctx_conf { struct cfg80211_chan_def min_def; struct cfg80211_chan_def ap; + int radio_idx; u8 rx_chains_static, rx_chains_dynamic; bool radar_enabled; @@ -361,7 +363,8 @@ struct ieee80211_vif_chanctx_switch { * @BSS_CHANGED_UNSOL_BCAST_PROBE_RESP: Unsolicited broadcast probe response * status changed. * @BSS_CHANGED_MLD_VALID_LINKS: MLD valid links status changed. - * @BSS_CHANGED_MLD_TTLM: TID to link mapping was changed + * @BSS_CHANGED_MLD_TTLM: negotiated TID to link mapping was changed + * @BSS_CHANGED_TPE: transmit power envelope changed */ enum ieee80211_bss_change { BSS_CHANGED_ASSOC = 1<<0, @@ -395,9 +398,10 @@ enum ieee80211_bss_change { BSS_CHANGED_HE_OBSS_PD = 1<<28, BSS_CHANGED_HE_BSS_COLOR = 1<<29, BSS_CHANGED_FILS_DISCOVERY = 1<<30, - BSS_CHANGED_UNSOL_BCAST_PROBE_RESP = 1<<31, + BSS_CHANGED_UNSOL_BCAST_PROBE_RESP = BIT_ULL(31), BSS_CHANGED_MLD_VALID_LINKS = BIT_ULL(33), BSS_CHANGED_MLD_TTLM = BIT_ULL(34), + BSS_CHANGED_TPE = BIT_ULL(35), /* when adding here, make sure to change ieee80211_reconfig */ }; @@ -550,6 +554,39 @@ struct ieee80211_fils_discovery { u32 max_interval; }; +#define IEEE80211_TPE_EIRP_ENTRIES_320MHZ 5 +struct ieee80211_parsed_tpe_eirp { + bool valid; + s8 power[IEEE80211_TPE_EIRP_ENTRIES_320MHZ]; + u8 count; +}; + +#define IEEE80211_TPE_PSD_ENTRIES_320MHZ 16 +struct ieee80211_parsed_tpe_psd { + bool valid; + s8 power[IEEE80211_TPE_PSD_ENTRIES_320MHZ]; + u8 count, n; +}; + +/** + * struct ieee80211_parsed_tpe - parsed transmit power envelope information + * @max_local: maximum local EIRP, one value for 20, 40, 80, 160, 320 MHz each + * (indexed by TX power category) + * @max_reg_client: maximum regulatory client EIRP, one value for 20, 40, 80, + * 160, 320 MHz each + * (indexed by TX power category) + * @psd_local: maximum local power spectral density, one value for each 20 MHz + * subchannel per bss_conf's chanreq.oper + * (indexed by TX power category) + * @psd_reg_client: maximum regulatory power spectral density, one value for + * each 20 MHz subchannel per bss_conf's chanreq.oper + * (indexed by TX power category) + */ +struct ieee80211_parsed_tpe { + struct ieee80211_parsed_tpe_eirp max_local[2], max_reg_client[2]; + struct ieee80211_parsed_tpe_psd psd_local[2], psd_reg_client[2]; +}; + /** * struct ieee80211_bss_conf - holds the BSS's changing parameters * @@ -645,6 +682,9 @@ struct ieee80211_fils_discovery { * responder functionality. * @ftmr_params: configurable lci/civic parameter when enabling FTM responder. * @nontransmitted: this BSS is a nontransmitted BSS profile + * @tx_bss_conf: Pointer to the BSS configuration of transmitting interface + * if MBSSID is enabled. This pointer is RCU-protected due to CSA finish + * and BSS color change flows accessing it. * @transmitter_bssid: the address of transmitter AP * @bssid_index: index inside the multiple BSSID set * @bssid_indicator: 2^bssid_indicator is the maximum number of APs in set @@ -662,10 +702,10 @@ struct ieee80211_fils_discovery { * @beacon_tx_rate: The configured beacon transmit rate that needs to be passed * to driver when rate control is offloaded to firmware. * @power_type: power type of BSS for 6 GHz - * @tx_pwr_env: transmit power envelope array of BSS. - * @tx_pwr_env_num: number of @tx_pwr_env. + * @tpe: transmit power envelope information * @pwr_reduction: power constraint of BSS. * @eht_support: does this BSS support EHT + * @epcs_support: does this BSS support EPCS * @csa_active: marks whether a channel switch is going on. * @mu_mimo_owner: indicates interface owns MU-MIMO capability * @chanctx_conf: The channel context this interface is assigned to, or %NULL @@ -701,6 +741,23 @@ struct ieee80211_fils_discovery { * beamformee * @eht_mu_beamformer: in AP-mode, does this BSS enable operation as an EHT MU * beamformer + * @eht_80mhz_full_bw_ul_mumimo: in AP-mode, does this BSS support the + * reception of an EHT TB PPDU on an RU that spans the entire PPDU + * bandwidth + * @eht_disable_mcs15: disable EHT-MCS 15 reception capability. + * @bss_param_ch_cnt: in BSS-mode, the BSS params change count. This + * information is the latest known value. It can come from this link's + * beacon or from a beacon sent by another link. + * @bss_param_ch_cnt_link_id: in BSS-mode, the link_id to which the beacon + * that updated &bss_param_ch_cnt belongs. E.g. if link 1 doesn't hear + * its beacons, and link 2 sent a beacon with an RNR element that updated + * link 1's BSS params change count, then, link 1's + * bss_param_ch_cnt_link_id will be 2. That means that link 1 knows that + * link 2 was the link that updated its bss_param_ch_cnt value. + * In case link 1 hears its beacon again, bss_param_ch_cnt_link_id will + * be updated to 1, even if bss_param_ch_cnt didn't change. This allows + * the link to know that it heard the latest value from its own beacon + * (as opposed to hearing its value from another link's beacon). */ struct ieee80211_bss_conf { struct ieee80211_vif *vif; @@ -751,6 +808,7 @@ struct ieee80211_bss_conf { struct ieee80211_ftm_responder_params *ftmr_params; /* Multiple BSSID data */ bool nontransmitted; + struct ieee80211_bss_conf __rcu *tx_bss_conf; u8 transmitter_bssid[ETH_ALEN]; u8 bssid_index; u8 bssid_indicator; @@ -766,11 +824,12 @@ struct ieee80211_bss_conf { u32 unsol_bcast_probe_resp_interval; struct cfg80211_bitrate_mask beacon_tx_rate; enum ieee80211_ap_reg_power power_type; - struct ieee80211_tx_pwr_env tx_pwr_env[IEEE80211_TPE_MAX_IE_COUNT]; - u8 tx_pwr_env_num; + + struct ieee80211_parsed_tpe tpe; + u8 pwr_reduction; bool eht_support; - + bool epcs_support; bool csa_active; bool mu_mimo_owner; @@ -793,6 +852,11 @@ struct ieee80211_bss_conf { bool eht_su_beamformer; bool eht_su_beamformee; bool eht_mu_beamformer; + bool eht_80mhz_full_bw_ul_mumimo; + bool eht_disable_mcs15; + + u8 bss_param_ch_cnt; + u8 bss_param_ch_cnt_link_id; }; /** @@ -953,8 +1017,9 @@ enum mac80211_tx_info_flags { * of their QoS TID or other priority field values. * @IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX: first MLO TX, used mostly internally * for sequence number assignment - * @IEEE80211_TX_CTRL_SCAN_TX: Indicates that this frame is transmitted - * due to scanning, not in normal operation on the interface. + * @IEEE80211_TX_CTRL_DONT_USE_RATE_MASK: Don't use rate mask for this frame + * which is transmitted due to scanning or offchannel TX, not in normal + * operation on the interface. * @IEEE80211_TX_CTRL_MLO_LINK: If not @IEEE80211_LINK_UNSPECIFIED, this * frame should be transmitted on the specific link. This really is * only relevant for frames that do not have data present, and is @@ -975,7 +1040,7 @@ enum mac80211_tx_control_flags { IEEE80211_TX_CTRL_NO_SEQNO = BIT(7), IEEE80211_TX_CTRL_DONT_REORDER = BIT(8), IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX = BIT(9), - IEEE80211_TX_CTRL_SCAN_TX = BIT(10), + IEEE80211_TX_CTRL_DONT_USE_RATE_MASK = BIT(10), IEEE80211_TX_CTRL_MLO_LINK = 0xf0000000, }; @@ -1406,8 +1471,6 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * @RX_FLAG_AMPDU_IS_LAST: this subframe is the last subframe of the A-MPDU * @RX_FLAG_AMPDU_DELIM_CRC_ERROR: A delimiter CRC error has been detected * on this subframe - * @RX_FLAG_AMPDU_DELIM_CRC_KNOWN: The delimiter CRC field is known (the CRC - * is stored in the @ampdu_delimiter_crc field) * @RX_FLAG_MIC_STRIPPED: The mic was stripped of this packet. Decryption was * done by the hardware * @RX_FLAG_ONLY_MONITOR: Report frame only to monitor interfaces without @@ -1479,7 +1542,7 @@ enum mac80211_rx_flags { RX_FLAG_AMPDU_LAST_KNOWN = BIT(12), RX_FLAG_AMPDU_IS_LAST = BIT(13), RX_FLAG_AMPDU_DELIM_CRC_ERROR = BIT(14), - RX_FLAG_AMPDU_DELIM_CRC_KNOWN = BIT(15), + /* one free bit at 15 */ RX_FLAG_MACTIME = BIT(16) | BIT(17), RX_FLAG_MACTIME_PLCP_START = 1 << 16, RX_FLAG_MACTIME_START = 2 << 16, @@ -1576,7 +1639,6 @@ enum mac80211_rx_encoding { * @rx_flags: internal RX flags for mac80211 * @ampdu_reference: A-MPDU reference number, must be a different value for * each A-MPDU but the same for each subframe within one A-MPDU - * @ampdu_delimiter_crc: A-MPDU delimiter CRC * @zero_length_psdu_type: radiotap type of the 0-length PSDU * @link_valid: if the link which is identified by @link_id is valid. This flag * is set only when connection is MLO. @@ -1614,7 +1676,6 @@ struct ieee80211_rx_status { s8 signal; u8 chains; s8 chain_signal[IEEE80211_MAX_CHAINS]; - u8 ampdu_delimiter_crc; u8 zero_length_psdu_type; u8 link_valid:1, link_id:4; }; @@ -1802,6 +1863,9 @@ struct ieee80211_channel_switch { * operation on this interface and request a channel context without * the AP definition. Use this e.g. because the device is able to * handle OFDMA (downlink and trigger for uplink) on a per-AP basis. + * @IEEE80211_VIF_REMOVE_AP_AFTER_DISASSOC: indicates that the AP sta should + * be removed only after setting the vif as unassociated, and not the + * opposite. Only relevant for STA vifs. */ enum ieee80211_vif_flags { IEEE80211_VIF_BEACON_FILTER = BIT(0), @@ -1810,6 +1874,7 @@ enum ieee80211_vif_flags { IEEE80211_VIF_GET_NOA_UPDATE = BIT(3), IEEE80211_VIF_EML_ACTIVE = BIT(4), IEEE80211_VIF_IGNORE_OFDMA_WIDER_BW = BIT(5), + IEEE80211_VIF_REMOVE_AP_AFTER_DISASSOC = BIT(6), }; @@ -1924,14 +1989,18 @@ enum ieee80211_neg_ttlm_res { * @active_links: The bitmap of active links, or 0 for non-MLO. * The driver shouldn't change this directly, but use the * API calls meant for that purpose. - * @dormant_links: bitmap of valid but disabled links, or 0 for non-MLO. - * Must be a subset of valid_links. + * @dormant_links: subset of the valid links that are disabled/suspended + * due to advertised or negotiated TTLM respectively. + * 0 for non-MLO. * @suspended_links: subset of dormant_links representing links that are - * suspended. + * suspended due to negotiated TTLM, and could be activated in the + * future by tearing down the TTLM negotiation. * 0 for non-MLO. * @neg_ttlm: negotiated TID to link mapping info. * see &struct ieee80211_neg_ttlm. * @addr: address of this interface + * @addr_valid: indicates if the address is actively used. Set to false for + * passive monitor interfaces, true in all other cases. * @p2p: indicates whether this AP or STA interface is a p2p * interface, i.e. a GO or p2p-sta respectively * @netdev_features: tx netdev features supported by the hardware for this @@ -1961,7 +2030,6 @@ enum ieee80211_neg_ttlm_res { * @txq: the multicast data TX queue * @offload_flags: 802.3 -> 802.11 enapsulation offload flags, see * &enum ieee80211_offload_flags. - * @mbssid_tx_vif: Pointer to the transmitting interface if MBSSID is enabled. */ struct ieee80211_vif { enum nl80211_iftype type; @@ -1971,6 +2039,7 @@ struct ieee80211_vif { u16 valid_links, active_links, dormant_links, suspended_links; struct ieee80211_neg_ttlm neg_ttlm; u8 addr[ETH_ALEN] __aligned(2); + bool addr_valid; bool p2p; u8 cab_queue; @@ -1989,8 +2058,6 @@ struct ieee80211_vif { bool probe_req_reg; bool rx_mcast_action_reg; - struct ieee80211_vif *mbssid_tx_vif; - /* must be last */ u8 drv_priv[] __aligned(sizeof(void *)); }; @@ -2052,7 +2119,7 @@ static inline bool ieee80211_vif_is_mesh(struct ieee80211_vif *vif) * This can be used by mac80211 drivers with direct cfg80211 APIs * (like the vendor commands) that get a wdev. * - * Note that this function may return %NULL if the given wdev isn't + * Return: pointer to the wdev, or %NULL if the given wdev isn't * associated with a vif that the driver knows about (e.g. monitor * or AP_VLAN interfaces.) */ @@ -2065,6 +2132,8 @@ struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev); * This can be used by mac80211 drivers with direct cfg80211 APIs * (like the vendor commands) that needs to get the wdev for a vif. * This can also be useful to get the netdev associated to a vif. + * + * Return: pointer to the wdev */ struct wireless_dev *ieee80211_vif_to_wdev(struct ieee80211_vif *vif); @@ -2123,8 +2192,8 @@ static inline bool lockdep_vif_wiphy_mutex_held(struct ieee80211_vif *vif) * @IEEE80211_KEY_FLAG_GENERATE_MMIC on the same key. * @IEEE80211_KEY_FLAG_NO_AUTO_TX: Key needs explicit Tx activation. * @IEEE80211_KEY_FLAG_GENERATE_MMIE: This flag should be set by the driver - * for a AES_CMAC key to indicate that it requires sequence number - * generation only + * for a AES_CMAC or a AES_GMAC key to indicate that it requires sequence + * number generation only * @IEEE80211_KEY_FLAG_SPP_AMSDU: SPP A-MSDUs can be used with this key * (set by mac80211 from the sta->spp_amsdu flag) */ @@ -2156,7 +2225,7 @@ enum ieee80211_key_flags { * @tx_pn: PN used for TX 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) + * @keyidx: the key index (0-7) * @keylen: key material length * @key: key material. For ALG_TKIP the key is encoded as a 256-bit (32 byte) * data block: @@ -2165,7 +2234,7 @@ enum ieee80211_key_flags { * - Temporal Authenticator Rx MIC Key (64 bits) * @icv_len: The ICV length for this key type * @iv_len: The IV length for this key type - * @link_id: the link ID for MLO, or -1 for non-MLO or pairwise keys + * @link_id: the link ID, 0 for non-MLO, or -1 for pairwise keys */ struct ieee80211_key_conf { atomic64_t tx_pn; @@ -2276,6 +2345,8 @@ enum ieee80211_sta_rx_bandwidth { IEEE80211_STA_RX_BW_320, }; +#define IEEE80211_STA_RX_BW_MAX IEEE80211_STA_RX_BW_320 + /** * struct ieee80211_sta_rates - station rate selection table * @@ -2421,6 +2492,7 @@ struct ieee80211_link_sta { * @max_amsdu_subframes: indicates the maximal number of MSDUs in a single * A-MSDU. Taken from the Extended Capabilities element. 0 means * unlimited. + * @eml_cap: EML capabilities of this MLO station * @cur: currently valid data as aggregated from the active links * For non MLO STA it will point to the deflink data. For MLO STA * ieee80211_sta_recalc_aggregates() must be called to update it. @@ -2442,7 +2514,7 @@ struct ieee80211_link_sta { * @spp_amsdu: indicates whether the STA uses SPP A-MSDU or not. */ struct ieee80211_sta { - u8 addr[ETH_ALEN]; + u8 addr[ETH_ALEN] __aligned(2); u16 aid; u16 max_rx_aggregation_subframes; bool wme; @@ -2455,6 +2527,7 @@ struct ieee80211_sta { bool mlo; bool spp_amsdu; u8 max_amsdu_subframes; + u16 eml_cap; struct ieee80211_sta_aggregates *cur; @@ -2637,6 +2710,11 @@ struct ieee80211_txq { * a virtual monitor interface when monitor interfaces are the only * active interfaces. * + * @IEEE80211_HW_NO_VIRTUAL_MONITOR: The driver would like to be informed + * of any monitor interface, as well as their configured channel. + * This is useful for supporting multiple monitor interfaces on different + * channels. + * * @IEEE80211_HW_NO_AUTO_VIF: The driver would like for no wlanX to * be created. It is expected user-space will create vifs as * desired (and thus have them named as desired). @@ -2724,14 +2802,6 @@ struct ieee80211_txq { * @IEEE80211_HW_SUPPORTS_TDLS_BUFFER_STA: Hardware supports buffer STA on * TDLS links. * - * @IEEE80211_HW_DEAUTH_NEED_MGD_TX_PREP: The driver requires the - * mgd_prepare_tx() callback to be called before transmission of a - * deauthentication frame in case the association was completed but no - * beacon was heard. This is required in multi-channel scenarios, where the - * virtual interface might not be given air time for the transmission of - * the frame, as it is not synced with the AP/P2P GO yet, and thus the - * deauthentication frame might not be transmitted. - * * @IEEE80211_HW_DOESNT_SUPPORT_QOS_NDP: The driver (or firmware) doesn't * support QoS NDP for AP probing - that's most likely a driver bug. * @@ -2780,12 +2850,19 @@ struct ieee80211_txq { * * @IEEE80211_HW_DISALLOW_PUNCTURING: HW requires disabling puncturing in EHT * and connecting with a lower bandwidth instead + * @IEEE80211_HW_DISALLOW_PUNCTURING_5GHZ: HW requires disabling puncturing in + * EHT in 5 GHz and connecting with a lower bandwidth instead * * @IEEE80211_HW_HANDLES_QUIET_CSA: HW/driver handles quieting for CSA, so * no need to stop queues. This really should be set by a driver that * implements MLO, so operation can continue on other links when one * link is switching. * + * @IEEE80211_HW_STRICT: strictly enforce certain things mandated by the spec + * but otherwise ignored/worked around for interoperability. This is a + * HW flag so drivers can opt in according to their own control, e.g. in + * testing. + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -2802,6 +2879,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_SUPPORTS_DYNAMIC_PS, IEEE80211_HW_MFP_CAPABLE, IEEE80211_HW_WANT_MONITOR_VIF, + IEEE80211_HW_NO_VIRTUAL_MONITOR, IEEE80211_HW_NO_AUTO_VIF, IEEE80211_HW_SW_CRYPTO_CONTROL, IEEE80211_HW_SUPPORT_FAST_XMIT, @@ -2829,7 +2907,6 @@ enum ieee80211_hw_flags { IEEE80211_HW_REPORTS_LOW_ACK, IEEE80211_HW_SUPPORTS_TX_FRAG, IEEE80211_HW_SUPPORTS_TDLS_BUFFER_STA, - IEEE80211_HW_DEAUTH_NEED_MGD_TX_PREP, IEEE80211_HW_DOESNT_SUPPORT_QOS_NDP, IEEE80211_HW_BUFF_MMPDU_TXQ, IEEE80211_HW_SUPPORTS_VHT_EXT_NSS_BW, @@ -2844,7 +2921,9 @@ enum ieee80211_hw_flags { IEEE80211_HW_DETECTS_COLOR_COLLISION, IEEE80211_HW_MLO_MCAST_MULTI_LINK_TX, IEEE80211_HW_DISALLOW_PUNCTURING, + IEEE80211_HW_DISALLOW_PUNCTURING_5GHZ, IEEE80211_HW_HANDLES_QUIET_CSA, + IEEE80211_HW_STRICT, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS @@ -3142,6 +3221,19 @@ ieee80211_get_alt_retry_rate(const struct ieee80211_hw *hw, void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb); /** + * ieee80211_purge_tx_queue - purge TX skb queue + * @hw: the hardware + * @skbs: the skbs + * + * Free a set of transmit skbs. Use this function when device is going to stop + * but some transmit skbs without TX status are still queued. + * This function does not take the list lock and the caller must hold the + * relevant locks to use it. + */ +void ieee80211_purge_tx_queue(struct ieee80211_hw *hw, + struct sk_buff_head *skbs); + +/** * DOC: Hardware crypto acceleration * * mac80211 is capable of taking advantage of many hardware @@ -3741,13 +3833,15 @@ enum ieee80211_reconfig_type { * @success: whether the frame exchange was successful, only * used with the mgd_complete_tx() method, and then only * valid for auth and (re)assoc. + * @was_assoc: set if this call is due to deauth/disassoc + * while just having been associated * @link_id: the link id on which the frame will be TX'ed. - * Only used with the mgd_prepare_tx() method. + * 0 for a non-MLO connection. */ struct ieee80211_prep_tx_info { u16 duration; u16 subtype; - u8 success:1; + u8 success:1, was_assoc:1; int link_id; }; @@ -4020,8 +4114,8 @@ struct ieee80211_prep_tx_info { * in @sta_state. * The callback can sleep. * - * @sta_rc_update: Notifies the driver of changes to the bitrates that can be - * used to transmit to the station. The changes are advertised with bits + * @link_sta_rc_update: Notifies the driver of changes to the bitrates that can + * be used to transmit to the station. The changes are advertised with bits * from &enum ieee80211_rate_control_changed and the values are reflected * in the station data. This callback should only be used when the driver * uses hardware rate control (%IEEE80211_HW_HAS_RATE_CONTROL) since @@ -4196,12 +4290,9 @@ struct ieee80211_prep_tx_info { * yet it need not necessarily be given airtime, in particular since any * transmission to a P2P GO needs to be synchronized against the GO's * powersave state. mac80211 will call this function before transmitting a - * management frame prior to having successfully associated to allow the - * driver to give it channel time for the transmission, to get a response - * and to be able to synchronize with the GO. - * For drivers that set %IEEE80211_HW_DEAUTH_NEED_MGD_TX_PREP, mac80211 - * would also call this function before transmitting a deauthentication - * frame in case that no beacon was heard from the AP/P2P GO. + * management frame prior to transmitting that frame to allow the driver + * to give it channel time for the transmission, to get a response and be + * able to synchronize with the GO. * The callback will be called before each transmission and upon return * mac80211 will transmit the frame right away. * Additional information is passed in the &struct ieee80211_prep_tx_info @@ -4392,13 +4483,19 @@ struct ieee80211_prep_tx_info { * if the requested TID-To-Link mapping can be accepted or not. * If it's not accepted the driver may suggest a preferred mapping and * modify @ttlm parameter with the suggested TID-to-Link mapping. + * @prep_add_interface: prepare for interface addition. This can be used by + * drivers to prepare for the addition of a new interface, e.g., allocate + * the needed resources etc. This callback doesn't guarantee that an + * interface with the specified type would be added, and thus drivers that + * implement this callback need to handle such cases. The type is the full + * &enum nl80211_iftype. */ struct ieee80211_ops { void (*tx)(struct ieee80211_hw *hw, struct ieee80211_tx_control *control, struct sk_buff *skb); int (*start)(struct ieee80211_hw *hw); - void (*stop)(struct ieee80211_hw *hw); + void (*stop)(struct ieee80211_hw *hw, bool suspend); #ifdef CONFIG_PM int (*suspend)(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan); int (*resume)(struct ieee80211_hw *hw); @@ -4508,10 +4605,10 @@ struct ieee80211_ops { void (*sta_pre_rcu_remove)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta); - void (*sta_rc_update)(struct ieee80211_hw *hw, - struct ieee80211_vif *vif, - struct ieee80211_sta *sta, - u32 changed); + void (*link_sta_rc_update)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_link_sta *link_sta, + u32 changed); void (*sta_rate_tbl_update)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta); @@ -4684,7 +4781,7 @@ struct ieee80211_ops { u32 (*get_expected_throughput)(struct ieee80211_hw *hw, struct ieee80211_sta *sta); int (*get_txpower)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - int *dbm); + unsigned int link_id, int *dbm); int (*tdls_channel_switch)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, @@ -4776,6 +4873,8 @@ struct ieee80211_ops { enum ieee80211_neg_ttlm_res (*can_neg_ttlm)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_neg_ttlm *ttlm); + void (*prep_add_interface)(struct ieee80211_hw *hw, + enum nl80211_iftype type); }; /** @@ -5254,22 +5353,6 @@ void ieee80211_get_tx_rates(struct ieee80211_vif *vif, int max_rates); /** - * ieee80211_sta_set_expected_throughput - set the expected tpt for a station - * - * Call this function to notify mac80211 about a change in expected throughput - * to a station. A driver for a device that does rate control in firmware can - * call this function when the expected throughput estimate towards a station - * changes. The information is used to tune the CoDel AQM applied to traffic - * going towards that station (which can otherwise be too aggressive and cause - * slow stations to starve). - * - * @pubsta: the station to set throughput for. - * @thr: the current expected throughput in kbps. - */ -void ieee80211_sta_set_expected_throughput(struct ieee80211_sta *pubsta, - u32 thr); - -/** * ieee80211_tx_rate_update - transmit rate update callback * * Drivers should call this functions with a non-NULL pub sta @@ -5600,7 +5683,7 @@ void ieee80211_csa_finish(struct ieee80211_vif *vif, unsigned int link_id); * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @link_id: valid link_id during MLO or 0 for non-MLO * - * This function returns whether the countdown reached zero. + * Return: %true if the countdown reached 1, %false otherwise */ bool ieee80211_beacon_cntdwn_is_complete(struct ieee80211_vif *vif, unsigned int link_id); @@ -5608,12 +5691,13 @@ bool ieee80211_beacon_cntdwn_is_complete(struct ieee80211_vif *vif, /** * ieee80211_color_change_finish - notify mac80211 about color change * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * @link_id: valid link_id during MLO or 0 for non-MLO * * After a color change announcement was scheduled and the counter in this * announcement hits 1, this function must be called by the driver to * notify mac80211 that the color can be changed */ -void ieee80211_color_change_finish(struct ieee80211_vif *vif); +void ieee80211_color_change_finish(struct ieee80211_vif *vif, u8 link_id); /** * ieee80211_proberesp_get - retrieve a Probe Response template @@ -5945,8 +6029,8 @@ void ieee80211_remove_key(struct ieee80211_key_conf *keyconf); * key(s) will be available. These will be needed by mac80211 for proper * RX processing, so this function allows setting them. * - * The function returns the newly allocated key structure, which will - * have similar contents to the passed key configuration but point to + * Return: the newly allocated key structure, which will have + * similar contents to the passed key configuration but point to * mac80211-owned memory. In case of errors, the function returns an * ERR_PTR(), use IS_ERR() etc. * @@ -6203,6 +6287,24 @@ void ieee80211_iterate_stations_atomic(struct ieee80211_hw *hw, void (*iterator)(void *data, struct ieee80211_sta *sta), void *data); + +/** + * ieee80211_iterate_stations_mtx - iterate stations + * + * This function iterates over all stations associated with a given + * hardware that are currently uploaded to the driver and calls the callback + * function for them. This version can only be used while holding the wiphy + * mutex. + * + * @hw: the hardware struct of which the interfaces should be iterated over + * @iterator: the iterator function to call + * @data: first argument of the iterator function + */ +void ieee80211_iterate_stations_mtx(struct ieee80211_hw *hw, + void (*iterator)(void *data, + struct ieee80211_sta *sta), + void *data); + /** * ieee80211_queue_work - add work onto the mac80211 workqueue * @@ -6345,6 +6447,8 @@ struct ieee80211_sta *ieee80211_find_sta_by_ifaddr(struct ieee80211_hw *hw, * may be %NULL if the link ID is not needed * * Obtain the STA by link address, must use RCU protection. + * + * Return: pointer to STA if found, otherwise %NULL. */ struct ieee80211_sta * ieee80211_find_sta_by_link_addrs(struct ieee80211_hw *hw, @@ -6474,8 +6578,8 @@ void ieee80211_sta_register_airtime(struct ieee80211_sta *pubsta, u8 tid, * @hw: pointer obtained from ieee80211_alloc_hw() * @txq: pointer obtained from station or virtual interface * - * Return true if the AQL's airtime limit has not been reached and the txq can - * continue to send more packets to the device. Otherwise return false. + * Return: %true if the AQL's airtime limit has not been reached and the txq can + * continue to send more packets to the device. Otherwise return %false. */ bool ieee80211_txq_airtime_check(struct ieee80211_hw *hw, struct ieee80211_txq *txq); @@ -6558,6 +6662,31 @@ void ieee80211_iter_chan_contexts_atomic( void *iter_data); /** + * ieee80211_iter_chan_contexts_mtx - iterate channel contexts + * @hw: pointer obtained from ieee80211_alloc_hw(). + * @iter: iterator function + * @iter_data: data passed to iterator function + * + * Iterate all active channel contexts. This function can only be used while + * holding the wiphy mutex. + * + * The iterator will not find a context that's being added (during + * the driver callback to add it) but will find it while it's being + * removed. + * + * Note that during hardware restart, all contexts that existed + * before the restart are considered already present so will be + * found while iterating, whether they've been re-added already + * or not. + */ +void ieee80211_iter_chan_contexts_mtx( + struct ieee80211_hw *hw, + void (*iter)(struct ieee80211_hw *hw, + struct ieee80211_chanctx_conf *chanctx_conf, + void *data), + void *iter_data); + +/** * ieee80211_ap_probereq_get - retrieve a Probe Request template * @hw: pointer obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from the add_interface callback. @@ -6675,8 +6804,11 @@ void ieee80211_cqm_beacon_loss_notify(struct ieee80211_vif *vif, gfp_t gfp); * ieee80211_radar_detected - inform that a radar was detected * * @hw: pointer as obtained from ieee80211_alloc_hw() + * @chanctx_conf: Channel context on which radar is detected. Mandatory to + * pass a valid pointer during MLO. For non-MLO %NULL can be passed */ -void ieee80211_radar_detected(struct ieee80211_hw *hw); +void ieee80211_radar_detected(struct ieee80211_hw *hw, + struct ieee80211_chanctx_conf *chanctx_conf); /** * ieee80211_chswitch_done - Complete channel switch process @@ -6694,14 +6826,12 @@ void ieee80211_chswitch_done(struct ieee80211_vif *vif, bool success, /** * ieee80211_channel_switch_disconnect - disconnect due to channel switch error * @vif: &struct ieee80211_vif pointer from the add_interface callback. - * @block_tx: if %true, do not send deauth frame. * * Instruct mac80211 to disconnect due to a channel switch error. The channel * switch can request to block the tx and so, we need to make sure we do not send * a deauth frame in this case. */ -void ieee80211_channel_switch_disconnect(struct ieee80211_vif *vif, - bool block_tx); +void ieee80211_channel_switch_disconnect(struct ieee80211_vif *vif); /** * ieee80211_request_smps - request SM PS transition @@ -6978,6 +7108,8 @@ bool rate_usable_index_exists(struct ieee80211_supported_band *sband, * @hw: pointer as obtained from ieee80211_alloc_hw() * @pubsta: &struct ieee80211_sta pointer to the target destination. * @rates: new tx rate set to be used for this station. + * + * Return: 0 on success. An error code otherwise. */ int rate_control_set_rates(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, @@ -7138,6 +7270,8 @@ void ieee80211_report_wowlan_wakeup(struct ieee80211_vif *vif, * @band: the band to transmit on * @sta: optional pointer to get the station to send the frame to * + * Return: %true if the skb was prepared, %false otherwise + * * Note: must be called under RCU lock */ bool ieee80211_tx_prepare_skb(struct ieee80211_hw *hw, @@ -7154,6 +7288,8 @@ bool ieee80211_tx_prepare_skb(struct ieee80211_hw *hw, * * @skb: packet injected by userspace * @dev: the &struct device of this 802.11 device + * + * Return: %true if the radiotap header was parsed, %false otherwise */ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, struct net_device *dev); @@ -7263,7 +7399,7 @@ void ieee80211_unreserve_tid(struct ieee80211_sta *sta, u8 tid); * @txq: pointer obtained from station or virtual interface, or from * ieee80211_next_txq() * - * Returns the skb if successful, %NULL if no frame was available. + * Return: the skb if successful, %NULL if no frame was available. * * Note that this must be called in an rcu_read_lock() critical section, * which can only be released after the SKB was handled. Some pointers in @@ -7289,6 +7425,8 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, * @hw: pointer as obtained from ieee80211_alloc_hw() * @txq: pointer obtained from station or virtual interface, or from * ieee80211_next_txq() + * + * Return: the skb if successful, %NULL if no frame was available. */ static inline struct sk_buff *ieee80211_tx_dequeue_ni(struct ieee80211_hw *hw, struct ieee80211_txq *txq) @@ -7320,7 +7458,7 @@ void ieee80211_handle_wake_tx_queue(struct ieee80211_hw *hw, * @hw: pointer as obtained from ieee80211_alloc_hw() * @ac: AC number to return packets from. * - * Returns the next txq if successful, %NULL if no queue is eligible. If a txq + * Return: the next txq if successful, %NULL if no queue is eligible. If a txq * is returned, it should be returned with ieee80211_return_txq() after the * driver has finished scheduling it. */ @@ -7403,6 +7541,8 @@ ieee80211_return_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq, * * @hw: pointer as obtained from ieee80211_alloc_hw() * @txq: pointer obtained from station or virtual interface + * + * Return: %true if transmission is allowed, %false otherwise */ bool ieee80211_txq_may_transmit(struct ieee80211_hw *hw, struct ieee80211_txq *txq); @@ -7463,6 +7603,8 @@ void ieee80211_nan_func_match(struct ieee80211_vif *vif, * @status: &struct ieee80211_rx_status containing the transmission rate * information. * @len: frame length in bytes + * + * Return: the airtime estimate */ u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, struct ieee80211_rx_status *status, @@ -7477,23 +7619,13 @@ u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, * @hw: pointer as obtained from ieee80211_alloc_hw() * @info: &struct ieee80211_tx_info of the frame. * @len: frame length in bytes + * + * Return: the airtime estimate */ u32 ieee80211_calc_tx_airtime(struct ieee80211_hw *hw, struct ieee80211_tx_info *info, int len); /** - * ieee80211_set_hw_80211_encap - enable hardware encapsulation offloading. - * - * This function is used to notify mac80211 that a vif can be passed raw 802.3 - * frames. The driver needs to then handle the 802.11 encapsulation inside the - * hardware or firmware. - * - * @vif: &struct ieee80211_vif pointer from the add_interface callback. - * @enable: indicate if the feature should be turned on or off - */ -bool ieee80211_set_hw_80211_encap(struct ieee80211_vif *vif, bool enable); - -/** * ieee80211_get_fils_discovery_tmpl - Get FILS discovery template. * @hw: pointer obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from the add_interface callback. @@ -7522,6 +7654,7 @@ ieee80211_get_unsol_bcast_probe_resp_tmpl(struct ieee80211_hw *hw, /** * ieee80211_obss_color_collision_notify - notify userland about a BSS color * collision. + * @link_id: valid link_id during MLO or 0 for non-MLO * * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @color_bitmap: a 64 bit bitmap representing the colors that the local BSS is @@ -7529,7 +7662,7 @@ ieee80211_get_unsol_bcast_probe_resp_tmpl(struct ieee80211_hw *hw, */ void ieee80211_obss_color_collision_notify(struct ieee80211_vif *vif, - u64 color_bitmap); + u64 color_bitmap, u8 link_id); /** * ieee80211_is_tx_data - check if frame is a data frame @@ -7538,6 +7671,8 @@ ieee80211_obss_color_collision_notify(struct ieee80211_vif *vif, * hardware encapsulation enabled are data frames. * * @skb: the frame to be transmitted. + * + * Return: %true if @skb is a data frame, %false otherwise */ static inline bool ieee80211_is_tx_data(struct sk_buff *skb) { @@ -7566,13 +7701,15 @@ static inline bool ieee80211_is_tx_data(struct sk_buff *skb) * * - change_vif_links(0x11) * - unassign_vif_chanctx(link_id=0) + * - assign_vif_chanctx(link_id=4) * - change_sta_links(0x11) for each affected STA (the AP) * (TDLS connections on now inactive links should be torn down) * - remove group keys on the old link (link_id 0) * - add new group keys (GTK/IGTK/BIGTK) on the new link (link_id 4) * - change_sta_links(0x10) for each affected STA (the AP) - * - assign_vif_chanctx(link_id=4) * - change_vif_links(0x10) + * + * Return: 0 on success. An error code otherwise. */ int ieee80211_set_active_links(struct ieee80211_vif *vif, u16 active_links); @@ -7589,6 +7726,86 @@ int ieee80211_set_active_links(struct ieee80211_vif *vif, u16 active_links); void ieee80211_set_active_links_async(struct ieee80211_vif *vif, u16 active_links); +/** + * ieee80211_send_teardown_neg_ttlm - tear down a negotiated TTLM request + * @vif: the interface on which the tear down request should be sent. + * + * This function can be used to tear down a previously accepted negotiated + * TTLM request. + */ +void ieee80211_send_teardown_neg_ttlm(struct ieee80211_vif *vif); + +/** + * ieee80211_chan_width_to_rx_bw - convert channel width to STA RX bandwidth + * @width: the channel width value to convert + * Return: the STA RX bandwidth value for the channel width + */ +static inline enum ieee80211_sta_rx_bandwidth +ieee80211_chan_width_to_rx_bw(enum nl80211_chan_width width) +{ + switch (width) { + default: + WARN_ON_ONCE(1); + fallthrough; + case NL80211_CHAN_WIDTH_20_NOHT: + case NL80211_CHAN_WIDTH_20: + return IEEE80211_STA_RX_BW_20; + case NL80211_CHAN_WIDTH_40: + return IEEE80211_STA_RX_BW_40; + case NL80211_CHAN_WIDTH_80: + return IEEE80211_STA_RX_BW_80; + case NL80211_CHAN_WIDTH_160: + case NL80211_CHAN_WIDTH_80P80: + return IEEE80211_STA_RX_BW_160; + case NL80211_CHAN_WIDTH_320: + return IEEE80211_STA_RX_BW_320; + } +} + +/** + * ieee80211_prepare_rx_omi_bw - prepare for sending BW RX OMI + * @link_sta: the link STA the OMI is going to be sent to + * @bw: the bandwidth requested + * + * When the driver decides to do RX OMI to change bandwidth with a STA + * it calls this function to prepare, then sends the OMI, and finally + * calls ieee80211_finalize_rx_omi_bw(). + * + * Note that the (link) STA rate control is updated accordingly as well, + * but the chanctx might not be updated if there are other users. + * If the intention is to reduce the listen bandwidth, the driver must + * ensure there are no TDLS stations nor other uses of the chanctx. + * + * Also note that in order to sequence correctly, narrowing bandwidth + * will only happen in ieee80211_finalize_rx_omi_bw(), whereas widening + * again (e.g. going back to normal) will happen here. + * + * Note that we treat this symmetrically, so if the driver calls this + * and tells the peer to only send with a lower bandwidth, we assume + * that the driver also wants to only send at that lower bandwidth, to + * allow narrowing of the chanctx request for this station/interface. + * + * Finally, the driver must ensure that if the function returned %true, + * ieee80211_finalize_rx_omi_bw() is also called, even for example in + * case of HW restart. + * + * Context: Must be called with wiphy mutex held, and will call back + * into the driver, so ensure no driver locks are held. + * + * Return: %true if changes are going to be made, %false otherwise + */ +bool ieee80211_prepare_rx_omi_bw(struct ieee80211_link_sta *link_sta, + enum ieee80211_sta_rx_bandwidth bw); + +/** + * ieee80211_finalize_rx_omi_bw - finalize BW RX OMI update + * @link_sta: the link STA the OMI was sent to + * + * See ieee80211_client_prepare_rx_omi_bw(). Context is the same here + * as well. + */ +void ieee80211_finalize_rx_omi_bw(struct ieee80211_link_sta *link_sta); + /* for older drivers - let's not document these ... */ int ieee80211_emulate_add_chanctx(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *ctx); diff --git a/include/net/mac802154.h b/include/net/mac802154.h index 4a3a9de9da73..d72006a85f02 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -7,7 +7,7 @@ #ifndef NET_MAC802154_H #define NET_MAC802154_H -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/af_ieee802154.h> #include <linux/ieee802154.h> #include <linux/skbuff.h> @@ -140,7 +140,7 @@ enum ieee802154_hw_flags { * * xmit_sync: * Handler that 802.15.4 module calls for each transmitted frame. - * skb cntains the buffer starting from the IEEE 802.15.4 header. + * skb contains the buffer starting from the IEEE 802.15.4 header. * The low-level driver should send the frame based on available * configuration. This is called by a workqueue and useful for * synchronous 802.15.4 drivers. @@ -152,7 +152,7 @@ enum ieee802154_hw_flags { * * xmit_async: * Handler that 802.15.4 module calls for each transmitted frame. - * skb cntains the buffer starting from the IEEE 802.15.4 header. + * skb contains the buffer starting from the IEEE 802.15.4 header. * The low-level driver should send the frame based on available * configuration. * This function should return zero or negative errno. diff --git a/include/net/macsec.h b/include/net/macsec.h index de216cbc6b05..bc7de5b53e54 100644 --- a/include/net/macsec.h +++ b/include/net/macsec.h @@ -38,8 +38,8 @@ struct metadata_dst; typedef union salt { struct { - u32 ssci; - u64 pn; + ssci_t ssci; + __be64 pn; } __packed; u8 bytes[MACSEC_SALT_LEN]; } __packed salt_t; diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index 27684135bb4d..3ce56a816425 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -60,6 +60,8 @@ enum gdma_eqe_type { GDMA_EQE_HWC_INIT_DONE = 131, GDMA_EQE_HWC_SOC_RECONFIG = 132, GDMA_EQE_HWC_SOC_RECONFIG_DATA = 133, + GDMA_EQE_HWC_SOC_SERVICE = 134, + GDMA_EQE_RNIC_QP_FATAL = 176, }; enum { @@ -69,6 +71,18 @@ enum { GDMA_DEVICE_MANA_IB = 3, }; +enum gdma_service_type { + GDMA_SERVICE_TYPE_NONE = 0, + GDMA_SERVICE_TYPE_RDMA_SUSPEND = 1, + GDMA_SERVICE_TYPE_RDMA_RESUME = 2, +}; + +struct mana_service_work { + struct work_struct work; + struct gdma_dev *gdma_dev; + enum gdma_service_type event; +}; + struct gdma_resource { /* Protect the bitmap */ spinlock_t lock; @@ -151,6 +165,7 @@ struct gdma_general_req { #define GDMA_MESSAGE_V1 1 #define GDMA_MESSAGE_V2 2 #define GDMA_MESSAGE_V3 3 +#define GDMA_MESSAGE_V4 4 struct gdma_general_resp { struct gdma_resp_hdr hdr; @@ -222,9 +237,19 @@ struct gdma_dev { void *driver_data; struct auxiliary_device *adev; + bool is_suspended; + bool rdma_teardown; }; -#define MINIMUM_SUPPORTED_PAGE_SIZE PAGE_SIZE +/* MANA_PAGE_SIZE is the DMA unit */ +#define MANA_PAGE_SHIFT 12 +#define MANA_PAGE_SIZE BIT(MANA_PAGE_SHIFT) +#define MANA_PAGE_ALIGN(x) ALIGN((x), MANA_PAGE_SIZE) +#define MANA_PAGE_ALIGNED(addr) IS_ALIGNED((unsigned long)(addr), MANA_PAGE_SIZE) +#define MANA_PFN(a) ((a) >> MANA_PAGE_SHIFT) + +/* Required by HW */ +#define MANA_MIN_QSIZE MANA_PAGE_SIZE #define GDMA_CQE_SIZE 64 #define GDMA_EQE_SIZE 16 @@ -258,7 +283,8 @@ struct gdma_event { struct gdma_queue; struct mana_eq { - struct gdma_queue *eq; + struct gdma_queue *eq; + struct dentry *mana_eq_debugfs; }; typedef void gdma_eq_callback(void *context, struct gdma_queue *q, @@ -356,6 +382,7 @@ struct gdma_irq_context { struct gdma_context { struct device *dev; + struct dentry *mana_pci_debugfs; /* Per-vPort max number of queues */ unsigned int max_num_queues; @@ -395,9 +422,11 @@ struct gdma_context { /* Azure RDMA adapter */ struct gdma_dev mana_ib; -}; -#define MAX_NUM_GDMA_DEVICES 4 + u64 pf_cap_flags1; + + struct workqueue_struct *service_wq; +}; static inline bool mana_gd_is_mana(struct gdma_dev *gd) { @@ -543,11 +572,18 @@ enum { */ #define GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX BIT(2) #define GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG BIT(3) +#define GDMA_DRV_CAP_FLAG_1_GDMA_PAGES_4MB_1GB_2GB BIT(4) +#define GDMA_DRV_CAP_FLAG_1_VARIABLE_INDIRECTION_TABLE_SUPPORT BIT(5) + +/* Driver can handle holes (zeros) in the device list */ +#define GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP BIT(11) #define GDMA_DRV_CAP_FLAGS1 \ (GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \ GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX | \ - GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG) + GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG | \ + GDMA_DRV_CAP_FLAG_1_VARIABLE_INDIRECTION_TABLE_SUPPORT | \ + GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP) #define GDMA_DRV_CAP_FLAGS2 0 @@ -608,11 +644,12 @@ struct gdma_query_max_resources_resp { }; /* HW DATA */ /* GDMA_LIST_DEVICES */ +#define GDMA_DEV_LIST_SIZE 64 struct gdma_list_devices_resp { struct gdma_resp_hdr hdr; u32 num_of_devs; u32 reserved; - struct gdma_dev_id devs[64]; + struct gdma_dev_id devs[GDMA_DEV_LIST_SIZE]; }; /* HW DATA */ /* GDMA_REGISTER_DEVICE */ @@ -690,20 +727,6 @@ struct gdma_query_hwc_timeout_resp { u32 reserved; }; -enum atb_page_size { - ATB_PAGE_SIZE_4K, - ATB_PAGE_SIZE_8K, - ATB_PAGE_SIZE_16K, - ATB_PAGE_SIZE_32K, - ATB_PAGE_SIZE_64K, - ATB_PAGE_SIZE_128K, - ATB_PAGE_SIZE_256K, - ATB_PAGE_SIZE_512K, - ATB_PAGE_SIZE_1M, - ATB_PAGE_SIZE_2M, - ATB_PAGE_SIZE_MAX, -}; - enum gdma_mr_access_flags { GDMA_ACCESS_FLAG_LOCAL_READ = BIT_ULL(0), GDMA_ACCESS_FLAG_LOCAL_WRITE = BIT_ULL(1), @@ -762,6 +785,7 @@ struct gdma_destroy_dma_region_req { enum gdma_pd_flags { GDMA_PD_FLAG_INVALID = 0, + GDMA_PD_FLAG_ALLOW_GPA_MR = 1, }; struct gdma_create_pd_req { @@ -787,11 +811,18 @@ struct gdma_destory_pd_resp { };/* HW DATA */ enum gdma_mr_type { + /* + * Guest Physical Address - MRs of this type allow access + * to any DMA-mapped memory using bus-logical address + */ + GDMA_MR_TYPE_GPA = 1, /* Guest Virtual Address - MRs of this type allow access * to memory mapped by PTEs associated with this MR using a virtual * address that is set up in the MST */ GDMA_MR_TYPE_GVA = 2, + /* Guest zero-based address MRs */ + GDMA_MR_TYPE_ZBVA = 4, }; struct gdma_create_mr_params { @@ -803,6 +834,10 @@ struct gdma_create_mr_params { u64 virtual_address; enum gdma_mr_access_flags access_flags; } gva; + struct { + u64 dma_region_handle; + enum gdma_mr_access_flags access_flags; + } zbva; }; }; @@ -818,7 +853,10 @@ struct gdma_create_mr_request { u64 virtual_address; enum gdma_mr_access_flags access_flags; } gva; - + struct { + u64 dma_region_handle; + enum gdma_mr_access_flags access_flags; + } zbva; }; u32 reserved_2; };/* HW DATA */ @@ -867,5 +905,9 @@ int mana_gd_send_request(struct gdma_context *gc, u32 req_len, const void *req, u32 resp_len, void *resp); int mana_gd_destroy_dma_region(struct gdma_context *gc, u64 dma_region_handle); +void mana_register_debugfs(void); +void mana_unregister_debugfs(void); + +int mana_rdma_service_event(struct gdma_context *gc, enum gdma_service_type event); #endif /* _GDMA_H */ diff --git a/include/net/mana/hw_channel.h b/include/net/mana/hw_channel.h index 158b125692c2..83cf93338eb3 100644 --- a/include/net/mana/hw_channel.h +++ b/include/net/mana/hw_channel.h @@ -49,6 +49,15 @@ union hwc_init_type_data { }; }; /* HW DATA */ +union hwc_init_soc_service_type { + u32 as_uint32; + + struct { + u32 value : 28; + u32 type : 4; + }; +}; /* HW DATA */ + struct hwc_rx_oob { u32 type : 6; u32 eom : 1; diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 4eeedf14711b..9abb66461211 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -30,19 +30,32 @@ enum TRI_STATE { }; /* Number of entries for hardware indirection table must be in power of 2 */ -#define MANA_INDIRECT_TABLE_SIZE 64 -#define MANA_INDIRECT_TABLE_MASK (MANA_INDIRECT_TABLE_SIZE - 1) +#define MANA_INDIRECT_TABLE_MAX_SIZE 512 +#define MANA_INDIRECT_TABLE_DEF_SIZE 64 /* The Toeplitz hash key's length in bytes: should be multiple of 8 */ #define MANA_HASH_KEY_SIZE 40 #define COMP_ENTRY_SIZE 64 -#define RX_BUFFERS_PER_QUEUE 512 +/* This Max value for RX buffers is derived from __alloc_page()'s max page + * allocation calculation. It allows maximum 2^(MAX_ORDER -1) pages. RX buffer + * size beyond this value gets rejected by __alloc_page() call. + */ +#define MAX_RX_BUFFERS_PER_QUEUE 8192 +#define DEF_RX_BUFFERS_PER_QUEUE 1024 +#define MIN_RX_BUFFERS_PER_QUEUE 128 + +/* This max value for TX buffers is derived as the maximum allocatable + * pages supported on host per guest through testing. TX buffer size beyond + * this value is rejected by the hardware. + */ +#define MAX_TX_BUFFERS_PER_QUEUE 16384 +#define DEF_TX_BUFFERS_PER_QUEUE 256 +#define MIN_TX_BUFFERS_PER_QUEUE 128 -#define MAX_SEND_BUFFERS_PER_QUEUE 256 +#define EQ_SIZE (8 * MANA_PAGE_SIZE) -#define EQ_SIZE (8 * PAGE_SIZE) #define LOG2_EQ_THROTTLE 3 #define MAX_PORTS_IN_MANA_DEV 256 @@ -97,6 +110,8 @@ struct mana_txq { atomic_t pending_sends; + bool napi_initialized; + struct mana_stats_tx stats; }; @@ -274,6 +289,7 @@ struct mana_cq { /* NAPI data */ struct napi_struct napi; int work_done; + int work_done_since_doorbell; int budget; }; @@ -284,7 +300,7 @@ struct mana_recv_buf_oob { void *buf_va; bool from_pool; /* allocated from a page pool */ - /* SGL of the buffer going to be sent has part of the work request. */ + /* SGL of the buffer going to be sent as part of the work request. */ u32 num_sge; struct gdma_sge sgl[MAX_RX_WQE_SGL_ENTRIES]; @@ -334,6 +350,7 @@ struct mana_rxq { int xdp_rc; /* XDP redirect return code */ struct page_pool *page_pool; + struct dentry *mana_rx_debugfs; /* MUST BE THE LAST MEMBER: * Each receive buffer has an associated mana_recv_buf_oob. @@ -347,6 +364,8 @@ struct mana_tx_qp { struct mana_cq tx_cq; mana_handle_t tx_object; + + struct dentry *mana_tx_debugfs; }; struct mana_ethtool_stats { @@ -389,8 +408,10 @@ struct mana_context { struct gdma_dev *gdma_dev; u16 num_ports; + u8 bm_hostmode; struct mana_eq *eqs; + struct dentry *mana_eqs_debugfs; struct net_device *ports[MAX_PORTS_IN_MANA_DEV]; }; @@ -410,10 +431,11 @@ struct mana_port_context { struct mana_tx_qp *tx_qp; /* Indirection Table for RX & TX. The values are queue indexes */ - u32 indir_table[MANA_INDIRECT_TABLE_SIZE]; + u32 *indir_table; + u32 indir_table_sz; /* Indirection table containing RxObject Handles */ - mana_handle_t rxobj_table[MANA_INDIRECT_TABLE_SIZE]; + mana_handle_t *rxobj_table; /* Hash key used by the NIC */ u8 hashkey[MANA_HASH_KEY_SIZE]; @@ -435,6 +457,9 @@ struct mana_port_context { unsigned int max_queues; unsigned int num_queues; + unsigned int rx_queue_size; + unsigned int tx_queue_size; + mana_handle_t port_handle; mana_handle_t pf_filter_handle; @@ -448,6 +473,9 @@ struct mana_port_context { bool port_st_save; /* Saved port state */ struct mana_ethtool_stats eth_stats; + + /* Debugfs */ + struct dentry *mana_port_debugfs; }; netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev); @@ -461,6 +489,9 @@ int mana_detach(struct net_device *ndev, bool from_close); int mana_probe(struct gdma_dev *gd, bool resuming); void mana_remove(struct gdma_dev *gd, bool suspending); +int mana_rdma_probe(struct gdma_dev *gd); +void mana_rdma_remove(struct gdma_dev *gd); + void mana_xdp_tx(struct sk_buff *skb, struct net_device *ndev); int mana_xdp_xmit(struct net_device *ndev, int n, struct xdp_frame **frames, u32 flags); @@ -470,8 +501,11 @@ struct bpf_prog *mana_xdp_get(struct mana_port_context *apc); void mana_chn_setxdp(struct mana_port_context *apc, struct bpf_prog *prog); int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf); void mana_query_gf_stats(struct mana_port_context *apc); +int mana_pre_alloc_rxbufs(struct mana_port_context *apc, int mtu, int num_queues); +void mana_pre_dealloc_rxbufs(struct mana_port_context *apc); extern const struct ethtool_ops mana_ethtool_ops; +extern struct dentry *mana_debugfs_root; /* A CQ can be created not associated with any EQ */ #define GDMA_CQ_NO_EQ 0xffff @@ -527,7 +561,8 @@ struct mana_query_device_cfg_resp { u64 pf_cap_flags4; u16 max_num_vports; - u16 reserved; + u8 bm_hostmode; /* response v3: Bare Metal Host Mode */ + u8 reserved; u32 max_num_eqs; /* response v2: */ @@ -670,6 +705,7 @@ struct mana_cfg_rx_steer_req_v2 { u8 hashkey[MANA_HASH_KEY_SIZE]; u8 cqe_coalescing_enable; u8 reserved2[7]; + mana_handle_t indir_tab[] __counted_by(num_indir_entries); }; /* HW DATA */ struct mana_cfg_rx_steer_resp { @@ -795,4 +831,8 @@ void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type, int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id, u32 doorbell_pg_id); void mana_uncfg_vport(struct mana_port_context *apc); + +struct net_device *mana_get_primary_netdev(struct mana_context *ac, + u32 port_index, + netdevice_tracker *tracker); #endif /* _MANA_H */ diff --git a/include/net/mctp.h b/include/net/mctp.h index 7b17c52e8ce2..07d458990113 100644 --- a/include/net/mctp.h +++ b/include/net/mctp.h @@ -212,7 +212,7 @@ static inline struct mctp_skb_cb *mctp_cb(struct sk_buff *skb) BUILD_BUG_ON(sizeof(struct mctp_skb_cb) > sizeof(skb->cb)); WARN_ON(cb->magic != 0x4d435450); - return (void *)(skb->cb); + return cb; } /* If CONFIG_MCTP_FLOWS, we may add one of these as a SKB extension, @@ -295,7 +295,25 @@ void mctp_neigh_remove_dev(struct mctp_dev *mdev); int mctp_routes_init(void); void mctp_routes_exit(void); -void mctp_device_init(void); +int mctp_device_init(void); void mctp_device_exit(void); +/* MCTP IDs and Codes from DMTF specification + * "DSP0239 Management Component Transport Protocol (MCTP) IDs and Codes" + * https://www.dmtf.org/sites/default/files/standards/documents/DSP0239_1.11.1.pdf + */ +enum mctp_phys_binding { + MCTP_PHYS_BINDING_UNSPEC = 0x00, + MCTP_PHYS_BINDING_SMBUS = 0x01, + MCTP_PHYS_BINDING_PCIE_VDM = 0x02, + MCTP_PHYS_BINDING_USB = 0x03, + MCTP_PHYS_BINDING_KCS = 0x04, + MCTP_PHYS_BINDING_SERIAL = 0x05, + MCTP_PHYS_BINDING_I3C = 0x06, + MCTP_PHYS_BINDING_MMBI = 0x07, + MCTP_PHYS_BINDING_PCC = 0x08, + MCTP_PHYS_BINDING_UCIE = 0x09, + MCTP_PHYS_BINDING_VENDOR = 0xFF, +}; + #endif /* __NET_MCTP_H */ diff --git a/include/net/mctpdevice.h b/include/net/mctpdevice.h index 5c0d04b5c12c..957d9ef924c5 100644 --- a/include/net/mctpdevice.h +++ b/include/net/mctpdevice.h @@ -22,6 +22,7 @@ struct mctp_dev { refcount_t refs; unsigned int net; + enum mctp_phys_binding binding; const struct mctp_netdev_ops *ops; @@ -44,7 +45,8 @@ struct mctp_dev *mctp_dev_get_rtnl(const struct net_device *dev); struct mctp_dev *__mctp_dev_get(const struct net_device *dev); int mctp_register_netdev(struct net_device *dev, - const struct mctp_netdev_ops *ops); + const struct mctp_netdev_ops *ops, + enum mctp_phys_binding binding); void mctp_unregister_netdev(struct net_device *dev); void mctp_dev_hold(struct mctp_dev *mdev); diff --git a/include/net/mptcp.h b/include/net/mptcp.h index fb996124b3d5..f7263fe2a2e4 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -14,6 +14,7 @@ struct mptcp_info; struct mptcp_sock; +struct mptcp_pm_addr_entry; struct seq_file; /* MPTCP sk_buff extension data */ @@ -97,17 +98,12 @@ struct mptcp_out_options { }; #define MPTCP_SCHED_NAME_MAX 16 -#define MPTCP_SUBFLOWS_MAX 8 - -struct mptcp_sched_data { - bool reinject; - u8 subflows; - struct mptcp_subflow_context *contexts[MPTCP_SUBFLOWS_MAX]; -}; +#define MPTCP_SCHED_MAX 128 +#define MPTCP_SCHED_BUF_MAX (MPTCP_SCHED_NAME_MAX * MPTCP_SCHED_MAX) struct mptcp_sched_ops { - int (*get_subflow)(struct mptcp_sock *msk, - struct mptcp_sched_data *data); + int (*get_send)(struct mptcp_sock *msk); + int (*get_retrans)(struct mptcp_sock *msk); char name[MPTCP_SCHED_NAME_MAX]; struct module *owner; @@ -117,6 +113,19 @@ struct mptcp_sched_ops { void (*release)(struct mptcp_sock *msk); } ____cacheline_aligned_in_smp; +#define MPTCP_PM_NAME_MAX 16 +#define MPTCP_PM_MAX 128 +#define MPTCP_PM_BUF_MAX (MPTCP_PM_NAME_MAX * MPTCP_PM_MAX) + +struct mptcp_pm_ops { + char name[MPTCP_PM_NAME_MAX]; + struct module *owner; + struct list_head list; + + void (*init)(struct mptcp_sock *msk); + void (*release)(struct mptcp_sock *msk); +} ____cacheline_aligned_in_smp; + #ifdef CONFIG_MPTCP void mptcp_init(void); @@ -220,6 +229,8 @@ static inline __be32 mptcp_reset_option(const struct sk_buff *skb) return htonl(0u); } + +void mptcp_active_detect_blackhole(struct sock *sk, bool expired); #else static inline void mptcp_init(void) @@ -304,6 +315,8 @@ static inline struct request_sock *mptcp_subflow_reqsk_alloc(const struct reques } static inline __be32 mptcp_reset_option(const struct sk_buff *skb) { return htonl(0u); } + +static inline void mptcp_active_detect_blackhole(struct sock *sk, bool expired) { } #endif /* CONFIG_MPTCP */ #if IS_ENABLED(CONFIG_MPTCP_IPV6) diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 9bbdf6eaa942..3c88d5bc5eed 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -147,11 +147,6 @@ void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data, * The following hooks can be defined; unless noted otherwise, they are * optional and can be filled with a null pointer. * - * int (*is_useropt)(u8 nd_opt_type): - * This function is called when IPv6 decide RA userspace options. if - * this function returns 1 then the option given by nd_opt_type will - * be handled as userspace option additional to the IPv6 options. - * * int (*parse_options)(const struct net_device *dev, * struct nd_opt_hdr *nd_opt, * struct ndisc_options *ndopts): @@ -200,7 +195,6 @@ void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data, * addresses. E.g. 802.15.4 6LoWPAN. */ struct ndisc_ops { - int (*is_useropt)(u8 nd_opt_type); int (*parse_options)(const struct net_device *dev, struct nd_opt_hdr *nd_opt, struct ndisc_options *ndopts); @@ -224,15 +218,6 @@ struct ndisc_ops { }; #if IS_ENABLED(CONFIG_IPV6) -static inline int ndisc_ops_is_useropt(const struct net_device *dev, - u8 nd_opt_type) -{ - if (dev->ndisc_ops && dev->ndisc_ops->is_useropt) - return dev->ndisc_ops->is_useropt(nd_opt_type); - else - return 0; -} - static inline int ndisc_ops_parse_options(const struct net_device *dev, struct nd_opt_hdr *nd_opt, struct ndisc_options *ndopts) @@ -486,7 +471,7 @@ void igmp6_event_report(struct sk_buff *skb); #ifdef CONFIG_SYSCTL -int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, +int ndisc_ifinfo_sysctl_change(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); #endif diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 0d28172193fa..9a832cab5b1d 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -29,6 +29,7 @@ #include <linux/sysctl.h> #include <linux/workqueue.h> #include <net/rtnetlink.h> +#include <net/neighbour_tables.h> /* * NUD stands for "neighbor unreachability detection" @@ -135,7 +136,8 @@ struct neigh_statistics { #define NEIGH_CACHE_STAT_INC(tbl, field) this_cpu_inc((tbl)->stats->field) struct neighbour { - struct neighbour __rcu *next; + struct hlist_node hash; + struct hlist_node dev_list; struct neigh_table *tbl; struct neigh_parms *parms; unsigned long confirmed; @@ -190,7 +192,7 @@ struct pneigh_entry { #define NEIGH_NUM_HASH_RND 4 struct neigh_hash_table { - struct neighbour __rcu **hash_buckets; + struct hlist_head *hash_heads; unsigned int hash_shift; __u32 hash_rnd[NEIGH_NUM_HASH_RND]; struct rcu_head rcu; @@ -236,14 +238,6 @@ struct neigh_table { struct pneigh_entry **phash_buckets; }; -enum { - NEIGH_ARP_TABLE = 0, - 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) { return p->tbl->family; @@ -276,6 +270,12 @@ static inline void *neighbour_priv(const struct neighbour *n) extern const struct nla_policy nda_policy[]; +#define neigh_for_each_in_bucket(pos, head) hlist_for_each_entry(pos, head, hash) +#define neigh_for_each_in_bucket_rcu(pos, head) \ + hlist_for_each_entry_rcu(pos, head, hash) +#define neigh_for_each_in_bucket_safe(pos, tmp, head) \ + hlist_for_each_entry_safe(pos, tmp, head, hash) + static inline bool neigh_key_eq32(const struct neighbour *n, const void *pkey) { return *(const u32 *)n->primary_key == *(const u32 *)pkey; @@ -304,12 +304,9 @@ static inline struct neighbour *___neigh_lookup_noref( u32 hash_val; hash_val = hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift); - for (n = rcu_dereference(nht->hash_buckets[hash_val]); - n != NULL; - n = rcu_dereference(n->next)) { + neigh_for_each_in_bucket_rcu(n, &nht->hash_heads[hash_val]) if (n->dev == dev && key_eq(n, pkey)) return n; - } return NULL; } @@ -350,7 +347,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb, int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u32 nlmsg_pid); void __neigh_set_probe_once(struct neighbour *neigh); -bool neigh_remove_one(struct neighbour *ndel, struct neigh_table *tbl); +bool neigh_remove_one(struct neighbour *ndel); void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev); int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev); int neigh_carrier_down(struct neigh_table *tbl, struct net_device *dev); @@ -412,12 +409,12 @@ void *neigh_seq_start(struct seq_file *, loff_t *, struct neigh_table *, void *neigh_seq_next(struct seq_file *, void *, loff_t *); void neigh_seq_stop(struct seq_file *, void *); -int neigh_proc_dointvec(struct ctl_table *ctl, int write, +int neigh_proc_dointvec(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); -int neigh_proc_dointvec_jiffies(struct ctl_table *ctl, int write, +int neigh_proc_dointvec_jiffies(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); -int neigh_proc_dointvec_ms_jiffies(struct ctl_table *ctl, int write, +int neigh_proc_dointvec_ms_jiffies(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, diff --git a/include/net/neighbour_tables.h b/include/net/neighbour_tables.h new file mode 100644 index 000000000000..bcffbe8f7601 --- /dev/null +++ b/include/net/neighbour_tables.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _NET_NEIGHBOUR_TABLES_H +#define _NET_NEIGHBOUR_TABLES_H + +enum { + NEIGH_ARP_TABLE = 0, + NEIGH_ND_TABLE = 1, + NEIGH_NR_TABLES, + NEIGH_LINK_TABLE = NEIGH_NR_TABLES /* Pseudo table for neigh_xmit */ +}; + +#endif diff --git a/include/net/net_debug.h b/include/net/net_debug.h index 1e74684cbbdb..47f7a4a878b9 100644 --- a/include/net/net_debug.h +++ b/include/net/net_debug.h @@ -27,7 +27,7 @@ void netdev_info(const struct net_device *dev, const char *format, ...); #define netdev_level_once(level, dev, fmt, ...) \ do { \ - static bool __section(".data.once") __print_once; \ + static bool __section(".data..once") __print_once; \ \ if (!__print_once) { \ __print_once = true; \ @@ -149,9 +149,11 @@ do { \ #if defined(CONFIG_DEBUG_NET) -#define DEBUG_NET_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond) +#define DEBUG_NET_WARN_ON_ONCE(cond) ((void)WARN_ON_ONCE(cond)) +#define DEBUG_NET_WARN_ONCE(cond, format...) ((void)WARN_ONCE(cond, format)) #else #define DEBUG_NET_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond) +#define DEBUG_NET_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond) #endif #endif /* _LINUX_NET_DEBUG_H */ diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 20c34bd7a077..025a7574b275 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -80,8 +80,12 @@ struct net { * or to unregister pernet ops * (pernet_ops_rwsem write locked). */ + struct llist_node defer_free_list; struct llist_node cleanup_list; /* namespaces on death row */ + struct list_head ptype_all; + struct list_head ptype_specific; + #ifdef CONFIG_KEYS struct key_tag *key_domain; /* Key domain of operation tag */ #endif @@ -188,6 +192,10 @@ struct net { #if IS_ENABLED(CONFIG_SMC) struct netns_smc smc; #endif +#ifdef CONFIG_DEBUG_NET_SMALL_RTNL + /* Move to a better place when the config guard is removed. */ + struct mutex rtnl_mutex; +#endif } __randomize_layout; #include <linux/seq_file_net.h> @@ -205,6 +213,8 @@ void net_ns_barrier(void); struct ns_common *get_net_ns(struct ns_common *ns); struct net *get_net_ns_by_fd(int fd); +extern struct task_struct *cleanup_net_task; + #else /* CONFIG_NET_NS */ #include <linux/sched.h> #include <linux/nsproxy.h> @@ -290,6 +300,7 @@ static inline int check_net(const struct net *net) } void net_drop_ns(void *); +void net_passive_dec(struct net *net); #else @@ -319,8 +330,23 @@ static inline int check_net(const struct net *net) } #define net_drop_ns NULL + +static inline void net_passive_dec(struct net *net) +{ + refcount_dec(&net->passive); +} #endif +static inline void net_passive_inc(struct net *net) +{ + refcount_inc(&net->passive); +} + +/* Returns true if the netns initialization is completed successfully */ +static inline bool net_initialized(const struct net *net) +{ + return READ_ONCE(net->list.next); +} static inline void __netns_tracker_alloc(struct net *net, netns_tracker *tracker, @@ -386,7 +412,7 @@ static inline struct net *read_pnet(const possible_net_t *pnet) #endif } -static inline struct net *read_pnet_rcu(possible_net_t *pnet) +static inline struct net *read_pnet_rcu(const possible_net_t *pnet) { #ifdef CONFIG_NET_NS return rcu_dereference(pnet->net); @@ -449,10 +475,10 @@ struct pernet_operations { void (*exit)(struct net *net); void (*exit_batch)(struct list_head *net_exit_list); /* Following method is called with RTNL held. */ - void (*exit_batch_rtnl)(struct list_head *net_exit_list, - struct list_head *dev_kill_list); - unsigned int *id; - size_t size; + void (*exit_rtnl)(struct net *net, + struct list_head *dev_kill_list); + unsigned int * const id; + const size_t size; }; /* diff --git a/include/net/net_shaper.h b/include/net/net_shaper.h new file mode 100644 index 000000000000..5c3f49b52fe9 --- /dev/null +++ b/include/net/net_shaper.h @@ -0,0 +1,120 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef _NET_SHAPER_H_ +#define _NET_SHAPER_H_ + +#include <linux/types.h> + +#include <uapi/linux/net_shaper.h> + +struct net_device; +struct devlink; +struct netlink_ext_ack; + +enum net_shaper_binding_type { + NET_SHAPER_BINDING_TYPE_NETDEV, + /* NET_SHAPER_BINDING_TYPE_DEVLINK_PORT */ +}; + +struct net_shaper_binding { + enum net_shaper_binding_type type; + union { + struct net_device *netdev; + struct devlink *devlink; + }; +}; + +struct net_shaper_handle { + enum net_shaper_scope scope; + u32 id; +}; + +/** + * struct net_shaper - represents a shaping node on the NIC H/W + * zeroed field are considered not set. + * @parent: Unique identifier for the shaper parent, usually implied + * @handle: Unique identifier for this shaper + * @metric: Specify if the rate limits refers to PPS or BPS + * @bw_min: Minimum guaranteed rate for this shaper + * @bw_max: Maximum peak rate allowed for this shaper + * @burst: Maximum burst for the peek rate of this shaper + * @priority: Scheduling priority for this shaper + * @weight: Scheduling weight for this shaper + */ +struct net_shaper { + struct net_shaper_handle parent; + struct net_shaper_handle handle; + enum net_shaper_metric metric; + u64 bw_min; + u64 bw_max; + u64 burst; + u32 priority; + u32 weight; + + /* private: */ + u32 leaves; /* accounted only for NODE scope */ + struct rcu_head rcu; +}; + +/** + * struct net_shaper_ops - Operations on device H/W shapers + * + * The operations applies to either net_device and devlink objects. + * The initial shaping configuration at device initialization is empty: + * does not constraint the rate in any way. + * The network core keeps track of the applied user-configuration in + * the net_device or devlink structure. + * The operations are serialized via a per device lock. + * + * Device not supporting any kind of nesting should not provide the + * group operation. + * + * Each shaper is uniquely identified within the device with a 'handle' + * comprising the shaper scope and a scope-specific id. + */ +struct net_shaper_ops { + /** + * @group: create the specified shapers scheduling group + * + * Nest the @leaves shapers identified under the * @node shaper. + * All the shapers belong to the device specified by @binding. + * The @leaves arrays size is specified by @leaves_count. + * Create either the @leaves and the @node shaper; or if they already + * exists, links them together in the desired way. + * @leaves scope must be NET_SHAPER_SCOPE_QUEUE. + */ + int (*group)(struct net_shaper_binding *binding, int leaves_count, + const struct net_shaper *leaves, + const struct net_shaper *node, + struct netlink_ext_ack *extack); + + /** + * @set: Updates the specified shaper + * + * Updates or creates the @shaper on the device specified by @binding. + */ + int (*set)(struct net_shaper_binding *binding, + const struct net_shaper *shaper, + struct netlink_ext_ack *extack); + + /** + * @delete: Removes the specified shaper + * + * Removes the shaper configuration as identified by the given @handle + * on the device specified by @binding, restoring the default behavior. + */ + int (*delete)(struct net_shaper_binding *binding, + const struct net_shaper_handle *handle, + struct netlink_ext_ack *extack); + + /** + * @capabilities: get the shaper features supported by the device + * + * Fills the bitmask @cap with the supported capabilities for the + * specified @scope and device specified by @binding. + */ + void (*capabilities)(struct net_shaper_binding *binding, + enum net_shaper_scope scope, unsigned long *cap); +}; + +#endif diff --git a/include/net/netdev_lock.h b/include/net/netdev_lock.h new file mode 100644 index 000000000000..3d3aef80beac --- /dev/null +++ b/include/net/netdev_lock.h @@ -0,0 +1,138 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef _NET_NETDEV_LOCK_H +#define _NET_NETDEV_LOCK_H + +#include <linux/lockdep.h> +#include <linux/netdevice.h> +#include <linux/rtnetlink.h> + +static inline bool netdev_trylock(struct net_device *dev) +{ + return mutex_trylock(&dev->lock); +} + +static inline void netdev_assert_locked(const struct net_device *dev) +{ + lockdep_assert_held(&dev->lock); +} + +static inline void +netdev_assert_locked_or_invisible(const struct net_device *dev) +{ + if (dev->reg_state == NETREG_REGISTERED || + dev->reg_state == NETREG_UNREGISTERING) + netdev_assert_locked(dev); +} + +static inline bool netdev_need_ops_lock(const struct net_device *dev) +{ + bool ret = dev->request_ops_lock || !!dev->queue_mgmt_ops; + +#if IS_ENABLED(CONFIG_NET_SHAPER) + ret |= !!dev->netdev_ops->net_shaper_ops; +#endif + + return ret; +} + +static inline void netdev_lock_ops(struct net_device *dev) +{ + if (netdev_need_ops_lock(dev)) + netdev_lock(dev); +} + +static inline void netdev_unlock_ops(struct net_device *dev) +{ + if (netdev_need_ops_lock(dev)) + netdev_unlock(dev); +} + +static inline void netdev_lock_ops_to_full(struct net_device *dev) +{ + if (netdev_need_ops_lock(dev)) + netdev_assert_locked(dev); + else + netdev_lock(dev); +} + +static inline void netdev_unlock_full_to_ops(struct net_device *dev) +{ + if (netdev_need_ops_lock(dev)) + netdev_assert_locked(dev); + else + netdev_unlock(dev); +} + +static inline void netdev_ops_assert_locked(const struct net_device *dev) +{ + if (netdev_need_ops_lock(dev)) + lockdep_assert_held(&dev->lock); + else + ASSERT_RTNL(); +} + +static inline void +netdev_ops_assert_locked_or_invisible(const struct net_device *dev) +{ + if (dev->reg_state == NETREG_REGISTERED || + dev->reg_state == NETREG_UNREGISTERING) + netdev_ops_assert_locked(dev); +} + +static inline void netdev_lock_ops_compat(struct net_device *dev) +{ + if (netdev_need_ops_lock(dev)) + netdev_lock(dev); + else + rtnl_lock(); +} + +static inline void netdev_unlock_ops_compat(struct net_device *dev) +{ + if (netdev_need_ops_lock(dev)) + netdev_unlock(dev); + else + rtnl_unlock(); +} + +static inline int netdev_lock_cmp_fn(const struct lockdep_map *a, + const struct lockdep_map *b) +{ + if (a == b) + return 0; + + /* Allow locking multiple devices only under rtnl_lock, + * the exact order doesn't matter. + * Note that upper devices don't lock their ops, so nesting + * mostly happens in batched device removal for now. + */ + return lockdep_rtnl_is_held() ? -1 : 1; +} + +#define netdev_lockdep_set_classes(dev) \ +{ \ + static struct lock_class_key qdisc_tx_busylock_key; \ + static struct lock_class_key qdisc_xmit_lock_key; \ + static struct lock_class_key dev_addr_list_lock_key; \ + static struct lock_class_key dev_instance_lock_key; \ + unsigned int i; \ + \ + (dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key; \ + lockdep_set_class(&(dev)->addr_list_lock, \ + &dev_addr_list_lock_key); \ + lockdep_set_class(&(dev)->lock, \ + &dev_instance_lock_key); \ + lock_set_cmp_fn(&dev->lock, netdev_lock_cmp_fn, NULL); \ + for (i = 0; i < (dev)->num_tx_queues; i++) \ + lockdep_set_class(&(dev)->_tx[i]._xmit_lock, \ + &qdisc_xmit_lock_key); \ +} + +#define netdev_lock_dereference(p, dev) \ + rcu_dereference_protected(p, lockdep_is_held(&(dev)->lock)) + +int netdev_debug_event(struct notifier_block *nb, unsigned long event, + void *ptr); + +#endif diff --git a/include/net/netdev_netlink.h b/include/net/netdev_netlink.h new file mode 100644 index 000000000000..075962dbe743 --- /dev/null +++ b/include/net/netdev_netlink.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __NET_NETDEV_NETLINK_H +#define __NET_NETDEV_NETLINK_H + +#include <linux/list.h> + +struct netdev_nl_sock { + struct mutex lock; + struct list_head bindings; +}; + +#endif /* __NET_NETDEV_NETLINK_H */ diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h index 1ec408585373..ba2eaf39089b 100644 --- a/include/net/netdev_queues.h +++ b/include/net/netdev_queues.h @@ -4,16 +4,57 @@ #include <linux/netdevice.h> +/** + * struct netdev_config - queue-related configuration for a netdev + * @hds_thresh: HDS Threshold value. + * @hds_config: HDS value from userspace. + */ +struct netdev_config { + u32 hds_thresh; + u8 hds_config; +}; + /* See the netdev.yaml spec for definition of each statistic */ struct netdev_queue_stats_rx { u64 bytes; u64 packets; u64 alloc_fail; + + u64 hw_drops; + u64 hw_drop_overruns; + + u64 csum_complete; + u64 csum_unnecessary; + u64 csum_none; + u64 csum_bad; + + u64 hw_gro_packets; + u64 hw_gro_bytes; + u64 hw_gro_wire_packets; + u64 hw_gro_wire_bytes; + + u64 hw_drop_ratelimits; }; struct netdev_queue_stats_tx { u64 bytes; u64 packets; + + u64 hw_drops; + u64 hw_drop_errors; + + u64 csum_none; + u64 needs_csum; + + u64 hw_gso_packets; + u64 hw_gso_bytes; + u64 hw_gso_wire_packets; + u64 hw_gso_wire_bytes; + + u64 hw_drop_ratelimits; + + u64 stop; + u64 wake; }; /** @@ -32,6 +73,8 @@ struct netdev_queue_stats_tx { * statistics will not generally add up to the total number of events for * the device. The @get_base_stats callback allows filling in the delta * between events for currently live queues and overall device history. + * @get_base_stats can also be used to report any miscellaneous packets + * transferred outside of the main set of queues used by the networking stack. * When the statistics for the entire device are queried, first @get_base_stats * is issued to collect the delta, and then a series of per-queue callbacks. * Only statistics which are set in @get_base_stats will be reported @@ -42,9 +85,11 @@ struct netdev_queue_stats_tx { * for some of the events is not maintained, and reliable "total" cannot * be provided). * + * Ops are called under the instance lock if netdev_need_ops_lock() + * returns true, otherwise under rtnl_lock. * Device drivers can assume that when collecting total device stats, * the @get_base_stats and subsequent per-queue calls are performed - * "atomically" (without releasing the rtnl_lock). + * "atomically" (without releasing the relevant lock). * * Device drivers are encouraged to reset the per-queue statistics when * number of queues change. This is because the primary use case for @@ -60,6 +105,47 @@ struct netdev_stat_ops { struct netdev_queue_stats_tx *tx); }; +void netdev_stat_queue_sum(struct net_device *netdev, + int rx_start, int rx_end, + struct netdev_queue_stats_rx *rx_sum, + int tx_start, int tx_end, + struct netdev_queue_stats_tx *tx_sum); + +/** + * struct netdev_queue_mgmt_ops - netdev ops for queue management + * + * @ndo_queue_mem_size: Size of the struct that describes a queue's memory. + * + * @ndo_queue_mem_alloc: Allocate memory for an RX queue at the specified index. + * The new memory is written at the specified address. + * + * @ndo_queue_mem_free: Free memory from an RX queue. + * + * @ndo_queue_start: Start an RX queue with the specified memory and at the + * specified index. + * + * @ndo_queue_stop: Stop the RX queue at the specified index. The stopped + * queue's memory is written at the specified address. + * + * Note that @ndo_queue_mem_alloc and @ndo_queue_mem_free may be called while + * the interface is closed. @ndo_queue_start and @ndo_queue_stop will only + * be called for an interface which is open. + */ +struct netdev_queue_mgmt_ops { + size_t ndo_queue_mem_size; + int (*ndo_queue_mem_alloc)(struct net_device *dev, + void *per_queue_mem, + int idx); + void (*ndo_queue_mem_free)(struct net_device *dev, + void *per_queue_mem); + int (*ndo_queue_start)(struct net_device *dev, + void *per_queue_mem, + int idx); + int (*ndo_queue_stop)(struct net_device *dev, + void *per_queue_mem, + int idx); +}; + /** * DOC: Lockless queue stopping / waking helpers. * @@ -202,27 +288,27 @@ netdev_txq_completed_mb(struct netdev_queue *dev_queue, #define netif_subqueue_try_stop(dev, idx, get_desc, start_thrs) \ ({ \ - struct netdev_queue *txq; \ + struct netdev_queue *_txq; \ \ - txq = netdev_get_tx_queue(dev, idx); \ - netif_txq_try_stop(txq, get_desc, start_thrs); \ + _txq = netdev_get_tx_queue(dev, idx); \ + netif_txq_try_stop(_txq, get_desc, start_thrs); \ }) #define netif_subqueue_maybe_stop(dev, idx, get_desc, stop_thrs, start_thrs) \ ({ \ - struct netdev_queue *txq; \ + struct netdev_queue *_txq; \ \ - txq = netdev_get_tx_queue(dev, idx); \ - netif_txq_maybe_stop(txq, get_desc, stop_thrs, start_thrs); \ + _txq = netdev_get_tx_queue(dev, idx); \ + netif_txq_maybe_stop(_txq, get_desc, stop_thrs, start_thrs); \ }) #define netif_subqueue_completed_wake(dev, idx, pkts, bytes, \ get_desc, start_thrs) \ ({ \ - struct netdev_queue *txq; \ + struct netdev_queue *_txq; \ \ - txq = netdev_get_tx_queue(dev, idx); \ - netif_txq_completed_wake(txq, pkts, bytes, \ + _txq = netdev_get_tx_queue(dev, idx); \ + netif_txq_completed_wake(_txq, pkts, bytes, \ get_desc, start_thrs); \ }) diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h index aa1716fb0e53..8cdcd138b33f 100644 --- a/include/net/netdev_rx_queue.h +++ b/include/net/netdev_rx_queue.h @@ -6,6 +6,7 @@ #include <linux/netdevice.h> #include <linux/sysfs.h> #include <net/xdp.h> +#include <net/page_pool/types.h> /* This structure contains an instance of an RX queue. */ struct netdev_rx_queue { @@ -15,16 +16,18 @@ struct netdev_rx_queue { struct rps_dev_flow_table __rcu *rps_flow_table; #endif struct kobject kobj; + const struct attribute_group **groups; struct net_device *dev; netdevice_tracker dev_tracker; + /* All fields below are "ops protected", + * see comment about net_device::lock + */ #ifdef CONFIG_XDP_SOCKETS struct xsk_buff_pool *pool; #endif - /* NAPI instance for the queue - * Readers and writers must hold RTNL - */ struct napi_struct *napi; + struct pp_memory_provider_params mp_params; } ____cacheline_aligned_in_smp; /* @@ -43,7 +46,6 @@ __netif_get_rx_queue(struct net_device *dev, unsigned int rxq) return dev->_rx + rxq; } -#ifdef CONFIG_SYSFS static inline unsigned int get_netdev_rx_queue_index(struct netdev_rx_queue *queue) { @@ -53,5 +55,7 @@ get_netdev_rx_queue_index(struct netdev_rx_queue *queue) BUG_ON(index >= dev->num_rx_queues); return index; } -#endif + +int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq); + #endif diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index cba3ccf03fcc..3f02a45773e8 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -204,8 +204,7 @@ bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff, struct nf_conntrack_tuple *tuple); void __nf_ct_refresh_acct(struct nf_conn *ct, enum ip_conntrack_info ctinfo, - const struct sk_buff *skb, - u32 extra_jiffies, bool do_acct); + u32 extra_jiffies, unsigned int bytes); /* Refresh conntrack for this many jiffies and do accounting */ static inline void nf_ct_refresh_acct(struct nf_conn *ct, @@ -213,15 +212,14 @@ static inline void nf_ct_refresh_acct(struct nf_conn *ct, const struct sk_buff *skb, u32 extra_jiffies) { - __nf_ct_refresh_acct(ct, ctinfo, skb, extra_jiffies, true); + __nf_ct_refresh_acct(ct, ctinfo, extra_jiffies, skb->len); } /* Refresh conntrack for this many jiffies */ static inline void nf_ct_refresh(struct nf_conn *ct, - const struct sk_buff *skb, u32 extra_jiffies) { - __nf_ct_refresh_acct(ct, 0, skb, extra_jiffies, false); + __nf_ct_refresh_acct(ct, 0, extra_jiffies, 0); } /* kill conntrack and do accounting */ @@ -314,16 +312,6 @@ static inline bool nf_ct_should_gc(const struct nf_conn *ct) #define NF_CT_DAY (86400 * HZ) -/* Set an arbitrary timeout large enough not to ever expire, this save - * us a check for the IPS_OFFLOAD_BIT from the packet path via - * nf_ct_is_expired(). - */ -static inline void nf_ct_offload_timeout(struct nf_conn *ct) -{ - if (nf_ct_expires(ct) < NF_CT_DAY / 2) - WRITE_ONCE(ct->timeout, nfct_time_stamp + NF_CT_DAY); -} - struct kernel_param; int nf_conntrack_set_hashsize(const char *val, const struct kernel_param *kp); diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h index e227d997fc71..1b58b5b91ff6 100644 --- a/include/net/netfilter/nf_conntrack_count.h +++ b/include/net/netfilter/nf_conntrack_count.h @@ -15,10 +15,8 @@ struct nf_conncount_list { unsigned int count; /* length of list */ }; -struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family, - unsigned int keylen); -void nf_conncount_destroy(struct net *net, unsigned int family, - struct nf_conncount_data *data); +struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int keylen); +void nf_conncount_destroy(struct net *net, struct nf_conncount_data *data); unsigned int nf_conncount_count(struct net *net, struct nf_conncount_data *data, diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index 0c1dac318e02..8dcf7c371ee9 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -12,6 +12,7 @@ #include <linux/netfilter/nf_conntrack_common.h> #include <linux/netfilter/nf_conntrack_tuple_common.h> #include <net/netfilter/nf_conntrack_extend.h> +#include <asm/local64.h> enum nf_ct_ecache_state { NFCT_ECACHE_DESTROY_FAIL, /* tried but failed to send destroy event */ @@ -20,6 +21,9 @@ enum nf_ct_ecache_state { struct nf_conntrack_ecache { unsigned long cache; /* bitops want long */ +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + local64_t timestamp; /* event timestamp, in nanoseconds */ +#endif u16 ctmask; /* bitmask of ct events to be delivered */ u16 expmask; /* bitmask of expect events to be delivered */ u32 missed; /* missed events */ @@ -108,6 +112,14 @@ nf_conntrack_event_cache(enum ip_conntrack_events event, struct nf_conn *ct) if (e == NULL) return; +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + /* renew only if this is the first cached event, so that the + * timestamp reflects the first, not the last, generated event. + */ + if (local64_read(&e->timestamp) && READ_ONCE(e->cache) == 0) + local64_set(&e->timestamp, ktime_get_real_ns()); +#endif + set_bit(event, &e->cache); #endif } diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 9abb7ee40d72..d711642e78b5 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -163,6 +163,7 @@ struct flow_offload_tuple_rhash { enum nf_flow_flags { NF_FLOW_SNAT, NF_FLOW_DNAT, + NF_FLOW_CLOSING, NF_FLOW_TEARDOWN, NF_FLOW_HW, NF_FLOW_HW_DYING, @@ -305,11 +306,26 @@ struct flow_ports { __be16 source, dest; }; +struct nf_flowtable *nf_flowtable_by_dev(const struct net_device *dev); +int nf_flow_offload_xdp_setup(struct nf_flowtable *flowtable, + struct net_device *dev, + enum flow_block_command cmd); + unsigned int nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); unsigned int nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); +#if (IS_BUILTIN(CONFIG_NF_FLOW_TABLE) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \ + (IS_MODULE(CONFIG_NF_FLOW_TABLE) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) +extern int nf_flow_register_bpf(void); +#else +static inline int nf_flow_register_bpf(void) +{ + return 0; +} +#endif + #define MODULE_ALIAS_NF_FLOWTABLE(family) \ MODULE_ALIAS("nf-flowtable-" __stringify(family)) diff --git a/include/net/netfilter/nf_hooks_lwtunnel.h b/include/net/netfilter/nf_hooks_lwtunnel.h index 52e27920f829..cef7a4eb8f97 100644 --- a/include/net/netfilter/nf_hooks_lwtunnel.h +++ b/include/net/netfilter/nf_hooks_lwtunnel.h @@ -2,6 +2,6 @@ #include <linux/types.h> #ifdef CONFIG_SYSCTL -int nf_hooks_lwtunnel_sysctl_handler(struct ctl_table *table, int write, +int nf_hooks_lwtunnel_sysctl_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); #endif diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 3f1ed467f951..e4d8e451e935 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -2,7 +2,7 @@ #ifndef _NET_NF_TABLES_H #define _NET_NF_TABLES_H -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/list.h> #include <linux/netfilter.h> #include <linux/netfilter/nfnetlink.h> @@ -209,6 +209,7 @@ static inline void nft_data_copy(u32 *dst, const struct nft_data *src, * @family: protocol family * @level: depth of the chains * @report: notify via unicast netlink message + * @reg_inited: bitmap of initialised registers */ struct nft_ctx { struct net *net; @@ -221,6 +222,7 @@ struct nft_ctx { u8 family; u8 level; bool report; + DECLARE_BITMAP(reg_inited, NFT_REG32_NUM); }; enum nft_data_desc_flags { @@ -254,7 +256,8 @@ static inline enum nft_registers nft_type_to_reg(enum nft_data_types type) int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest); int nft_dump_register(struct sk_buff *skb, unsigned int attr, unsigned int reg); -int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len); +int nft_parse_register_load(const struct nft_ctx *ctx, + const struct nlattr *attr, u8 *sreg, u32 len); int nft_parse_register_store(const struct nft_ctx *ctx, const struct nlattr *attr, u8 *dreg, const struct nft_data *data, @@ -311,6 +314,7 @@ static inline void *nft_elem_priv_cast(const struct nft_elem_priv *priv) /** * enum nft_iter_type - nftables set iterator type * + * @NFT_ITER_UNSPEC: unspecified, to catch errors * @NFT_ITER_READ: read-only iteration over set elements * @NFT_ITER_UPDATE: iteration under mutex to update set element state */ @@ -416,7 +420,7 @@ struct nft_expr_info; int nft_expr_inner_parse(const struct nft_ctx *ctx, const struct nlattr *nla, struct nft_expr_info *info); -int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src); +int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src, gfp_t gfp); 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, bool reset); @@ -438,6 +442,9 @@ struct nft_set_ext; * @remove: remove element from set * @walk: iterate over all set elements * @get: get set elements + * @ksize: kernel set size + * @usize: userspace set size + * @adjust_maxsize: delta to adjust maximum set size * @commit: commit set elements * @abort: abort set elements * @privsize: function to return size of set private data @@ -491,6 +498,9 @@ struct nft_set_ops { const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags); + u32 (*ksize)(u32 size); + u32 (*usize)(u32 size); + u32 (*adjust_maxsize)(const struct nft_set *set); void (*commit)(struct nft_set *set); void (*abort)(const struct nft_set *set); u64 (*privsize)(const struct nlattr * const nla[], @@ -619,6 +629,11 @@ static inline void *nft_set_priv(const struct nft_set *set) return (void *)set->data; } +static inline enum nft_data_types nft_set_datatype(const struct nft_set *set) +{ + return set->dtype == NFT_DATA_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE; +} + static inline bool nft_set_gc_is_pending(const struct nft_set *s) { return refcount_read(&s->refs) != 1; @@ -678,9 +693,8 @@ void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set); * @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_EXPRESSIONS: expressions assiciated with the element + * @NFT_SET_EXT_EXPRESSIONS: expressions associated with the element * @NFT_SET_EXT_OBJREF: stateful object reference associated with element * @NFT_SET_EXT_NUM: number of extension types */ @@ -690,7 +704,6 @@ enum nft_set_extensions { NFT_SET_EXT_DATA, NFT_SET_EXT_FLAGS, NFT_SET_EXT_TIMEOUT, - NFT_SET_EXT_EXPIRATION, NFT_SET_EXT_USERDATA, NFT_SET_EXT_EXPRESSIONS, NFT_SET_EXT_OBJREF, @@ -726,15 +739,18 @@ struct nft_set_ext_tmpl { /** * struct nft_set_ext - set extensions * - * @genmask: generation mask + * @genmask: generation mask, but also flags (see NFT_SET_ELEM_DEAD_BIT) * @offset: offsets of individual extension types * @data: beginning of extension data + * + * This structure must be aligned to word size, otherwise atomic bitops + * on genmask field can cause alignment failure on some archs. */ struct nft_set_ext { u8 genmask; u8 offset[NFT_SET_EXT_NUM]; char data[]; -}; +} __aligned(BITS_PER_LONG / 8); static inline void nft_set_ext_prepare(struct nft_set_ext_tmpl *tmpl) { @@ -802,14 +818,14 @@ 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); -} +struct nft_timeout { + u64 timeout; + u64 expiration; +}; -static inline u64 *nft_set_ext_expiration(const struct nft_set_ext *ext) +static inline struct nft_timeout *nft_set_ext_timeout(const struct nft_set_ext *ext) { - return nft_set_ext(ext, NFT_SET_EXT_EXPIRATION); + return nft_set_ext(ext, NFT_SET_EXT_TIMEOUT); } static inline struct nft_userdata *nft_set_ext_userdata(const struct nft_set_ext *ext) @@ -825,8 +841,11 @@ static inline struct nft_set_elem_expr *nft_set_ext_expr(const struct nft_set_ex static inline bool __nft_set_elem_expired(const struct nft_set_ext *ext, u64 tstamp) { - return nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION) && - time_after_eq64(tstamp, *nft_set_ext_expiration(ext)); + if (!nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) || + READ_ONCE(nft_set_ext_timeout(ext)->timeout) == 0) + return false; + + return time_after_eq64(tstamp, READ_ONCE(nft_set_ext_timeout(ext)->expiration)); } static inline bool nft_set_elem_expired(const struct nft_set_ext *ext) @@ -935,7 +954,7 @@ struct nft_expr_ops { struct nft_regs *regs, const struct nft_pktinfo *pkt); int (*clone)(struct nft_expr *dst, - const struct nft_expr *src); + const struct nft_expr *src, gfp_t gfp); unsigned int size; int (*init)(const struct nft_ctx *ctx, @@ -954,8 +973,7 @@ struct nft_expr_ops { const struct nft_expr *expr, bool reset); int (*validate)(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data); + const struct nft_expr *expr); bool (*reduce)(struct nft_regs_track *track, const struct nft_expr *expr); bool (*gc)(struct net *net, @@ -1124,6 +1142,11 @@ int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set); int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); void nf_tables_unbind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); +struct nft_hook; +void nf_tables_chain_device_notify(const struct nft_chain *chain, + const struct nft_hook *hook, + const struct net_device *dev, int event); + enum nft_chain_types { NFT_CHAIN_T_DEFAULT = 0, NFT_CHAIN_T_ROUTE, @@ -1171,7 +1194,7 @@ static inline bool nft_chain_is_bound(struct nft_chain *chain) int nft_chain_add(struct nft_table *table, struct nft_chain *chain); void nft_chain_del(struct nft_chain *chain); -void nf_tables_chain_destroy(struct nft_ctx *ctx); +void nf_tables_chain_destroy(struct nft_chain *chain); struct nft_stats { u64 bytes; @@ -1181,10 +1204,17 @@ struct nft_stats { struct nft_hook { struct list_head list; - struct nf_hook_ops ops; + struct list_head ops_list; struct rcu_head rcu; + char ifname[IFNAMSIZ]; + u8 ifnamelen; }; +struct nf_hook_ops *nft_hook_find_ops(const struct nft_hook *hook, + const struct net_device *dev); +struct nf_hook_ops *nft_hook_find_ops_rcu(const struct nft_hook *hook, + const struct net_device *dev); + /** * struct nft_base_chain - nf_tables base chain * @@ -1218,8 +1248,6 @@ static inline bool nft_is_base_chain(const struct nft_chain *chain) return chain->flags & NFT_CHAIN_BASE; } -int __nft_release_basechain(struct nft_ctx *ctx); - unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv); static inline bool nft_use_inc(u32 *use) @@ -1454,7 +1482,8 @@ struct nft_flowtable { struct nf_flowtable data; }; -struct nft_flowtable *nft_flowtable_lookup(const struct nft_table *table, +struct nft_flowtable *nft_flowtable_lookup(const struct net *net, + const struct nft_table *table, const struct nlattr *nla, u8 genmask); @@ -1608,41 +1637,68 @@ static inline int nft_set_elem_is_dead(const struct nft_set_ext *ext) } /** - * struct nft_trans - nf_tables object update in transaction + * struct nft_trans - nf_tables object update in transaction * - * @list: used internally - * @binding_list: list of objects with possible bindings - * @msg_type: message type - * @put_net: ctx->net needs to be put - * @ctx: transaction context - * @data: internal information related to the transaction + * @list: used internally + * @net: struct net + * @table: struct nft_table the object resides in + * @msg_type: message type + * @seq: netlink sequence number + * @flags: modifiers to new request + * @report: notify via unicast netlink message + * @put_net: net needs to be put + * + * This is the information common to all objects in the transaction, + * this must always be the first member of derived sub-types. */ struct nft_trans { struct list_head list; - struct list_head binding_list; + struct net *net; + struct nft_table *table; int msg_type; - bool put_net; - struct nft_ctx ctx; - char data[]; + u32 seq; + u16 flags; + u8 report:1; + u8 put_net:1; +}; + +/** + * struct nft_trans_binding - nf_tables object with binding support in transaction + * @nft_trans: base structure, MUST be first member + * @binding_list: list of objects with possible bindings + * + * This is the base type used by objects that can be bound to a chain. + */ +struct nft_trans_binding { + struct nft_trans nft_trans; + struct list_head binding_list; }; struct nft_trans_rule { + struct nft_trans nft_trans; struct nft_rule *rule; + struct nft_chain *chain; struct nft_flow_rule *flow; u32 rule_id; bool bound; }; -#define nft_trans_rule(trans) \ - (((struct nft_trans_rule *)trans->data)->rule) -#define nft_trans_flow_rule(trans) \ - (((struct nft_trans_rule *)trans->data)->flow) -#define nft_trans_rule_id(trans) \ - (((struct nft_trans_rule *)trans->data)->rule_id) -#define nft_trans_rule_bound(trans) \ - (((struct nft_trans_rule *)trans->data)->bound) +#define nft_trans_container_rule(trans) \ + container_of(trans, struct nft_trans_rule, nft_trans) +#define nft_trans_rule(trans) \ + nft_trans_container_rule(trans)->rule +#define nft_trans_flow_rule(trans) \ + nft_trans_container_rule(trans)->flow +#define nft_trans_rule_id(trans) \ + nft_trans_container_rule(trans)->rule_id +#define nft_trans_rule_bound(trans) \ + nft_trans_container_rule(trans)->bound +#define nft_trans_rule_chain(trans) \ + nft_trans_container_rule(trans)->chain struct nft_trans_set { + struct nft_trans_binding nft_trans_binding; + struct list_head list_trans_newset; struct nft_set *set; u32 set_id; u32 gc_int; @@ -1652,100 +1708,132 @@ struct nft_trans_set { u32 size; }; -#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) -#define nft_trans_set_bound(trans) \ - (((struct nft_trans_set *)trans->data)->bound) -#define nft_trans_set_update(trans) \ - (((struct nft_trans_set *)trans->data)->update) -#define nft_trans_set_timeout(trans) \ - (((struct nft_trans_set *)trans->data)->timeout) -#define nft_trans_set_gc_int(trans) \ - (((struct nft_trans_set *)trans->data)->gc_int) -#define nft_trans_set_size(trans) \ - (((struct nft_trans_set *)trans->data)->size) +#define nft_trans_container_set(t) \ + container_of(t, struct nft_trans_set, nft_trans_binding.nft_trans) +#define nft_trans_set(trans) \ + nft_trans_container_set(trans)->set +#define nft_trans_set_id(trans) \ + nft_trans_container_set(trans)->set_id +#define nft_trans_set_bound(trans) \ + nft_trans_container_set(trans)->bound +#define nft_trans_set_update(trans) \ + nft_trans_container_set(trans)->update +#define nft_trans_set_timeout(trans) \ + nft_trans_container_set(trans)->timeout +#define nft_trans_set_gc_int(trans) \ + nft_trans_container_set(trans)->gc_int +#define nft_trans_set_size(trans) \ + nft_trans_container_set(trans)->size struct nft_trans_chain { + struct nft_trans_binding nft_trans_binding; struct nft_chain *chain; - bool update; char *name; struct nft_stats __percpu *stats; u8 policy; + bool update; bool bound; u32 chain_id; struct nft_base_chain *basechain; struct list_head hook_list; }; -#define nft_trans_chain(trans) \ - (((struct nft_trans_chain *)trans->data)->chain) -#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) -#define nft_trans_chain_bound(trans) \ - (((struct nft_trans_chain *)trans->data)->bound) -#define nft_trans_chain_id(trans) \ - (((struct nft_trans_chain *)trans->data)->chain_id) -#define nft_trans_basechain(trans) \ - (((struct nft_trans_chain *)trans->data)->basechain) -#define nft_trans_chain_hooks(trans) \ - (((struct nft_trans_chain *)trans->data)->hook_list) +#define nft_trans_container_chain(t) \ + container_of(t, struct nft_trans_chain, nft_trans_binding.nft_trans) +#define nft_trans_chain(trans) \ + nft_trans_container_chain(trans)->chain +#define nft_trans_chain_update(trans) \ + nft_trans_container_chain(trans)->update +#define nft_trans_chain_name(trans) \ + nft_trans_container_chain(trans)->name +#define nft_trans_chain_stats(trans) \ + nft_trans_container_chain(trans)->stats +#define nft_trans_chain_policy(trans) \ + nft_trans_container_chain(trans)->policy +#define nft_trans_chain_bound(trans) \ + nft_trans_container_chain(trans)->bound +#define nft_trans_chain_id(trans) \ + nft_trans_container_chain(trans)->chain_id +#define nft_trans_basechain(trans) \ + nft_trans_container_chain(trans)->basechain +#define nft_trans_chain_hooks(trans) \ + nft_trans_container_chain(trans)->hook_list struct nft_trans_table { + struct nft_trans nft_trans; bool update; }; -#define nft_trans_table_update(trans) \ - (((struct nft_trans_table *)trans->data)->update) +#define nft_trans_container_table(trans) \ + container_of(trans, struct nft_trans_table, nft_trans) +#define nft_trans_table_update(trans) \ + nft_trans_container_table(trans)->update + +enum nft_trans_elem_flags { + NFT_TRANS_UPD_TIMEOUT = (1 << 0), + NFT_TRANS_UPD_EXPIRATION = (1 << 1), +}; + +struct nft_elem_update { + u64 timeout; + u64 expiration; + u8 flags; +}; + +struct nft_trans_one_elem { + struct nft_elem_priv *priv; + struct nft_elem_update *update; +}; struct nft_trans_elem { + struct nft_trans nft_trans; struct nft_set *set; - struct nft_elem_priv *elem_priv; bool bound; + unsigned int nelems; + struct nft_trans_one_elem elems[] __counted_by(nelems); }; -#define nft_trans_elem_set(trans) \ - (((struct nft_trans_elem *)trans->data)->set) -#define nft_trans_elem_priv(trans) \ - (((struct nft_trans_elem *)trans->data)->elem_priv) -#define nft_trans_elem_set_bound(trans) \ - (((struct nft_trans_elem *)trans->data)->bound) +#define nft_trans_container_elem(t) \ + container_of(t, struct nft_trans_elem, nft_trans) +#define nft_trans_elem_set(trans) \ + nft_trans_container_elem(trans)->set +#define nft_trans_elem_set_bound(trans) \ + nft_trans_container_elem(trans)->bound struct nft_trans_obj { + struct nft_trans nft_trans; struct nft_object *obj; struct nft_object *newobj; bool update; }; -#define nft_trans_obj(trans) \ - (((struct nft_trans_obj *)trans->data)->obj) -#define nft_trans_obj_newobj(trans) \ - (((struct nft_trans_obj *)trans->data)->newobj) -#define nft_trans_obj_update(trans) \ - (((struct nft_trans_obj *)trans->data)->update) +#define nft_trans_container_obj(t) \ + container_of(t, struct nft_trans_obj, nft_trans) +#define nft_trans_obj(trans) \ + nft_trans_container_obj(trans)->obj +#define nft_trans_obj_newobj(trans) \ + nft_trans_container_obj(trans)->newobj +#define nft_trans_obj_update(trans) \ + nft_trans_container_obj(trans)->update struct nft_trans_flowtable { + struct nft_trans nft_trans; struct nft_flowtable *flowtable; - bool update; struct list_head hook_list; u32 flags; + bool update; }; -#define nft_trans_flowtable(trans) \ - (((struct nft_trans_flowtable *)trans->data)->flowtable) -#define nft_trans_flowtable_update(trans) \ - (((struct nft_trans_flowtable *)trans->data)->update) -#define nft_trans_flowtable_hooks(trans) \ - (((struct nft_trans_flowtable *)trans->data)->hook_list) -#define nft_trans_flowtable_flags(trans) \ - (((struct nft_trans_flowtable *)trans->data)->flags) +#define nft_trans_container_flowtable(t) \ + container_of(t, struct nft_trans_flowtable, nft_trans) +#define nft_trans_flowtable(trans) \ + nft_trans_container_flowtable(trans)->flowtable +#define nft_trans_flowtable_update(trans) \ + nft_trans_container_flowtable(trans)->update +#define nft_trans_flowtable_hooks(trans) \ + nft_trans_container_flowtable(trans)->hook_list +#define nft_trans_flowtable_flags(trans) \ + nft_trans_container_flowtable(trans)->flags #define NFT_TRANS_GC_BATCHCOUNT 256 @@ -1759,6 +1847,33 @@ struct nft_trans_gc { struct rcu_head rcu; }; +static inline void nft_ctx_update(struct nft_ctx *ctx, + const struct nft_trans *trans) +{ + switch (trans->msg_type) { + case NFT_MSG_NEWRULE: + case NFT_MSG_DELRULE: + case NFT_MSG_DESTROYRULE: + ctx->chain = nft_trans_rule_chain(trans); + break; + case NFT_MSG_NEWCHAIN: + case NFT_MSG_DELCHAIN: + case NFT_MSG_DESTROYCHAIN: + ctx->chain = nft_trans_chain(trans); + break; + default: + ctx->chain = NULL; + break; + } + + ctx->net = trans->net; + ctx->table = trans->table; + ctx->family = trans->table->family; + ctx->report = trans->report; + ctx->flags = trans->flags; + ctx->seq = trans->seq; +} + struct nft_trans_gc *nft_trans_gc_alloc(struct nft_set *set, unsigned int gc_seq, gfp_t gfp); void nft_trans_gc_destroy(struct nft_trans_gc *trans); @@ -1786,7 +1901,7 @@ void nft_chain_filter_fini(void); void __init nft_chain_route_init(void); void nft_chain_route_fini(void); -void nf_tables_trans_destroy_flush_work(void); +void nf_tables_trans_destroy_flush_work(struct net *net); int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result); __be64 nf_jiffies64_to_msecs(u64 input); @@ -1800,6 +1915,8 @@ static inline int nft_request_module(struct net *net, const char *fmt, ...) { re struct nftables_pernet { struct list_head tables; struct list_head commit_list; + struct list_head destroy_list; + struct list_head commit_set_list; struct list_head binding_list; struct list_head module_list; struct list_head notify_list; @@ -1809,6 +1926,7 @@ struct nftables_pernet { unsigned int base_seq; unsigned int gc_seq; u8 validate_state; + struct work_struct destroy_work; }; extern unsigned int nf_tables_net_id; diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index ff27cb2e1662..03b6165756fc 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -161,6 +161,7 @@ enum { }; struct nft_inner_tun_ctx { + unsigned long cookie; u16 type; u16 inner_tunoff; u16 inner_lloff; diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h index 60a7d0ce3080..fcf967286e37 100644 --- a/include/net/netfilter/nf_tables_ipv4.h +++ b/include/net/netfilter/nf_tables_ipv4.h @@ -19,7 +19,7 @@ static inline void nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt) static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt) { struct iphdr *iph, _iph; - u32 len, thoff; + u32 len, thoff, skb_len; iph = skb_header_pointer(pkt->skb, skb_network_offset(pkt->skb), sizeof(*iph), &_iph); @@ -30,8 +30,10 @@ static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt) return -1; len = iph_totlen(pkt->skb, iph); - thoff = skb_network_offset(pkt->skb) + (iph->ihl * 4); - if (pkt->skb->len < len) + thoff = iph->ihl * 4; + skb_len = pkt->skb->len - skb_network_offset(pkt->skb); + + if (skb_len < len) return -1; else if (len < thoff) return -1; @@ -40,7 +42,7 @@ static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt) pkt->flags = NFT_PKTINFO_L4PROTO; pkt->tprot = iph->protocol; - pkt->thoff = thoff; + pkt->thoff = skb_network_offset(pkt->skb) + thoff; pkt->fragoff = ntohs(iph->frag_off) & IP_OFFSET; return 0; diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h index 467d59b9e533..a0633eeaec97 100644 --- a/include/net/netfilter/nf_tables_ipv6.h +++ b/include/net/netfilter/nf_tables_ipv6.h @@ -31,8 +31,8 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt) struct ipv6hdr *ip6h, _ip6h; unsigned int thoff = 0; unsigned short frag_off; + u32 pkt_len, skb_len; int protohdr; - u32 pkt_len; ip6h = skb_header_pointer(pkt->skb, skb_network_offset(pkt->skb), sizeof(*ip6h), &_ip6h); @@ -43,7 +43,8 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt) return -1; pkt_len = ntohs(ip6h->payload_len); - if (pkt_len + sizeof(*ip6h) > pkt->skb->len) + skb_len = pkt->skb->len - skb_network_offset(pkt->skb); + if (pkt_len + sizeof(*ip6h) > skb_len) return -1; protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags); diff --git a/include/net/netfilter/nf_tproxy.h b/include/net/netfilter/nf_tproxy.h index faa108b1ba67..06985530517b 100644 --- a/include/net/netfilter/nf_tproxy.h +++ b/include/net/netfilter/nf_tproxy.h @@ -36,6 +36,7 @@ __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr); /** * nf_tproxy_handle_time_wait4 - handle IPv4 TCP TIME_WAIT reopen redirections + * @net: The network namespace. * @skb: The skb being processed. * @laddr: IPv4 address to redirect to or zero. * @lport: TCP port to redirect to or zero. @@ -48,7 +49,7 @@ __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr); * * nf_tproxy_handle_time_wait4() consumes the socket reference passed in. * - * Returns the listener socket if there's one, the TIME_WAIT socket if + * Returns: the listener socket if there's one, the TIME_WAIT socket if * no such listener is found, or NULL if the TCP header is incomplete. */ struct sock * @@ -107,7 +108,7 @@ nf_tproxy_laddr6(struct sk_buff *skb, const struct in6_addr *user_laddr, * * nf_tproxy_handle_time_wait6() consumes the socket reference passed in. * - * Returns the listener socket if there's one, the TIME_WAIT socket if + * Returns: the listener socket if there's one, the TIME_WAIT socket if * no such listener is found, or NULL if the TCP header is incomplete. */ struct sock * diff --git a/include/net/netfilter/nft_fib.h b/include/net/netfilter/nft_fib.h index 167640b843ef..7370fba844ef 100644 --- a/include/net/netfilter/nft_fib.h +++ b/include/net/netfilter/nft_fib.h @@ -2,6 +2,7 @@ #ifndef _NFT_FIB_H_ #define _NFT_FIB_H_ +#include <net/l3mdev.h> #include <net/netfilter/nf_tables.h> struct nft_fib { @@ -18,12 +19,39 @@ nft_fib_is_loopback(const struct sk_buff *skb, const struct net_device *in) return skb->pkt_type == PACKET_LOOPBACK || in->flags & IFF_LOOPBACK; } +static inline bool nft_fib_can_skip(const struct nft_pktinfo *pkt) +{ + const struct net_device *indev = nft_in(pkt); + const struct sock *sk; + + switch (nft_hook(pkt)) { + case NF_INET_PRE_ROUTING: + case NF_INET_INGRESS: + case NF_INET_LOCAL_IN: + break; + default: + return false; + } + + sk = pkt->skb->sk; + if (sk && sk_fullsock(sk)) + return sk->sk_rx_dst_ifindex == indev->ifindex; + + return nft_fib_is_loopback(pkt->skb, indev); +} + +static inline int nft_fib_l3mdev_master_ifindex_rcu(const struct nft_pktinfo *pkt, + const struct net_device *iif) +{ + const struct net_device *dev = iif ? iif : pkt->skb->dev; + + return l3mdev_master_ifindex_rcu(dev); +} + int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset); int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]); -int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, - const struct nft_data **data); - +int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr); void nft_fib4_eval_type(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); diff --git a/include/net/netfilter/nft_meta.h b/include/net/netfilter/nft_meta.h index ba1238f12a48..d602263590fe 100644 --- a/include/net/netfilter/nft_meta.h +++ b/include/net/netfilter/nft_meta.h @@ -41,8 +41,7 @@ void nft_meta_set_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr); int nft_meta_set_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data); + const struct nft_expr *expr); bool nft_meta_get_reduce(struct nft_regs_track *track, const struct nft_expr *expr); diff --git a/include/net/netfilter/nft_reject.h b/include/net/netfilter/nft_reject.h index 6d9ba62efd75..19060212988a 100644 --- a/include/net/netfilter/nft_reject.h +++ b/include/net/netfilter/nft_reject.h @@ -15,8 +15,7 @@ struct nft_reject { extern const struct nla_policy nft_reject_policy[]; int nft_reject_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data); + const struct nft_expr *expr); int nft_reject_init(const struct nft_ctx *ctx, const struct nft_expr *expr, diff --git a/include/net/netlabel.h b/include/net/netlabel.h index f3ab0b8a4b18..02914b1df38b 100644 --- a/include/net/netlabel.h +++ b/include/net/netlabel.h @@ -30,7 +30,7 @@ struct calipso_doi; /* * NetLabel - A management interface for maintaining network packet label - * mapping tables for explicit packet labling protocols. + * mapping tables for explicit packet labeling protocols. * * Network protocols such as CIPSO and RIPSO require a label translation layer * to convert the label on the packet into something meaningful on the host @@ -97,7 +97,7 @@ struct calipso_doi; /* NetLabel audit information */ struct netlbl_audit { - u32 secid; + struct lsm_prop prop; kuid_t loginuid; unsigned int sessionid; }; @@ -208,6 +208,7 @@ struct netlbl_lsm_secattr { * struct netlbl_calipso_ops - NetLabel CALIPSO operations * @doi_add: add a CALIPSO DOI * @doi_free: free a CALIPSO DOI + * @doi_remove: remove a CALIPSO DOI * @doi_getdef: returns a reference to a DOI * @doi_putdef: releases a reference of a DOI * @doi_walk: enumerate the DOI list @@ -274,15 +275,17 @@ struct netlbl_calipso_ops { * on success, NULL on failure. * */ -static inline struct netlbl_lsm_cache *netlbl_secattr_cache_alloc(gfp_t flags) +static inline struct netlbl_lsm_cache *netlbl_secattr_cache_alloc_noprof(gfp_t flags) { struct netlbl_lsm_cache *cache; - cache = kzalloc(sizeof(*cache), flags); + cache = kzalloc_noprof(sizeof(*cache), flags); if (cache) refcount_set(&cache->refcount, 1); return cache; } +#define netlbl_secattr_cache_alloc(...) \ + alloc_hooks(netlbl_secattr_cache_alloc_noprof(__VA_ARGS__)) /** * netlbl_secattr_cache_free - Frees a netlbl_lsm_cache struct @@ -311,10 +314,11 @@ static inline void netlbl_secattr_cache_free(struct netlbl_lsm_cache *cache) * on failure. * */ -static inline struct netlbl_lsm_catmap *netlbl_catmap_alloc(gfp_t flags) +static inline struct netlbl_lsm_catmap *netlbl_catmap_alloc_noprof(gfp_t flags) { - return kzalloc(sizeof(struct netlbl_lsm_catmap), flags); + return kzalloc_noprof(sizeof(struct netlbl_lsm_catmap), flags); } +#define netlbl_catmap_alloc(...) alloc_hooks(netlbl_catmap_alloc_noprof(__VA_ARGS__)) /** * netlbl_catmap_free - Free a LSM secattr catmap @@ -376,10 +380,11 @@ static inline void netlbl_secattr_destroy(struct netlbl_lsm_secattr *secattr) * pointer on success, or NULL on failure. * */ -static inline struct netlbl_lsm_secattr *netlbl_secattr_alloc(gfp_t flags) +static inline struct netlbl_lsm_secattr *netlbl_secattr_alloc_noprof(gfp_t flags) { - return kzalloc(sizeof(struct netlbl_lsm_secattr), flags); + return kzalloc_noprof(sizeof(struct netlbl_lsm_secattr), flags); } +#define netlbl_secattr_alloc(...) alloc_hooks(netlbl_secattr_alloc_noprof(__VA_ARGS__)) /** * netlbl_secattr_free - Frees a netlbl_lsm_secattr struct @@ -470,7 +475,8 @@ void netlbl_bitmap_setbit(unsigned char *bitmap, u32 bit, u8 state); int netlbl_enabled(void); int netlbl_sock_setattr(struct sock *sk, u16 family, - const struct netlbl_lsm_secattr *secattr); + const struct netlbl_lsm_secattr *secattr, + bool sk_locked); void netlbl_sock_delattr(struct sock *sk); int netlbl_sock_getattr(struct sock *sk, struct netlbl_lsm_secattr *secattr); @@ -487,6 +493,7 @@ int netlbl_skbuff_getattr(const struct sk_buff *skb, u16 family, struct netlbl_lsm_secattr *secattr); void netlbl_skbuff_err(struct sk_buff *skb, u16 family, int error, int gateway); +bool netlbl_sk_lock_check(struct sock *sk); /* * LSM label mapping cache operations @@ -614,7 +621,8 @@ static inline int netlbl_enabled(void) } static inline int netlbl_sock_setattr(struct sock *sk, u16 family, - const struct netlbl_lsm_secattr *secattr) + const struct netlbl_lsm_secattr *secattr, + bool sk_locked) { return -ENOSYS; } @@ -673,6 +681,11 @@ static inline struct audit_buffer *netlbl_audit_start(int type, { return NULL; } + +static inline bool netlbl_sk_lock_check(struct sock *sk) +{ + return true; +} #endif /* CONFIG_NETLABEL */ const struct netlbl_calipso_ops * diff --git a/include/net/netlink.h b/include/net/netlink.h index c19ff921b661..90a560dc167a 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -41,7 +41,8 @@ * nlmsg_get_pos() return current position in message * nlmsg_trim() trim part of message * nlmsg_cancel() cancel message construction - * nlmsg_free() free a netlink message + * nlmsg_consume() free a netlink message (expected) + * nlmsg_free() free a netlink message (drop) * * Message Sending: * nlmsg_multicast() multicast message to several groups @@ -117,6 +118,7 @@ * nla_nest_start(skb, type) start a nested attribute * nla_nest_end(skb, nla) finalize a nested attribute * nla_nest_cancel(skb, nla) cancel nested attribute construction + * nla_put_empty_nest(skb, type) create an empty nest * * Attribute Length Calculations: * nla_attr_size(payload) length of attribute w/o padding @@ -141,6 +143,8 @@ * nla_get_flag(nla) return 1 if flag is true * nla_get_msecs(nla) get payload for a msecs attribute * + * The same functions also exist with _default(). + * * Attribute Misc: * nla_memcpy(dest, nla, count) copy attribute into memory * nla_memcmp(nla, data, size) compare attribute with memory area @@ -157,7 +161,11 @@ * nla_parse() parse and validate stream of attrs * nla_parse_nested() parse nested attributes * nla_for_each_attr() loop over all attributes + * nla_for_each_attr_type() loop over all attributes with the + * given type * nla_for_each_nested() loop over the nested attributes + * nla_for_each_nested_type() loop over the nested attributes with + * the given type *========================================================================= */ @@ -313,7 +321,13 @@ enum nla_policy_validation { * All other Unused - but note that it's a union * * Meaning of `validate' field, use via NLA_POLICY_VALIDATE_FN: + * NLA_U8, NLA_U16, + * NLA_U32, NLA_U64, + * NLA_S8, NLA_S16, + * NLA_S32, NLA_S64, + * NLA_MSECS, * NLA_BINARY Validation function called for the attribute. + * * All other Unused - but note that it's a union * * Example: @@ -464,6 +478,7 @@ struct nla_policy { .max = _len \ } #define NLA_POLICY_MIN_LEN(_len) NLA_POLICY_MIN(NLA_BINARY, _len) +#define NLA_POLICY_MAX_LEN(_len) NLA_POLICY_MAX(NLA_BINARY, _len) /** * struct nl_info - netlink source information @@ -603,6 +618,22 @@ static inline int nlmsg_len(const struct nlmsghdr *nlh) } /** + * nlmsg_payload - message payload if the data fits in the len + * @nlh: netlink message header + * @len: struct length + * + * Returns: The netlink message payload/data if the length is sufficient, + * otherwise NULL. + */ +static inline void *nlmsg_payload(const struct nlmsghdr *nlh, size_t len) +{ + if (nlh->nlmsg_len < nlmsg_msg_size(len)) + return NULL; + + return nlmsg_data(nlh); +} + +/** * nlmsg_attrdata - head of attributes data * @nlh: netlink message header * @hdrlen: length of family specific header @@ -641,7 +672,7 @@ static inline int nlmsg_ok(const struct nlmsghdr *nlh, int remaining) * @nlh: netlink message header * @remaining: number of bytes remaining in message stream * - * Returns the next netlink message in the message stream and + * Returns: the next netlink message in the message stream and * decrements remaining by the size of the current message. */ static inline struct nlmsghdr * @@ -668,7 +699,7 @@ nlmsg_next(const struct nlmsghdr *nlh, int *remaining) * exceeding maxtype will be rejected, policy must be specified, attributes * will be validated in the strictest way possible. * - * Returns 0 on success or a negative error code. + * Returns: 0 on success or a negative error code. */ static inline int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head, int len, @@ -693,7 +724,7 @@ static inline int nla_parse(struct nlattr **tb, int maxtype, * exceeding maxtype will be ignored and attributes from the policy are not * always strictly validated (only for new attributes). * - * Returns 0 on success or a negative error code. + * Returns: 0 on success or a negative error code. */ static inline int nla_parse_deprecated(struct nlattr **tb, int maxtype, const struct nlattr *head, int len, @@ -718,7 +749,7 @@ static inline int nla_parse_deprecated(struct nlattr **tb, int maxtype, * exceeding maxtype will be rejected as well as trailing data, but the * policy is not completely strictly validated (only for new attributes). * - * Returns 0 on success or a negative error code. + * Returns: 0 on success or a negative error code. */ static inline int nla_parse_deprecated_strict(struct nlattr **tb, int maxtype, const struct nlattr *head, @@ -822,10 +853,10 @@ nlmsg_parse_deprecated_strict(const struct nlmsghdr *nlh, int hdrlen, /** * nlmsg_find_attr - find a specific attribute in a netlink message * @nlh: netlink message header - * @hdrlen: length of familiy specific header + * @hdrlen: length of family specific header * @attrtype: type of attribute to look for * - * Returns the first attribute which matches the specified type. + * Returns: the first attribute which matches the specified type. */ static inline struct nlattr *nlmsg_find_attr(const struct nlmsghdr *nlh, int hdrlen, int attrtype) @@ -844,9 +875,9 @@ static inline struct nlattr *nlmsg_find_attr(const struct nlmsghdr *nlh, * * Validates all attributes in the specified attribute stream against the * specified policy. Validation is done in liberal mode. - * See documenation of struct nla_policy for more details. + * See documentation of struct nla_policy for more details. * - * Returns 0 on success or a negative error code. + * Returns: 0 on success or a negative error code. */ static inline int nla_validate_deprecated(const struct nlattr *head, int len, int maxtype, @@ -867,9 +898,9 @@ static inline int nla_validate_deprecated(const struct nlattr *head, int len, * * Validates all attributes in the specified attribute stream against the * specified policy. Validation is done in strict mode. - * See documenation of struct nla_policy for more details. + * See documentation of struct nla_policy for more details. * - * Returns 0 on success or a negative error code. + * Returns: 0 on success or a negative error code. */ static inline int nla_validate(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, @@ -882,7 +913,7 @@ static inline int nla_validate(const struct nlattr *head, int len, int maxtype, /** * nlmsg_validate_deprecated - validate a netlink message including attributes * @nlh: netlinket message header - * @hdrlen: length of familiy specific header + * @hdrlen: length of family specific header * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct @@ -906,7 +937,7 @@ static inline int nlmsg_validate_deprecated(const struct nlmsghdr *nlh, * nlmsg_report - need to report back to application? * @nlh: netlink message header * - * Returns 1 if a report back to the application is requested. + * Returns: 1 if a report back to the application is requested. */ static inline int nlmsg_report(const struct nlmsghdr *nlh) { @@ -917,7 +948,7 @@ static inline int nlmsg_report(const struct nlmsghdr *nlh) * nlmsg_seq - return the seq number of netlink message * @nlh: netlink message header * - * Returns 0 if netlink message is NULL + * Returns: 0 if netlink message is NULL */ static inline u32 nlmsg_seq(const struct nlmsghdr *nlh) { @@ -928,7 +959,7 @@ static inline u32 nlmsg_seq(const struct nlmsghdr *nlh) * nlmsg_for_each_attr - iterate over a stream of attributes * @pos: loop counter, set to current attribute * @nlh: netlink message header - * @hdrlen: length of familiy specific header + * @hdrlen: length of family specific header * @rem: initialized to len, holds bytes currently remaining in stream */ #define nlmsg_for_each_attr(pos, nlh, hdrlen, rem) \ @@ -944,7 +975,7 @@ static inline u32 nlmsg_seq(const struct nlmsghdr *nlh) * @payload: length of message payload * @flags: message flags * - * Returns NULL if the tailroom of the skb is insufficient to store + * Returns: NULL if the tailroom of the skb is insufficient to store * the message header and payload. */ static inline struct nlmsghdr *nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, @@ -963,7 +994,7 @@ static inline struct nlmsghdr *nlmsg_put(struct sk_buff *skb, u32 portid, u32 se * * Append data to an existing nlmsg, used when constructing a message * with multiple fixed-format headers (which is rare). - * Returns NULL if the tailroom of the skb is insufficient to store + * Returns: NULL if the tailroom of the skb is insufficient to store * the extra payload. */ static inline void *nlmsg_append(struct sk_buff *skb, u32 size) @@ -985,7 +1016,7 @@ static inline void *nlmsg_append(struct sk_buff *skb, u32 size) * @payload: length of message payload * @flags: message flags * - * Returns NULL if the tailroom of the skb is insufficient to store + * Returns: NULL if the tailroom of the skb is insufficient to store * the message header and payload. */ static inline struct nlmsghdr *nlmsg_put_answer(struct sk_buff *skb, @@ -1029,7 +1060,7 @@ static inline struct sk_buff *nlmsg_new_large(size_t payload) * @skb: socket buffer the message is stored in * @nlh: netlink message header * - * Corrects the netlink message header to include the appeneded + * Corrects the netlink message header to include the appended * attributes. Only necessary if attributes have been added to * the message. */ @@ -1042,7 +1073,7 @@ static inline void nlmsg_end(struct sk_buff *skb, struct nlmsghdr *nlh) * nlmsg_get_pos - return current position in netlink message * @skb: socket buffer the message is stored in * - * Returns a pointer to the current tail of the message. + * Returns: a pointer to the current tail of the message. */ static inline void *nlmsg_get_pos(struct sk_buff *skb) { @@ -1078,7 +1109,7 @@ static inline void nlmsg_cancel(struct sk_buff *skb, struct nlmsghdr *nlh) } /** - * nlmsg_free - free a netlink message + * nlmsg_free - drop a netlink message * @skb: socket buffer of netlink message */ static inline void nlmsg_free(struct sk_buff *skb) @@ -1087,6 +1118,15 @@ static inline void nlmsg_free(struct sk_buff *skb) } /** + * nlmsg_consume - free a netlink message + * @skb: socket buffer of netlink message + */ +static inline void nlmsg_consume(struct sk_buff *skb) +{ + consume_skb(skb); +} + +/** * nlmsg_multicast_filtered - multicast a netlink message with filter function * @sk: netlink socket to spread messages to * @skb: netlink message as socket buffer @@ -1259,7 +1299,7 @@ static inline int nla_ok(const struct nlattr *nla, int remaining) * @nla: netlink attribute * @remaining: number of bytes remaining in attribute stream * - * Returns the next netlink attribute in the attribute stream and + * Returns: the next netlink attribute in the attribute stream and * decrements remaining by the size of the current attribute. */ static inline struct nlattr *nla_next(const struct nlattr *nla, int *remaining) @@ -1275,7 +1315,7 @@ static inline struct nlattr *nla_next(const struct nlattr *nla, int *remaining) * @nla: attribute containing the nested attributes * @attrtype: type of attribute to look for * - * Returns the first attribute which matches the specified type. + * Returns: the first attribute which matches the specified type. */ static inline struct nlattr * nla_find_nested(const struct nlattr *nla, int attrtype) @@ -1681,6 +1721,20 @@ static inline u32 nla_get_u32(const struct nlattr *nla) } /** + * nla_get_u32_default - return payload of u32 attribute or default + * @nla: u32 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline u32 nla_get_u32_default(const struct nlattr *nla, u32 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_u32(nla); +} + +/** * nla_get_be32 - return payload of __be32 attribute * @nla: __be32 netlink attribute */ @@ -1690,6 +1744,21 @@ static inline __be32 nla_get_be32(const struct nlattr *nla) } /** + * nla_get_be32_default - return payload of be32 attribute or default + * @nla: __be32 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline __be32 nla_get_be32_default(const struct nlattr *nla, + __be32 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_be32(nla); +} + +/** * nla_get_le32 - return payload of __le32 attribute * @nla: __le32 netlink attribute */ @@ -1699,6 +1768,21 @@ static inline __le32 nla_get_le32(const struct nlattr *nla) } /** + * nla_get_le32_default - return payload of le32 attribute or default + * @nla: __le32 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline __le32 nla_get_le32_default(const struct nlattr *nla, + __le32 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_le32(nla); +} + +/** * nla_get_u16 - return payload of u16 attribute * @nla: u16 netlink attribute */ @@ -1708,6 +1792,20 @@ static inline u16 nla_get_u16(const struct nlattr *nla) } /** + * nla_get_u16_default - return payload of u16 attribute or default + * @nla: u16 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline u16 nla_get_u16_default(const struct nlattr *nla, u16 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_u16(nla); +} + +/** * nla_get_be16 - return payload of __be16 attribute * @nla: __be16 netlink attribute */ @@ -1717,6 +1815,21 @@ static inline __be16 nla_get_be16(const struct nlattr *nla) } /** + * nla_get_be16_default - return payload of be16 attribute or default + * @nla: __be16 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline __be16 nla_get_be16_default(const struct nlattr *nla, + __be16 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_be16(nla); +} + +/** * nla_get_le16 - return payload of __le16 attribute * @nla: __le16 netlink attribute */ @@ -1726,6 +1839,21 @@ static inline __le16 nla_get_le16(const struct nlattr *nla) } /** + * nla_get_le16_default - return payload of le16 attribute or default + * @nla: __le16 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline __le16 nla_get_le16_default(const struct nlattr *nla, + __le16 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_le16(nla); +} + +/** * nla_get_u8 - return payload of u8 attribute * @nla: u8 netlink attribute */ @@ -1735,6 +1863,20 @@ static inline u8 nla_get_u8(const struct nlattr *nla) } /** + * nla_get_u8_default - return payload of u8 attribute or default + * @nla: u8 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline u8 nla_get_u8_default(const struct nlattr *nla, u8 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_u8(nla); +} + +/** * nla_get_u64 - return payload of u64 attribute * @nla: u64 netlink attribute */ @@ -1748,6 +1890,20 @@ static inline u64 nla_get_u64(const struct nlattr *nla) } /** + * nla_get_u64_default - return payload of u64 attribute or default + * @nla: u64 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline u64 nla_get_u64_default(const struct nlattr *nla, u64 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_u64(nla); +} + +/** * nla_get_uint - return payload of uint attribute * @nla: uint netlink attribute */ @@ -1759,6 +1915,20 @@ static inline u64 nla_get_uint(const struct nlattr *nla) } /** + * nla_get_uint_default - return payload of uint attribute or default + * @nla: uint netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline u64 nla_get_uint_default(const struct nlattr *nla, u64 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_uint(nla); +} + +/** * nla_get_be64 - return payload of __be64 attribute * @nla: __be64 netlink attribute */ @@ -1772,6 +1942,21 @@ static inline __be64 nla_get_be64(const struct nlattr *nla) } /** + * nla_get_be64_default - return payload of be64 attribute or default + * @nla: __be64 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline __be64 nla_get_be64_default(const struct nlattr *nla, + __be64 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_be64(nla); +} + +/** * nla_get_le64 - return payload of __le64 attribute * @nla: __le64 netlink attribute */ @@ -1781,6 +1966,21 @@ static inline __le64 nla_get_le64(const struct nlattr *nla) } /** + * nla_get_le64_default - return payload of le64 attribute or default + * @nla: __le64 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline __le64 nla_get_le64_default(const struct nlattr *nla, + __le64 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_le64(nla); +} + +/** * nla_get_s32 - return payload of s32 attribute * @nla: s32 netlink attribute */ @@ -1790,6 +1990,20 @@ static inline s32 nla_get_s32(const struct nlattr *nla) } /** + * nla_get_s32_default - return payload of s32 attribute or default + * @nla: s32 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline s32 nla_get_s32_default(const struct nlattr *nla, s32 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_s32(nla); +} + +/** * nla_get_s16 - return payload of s16 attribute * @nla: s16 netlink attribute */ @@ -1799,6 +2013,20 @@ static inline s16 nla_get_s16(const struct nlattr *nla) } /** + * nla_get_s16_default - return payload of s16 attribute or default + * @nla: s16 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline s16 nla_get_s16_default(const struct nlattr *nla, s16 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_s16(nla); +} + +/** * nla_get_s8 - return payload of s8 attribute * @nla: s8 netlink attribute */ @@ -1808,6 +2036,20 @@ static inline s8 nla_get_s8(const struct nlattr *nla) } /** + * nla_get_s8_default - return payload of s8 attribute or default + * @nla: s8 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline s8 nla_get_s8_default(const struct nlattr *nla, s8 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_s8(nla); +} + +/** * nla_get_s64 - return payload of s64 attribute * @nla: s64 netlink attribute */ @@ -1821,6 +2063,20 @@ static inline s64 nla_get_s64(const struct nlattr *nla) } /** + * nla_get_s64_default - return payload of s64 attribute or default + * @nla: s64 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline s64 nla_get_s64_default(const struct nlattr *nla, s64 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_s64(nla); +} + +/** * nla_get_sint - return payload of uint attribute * @nla: uint netlink attribute */ @@ -1832,6 +2088,20 @@ static inline s64 nla_get_sint(const struct nlattr *nla) } /** + * nla_get_sint_default - return payload of sint attribute or default + * @nla: sint netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline s64 nla_get_sint_default(const struct nlattr *nla, s64 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_sint(nla); +} + +/** * nla_get_flag - return payload of flag attribute * @nla: flag netlink attribute */ @@ -1844,7 +2114,7 @@ static inline int nla_get_flag(const struct nlattr *nla) * nla_get_msecs - return payload of msecs attribute * @nla: msecs netlink attribute * - * Returns the number of milliseconds in jiffies. + * Returns: the number of milliseconds in jiffies. */ static inline unsigned long nla_get_msecs(const struct nlattr *nla) { @@ -1854,6 +2124,21 @@ static inline unsigned long nla_get_msecs(const struct nlattr *nla) } /** + * nla_get_msecs_default - return payload of msecs attribute or default + * @nla: msecs netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline unsigned long nla_get_msecs_default(const struct nlattr *nla, + unsigned long defvalue) +{ + if (!nla) + return defvalue; + return nla_get_msecs(nla); +} + +/** * nla_get_in_addr - return payload of IPv4 address attribute * @nla: IPv4 address netlink attribute */ @@ -1863,6 +2148,21 @@ static inline __be32 nla_get_in_addr(const struct nlattr *nla) } /** + * nla_get_in_addr_default - return payload of be32 attribute or default + * @nla: IPv4 address netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline __be32 nla_get_in_addr_default(const struct nlattr *nla, + __be32 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_in_addr(nla); +} + +/** * nla_get_in6_addr - return payload of IPv6 address attribute * @nla: IPv6 address netlink attribute */ @@ -1891,10 +2191,11 @@ static inline struct nla_bitfield32 nla_get_bitfield32(const struct nlattr *nla) * @src: netlink attribute to duplicate from * @gfp: GFP mask */ -static inline void *nla_memdup(const struct nlattr *src, gfp_t gfp) +static inline void *nla_memdup_noprof(const struct nlattr *src, gfp_t gfp) { - return kmemdup(nla_data(src), nla_len(src), gfp); + return kmemdup_noprof(nla_data(src), nla_len(src), gfp); } +#define nla_memdup(...) alloc_hooks(nla_memdup_noprof(__VA_ARGS__)) /** * nla_nest_start_noflag - Start a new level of nested attributes @@ -1905,7 +2206,7 @@ static inline void *nla_memdup(const struct nlattr *src, gfp_t gfp) * marked their nest attributes with NLA_F_NESTED flag. New APIs should use * nla_nest_start() which sets the flag. * - * Returns the container attribute or NULL on error + * Returns: the container attribute or NULL on error */ static inline struct nlattr *nla_nest_start_noflag(struct sk_buff *skb, int attrtype) @@ -1926,7 +2227,7 @@ static inline struct nlattr *nla_nest_start_noflag(struct sk_buff *skb, * Unlike nla_nest_start_noflag(), mark the nest attribute with NLA_F_NESTED * flag. This is the preferred function to use in new code. * - * Returns the container attribute or NULL on error + * Returns: the container attribute or NULL on error */ static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype) { @@ -1939,9 +2240,9 @@ static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype) * @start: container attribute * * Corrects the container attribute header to include the all - * appeneded attributes. + * appended attributes. * - * Returns the total data length of the skb. + * Returns: the total data length of the skb. */ static inline int nla_nest_end(struct sk_buff *skb, struct nlattr *start) { @@ -1963,6 +2264,20 @@ static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start) } /** + * nla_put_empty_nest - Create an empty nest + * @skb: socket buffer the message is stored in + * @attrtype: attribute type of the container + * + * This function is a helper for creating empty nests. + * + * Returns: 0 when successful or -EMSGSIZE on failure. + */ +static inline int nla_put_empty_nest(struct sk_buff *skb, int attrtype) +{ + return nla_nest_start(skb, attrtype) ? 0 : -EMSGSIZE; +} + +/** * __nla_validate_nested - Validate a stream of nested attributes * @start: container attribute * @maxtype: maximum attribute type to be expected @@ -1972,9 +2287,9 @@ static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start) * * Validates all attributes in the nested attribute stream against the * specified policy. Attributes with a type exceeding maxtype will be - * ignored. See documenation of struct nla_policy for more details. + * ignored. See documentation of struct nla_policy for more details. * - * Returns 0 on success or a negative error code. + * Returns: 0 on success or a negative error code. */ static inline int __nla_validate_nested(const struct nlattr *start, int maxtype, const struct nla_policy *policy, @@ -2007,7 +2322,7 @@ nla_validate_nested_deprecated(const struct nlattr *start, int maxtype, * nla_need_padding_for_64bit - test 64-bit alignment of the next attribute * @skb: socket buffer the message is stored in * - * Return true if padding is needed to align the next attribute (nla_data()) to + * Return: true if padding is needed to align the next attribute (nla_data()) to * a 64-bit aligned area. */ static inline bool nla_need_padding_for_64bit(struct sk_buff *skb) @@ -2034,7 +2349,7 @@ static inline bool nla_need_padding_for_64bit(struct sk_buff *skb) * This will only be done in architectures which do not have * CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS defined. * - * Returns zero on success or a negative error code. + * Returns: zero on success or a negative error code. */ static inline int nla_align_64bit(struct sk_buff *skb, int padattr) { @@ -2071,6 +2386,18 @@ static inline int nla_total_size_64bit(int payload) pos = nla_next(pos, &(rem))) /** + * nla_for_each_attr_type - iterate over a stream of attributes + * @pos: loop counter, set to current attribute + * @type: required attribute type for @pos + * @head: head of attribute stream + * @len: length of attribute stream + * @rem: initialized to len, holds bytes currently remaining in stream + */ +#define nla_for_each_attr_type(pos, type, head, len, rem) \ + nla_for_each_attr(pos, head, len, rem) \ + if (nla_type(pos) == type) + +/** * nla_for_each_nested - iterate over nested attributes * @pos: loop counter, set to current attribute * @nla: attribute containing the nested attributes @@ -2080,6 +2407,17 @@ static inline int nla_total_size_64bit(int payload) nla_for_each_attr(pos, nla_data(nla), nla_len(nla), rem) /** + * nla_for_each_nested_type - iterate over nested attributes + * @pos: loop counter, set to current attribute + * @type: required attribute type for @pos + * @nla: attribute containing the nested attributes + * @rem: initialized to len, holds bytes currently remaining in stream + */ +#define nla_for_each_nested_type(pos, type, nla, rem) \ + nla_for_each_nested(pos, nla, rem) \ + if (nla_type(pos) == type) + +/** * nla_is_last - Test if attribute is last in stream * @nla: attribute to test * @rem: bytes remaining in stream diff --git a/include/net/netmem.h b/include/net/netmem.h index d8b810245c1d..386164fb9c18 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -8,6 +8,83 @@ #ifndef _NET_NETMEM_H #define _NET_NETMEM_H +#include <linux/dma-mapping.h> +#include <linux/mm.h> +#include <net/net_debug.h> + +/* net_iov */ + +DECLARE_STATIC_KEY_FALSE(page_pool_mem_providers); + +/* We overload the LSB of the struct page pointer to indicate whether it's + * a page or net_iov. + */ +#define NET_IOV 0x01UL + +enum net_iov_type { + NET_IOV_DMABUF, + NET_IOV_IOURING, + + /* Force size to unsigned long to make the NET_IOV_ASSERTS below pass. + */ + NET_IOV_MAX = ULONG_MAX +}; + +struct net_iov { + enum net_iov_type type; + unsigned long pp_magic; + struct page_pool *pp; + struct net_iov_area *owner; + unsigned long dma_addr; + atomic_long_t pp_ref_count; +}; + +struct net_iov_area { + /* Array of net_iovs for this area. */ + struct net_iov *niovs; + size_t num_niovs; + + /* Offset into the dma-buf where this chunk starts. */ + unsigned long base_virtual; +}; + +/* These fields in struct page are used by the page_pool and net stack: + * + * struct { + * unsigned long pp_magic; + * struct page_pool *pp; + * unsigned long _pp_mapping_pad; + * unsigned long dma_addr; + * atomic_long_t pp_ref_count; + * }; + * + * We mirror the page_pool fields here so the page_pool can access these fields + * without worrying whether the underlying fields belong to a page or net_iov. + * + * The non-net stack fields of struct page are private to the mm stack and must + * never be mirrored to net_iov. + */ +#define NET_IOV_ASSERT_OFFSET(pg, iov) \ + static_assert(offsetof(struct page, pg) == \ + offsetof(struct net_iov, iov)) +NET_IOV_ASSERT_OFFSET(pp_magic, pp_magic); +NET_IOV_ASSERT_OFFSET(pp, pp); +NET_IOV_ASSERT_OFFSET(dma_addr, dma_addr); +NET_IOV_ASSERT_OFFSET(pp_ref_count, pp_ref_count); +#undef NET_IOV_ASSERT_OFFSET + +static inline struct net_iov_area *net_iov_owner(const struct net_iov *niov) +{ + return niov->owner; +} + +static inline unsigned int net_iov_idx(const struct net_iov *niov) +{ + return niov - net_iov_owner(niov)->niovs; +} + +/* netmem */ + /** * typedef netmem_ref - a nonexistent type marking a reference to generic * network memory. @@ -19,23 +96,204 @@ */ typedef unsigned long __bitwise netmem_ref; -/* This conversion fails (returns NULL) if the netmem_ref is not struct page - * backed. +static inline bool netmem_is_net_iov(const netmem_ref netmem) +{ + return (__force unsigned long)netmem & NET_IOV; +} + +/** + * __netmem_to_page - unsafely get pointer to the &page backing @netmem + * @netmem: netmem reference to convert * - * Currently struct page is the only possible netmem, and this helper never - * fails. + * Unsafe version of netmem_to_page(). When @netmem is always page-backed, + * e.g. when it's a header buffer, performs faster and generates smaller + * object code (no check for the LSB, no WARN). When @netmem points to IOV, + * provokes undefined behaviour. + * + * Return: pointer to the &page (garbage if @netmem is not page-backed). */ -static inline struct page *netmem_to_page(netmem_ref netmem) +static inline struct page *__netmem_to_page(netmem_ref netmem) { return (__force struct page *)netmem; } -/* Converting from page to netmem is always safe, because a page can always be - * a netmem. +/* This conversion fails (returns NULL) if the netmem_ref is not struct page + * backed. */ +static inline struct page *netmem_to_page(netmem_ref netmem) +{ + if (WARN_ON_ONCE(netmem_is_net_iov(netmem))) + return NULL; + + return __netmem_to_page(netmem); +} + +static inline struct net_iov *netmem_to_net_iov(netmem_ref netmem) +{ + if (netmem_is_net_iov(netmem)) + return (struct net_iov *)((__force unsigned long)netmem & + ~NET_IOV); + + DEBUG_NET_WARN_ON_ONCE(true); + return NULL; +} + +static inline netmem_ref net_iov_to_netmem(struct net_iov *niov) +{ + return (__force netmem_ref)((unsigned long)niov | NET_IOV); +} + static inline netmem_ref page_to_netmem(struct page *page) { return (__force netmem_ref)page; } +/** + * virt_to_netmem - convert virtual memory pointer to a netmem reference + * @data: host memory pointer to convert + * + * Return: netmem reference to the &page backing this virtual address. + */ +static inline netmem_ref virt_to_netmem(const void *data) +{ + return page_to_netmem(virt_to_page(data)); +} + +static inline int netmem_ref_count(netmem_ref netmem) +{ + /* The non-pp refcount of net_iov is always 1. On net_iov, we only + * support pp refcounting which uses the pp_ref_count field. + */ + if (netmem_is_net_iov(netmem)) + return 1; + + return page_ref_count(netmem_to_page(netmem)); +} + +static inline unsigned long netmem_pfn_trace(netmem_ref netmem) +{ + if (netmem_is_net_iov(netmem)) + return 0; + + return page_to_pfn(netmem_to_page(netmem)); +} + +static inline struct net_iov *__netmem_clear_lsb(netmem_ref netmem) +{ + return (struct net_iov *)((__force unsigned long)netmem & ~NET_IOV); +} + +/** + * __netmem_get_pp - unsafely get pointer to the &page_pool backing @netmem + * @netmem: netmem reference to get the pointer from + * + * Unsafe version of netmem_get_pp(). When @netmem is always page-backed, + * e.g. when it's a header buffer, performs faster and generates smaller + * object code (avoids clearing the LSB). When @netmem points to IOV, + * provokes invalid memory access. + * + * Return: pointer to the &page_pool (garbage if @netmem is not page-backed). + */ +static inline struct page_pool *__netmem_get_pp(netmem_ref netmem) +{ + return __netmem_to_page(netmem)->pp; +} + +static inline struct page_pool *netmem_get_pp(netmem_ref netmem) +{ + return __netmem_clear_lsb(netmem)->pp; +} + +static inline atomic_long_t *netmem_get_pp_ref_count_ref(netmem_ref netmem) +{ + return &__netmem_clear_lsb(netmem)->pp_ref_count; +} + +static inline bool netmem_is_pref_nid(netmem_ref netmem, int pref_nid) +{ + /* NUMA node preference only makes sense if we're allocating + * system memory. Memory providers (which give us net_iovs) + * choose for us. + */ + if (netmem_is_net_iov(netmem)) + return true; + + return page_to_nid(netmem_to_page(netmem)) == pref_nid; +} + +static inline netmem_ref netmem_compound_head(netmem_ref netmem) +{ + /* niov are never compounded */ + if (netmem_is_net_iov(netmem)) + return netmem; + + return page_to_netmem(compound_head(netmem_to_page(netmem))); +} + +/** + * __netmem_address - unsafely get pointer to the memory backing @netmem + * @netmem: netmem reference to get the pointer for + * + * Unsafe version of netmem_address(). When @netmem is always page-backed, + * e.g. when it's a header buffer, performs faster and generates smaller + * object code (no check for the LSB). When @netmem points to IOV, provokes + * undefined behaviour. + * + * Return: pointer to the memory (garbage if @netmem is not page-backed). + */ +static inline void *__netmem_address(netmem_ref netmem) +{ + return page_address(__netmem_to_page(netmem)); +} + +static inline void *netmem_address(netmem_ref netmem) +{ + if (netmem_is_net_iov(netmem)) + return NULL; + + return __netmem_address(netmem); +} + +/** + * netmem_is_pfmemalloc - check if @netmem was allocated under memory pressure + * @netmem: netmem reference to check + * + * Return: true if @netmem is page-backed and the page was allocated under + * memory pressure, false otherwise. + */ +static inline bool netmem_is_pfmemalloc(netmem_ref netmem) +{ + if (netmem_is_net_iov(netmem)) + return false; + + return page_is_pfmemalloc(netmem_to_page(netmem)); +} + +static inline unsigned long netmem_get_dma_addr(netmem_ref netmem) +{ + return __netmem_clear_lsb(netmem)->dma_addr; +} + +void get_netmem(netmem_ref netmem); +void put_netmem(netmem_ref netmem); + +#define netmem_dma_unmap_addr_set(NETMEM, PTR, ADDR_NAME, VAL) \ + do { \ + if (!netmem_is_net_iov(NETMEM)) \ + dma_unmap_addr_set(PTR, ADDR_NAME, VAL); \ + else \ + dma_unmap_addr_set(PTR, ADDR_NAME, 0); \ + } while (0) + +static inline void netmem_dma_unmap_page_attrs(struct device *dev, + dma_addr_t addr, size_t size, + enum dma_data_direction dir, + unsigned long attrs) +{ + if (!addr) + return; + + dma_unmap_page_attrs(dev, addr, size, dir, attrs); +} + #endif /* _NET_NETMEM_H */ diff --git a/include/net/netns/core.h b/include/net/netns/core.h index 78214f1b43a2..9b36f0ff0c20 100644 --- a/include/net/netns/core.h +++ b/include/net/netns/core.h @@ -15,6 +15,7 @@ struct netns_core { int sysctl_somaxconn; int sysctl_optmem_max; u8 sysctl_txrehash; + u8 sysctl_tstamp_allow_data; #ifdef CONFIG_PROC_FS struct prot_inuse __percpu *prot_inuse; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index c356c458b340..6373e3f17da8 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -40,6 +40,18 @@ struct inet_timewait_death_row { struct tcp_fastopen_context; +#ifdef CONFIG_IP_ROUTE_MULTIPATH +struct sysctl_fib_multipath_hash_seed { + u32 user_seed; + u32 mp_seed; +}; +#endif + +struct udp_tunnel_gro { + struct sock __rcu *sk; + struct hlist_head list; +}; + struct netns_ipv4 { /* Cacheline organization can be found documented in * Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst. @@ -69,6 +81,8 @@ struct netns_ipv4 { __cacheline_group_begin(netns_ipv4_read_rx); u8 sysctl_ip_early_demux; u8 sysctl_tcp_early_demux; + u8 sysctl_tcp_l3mdev_accept; + /* 3 bytes hole, try to pack */ int sysctl_tcp_reordering; int sysctl_tcp_rmem[3]; __cacheline_group_end(netns_ipv4_read_rx); @@ -76,6 +90,11 @@ struct netns_ipv4 { struct inet_timewait_death_row tcp_death_row; struct udp_table *udp_table; +#if IS_ENABLED(CONFIG_NET_UDP_TUNNEL) + /* Not in a pernet subsys because need to be available at GRO stage */ + struct udp_tunnel_gro udp_tunnel_gro[2]; +#endif + #ifdef CONFIG_SYSCTL struct ctl_table_header *forw_hdr; struct ctl_table_header *frags_hdr; @@ -102,6 +121,9 @@ struct netns_ipv4 { #endif struct hlist_head *fib_table_hash; struct sock *fibnl; + struct hlist_head *fib_info_hash; + unsigned int fib_info_hash_bits; + unsigned int fib_info_cnt; struct sock *mc_autojoin_sk; @@ -115,7 +137,10 @@ struct netns_ipv4 { u8 sysctl_icmp_errors_use_inbound_ifaddr; int sysctl_icmp_ratelimit; int sysctl_icmp_ratemask; - + int sysctl_icmp_msgs_per_sec; + int sysctl_icmp_msgs_burst; + atomic_t icmp_global_credit; + u32 icmp_global_stamp; u32 ip_rt_min_pmtu; int ip_rt_mtu_expires; int ip_rt_min_advmss; @@ -141,9 +166,6 @@ struct netns_ipv4 { u8 sysctl_fwmark_reflect; u8 sysctl_tcp_fwmark_accept; -#ifdef CONFIG_NET_L3_MASTER_DEV - u8 sysctl_tcp_l3mdev_accept; -#endif u8 sysctl_tcp_mtu_probing; int sysctl_tcp_mtu_probe_floor; int sysctl_tcp_base_mss; @@ -166,10 +188,13 @@ struct netns_ipv4 { u8 sysctl_tcp_retries2; u8 sysctl_tcp_orphan_retries; u8 sysctl_tcp_tw_reuse; + unsigned int sysctl_tcp_tw_reuse_delay; int sysctl_tcp_fin_timeout; u8 sysctl_tcp_sack; u8 sysctl_tcp_window_scaling; u8 sysctl_tcp_timestamps; + int sysctl_tcp_rto_min_us; + int sysctl_tcp_rto_max_ms; u8 sysctl_tcp_recovery; u8 sysctl_tcp_thin_linear_timeouts; u8 sysctl_tcp_slow_start_after_idle; @@ -245,18 +270,22 @@ struct netns_ipv4 { #endif #endif #ifdef CONFIG_IP_ROUTE_MULTIPATH + struct sysctl_fib_multipath_hash_seed sysctl_fib_multipath_hash_seed; u32 sysctl_fib_multipath_hash_fields; u8 sysctl_fib_multipath_use_neigh; u8 sysctl_fib_multipath_hash_policy; #endif struct fib_notifier_ops *notifier_ops; - unsigned int fib_seq; /* protected by rtnl_mutex */ + unsigned int fib_seq; /* writes protected by rtnl_mutex */ struct fib_notifier_ops *ipmr_notifier_ops; unsigned int ipmr_seq; /* protected by rtnl_mutex */ atomic_t rt_genid; siphash_key_t ip_id_key; + struct hlist_head *inet_addr_lst; + struct delayed_work addr_chk_work; }; + #endif diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 5f2cfd84570a..47dc70d8100a 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -72,6 +72,7 @@ struct netns_ipv6 { struct rt6_statistics *rt6_stats; struct timer_list ip6_fib_timer; struct hlist_head *fib_table_hash; + spinlock_t fib_table_hash_lock; struct fib6_table *fib6_main_tbl; struct list_head fib6_walkers; rwlock_t fib6_walker_lock; diff --git a/include/net/netns/netfilter.h b/include/net/netns/netfilter.h index 02bbdc577f8e..a6a0bf4a247e 100644 --- a/include/net/netns/netfilter.h +++ b/include/net/netns/netfilter.h @@ -15,6 +15,9 @@ struct netns_nf { const struct nf_logger __rcu *nf_loggers[NFPROTO_NUMPROTO]; #ifdef CONFIG_SYSCTL struct ctl_table_header *nf_log_dir_header; +#ifdef CONFIG_LWTUNNEL + struct ctl_table_header *nf_lwtnl_dir_header; +#endif #endif struct nf_hook_entries __rcu *hooks_ipv4[NF_INET_NUMHOOKS]; struct nf_hook_entries __rcu *hooks_ipv6[NF_INET_NUMHOOKS]; diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h index 7eff3d981b89..d25cd7a9c5ff 100644 --- a/include/net/netns/sctp.h +++ b/include/net/netns/sctp.h @@ -125,14 +125,14 @@ struct netns_sctp { int pf_expose; /* - * Policy for preforming sctp/socket accounting + * Policy for performing sctp/socket accounting * 0 - do socket level accounting, all assocs share sk_sndbuf * 1 - do sctp accounting, each asoc may use sk_sndbuf bytes */ int sndbuf_policy; /* - * Policy for preforming sctp/socket accounting + * Policy for performing sctp/socket accounting * 0 - do socket level accounting, all assocs share sk_rcvbuf * 1 - do sctp accounting, each asoc may use sk_rcvbuf bytes */ diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index 423b52eca908..23dd647fe024 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -43,6 +43,7 @@ struct netns_xfrm { struct hlist_head __rcu *state_bysrc; struct hlist_head __rcu *state_byspi; struct hlist_head __rcu *state_byseq; + struct hlist_head __percpu *state_cache_input; unsigned int state_hmask; unsigned int state_num; struct work_struct state_hash_work; @@ -51,7 +52,6 @@ struct netns_xfrm { struct hlist_head *policy_byidx; unsigned int policy_idx_hmask; unsigned int idx_generator; - struct hlist_head policy_inexact[XFRM_POLICY_MAX]; struct xfrm_policy_hash policy_bydst[XFRM_POLICY_MAX]; unsigned int policy_count[XFRM_POLICY_MAX * 2]; struct work_struct policy_hash_work; @@ -83,6 +83,7 @@ struct netns_xfrm { spinlock_t xfrm_policy_lock; struct mutex xfrm_cfg_mutex; + struct delayed_work nat_keepalive_work; }; #endif diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 7ca315ad500e..572e69cda476 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -105,7 +105,7 @@ struct nh_grp_entry_stats { struct nh_grp_entry { struct nexthop *nh; struct nh_grp_entry_stats __percpu *stats; - u8 weight; + u16 weight; union { struct { @@ -152,6 +152,8 @@ struct nexthop { u8 protocol; /* app managing this nh */ u8 nh_flags; bool is_group; + bool dead; + spinlock_t lock; /* protect dead and f6i_list */ refcount_t refcnt; struct rcu_head rcu; @@ -192,7 +194,7 @@ struct nh_notifier_single_info { }; struct nh_notifier_grp_entry_info { - u8 weight; + u16 weight; struct nh_notifier_single_info nh; }; @@ -267,7 +269,7 @@ static inline bool nexthop_get(struct nexthop *nh) static inline void nexthop_put(struct nexthop *nh) { if (refcount_dec_and_test(&nh->refcnt)) - call_rcu(&nh->rcu, nexthop_free_rcu); + call_rcu_hurry(&nh->rcu, nexthop_free_rcu); } static inline bool nexthop_cmp(const struct nexthop *nh1, diff --git a/include/net/nfc/nci.h b/include/net/nfc/nci.h index e82f55f543bb..09efcaed7c3f 100644 --- a/include/net/nfc/nci.h +++ b/include/net/nfc/nci.h @@ -332,7 +332,7 @@ struct nci_core_init_rsp_1 { __le32 nfcc_features; __u8 num_supported_rf_interfaces; __u8 supported_rf_interfaces[]; /* variable size array */ - /* continuted in nci_core_init_rsp_2 */ + /* continued in nci_core_init_rsp_2 */ } __packed; struct nci_core_init_rsp_2 { @@ -475,7 +475,7 @@ struct nci_rf_discover_ntf { #define NCI_OP_RF_INTF_ACTIVATED_NTF nci_opcode_pack(NCI_GID_RF_MGMT, 0x05) struct activation_params_nfca_poll_iso_dep { __u8 rats_res_len; - __u8 rats_res[20]; + __u8 rats_res[NFC_ATS_MAXSIZE]; }; struct activation_params_nfcb_poll_iso_dep { diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h index ea8595651c38..e180bdf2f82b 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -265,6 +265,10 @@ struct nci_dev { /* stored during intf_activated_ntf */ __u8 remote_gb[NFC_MAX_GT_LEN]; __u8 remote_gb_len; + + /* stored during intf_activated_ntf */ + __u8 target_ats[NFC_ATS_MAXSIZE]; + __u8 target_ats_len; }; /* ----- NCI Devices ----- */ diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h index 3d07abacf08b..127e6c7d910d 100644 --- a/include/net/nfc/nfc.h +++ b/include/net/nfc/nfc.h @@ -80,12 +80,14 @@ struct nfc_ops { #define NFC_ATR_REQ_GT_OFFSET 14 /** - * struct nfc_target - NFC target descriptiom + * struct nfc_target - NFC target description * * @sens_res: 2 bytes describing the target SENS_RES response, if the target * is a type A one. The %sens_res most significant byte must be byte 2 * as described by the NFC Forum digital specification (i.e. the platform * configuration one) while %sens_res least significant byte is byte 1. + * @ats_len: length of Answer To Select in bytes + * @ats: Answer To Select returned by an ISO 14443 Type A target upon activation */ struct nfc_target { u32 idx; @@ -105,6 +107,8 @@ struct nfc_target { u8 is_iso15693; u8 iso15693_dsfid; u8 iso15693_uid[NFC_ISO15693_UID_MAXSIZE]; + u8 ats_len; + u8 ats[NFC_ATS_MAXSIZE]; }; /** @@ -230,10 +234,10 @@ static inline void nfc_set_parent_dev(struct nfc_dev *nfc_dev, } /** - * nfc_set_drvdata - set driver specifc data + * nfc_set_drvdata - set driver specific data * * @dev: The nfc device - * @data: Pointer to driver specifc data + * @data: Pointer to driver specific data */ static inline void nfc_set_drvdata(struct nfc_dev *dev, void *data) { @@ -241,7 +245,7 @@ static inline void nfc_set_drvdata(struct nfc_dev *dev, void *data) } /** - * nfc_get_drvdata - get driver specifc data + * nfc_get_drvdata - get driver specific data * * @dev: The nfc device */ diff --git a/include/net/nl802154.h b/include/net/nl802154.h index 4c752f799957..a994dea74596 100644 --- a/include/net/nl802154.h +++ b/include/net/nl802154.h @@ -192,7 +192,7 @@ enum nl802154_iftype { * @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_MAX_CCA_ED_LEVEL: maximum 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 diff --git a/include/net/p8022.h b/include/net/p8022.h deleted file mode 100644 index a29e224ac498..000000000000 --- a/include/net/p8022.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _NET_P8022_H -#define _NET_P8022_H - -struct net_device; -struct packet_type; -struct sk_buff; - -struct datalink_proto * -register_8022_client(unsigned char type, - int (*func)(struct sk_buff *skb, - struct net_device *dev, - struct packet_type *pt, - struct net_device *orig_dev)); -void unregister_8022_client(struct datalink_proto *proto); -#endif diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h index 1d397c1a0043..93f2c31baf9b 100644 --- a/include/net/page_pool/helpers.h +++ b/include/net/page_pool/helpers.h @@ -52,13 +52,17 @@ #ifndef _NET_PAGE_POOL_HELPERS_H #define _NET_PAGE_POOL_HELPERS_H +#include <linux/dma-mapping.h> + #include <net/page_pool/types.h> +#include <net/net_debug.h> +#include <net/netmem.h> #ifdef CONFIG_PAGE_POOL_STATS /* Deprecated driver-facing API, use netlink instead */ int page_pool_ethtool_stats_get_count(void); u8 *page_pool_ethtool_stats_get_strings(u8 *data); -u64 *page_pool_ethtool_stats_get(u64 *data, void *stats); +u64 *page_pool_ethtool_stats_get(u64 *data, const void *stats); bool page_pool_get_stats(const struct page_pool *pool, struct page_pool_stats *stats); @@ -73,7 +77,7 @@ static inline u8 *page_pool_ethtool_stats_get_strings(u8 *data) return data; } -static inline u64 *page_pool_ethtool_stats_get(u64 *data, void *stats) +static inline u64 *page_pool_ethtool_stats_get(u64 *data, const void *stats) { return data; } @@ -100,8 +104,7 @@ static inline struct page *page_pool_dev_alloc_pages(struct page_pool *pool) * * Get a page fragment from the page allocator or page_pool caches. * - * Return: - * Return allocated page fragment, otherwise return NULL. + * Return: allocated page fragment, otherwise return NULL. */ static inline struct page *page_pool_dev_alloc_frag(struct page_pool *pool, unsigned int *offset, @@ -112,22 +115,22 @@ static inline struct page *page_pool_dev_alloc_frag(struct page_pool *pool, return page_pool_alloc_frag(pool, offset, size, gfp); } -static inline struct page *page_pool_alloc(struct page_pool *pool, - unsigned int *offset, - unsigned int *size, gfp_t gfp) +static inline netmem_ref page_pool_alloc_netmem(struct page_pool *pool, + unsigned int *offset, + unsigned int *size, gfp_t gfp) { unsigned int max_size = PAGE_SIZE << pool->p.order; - struct page *page; + netmem_ref netmem; if ((*size << 1) > max_size) { *size = max_size; *offset = 0; - return page_pool_alloc_pages(pool, gfp); + return page_pool_alloc_netmems(pool, gfp); } - page = page_pool_alloc_frag(pool, offset, *size, gfp); - if (unlikely(!page)) - return NULL; + netmem = page_pool_alloc_frag_netmem(pool, offset, *size, gfp); + if (unlikely(!netmem)) + return 0; /* There is very likely not enough space for another fragment, so append * the remaining size to the current fragment to avoid truesize @@ -138,7 +141,23 @@ static inline struct page *page_pool_alloc(struct page_pool *pool, pool->frag_offset = max_size; } - return page; + return netmem; +} + +static inline netmem_ref page_pool_dev_alloc_netmem(struct page_pool *pool, + unsigned int *offset, + unsigned int *size) +{ + gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN; + + return page_pool_alloc_netmem(pool, offset, size, gfp); +} + +static inline struct page *page_pool_alloc(struct page_pool *pool, + unsigned int *offset, + unsigned int *size, gfp_t gfp) +{ + return netmem_to_page(page_pool_alloc_netmem(pool, offset, size, gfp)); } /** @@ -151,8 +170,7 @@ static inline struct page *page_pool_alloc(struct page_pool *pool, * depending on the requested size in order to allocate memory with least memory * utilization and performance penalty. * - * Return: - * Return allocated page or page fragment, otherwise return NULL. + * Return: allocated page or page fragment, otherwise return NULL. */ static inline struct page *page_pool_dev_alloc(struct page_pool *pool, unsigned int *offset, @@ -186,8 +204,7 @@ static inline void *page_pool_alloc_va(struct page_pool *pool, * This is just a thin wrapper around the page_pool_alloc() API, and * it returns va of the allocated page or page fragment. * - * Return: - * Return the va for the allocated page or page fragment, otherwise return NULL. + * Return: the va for the allocated page or page fragment, otherwise return NULL. */ static inline void *page_pool_dev_alloc_va(struct page_pool *pool, unsigned int *size) @@ -204,12 +221,17 @@ static inline void *page_pool_dev_alloc_va(struct page_pool *pool, * Get the stored dma direction. A driver might decide to store this locally * and avoid the extra cache line from page_pool to determine the direction. */ -static -inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool) +static inline enum dma_data_direction +page_pool_get_dma_dir(const struct page_pool *pool) { return pool->p.dma_dir; } +static inline void page_pool_fragment_netmem(netmem_ref netmem, long nr) +{ + atomic_long_set(netmem_get_pp_ref_count_ref(netmem), nr); +} + /** * page_pool_fragment_page() - split a fresh page into fragments * @page: page to split @@ -230,11 +252,12 @@ inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool) */ static inline void page_pool_fragment_page(struct page *page, long nr) { - atomic_long_set(&page->pp_ref_count, nr); + page_pool_fragment_netmem(page_to_netmem(page), nr); } -static inline long page_pool_unref_page(struct page *page, long nr) +static inline long page_pool_unref_netmem(netmem_ref netmem, long nr) { + atomic_long_t *pp_ref_count = netmem_get_pp_ref_count_ref(netmem); long ret; /* If nr == pp_ref_count then we have cleared all remaining @@ -251,19 +274,19 @@ static inline long page_pool_unref_page(struct page *page, long nr) * initially, and only overwrite it when the page is partitioned into * more than one piece. */ - if (atomic_long_read(&page->pp_ref_count) == nr) { + if (atomic_long_read(pp_ref_count) == nr) { /* As we have ensured nr is always one for constant case using * the BUILD_BUG_ON(), only need to handle the non-constant case * here for pp_ref_count draining, which is a rare case. */ BUILD_BUG_ON(__builtin_constant_p(nr) && nr != 1); if (!__builtin_constant_p(nr)) - atomic_long_set(&page->pp_ref_count, 1); + atomic_long_set(pp_ref_count, 1); return 0; } - ret = atomic_long_sub_return(nr, &page->pp_ref_count); + ret = atomic_long_sub_return(nr, pp_ref_count); WARN_ON(ret < 0); /* We are the last user here too, reset pp_ref_count back to 1 to @@ -272,20 +295,46 @@ static inline long page_pool_unref_page(struct page *page, long nr) * page_pool_unref_page() currently. */ if (unlikely(!ret)) - atomic_long_set(&page->pp_ref_count, 1); + atomic_long_set(pp_ref_count, 1); return ret; } +static inline long page_pool_unref_page(struct page *page, long nr) +{ + return page_pool_unref_netmem(page_to_netmem(page), nr); +} + +static inline void page_pool_ref_netmem(netmem_ref netmem) +{ + atomic_long_inc(netmem_get_pp_ref_count_ref(netmem)); +} + static inline void page_pool_ref_page(struct page *page) { - atomic_long_inc(&page->pp_ref_count); + page_pool_ref_netmem(page_to_netmem(page)); } -static inline bool page_pool_is_last_ref(struct page *page) +static inline bool page_pool_unref_and_test(netmem_ref netmem) { /* If page_pool_unref_page() returns 0, we were the last user */ - return page_pool_unref_page(page, 1) == 0; + return page_pool_unref_netmem(netmem, 1) == 0; +} + +static inline void page_pool_put_netmem(struct page_pool *pool, + netmem_ref netmem, + unsigned int dma_sync_size, + bool allow_direct) +{ + /* When page_pool isn't compiled-in, net/core/xdp.c doesn't + * allow registering MEM_TYPE_PAGE_POOL, but shield linker. + */ +#ifdef CONFIG_PAGE_POOL + if (!page_pool_unref_and_test(netmem)) + return; + + page_pool_put_unrefed_netmem(pool, netmem, dma_sync_size, allow_direct); +#endif } /** @@ -306,15 +355,15 @@ static inline void page_pool_put_page(struct page_pool *pool, unsigned int dma_sync_size, bool allow_direct) { - /* When page_pool isn't compiled-in, net/core/xdp.c doesn't - * allow registering MEM_TYPE_PAGE_POOL, but shield linker. - */ -#ifdef CONFIG_PAGE_POOL - if (!page_pool_is_last_ref(page)) - return; + page_pool_put_netmem(pool, page_to_netmem(page), dma_sync_size, + allow_direct); +} - page_pool_put_unrefed_page(pool, page, dma_sync_size, allow_direct); -#endif +static inline void page_pool_put_full_netmem(struct page_pool *pool, + netmem_ref netmem, + bool allow_direct) +{ + page_pool_put_netmem(pool, netmem, -1, allow_direct); } /** @@ -329,7 +378,7 @@ static inline void page_pool_put_page(struct page_pool *pool, static inline void page_pool_put_full_page(struct page_pool *pool, struct page *page, bool allow_direct) { - page_pool_put_page(pool, page, -1, allow_direct); + page_pool_put_netmem(pool, page_to_netmem(page), -1, allow_direct); } /** @@ -346,6 +395,12 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, page_pool_put_full_page(pool, page, true); } +static inline void page_pool_recycle_direct_netmem(struct page_pool *pool, + netmem_ref netmem) +{ + page_pool_put_full_netmem(pool, netmem, true); +} + #define PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA \ (sizeof(dma_addr_t) > sizeof(unsigned long)) @@ -363,6 +418,16 @@ static inline void page_pool_free_va(struct page_pool *pool, void *va, page_pool_put_page(pool, virt_to_head_page(va), -1, allow_direct); } +static inline dma_addr_t page_pool_get_dma_addr_netmem(netmem_ref netmem) +{ + dma_addr_t ret = netmem_get_dma_addr(netmem); + + if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) + ret <<= PAGE_SHIFT; + + return ret; +} + /** * page_pool_get_dma_addr() - Retrieve the stored DMA address. * @page: page allocated from a page pool @@ -370,7 +435,7 @@ static inline void page_pool_free_va(struct page_pool *pool, void *va, * Fetch the DMA address of the page. The page pool to which the page belongs * must had been created with PP_FLAG_DMA_MAP. */ -static inline dma_addr_t page_pool_get_dma_addr(struct page *page) +static inline dma_addr_t page_pool_get_dma_addr(const struct page *page) { dma_addr_t ret = page->dma_addr; @@ -380,19 +445,46 @@ static inline dma_addr_t page_pool_get_dma_addr(struct page *page) return ret; } -static inline bool page_pool_set_dma_addr(struct page *page, dma_addr_t addr) +static inline void __page_pool_dma_sync_for_cpu(const struct page_pool *pool, + const dma_addr_t dma_addr, + u32 offset, u32 dma_sync_size) { - if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) { - page->dma_addr = addr >> PAGE_SHIFT; + dma_sync_single_range_for_cpu(pool->p.dev, dma_addr, + offset + pool->p.offset, dma_sync_size, + page_pool_get_dma_dir(pool)); +} - /* We assume page alignment to shave off bottom bits, - * if this "compression" doesn't work we need to drop. - */ - return addr != (dma_addr_t)page->dma_addr << PAGE_SHIFT; - } +/** + * page_pool_dma_sync_for_cpu - sync Rx page for CPU after it's written by HW + * @pool: &page_pool the @page belongs to + * @page: page to sync + * @offset: offset from page start to "hard" start if using PP frags + * @dma_sync_size: size of the data written to the page + * + * Can be used as a shorthand to sync Rx pages before accessing them in the + * driver. Caller must ensure the pool was created with ``PP_FLAG_DMA_MAP``. + * Note that this version performs DMA sync unconditionally, even if the + * associated PP doesn't perform sync-for-device. + */ +static inline void page_pool_dma_sync_for_cpu(const struct page_pool *pool, + const struct page *page, + u32 offset, u32 dma_sync_size) +{ + __page_pool_dma_sync_for_cpu(pool, page_pool_get_dma_addr(page), offset, + dma_sync_size); +} - page->dma_addr = addr; - return false; +static inline void +page_pool_dma_sync_netmem_for_cpu(const struct page_pool *pool, + const netmem_ref netmem, u32 offset, + u32 dma_sync_size) +{ + if (!pool->dma_sync_for_cpu) + return; + + __page_pool_dma_sync_for_cpu(pool, + page_pool_get_dma_addr_netmem(netmem), + offset, dma_sync_size); } static inline bool page_pool_put(struct page_pool *pool) @@ -406,4 +498,9 @@ static inline void page_pool_nid_changed(struct page_pool *pool, int new_nid) page_pool_update_nid(pool, new_nid); } +static inline bool page_pool_is_unreadable(struct page_pool *pool) +{ + return !!pool->mp_ops; +} + #endif /* _NET_PAGE_POOL_HELPERS_H */ diff --git a/include/net/page_pool/memory_provider.h b/include/net/page_pool/memory_provider.h new file mode 100644 index 000000000000..ada4f968960a --- /dev/null +++ b/include/net/page_pool/memory_provider.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _NET_PAGE_POOL_MEMORY_PROVIDER_H +#define _NET_PAGE_POOL_MEMORY_PROVIDER_H + +#include <net/netmem.h> +#include <net/page_pool/types.h> + +struct netdev_rx_queue; +struct netlink_ext_ack; +struct sk_buff; + +struct memory_provider_ops { + netmem_ref (*alloc_netmems)(struct page_pool *pool, gfp_t gfp); + bool (*release_netmem)(struct page_pool *pool, netmem_ref netmem); + int (*init)(struct page_pool *pool); + void (*destroy)(struct page_pool *pool); + int (*nl_fill)(void *mp_priv, struct sk_buff *rsp, + struct netdev_rx_queue *rxq); + void (*uninstall)(void *mp_priv, struct netdev_rx_queue *rxq); +}; + +bool net_mp_niov_set_dma_addr(struct net_iov *niov, dma_addr_t addr); +void net_mp_niov_set_page_pool(struct page_pool *pool, struct net_iov *niov); +void net_mp_niov_clear_page_pool(struct net_iov *niov); + +int net_mp_open_rxq(struct net_device *dev, unsigned ifq_idx, + struct pp_memory_provider_params *p); +int __net_mp_open_rxq(struct net_device *dev, unsigned int rxq_idx, + const struct pp_memory_provider_params *p, + struct netlink_ext_ack *extack); +void net_mp_close_rxq(struct net_device *dev, unsigned ifq_idx, + struct pp_memory_provider_params *old_p); +void __net_mp_close_rxq(struct net_device *dev, unsigned int rxq_idx, + const struct pp_memory_provider_params *old_p); + +/** + * net_mp_netmem_place_in_cache() - give a netmem to a page pool + * @pool: the page pool to place the netmem into + * @netmem: netmem to give + * + * Push an accounted netmem into the page pool's allocation cache. The caller + * must ensure that there is space in the cache. It should only be called off + * the mp_ops->alloc_netmems() path. + */ +static inline void net_mp_netmem_place_in_cache(struct page_pool *pool, + netmem_ref netmem) +{ + pool->alloc.cache[pool->alloc.count++] = netmem; +} + +#endif diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index 5e43a08d3231..431b593de709 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -6,6 +6,8 @@ #include <linux/dma-direction.h> #include <linux/ptr_ring.h> #include <linux/types.h> +#include <linux/xarray.h> +#include <net/netmem.h> #define PP_FLAG_DMA_MAP BIT(0) /* Should page_pool do the DMA * map/unmap @@ -19,8 +21,21 @@ * device driver responsibility */ #define PP_FLAG_SYSTEM_POOL BIT(2) /* Global system page_pool */ + +/* Allow unreadable (net_iov backed) netmem in this page_pool. Drivers setting + * this must be able to support unreadable netmem, where netmem_address() would + * return NULL. This flag should not be set for header page_pools. + * + * If the driver sets PP_FLAG_ALLOW_UNREADABLE_NETMEM, it should also set + * page_pool_params.slow.queue_idx. + */ +#define PP_FLAG_ALLOW_UNREADABLE_NETMEM BIT(3) + #define PP_FLAG_ALL (PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV | \ - PP_FLAG_SYSTEM_POOL) + PP_FLAG_SYSTEM_POOL | PP_FLAG_ALLOW_UNREADABLE_NETMEM) + +/* Index limit to stay within PP_DMA_INDEX_BITS for DMA indices */ +#define PP_DMA_INDEX_LIMIT XA_LIMIT(1, BIT(PP_DMA_INDEX_BITS) - 1) /* * Fast allocation side cache array/stack @@ -40,25 +55,28 @@ #define PP_ALLOC_CACHE_REFILL 64 struct pp_alloc_cache { u32 count; - struct page *cache[PP_ALLOC_CACHE_SIZE]; + netmem_ref cache[PP_ALLOC_CACHE_SIZE]; }; /** * struct page_pool_params - page pool parameters - * @flags: PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV + * @fast: params accessed frequently on hotpath * @order: 2^order pages on allocation * @pool_size: size of the ptr_ring * @nid: NUMA node id to allocate from pages from * @dev: device, for DMA pre-mapping purposes - * @netdev: netdev this pool will serve (leave as NULL if none or multiple) * @napi: NAPI which is the sole consumer of pages, otherwise NULL * @dma_dir: DMA mapping direction * @max_len: max DMA sync memory size for PP_FLAG_DMA_SYNC_DEV * @offset: DMA sync address offset for PP_FLAG_DMA_SYNC_DEV + * @slow: params with slowpath access only (initialization and Netlink) + * @netdev: netdev this pool will serve (leave as NULL if none or multiple) + * @queue_idx: queue idx this page_pool is being created for. + * @flags: PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV, PP_FLAG_SYSTEM_POOL, + * PP_FLAG_ALLOW_UNREADABLE_NETMEM. */ struct page_pool_params { struct_group_tagged(page_pool_params_fast, fast, - unsigned int flags; unsigned int order; unsigned int pool_size; int nid; @@ -70,8 +88,10 @@ struct page_pool_params { ); struct_group_tagged(page_pool_params_slow, slow, struct net_device *netdev; + unsigned int queue_idx; + unsigned int flags; /* private: used by test code only */ - void (*init_callback)(struct page *page, void *arg); + void (*init_callback)(netmem_ref netmem, void *arg); void *init_arg; ); }; @@ -126,16 +146,42 @@ struct page_pool_stats { }; #endif +/* The whole frag API block must stay within one cacheline. On 32-bit systems, + * sizeof(long) == sizeof(int), so that the block size is ``3 * sizeof(long)``. + * On 64-bit systems, the actual size is ``2 * sizeof(long) + sizeof(int)``. + * The closest pow-2 to both of them is ``4 * sizeof(long)``, so just use that + * one for simplicity. + * Having it aligned to a cacheline boundary may be excessive and doesn't bring + * any good. + */ +#define PAGE_POOL_FRAG_GROUP_ALIGN (4 * sizeof(long)) + +struct memory_provider_ops; + +struct pp_memory_provider_params { + void *mp_priv; + const struct memory_provider_ops *mp_ops; +}; + struct page_pool { struct page_pool_params_fast p; int cpuid; - bool has_init_callback; + u32 pages_state_hold_cnt; + + bool has_init_callback:1; /* slow::init_callback is set */ + bool dma_map:1; /* Perform DMA mapping */ + bool dma_sync:1; /* Perform DMA sync for device */ + bool dma_sync_for_cpu:1; /* Perform DMA sync for cpu */ +#ifdef CONFIG_PAGE_POOL_STATS + bool system:1; /* This is a global percpu pool */ +#endif + __cacheline_group_begin_aligned(frag, PAGE_POOL_FRAG_GROUP_ALIGN); long frag_users; - struct page *frag_page; + netmem_ref frag_page; unsigned int frag_offset; - u32 pages_state_hold_cnt; + __cacheline_group_end_aligned(frag, PAGE_POOL_FRAG_GROUP_ALIGN); struct delayed_work release_dw; void (*disconnect)(void *pool); @@ -176,6 +222,11 @@ struct page_pool { */ struct ptr_ring ring; + void *mp_priv; + const struct memory_provider_ops *mp_ops; + + struct xarray dma_mapped; + #ifdef CONFIG_PAGE_POOL_STATS /* recycle stats are per-cpu to avoid locking */ struct page_pool_recycle_stats __percpu *recycle_stats; @@ -196,14 +247,17 @@ struct page_pool { struct { struct hlist_node list; u64 detach_time; - u32 napi_id; u32 id; } user; }; struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp); +netmem_ref page_pool_alloc_netmems(struct page_pool *pool, gfp_t gfp); struct page *page_pool_alloc_frag(struct page_pool *pool, unsigned int *offset, unsigned int size, gfp_t gfp); +netmem_ref page_pool_alloc_frag_netmem(struct page_pool *pool, + unsigned int *offset, unsigned int size, + gfp_t gfp); struct page_pool *page_pool_create(const struct page_pool_params *params); struct page_pool *page_pool_create_percpu(const struct page_pool_params *params, int cpuid); @@ -211,11 +265,11 @@ struct page_pool *page_pool_create_percpu(const struct page_pool_params *params, struct xdp_mem_info; #ifdef CONFIG_PAGE_POOL +void page_pool_disable_direct_recycling(struct page_pool *pool); void page_pool_destroy(struct page_pool *pool); void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *), - struct xdp_mem_info *mem); -void page_pool_put_page_bulk(struct page_pool *pool, void **data, - int count); + const struct xdp_mem_info *mem); +void page_pool_put_netmem_bulk(netmem_ref *data, u32 count); #else static inline void page_pool_destroy(struct page_pool *pool) { @@ -223,16 +277,18 @@ static inline void page_pool_destroy(struct page_pool *pool) static inline void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *), - struct xdp_mem_info *mem) + const struct xdp_mem_info *mem) { } -static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data, - int count) +static inline void page_pool_put_netmem_bulk(netmem_ref *data, u32 count) { } #endif +void page_pool_put_unrefed_netmem(struct page_pool *pool, netmem_ref netmem, + unsigned int dma_sync_size, + bool allow_direct); void page_pool_put_unrefed_page(struct page_pool *pool, struct page *page, unsigned int dma_sync_size, bool allow_direct); diff --git a/include/net/pfcp.h b/include/net/pfcp.h new file mode 100644 index 000000000000..af14f970b80e --- /dev/null +++ b/include/net/pfcp.h @@ -0,0 +1,90 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _PFCP_H_ +#define _PFCP_H_ + +#include <uapi/linux/if_ether.h> +#include <net/dst_metadata.h> +#include <linux/netdevice.h> +#include <uapi/linux/ipv6.h> +#include <net/udp_tunnel.h> +#include <uapi/linux/udp.h> +#include <uapi/linux/ip.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/bits.h> + +#define PFCP_PORT 8805 + +/* PFCP protocol header */ +struct pfcphdr { + u8 flags; + u8 message_type; + __be16 message_length; +}; + +/* PFCP header flags */ +#define PFCP_SEID_FLAG BIT(0) +#define PFCP_MP_FLAG BIT(1) + +#define PFCP_VERSION_MASK GENMASK(4, 0) + +#define PFCP_HLEN (sizeof(struct udphdr) + sizeof(struct pfcphdr)) + +/* PFCP node related messages */ +struct pfcphdr_node { + u8 seq_number[3]; + u8 reserved; +}; + +/* PFCP session related messages */ +struct pfcphdr_session { + __be64 seid; + u8 seq_number[3]; +#ifdef __LITTLE_ENDIAN_BITFIELD + u8 message_priority:4, + reserved:4; +#elif defined(__BIG_ENDIAN_BITFIELD) + u8 reserved:4, + message_priprity:4; +#else +#error "Please fix <asm/byteorder>" +#endif +}; + +struct pfcp_metadata { + u8 type; + __be64 seid; +} __packed; + +enum { + PFCP_TYPE_NODE = 0, + PFCP_TYPE_SESSION = 1, +}; + +#define PFCP_HEADROOM (sizeof(struct iphdr) + sizeof(struct udphdr) + \ + sizeof(struct pfcphdr) + sizeof(struct ethhdr)) +#define PFCP6_HEADROOM (sizeof(struct ipv6hdr) + sizeof(struct udphdr) + \ + sizeof(struct pfcphdr) + sizeof(struct ethhdr)) + +static inline struct pfcphdr *pfcp_hdr(struct sk_buff *skb) +{ + return (struct pfcphdr *)(udp_hdr(skb) + 1); +} + +static inline struct pfcphdr_node *pfcp_hdr_node(struct sk_buff *skb) +{ + return (struct pfcphdr_node *)(pfcp_hdr(skb) + 1); +} + +static inline struct pfcphdr_session *pfcp_hdr_session(struct sk_buff *skb) +{ + return (struct pfcphdr_session *)(pfcp_hdr(skb) + 1); +} + +static inline bool netif_is_pfcp(const struct net_device *dev) +{ + return dev->rtnl_link_ops && + !strcmp(dev->rtnl_link_ops->kind, "pfcp"); +} + +#endif diff --git a/include/net/phonet/pn_dev.h b/include/net/phonet/pn_dev.h index e9dc8dca5817..37a3e83531c6 100644 --- a/include/net/phonet/pn_dev.h +++ b/include/net/phonet/pn_dev.h @@ -11,13 +11,13 @@ #define PN_DEV_H #include <linux/list.h> -#include <linux/mutex.h> +#include <linux/spinlock.h> struct net; struct phonet_device_list { struct list_head list; - struct mutex lock; + spinlock_t lock; }; struct phonet_device_list *phonet_device_list(struct net *net); @@ -38,11 +38,11 @@ int phonet_address_add(struct net_device *dev, u8 addr); int phonet_address_del(struct net_device *dev, u8 addr); u8 phonet_address_get(struct net_device *dev, u8 addr); int phonet_address_lookup(struct net *net, u8 addr); -void phonet_address_notify(int event, struct net_device *dev, u8 addr); +void phonet_address_notify(struct net *net, int event, u32 ifindex, u8 addr); int phonet_route_add(struct net_device *dev, u8 daddr); int phonet_route_del(struct net_device *dev, u8 daddr); -void rtm_phonet_notify(int event, struct net_device *dev, u8 dst); +void rtm_phonet_notify(struct net *net, int event, u32 ifindex, u8 dst); struct net_device *phonet_route_get_rcu(struct net *net, u8 daddr); struct net_device *phonet_route_output(struct net *net, u8 daddr); diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index a4ee43f493bb..c64fd896b1f9 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -74,6 +74,15 @@ static inline bool tcf_block_non_null_shared(struct tcf_block *block) return block && block->index; } +#ifdef CONFIG_NET_CLS_ACT +DECLARE_STATIC_KEY_FALSE(tcf_sw_enabled_key); + +static inline bool tcf_block_bypass_sw(struct tcf_block *block) +{ + return block && !atomic_read(&block->useswcnt); +} +#endif + static inline struct Qdisc *tcf_block_q(struct tcf_block *block) { WARN_ON(tcf_block_shared(block)); @@ -310,7 +319,7 @@ tcf_exts_hw_stats_update(const struct tcf_exts *exts, * tcf_exts_has_actions - check if at least one action is present * @exts: tc filter extensions handle * - * Returns true if at least one action is present. + * Returns: true if at least one action is present. */ static inline bool tcf_exts_has_actions(struct tcf_exts *exts) { @@ -482,7 +491,7 @@ int __tcf_em_tree_match(struct sk_buff *, struct tcf_ematch_tree *, struct tcf_pkt_info *); /** - * tcf_em_tree_match - evaulate an ematch tree + * tcf_em_tree_match - evaluate an ematch tree * * @skb: socket buffer of the packet in question * @tree: ematch tree to be used for evaluation @@ -492,7 +501,7 @@ int __tcf_em_tree_match(struct sk_buff *, struct tcf_ematch_tree *, * through all ematches respecting their logic relations returning * as soon as the result is obvious. * - * Returns 1 if the ematch tree as-one matches, no ematches are configured + * Returns: 1 if the ematch tree as-one matches, no ematches are configured * or ematch is not enabled in the kernel, otherwise 0 is returned. */ static inline int tcf_em_tree_match(struct sk_buff *skb, @@ -746,10 +755,20 @@ tc_cls_common_offload_init(struct flow_cls_common_offload *cls_common, cls_common->chain_index = tp->chain->index; cls_common->protocol = tp->protocol; cls_common->prio = tp->prio >> 16; + cls_common->skip_sw = tc_skip_sw(flags); if (tc_skip_sw(flags) || flags & TCA_CLS_FLAGS_VERBOSE) cls_common->extack = extack; } +static inline void tcf_proto_update_usesw(struct tcf_proto *tp, u32 flags) +{ + if (tp->usesw) + return; + if (tc_skip_sw(flags) && tc_in_hw(flags)) + return; + tp->usesw = true; +} + #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) static inline struct tc_skb_ext *tc_skb_ext_alloc(struct sk_buff *skb) { diff --git a/include/net/proto_memory.h b/include/net/proto_memory.h new file mode 100644 index 000000000000..a6ab2f4f5e28 --- /dev/null +++ b/include/net/proto_memory.h @@ -0,0 +1,83 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _PROTO_MEMORY_H +#define _PROTO_MEMORY_H + +#include <net/sock.h> +#include <net/hotdata.h> + +/* 1 MB per cpu, in page units */ +#define SK_MEMORY_PCPU_RESERVE (1 << (20 - PAGE_SHIFT)) + +static inline bool sk_has_memory_pressure(const struct sock *sk) +{ + return sk->sk_prot->memory_pressure != NULL; +} + +static inline bool +proto_memory_pressure(const struct proto *prot) +{ + if (!prot->memory_pressure) + return false; + return !!READ_ONCE(*prot->memory_pressure); +} + +static inline bool sk_under_global_memory_pressure(const struct sock *sk) +{ + return proto_memory_pressure(sk->sk_prot); +} + +static inline bool sk_under_memory_pressure(const struct sock *sk) +{ + if (!sk->sk_prot->memory_pressure) + return false; + + if (mem_cgroup_sockets_enabled && sk->sk_memcg && + mem_cgroup_under_socket_pressure(sk->sk_memcg)) + return true; + + return !!READ_ONCE(*sk->sk_prot->memory_pressure); +} + +static inline long +proto_memory_allocated(const struct proto *prot) +{ + return max(0L, atomic_long_read(prot->memory_allocated)); +} + +static inline long +sk_memory_allocated(const struct sock *sk) +{ + return proto_memory_allocated(sk->sk_prot); +} + +static inline void proto_memory_pcpu_drain(struct proto *proto) +{ + int val = this_cpu_xchg(*proto->per_cpu_fw_alloc, 0); + + if (val) + atomic_long_add(val, proto->memory_allocated); +} + +static inline void +sk_memory_allocated_add(const struct sock *sk, int val) +{ + struct proto *proto = sk->sk_prot; + + val = this_cpu_add_return(*proto->per_cpu_fw_alloc, val); + + if (unlikely(val >= READ_ONCE(net_hotdata.sysctl_mem_pcpu_rsv))) + proto_memory_pcpu_drain(proto); +} + +static inline void +sk_memory_allocated_sub(const struct sock *sk, int val) +{ + struct proto *proto = sk->sk_prot; + + val = this_cpu_sub_return(*proto->per_cpu_fw_alloc, val); + + if (unlikely(val <= -READ_ONCE(net_hotdata.sysctl_mem_pcpu_rsv))) + proto_memory_pcpu_drain(proto); +} + +#endif /* _PROTO_MEMORY_H */ diff --git a/include/net/psample.h b/include/net/psample.h index 0509d2d6be67..5071b5fc2b59 100644 --- a/include/net/psample.h +++ b/include/net/psample.h @@ -24,7 +24,10 @@ struct psample_metadata { u8 out_tc_valid:1, out_tc_occ_valid:1, latency_valid:1, - unused:5; + rate_as_probability:1, + unused:4; + const u8 *user_cookie; + u32 user_cookie_len; }; struct psample_group *psample_group_get(struct net *net, u32 group_num); @@ -35,13 +38,15 @@ struct sk_buff; #if IS_ENABLED(CONFIG_PSAMPLE) -void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, - u32 sample_rate, const struct psample_metadata *md); +void psample_sample_packet(struct psample_group *group, + const struct sk_buff *skb, u32 sample_rate, + const struct psample_metadata *md); #else static inline void psample_sample_packet(struct psample_group *group, - struct sk_buff *skb, u32 sample_rate, + const struct sk_buff *skb, + u32 sample_rate, const struct psample_metadata *md) { } diff --git a/include/net/red.h b/include/net/red.h index 425364de0df7..159a09359fc0 100644 --- a/include/net/red.h +++ b/include/net/red.h @@ -40,7 +40,7 @@ max_P should be small (not 1), usually 0.01..0.02 is good value. max_P is chosen as a number, so that max_P/(th_max-th_min) - is a negative power of two in order arithmetics to contain + is a negative power of two in order arithmetic to contain only shifts. @@ -159,7 +159,7 @@ static inline u32 red_maxp(u8 Plog) static inline void red_set_vars(struct red_vars *v) { /* Reset average queue length, the value is strictly bound - * to the parameters below, reseting hurts a bit but leaving + * to the parameters below, resetting hurts a bit but leaving * it might result in an unreasonable qavg for a while. --TGR */ v->qavg = 0; @@ -233,10 +233,10 @@ static inline void red_set_parms(struct red_parms *p, int delta = qth_max - qth_min; u32 max_p_delta; - p->qth_min = qth_min << Wlog; - p->qth_max = qth_max << Wlog; - p->Wlog = Wlog; - p->Plog = Plog; + WRITE_ONCE(p->qth_min, qth_min << Wlog); + WRITE_ONCE(p->qth_max, qth_max << Wlog); + WRITE_ONCE(p->Wlog, Wlog); + WRITE_ONCE(p->Plog, Plog); if (delta <= 0) delta = 1; p->qth_delta = delta; @@ -244,7 +244,7 @@ static inline void red_set_parms(struct red_parms *p, max_P = red_maxp(Plog); max_P *= delta; /* max_P = (qth_max - qth_min)/2^Plog */ } - p->max_P = max_P; + WRITE_ONCE(p->max_P, max_P); max_p_delta = max_P / delta; max_p_delta = max(max_p_delta, 1U); p->max_P_reciprocal = reciprocal_value(max_p_delta); @@ -257,7 +257,7 @@ static inline void red_set_parms(struct red_parms *p, p->target_min = qth_min + 2*delta; p->target_max = qth_min + 3*delta; - p->Scell_log = Scell_log; + WRITE_ONCE(p->Scell_log, Scell_log); p->Scell_max = (255 << Scell_log); if (stab) @@ -340,7 +340,7 @@ static inline unsigned long red_calc_qavg_no_idle_time(const struct red_parms *p { /* * NOTE: v->qavg is fixed point number with point at Wlog. - * The formula below is equvalent to floating point + * The formula below is equivalent to floating point * version: * * qavg = qavg*(1-W) + backlog*W; @@ -375,7 +375,7 @@ static inline int red_mark_probability(const struct red_parms *p, OK. qR is random number in the interval (0..1/max_P)*(qth_max-qth_min) i.e. 0..(2^Plog). If we used floating point - arithmetics, it would be: (2^Plog)*rnd_num, + arithmetic, it would be: (2^Plog)*rnd_num, where rnd_num is less 1. Taking into account, that qavg have fixed diff --git a/include/net/regulatory.h b/include/net/regulatory.h index ebf9e028d1ef..6633627f6e76 100644 --- a/include/net/regulatory.h +++ b/include/net/regulatory.h @@ -71,8 +71,6 @@ enum environment_cap { * CRDA and can be used by other regulatory requests. When a * the last request is not yet processed we must yield until it * is processed before processing any new requests. - * @country_ie_checksum: checksum of the last processed and accepted - * country IE * @country_ie_env: lets us know if the AP is telling us we are outdoor, * indoor, or if it doesn't matter * @list: used to insert into the reg_requests_list linked list @@ -123,7 +121,7 @@ struct regulatory_request { * @REGULATORY_DISABLE_BEACON_HINTS: enable this if your driver needs to * ensure that passive scan flags and beaconing flags may not be lifted by * cfg80211 due to regulatory beacon hints. For more information on beacon - * hints read the documenation for regulatory_hint_found_beacon() + * hints read the documentation for regulatory_hint_found_beacon() * @REGULATORY_COUNTRY_IE_FOLLOW_POWER: for devices that have a preference * that even though they may have programmed their own custom power * setting prior to wiphy registration, they want to ensure their channel diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 004e651e6067..b07b1cd14e9f 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -18,6 +18,7 @@ #include <linux/refcount.h> #include <net/sock.h> +#include <net/rstreason.h> struct request_sock; struct sk_buff; @@ -34,7 +35,8 @@ struct request_sock_ops { void (*send_ack)(const struct sock *sk, struct sk_buff *skb, struct request_sock *req); void (*send_reset)(const struct sock *sk, - struct sk_buff *skb); + struct sk_buff *skb, + enum sk_rst_reason reason); void (*destructor)(struct request_sock *req); void (*syn_ack_timeout)(const struct request_sock *req); }; @@ -126,38 +128,6 @@ static inline struct sock *skb_steal_sock(struct sk_buff *skb, return sk; } -static inline struct request_sock * -reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener, - bool attach_listener) -{ - struct request_sock *req; - - req = kmem_cache_alloc(ops->slab, GFP_ATOMIC | __GFP_NOWARN); - if (!req) - return NULL; - req->rsk_listener = NULL; - if (attach_listener) { - if (unlikely(!refcount_inc_not_zero(&sk_listener->sk_refcnt))) { - kmem_cache_free(ops->slab, req); - return NULL; - } - req->rsk_listener = sk_listener; - } - req->rsk_ops = ops; - req_to_sk(req)->sk_prot = sk_listener->sk_prot; - sk_node_init(&req_to_sk(req)->sk_node); - sk_tx_queue_clear(req_to_sk(req)); - req->saved_syn = NULL; - req->syncookie = 0; - req->timeout = 0; - req->num_timeout = 0; - req->num_retrans = 0; - req->sk = NULL; - refcount_set(&req->rsk_refcnt, 0); - - return req; -} - static inline void __reqsk_free(struct request_sock *req) { req->rsk_ops->destructor(req); @@ -169,14 +139,14 @@ static inline void __reqsk_free(struct request_sock *req) static inline void reqsk_free(struct request_sock *req) { - WARN_ON_ONCE(refcount_read(&req->rsk_refcnt) != 0); + DEBUG_NET_WARN_ON_ONCE(refcount_read(&req->rsk_refcnt) != 0); __reqsk_free(req); } static inline void reqsk_put(struct request_sock *req) { if (refcount_dec_and_test(&req->rsk_refcnt)) - reqsk_free(req); + __reqsk_free(req); } /* @@ -282,4 +252,16 @@ static inline int reqsk_queue_len_young(const struct request_sock_queue *queue) return atomic_read(&queue->young); } +/* RFC 7323 2.3 Using the Window Scale Option + * The window field (SEG.WND) of every outgoing segment, with the + * exception of <SYN> segments, MUST be right-shifted by + * Rcv.Wind.Shift bits. + * + * This means the SEG.WND carried in SYNACK can not exceed 65535. + * We use this property to harden TCP stack while in NEW_SYN_RECV state. + */ +static inline u32 tcp_synack_window(const struct request_sock *req) +{ + return min(req->rsk_rcv_wnd, 65535U); +} #endif /* _REQUEST_SOCK_H */ diff --git a/include/net/route.h b/include/net/route.h index d4a0147942f1..8e39aa822cf9 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -27,6 +27,8 @@ #include <net/ip_fib.h> #include <net/arp.h> #include <net/ndisc.h> +#include <net/inet_dscp.h> +#include <net/sock.h> #include <linux/in_route.h> #include <linux/rtnetlink.h> #include <linux/rcupdate.h> @@ -35,8 +37,6 @@ #include <linux/cache.h> #include <linux/security.h> -#define RTO_ONLINK 0x01 - static inline __u8 ip_sock_rt_scope(const struct sock *sk) { if (sock_flag(sk, SOCK_LOCALROUTE)) @@ -47,7 +47,7 @@ static inline __u8 ip_sock_rt_scope(const struct sock *sk) static inline __u8 ip_sock_rt_tos(const struct sock *sk) { - return RT_TOS(READ_ONCE(inet_sk(sk)->tos)); + return READ_ONCE(inet_sk(sk)->tos) & INET_DSCP_MASK; } struct ip_tunnel_info; @@ -77,6 +77,17 @@ struct rtable { rt_pmtu:31; }; +#define dst_rtable(_ptr) container_of_const(_ptr, struct rtable, dst) + +/** + * skb_rtable - Returns the skb &rtable + * @skb: buffer + */ +static inline struct rtable *skb_rtable(const struct sk_buff *skb) +{ + return dst_rtable(skb_dst(skb)); +} + static inline bool rt_is_input_route(const struct rtable *rt) { return rt->rt_is_input != 0; @@ -119,6 +130,33 @@ struct in_device; int ip_rt_init(void); void rt_cache_flush(struct net *net); void rt_flush_dev(struct net_device *dev); + +static inline void inet_sk_init_flowi4(const struct inet_sock *inet, + struct flowi4 *fl4) +{ + const struct ip_options_rcu *ip4_opt; + const struct sock *sk; + __be32 daddr; + + rcu_read_lock(); + ip4_opt = rcu_dereference(inet->inet_opt); + + /* Source routing option overrides the socket destination address */ + if (ip4_opt && ip4_opt->opt.srr) + daddr = ip4_opt->opt.faddr; + else + daddr = inet->inet_daddr; + rcu_read_unlock(); + + sk = &inet->sk; + flowi4_init_output(fl4, sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark), + ip_sock_rt_tos(sk), ip_sock_rt_scope(sk), + sk->sk_protocol, inet_sk_flowi_flags(sk), daddr, + inet->inet_saddr, inet->inet_dport, + inet->inet_sport, sk->sk_uid); + security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4)); +} + struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *flp, const struct sk_buff *skb); struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *flp, @@ -141,15 +179,22 @@ static inline struct rtable *ip_route_output_key(struct net *net, struct flowi4 return ip_route_output_flow(net, flp, NULL); } +/* Simplistic IPv4 route lookup function. + * This is only suitable for some particular use cases: since the flowi4 + * structure is only partially set, it may bypass some fib-rules. + */ static inline struct rtable *ip_route_output(struct net *net, __be32 daddr, - __be32 saddr, u8 tos, int oif) + __be32 saddr, dscp_t dscp, + int oif, __u8 scope) { struct flowi4 fl4 = { .flowi4_oif = oif, - .flowi4_tos = tos, + .flowi4_tos = inet_dscp_to_dsfield(dscp), + .flowi4_scope = scope, .daddr = daddr, .saddr = saddr, }; + return ip_route_output_key(net, &fl4); } @@ -168,43 +213,34 @@ static inline struct rtable *ip_route_output_ports(struct net *net, struct flowi return ip_route_output_flow(net, fl4, sk); } -static inline struct rtable *ip_route_output_gre(struct net *net, struct flowi4 *fl4, - __be32 daddr, __be32 saddr, - __be32 gre_key, __u8 tos, int oif) +enum skb_drop_reason +ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, + dscp_t dscp, struct net_device *dev, + struct in_device *in_dev, u32 *itag); +enum skb_drop_reason +ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, + dscp_t dscp, struct net_device *dev); +enum skb_drop_reason +ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr, + dscp_t dscp, struct net_device *dev, + const struct sk_buff *hint); + +static inline enum skb_drop_reason +ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src, dscp_t dscp, + struct net_device *devin) { - memset(fl4, 0, sizeof(*fl4)); - fl4->flowi4_oif = oif; - fl4->daddr = daddr; - fl4->saddr = saddr; - fl4->flowi4_tos = tos; - fl4->flowi4_proto = IPPROTO_GRE; - fl4->fl4_gre_key = gre_key; - return ip_route_output_key(net, fl4); -} -int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, - u8 tos, struct net_device *dev, - struct in_device *in_dev, u32 *itag); -int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src, - u8 tos, struct net_device *devin); -int ip_route_use_hint(struct sk_buff *skb, __be32 dst, __be32 src, - u8 tos, struct net_device *devin, - const struct sk_buff *hint); - -static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src, - u8 tos, struct net_device *devin) -{ - int err; + enum skb_drop_reason reason; rcu_read_lock(); - err = ip_route_input_noref(skb, dst, src, tos, devin); - if (!err) { + reason = ip_route_input_noref(skb, dst, src, dscp, devin); + if (!reason) { skb_dst_force(skb); if (!skb_dst(skb)) - err = -EINVAL; + reason = SKB_DROP_REASON_NOT_SPECIFIED; } rcu_read_unlock(); - return err; + return reason; } void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, int oif, @@ -249,8 +285,6 @@ static inline void ip_rt_put(struct rtable *rt) dst_release(&rt->dst); } -#define IPTOS_RT_MASK (IPTOS_TOS_MASK & ~3) - extern const __u8 ip_tos2prio[16]; static inline char rt_tos2priority(u8 tos) @@ -292,6 +326,9 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, if (inet_test_bit(TRANSPARENT, sk)) flow_flags |= FLOWI_FLAG_ANYSRC; + if (IS_ENABLED(CONFIG_IP_ROUTE_MULTIPATH) && !sport) + flow_flags |= FLOWI_FLAG_ANY_SPORT; + flowi4_init_output(fl4, oif, READ_ONCE(sk->sk_mark), ip_sock_rt_tos(sk), ip_sock_rt_scope(sk), protocol, flow_flags, dst, src, dport, sport, sk->sk_uid); @@ -348,10 +385,15 @@ static inline int inet_iif(const struct sk_buff *skb) static inline int ip4_dst_hoplimit(const struct dst_entry *dst) { int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT); - struct net *net = dev_net(dst->dev); - if (hoplimit == 0) + if (hoplimit == 0) { + const struct net *net; + + rcu_read_lock(); + net = dev_net_rcu(dst->dev); hoplimit = READ_ONCE(net->ipv4.sysctl_ip_default_ttl); + rcu_read_unlock(); + } return hoplimit; } diff --git a/include/net/rps.h b/include/net/rps.h index 7660243e905b..d8ab3a08bcc4 100644 --- a/include/net/rps.h +++ b/include/net/rps.h @@ -39,7 +39,7 @@ struct rps_dev_flow { * The rps_dev_flow_table structure contains a table of flow mappings. */ struct rps_dev_flow_table { - unsigned int mask; + u8 log; struct rcu_head rcu; struct rps_dev_flow flows[]; }; @@ -57,9 +57,10 @@ struct rps_dev_flow_table { * meaning we use 32-6=26 bits for the hash. */ struct rps_sock_flow_table { - u32 mask; + struct rcu_head rcu; + u32 mask; - u32 ents[] ____cacheline_aligned_in_smp; + u32 ents[] ____cacheline_aligned_in_smp; }; #define RPS_SOCK_FLOW_TABLE_SIZE(_num) (offsetof(struct rps_sock_flow_table, ents[_num])) @@ -122,4 +123,56 @@ static inline void sock_rps_record_flow(const struct sock *sk) #endif } +static inline void sock_rps_delete_flow(const struct sock *sk) +{ +#ifdef CONFIG_RPS + struct rps_sock_flow_table *table; + u32 hash, index; + + if (!static_branch_unlikely(&rfs_needed)) + return; + + hash = READ_ONCE(sk->sk_rxhash); + if (!hash) + return; + + rcu_read_lock(); + table = rcu_dereference(net_hotdata.rps_sock_flow_table); + if (table) { + index = hash & table->mask; + if (READ_ONCE(table->ents[index]) != RPS_NO_CPU) + WRITE_ONCE(table->ents[index], RPS_NO_CPU); + } + rcu_read_unlock(); +#endif +} + +static inline u32 rps_input_queue_tail_incr(struct softnet_data *sd) +{ +#ifdef CONFIG_RPS + return ++sd->input_queue_tail; +#else + return 0; +#endif +} + +static inline void rps_input_queue_tail_save(u32 *dest, u32 tail) +{ +#ifdef CONFIG_RPS + WRITE_ONCE(*dest, tail); +#endif +} + +static inline void rps_input_queue_head_add(struct softnet_data *sd, int val) +{ +#ifdef CONFIG_RPS + WRITE_ONCE(sd->input_queue_head, sd->input_queue_head + val); +#endif +} + +static inline void rps_input_queue_head_incr(struct softnet_data *sd) +{ + rps_input_queue_head_add(sd, 1); +} + #endif /* _NET_RPS_H */ diff --git a/include/net/rstreason.h b/include/net/rstreason.h new file mode 100644 index 000000000000..979ac87b5d99 --- /dev/null +++ b/include/net/rstreason.h @@ -0,0 +1,221 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef _LINUX_RSTREASON_H +#define _LINUX_RSTREASON_H +#include <net/dropreason-core.h> +#include <uapi/linux/mptcp.h> + +#define DEFINE_RST_REASON(FN, FNe) \ + FN(NOT_SPECIFIED) \ + FN(NO_SOCKET) \ + FN(TCP_INVALID_ACK_SEQUENCE) \ + FN(TCP_RFC7323_PAWS) \ + FN(TCP_TOO_OLD_ACK) \ + FN(TCP_ACK_UNSENT_DATA) \ + FN(TCP_FLAGS) \ + FN(TCP_OLD_ACK) \ + FN(TCP_ABORT_ON_DATA) \ + FN(TCP_TIMEWAIT_SOCKET) \ + FN(INVALID_SYN) \ + FN(TCP_ABORT_ON_CLOSE) \ + FN(TCP_ABORT_ON_LINGER) \ + FN(TCP_ABORT_ON_MEMORY) \ + FN(TCP_STATE) \ + FN(TCP_KEEPALIVE_TIMEOUT) \ + FN(TCP_DISCONNECT_WITH_DATA) \ + FN(MPTCP_RST_EUNSPEC) \ + FN(MPTCP_RST_EMPTCP) \ + FN(MPTCP_RST_ERESOURCE) \ + FN(MPTCP_RST_EPROHIBIT) \ + FN(MPTCP_RST_EWQ2BIG) \ + FN(MPTCP_RST_EBADPERF) \ + FN(MPTCP_RST_EMIDDLEBOX) \ + FN(ERROR) \ + FNe(MAX) + +/** + * enum sk_rst_reason - the reasons of socket reset + * + * The reasons of sk reset, which are used in TCP/MPTCP protocols. + * + * There are three parts in order: + * 1) skb drop reasons: relying on drop reasons for such as passive reset + * 2) independent reset reasons: such as active reset reasons + * 3) reset reasons in MPTCP: only for MPTCP use + */ +enum sk_rst_reason { + /* Refer to include/net/dropreason-core.h + * Rely on skb drop reasons because it indicates exactly why RST + * could happen. + */ + /** @SK_RST_REASON_NOT_SPECIFIED: reset reason is not specified */ + SK_RST_REASON_NOT_SPECIFIED, + /** @SK_RST_REASON_NO_SOCKET: no valid socket that can be used */ + SK_RST_REASON_NO_SOCKET, + /** + * @SK_RST_REASON_TCP_INVALID_ACK_SEQUENCE: Not acceptable ACK SEQ + * field because ack sequence is not in the window between snd_una + * and snd_nxt + */ + SK_RST_REASON_TCP_INVALID_ACK_SEQUENCE, + /** + * @SK_RST_REASON_TCP_RFC7323_PAWS: PAWS check, corresponding to + * LINUX_MIB_PAWSESTABREJECTED, LINUX_MIB_PAWSACTIVEREJECTED + */ + SK_RST_REASON_TCP_RFC7323_PAWS, + /** @SK_RST_REASON_TCP_TOO_OLD_ACK: TCP ACK is too old */ + SK_RST_REASON_TCP_TOO_OLD_ACK, + /** + * @SK_RST_REASON_TCP_ACK_UNSENT_DATA: TCP ACK for data we haven't + * sent yet + */ + SK_RST_REASON_TCP_ACK_UNSENT_DATA, + /** @SK_RST_REASON_TCP_FLAGS: TCP flags invalid */ + SK_RST_REASON_TCP_FLAGS, + /** @SK_RST_REASON_TCP_OLD_ACK: TCP ACK is old, but in window */ + SK_RST_REASON_TCP_OLD_ACK, + /** + * @SK_RST_REASON_TCP_ABORT_ON_DATA: abort on data + * corresponding to LINUX_MIB_TCPABORTONDATA + */ + SK_RST_REASON_TCP_ABORT_ON_DATA, + + /* Here start with the independent reasons */ + /** @SK_RST_REASON_TCP_TIMEWAIT_SOCKET: happen on the timewait socket */ + SK_RST_REASON_TCP_TIMEWAIT_SOCKET, + /** + * @SK_RST_REASON_INVALID_SYN: receive bad syn packet + * RFC 793 says if the state is not CLOSED/LISTEN/SYN-SENT then + * "fourth, check the SYN bit,...If the SYN is in the window it is + * an error, send a reset" + */ + SK_RST_REASON_INVALID_SYN, + /** + * @SK_RST_REASON_TCP_ABORT_ON_CLOSE: abort on close + * corresponding to LINUX_MIB_TCPABORTONCLOSE + */ + SK_RST_REASON_TCP_ABORT_ON_CLOSE, + /** + * @SK_RST_REASON_TCP_ABORT_ON_LINGER: abort on linger + * corresponding to LINUX_MIB_TCPABORTONLINGER + */ + SK_RST_REASON_TCP_ABORT_ON_LINGER, + /** + * @SK_RST_REASON_TCP_ABORT_ON_MEMORY: abort on memory + * corresponding to LINUX_MIB_TCPABORTONMEMORY + */ + SK_RST_REASON_TCP_ABORT_ON_MEMORY, + /** + * @SK_RST_REASON_TCP_STATE: abort on tcp state + * Please see RFC 9293 for all possible reset conditions + */ + SK_RST_REASON_TCP_STATE, + /** + * @SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT: time to timeout + * When we have already run out of all the chances, which means + * keepalive timeout, we have to reset the connection + */ + SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT, + /** + * @SK_RST_REASON_TCP_DISCONNECT_WITH_DATA: disconnect when write + * queue is not empty + * It means user has written data into the write queue when doing + * disconnecting, so we have to send an RST. + */ + SK_RST_REASON_TCP_DISCONNECT_WITH_DATA, + + /* Copy from include/uapi/linux/mptcp.h. + * These reset fields will not be changed since they adhere to + * RFC 8684. So do not touch them. I'm going to list each definition + * of them respectively. + */ + /** + * @SK_RST_REASON_MPTCP_RST_EUNSPEC: Unspecified error. + * This is the default error; it implies that the subflow is no + * longer available. The presence of this option shows that the + * RST was generated by an MPTCP-aware device. + */ + SK_RST_REASON_MPTCP_RST_EUNSPEC, + /** + * @SK_RST_REASON_MPTCP_RST_EMPTCP: MPTCP-specific error. + * An error has been detected in the processing of MPTCP options. + * This is the usual reason code to return in the cases where a RST + * is being sent to close a subflow because of an invalid response. + */ + SK_RST_REASON_MPTCP_RST_EMPTCP, + /** + * @SK_RST_REASON_MPTCP_RST_ERESOURCE: Lack of resources. + * This code indicates that the sending host does not have enough + * resources to support the terminated subflow. + */ + SK_RST_REASON_MPTCP_RST_ERESOURCE, + /** + * @SK_RST_REASON_MPTCP_RST_EPROHIBIT: Administratively prohibited. + * This code indicates that the requested subflow is prohibited by + * the policies of the sending host. + */ + SK_RST_REASON_MPTCP_RST_EPROHIBIT, + /** + * @SK_RST_REASON_MPTCP_RST_EWQ2BIG: Too much outstanding data. + * This code indicates that there is an excessive amount of data + * that needs to be transmitted over the terminated subflow while + * having already been acknowledged over one or more other subflows. + * This may occur if a path has been unavailable for a short period + * and it is more efficient to reset and start again than it is to + * retransmit the queued data. + */ + SK_RST_REASON_MPTCP_RST_EWQ2BIG, + /** + * @SK_RST_REASON_MPTCP_RST_EBADPERF: Unacceptable performance. + * This code indicates that the performance of this subflow was + * too low compared to the other subflows of this Multipath TCP + * connection. + */ + SK_RST_REASON_MPTCP_RST_EBADPERF, + /** + * @SK_RST_REASON_MPTCP_RST_EMIDDLEBOX: Middlebox interference. + * Middlebox interference has been detected over this subflow, + * making MPTCP signaling invalid. For example, this may be sent + * if the checksum does not validate. + */ + SK_RST_REASON_MPTCP_RST_EMIDDLEBOX, + + /** @SK_RST_REASON_ERROR: unexpected error happens */ + SK_RST_REASON_ERROR, + + /** + * @SK_RST_REASON_MAX: Maximum of socket reset reasons. + * It shouldn't be used as a real 'reason'. + */ + SK_RST_REASON_MAX, +}; + +/* Convert skb drop reasons to enum sk_rst_reason type */ +static inline enum sk_rst_reason +sk_rst_convert_drop_reason(enum skb_drop_reason reason) +{ + switch (reason) { + case SKB_DROP_REASON_NOT_SPECIFIED: + return SK_RST_REASON_NOT_SPECIFIED; + case SKB_DROP_REASON_NO_SOCKET: + return SK_RST_REASON_NO_SOCKET; + case SKB_DROP_REASON_TCP_INVALID_ACK_SEQUENCE: + return SK_RST_REASON_TCP_INVALID_ACK_SEQUENCE; + case SKB_DROP_REASON_TCP_RFC7323_PAWS: + return SK_RST_REASON_TCP_RFC7323_PAWS; + case SKB_DROP_REASON_TCP_TOO_OLD_ACK: + return SK_RST_REASON_TCP_TOO_OLD_ACK; + case SKB_DROP_REASON_TCP_ACK_UNSENT_DATA: + return SK_RST_REASON_TCP_ACK_UNSENT_DATA; + case SKB_DROP_REASON_TCP_FLAGS: + return SK_RST_REASON_TCP_FLAGS; + case SKB_DROP_REASON_TCP_OLD_ACK: + return SK_RST_REASON_TCP_OLD_ACK; + case SKB_DROP_REASON_TCP_ABORT_ON_DATA: + return SK_RST_REASON_TCP_ABORT_ON_DATA; + default: + /* If we don't have our own corresponding reason */ + return SK_RST_REASON_NOT_SPECIFIED; + } +} +#endif diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 3bfb80bad173..ec65a8cebb99 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -3,6 +3,7 @@ #define __NET_RTNETLINK_H #include <linux/rtnetlink.h> +#include <linux/srcu.h> #include <net/netlink.h> typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *, @@ -11,8 +12,11 @@ typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *); enum rtnl_link_flags { RTNL_FLAG_DOIT_UNLOCKED = BIT(0), +#define RTNL_FLAG_DOIT_PERNET RTNL_FLAG_DOIT_UNLOCKED +#define RTNL_FLAG_DOIT_PERNET_WIP RTNL_FLAG_DOIT_UNLOCKED RTNL_FLAG_BULK_DEL_SUPPORTED = BIT(1), RTNL_FLAG_DUMP_UNLOCKED = BIT(2), + RTNL_FLAG_DUMP_SPLIT_NLM_DONE = BIT(3), /* legacy behavior */ }; enum rtnl_kinds { @@ -28,13 +32,35 @@ static inline enum rtnl_kinds rtnl_msgtype_kind(int msgtype) return msgtype & RTNL_KIND_MASK; } -void rtnl_register(int protocol, int msgtype, - rtnl_doit_func, rtnl_dumpit_func, unsigned int flags); -int rtnl_register_module(struct module *owner, int protocol, int msgtype, - rtnl_doit_func, rtnl_dumpit_func, unsigned int flags); -int rtnl_unregister(int protocol, int msgtype); +/** + * struct rtnl_msg_handler - rtnetlink message type and handlers + * + * @owner: NULL for built-in, THIS_MODULE for module + * @protocol: Protocol family or PF_UNSPEC + * @msgtype: rtnetlink message type + * @doit: Function pointer called for each request message + * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message + * @flags: rtnl_link_flags to modify behaviour of doit/dumpit functions + */ +struct rtnl_msg_handler { + struct module *owner; + int protocol; + int msgtype; + rtnl_doit_func doit; + rtnl_dumpit_func dumpit; + int flags; +}; + void rtnl_unregister_all(int protocol); +int __rtnl_register_many(const struct rtnl_msg_handler *handlers, int n); +void __rtnl_unregister_many(const struct rtnl_msg_handler *handlers, int n); + +#define rtnl_register_many(handlers) \ + __rtnl_register_many(handlers, ARRAY_SIZE(handlers)) +#define rtnl_unregister_many(handlers) \ + __rtnl_unregister_many(handlers, ARRAY_SIZE(handlers)) + static inline int rtnl_msg_family(const struct nlmsghdr *nlh) { if (nlmsg_len(nlh) >= sizeof(struct rtgenmsg)) @@ -44,11 +70,47 @@ static inline int rtnl_msg_family(const struct nlmsghdr *nlh) } /** + * struct rtnl_newlink_params - parameters of rtnl_link_ops::newlink() + * + * @src_net: Source netns of rtnetlink socket + * @link_net: Link netns by IFLA_LINK_NETNSID, NULL if not specified + * @peer_net: Peer netns + * @tb: IFLA_* attributes + * @data: IFLA_INFO_DATA attributes + */ +struct rtnl_newlink_params { + struct net *src_net; + struct net *link_net; + struct net *peer_net; + struct nlattr **tb; + struct nlattr **data; +}; + +/* Get effective link netns from newlink params. Generally, this is link_net + * and falls back to src_net. But for compatibility, a driver may * choose to + * use dev_net(dev) instead. + */ +static inline struct net *rtnl_newlink_link_net(struct rtnl_newlink_params *p) +{ + return p->link_net ? : p->src_net; +} + +/* Get peer netns from newlink params. Fallback to link netns if peer netns is + * not specified explicitly. + */ +static inline struct net *rtnl_newlink_peer_net(struct rtnl_newlink_params *p) +{ + return p->peer_net ? : rtnl_newlink_link_net(p); +} + +/** * struct rtnl_link_ops - rtnetlink link operations * - * @list: Used internally + * @list: Used internally, protected by link_ops_mutex and SRCU + * @srcu: Used internally * @kind: Identifier * @netns_refund: Physical device, move to init_net on netns exit + * @peer_type: Peer device specific netlink attribute number (e.g. VETH_INFO_PEER) * @maxtype: Highest device specific netlink attribute number * @policy: Netlink policy for device specific attribute validation * @validate: Optional validation function for netlink/changelink parameters @@ -77,6 +139,7 @@ static inline int rtnl_msg_family(const struct nlmsghdr *nlh) */ struct rtnl_link_ops { struct list_head list; + struct srcu_struct srcu; const char *kind; @@ -89,16 +152,15 @@ struct rtnl_link_ops { void (*setup)(struct net_device *dev); bool netns_refund; + const u16 peer_type; unsigned int maxtype; const struct nla_policy *policy; int (*validate)(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack); - int (*newlink)(struct net *src_net, - struct net_device *dev, - struct nlattr *tb[], - struct nlattr *data[], + int (*newlink)(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack); int (*changelink)(struct net_device *dev, struct nlattr *tb[], @@ -137,16 +199,14 @@ struct rtnl_link_ops { int *prividx, int attr); }; -int __rtnl_link_register(struct rtnl_link_ops *ops); -void __rtnl_link_unregister(struct rtnl_link_ops *ops); - int rtnl_link_register(struct rtnl_link_ops *ops); void rtnl_link_unregister(struct rtnl_link_ops *ops); /** * struct rtnl_af_ops - rtnetlink address family operations * - * @list: Used internally + * @list: Used internally, protected by RTNL and SRCU + * @srcu: Used internally * @family: Address family * @fill_link_af: Function to fill IFLA_AF_SPEC with address family * specific netlink attributes. @@ -159,6 +219,8 @@ void rtnl_link_unregister(struct rtnl_link_ops *ops); */ struct rtnl_af_ops { struct list_head list; + struct srcu_struct srcu; + int family; int (*fill_link_af)(struct sk_buff *skb, @@ -178,7 +240,7 @@ struct rtnl_af_ops { size_t (*get_stats_af_size)(const struct net_device *dev); }; -void rtnl_af_register(struct rtnl_af_ops *ops); +int 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[]); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 41ca14e81d55..629368ab2787 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -128,6 +128,7 @@ struct Qdisc { struct rcu_head rcu; netdevice_tracker dev_tracker; + struct lock_class_key root_lock_key; /* private data */ long privdata[] ____cacheline_aligned; }; @@ -423,6 +424,8 @@ struct tcf_proto { */ spinlock_t lock; bool deleting; + bool counted; + bool usesw; refcount_t refcnt; struct rcu_head rcu; struct hlist_node destroy_ht_node; @@ -472,6 +475,7 @@ struct tcf_block { struct flow_block flow_block; struct list_head owner_list; bool keep_dst; + atomic_t useswcnt; atomic_t offloadcnt; /* Number of oddloaded filters */ unsigned int nooffloaddevcnt; /* Number of devs unable to do offload */ unsigned int lockeddevcnt; /* Number of devs that require rtnl lock. */ @@ -799,6 +803,14 @@ static inline bool qdisc_tx_changing(const struct net_device *dev) return false; } +/* "noqueue" qdisc identified by not having any enqueue, see noqueue_init() */ +static inline bool qdisc_txq_has_no_queue(const struct netdev_queue *txq) +{ + struct Qdisc *qdisc = rcu_access_pointer(txq->qdisc); + + return qdisc->enqueue == NULL; +} + /* Is the device using the noop qdisc on all queues? */ static inline bool qdisc_tx_is_noop(const struct net_device *dev) { @@ -843,12 +855,11 @@ static inline void qdisc_calculate_pkt_len(struct sk_buff *skb, static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { - qdisc_calculate_pkt_len(skb, sch); return sch->enqueue(skb, sch, to_free); } static inline void _bstats_update(struct gnet_stats_basic_sync *bstats, - __u64 bytes, __u32 packets) + __u64 bytes, __u64 packets) { u64_stats_update_begin(&bstats->syncp); u64_stats_add(&bstats->bytes, bytes); @@ -1028,6 +1039,21 @@ static inline struct sk_buff *__qdisc_dequeue_head(struct qdisc_skb_head *qh) return skb; } +static inline struct sk_buff *qdisc_dequeue_internal(struct Qdisc *sch, bool direct) +{ + struct sk_buff *skb; + + skb = __skb_dequeue(&sch->gso_skb); + if (skb) { + sch->q.qlen--; + return skb; + } + if (direct) + return __qdisc_dequeue_head(&sch->q); + else + return sch->dequeue(sch); +} + static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch) { struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); @@ -1241,6 +1267,14 @@ static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch, return NET_XMIT_DROP; } +static inline int qdisc_drop_reason(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free, + enum skb_drop_reason reason) +{ + tcf_set_drop_reason(skb, reason); + return qdisc_drop(skb, sch, to_free); +} + static inline int qdisc_drop_all(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { diff --git a/include/net/scm.h b/include/net/scm.h index 92276a2c5543..84c4707e78a5 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -23,10 +23,20 @@ struct scm_creds { kgid_t gid; }; +#ifdef CONFIG_UNIX +struct unix_edge; +#endif + struct scm_fp_list { short count; short count_unix; short max; +#ifdef CONFIG_UNIX + bool inflight; + bool dead; + struct list_head vertices; + struct unix_edge *edges; +#endif struct user_struct *user; struct file *fp[SCM_MAX_FD]; }; @@ -92,123 +102,10 @@ static __inline__ int scm_send(struct socket *sock, struct msghdr *msg, return __scm_send(sock, msg, scm); } -#ifdef CONFIG_SECURITY_NETWORK -static inline void scm_passec(struct socket *sock, struct msghdr *msg, struct scm_cookie *scm) -{ - char *secdata; - u32 seclen; - int err; - - if (test_bit(SOCK_PASSSEC, &sock->flags)) { - err = security_secid_to_secctx(scm->secid, &secdata, &seclen); - - if (!err) { - put_cmsg(msg, SOL_SOCKET, SCM_SECURITY, seclen, secdata); - security_release_secctx(secdata, seclen); - } - } -} - -static inline bool scm_has_secdata(struct socket *sock) -{ - return test_bit(SOCK_PASSSEC, &sock->flags); -} -#else -static inline void scm_passec(struct socket *sock, struct msghdr *msg, struct scm_cookie *scm) -{ } - -static inline bool scm_has_secdata(struct socket *sock) -{ - return false; -} -#endif /* CONFIG_SECURITY_NETWORK */ - -static __inline__ void scm_pidfd_recv(struct msghdr *msg, struct scm_cookie *scm) -{ - struct file *pidfd_file = NULL; - int len, pidfd; - - /* put_cmsg() doesn't return an error if CMSG is truncated, - * that's why we need to opencode these checks here. - */ - if (msg->msg_flags & MSG_CMSG_COMPAT) - len = sizeof(struct compat_cmsghdr) + sizeof(int); - else - len = sizeof(struct cmsghdr) + sizeof(int); - - if (msg->msg_controllen < len) { - msg->msg_flags |= MSG_CTRUNC; - return; - } - - if (!scm->pid) - return; - - pidfd = pidfd_prepare(scm->pid, 0, &pidfd_file); - - if (put_cmsg(msg, SOL_SOCKET, SCM_PIDFD, sizeof(int), &pidfd)) { - if (pidfd_file) { - put_unused_fd(pidfd); - fput(pidfd_file); - } - - return; - } - - if (pidfd_file) - fd_install(pidfd, pidfd_file); -} - -static inline bool __scm_recv_common(struct socket *sock, struct msghdr *msg, - struct scm_cookie *scm, int flags) -{ - if (!msg->msg_control) { - if (test_bit(SOCK_PASSCRED, &sock->flags) || - test_bit(SOCK_PASSPIDFD, &sock->flags) || - scm->fp || scm_has_secdata(sock)) - msg->msg_flags |= MSG_CTRUNC; - scm_destroy(scm); - return false; - } - - if (test_bit(SOCK_PASSCRED, &sock->flags)) { - struct user_namespace *current_ns = current_user_ns(); - struct ucred ucreds = { - .pid = scm->creds.pid, - .uid = from_kuid_munged(current_ns, scm->creds.uid), - .gid = from_kgid_munged(current_ns, scm->creds.gid), - }; - put_cmsg(msg, SOL_SOCKET, SCM_CREDENTIALS, sizeof(ucreds), &ucreds); - } - - scm_passec(sock, msg, scm); - - if (scm->fp) - scm_detach_fds(msg, scm); - - return true; -} - -static inline void scm_recv(struct socket *sock, struct msghdr *msg, - struct scm_cookie *scm, int flags) -{ - if (!__scm_recv_common(sock, msg, scm, flags)) - return; - - scm_destroy_cred(scm); -} - -static inline void scm_recv_unix(struct socket *sock, struct msghdr *msg, - struct scm_cookie *scm, int flags) -{ - if (!__scm_recv_common(sock, msg, scm, flags)) - return; - - if (test_bit(SOCK_PASSPIDFD, &sock->flags)) - scm_pidfd_recv(msg, scm); - - scm_destroy_cred(scm); -} +void scm_recv(struct socket *sock, struct msghdr *msg, + struct scm_cookie *scm, int flags); +void scm_recv_unix(struct socket *sock, struct msghdr *msg, + struct scm_cookie *scm, int flags); static inline int scm_recv_one_fd(struct file *f, int __user *ufd, unsigned int flags) diff --git a/include/net/sctp/checksum.h b/include/net/sctp/checksum.h index f514a0aa849e..654d37ec0402 100644 --- a/include/net/sctp/checksum.h +++ b/include/net/sctp/checksum.h @@ -15,8 +15,6 @@ * Dinakaran Joseph * Jon Grimm <jgrimm@us.ibm.com> * Sridhar Samudrala <sri@us.ibm.com> - * - * Rewritten to use libcrc32c by: * Vlad Yasevich <vladislav.yasevich@hp.com> */ @@ -25,42 +23,18 @@ #include <linux/types.h> #include <linux/sctp.h> -#include <linux/crc32c.h> -#include <linux/crc32.h> - -static inline __wsum sctp_csum_update(const void *buff, int len, __wsum sum) -{ - /* This uses the crypto implementation of crc32c, which is either - * implemented w/ hardware support or resolves to __crc32c_le(). - */ - return (__force __wsum)crc32c((__force __u32)sum, buff, len); -} - -static inline __wsum sctp_csum_combine(__wsum csum, __wsum csum2, - int offset, int len) -{ - return (__force __wsum)__crc32c_le_combine((__force __u32)csum, - (__force __u32)csum2, len); -} - -static const struct skb_checksum_ops sctp_csum_ops = { - .update = sctp_csum_update, - .combine = sctp_csum_combine, -}; static inline __le32 sctp_compute_cksum(const struct sk_buff *skb, unsigned int offset) { struct sctphdr *sh = (struct sctphdr *)(skb->data + offset); __le32 old = sh->checksum; - __wsum new; + u32 new; sh->checksum = 0; - new = ~__skb_checksum(skb, offset, skb->len - offset, ~(__wsum)0, - &sctp_csum_ops); + new = ~skb_crc32c(skb, offset, skb->len - offset, ~0); sh->checksum = old; - - return cpu_to_le32((__force __u32)new); + return cpu_to_le32(new); } #endif /* __sctp_checksum_h__ */ diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index a2310fa995f6..e96d1bd087f6 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -28,7 +28,7 @@ #define __net_sctp_h__ /* Header Strategy. - * Start getting some control over the header file depencies: + * Start getting some control over the header file dependencies: * includes * constants * structs @@ -364,8 +364,6 @@ sctp_assoc_to_state(const struct sctp_association *asoc) /* Look up the association by its id. */ struct sctp_association *sctp_id2assoc(struct sock *sk, sctp_assoc_t id); -int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp); - /* A macro to walk a list of skbs. */ #define sctp_skb_for_each(pos, head, tmp) \ skb_queue_walk_safe(head, pos, tmp) @@ -636,7 +634,7 @@ static inline void sctp_transport_pl_reset(struct sctp_transport *t) } } else { if (t->pl.state != SCTP_PL_DISABLED) { - if (del_timer(&t->probe_timer)) + if (timer_delete(&t->probe_timer)) sctp_transport_put(t); t->pl.state = SCTP_PL_DISABLED; } diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index 64c42bd56bb2..3bfd261a53cc 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -161,7 +161,6 @@ const struct sctp_sm_table_entry *sctp_sm_lookup_event( enum sctp_event_type event_type, enum sctp_state state, union sctp_subtype event_subtype); -int sctp_chunk_iif(const struct sctp_chunk *); struct sctp_association *sctp_make_temp_asoc(const struct sctp_endpoint *, struct sctp_chunk *, gfp_t gfp); diff --git a/include/net/sctp/stream_sched.h b/include/net/sctp/stream_sched.h index 572d73fdcd5e..8034bf5febbe 100644 --- a/include/net/sctp/stream_sched.h +++ b/include/net/sctp/stream_sched.h @@ -35,10 +35,10 @@ struct sctp_sched_ops { struct sctp_chunk *(*dequeue)(struct sctp_outq *q); /* Called only if the chunk fit the packet */ void (*dequeue_done)(struct sctp_outq *q, struct sctp_chunk *chunk); - /* Sched all chunks already enqueued */ - void (*sched_all)(struct sctp_stream *steam); - /* Unched all chunks already enqueued */ - void (*unsched_all)(struct sctp_stream *steam); + /* Schedule all chunks already enqueued */ + void (*sched_all)(struct sctp_stream *stream); + /* Unschedule all chunks already enqueued */ + void (*unsched_all)(struct sctp_stream *stream); }; int sctp_sched_set_sched(struct sctp_association *asoc, diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index f24a1bbcb3ef..1ad7ce71d0a7 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -521,7 +521,7 @@ struct sctp_datamsg { refcount_t refcnt; /* When is this message no longer interesting to the peer? */ unsigned long expires_at; - /* Did the messenge fail to send? */ + /* Did the message fail to send? */ int send_error; u8 send_failed:1, can_delay:1, /* should this message be Nagle delayed */ @@ -775,6 +775,7 @@ struct sctp_transport { /* Reference counting. */ refcount_t refcnt; + __u32 dead:1, /* RTO-Pending : A flag used to track if one of the DATA * chunks sent to this address is currently being * used to compute a RTT. If this flag is 0, @@ -784,7 +785,7 @@ struct sctp_transport { * calculation completes (i.e. the DATA chunk * is SACK'd) clear this flag. */ - __u32 rto_pending:1, + rto_pending:1, /* * hb_sent : a flag that signals that we have a pending @@ -792,7 +793,7 @@ struct sctp_transport { */ hb_sent:1, - /* Is the Path MTU update pending on this tranport */ + /* Is the Path MTU update pending on this transport */ pmtu_pending:1, dst_pending_confirm:1, /* need to confirm neighbour */ @@ -1223,7 +1224,7 @@ enum sctp_endpoint_type { }; /* - * A common base class to bridge the implmentation view of a + * A common base class to bridge the implementation view of a * socket (usually listening) endpoint versus an association's * local endpoint. * This common structure is useful for several purposes: @@ -1353,7 +1354,7 @@ struct sctp_endpoint { struct rcu_head rcu; }; -/* Recover the outter endpoint structure. */ +/* Recover the outer endpoint structure. */ static inline struct sctp_endpoint *sctp_ep(struct sctp_ep_common *base) { struct sctp_endpoint *ep; @@ -1906,7 +1907,7 @@ struct sctp_association { __u32 rwnd_over; /* Keeps treack of rwnd pressure. This happens when we have - * a window, but not recevie buffer (i.e small packets). This one + * a window, but not receive buffer (i.e small packets). This one * is releases slowly (1 PMTU at a time ). */ __u32 rwnd_press; @@ -1994,7 +1995,7 @@ struct sctp_association { /* ADDIP Section 5.2 Upon reception of an ASCONF Chunk. * - * This is needed to implement itmes E1 - E4 of the updated + * This is needed to implement items E1 - E4 of the updated * spec. Here is the justification: * * Since the peer may bundle multiple ASCONF chunks toward us, @@ -2005,7 +2006,7 @@ struct sctp_association { /* These ASCONF chunks are waiting to be sent. * - * These chunaks can't be pushed to outqueue until receiving + * These chunks can't be pushed to outqueue until receiving * ASCONF_ACK for the previous ASCONF indicated by * addip_last_asconf, so as to guarantee that only one ASCONF * is in flight at any time. @@ -2059,13 +2060,13 @@ struct sctp_association { struct sctp_transport *new_transport; /* SCTP AUTH: list of the endpoint shared keys. These - * keys are provided out of band by the user applicaton + * keys are provided out of band by the user application * and can't change during the lifetime of the association */ struct list_head endpoint_shared_keys; /* SCTP AUTH: - * The current generated assocaition shared key (secret) + * The current generated association shared key (secret) */ struct sctp_auth_bytes *asoc_shared_key; struct sctp_shared_key *shkey; @@ -2121,7 +2122,7 @@ enum { SCTP_ASSOC_EYECATCHER = 0xa550c123, }; -/* Recover the outter association structure. */ +/* Recover the outer association structure. */ static inline struct sctp_association *sctp_assoc(struct sctp_ep_common *base) { struct sctp_association *asoc; @@ -2151,8 +2152,6 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *, const union sctp_addr *address, const gfp_t gfp, const int peer_state); -void sctp_assoc_del_peer(struct sctp_association *asoc, - const union sctp_addr *addr); void sctp_assoc_rm_peer(struct sctp_association *asoc, struct sctp_transport *peer); void sctp_assoc_control_transport(struct sctp_association *asoc, diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h index 21e7fa2a1813..cddebafb9f77 100644 --- a/include/net/secure_seq.h +++ b/include/net/secure_seq.h @@ -16,9 +16,5 @@ u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, __be16 sport, __be16 dport); u32 secure_tcpv6_ts_off(const struct net *net, const __be32 *saddr, const __be32 *daddr); -u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr, - __be16 sport, __be16 dport); -u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr, - __be16 sport, __be16 dport); #endif /* _NET_SECURE_SEQ */ diff --git a/include/net/seg6.h b/include/net/seg6.h index af668f17b398..82b3fbbcbb93 100644 --- a/include/net/seg6.h +++ b/include/net/seg6.h @@ -52,10 +52,17 @@ static inline struct seg6_pernet_data *seg6_pernet(struct net *net) extern int seg6_init(void); extern void seg6_exit(void); +#ifdef CONFIG_IPV6_SEG6_LWTUNNEL extern int seg6_iptunnel_init(void); extern void seg6_iptunnel_exit(void); extern int seg6_local_init(void); extern void seg6_local_exit(void); +#else +static inline int seg6_iptunnel_init(void) { return 0; } +static inline void seg6_iptunnel_exit(void) {} +static inline int seg6_local_init(void) { return 0; } +static inline void seg6_local_exit(void) {} +#endif extern bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len, bool reduced); extern struct ipv6_sr_hdr *seg6_get_srh(struct sk_buff *skb, int flags); diff --git a/include/net/seg6_hmac.h b/include/net/seg6_hmac.h index 2b5d2ee5613e..24f733b3e3fe 100644 --- a/include/net/seg6_hmac.h +++ b/include/net/seg6_hmac.h @@ -49,9 +49,16 @@ extern int seg6_hmac_info_del(struct net *net, u32 key); extern int seg6_push_hmac(struct net *net, struct in6_addr *saddr, struct ipv6_sr_hdr *srh); extern bool seg6_hmac_validate_skb(struct sk_buff *skb); +#ifdef CONFIG_IPV6_SEG6_HMAC extern int seg6_hmac_init(void); extern void seg6_hmac_exit(void); extern int seg6_hmac_net_init(struct net *net); extern void seg6_hmac_net_exit(struct net *net); +#else +static inline int seg6_hmac_init(void) { return 0; } +static inline void seg6_hmac_exit(void) {} +static inline int seg6_hmac_net_init(struct net *net) { return 0; } +static inline void seg6_hmac_net_exit(struct net *net) {} +#endif #endif diff --git a/include/net/seg6_local.h b/include/net/seg6_local.h index 3fab9dec2ec4..888c1ce6f527 100644 --- a/include/net/seg6_local.h +++ b/include/net/seg6_local.h @@ -19,6 +19,7 @@ extern int seg6_lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr, extern bool seg6_bpf_has_valid_srh(struct sk_buff *skb); struct seg6_bpf_srh_state { + local_lock_t bh_lock; struct ipv6_sr_hdr *srh; u16 hdrlen; bool valid; diff --git a/include/net/smc.h b/include/net/smc.h index c9dcb30e3fd9..db84e4e35080 100644 --- a/include/net/smc.h +++ b/include/net/smc.h @@ -26,9 +26,6 @@ struct smc_hashinfo { struct hlist_head ht; }; -int smc_hash_sk(struct sock *sk); -void smc_unhash_sk(struct sock *sk); - /* SMCD/ISM device driver interface */ struct smcd_dmb { u64 dmb_tok; @@ -50,7 +47,6 @@ struct smcd_dmb { #define ISM_ERROR 0xFFFF struct smcd_dev; -struct ism_client; struct smcd_gid { u64 gid; @@ -61,14 +57,8 @@ struct smcd_ops { int (*query_remote_gid)(struct smcd_dev *dev, struct smcd_gid *rgid, u32 vid_valid, u32 vid); int (*register_dmb)(struct smcd_dev *dev, struct smcd_dmb *dmb, - struct ism_client *client); + void *client); int (*unregister_dmb)(struct smcd_dev *dev, struct smcd_dmb *dmb); - int (*add_vlan_id)(struct smcd_dev *dev, u64 vlan_id); - int (*del_vlan_id)(struct smcd_dev *dev, u64 vlan_id); - int (*set_vlan_required)(struct smcd_dev *dev); - int (*reset_vlan_required)(struct smcd_dev *dev); - int (*signal_event)(struct smcd_dev *dev, struct smcd_gid *rgid, - u32 trigger_irq, u32 event_code, u64 info); int (*move_data)(struct smcd_dev *dev, u64 dmb_tok, unsigned int idx, bool sf, unsigned int offset, void *data, unsigned int size); @@ -76,11 +66,23 @@ struct smcd_ops { void (*get_local_gid)(struct smcd_dev *dev, struct smcd_gid *gid); u16 (*get_chid)(struct smcd_dev *dev); struct device* (*get_dev)(struct smcd_dev *dev); + + /* optional operations */ + int (*add_vlan_id)(struct smcd_dev *dev, u64 vlan_id); + int (*del_vlan_id)(struct smcd_dev *dev, u64 vlan_id); + int (*set_vlan_required)(struct smcd_dev *dev); + int (*reset_vlan_required)(struct smcd_dev *dev); + int (*signal_event)(struct smcd_dev *dev, struct smcd_gid *rgid, + u32 trigger_irq, u32 event_code, u64 info); + int (*support_dmb_nocopy)(struct smcd_dev *dev); + int (*attach_dmb)(struct smcd_dev *dev, struct smcd_dmb *dmb); + int (*detach_dmb)(struct smcd_dev *dev, u64 token); }; struct smcd_dev { const struct smcd_ops *ops; void *priv; + void *client; struct list_head list; spinlock_t lock; struct smc_connection **conn; diff --git a/include/net/snmp.h b/include/net/snmp.h index 468a67836e2f..4cb4326dfebe 100644 --- a/include/net/snmp.h +++ b/include/net/snmp.h @@ -159,7 +159,7 @@ struct linux_tls_mib { #define __SNMP_ADD_STATS64(mib, field, addend) \ do { \ - __typeof__(*mib) *ptr = raw_cpu_ptr(mib); \ + TYPEOF_UNQUAL(*mib) *ptr = raw_cpu_ptr(mib); \ u64_stats_update_begin(&ptr->syncp); \ ptr->mibs[field] += addend; \ u64_stats_update_end(&ptr->syncp); \ @@ -176,8 +176,7 @@ struct linux_tls_mib { #define SNMP_INC_STATS64(mib, field) SNMP_ADD_STATS64(mib, field, 1) #define __SNMP_UPD_PO_STATS64(mib, basefield, addend) \ do { \ - __typeof__(*mib) *ptr; \ - ptr = raw_cpu_ptr((mib)); \ + TYPEOF_UNQUAL(*mib) *ptr = raw_cpu_ptr(mib); \ u64_stats_update_begin(&ptr->syncp); \ ptr->mibs[basefield##PKTS]++; \ ptr->mibs[basefield##OCTETS] += addend; \ diff --git a/include/net/sock.h b/include/net/sock.h index b4b553df7870..92e7c1aae3cc 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -303,6 +303,7 @@ struct sk_filter; * @sk_stamp: time stamp of last packet received * @sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only * @sk_tsflags: SO_TIMESTAMPING flags + * @sk_bpf_cb_flags: used in bpf_setsockopt() * @sk_use_task_frag: allow sk_page_frag() to use current->task_frag. * Sockets that can be used under memory reclaim should * set this to false. @@ -336,7 +337,16 @@ struct sk_filter; * @sk_txtime_deadline_mode: set deadline mode for SO_TXTIME * @sk_txtime_report_errors: set report errors mode for SO_TXTIME * @sk_txtime_unused: unused txtime flags + * @sk_scm_recv_flags: all flags used by scm_recv() + * @sk_scm_credentials: flagged by SO_PASSCRED to recv SCM_CREDENTIALS + * @sk_scm_security: flagged by SO_PASSSEC to recv SCM_SECURITY + * @sk_scm_pidfd: flagged by SO_PASSPIDFD to recv SCM_PIDFD + * @sk_scm_rights: flagged by SO_PASSRIGHTS to recv SCM_RIGHTS + * @sk_scm_unused: unused flags for scm_recv() * @ns_tracker: tracker for netns reference + * @sk_user_frags: xarray of pages the user is holding a reference on. + * @sk_owner: reference to the real owner of the socket that calls + * sock_lock_init_class_and_name(). */ struct sock { /* @@ -519,11 +529,23 @@ struct sock { #endif int sk_disconnects; - u8 sk_txrehash; + union { + u8 sk_txrehash; + u8 sk_scm_recv_flags; + struct { + u8 sk_scm_credentials : 1, + sk_scm_security : 1, + sk_scm_pidfd : 1, + sk_scm_rights : 1, + sk_scm_unused : 4; + }; + }; u8 sk_clockid; u8 sk_txtime_deadline_mode : 1, sk_txtime_report_errors : 1, sk_txtime_unused : 6; +#define SK_BPF_CB_FLAG_TEST(SK, FLAG) ((SK)->sk_bpf_cb_flags & (FLAG)) + u8 sk_bpf_cb_flags; void *sk_user_data; #ifdef CONFIG_SECURITY @@ -542,6 +564,16 @@ struct sock { #endif struct rcu_head sk_rcu; netns_tracker ns_tracker; + struct xarray sk_user_frags; + +#if IS_ENABLED(CONFIG_PROVE_LOCKING) && IS_ENABLED(CONFIG_MODULES) + struct module *sk_owner; +#endif +}; + +struct sock_bh_locked { + struct sock *sock; + local_lock_t bh_lock; }; enum sk_pacing { @@ -887,6 +919,8 @@ static inline void sk_add_bind_node(struct sock *sk, hlist_for_each_entry_safe(__sk, tmp, list, sk_node) #define sk_for_each_bound(__sk, list) \ hlist_for_each_entry(__sk, list, sk_bind_node) +#define sk_for_each_bound_safe(__sk, tmp, list) \ + hlist_for_each_entry_safe(__sk, tmp, list, sk_bind_node) /** * sk_for_each_entry_offset_rcu - iterate over a list at a given struct offset @@ -944,9 +978,17 @@ enum sock_flags { SOCK_XDP, /* XDP is attached */ SOCK_TSTAMP_NEW, /* Indicates 64 bit timestamps always */ SOCK_RCVMARK, /* Receive SO_MARK ancillary data with packet */ + SOCK_RCVPRIORITY, /* Receive SO_PRIORITY ancillary data with packet */ + SOCK_TIMESTAMPING_ANY, /* Copy of sk_tsflags & TSFLAGS_ANY */ }; #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) +/* + * The highest bit of sk_tsflags is reserved for kernel-internal + * SOCKCM_FLAG_TS_OPT_ID. There is a check in core/sock.c to control that + * SOF_TIMESTAMPING* values do not reach this reserved area + */ +#define SOCKCM_FLAG_TS_OPT_ID BIT(31) static inline void sock_copy_flags(struct sock *nsk, const struct sock *osk) { @@ -1194,6 +1236,13 @@ static inline void sk_prot_clear_nulls(struct sock *sk, int size) size - offsetof(struct sock, sk_node.pprev)); } +struct proto_accept_arg { + int flags; + int err; + int is_empty; + bool kern; +}; + /* Networking protocol blocks we attach to sockets. * socket layer -> transport layer interface */ @@ -1208,8 +1257,8 @@ struct proto { int addr_len); int (*disconnect)(struct sock *sk, int flags); - struct sock * (*accept)(struct sock *sk, int flags, int *err, - bool kern); + struct sock * (*accept)(struct sock *sk, + struct proto_accept_arg *arg); int (*ioctl)(struct sock *sk, int cmd, int *karg); @@ -1261,10 +1310,6 @@ struct proto { unsigned int inuse_idx; #endif -#if IS_ENABLED(CONFIG_MPTCP) - int (*forward_alloc_get)(const struct sock *sk); -#endif - bool (*stream_memory_free)(const struct sock *sk, int wake); bool (*sock_is_readable)(struct sock *sk); /* Memory pressure */ @@ -1325,15 +1370,6 @@ int sock_load_diag_module(int family, int protocol); INDIRECT_CALLABLE_DECLARE(bool tcp_stream_memory_free(const struct sock *sk, int wake)); -static inline int sk_forward_alloc_get(const struct sock *sk) -{ -#if IS_ENABLED(CONFIG_MPTCP) - if (sk->sk_prot->forward_alloc_get) - return sk->sk_prot->forward_alloc_get(sk); -#endif - return READ_ONCE(sk->sk_forward_alloc); -} - static inline bool __sk_stream_memory_free(const struct sock *sk, int wake) { if (READ_ONCE(sk->sk_wmem_queued) >= READ_ONCE(sk->sk_sndbuf)) @@ -1371,75 +1407,6 @@ static inline int sk_under_cgroup_hierarchy(struct sock *sk, #endif } -static inline bool sk_has_memory_pressure(const struct sock *sk) -{ - return sk->sk_prot->memory_pressure != NULL; -} - -static inline bool sk_under_global_memory_pressure(const struct sock *sk) -{ - return sk->sk_prot->memory_pressure && - !!READ_ONCE(*sk->sk_prot->memory_pressure); -} - -static inline bool sk_under_memory_pressure(const struct sock *sk) -{ - if (!sk->sk_prot->memory_pressure) - return false; - - if (mem_cgroup_sockets_enabled && sk->sk_memcg && - mem_cgroup_under_socket_pressure(sk->sk_memcg)) - return true; - - return !!READ_ONCE(*sk->sk_prot->memory_pressure); -} - -static inline long -proto_memory_allocated(const struct proto *prot) -{ - return max(0L, atomic_long_read(prot->memory_allocated)); -} - -static inline long -sk_memory_allocated(const struct sock *sk) -{ - return proto_memory_allocated(sk->sk_prot); -} - -/* 1 MB per cpu, in page units */ -#define SK_MEMORY_PCPU_RESERVE (1 << (20 - PAGE_SHIFT)) -extern int sysctl_mem_pcpu_rsv; - -static inline void proto_memory_pcpu_drain(struct proto *proto) -{ - int val = this_cpu_xchg(*proto->per_cpu_fw_alloc, 0); - - if (val) - atomic_long_add(val, proto->memory_allocated); -} - -static inline void -sk_memory_allocated_add(const struct sock *sk, int val) -{ - struct proto *proto = sk->sk_prot; - - val = this_cpu_add_return(*proto->per_cpu_fw_alloc, val); - - if (unlikely(val >= READ_ONCE(sysctl_mem_pcpu_rsv))) - proto_memory_pcpu_drain(proto); -} - -static inline void -sk_memory_allocated_sub(const struct sock *sk, int val) -{ - struct proto *proto = sk->sk_prot; - - val = this_cpu_sub_return(*proto->per_cpu_fw_alloc, val); - - if (unlikely(val <= -READ_ONCE(sysctl_mem_pcpu_rsv))) - proto_memory_pcpu_drain(proto); -} - #define SK_ALLOC_PERCPU_COUNTER_BATCH 16 static inline void sk_sockets_allocated_dec(struct sock *sk) @@ -1466,15 +1433,6 @@ proto_sockets_allocated_sum_positive(struct proto *prot) return percpu_counter_sum_positive(prot->sockets_allocated); } -static inline bool -proto_memory_pressure(struct proto *prot) -{ - if (!prot->memory_pressure) - return false; - return !!READ_ONCE(*prot->memory_pressure); -} - - #ifdef CONFIG_PROC_FS #define PROTO_INUSE_NR 64 /* should be enough for the first time */ struct prot_inuse { @@ -1583,7 +1541,7 @@ static inline bool sk_wmem_schedule(struct sock *sk, int size) } static inline bool -sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) +__sk_rmem_schedule(struct sock *sk, int size, bool pfmemalloc) { int delta; @@ -1591,7 +1549,13 @@ sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) return true; delta = size - sk->sk_forward_alloc; return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_RECV) || - skb_pfmemalloc(skb); + pfmemalloc; +} + +static inline bool +sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) +{ + return __sk_rmem_schedule(sk, size, skb_pfmemalloc(skb)); } static inline int sk_unused_reserved_mem(const struct sock *sk) @@ -1641,6 +1605,35 @@ static inline void sk_mem_uncharge(struct sock *sk, int size) sk_mem_reclaim(sk); } +#if IS_ENABLED(CONFIG_PROVE_LOCKING) && IS_ENABLED(CONFIG_MODULES) +static inline void sk_owner_set(struct sock *sk, struct module *owner) +{ + __module_get(owner); + sk->sk_owner = owner; +} + +static inline void sk_owner_clear(struct sock *sk) +{ + sk->sk_owner = NULL; +} + +static inline void sk_owner_put(struct sock *sk) +{ + module_put(sk->sk_owner); +} +#else +static inline void sk_owner_set(struct sock *sk, struct module *owner) +{ +} + +static inline void sk_owner_clear(struct sock *sk) +{ +} + +static inline void sk_owner_put(struct sock *sk) +{ +} +#endif /* * Macro so as to not evaluate some arguments when * lockdep is not enabled. @@ -1650,13 +1643,14 @@ static inline void sk_mem_uncharge(struct sock *sk, int size) */ #define sock_lock_init_class_and_name(sk, sname, skey, name, key) \ do { \ + sk_owner_set(sk, THIS_MODULE); \ sk->sk_lock.owned = 0; \ init_waitqueue_head(&sk->sk_lock.wq); \ spin_lock_init(&(sk)->sk_lock.slock); \ debug_check_no_locks_freed((void *)&(sk)->sk_lock, \ - sizeof((sk)->sk_lock)); \ + sizeof((sk)->sk_lock)); \ lockdep_set_class_and_name(&(sk)->sk_lock.slock, \ - (skey), (sname)); \ + (skey), (sname)); \ lockdep_init_map(&(sk)->sk_lock.dep_map, (name), (key), 0); \ } while (0) @@ -1690,7 +1684,7 @@ bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock); * lock_sock_fast - fast version of lock_sock * @sk: socket * - * This version should be used for very small section, where process wont block + * This version should be used for very small section, where process won't block * return false if fast path is taken: * * sk_lock.slock locked, owned = 0, BH disabled @@ -1800,9 +1794,9 @@ static inline bool sock_allow_reclassification(const struct sock *csk) struct sock *sk_alloc(struct net *net, int family, gfp_t priority, struct proto *prot, int kern); void sk_free(struct sock *sk); +void sk_net_refcnt_upgrade(struct sock *sk); void sk_destruct(struct sock *sk); struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority); -void sk_free_unlock_clone(struct sock *sk); struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority); @@ -1816,6 +1810,15 @@ void sock_efree(struct sk_buff *skb); #ifdef CONFIG_INET void sock_edemux(struct sk_buff *skb); void sock_pfree(struct sk_buff *skb); + +static inline void skb_set_owner_edemux(struct sk_buff *skb, struct sock *sk) +{ + skb_orphan(skb); + if (refcount_inc_not_zero(&sk->sk_refcnt)) { + skb->sk = sk; + skb->destructor = sock_edemux; + } +} #else #define sock_edemux sock_efree #endif @@ -1845,6 +1848,8 @@ static inline struct sk_buff *sock_alloc_send_skb(struct sock *sk, } void *sock_kmalloc(struct sock *sk, int size, gfp_t priority); +void *sock_kmemdup(struct sock *sk, const void *src, + int size, gfp_t priority); void sock_kfree_s(struct sock *sk, void *mem, int size); void sock_kzfree_s(struct sock *sk, void *mem, int size); void sk_send_sigurg(struct sock *sk); @@ -1860,13 +1865,18 @@ struct sockcm_cookie { u64 transmit_time; u32 mark; u32 tsflags; + u32 ts_opt_id; + u32 priority; + u32 dmabuf_id; }; static inline void sockcm_init(struct sockcm_cookie *sockc, const struct sock *sk) { *sockc = (struct sockcm_cookie) { - .tsflags = READ_ONCE(sk->sk_tsflags) + .mark = READ_ONCE(sk->sk_mark), + .tsflags = READ_ONCE(sk->sk_tsflags), + .priority = READ_ONCE(sk->sk_priority), }; } @@ -1882,7 +1892,7 @@ int sock_cmsg_send(struct sock *sk, struct msghdr *msg, int sock_no_bind(struct socket *, struct sockaddr *, int); int sock_no_connect(struct socket *, struct sockaddr *, int, int); int sock_no_socketpair(struct socket *, struct socket *); -int sock_no_accept(struct socket *, struct socket *, int, bool); +int sock_no_accept(struct socket *, struct socket *, struct proto_accept_arg *); int sock_no_getname(struct socket *, struct sockaddr *, int); int sock_no_ioctl(struct socket *, unsigned int, unsigned long); int sock_no_listen(struct socket *, int); @@ -2134,17 +2144,10 @@ sk_dst_get(const struct sock *sk) static inline void __dst_negative_advice(struct sock *sk) { - struct dst_entry *ndst, *dst = __sk_dst_get(sk); - - if (dst && dst->ops->negative_advice) { - ndst = dst->ops->negative_advice(dst); + struct dst_entry *dst = __sk_dst_get(sk); - if (ndst != dst) { - rcu_assign_pointer(sk->sk_dst_cache, ndst); - sk_tx_queue_clear(sk); - WRITE_ONCE(sk->sk_dst_pending_confirm, 0); - } - } + if (dst && dst->ops->negative_advice) + dst->ops->negative_advice(sk, dst); } static inline void dst_negative_advice(struct sock *sk) @@ -2173,7 +2176,7 @@ sk_dst_set(struct sock *sk, struct dst_entry *dst) sk_tx_queue_clear(sk); WRITE_ONCE(sk->sk_dst_pending_confirm, 0); - old_dst = xchg((__force struct dst_entry **)&sk->sk_dst_cache, dst); + old_dst = unrcu_pointer(xchg(&sk->sk_dst_cache, RCU_INITIALIZER(dst))); dst_release(old_dst); } @@ -2344,7 +2347,7 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq) } /** - * sock_poll_wait - place memory barrier behind the poll_wait call. + * sock_poll_wait - wrapper for the poll_wait call. * @filp: file * @sock: socket to wait on * @p: poll_table @@ -2354,15 +2357,12 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq) static inline void sock_poll_wait(struct file *filp, struct socket *sock, poll_table *p) { - if (!poll_does_not_wait(p)) { - poll_wait(filp, &sock->wq.wait, p); - /* We need to be sure we are in sync with the - * socket flags modification. - * - * This memory barrier is paired in the wq_has_sleeper. - */ - smp_mb(); - } + /* Provides a barrier we need to be sure we are in sync + * with the socket flags modification. + * + * This memory barrier is paired in the wq_has_sleeper. + */ + poll_wait(filp, &sock->wq.wait, p); } static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk) @@ -2515,6 +2515,12 @@ static inline void sk_wake_async(const struct sock *sk, int how, int band) } } +static inline void sk_wake_async_rcu(const struct sock *sk, int how, int band) +{ + if (unlikely(sock_flag(sk, SOCK_FASYNC))) + sock_wake_async(rcu_dereference(sk->sk_wq), how, band); +} + /* Since sk_{r,w}mem_alloc sums skb->truesize, even a small frame might * need sizeof(sk_buff) + MTU + padding, unless net driver perform copybreak. * Note: for send buffers, TCP works better if we can build two skbs at @@ -2613,10 +2619,10 @@ struct sock_skb_cb { /* 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. + * alignment guarantee. */ -#define SOCK_SKB_CB_OFFSET ((sizeof_field(struct sk_buff, cb) - \ - sizeof(struct sock_skb_cb))) +#define SOCK_SKB_CB_OFFSET (sizeof_field(struct sk_buff, cb) - \ + sizeof(struct sock_skb_cb)) #define SOCK_SKB_CB(__skb) ((struct sock_skb_cb *)((__skb)->cb + \ SOCK_SKB_CB_OFFSET)) @@ -2705,12 +2711,13 @@ static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, { #define FLAGS_RECV_CMSGS ((1UL << SOCK_RXQ_OVFL) | \ (1UL << SOCK_RCVTSTAMP) | \ - (1UL << SOCK_RCVMARK)) + (1UL << SOCK_RCVMARK) | \ + (1UL << SOCK_RCVPRIORITY) | \ + (1UL << SOCK_TIMESTAMPING_ANY)) #define TSFLAGS_ANY (SOF_TIMESTAMPING_SOFTWARE | \ SOF_TIMESTAMPING_RAW_HARDWARE) - if (sk->sk_flags & FLAGS_RECV_CMSGS || - READ_ONCE(sk->sk_tsflags) & TSFLAGS_ANY) + if (READ_ONCE(sk->sk_flags) & FLAGS_RECV_CMSGS) __sock_recv_cmsgs(msg, sk, skb); else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP))) sock_write_timestamp(sk, skb->tstamp); @@ -2718,39 +2725,46 @@ static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, sock_write_timestamp(sk, 0); } -void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags); +void __sock_tx_timestamp(__u32 tsflags, __u8 *tx_flags); /** * _sock_tx_timestamp - checks whether the outgoing packet is to be time stamped * @sk: socket sending this packet - * @tsflags: timestamping flags to use + * @sockc: pointer to socket cmsg cookie to get timestamping info * @tx_flags: completed with instructions for time stamping * @tskey: filled in with next sk_tskey (not for TCP, which uses seqno) * * Note: callers should take care of initial ``*tx_flags`` value (usually 0) */ -static inline void _sock_tx_timestamp(struct sock *sk, __u16 tsflags, +static inline void _sock_tx_timestamp(struct sock *sk, + const struct sockcm_cookie *sockc, __u8 *tx_flags, __u32 *tskey) { + __u32 tsflags = sockc->tsflags; + if (unlikely(tsflags)) { __sock_tx_timestamp(tsflags, tx_flags); if (tsflags & SOF_TIMESTAMPING_OPT_ID && tskey && - tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) - *tskey = atomic_inc_return(&sk->sk_tskey) - 1; + tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) { + if (tsflags & SOCKCM_FLAG_TS_OPT_ID) + *tskey = sockc->ts_opt_id; + else + *tskey = atomic_inc_return(&sk->sk_tskey) - 1; + } } - if (unlikely(sock_flag(sk, SOCK_WIFI_STATUS))) - *tx_flags |= SKBTX_WIFI_STATUS; } -static inline void sock_tx_timestamp(struct sock *sk, __u16 tsflags, +static inline void sock_tx_timestamp(struct sock *sk, + const struct sockcm_cookie *sockc, __u8 *tx_flags) { - _sock_tx_timestamp(sk, tsflags, tx_flags, NULL); + _sock_tx_timestamp(sk, sockc, tx_flags, NULL); } -static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags) +static inline void skb_setup_tx_timestamp(struct sk_buff *skb, + const struct sockcm_cookie *sockc) { - _sock_tx_timestamp(skb->sk, tsflags, &skb_shinfo(skb)->tx_flags, + _sock_tx_timestamp(skb->sk, sockc, &skb_shinfo(skb)->tx_flags, &skb_shinfo(skb)->tskey); } @@ -2775,9 +2789,26 @@ static inline bool sk_is_udp(const struct sock *sk) sk->sk_protocol == IPPROTO_UDP; } +static inline bool sk_is_unix(const struct sock *sk) +{ + return sk->sk_family == AF_UNIX; +} + static inline bool sk_is_stream_unix(const struct sock *sk) { - return sk->sk_family == AF_UNIX && sk->sk_type == SOCK_STREAM; + return sk_is_unix(sk) && sk->sk_type == SOCK_STREAM; +} + +static inline bool sk_is_vsock(const struct sock *sk) +{ + return sk->sk_family == AF_VSOCK; +} + +static inline bool sk_may_scm_recv(const struct sock *sk) +{ + return (IS_ENABLED(CONFIG_UNIX) && sk->sk_family == AF_UNIX) || + sk->sk_family == AF_NETLINK || + (IS_ENABLED(CONFIG_BT) && sk->sk_family == AF_BLUETOOTH); } /** @@ -2819,6 +2850,12 @@ sk_is_refcounted(struct sock *sk) return !sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE); } +static inline bool +sk_requests_wifi_status(struct sock *sk) +{ + return sk && sk_fullsock(sk) && sock_flag(sk, SOCK_WIFI_STATUS); +} + /* Checks if this SKB belongs to an HW offloaded socket * and whether any SW fallbacks are required based on dev. * Check decrypted mark in case skb_orphan() cleared socket. @@ -2831,12 +2868,10 @@ static inline struct sk_buff *sk_validate_xmit_skb(struct sk_buff *skb, if (sk && sk_fullsock(sk) && sk->sk_validate_xmit_skb) { skb = sk->sk_validate_xmit_skb(sk, dev, skb); -#ifdef CONFIG_TLS_DEVICE - } else if (unlikely(skb->decrypted)) { + } else if (unlikely(skb_is_decrypted(skb))) { pr_warn_ratelimited("unencrypted skb with no associated socket - dropping\n"); kfree_skb(skb); skb = NULL; -#endif } #endif @@ -2851,6 +2886,16 @@ static inline bool sk_listener(const struct sock *sk) return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV); } +/* This helper checks if a socket is a LISTEN or NEW_SYN_RECV or TIME_WAIT + * TCP SYNACK messages can be attached to LISTEN or NEW_SYN_RECV (depending on SYNCOOKIE) + * TCP RST and ACK can be attached to TIME_WAIT. + */ +static inline bool sk_listener_or_tw(const struct sock *sk) +{ + return (1 << READ_ONCE(sk->sk_state)) & + (TCPF_LISTEN | TCPF_NEW_SYN_RECV | TCPF_TIME_WAIT); +} + void sock_enable_timestamp(struct sock *sk, enum sock_flags flag); int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level, int type); @@ -2875,8 +2920,6 @@ void sk_get_meminfo(const struct sock *sk, u32 *meminfo); extern __u32 sysctl_wmem_max; extern __u32 sysctl_rmem_max; -extern int sysctl_tstamp_allow_data; - extern __u32 sysctl_wmem_default; extern __u32 sysctl_rmem_default; @@ -2940,6 +2983,13 @@ int sock_set_timestamping(struct sock *sk, int optname, struct so_timestamping timestamping); void sock_enable_timestamps(struct sock *sk); +#if defined(CONFIG_CGROUP_BPF) +void bpf_skops_tx_timestamping(struct sock *sk, struct sk_buff *skb, int op); +#else +static inline void bpf_skops_tx_timestamping(struct sock *sk, struct sk_buff *skb, int op) +{ +} +#endif void sock_no_linger(struct sock *sk); void sock_set_keepalive(struct sock *sk); void sock_set_priority(struct sock *sk, u32 priority); diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h index 6ec140b0a61b..6e4faf3ee76f 100644 --- a/include/net/sock_reuseport.h +++ b/include/net/sock_reuseport.h @@ -26,7 +26,7 @@ struct sock_reuseport { unsigned int bind_inany:1; unsigned int has_conns:1; struct bpf_prog __rcu *prog; /* optional BPF sock selector */ - struct sock *socks[]; /* array of sock pointers */ + struct sock *socks[] __counted_by(max_socks); }; extern int reuseport_alloc(struct sock *sk, bool bind_inany); diff --git a/include/net/strparser.h b/include/net/strparser.h index 41e2ce9e9e10..0ed73e364faa 100644 --- a/include/net/strparser.h +++ b/include/net/strparser.h @@ -43,6 +43,8 @@ struct strparser; struct strp_callbacks { int (*parse_msg)(struct strparser *strp, struct sk_buff *skb); void (*rcv_msg)(struct strparser *strp, struct sk_buff *skb); + int (*read_sock)(struct strparser *strp, read_descriptor_t *desc, + sk_read_actor_t recv_actor); int (*read_sock_done)(struct strparser *strp, int err); void (*abort_parser)(struct strparser *strp, int err); void (*lock)(struct strparser *strp); @@ -112,8 +114,6 @@ static inline void strp_pause(struct strparser *strp) /* May be called without holding lock for attached socket */ void strp_unpause(struct strparser *strp); -/* Must be called with process lock held (lock_sock) */ -void __strp_unpause(struct strparser *strp); static inline void save_strp_stats(struct strparser *strp, struct strp_aggr_stats *agg_stats) diff --git a/include/net/tcp.h b/include/net/tcp.h index 6ae35199d3b3..5078ad868fee 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -26,6 +26,7 @@ #include <linux/kref.h> #include <linux/ktime.h> #include <linux/indirect_call_wrapper.h> +#include <linux/bits.h> #include <net/inet_connection_sock.h> #include <net/inet_timewait_sock.h> @@ -41,6 +42,7 @@ #include <net/inet_ecn.h> #include <net/dst.h> #include <net/mptcp.h> +#include <net/xfrm.h> #include <linux/seq_file.h> #include <linux/memcontrol.h> @@ -52,6 +54,8 @@ extern struct inet_hashinfo tcp_hashinfo; DECLARE_PER_CPU(unsigned int, tcp_orphan_count); int tcp_orphan_count_sum(void); +DECLARE_PER_CPU(u32, tcp_tw_isn); + void tcp_time_wait(struct sock *sk, int state, int timeo); #define MAX_TCP_HEADER L1_CACHE_ALIGN(128 + MAX_HEADER) @@ -141,8 +145,9 @@ static_assert((1 << ATO_BITS) > TCP_DELACK_MAX); #define TCP_DELACK_MIN 4U #define TCP_ATO_MIN 4U #endif -#define TCP_RTO_MAX ((unsigned)(120*HZ)) -#define TCP_RTO_MIN ((unsigned)(HZ/5)) +#define TCP_RTO_MAX_SEC 120 +#define TCP_RTO_MAX ((unsigned)(TCP_RTO_MAX_SEC * HZ)) +#define TCP_RTO_MIN ((unsigned)(HZ / 5)) #define TCP_TIMEOUT_MIN (2U) /* Min timeout for TCP timers in jiffies */ #define TCP_TIMEOUT_MIN_US (2*USEC_PER_MSEC) /* Min TCP timeout in microsecs */ @@ -294,14 +299,6 @@ static inline bool between(__u32 seq1, __u32 seq2, __u32 seq3) return seq3 - seq2 >= seq1 - seq2; } -static inline bool tcp_out_of_memory(struct sock *sk) -{ - if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF && - sk_memory_allocated(sk) > sk_prot_mem_limits(sk, 2)) - return true; - return false; -} - static inline void tcp_wmem_free_skb(struct sock *sk, struct sk_buff *skb) { sk_wmem_queued_add(sk, -skb->truesize); @@ -314,7 +311,7 @@ static inline void tcp_wmem_free_skb(struct sock *sk, struct sk_buff *skb) void sk_forced_mem_schedule(struct sock *sk, int size); -bool tcp_check_oom(struct sock *sk, int shift); +bool tcp_check_oom(const struct sock *sk, int shift); extern struct proto tcp_prot; @@ -353,7 +350,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb); void tcp_rcv_space_adjust(struct sock *sk); int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp); void tcp_twsk_destructor(struct sock *sk); -void tcp_twsk_purge(struct list_head *net_exit_list, int family); +void tcp_twsk_purge(struct list_head *net_exit_list); ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); @@ -377,25 +374,64 @@ static inline void tcp_dec_quickack_mode(struct sock *sk) } } -#define TCP_ECN_OK 1 -#define TCP_ECN_QUEUE_CWR 2 -#define TCP_ECN_DEMAND_CWR 4 -#define TCP_ECN_SEEN 8 +#define TCP_ECN_MODE_RFC3168 BIT(0) +#define TCP_ECN_QUEUE_CWR BIT(1) +#define TCP_ECN_DEMAND_CWR BIT(2) +#define TCP_ECN_SEEN BIT(3) +#define TCP_ECN_MODE_ACCECN BIT(4) + +#define TCP_ECN_DISABLED 0 +#define TCP_ECN_MODE_PENDING (TCP_ECN_MODE_RFC3168 | TCP_ECN_MODE_ACCECN) +#define TCP_ECN_MODE_ANY (TCP_ECN_MODE_RFC3168 | TCP_ECN_MODE_ACCECN) + +static inline bool tcp_ecn_mode_any(const struct tcp_sock *tp) +{ + return tp->ecn_flags & TCP_ECN_MODE_ANY; +} + +static inline bool tcp_ecn_mode_rfc3168(const struct tcp_sock *tp) +{ + return (tp->ecn_flags & TCP_ECN_MODE_ANY) == TCP_ECN_MODE_RFC3168; +} + +static inline bool tcp_ecn_mode_accecn(const struct tcp_sock *tp) +{ + return (tp->ecn_flags & TCP_ECN_MODE_ANY) == TCP_ECN_MODE_ACCECN; +} + +static inline bool tcp_ecn_disabled(const struct tcp_sock *tp) +{ + return !tcp_ecn_mode_any(tp); +} + +static inline bool tcp_ecn_mode_pending(const struct tcp_sock *tp) +{ + return (tp->ecn_flags & TCP_ECN_MODE_PENDING) == TCP_ECN_MODE_PENDING; +} + +static inline void tcp_ecn_mode_set(struct tcp_sock *tp, u8 mode) +{ + tp->ecn_flags &= ~TCP_ECN_MODE_ANY; + tp->ecn_flags |= mode; +} enum tcp_tw_status { TCP_TW_SUCCESS = 0, TCP_TW_RST = 1, TCP_TW_ACK = 2, - TCP_TW_SYN = 3 + TCP_TW_SYN = 3, + TCP_TW_ACK_OOW = 4 }; enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, - const struct tcphdr *th); + const struct tcphdr *th, + u32 *tw_isn, + enum skb_drop_reason *drop_reason); struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, struct request_sock *req, bool fastopen, - bool *lost_race); + bool *lost_race, enum skb_drop_reason *drop_reason); enum skb_drop_reason tcp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb); void tcp_enter_loss(struct sock *sk); @@ -420,6 +456,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); +void tcp_reset_keepalive_timer(struct sock *sk, unsigned long timeout); void tcp_set_keepalive(struct sock *sk, int val); void tcp_syn_ack_timeout(const struct request_sock *req); int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, @@ -667,10 +704,11 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, void tcp_send_probe0(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); +void tcp_send_active_reset(struct sock *sk, gfp_t priority, + enum sk_rst_reason reason); int tcp_send_synack(struct sock *); void tcp_push_one(struct sock *, unsigned int mss_now); -void __tcp_send_ack(struct sock *sk, u32 rcv_nxt); +void __tcp_send_ack(struct sock *sk, u32 rcv_nxt, u16 flags); void tcp_send_ack(struct sock *sk); void tcp_send_delayed_ack(struct sock *sk); void tcp_send_loss_probe(struct sock *sk); @@ -681,11 +719,25 @@ void tcp_skb_collapse_tstamp(struct sk_buff *skb, /* tcp_input.c */ void tcp_rearm_rto(struct sock *sk); void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req); +void tcp_done_with_error(struct sock *sk, int err); void tcp_reset(struct sock *sk, struct sk_buff *skb); void tcp_fin(struct sock *sk); void tcp_check_space(struct sock *sk); void tcp_sack_compress_send_ack(struct sock *sk); +static inline void tcp_cleanup_skb(struct sk_buff *skb) +{ + skb_dst_drop(skb); + secpath_reset(skb); +} + +static inline void tcp_add_receive_queue(struct sock *sk, struct sk_buff *skb) +{ + DEBUG_NET_WARN_ON_ONCE(skb_dst(skb)); + DEBUG_NET_WARN_ON_ONCE(secpath_exists(skb)); + __skb_queue_tail(&sk->sk_receive_queue, skb); +} + /* tcp_timer.c */ void tcp_init_xmit_timers(struct sock *); static inline void tcp_clear_xmit_timers(struct sock *sk) @@ -732,6 +784,9 @@ void tcp_get_info(struct sock *, struct tcp_info *); /* Read 'sendfile()'-style from a TCP socket */ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor); +int tcp_read_sock_noack(struct sock *sk, read_descriptor_t *desc, + sk_read_actor_t recv_actor, bool noack, + u32 *copied_seq); int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor); struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off); void tcp_read_done(struct sock *sk, size_t len); @@ -742,10 +797,14 @@ int tcp_mtu_to_mss(struct sock *sk, int pmtu); int tcp_mss_to_mtu(struct sock *sk, int mss); void tcp_mtup_init(struct sock *sk); -static inline void tcp_bound_rto(const struct sock *sk) +static inline unsigned int tcp_rto_max(const struct sock *sk) { - if (inet_csk(sk)->icsk_rto > TCP_RTO_MAX) - inet_csk(sk)->icsk_rto = TCP_RTO_MAX; + return READ_ONCE(inet_csk(sk)->icsk_rto_max); +} + +static inline void tcp_bound_rto(struct sock *sk) +{ + inet_csk(sk)->icsk_rto = min(inet_csk(sk)->icsk_rto, tcp_rto_max(sk)); } static inline u32 __tcp_set_rto(const struct tcp_sock *tp) @@ -786,7 +845,7 @@ u32 tcp_delack_max(const struct sock *sk); static inline u32 tcp_rto_min(const struct sock *sk) { const struct dst_entry *dst = __sk_dst_get(sk); - u32 rto_min = inet_csk(sk)->icsk_rto_min; + u32 rto_min = READ_ONCE(inet_csk(sk)->icsk_rto_min); if (dst && dst_metric_locked(dst, RTAX_RTO_MIN)) rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN); @@ -914,17 +973,37 @@ static inline u32 tcp_rsk_tsval(const struct tcp_request_sock *treq) #define tcp_flag_byte(th) (((u_int8_t *)th)[13]) -#define TCPHDR_FIN 0x01 -#define TCPHDR_SYN 0x02 -#define TCPHDR_RST 0x04 -#define TCPHDR_PSH 0x08 -#define TCPHDR_ACK 0x10 -#define TCPHDR_URG 0x20 -#define TCPHDR_ECE 0x40 -#define TCPHDR_CWR 0x80 - +#define TCPHDR_FIN BIT(0) +#define TCPHDR_SYN BIT(1) +#define TCPHDR_RST BIT(2) +#define TCPHDR_PSH BIT(3) +#define TCPHDR_ACK BIT(4) +#define TCPHDR_URG BIT(5) +#define TCPHDR_ECE BIT(6) +#define TCPHDR_CWR BIT(7) +#define TCPHDR_AE BIT(8) +#define TCPHDR_FLAGS_MASK (TCPHDR_FIN | TCPHDR_SYN | TCPHDR_RST | \ + TCPHDR_PSH | TCPHDR_ACK | TCPHDR_URG | \ + TCPHDR_ECE | TCPHDR_CWR | TCPHDR_AE) +#define tcp_flags_ntohs(th) (ntohs(*(__be16 *)&tcp_flag_word(th)) & \ + TCPHDR_FLAGS_MASK) + +#define TCPHDR_ACE (TCPHDR_ECE | TCPHDR_CWR | TCPHDR_AE) #define TCPHDR_SYN_ECN (TCPHDR_SYN | TCPHDR_ECE | TCPHDR_CWR) +/* State flags for sacked in struct tcp_skb_cb */ +enum tcp_skb_cb_sacked_flags { + TCPCB_SACKED_ACKED = (1 << 0), /* SKB ACK'd by a SACK block */ + TCPCB_SACKED_RETRANS = (1 << 1), /* SKB retransmitted */ + TCPCB_LOST = (1 << 2), /* SKB is lost */ + TCPCB_TAGBITS = (TCPCB_SACKED_ACKED | TCPCB_SACKED_RETRANS | + TCPCB_LOST), /* All tag bits */ + TCPCB_REPAIRED = (1 << 4), /* SKB repaired (no skb_mstamp_ns) */ + TCPCB_EVER_RETRANS = (1 << 7), /* Ever retransmitted frame */ + TCPCB_RETRANS = (TCPCB_SACKED_RETRANS | TCPCB_EVER_RETRANS | + TCPCB_REPAIRED), +}; + /* 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. @@ -935,35 +1014,25 @@ struct tcp_skb_cb { __u32 seq; /* Starting sequence number */ __u32 end_seq; /* SEQ + FIN + SYN + datalen */ union { - /* Note : tcp_tw_isn is used in input path only - * (isn chosen by tcp_timewait_state_process()) - * + /* Note : * tcp_gso_segs/size are used in write queue only, * cf tcp_skb_pcount()/tcp_skb_mss() */ - __u32 tcp_tw_isn; struct { u16 tcp_gso_segs; u16 tcp_gso_size; }; }; - __u8 tcp_flags; /* TCP header flags. (tcp[13]) */ + __u16 tcp_flags; /* TCP header flags (tcp[12-13])*/ __u8 sacked; /* State flags for SACK. */ -#define TCPCB_SACKED_ACKED 0x01 /* SKB ACK'd by a SACK block */ -#define TCPCB_SACKED_RETRANS 0x02 /* SKB retransmitted */ -#define TCPCB_LOST 0x04 /* SKB is lost */ -#define TCPCB_TAGBITS 0x07 /* All tag bits */ -#define TCPCB_REPAIRED 0x10 /* SKB repaired (no skb_mstamp_ns) */ -#define TCPCB_EVER_RETRANS 0x80 /* Ever retransmitted frame */ -#define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \ - TCPCB_REPAIRED) - __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */ - __u8 txstamp_ack:1, /* Record TX timestamp for ack? */ +#define TSTAMP_ACK_SK 0x1 +#define TSTAMP_ACK_BPF 0x2 + __u8 txstamp_ack:2, /* Record TX timestamp for ack? */ eor:1, /* Is skb MSG_EOR marked? */ has_rxtstamp:1, /* SKB has a RX timestamp */ - unused:5; + unused:4; __u32 ack_seq; /* Sequence number ACK'd */ union { struct { @@ -1068,9 +1137,18 @@ static inline bool tcp_skb_can_collapse_to(const struct sk_buff *skb) static inline bool tcp_skb_can_collapse(const struct sk_buff *to, const struct sk_buff *from) { + /* skb_cmp_decrypted() not needed, use tcp_write_collapse_fence() */ return likely(tcp_skb_can_collapse_to(to) && mptcp_skb_can_collapse(to, from) && - skb_pure_zcopy_same(to, from)); + skb_pure_zcopy_same(to, from) && + skb_frags_readable(to) == skb_frags_readable(from)); +} + +static inline bool tcp_skb_can_collapse_rx(const struct sk_buff *to, + const struct sk_buff *from) +{ + return likely(mptcp_skb_can_collapse(to, from) && + !skb_cmp_decrypted(to, from)); } /* Events passed to congestion control interface */ @@ -1100,9 +1178,9 @@ enum tcp_ca_ack_event_flags { #define TCP_CA_UNSPEC 0 /* Algorithm can be set on socket without CAP_NET_ADMIN privileges */ -#define TCP_CONG_NON_RESTRICTED 0x1 +#define TCP_CONG_NON_RESTRICTED BIT(0) /* Requires ECN/ECT set on all packets */ -#define TCP_CONG_NEEDS_ECN 0x2 +#define TCP_CONG_NEEDS_ECN BIT(1) #define TCP_CONG_MASK (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN) union tcp_cc_info; @@ -1167,7 +1245,7 @@ struct tcp_congestion_ops { /* call when packets are delivered to update cwnd and pacing rate, * after all the ca_state processing. (optional) */ - void (*cong_control)(struct sock *sk, const struct rate_sample *rs); + void (*cong_control)(struct sock *sk, u32 ack, int flag, const struct rate_sample *rs); /* new value of cwnd after loss (required) */ @@ -1218,7 +1296,7 @@ extern struct tcp_congestion_ops tcp_reno; struct tcp_congestion_ops *tcp_ca_find(const char *name); struct tcp_congestion_ops *tcp_ca_find_key(u32 key); -u32 tcp_ca_get_key_by_name(struct net *net, const char *name, bool *ecn_ca); +u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca); #ifdef CONFIG_INET char *tcp_ca_get_name_by_key(u32 key, char *buffer); #else @@ -1416,10 +1494,12 @@ static inline unsigned long tcp_pacing_delay(const struct sock *sk) static inline void tcp_reset_xmit_timer(struct sock *sk, const int what, unsigned long when, - const unsigned long max_when) + bool pace_delay) { - inet_csk_reset_xmit_timer(sk, what, when + tcp_pacing_delay(sk), - max_when); + if (pace_delay) + when += tcp_pacing_delay(sk); + inet_csk_reset_xmit_timer(sk, what, when, + tcp_rto_max(sk)); } /* Something is really bad, we could not queue an additional packet, @@ -1448,7 +1528,7 @@ static inline void tcp_check_probe_timer(struct sock *sk) { if (!tcp_sk(sk)->packets_out && !inet_csk(sk)->icsk_pending) tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, - tcp_probe0_base(sk), TCP_RTO_MAX); + tcp_probe0_base(sk), true); } static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq) @@ -1539,11 +1619,10 @@ static inline int tcp_space_from_win(const struct sock *sk, int win) return __tcp_space_from_win(tcp_sk(sk)->scaling_ratio, win); } -/* Assume a conservative default of 1200 bytes of payload per 4K page. +/* Assume a 50% default for skb->len/skb->truesize ratio. * This may be adjusted later in tcp_measure_rcv_mss(). */ -#define TCP_DEFAULT_SCALING_RATIO ((1200 << TCP_RMEM_TO_WIN_SCALE) / \ - SKB_TRUESIZE(4096)) +#define TCP_DEFAULT_SCALING_RATIO (1 << (TCP_RMEM_TO_WIN_SCALE - 1)) static inline void tcp_scaling_ratio_init(struct sock *sk) { @@ -1811,7 +1890,7 @@ int tcp_sigpool_hash_skb_data(struct tcp_sigpool *hp, * @id: tcp_sigpool that was previously allocated by tcp_sigpool_alloc_ahash() * @c: returned tcp_sigpool for usage (uninitialized on failure) * - * Returns 0 on success, error otherwise. + * Returns: 0 on success, error otherwise. */ int tcp_sigpool_start(unsigned int id, struct tcp_sigpool *c); /** @@ -1858,12 +1937,6 @@ tcp_md5_do_lookup_any_l3index(const struct sock *sk, return __tcp_md5_do_lookup(sk, 0, addr, family, true); } -enum skb_drop_reason -tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, - const void *saddr, const void *daddr, - int family, int l3index, const __u8 *hash_location); - - #define tcp_twsk_md5_key(twsk) ((twsk)->tw_md5_key) #else static inline struct tcp_md5sig_key * @@ -1880,13 +1953,6 @@ tcp_md5_do_lookup_any_l3index(const struct sock *sk, return NULL; } -static inline enum skb_drop_reason -tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, - const void *saddr, const void *daddr, - int family, int l3index, const __u8 *hash_location) -{ - return SKB_NOT_DROPPED_YET; -} #define tcp_twsk_md5_key(twsk) NULL #endif @@ -2098,6 +2164,14 @@ static inline void tcp_rtx_queue_unlink_and_free(struct sk_buff *skb, struct soc tcp_wmem_free_skb(sk, skb); } +static inline void tcp_write_collapse_fence(struct sock *sk) +{ + struct sk_buff *skb = tcp_write_queue_tail(sk); + + if (skb) + TCP_SKB_CB(skb)->eor = 1; +} + static inline void tcp_push_pending_frames(struct sock *sk) { if (tcp_send_head(sk)) { @@ -2195,7 +2269,10 @@ void tcp_v4_destroy_sock(struct sock *sk); struct sk_buff *tcp_gso_segment(struct sk_buff *skb, netdev_features_t features); -struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb); +struct tcphdr *tcp_gro_pull_header(struct sk_buff *skb); +struct sk_buff *tcp_gro_lookup(struct list_head *head, struct tcphdr *th); +struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb, + struct tcphdr *th); INDIRECT_CALLABLE_DECLARE(int tcp4_gro_complete(struct sk_buff *skb, int thoff)); INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb)); INDIRECT_CALLABLE_DECLARE(int tcp6_gro_complete(struct sk_buff *skb, int thoff)); @@ -2284,7 +2361,8 @@ struct tcp_request_sock_ops { struct dst_entry *(*route_req)(const struct sock *sk, struct sk_buff *skb, struct flowi *fl, - struct request_sock *req); + struct request_sock *req, + u32 tw_isn); u32 (*init_seq)(const struct sk_buff *skb); u32 (*init_ts_off)(const struct net *net, const struct sk_buff *skb); int (*send_synack)(const struct sock *sk, struct dst_entry *dst, @@ -2369,21 +2447,15 @@ static inline void tcp_get_current_key(const struct sock *sk, static inline bool tcp_key_is_md5(const struct tcp_key *key) { -#ifdef CONFIG_TCP_MD5SIG - if (static_branch_unlikely(&tcp_md5_needed.key) && - key->type == TCP_KEY_MD5) - return true; -#endif + if (static_branch_tcp_md5()) + return key->type == TCP_KEY_MD5; return false; } static inline bool tcp_key_is_ao(const struct tcp_key *key) { -#ifdef CONFIG_TCP_AO - if (static_branch_unlikely(&tcp_ao_needed.key) && - key->type == TCP_KEY_AO) - return true; -#endif + if (static_branch_tcp_ao()) + return key->type == TCP_KEY_AO; return false; } @@ -2431,14 +2503,35 @@ void tcp_plb_update_state(const struct sock *sk, struct tcp_plb_state *plb, void tcp_plb_check_rehash(struct sock *sk, struct tcp_plb_state *plb); void tcp_plb_update_state_upon_rto(struct sock *sk, struct tcp_plb_state *plb); +static inline void tcp_warn_once(const struct sock *sk, bool cond, const char *str) +{ + WARN_ONCE(cond, + "%scwn:%u out:%u sacked:%u lost:%u retrans:%u tlp_high_seq:%u sk_state:%u ca_state:%u advmss:%u mss_cache:%u pmtu:%u\n", + str, + tcp_snd_cwnd(tcp_sk(sk)), + tcp_sk(sk)->packets_out, tcp_sk(sk)->sacked_out, + tcp_sk(sk)->lost_out, tcp_sk(sk)->retrans_out, + tcp_sk(sk)->tlp_high_seq, sk->sk_state, + inet_csk(sk)->icsk_ca_state, + tcp_sk(sk)->advmss, tcp_sk(sk)->mss_cache, + inet_csk(sk)->icsk_pmtu_cookie); +} + /* At how many usecs into the future should the RTO fire? */ static inline s64 tcp_rto_delta_us(const struct sock *sk) { const struct sk_buff *skb = tcp_rtx_queue_head(sk); u32 rto = inet_csk(sk)->icsk_rto; - u64 rto_time_stamp_us = tcp_skb_timestamp_us(skb) + jiffies_to_usecs(rto); - return rto_time_stamp_us - tcp_sk(sk)->tcp_mstamp; + if (likely(skb)) { + u64 rto_time_stamp_us = tcp_skb_timestamp_us(skb) + jiffies_to_usecs(rto); + + return rto_time_stamp_us - tcp_sk(sk)->tcp_mstamp; + } else { + tcp_warn_once(sk, 1, "rtx queue empty: "); + return jiffies_to_usecs(rto); + } + } /* @@ -2551,8 +2644,8 @@ struct tcp_ulp_ops { /* cleanup ulp */ void (*release)(struct sock *sk); /* diagnostic */ - int (*get_info)(struct sock *sk, struct sk_buff *skb); - size_t (*get_info_size)(const struct sock *sk); + int (*get_info)(struct sock *sk, struct sk_buff *skb, bool net_admin); + size_t (*get_info_size)(const struct sock *sk, bool net_admin); /* clone ulp */ void (*clone)(const struct request_sock *req, struct sock *newsk, const gfp_t priority); @@ -2579,6 +2672,11 @@ struct sk_psock; #ifdef CONFIG_BPF_SYSCALL int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); void tcp_bpf_clone(const struct sock *sk, struct sock *newsk); +#ifdef CONFIG_BPF_STREAM_PARSER +struct strparser; +int tcp_bpf_strp_read_sock(struct strparser *strp, read_descriptor_t *desc, + sk_read_actor_t recv_actor); +#endif /* CONFIG_BPF_STREAM_PARSER */ #endif /* CONFIG_BPF_SYSCALL */ #ifdef CONFIG_INET @@ -2629,6 +2727,7 @@ static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args) memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); if (sk_fullsock(sk)) { sock_ops.is_fullsock = 1; + sock_ops.is_locked_tcp_sock = 1; sock_owned_by_me(sk); } @@ -2706,10 +2805,10 @@ static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk) return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN, 0, NULL) == 1); } -static inline void tcp_bpf_rtt(struct sock *sk) +static inline void tcp_bpf_rtt(struct sock *sk, long mrtt, u32 srtt) { if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_RTT_CB_FLAG)) - tcp_call_bpf(sk, BPF_SOCK_OPS_RTT_CB, 0, NULL); + tcp_call_bpf_2arg(sk, BPF_SOCK_OPS_RTT_CB, mrtt, srtt); } #if IS_ENABLED(CONFIG_SMC) @@ -2717,9 +2816,9 @@ extern struct static_key_false tcp_have_smc; #endif #if IS_ENABLED(CONFIG_TLS_DEVICE) -void clean_acked_data_enable(struct inet_connection_sock *icsk, +void clean_acked_data_enable(struct tcp_sock *tp, void (*cad)(struct sock *sk, u32 ack_seq)); -void clean_acked_data_disable(struct inet_connection_sock *icsk); +void clean_acked_data_disable(struct tcp_sock *tp); void clean_acked_data_flush(void); #endif @@ -2795,66 +2894,9 @@ static inline bool tcp_ao_required(struct sock *sk, const void *saddr, return false; } -/* Called with rcu_read_lock() */ -static inline enum skb_drop_reason -tcp_inbound_hash(struct sock *sk, const struct request_sock *req, - const struct sk_buff *skb, - const void *saddr, const void *daddr, - int family, int dif, int sdif) -{ - const struct tcphdr *th = tcp_hdr(skb); - const struct tcp_ao_hdr *aoh; - const __u8 *md5_location; - int l3index; - - /* Invalid option or two times meet any of auth options */ - if (tcp_parse_auth_options(th, &md5_location, &aoh)) { - tcp_hash_fail("TCP segment has incorrect auth options set", - family, skb, ""); - return SKB_DROP_REASON_TCP_AUTH_HDR; - } - - if (req) { - if (tcp_rsk_used_ao(req) != !!aoh) { - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD); - tcp_hash_fail("TCP connection can't start/end using TCP-AO", - family, skb, "%s", - !aoh ? "missing AO" : "AO signed"); - return SKB_DROP_REASON_TCP_AOFAILURE; - } - } - - /* sdif set, means packet ingressed via a device - * in an L3 domain and dif is set to the l3mdev - */ - l3index = sdif ? dif : 0; - - /* Fast path: unsigned segments */ - if (likely(!md5_location && !aoh)) { - /* Drop if there's TCP-MD5 or TCP-AO key with any rcvid/sndid - * for the remote peer. On TCP-AO established connection - * the last key is impossible to remove, so there's - * always at least one current_key. - */ - if (tcp_ao_required(sk, saddr, family, l3index, true)) { - tcp_hash_fail("AO hash is required, but not found", - family, skb, "L3 index %d", l3index); - return SKB_DROP_REASON_TCP_AONOTFOUND; - } - if (unlikely(tcp_md5_do_lookup(sk, l3index, saddr, family))) { - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); - tcp_hash_fail("MD5 Hash not found", - family, skb, "L3 index %d", l3index); - return SKB_DROP_REASON_TCP_MD5NOTFOUND; - } - return SKB_NOT_DROPPED_YET; - } - - if (aoh) - return tcp_inbound_ao_hash(sk, skb, family, req, l3index, aoh); - - return tcp_inbound_md5_hash(sk, skb, saddr, daddr, family, - l3index, md5_location); -} +enum skb_drop_reason tcp_inbound_hash(struct sock *sk, + const struct request_sock *req, const struct sk_buff *skb, + const void *saddr, const void *daddr, + int family, int dif, int sdif); #endif /* _TCP_H */ diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h index 471e177362b4..df655ce6987d 100644 --- a/include/net/tcp_ao.h +++ b/include/net/tcp_ao.h @@ -19,6 +19,11 @@ struct tcp_ao_hdr { u8 rnext_keyid; }; +static inline u8 tcp_ao_hdr_maclen(const struct tcp_ao_hdr *aoh) +{ + return aoh->length - sizeof(struct tcp_ao_hdr); +} + struct tcp_ao_counters { atomic64_t pkt_good; atomic64_t pkt_bad; @@ -86,7 +91,8 @@ static inline int tcp_ao_sizeof_key(const struct tcp_ao_key *key) struct tcp_ao_info { /* List of tcp_ao_key's */ struct hlist_head head; - /* current_key and rnext_key aren't maintained on listen sockets. + /* current_key and rnext_key are maintained on sockets + * in TCP_AO_ESTABLISHED states. * Their purpose is to cache keys on established connections, * saving needless lookups. Never dereference any of them from * listen sockets. @@ -143,43 +149,6 @@ extern struct static_key_false_deferred tcp_ao_needed; #define static_branch_tcp_ao() false #endif -static inline bool tcp_hash_should_produce_warnings(void) -{ - return static_branch_tcp_md5() || static_branch_tcp_ao(); -} - -#define tcp_hash_fail(msg, family, skb, fmt, ...) \ -do { \ - const struct tcphdr *th = tcp_hdr(skb); \ - char hdr_flags[6]; \ - char *f = hdr_flags; \ - \ - if (!tcp_hash_should_produce_warnings()) \ - break; \ - if (th->fin) \ - *f++ = 'F'; \ - if (th->syn) \ - *f++ = 'S'; \ - if (th->rst) \ - *f++ = 'R'; \ - if (th->psh) \ - *f++ = 'P'; \ - if (th->ack) \ - *f++ = '.'; \ - *f = 0; \ - if ((family) == AF_INET) { \ - net_info_ratelimited("%s for %pI4.%d->%pI4.%d [%s] " fmt "\n", \ - msg, &ip_hdr(skb)->saddr, ntohs(th->source), \ - &ip_hdr(skb)->daddr, ntohs(th->dest), \ - hdr_flags, ##__VA_ARGS__); \ - } else { \ - net_info_ratelimited("%s for [%pI6c].%d->[%pI6c].%d [%s]" fmt "\n", \ - msg, &ipv6_hdr(skb)->saddr, ntohs(th->source), \ - &ipv6_hdr(skb)->daddr, ntohs(th->dest), \ - hdr_flags, ##__VA_ARGS__); \ - } \ -} while (0) - #ifdef CONFIG_TCP_AO /* TCP-AO structures and functions */ struct tcp4_ao_context { @@ -201,9 +170,9 @@ struct tcp6_ao_context { }; struct tcp_sigpool; +/* Established states are fast-path and there always is current_key/rnext_key */ #define TCP_AO_ESTABLISHED (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | \ - TCPF_CLOSE | TCPF_CLOSE_WAIT | \ - TCPF_LAST_ACK | TCPF_CLOSING) + TCPF_CLOSE_WAIT | TCPF_LAST_ACK | TCPF_CLOSING) int tcp_ao_transmit_skb(struct sock *sk, struct sk_buff *skb, struct tcp_ao_key *key, struct tcphdr *th, @@ -214,7 +183,8 @@ int tcp_ao_hash_skb(unsigned short int family, const u8 *tkey, int hash_offset, u32 sne); int tcp_parse_ao(struct sock *sk, int cmd, unsigned short int family, sockptr_t optval, int optlen); -struct tcp_ao_key *tcp_ao_established_key(struct tcp_ao_info *ao, +struct tcp_ao_key *tcp_ao_established_key(const struct sock *sk, + struct tcp_ao_info *ao, int sndid, int rcvid); int tcp_ao_copy_all_matching(const struct sock *sk, struct sock *newsk, struct request_sock *req, struct sk_buff *skb, diff --git a/include/net/tcx.h b/include/net/tcx.h index 04be9377785d..5ce0ce9e0c02 100644 --- a/include/net/tcx.h +++ b/include/net/tcx.h @@ -13,7 +13,7 @@ struct mini_Qdisc; struct tcx_entry { struct mini_Qdisc __rcu *miniq; struct bpf_mprog_bundle bundle; - bool miniq_active; + u32 miniq_active; struct rcu_head rcu; }; @@ -75,9 +75,9 @@ tcx_entry_fetch(struct net_device *dev, bool ingress) return rcu_dereference_rtnl(dev->tcx_egress); } -static inline struct bpf_mprog_entry *tcx_entry_create(void) +static inline struct bpf_mprog_entry *tcx_entry_create_noprof(void) { - struct tcx_entry *tcx = kzalloc(sizeof(*tcx), GFP_KERNEL); + struct tcx_entry *tcx = kzalloc_noprof(sizeof(*tcx), GFP_KERNEL); if (tcx) { bpf_mprog_bundle_init(&tcx->bundle); @@ -85,6 +85,7 @@ static inline struct bpf_mprog_entry *tcx_entry_create(void) } return NULL; } +#define tcx_entry_create(...) alloc_hooks(tcx_entry_create_noprof(__VA_ARGS__)) static inline void tcx_entry_free(struct bpf_mprog_entry *entry) { @@ -124,11 +125,16 @@ static inline void tcx_skeys_dec(bool ingress) tcx_dec(); } -static inline void tcx_miniq_set_active(struct bpf_mprog_entry *entry, - const bool active) +static inline void tcx_miniq_inc(struct bpf_mprog_entry *entry) { ASSERT_RTNL(); - tcx_entry(entry)->miniq_active = active; + tcx_entry(entry)->miniq_active++; +} + +static inline void tcx_miniq_dec(struct bpf_mprog_entry *entry) +{ + ASSERT_RTNL(); + tcx_entry(entry)->miniq_active--; } static inline bool tcx_entry_is_active(struct bpf_mprog_entry *entry) diff --git a/include/net/timewait_sock.h b/include/net/timewait_sock.h index 74d2b463cc95..62b3e9f2aed4 100644 --- a/include/net/timewait_sock.h +++ b/include/net/timewait_sock.h @@ -15,18 +15,9 @@ struct timewait_sock_ops { struct kmem_cache *twsk_slab; char *twsk_slab_name; unsigned int twsk_obj_size; - int (*twsk_unique)(struct sock *sk, - struct sock *sktw, void *twp); void (*twsk_destructor)(struct sock *sk); }; -static inline int twsk_unique(struct sock *sk, struct sock *sktw, void *twp) -{ - if (sk->sk_prot->twsk_prot->twsk_unique != NULL) - return sk->sk_prot->twsk_prot->twsk_unique(sk, sktw, twp); - return 0; -} - static inline void twsk_destructor(struct sock *sk) { if (sk->sk_prot->twsk_prot->twsk_destructor != NULL) diff --git a/include/net/tls.h b/include/net/tls.h index 33f657d3c051..857340338b69 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -59,6 +59,8 @@ struct tls_rec; #define TLS_CRYPTO_INFO_READY(info) ((info)->cipher_type) +#define TLS_HANDSHAKE_KEYUPDATE 24 /* rfc8446 B.3: Key update */ + #define TLS_AAD_SPACE_SIZE 13 #define TLS_MAX_IV_SIZE 16 @@ -130,6 +132,7 @@ struct tls_sw_context_rx { u8 async_capable:1; u8 zc_capable:1; u8 reader_contended:1; + bool key_update_pending; struct tls_strparser strp; @@ -362,7 +365,7 @@ static inline bool tls_is_skb_tx_device_offloaded(const struct sk_buff *skb) static inline struct tls_context *tls_get_ctx(const struct sock *sk) { - struct inet_connection_sock *icsk = inet_csk(sk); + const struct inet_connection_sock *icsk = inet_csk(sk); /* Use RCU on icsk_ulp_data only for sock diag code, * TLS data path doesn't need rcu_dereference(). @@ -390,8 +393,12 @@ tls_offload_ctx_tx(const struct tls_context *tls_ctx) static inline bool tls_sw_has_ctx_tx(const struct sock *sk) { - struct tls_context *ctx = tls_get_ctx(sk); + struct tls_context *ctx; + + if (!sk_is_inet(sk) || !inet_test_bit(IS_ICSK, sk)) + return false; + ctx = tls_get_ctx(sk); if (!ctx) return false; return !!tls_sw_ctx_tx(ctx); @@ -399,8 +406,12 @@ static inline bool tls_sw_has_ctx_tx(const struct sock *sk) static inline bool tls_sw_has_ctx_rx(const struct sock *sk) { - struct tls_context *ctx = tls_get_ctx(sk); + struct tls_context *ctx; + + if (!sk_is_inet(sk) || !inet_test_bit(IS_ICSK, sk)) + return false; + ctx = tls_get_ctx(sk); if (!ctx) return false; return !!tls_sw_ctx_rx(ctx); diff --git a/include/net/udp.h b/include/net/udp.h index 488a6d2babcc..a772510b2aa5 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -50,39 +50,68 @@ struct udp_skb_cb { #define UDP_SKB_CB(__skb) ((struct udp_skb_cb *)((__skb)->cb)) /** - * struct udp_hslot - UDP hash slot + * struct udp_hslot - UDP hash slot used by udp_table.hash/hash4 * * @head: head of list of sockets + * @nulls_head: head of list of sockets, only used by hash4 * @count: number of sockets in 'head' list * @lock: spinlock protecting changes to head/count */ struct udp_hslot { - struct hlist_head head; + union { + struct hlist_head head; + /* hash4 uses hlist_nulls to avoid moving wrongly onto another + * hlist, because rehash() can happen with lookup(). + */ + struct hlist_nulls_head nulls_head; + }; int count; spinlock_t lock; -} __attribute__((aligned(2 * sizeof(long)))); +} __aligned(2 * sizeof(long)); + +/** + * struct udp_hslot_main - UDP hash slot used by udp_table.hash2 + * + * @hslot: basic hash slot + * @hash4_cnt: number of sockets in hslot4 of the same + * (local port, local address) + */ +struct udp_hslot_main { + struct udp_hslot hslot; /* must be the first member */ +#if !IS_ENABLED(CONFIG_BASE_SMALL) + u32 hash4_cnt; +#endif +} __aligned(2 * sizeof(long)); +#define UDP_HSLOT_MAIN(__hslot) ((struct udp_hslot_main *)(__hslot)) /** * struct udp_table - UDP table * * @hash: hash table, sockets are hashed on (local port) * @hash2: hash table, sockets are hashed on (local port, local address) + * @hash4: hash table, connected sockets are hashed on + * (local port, local address, remote port, remote address) * @mask: number of slots in hash tables, minus 1 * @log: log2(number of slots in hash table) */ struct udp_table { struct udp_hslot *hash; - struct udp_hslot *hash2; + struct udp_hslot_main *hash2; +#if !IS_ENABLED(CONFIG_BASE_SMALL) + struct udp_hslot *hash4; +#endif unsigned int mask; unsigned int log; }; extern struct udp_table udp_table; void udp_table_init(struct udp_table *, const char *); static inline struct udp_hslot *udp_hashslot(struct udp_table *table, - struct net *net, unsigned int num) + const struct net *net, + unsigned int num) { return &table->hash[udp_hashfn(net, num, table->mask)]; } + /* * For secondary hash, net_hash_mix() is performed before calling * udp_hashslot2(), this explains difference with udp_hashslot() @@ -90,9 +119,90 @@ static inline struct udp_hslot *udp_hashslot(struct udp_table *table, static inline struct udp_hslot *udp_hashslot2(struct udp_table *table, unsigned int hash) { - return &table->hash2[hash & table->mask]; + return &table->hash2[hash & table->mask].hslot; +} + +#if IS_ENABLED(CONFIG_BASE_SMALL) +static inline void udp_table_hash4_init(struct udp_table *table) +{ +} + +static inline struct udp_hslot *udp_hashslot4(struct udp_table *table, + unsigned int hash) +{ + BUILD_BUG(); + return NULL; +} + +static inline bool udp_hashed4(const struct sock *sk) +{ + return false; +} + +static inline unsigned int udp_hash4_slot_size(void) +{ + return 0; +} + +static inline bool udp_has_hash4(const struct udp_hslot *hslot2) +{ + return false; +} + +static inline void udp_hash4_inc(struct udp_hslot *hslot2) +{ } +static inline void udp_hash4_dec(struct udp_hslot *hslot2) +{ +} +#else /* !CONFIG_BASE_SMALL */ + +/* Must be called with table->hash2 initialized */ +static inline void udp_table_hash4_init(struct udp_table *table) +{ + table->hash4 = (void *)(table->hash2 + (table->mask + 1)); + for (int i = 0; i <= table->mask; i++) { + table->hash2[i].hash4_cnt = 0; + + INIT_HLIST_NULLS_HEAD(&table->hash4[i].nulls_head, i); + table->hash4[i].count = 0; + spin_lock_init(&table->hash4[i].lock); + } +} + +static inline struct udp_hslot *udp_hashslot4(struct udp_table *table, + unsigned int hash) +{ + return &table->hash4[hash & table->mask]; +} + +static inline bool udp_hashed4(const struct sock *sk) +{ + return !hlist_nulls_unhashed(&udp_sk(sk)->udp_lrpa_node); +} + +static inline unsigned int udp_hash4_slot_size(void) +{ + return sizeof(struct udp_hslot); +} + +static inline bool udp_has_hash4(const struct udp_hslot *hslot2) +{ + return UDP_HSLOT_MAIN(hslot2)->hash4_cnt; +} + +static inline void udp_hash4_inc(struct udp_hslot *hslot2) +{ + UDP_HSLOT_MAIN(hslot2)->hash4_cnt++; +} + +static inline void udp_hash4_dec(struct udp_hslot *hslot2) +{ + UDP_HSLOT_MAIN(hslot2)->hash4_cnt--; +} +#endif /* CONFIG_BASE_SMALL */ + extern struct proto udp_prot; extern atomic_long_t udp_memory_allocated; @@ -180,6 +290,7 @@ static inline void udp_lib_init_sock(struct sock *sk) struct udp_sock *up = udp_sk(sk); skb_queue_head_init(&up->reader_queue); + INIT_HLIST_NODE(&up->tunnel_list); up->forward_threshold = sk->sk_rcvbuf >> 2; set_bit(SOCK_CUSTOM_SOCKOPT, &sk->sk_socket->flags); } @@ -192,13 +303,29 @@ static inline int udp_lib_hash(struct sock *sk) } void udp_lib_unhash(struct sock *sk); -void udp_lib_rehash(struct sock *sk, u16 new_hash); +void udp_lib_rehash(struct sock *sk, u16 new_hash, u16 new_hash4); +u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, + const __be32 faddr, const __be16 fport); static inline void udp_lib_close(struct sock *sk, long timeout) { sk_common_release(sk); } +/* hash4 routines shared between UDPv4/6 */ +#if IS_ENABLED(CONFIG_BASE_SMALL) +static inline void udp_lib_hash4(struct sock *sk, u16 hash) +{ +} + +static inline void udp4_hash4(struct sock *sk) +{ +} +#else /* !CONFIG_BASE_SMALL */ +void udp_lib_hash4(struct sock *sk, u16 hash); +void udp4_hash4(struct sock *sk); +#endif /* CONFIG_BASE_SMALL */ + int udp_lib_get_port(struct sock *sk, unsigned short snum, unsigned int hash2_nulladdr); @@ -231,7 +358,7 @@ static inline __be16 udp_flow_src_port(struct net *net, struct sk_buff *skb, } /* Since this is being sent on the wire obfuscate hash a bit - * to minimize possbility that any useful information to an + * to minimize possibility that any useful information to an * attacker is leaked. Only upper 16 bits are relevant in the * computation for 16 bit port value. */ @@ -245,7 +372,7 @@ static inline int udp_rqueue_get(struct sock *sk) return sk_rmem_alloc_get(sk) - READ_ONCE(udp_sk(sk)->forward_deficit); } -static inline bool udp_sk_bound_dev_eq(struct net *net, int bound_dev_if, +static inline bool udp_sk_bound_dev_eq(const struct net *net, int bound_dev_if, int dif, int sdif) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) @@ -296,18 +423,19 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, int udp_lib_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen, int (*push_pending_frames)(struct sock *)); -struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, +struct sock *udp4_lib_lookup(const struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif); -struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, +struct sock *__udp4_lib_lookup(const struct net *net, __be32 saddr, + __be16 sport, __be32 daddr, __be16 dport, int dif, int sdif, struct udp_table *tbl, struct sk_buff *skb); struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport); -struct sock *udp6_lib_lookup(struct net *net, +struct sock *udp6_lib_lookup(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif); -struct sock *__udp6_lib_lookup(struct net *net, +struct sock *__udp6_lib_lookup(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif, int sdif, struct udp_table *tbl, @@ -379,14 +507,7 @@ static inline bool udp_skb_is_linear(struct sk_buff *skb) static inline int copy_linear_skb(struct sk_buff *skb, int len, int off, struct iov_iter *to) { - int n; - - n = copy_to_iter(skb->data + off, len, to); - if (n == len) - return 0; - - iov_iter_revert(to, n); - return -EFAULT; + return copy_to_iter_full(skb->data + off, len, to) ? 0 : -EFAULT; } /* diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index d716214fe03d..2df3b8344eb5 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -179,8 +179,8 @@ struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb, struct dst_cache *dst_cache); struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, - __be16 flags, __be64 tunnel_id, - int md_size); + const unsigned long *flags, + __be64 tunnel_id, int md_size); #ifdef CONFIG_INET static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum) @@ -191,6 +191,21 @@ static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum) } #endif +#if IS_ENABLED(CONFIG_NET_UDP_TUNNEL) +void udp_tunnel_update_gro_lookup(struct net *net, struct sock *sk, bool add); +void udp_tunnel_update_gro_rcv(struct sock *sk, bool add); +#else +static inline void udp_tunnel_update_gro_lookup(struct net *net, + struct sock *sk, bool add) {} +static inline void udp_tunnel_update_gro_rcv(struct sock *sk, bool add) {} +#endif + +static inline void udp_tunnel_cleanup_gro(struct sock *sk) +{ + udp_tunnel_update_gro_rcv(sk, false); + udp_tunnel_update_gro_lookup(sock_net(sk), sk, false); +} + static inline void udp_tunnel_encap_enable(struct sock *sk) { if (udp_test_and_set_bit(ENCAP_ENABLED, sk)) diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 33ba6fc151cf..e2f7ca045d3e 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -227,6 +227,7 @@ struct vxlan_config { unsigned int addrmax; bool no_share; enum ifla_vxlan_df df; + struct vxlanhdr reserved_bits; }; enum { @@ -295,7 +296,7 @@ struct vxlan_dev { struct vxlan_rdst default_dst; /* default destination */ struct timer_list age_timer; - spinlock_t hash_lock[FDB_HASH_SIZE]; + spinlock_t hash_lock; unsigned int addrcnt; struct gro_cells gro_cells; @@ -303,9 +304,10 @@ struct vxlan_dev { struct vxlan_vni_group __rcu *vnigrp; - struct hlist_head fdb_head[FDB_HASH_SIZE]; + struct rhashtable fdb_hash_tbl; struct rhashtable mdb_tbl; + struct hlist_head fdb_list; struct hlist_head mdb_list; unsigned int mdb_seq; }; diff --git a/include/net/x25.h b/include/net/x25.h index 597eb53c471e..5e833cfc864e 100644 --- a/include/net/x25.h +++ b/include/net/x25.h @@ -81,7 +81,7 @@ enum { #define X25_DEFAULT_WINDOW_SIZE 2 /* Default Window Size */ #define X25_DEFAULT_PACKET_SIZE X25_PS128 /* Default Packet Size */ -#define X25_DEFAULT_THROUGHPUT 0x0A /* Deafult Throughput */ +#define X25_DEFAULT_THROUGHPUT 0x0A /* Default Throughput */ #define X25_DEFAULT_REVERSE 0x00 /* Default Reverse Charging */ #define X25_SMODULUS 8 diff --git a/include/net/xdp.h b/include/net/xdp.h index e6770dd40c91..b40f1f96cb11 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -11,6 +11,8 @@ #include <linux/netdevice.h> #include <linux/skbuff.h> /* skb_shared_info */ +#include <net/page_pool/types.h> + /** * DOC: XDP RX-queue information * @@ -62,7 +64,6 @@ struct xdp_rxq_info { u32 queue_index; u32 reg_state; struct xdp_mem_info mem; - unsigned int napi_id; u32 frag_size; } ____cacheline_aligned; /* perf critical, avoid false-sharing */ @@ -88,7 +89,7 @@ struct xdp_buff { u32 flags; /* supported values defined in xdp_buff_flags */ }; -static __always_inline bool xdp_buff_has_frags(struct xdp_buff *xdp) +static __always_inline bool xdp_buff_has_frags(const struct xdp_buff *xdp) { return !!(xdp->flags & XDP_FLAGS_HAS_FRAGS); } @@ -103,7 +104,8 @@ static __always_inline void xdp_buff_clear_frags_flag(struct xdp_buff *xdp) xdp->flags &= ~XDP_FLAGS_HAS_FRAGS; } -static __always_inline bool xdp_buff_is_frag_pfmemalloc(struct xdp_buff *xdp) +static __always_inline bool +xdp_buff_is_frag_pfmemalloc(const struct xdp_buff *xdp) { return !!(xdp->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC); } @@ -144,15 +146,16 @@ xdp_prepare_buff(struct xdp_buff *xdp, unsigned char *hard_start, SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) static inline struct skb_shared_info * -xdp_get_shared_info_from_buff(struct xdp_buff *xdp) +xdp_get_shared_info_from_buff(const struct xdp_buff *xdp) { return (struct skb_shared_info *)xdp_data_hard_end(xdp); } -static __always_inline unsigned int xdp_get_buff_len(struct xdp_buff *xdp) +static __always_inline unsigned int +xdp_get_buff_len(const struct xdp_buff *xdp) { unsigned int len = xdp->data_end - xdp->data; - struct skb_shared_info *sinfo; + const struct skb_shared_info *sinfo; if (likely(!xdp_buff_has_frags(xdp))) goto out; @@ -163,26 +166,114 @@ out: return len; } +void xdp_return_frag(netmem_ref netmem, const struct xdp_buff *xdp); + +/** + * __xdp_buff_add_frag - attach frag to &xdp_buff + * @xdp: XDP buffer to attach the frag to + * @netmem: network memory containing the frag + * @offset: offset at which the frag starts + * @size: size of the frag + * @truesize: total memory size occupied by the frag + * @try_coalesce: whether to try coalescing the frags (not valid for XSk) + * + * Attach frag to the XDP buffer. If it currently has no frags attached, + * initialize the related fields, otherwise check that the frag number + * didn't reach the limit of ``MAX_SKB_FRAGS``. If possible, try coalescing + * the frag with the previous one. + * The function doesn't check/update the pfmemalloc bit. Please use the + * non-underscored wrapper in drivers. + * + * Return: true on success, false if there's no space for the frag in + * the shared info struct. + */ +static inline bool __xdp_buff_add_frag(struct xdp_buff *xdp, netmem_ref netmem, + u32 offset, u32 size, u32 truesize, + bool try_coalesce) +{ + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); + skb_frag_t *prev; + u32 nr_frags; + + if (!xdp_buff_has_frags(xdp)) { + xdp_buff_set_frags_flag(xdp); + + nr_frags = 0; + sinfo->xdp_frags_size = 0; + sinfo->xdp_frags_truesize = 0; + + goto fill; + } + + nr_frags = sinfo->nr_frags; + prev = &sinfo->frags[nr_frags - 1]; + + if (try_coalesce && netmem == skb_frag_netmem(prev) && + offset == skb_frag_off(prev) + skb_frag_size(prev)) { + skb_frag_size_add(prev, size); + /* Guaranteed to only decrement the refcount */ + xdp_return_frag(netmem, xdp); + } else if (unlikely(nr_frags == MAX_SKB_FRAGS)) { + return false; + } else { +fill: + __skb_fill_netmem_desc_noacc(sinfo, nr_frags++, netmem, + offset, size); + } + + sinfo->nr_frags = nr_frags; + sinfo->xdp_frags_size += size; + sinfo->xdp_frags_truesize += truesize; + + return true; +} + +/** + * xdp_buff_add_frag - attach frag to &xdp_buff + * @xdp: XDP buffer to attach the frag to + * @netmem: network memory containing the frag + * @offset: offset at which the frag starts + * @size: size of the frag + * @truesize: total memory size occupied by the frag + * + * Version of __xdp_buff_add_frag() which takes care of the pfmemalloc bit. + * + * Return: true on success, false if there's no space for the frag in + * the shared info struct. + */ +static inline bool xdp_buff_add_frag(struct xdp_buff *xdp, netmem_ref netmem, + u32 offset, u32 size, u32 truesize) +{ + if (!__xdp_buff_add_frag(xdp, netmem, offset, size, truesize, true)) + return false; + + if (unlikely(netmem_is_pfmemalloc(netmem))) + xdp_buff_set_frag_pfmemalloc(xdp); + + return true; +} + struct xdp_frame { void *data; - u16 len; - u16 headroom; + u32 len; + u32 headroom; u32 metasize; /* uses lower 8-bits */ /* Lifetime of xdp_rxq_info is limited to NAPI/enqueue time, - * while mem info is valid on remote CPU. + * while mem_type is valid on remote CPU. */ - struct xdp_mem_info mem; + enum xdp_mem_type mem_type:32; struct net_device *dev_rx; /* used by cpumap */ u32 frame_sz; u32 flags; /* supported values defined in xdp_buff_flags */ }; -static __always_inline bool xdp_frame_has_frags(struct xdp_frame *frame) +static __always_inline bool xdp_frame_has_frags(const struct xdp_frame *frame) { return !!(frame->flags & XDP_FLAGS_HAS_FRAGS); } -static __always_inline bool xdp_frame_is_frag_pfmemalloc(struct xdp_frame *frame) +static __always_inline bool +xdp_frame_is_frag_pfmemalloc(const struct xdp_frame *frame) { return !!(frame->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC); } @@ -190,18 +281,16 @@ static __always_inline bool xdp_frame_is_frag_pfmemalloc(struct xdp_frame *frame #define XDP_BULK_QUEUE_SIZE 16 struct xdp_frame_bulk { int count; - void *xa; - void *q[XDP_BULK_QUEUE_SIZE]; + netmem_ref q[XDP_BULK_QUEUE_SIZE]; }; static __always_inline void xdp_frame_bulk_init(struct xdp_frame_bulk *bq) { - /* bq->count will be zero'ed when bq->xa gets updated */ - bq->xa = NULL; + bq->count = 0; } static inline struct skb_shared_info * -xdp_get_shared_info_from_frame(struct xdp_frame *frame) +xdp_get_shared_info_from_frame(const struct xdp_frame *frame) { void *data_hard_start = frame->data - frame->headroom - sizeof(*frame); @@ -227,7 +316,14 @@ xdp_update_skb_shared_info(struct sk_buff *skb, u8 nr_frags, unsigned int size, unsigned int truesize, bool pfmemalloc) { - skb_shinfo(skb)->nr_frags = nr_frags; + struct skb_shared_info *sinfo = skb_shinfo(skb); + + sinfo->nr_frags = nr_frags; + /* + * ``destructor_arg`` is unionized with ``xdp_frags_{,true}size``, + * reset it after that these fields aren't used anymore. + */ + sinfo->destructor_arg = NULL; skb->len += size; skb->data_len += size; @@ -239,17 +335,19 @@ xdp_update_skb_shared_info(struct sk_buff *skb, u8 nr_frags, void xdp_warn(const char *msg, const char *func, const int line); #define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__) +struct sk_buff *xdp_build_skb_from_buff(const struct xdp_buff *xdp); +struct sk_buff *xdp_build_skb_from_zc(struct xdp_buff *xdp); struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp); struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct sk_buff *skb, struct net_device *dev); struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct net_device *dev); -int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp); struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf); static inline -void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp) +void xdp_convert_frame_to_buff(const struct xdp_frame *frame, + struct xdp_buff *xdp) { xdp->data_hard_start = frame->data - frame->headroom - sizeof(*frame); xdp->data = frame->data; @@ -260,7 +358,7 @@ void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp) } static inline -int xdp_update_frame_from_buff(struct xdp_buff *xdp, +int xdp_update_frame_from_buff(const struct xdp_buff *xdp, struct xdp_frame *xdp_frame) { int metasize, headroom; @@ -302,24 +400,33 @@ struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp) if (unlikely(xdp_update_frame_from_buff(xdp, xdp_frame) < 0)) return NULL; - /* rxq only valid until napi_schedule ends, convert to xdp_mem_info */ - xdp_frame->mem = xdp->rxq->mem; + /* rxq only valid until napi_schedule ends, convert to xdp_mem_type */ + xdp_frame->mem_type = xdp->rxq->mem.type; return xdp_frame; } -void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, - struct xdp_buff *xdp); +void __xdp_return(netmem_ref netmem, enum xdp_mem_type mem_type, + bool napi_direct, struct xdp_buff *xdp); void xdp_return_frame(struct xdp_frame *xdpf); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf); void xdp_return_buff(struct xdp_buff *xdp); -void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq); void xdp_return_frame_bulk(struct xdp_frame *xdpf, struct xdp_frame_bulk *bq); -static __always_inline unsigned int xdp_get_frame_len(struct xdp_frame *xdpf) +static inline void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq) +{ + if (unlikely(!bq->count)) + return; + + page_pool_put_netmem_bulk(bq->q, bq->count); + bq->count = 0; +} + +static __always_inline unsigned int +xdp_get_frame_len(const struct xdp_frame *xdpf) { - struct skb_shared_info *sinfo; + const struct skb_shared_info *sinfo; unsigned int len = xdpf->len; if (likely(!xdp_frame_has_frags(xdpf))) @@ -351,6 +458,38 @@ void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq); int xdp_reg_mem_model(struct xdp_mem_info *mem, enum xdp_mem_type type, void *allocator); void xdp_unreg_mem_model(struct xdp_mem_info *mem); +int xdp_reg_page_pool(struct page_pool *pool); +void xdp_unreg_page_pool(const struct page_pool *pool); +void xdp_rxq_info_attach_page_pool(struct xdp_rxq_info *xdp_rxq, + const struct page_pool *pool); + +/** + * xdp_rxq_info_attach_mem_model - attach registered mem info to RxQ info + * @xdp_rxq: XDP RxQ info to attach the memory info to + * @mem: already registered memory info + * + * If the driver registers its memory providers manually, it must use this + * function instead of xdp_rxq_info_reg_mem_model(). + */ +static inline void +xdp_rxq_info_attach_mem_model(struct xdp_rxq_info *xdp_rxq, + const struct xdp_mem_info *mem) +{ + xdp_rxq->mem = *mem; +} + +/** + * xdp_rxq_info_detach_mem_model - detach registered mem info from RxQ info + * @xdp_rxq: XDP RxQ info to detach the memory info from + * + * If the driver registers its memory providers manually and then attaches it + * via xdp_rxq_info_attach_mem_model(), it must call this function before + * xdp_rxq_info_unreg(). + */ +static inline void xdp_rxq_info_detach_mem_model(struct xdp_rxq_info *xdp_rxq) +{ + xdp_rxq->mem = (struct xdp_mem_info){ }; +} /* Drivers not supporting XDP metadata can use this helper, which * rejects any room expansion for metadata as a result. @@ -477,8 +616,12 @@ struct xdp_metadata_ops { u32 bpf_xdp_metadata_kfunc_id(int id); bool bpf_dev_bound_kfunc_id(u32 btf_id); void xdp_set_features_flag(struct net_device *dev, xdp_features_t val); +void xdp_set_features_flag_locked(struct net_device *dev, xdp_features_t val); void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg); +void xdp_features_set_redirect_target_locked(struct net_device *dev, + bool support_sg); void xdp_features_clear_redirect_target(struct net_device *dev); +void xdp_features_clear_redirect_target_locked(struct net_device *dev); #else static inline u32 bpf_xdp_metadata_kfunc_id(int id) { return 0; } static inline bool bpf_dev_bound_kfunc_id(u32 btf_id) { return false; } diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 3d54de168a6d..e8bd6ddb7b12 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -71,9 +71,6 @@ struct xdp_sock { */ u32 tx_budget_spent; - /* Protects generic receive. */ - spinlock_t rx_lock; - /* Statistics */ u64 rx_dropped; u64 rx_queue_full; @@ -110,18 +107,23 @@ struct xdp_sock { * indicates position where checksumming should start. * csum_offset indicates position where checksum should be stored. * + * void (*tmo_request_launch_time)(u64 launch_time, void *priv) + * Called when AF_XDP frame requested launch time HW offload support. + * launch_time indicates the PTP time at which the device can schedule the + * packet for transmission. */ struct xsk_tx_metadata_ops { void (*tmo_request_timestamp)(void *priv); u64 (*tmo_fill_timestamp)(void *priv); void (*tmo_request_checksum)(u16 csum_start, u16 csum_offset, void *priv); + void (*tmo_request_launch_time)(u64 launch_time, void *priv); }; #ifdef CONFIG_XDP_SOCKETS int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp); int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp); -void __xsk_map_flush(void); +void __xsk_map_flush(struct list_head *flush_list); /** * xsk_tx_metadata_to_compl - Save enough relevant metadata information @@ -162,6 +164,11 @@ static inline void xsk_tx_metadata_request(const struct xsk_tx_metadata *meta, if (!meta) return; + if (ops->tmo_request_launch_time) + if (meta->flags & XDP_TXMD_FLAGS_LAUNCH_TIME) + ops->tmo_request_launch_time(meta->request.launch_time, + priv); + if (ops->tmo_request_timestamp) if (meta->flags & XDP_TXMD_FLAGS_TIMESTAMP) ops->tmo_request_timestamp(priv); @@ -206,7 +213,7 @@ static inline int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp) return -EOPNOTSUPP; } -static inline void __xsk_map_flush(void) +static inline void __xsk_map_flush(struct list_head *flush_list) { } @@ -228,14 +235,4 @@ static inline void xsk_tx_metadata_complete(struct xsk_tx_metadata_compl *compl, } #endif /* CONFIG_XDP_SOCKETS */ - -#if defined(CONFIG_XDP_SOCKETS) && defined(CONFIG_DEBUG_NET) -bool xsk_map_check_flush(void); -#else -static inline bool xsk_map_check_flush(void) -{ - return false; -} -#endif - #endif /* _LINUX_XDP_SOCK_H */ diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index c9aec9ab6191..513c8e9704f6 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -59,15 +59,6 @@ static inline void xsk_pool_fill_cb(struct xsk_buff_pool *pool, xp_fill_cb(pool, desc); } -static inline unsigned int xsk_pool_get_napi_id(struct xsk_buff_pool *pool) -{ -#ifdef CONFIG_NET_RX_BUSY_POLL - return pool->heads[0].xdp.rxq->napi_id; -#else - return 0; -#endif -} - static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs) { @@ -101,7 +92,7 @@ static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool) return xp_alloc(pool); } -static inline bool xsk_is_eop_desc(struct xdp_desc *desc) +static inline bool xsk_is_eop_desc(const struct xdp_desc *desc) { return !xp_mb_desc(desc); } @@ -126,8 +117,8 @@ static inline void xsk_buff_free(struct xdp_buff *xdp) if (likely(!xdp_buff_has_frags(xdp))) goto out; - list_for_each_entry_safe(pos, tmp, xskb_list, xskb_list_node) { - list_del(&pos->xskb_list_node); + list_for_each_entry_safe(pos, tmp, xskb_list, list_node) { + list_del(&pos->list_node); xp_free(pos); } @@ -136,23 +127,33 @@ out: xp_free(xskb); } -static inline void xsk_buff_add_frag(struct xdp_buff *xdp) +static inline bool xsk_buff_add_frag(struct xdp_buff *head, + struct xdp_buff *xdp) { - struct xdp_buff_xsk *frag = container_of(xdp, struct xdp_buff_xsk, xdp); + const void *data = xdp->data; + struct xdp_buff_xsk *frag; + + if (!__xdp_buff_add_frag(head, virt_to_netmem(data), + offset_in_page(data), xdp->data_end - data, + xdp->frame_sz, false)) + return false; + + frag = container_of(xdp, struct xdp_buff_xsk, xdp); + list_add_tail(&frag->list_node, &frag->pool->xskb_list); - list_add_tail(&frag->xskb_list_node, &frag->pool->xskb_list); + return true; } -static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first) +static inline struct xdp_buff *xsk_buff_get_frag(const struct xdp_buff *first) { struct xdp_buff_xsk *xskb = container_of(first, struct xdp_buff_xsk, xdp); struct xdp_buff *ret = NULL; struct xdp_buff_xsk *frag; frag = list_first_entry_or_null(&xskb->pool->xskb_list, - struct xdp_buff_xsk, xskb_list_node); + struct xdp_buff_xsk, list_node); if (frag) { - list_del(&frag->xskb_list_node); + list_del(&frag->list_node); ret = &frag->xdp; } @@ -163,7 +164,7 @@ static inline void xsk_buff_del_tail(struct xdp_buff *tail) { struct xdp_buff_xsk *xskb = container_of(tail, struct xdp_buff_xsk, xdp); - list_del(&xskb->xskb_list_node); + list_del(&xskb->list_node); } static inline struct xdp_buff *xsk_buff_get_tail(struct xdp_buff *first) @@ -172,7 +173,7 @@ static inline struct xdp_buff *xsk_buff_get_tail(struct xdp_buff *first) struct xdp_buff_xsk *frag; frag = list_last_entry(&xskb->pool->xskb_list, struct xdp_buff_xsk, - xskb_list_node); + list_node); return &frag->xdp; } @@ -195,36 +196,59 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr) return xp_raw_get_data(pool, addr); } +/** + * xsk_buff_raw_get_ctx - get &xdp_desc context + * @pool: XSk buff pool desc address belongs to + * @addr: desc address (from userspace) + * + * Wrapper for xp_raw_get_ctx() to be used in drivers, see its kdoc for + * details. + * + * Return: new &xdp_desc_ctx struct containing desc's DMA address and metadata + * pointer, if it is present and valid (initialized to %NULL otherwise). + */ +static inline struct xdp_desc_ctx +xsk_buff_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr) +{ + return xp_raw_get_ctx(pool, addr); +} + #define XDP_TXMD_FLAGS_VALID ( \ XDP_TXMD_FLAGS_TIMESTAMP | \ XDP_TXMD_FLAGS_CHECKSUM | \ + XDP_TXMD_FLAGS_LAUNCH_TIME | \ 0) -static inline bool xsk_buff_valid_tx_metadata(struct xsk_tx_metadata *meta) +static inline bool +xsk_buff_valid_tx_metadata(const struct xsk_tx_metadata *meta) { return !(meta->flags & ~XDP_TXMD_FLAGS_VALID); } -static inline struct xsk_tx_metadata *xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr) +static inline struct xsk_tx_metadata * +__xsk_buff_get_metadata(const struct xsk_buff_pool *pool, void *data) { struct xsk_tx_metadata *meta; if (!pool->tx_metadata_len) return NULL; - meta = xp_raw_get_data(pool, addr) - pool->tx_metadata_len; + meta = data - pool->tx_metadata_len; if (unlikely(!xsk_buff_valid_tx_metadata(meta))) return NULL; /* no way to signal the error to the user */ return meta; } -static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool) +static inline struct xsk_tx_metadata * +xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr) { - struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp); + return __xsk_buff_get_metadata(pool, xp_raw_get_data(pool, addr)); +} - if (!pool->dma_need_sync) - return; +static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp) +{ + struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp); xp_dma_sync_for_cpu(xskb); } @@ -309,11 +333,6 @@ static inline void xsk_pool_fill_cb(struct xsk_buff_pool *pool, { } -static inline unsigned int xsk_pool_get_napi_id(struct xsk_buff_pool *pool) -{ - return 0; -} - static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs) { @@ -340,7 +359,7 @@ static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool) return NULL; } -static inline bool xsk_is_eop_desc(struct xdp_desc *desc) +static inline bool xsk_is_eop_desc(const struct xdp_desc *desc) { return false; } @@ -359,11 +378,13 @@ static inline void xsk_buff_free(struct xdp_buff *xdp) { } -static inline void xsk_buff_add_frag(struct xdp_buff *xdp) +static inline bool xsk_buff_add_frag(struct xdp_buff *head, + struct xdp_buff *xdp) { + return false; } -static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first) +static inline struct xdp_buff *xsk_buff_get_frag(const struct xdp_buff *first) { return NULL; } @@ -392,17 +413,30 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr) return NULL; } +static inline struct xdp_desc_ctx +xsk_buff_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr) +{ + return (struct xdp_desc_ctx){ }; +} + static inline bool xsk_buff_valid_tx_metadata(struct xsk_tx_metadata *meta) { return false; } -static inline struct xsk_tx_metadata *xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr) +static inline struct xsk_tx_metadata * +__xsk_buff_get_metadata(const struct xsk_buff_pool *pool, void *data) +{ + return NULL; +} + +static inline struct xsk_tx_metadata * +xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr) { return NULL; } -static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool) +static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp) { } diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 57c743b7e4fe..a21e276dbe44 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -19,6 +19,7 @@ #include <net/sock.h> #include <net/dst.h> +#include <net/inet_dscp.h> #include <net/ip.h> #include <net/route.h> #include <net/ipv6.h> @@ -37,6 +38,7 @@ #define XFRM_PROTO_COMP 108 #define XFRM_PROTO_IPIP 4 #define XFRM_PROTO_IPV6 41 +#define XFRM_PROTO_IPTFS IPPROTO_AGGFRAG #define XFRM_PROTO_ROUTING IPPROTO_ROUTING #define XFRM_PROTO_DSTOPTS IPPROTO_DSTOPTS @@ -67,27 +69,27 @@ - instance of a transformer, struct xfrm_state (=SA) - template to clone xfrm_state, struct xfrm_tmpl - SPD is plain linear list of xfrm_policy rules, ordered by priority. + SPD is organized as hash table (for policies that meet minimum address prefix + length setting, net->xfrm.policy_hthresh). Other policies are stored in + lists, sorted into rbtree ordered by destination and source address networks. + See net/xfrm/xfrm_policy.c for details. + (To be compatible with existing pfkeyv2 implementations, many rules with priority of 0x7fffffff are allowed to exist and such rules are ordered in an unpredictable way, thanks to bsd folks.) - Lookup is plain linear search until the first match with selector. - If "action" is "block", then we prohibit the flow, otherwise: if "xfrms_nr" is zero, the flow passes untransformed. Otherwise, policy entry has list of up to XFRM_MAX_DEPTH transformations, described by templates xfrm_tmpl. Each template is resolved to a complete xfrm_state (see below) and we pack bundle of transformations - to a dst_entry returned to requestor. + to a dst_entry returned to requester. dst -. xfrm .-> xfrm_state #1 |---. child .-> dst -. xfrm .-> xfrm_state #2 |---. child .-> dst -. xfrm .-> xfrm_state #3 |---. child .-> NULL - Bundles are cached at xrfm_policy struct (field ->bundles). - Resolution of xrfm_tmpl ----------------------- @@ -145,8 +147,19 @@ enum { }; struct xfrm_dev_offload { + /* The device for this offload. + * Device drivers should not use this directly, as that will prevent + * them from working with bonding device. Instead, the device passed + * to the add/delete callbacks should be used. + */ struct net_device *dev; netdevice_tracker dev_tracker; + /* This is a private pointer used by the bonding driver (and eventually + * should be moved there). Device drivers should not use it. + * Protected by xfrm_state.lock AND bond.ipsec_lock in most cases, + * except in the .xdo_dev_state_del() flow, where only xfrm_state.lock + * is held. + */ struct net_device *real_dev; unsigned long offload_handle; u8 dir : 2; @@ -178,13 +191,19 @@ struct xfrm_state { struct hlist_node gclist; struct hlist_node bydst; }; - struct hlist_node bysrc; + union { + struct hlist_node dev_gclist; + struct hlist_node bysrc; + }; struct hlist_node byspi; struct hlist_node byseq; + struct hlist_node state_cache; + struct hlist_node state_cache_input; refcount_t refcnt; spinlock_t lock; + u32 pcpu_num; struct xfrm_id id; struct xfrm_selector sel; struct xfrm_mark mark; @@ -206,6 +225,7 @@ struct xfrm_state { u16 family; xfrm_address_t saddr; int header_len; + int enc_hdr_len; int trailer_len; u32 extra_flags; struct xfrm_mark smark; @@ -227,7 +247,10 @@ struct xfrm_state { /* Data for encapsulator */ struct xfrm_encap_tmpl *encap; - struct sock __rcu *encap_sk; + + /* NAT keepalive */ + u32 nat_keepalive_interval; /* seconds */ + time64_t nat_keepalive_expiration; /* Data for care-of address */ xfrm_address_t *coaddr; @@ -291,6 +314,10 @@ struct xfrm_state { /* Private data of this transformer, format is opaque, * interpreted by xfrm_type methods. */ void *data; + u8 dir; + + const struct xfrm_mode_cbs *mode_cbs; + void *mode_data; }; static inline struct net *xs_net(struct xfrm_state *x) @@ -341,20 +368,25 @@ struct xfrm_if_cb { void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb); void xfrm_if_unregister_cb(void); +struct xfrm_dst_lookup_params { + struct net *net; + dscp_t dscp; + int oif; + xfrm_address_t *saddr; + xfrm_address_t *daddr; + u32 mark; + __u8 ipproto; + union flowi_uli uli; +}; + struct net_device; struct xfrm_type; struct xfrm_dst; struct xfrm_policy_afinfo { struct dst_ops *dst_ops; - struct dst_entry *(*dst_lookup)(struct net *net, - int tos, int oif, - const xfrm_address_t *saddr, - const xfrm_address_t *daddr, - u32 mark); - int (*get_saddr)(struct net *net, int oif, - xfrm_address_t *saddr, - xfrm_address_t *daddr, - u32 mark); + struct dst_entry *(*dst_lookup)(const struct xfrm_dst_lookup_params *params); + int (*get_saddr)(xfrm_address_t *saddr, + const struct xfrm_dst_lookup_params *params); int (*fill_dst)(struct xfrm_dst *xdst, struct net_device *dev, const struct flowi *fl); @@ -442,6 +474,54 @@ struct xfrm_type_offload { int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned short family); void xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family); +void xfrm_set_type_offload(struct xfrm_state *x); +static inline void xfrm_unset_type_offload(struct xfrm_state *x) +{ + if (!x->type_offload) + return; + + module_put(x->type_offload->owner); + x->type_offload = NULL; +} + +/** + * struct xfrm_mode_cbs - XFRM mode callbacks + * @owner: module owner or NULL + * @init_state: Add/init mode specific state in `xfrm_state *x` + * @clone_state: Copy mode specific values from `orig` to new state `x` + * @destroy_state: Cleanup mode specific state from `xfrm_state *x` + * @user_init: Process mode specific netlink attributes from user + * @copy_to_user: Add netlink attributes to `attrs` based on state in `x` + * @sa_len: Return space required to store mode specific netlink attributes + * @get_inner_mtu: Return avail payload space after removing encap overhead + * @input: Process received packet from SA using mode + * @output: Output given packet using mode + * @prepare_output: Add mode specific encapsulation to packet in skb. On return + * `transport_header` should point at ESP header, `network_header` should + * point at outer IP header and `mac_header` should opint at the + * protocol/nexthdr field of the outer IP. + * + * One should examine and understand the specific uses of these callbacks in + * xfrm for further detail on how and when these functions are called. RTSL. + */ +struct xfrm_mode_cbs { + struct module *owner; + int (*init_state)(struct xfrm_state *x); + int (*clone_state)(struct xfrm_state *x, struct xfrm_state *orig); + void (*destroy_state)(struct xfrm_state *x); + int (*user_init)(struct net *net, struct xfrm_state *x, + struct nlattr **attrs, + struct netlink_ext_ack *extack); + int (*copy_to_user)(struct xfrm_state *x, struct sk_buff *skb); + unsigned int (*sa_len)(const struct xfrm_state *x); + u32 (*get_inner_mtu)(struct xfrm_state *x, int outer_mtu); + int (*input)(struct xfrm_state *x, struct sk_buff *skb); + int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); + int (*prepare_output)(struct xfrm_state *x, struct sk_buff *skb); +}; + +int xfrm_register_mode_cbs(u8 mode, const struct xfrm_mode_cbs *mode_cbs); +void xfrm_unregister_mode_cbs(u8 mode); static inline int xfrm_af2proto(unsigned int family) { @@ -518,11 +598,44 @@ struct xfrm_policy_queue { unsigned long timeout; }; +/** + * struct xfrm_policy - xfrm policy + * @xp_net: network namespace the policy lives in + * @bydst: hlist node for SPD hash table or rbtree list + * @byidx: hlist node for index hash table + * @state_cache_list: hlist head for policy cached xfrm states + * @lock: serialize changes to policy structure members + * @refcnt: reference count, freed once it reaches 0 + * @pos: kernel internal tie-breaker to determine age of policy + * @timer: timer + * @genid: generation, used to invalidate old policies + * @priority: priority, set by userspace + * @index: policy index (autogenerated) + * @if_id: virtual xfrm interface id + * @mark: packet mark + * @selector: selector + * @lft: liftime configuration data + * @curlft: liftime state + * @walk: list head on pernet policy list + * @polq: queue to hold packets while aqcuire operaion in progress + * @bydst_reinsert: policy tree node needs to be merged + * @type: XFRM_POLICY_TYPE_MAIN or _SUB + * @action: XFRM_POLICY_ALLOW or _BLOCK + * @flags: XFRM_POLICY_LOCALOK, XFRM_POLICY_ICMP + * @xfrm_nr: number of used templates in @xfrm_vec + * @family: protocol family + * @security: SELinux security label + * @xfrm_vec: array of templates to resolve state + * @rcu: rcu head, used to defer memory release + * @xdo: hardware offload state + */ struct xfrm_policy { possible_net_t xp_net; struct hlist_node bydst; struct hlist_node byidx; + struct hlist_head state_cache_list; + /* This lock only affects elements except for entry. */ rwlock_t lock; refcount_t refcnt; @@ -547,7 +660,6 @@ struct xfrm_policy { u16 family; struct xfrm_sec_ctx *security; struct xfrm_tmpl xfrm_vec[XFRM_MAX_DEPTH]; - struct hlist_node bydst_inexact_list; struct rcu_head rcu; struct xfrm_dev_offload xdo; @@ -1008,7 +1120,7 @@ void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev); struct xfrm_if_parms { int link; /* ifindex of underlying L2 interface */ - u32 if_id; /* interface identifyer */ + u32 if_id; /* interface identifier */ bool collect_md; }; @@ -1049,6 +1161,9 @@ struct xfrm_offload { #define CRYPTO_INVALID_PACKET_SYNTAX 64 #define CRYPTO_INVALID_PROTOCOL 128 + /* Used to keep whole l2 header for transport mode GRO */ + __u32 orig_mac_len; + __u8 proto; __u8 inner_ipproto; }; @@ -1172,9 +1287,19 @@ static inline int __xfrm_policy_check2(struct sock *sk, int dir, if (xo) { x = xfrm_input_state(skb); - if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) - return (xo->flags & CRYPTO_DONE) && - (xo->status & CRYPTO_SUCCESS); + if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) { + bool check = (xo->flags & CRYPTO_DONE) && + (xo->status & CRYPTO_SUCCESS); + + /* The packets here are plain ones and secpath was + * needed to indicate that hardware already handled + * them and there is no need to do nothing in addition. + * + * Consume secpath which was set by drivers. + */ + secpath_reset(skb); + return check; + } } return __xfrm_check_nopolicy(net, skb, dir) || @@ -1584,7 +1709,7 @@ void xfrm_state_update_stats(struct net *net); static inline void xfrm_dev_state_update_stats(struct xfrm_state *x) { struct xfrm_dev_offload *xdo = &x->xso; - struct net_device *dev = xdo->dev; + struct net_device *dev = READ_ONCE(xdo->dev); if (dev && dev->xfrmdev_ops && dev->xfrmdev_ops->xdo_dev_state_update_stats) @@ -1600,6 +1725,10 @@ int xfrm_state_update(struct xfrm_state *x); struct xfrm_state *xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family); +struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark, + const xfrm_address_t *daddr, + __be32 spi, u8 proto, + unsigned short family); struct xfrm_state *xfrm_state_lookup_byaddr(struct net *net, u32 mark, const xfrm_address_t *daddr, const xfrm_address_t *saddr, @@ -1639,7 +1768,7 @@ struct xfrmk_spdinfo { u32 spdhmcnt; }; -struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq); +struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq, u32 pcpu_num); int xfrm_state_delete(struct xfrm_state *x); int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync); int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid); @@ -1650,8 +1779,7 @@ void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si); u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq); int xfrm_init_replay(struct xfrm_state *x, struct netlink_ext_ack *extack); u32 xfrm_state_mtu(struct xfrm_state *x, int mtu); -int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload, - struct netlink_ext_ack *extack); +int __xfrm_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack); int xfrm_init_state(struct xfrm_state *x); int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); int xfrm_input_resume(struct sk_buff *skb, int nexthdr); @@ -1663,6 +1791,15 @@ int xfrm_trans_queue(struct sk_buff *skb, struct sk_buff *)); int xfrm_output_resume(struct sock *sk, struct sk_buff *skb, int err); int xfrm_output(struct sock *sk, struct sk_buff *skb); +int xfrm4_tunnel_check_size(struct sk_buff *skb); +#if IS_ENABLED(CONFIG_IPV6) +int xfrm6_tunnel_check_size(struct sk_buff *skb); +#else +static inline int xfrm6_tunnel_check_size(struct sk_buff *skb) +{ + return -EMSGSIZE; +} +#endif #if IS_ENABLED(CONFIG_NET_PKTGEN) int pktgen_xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *skb); @@ -1724,10 +1861,7 @@ static inline int xfrm_user_policy(struct sock *sk, int optname, } #endif -struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif, - const xfrm_address_t *saddr, - const xfrm_address_t *daddr, - int family, u32 mark); +struct dst_entry *__xfrm_dst_lookup(int family, const struct xfrm_dst_lookup_params *params); struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp); @@ -1754,7 +1888,7 @@ int verify_spi_info(u8 proto, u32 min, u32 max, struct netlink_ext_ack *extack); int xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi, struct netlink_ext_ack *extack); struct xfrm_state *xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, - u8 mode, u32 reqid, u32 if_id, u8 proto, + u8 mode, u32 reqid, u32 if_id, u32 pcpu_num, u8 proto, const xfrm_address_t *daddr, const xfrm_address_t *saddr, int create, unsigned short family); @@ -1769,12 +1903,16 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n u32 if_id); struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, struct xfrm_migrate *m, - struct xfrm_encap_tmpl *encap); + struct xfrm_encap_tmpl *encap, + struct net *net, + struct xfrm_user_offload *xuo, + struct netlink_ext_ack *extack); int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_bundles, struct xfrm_kmaddress *k, struct net *net, struct xfrm_encap_tmpl *encap, u32 if_id, - struct netlink_ext_ack *extack); + struct netlink_ext_ack *extack, + struct xfrm_user_offload *xuo); #endif int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport); @@ -1942,13 +2080,16 @@ int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp, struct xfrm_user_offload *xuo, u8 dir, struct netlink_ext_ack *extack); bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x); +void xfrm_dev_state_delete(struct xfrm_state *x); +void xfrm_dev_state_free(struct xfrm_state *x); static inline void xfrm_dev_state_advance_esn(struct xfrm_state *x) { struct xfrm_dev_offload *xso = &x->xso; + struct net_device *dev = READ_ONCE(xso->dev); - if (xso->dev && xso->dev->xfrmdev_ops->xdo_dev_state_advance_esn) - xso->dev->xfrmdev_ops->xdo_dev_state_advance_esn(x); + if (dev && dev->xfrmdev_ops->xdo_dev_state_advance_esn) + dev->xfrmdev_ops->xdo_dev_state_advance_esn(x); } static inline bool xfrm_dst_offload_ok(struct dst_entry *dst) @@ -1969,28 +2110,6 @@ static inline bool xfrm_dst_offload_ok(struct dst_entry *dst) return false; } -static inline void xfrm_dev_state_delete(struct xfrm_state *x) -{ - struct xfrm_dev_offload *xso = &x->xso; - - if (xso->dev) - xso->dev->xfrmdev_ops->xdo_dev_state_delete(x); -} - -static inline void xfrm_dev_state_free(struct xfrm_state *x) -{ - struct xfrm_dev_offload *xso = &x->xso; - struct net_device *dev = xso->dev; - - if (dev && dev->xfrmdev_ops) { - if (dev->xfrmdev_ops->xdo_dev_state_free) - dev->xfrmdev_ops->xdo_dev_state_free(x); - xso->dev = NULL; - xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; - netdev_put(dev, &xso->dev_tracker); - } -} - static inline void xfrm_dev_policy_delete(struct xfrm_policy *x) { struct xfrm_dev_offload *xdo = &x->xdo; @@ -2199,4 +2318,10 @@ static inline int register_xfrm_state_bpf(void) } #endif +int xfrm_nat_keepalive_init(unsigned short family); +void xfrm_nat_keepalive_fini(unsigned short family); +int xfrm_nat_keepalive_net_init(struct net *net); +int xfrm_nat_keepalive_net_fini(struct net *net); +void xfrm_nat_keepalive_state_updated(struct xfrm_state *x); + #endif /* _NET_XFRM_H */ diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 99dd7376df6a..cac56e6b0869 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -28,10 +28,8 @@ struct xdp_buff_xsk { dma_addr_t dma; dma_addr_t frame_dma; struct xsk_buff_pool *pool; - u64 orig_addr; - struct list_head free_list_node; - struct list_head xskb_list_node; -}; + struct list_head list_node; +} __aligned_largest; #define XSK_CHECK_PRIV_TYPE(t) BUILD_BUG_ON(sizeof(t) > offsetofend(struct xdp_buff_xsk, cb)) #define XSK_TX_COMPL_FITS(t) BUILD_BUG_ON(sizeof(struct xsk_tx_metadata_compl) > sizeof(t)) @@ -43,7 +41,6 @@ struct xsk_dma_map { refcount_t users; struct list_head list; /* Protected by the RTNL_LOCK */ u32 dma_pages_cnt; - bool dma_need_sync; }; struct xsk_buff_pool { @@ -56,6 +53,8 @@ struct xsk_buff_pool { refcount_t users; struct xdp_umem *umem; struct work_struct work; + /* Protects generic receive in shared and non-shared umem mode. */ + spinlock_t rx_lock; struct list_head free_list; struct list_head xskb_list; u32 heads_cnt; @@ -79,10 +78,10 @@ struct xsk_buff_pool { u32 chunk_size; u32 chunk_shift; u32 frame_len; + u32 xdp_zc_max_segs; u8 tx_metadata_len; /* inherited from umem */ u8 cached_need_wakeup; bool uses_need_wakeup; - bool dma_need_sync; bool unaligned; bool tx_sw_csum; void *addrs; @@ -122,7 +121,6 @@ void xp_free(struct xdp_buff_xsk *xskb); static inline void xp_init_xskb_addr(struct xdp_buff_xsk *xskb, struct xsk_buff_pool *pool, u64 addr) { - xskb->orig_addr = addr; xskb->xdp.data_hard_start = pool->addrs + addr + pool->headroom; } @@ -145,6 +143,14 @@ u32 xp_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max); bool xp_can_alloc(struct xsk_buff_pool *pool, u32 count); void *xp_raw_get_data(struct xsk_buff_pool *pool, u64 addr); dma_addr_t xp_raw_get_dma(struct xsk_buff_pool *pool, u64 addr); + +struct xdp_desc_ctx { + dma_addr_t dma; + struct xsk_tx_metadata *meta; +}; + +struct xdp_desc_ctx xp_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr); + static inline dma_addr_t xp_get_dma(struct xdp_buff_xsk *xskb) { return xskb->dma; @@ -155,21 +161,17 @@ static inline dma_addr_t xp_get_frame_dma(struct xdp_buff_xsk *xskb) return xskb->frame_dma; } -void xp_dma_sync_for_cpu_slow(struct xdp_buff_xsk *xskb); static inline void xp_dma_sync_for_cpu(struct xdp_buff_xsk *xskb) { - xp_dma_sync_for_cpu_slow(xskb); + dma_sync_single_for_cpu(xskb->pool->dev, xskb->dma, + xskb->pool->frame_len, + DMA_BIDIRECTIONAL); } -void xp_dma_sync_for_device_slow(struct xsk_buff_pool *pool, dma_addr_t dma, - size_t size); static inline void xp_dma_sync_for_device(struct xsk_buff_pool *pool, dma_addr_t dma, size_t size) { - if (!pool->dma_need_sync) - return; - - xp_dma_sync_for_device_slow(pool, dma, size); + dma_sync_single_for_device(pool->dev, dma, size, DMA_BIDIRECTIONAL); } /* Masks for xdp_umem_page flags. @@ -191,7 +193,7 @@ static inline bool xp_desc_crosses_non_contig_pg(struct xsk_buff_pool *pool, !(pool->dma_pages[addr >> PAGE_SHIFT] & XSK_NEXT_PG_CONTIG_MASK); } -static inline bool xp_mb_desc(struct xdp_desc *desc) +static inline bool xp_mb_desc(const struct xdp_desc *desc) { return desc->options & XDP_PKT_CONTD; } @@ -228,14 +230,19 @@ static inline void xp_release(struct xdp_buff_xsk *xskb) xskb->pool->free_heads[xskb->pool->free_heads_cnt++] = xskb; } -static inline u64 xp_get_handle(struct xdp_buff_xsk *xskb) +static inline u64 xp_get_handle(struct xdp_buff_xsk *xskb, + struct xsk_buff_pool *pool) { - u64 offset = xskb->xdp.data - xskb->xdp.data_hard_start; + u64 orig_addr = xskb->xdp.data - pool->addrs; + u64 offset; + + if (!pool->unaligned) + return orig_addr; - offset += xskb->pool->headroom; - if (!xskb->pool->unaligned) - return xskb->orig_addr + offset; - return xskb->orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT); + offset = xskb->xdp.data - xskb->xdp.data_hard_start; + offset += pool->headroom; + orig_addr -= offset; + return orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT); } static inline bool xp_tx_metadata_enabled(const struct xsk_buff_pool *pool) |