diff options
Diffstat (limited to 'include/net')
47 files changed, 1276 insertions, 428 deletions
diff --git a/include/net/act_api.h b/include/net/act_api.h index f19f7f4a463c..b5b624c7e488 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -30,13 +30,13 @@ struct tc_action { atomic_t tcfa_bindcnt; int tcfa_action; struct tcf_t tcfa_tm; - struct gnet_stats_basic_packed tcfa_bstats; - struct gnet_stats_basic_packed tcfa_bstats_hw; + struct gnet_stats_basic_sync tcfa_bstats; + struct gnet_stats_basic_sync tcfa_bstats_hw; struct gnet_stats_queue tcfa_qstats; struct net_rate_estimator __rcu *tcfa_rate_est; spinlock_t tcfa_lock; - struct gnet_stats_basic_cpu __percpu *cpu_bstats; - struct gnet_stats_basic_cpu __percpu *cpu_bstats_hw; + struct gnet_stats_basic_sync __percpu *cpu_bstats; + struct gnet_stats_basic_sync __percpu *cpu_bstats_hw; struct gnet_stats_queue __percpu *cpu_qstats; struct tc_cookie __rcu *act_cookie; struct tcf_chain __rcu *goto_chain; @@ -206,7 +206,7 @@ static inline void tcf_action_update_bstats(struct tc_action *a, struct sk_buff *skb) { if (likely(a->cpu_bstats)) { - bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), skb); + bstats_update(this_cpu_ptr(a->cpu_bstats), skb); return; } spin_lock(&a->tcfa_lock); diff --git a/include/net/amt.h b/include/net/amt.h new file mode 100644 index 000000000000..7a4db8b903ee --- /dev/null +++ b/include/net/amt.h @@ -0,0 +1,385 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (c) 2021 Taehee Yoo <ap420073@gmail.com> + */ +#ifndef _NET_AMT_H_ +#define _NET_AMT_H_ + +#include <linux/siphash.h> +#include <linux/jhash.h> + +enum amt_msg_type { + AMT_MSG_DISCOVERY = 1, + AMT_MSG_ADVERTISEMENT, + AMT_MSG_REQUEST, + AMT_MSG_MEMBERSHIP_QUERY, + AMT_MSG_MEMBERSHIP_UPDATE, + AMT_MSG_MULTICAST_DATA, + AMT_MSG_TEARDOWM, + __AMT_MSG_MAX, +}; + +#define AMT_MSG_MAX (__AMT_MSG_MAX - 1) + +enum amt_ops { + /* A*B */ + AMT_OPS_INT, + /* A+B */ + AMT_OPS_UNI, + /* A-B */ + AMT_OPS_SUB, + /* B-A */ + AMT_OPS_SUB_REV, + __AMT_OPS_MAX, +}; + +#define AMT_OPS_MAX (__AMT_OPS_MAX - 1) + +enum amt_filter { + AMT_FILTER_FWD, + AMT_FILTER_D_FWD, + AMT_FILTER_FWD_NEW, + AMT_FILTER_D_FWD_NEW, + AMT_FILTER_ALL, + AMT_FILTER_NONE_NEW, + AMT_FILTER_BOTH, + AMT_FILTER_BOTH_NEW, + __AMT_FILTER_MAX, +}; + +#define AMT_FILTER_MAX (__AMT_FILTER_MAX - 1) + +enum amt_act { + AMT_ACT_GMI, + AMT_ACT_GMI_ZERO, + AMT_ACT_GT, + AMT_ACT_STATUS_FWD_NEW, + AMT_ACT_STATUS_D_FWD_NEW, + AMT_ACT_STATUS_NONE_NEW, + __AMT_ACT_MAX, +}; + +#define AMT_ACT_MAX (__AMT_ACT_MAX - 1) + +enum amt_status { + AMT_STATUS_INIT, + AMT_STATUS_SENT_DISCOVERY, + AMT_STATUS_RECEIVED_DISCOVERY, + AMT_STATUS_SENT_ADVERTISEMENT, + AMT_STATUS_RECEIVED_ADVERTISEMENT, + AMT_STATUS_SENT_REQUEST, + AMT_STATUS_RECEIVED_REQUEST, + AMT_STATUS_SENT_QUERY, + AMT_STATUS_RECEIVED_QUERY, + AMT_STATUS_SENT_UPDATE, + AMT_STATUS_RECEIVED_UPDATE, + __AMT_STATUS_MAX, +}; + +#define AMT_STATUS_MAX (__AMT_STATUS_MAX - 1) + +struct amt_header { +#if defined(__LITTLE_ENDIAN_BITFIELD) + u8 type:4, + version:4; +#elif defined(__BIG_ENDIAN_BITFIELD) + u8 version:4, + type:4; +#else +#error "Please fix <asm/byteorder.h>" +#endif +} __packed; + +struct amt_header_discovery { +#if defined(__LITTLE_ENDIAN_BITFIELD) + u32 type:4, + version:4, + reserved:24; +#elif defined(__BIG_ENDIAN_BITFIELD) + u32 version:4, + type:4, + reserved:24; +#else +#error "Please fix <asm/byteorder.h>" +#endif + __be32 nonce; +} __packed; + +struct amt_header_advertisement { +#if defined(__LITTLE_ENDIAN_BITFIELD) + u32 type:4, + version:4, + reserved:24; +#elif defined(__BIG_ENDIAN_BITFIELD) + u32 version:4, + type:4, + reserved:24; +#else +#error "Please fix <asm/byteorder.h>" +#endif + __be32 nonce; + __be32 ip4; +} __packed; + +struct amt_header_request { +#if defined(__LITTLE_ENDIAN_BITFIELD) + u32 type:4, + version:4, + reserved1:7, + p:1, + reserved2:16; +#elif defined(__BIG_ENDIAN_BITFIELD) + u32 version:4, + type:4, + p:1, + reserved1:7, + reserved2:16; +#else +#error "Please fix <asm/byteorder.h>" +#endif + __be32 nonce; +} __packed; + +struct amt_header_membership_query { +#if defined(__LITTLE_ENDIAN_BITFIELD) + u64 type:4, + version:4, + reserved:6, + l:1, + g:1, + response_mac:48; +#elif defined(__BIG_ENDIAN_BITFIELD) + u64 version:4, + type:4, + g:1, + l:1, + reserved:6, + response_mac:48; +#else +#error "Please fix <asm/byteorder.h>" +#endif + __be32 nonce; +} __packed; + +struct amt_header_membership_update { +#if defined(__LITTLE_ENDIAN_BITFIELD) + u64 type:4, + version:4, + reserved:8, + response_mac:48; +#elif defined(__BIG_ENDIAN_BITFIELD) + u64 version:4, + type:4, + reserved:8, + response_mac:48; +#else +#error "Please fix <asm/byteorder.h>" +#endif + __be32 nonce; +} __packed; + +struct amt_header_mcast_data { +#if defined(__LITTLE_ENDIAN_BITFIELD) + u16 type:4, + version:4, + reserved:8; +#elif defined(__BIG_ENDIAN_BITFIELD) + u16 version:4, + type:4, + reserved:8; +#else +#error "Please fix <asm/byteorder.h>" +#endif +} __packed; + +struct amt_headers { + union { + struct amt_header_discovery discovery; + struct amt_header_advertisement advertisement; + struct amt_header_request request; + struct amt_header_membership_query query; + struct amt_header_membership_update update; + struct amt_header_mcast_data data; + }; +} __packed; + +struct amt_gw_headers { + union { + struct amt_header_discovery discovery; + struct amt_header_request request; + struct amt_header_membership_update update; + }; +} __packed; + +struct amt_relay_headers { + union { + struct amt_header_advertisement advertisement; + struct amt_header_membership_query query; + struct amt_header_mcast_data data; + }; +} __packed; + +struct amt_skb_cb { + struct amt_tunnel_list *tunnel; +}; + +struct amt_tunnel_list { + struct list_head list; + /* Protect All resources under an amt_tunne_list */ + spinlock_t lock; + struct amt_dev *amt; + u32 nr_groups; + u32 nr_sources; + enum amt_status status; + struct delayed_work gc_wq; + __be16 source_port; + __be32 ip4; + __be32 nonce; + siphash_key_t key; + u64 mac:48, + reserved:16; + struct rcu_head rcu; + struct hlist_head groups[]; +}; + +union amt_addr { + __be32 ip4; +#if IS_ENABLED(CONFIG_IPV6) + struct in6_addr ip6; +#endif +}; + +/* RFC 3810 + * + * When the router is in EXCLUDE mode, the router state is represented + * by the notation EXCLUDE (X,Y), where X is called the "Requested List" + * and Y is called the "Exclude List". All sources, except those from + * the Exclude List, will be forwarded by the router + */ +enum amt_source_status { + AMT_SOURCE_STATUS_NONE, + /* Node of Requested List */ + AMT_SOURCE_STATUS_FWD, + /* Node of Exclude List */ + AMT_SOURCE_STATUS_D_FWD, +}; + +/* protected by gnode->lock */ +struct amt_source_node { + struct hlist_node node; + struct amt_group_node *gnode; + struct delayed_work source_timer; + union amt_addr source_addr; + enum amt_source_status status; +#define AMT_SOURCE_OLD 0 +#define AMT_SOURCE_NEW 1 + u8 flags; + struct rcu_head rcu; +}; + +/* Protected by amt_tunnel_list->lock */ +struct amt_group_node { + struct amt_dev *amt; + union amt_addr group_addr; + union amt_addr host_addr; + bool v6; + u8 filter_mode; + u32 nr_sources; + struct amt_tunnel_list *tunnel_list; + struct hlist_node node; + struct delayed_work group_timer; + struct rcu_head rcu; + struct hlist_head sources[]; +}; + +struct amt_dev { + struct net_device *dev; + struct net_device *stream_dev; + struct net *net; + /* Global lock for amt device */ + spinlock_t lock; + /* Used only in relay mode */ + struct list_head tunnel_list; + struct gro_cells gro_cells; + + /* Protected by RTNL */ + struct delayed_work discovery_wq; + /* Protected by RTNL */ + struct delayed_work req_wq; + /* Protected by RTNL */ + struct delayed_work secret_wq; + /* AMT status */ + enum amt_status status; + /* Generated key */ + siphash_key_t key; + struct socket __rcu *sock; + u32 max_groups; + u32 max_sources; + u32 hash_buckets; + u32 hash_seed; + /* Default 128 */ + u32 max_tunnels; + /* Default 128 */ + u32 nr_tunnels; + /* Gateway or Relay mode */ + u32 mode; + /* Default 2268 */ + __be16 relay_port; + /* Default 2268 */ + __be16 gw_port; + /* Outer local ip */ + __be32 local_ip; + /* Outer remote ip */ + __be32 remote_ip; + /* Outer discovery ip */ + __be32 discovery_ip; + /* Only used in gateway mode */ + __be32 nonce; + /* Gateway sent request and received query */ + bool ready4; + bool ready6; + u8 req_cnt; + u8 qi; + u64 qrv; + u64 qri; + /* Used only in gateway mode */ + u64 mac:48, + reserved:16; +}; + +#define AMT_TOS 0xc0 +#define AMT_IPHDR_OPTS 4 +#define AMT_IP6HDR_OPTS 8 +#define AMT_GC_INTERVAL (30 * 1000) +#define AMT_MAX_GROUP 32 +#define AMT_MAX_SOURCE 128 +#define AMT_HSIZE_SHIFT 8 +#define AMT_HSIZE (1 << AMT_HSIZE_SHIFT) + +#define AMT_DISCOVERY_TIMEOUT 5000 +#define AMT_INIT_REQ_TIMEOUT 1 +#define AMT_INIT_QUERY_INTERVAL 125 +#define AMT_MAX_REQ_TIMEOUT 120 +#define AMT_MAX_REQ_COUNT 3 +#define AMT_SECRET_TIMEOUT 60000 +#define IANA_AMT_UDP_PORT 2268 +#define AMT_MAX_TUNNELS 128 +#define AMT_MAX_REQS 128 +#define AMT_GW_HLEN (sizeof(struct iphdr) + \ + sizeof(struct udphdr) + \ + sizeof(struct amt_gw_headers)) +#define AMT_RELAY_HLEN (sizeof(struct iphdr) + \ + sizeof(struct udphdr) + \ + sizeof(struct amt_relay_headers)) + +static inline bool netif_is_amt(const struct net_device *dev) +{ + return dev->rtnl_link_ops && !strcmp(dev->rtnl_link_ops->kind, "amt"); +} + +static inline u64 amt_gmi(const struct amt_dev *amt) +{ + return ((amt->qrv * amt->qi) + amt->qri) * 1000; +} + +#endif /* _NET_AMT_H_ */ diff --git a/include/net/ax25.h b/include/net/ax25.h index 8b7eb46ad72d..03d409de61ad 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -304,7 +304,7 @@ extern spinlock_t ax25_list_lock; void ax25_cb_add(ax25_cb *); struct sock *ax25_find_listener(ax25_address *, int, struct net_device *, int); struct sock *ax25_get_socket(ax25_address *, ax25_address *, int); -ax25_cb *ax25_find_cb(ax25_address *, ax25_address *, ax25_digi *, +ax25_cb *ax25_find_cb(const ax25_address *, ax25_address *, ax25_digi *, struct net_device *); void ax25_send_to_raw(ax25_address *, struct sk_buff *, int); void ax25_destroy_socket(ax25_cb *); @@ -384,10 +384,11 @@ struct ax25_linkfail { void ax25_linkfail_register(struct ax25_linkfail *lf); void ax25_linkfail_release(struct ax25_linkfail *lf); -int __must_check ax25_listen_register(ax25_address *, struct net_device *); -void ax25_listen_release(ax25_address *, struct net_device *); +int __must_check ax25_listen_register(const ax25_address *, + struct net_device *); +void ax25_listen_release(const ax25_address *, struct net_device *); int(*ax25_protocol_function(unsigned int))(struct sk_buff *, ax25_cb *); -int ax25_listen_mine(ax25_address *, struct net_device *); +int ax25_listen_mine(const ax25_address *, struct net_device *); void ax25_link_failed(ax25_cb *, int); int ax25_protocol_is_registered(unsigned int); @@ -401,8 +402,8 @@ netdev_tx_t ax25_ip_xmit(struct sk_buff *skb); extern const struct header_ops ax25_header_ops; /* ax25_out.c */ -ax25_cb *ax25_send_frame(struct sk_buff *, int, ax25_address *, ax25_address *, - ax25_digi *, struct net_device *); +ax25_cb *ax25_send_frame(struct sk_buff *, int, const ax25_address *, + ax25_address *, ax25_digi *, struct net_device *); void ax25_output(ax25_cb *, int, struct sk_buff *); void ax25_kick(ax25_cb *); void ax25_transmit_buffer(ax25_cb *, struct sk_buff *, int); diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 9125effbf448..3271870fd85e 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -153,6 +153,30 @@ struct bt_voice { #define BT_SCM_PKT_STATUS 0x03 +#define BT_CODEC 19 + +struct bt_codec_caps { + __u8 len; + __u8 data[]; +} __packed; + +struct bt_codec { + __u8 id; + __u16 cid; + __u16 vid; + __u8 data_path; + __u8 num_caps; +} __packed; + +struct bt_codecs { + __u8 num_codecs; + struct bt_codec codecs[]; +} __packed; + +#define BT_CODEC_CVSD 0x02 +#define BT_CODEC_TRANSPARENT 0x03 +#define BT_CODEC_MSBC 0x05 + __printf(1, 2) void bt_info(const char *fmt, ...); __printf(1, 2) @@ -420,6 +444,72 @@ out: return NULL; } +/* Shall not be called with lock_sock held */ +static inline struct sk_buff *bt_skb_sendmsg(struct sock *sk, + struct msghdr *msg, + size_t len, size_t mtu, + size_t headroom, size_t tailroom) +{ + struct sk_buff *skb; + size_t size = min_t(size_t, len, mtu); + int err; + + skb = bt_skb_send_alloc(sk, size + headroom + tailroom, + msg->msg_flags & MSG_DONTWAIT, &err); + if (!skb) + return ERR_PTR(err); + + skb_reserve(skb, headroom); + skb_tailroom_reserve(skb, mtu, tailroom); + + if (!copy_from_iter_full(skb_put(skb, size), size, &msg->msg_iter)) { + kfree_skb(skb); + return ERR_PTR(-EFAULT); + } + + skb->priority = sk->sk_priority; + + return skb; +} + +/* Similar to bt_skb_sendmsg but can split the msg into multiple fragments + * accourding to the MTU. + */ +static inline struct sk_buff *bt_skb_sendmmsg(struct sock *sk, + struct msghdr *msg, + size_t len, size_t mtu, + size_t headroom, size_t tailroom) +{ + struct sk_buff *skb, **frag; + + skb = bt_skb_sendmsg(sk, msg, len, mtu, headroom, tailroom); + if (IS_ERR_OR_NULL(skb)) + return skb; + + len -= skb->len; + if (!len) + return skb; + + /* Add remaining data over MTU as continuation fragments */ + frag = &skb_shinfo(skb)->frag_list; + while (len) { + struct sk_buff *tmp; + + tmp = bt_skb_sendmsg(sk, msg, len, mtu, headroom, tailroom); + if (IS_ERR(tmp)) { + kfree_skb(skb); + return tmp; + } + + len -= tmp->len; + + *frag = tmp; + frag = &(*frag)->next; + } + + return skb; +} + int bt_to_errno(u16 code); void hci_sock_set_flag(struct sock *sk, int nr); diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index b80415011dcd..63065bc01b76 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -330,6 +330,8 @@ enum { HCI_ENABLE_LL_PRIVACY, HCI_CMD_PENDING, HCI_FORCE_NO_MITM, + HCI_QUALITY_REPORT, + HCI_OFFLOAD_CODECS_ENABLED, __HCI_NUM_FLAGS, }; @@ -871,6 +873,40 @@ struct hci_cp_logical_link_cancel { __u8 flow_spec_id; } __packed; +#define HCI_OP_ENHANCED_SETUP_SYNC_CONN 0x043d +struct hci_coding_format { + __u8 id; + __le16 cid; + __le16 vid; +} __packed; + +struct hci_cp_enhanced_setup_sync_conn { + __le16 handle; + __le32 tx_bandwidth; + __le32 rx_bandwidth; + struct hci_coding_format tx_coding_format; + struct hci_coding_format rx_coding_format; + __le16 tx_codec_frame_size; + __le16 rx_codec_frame_size; + __le32 in_bandwidth; + __le32 out_bandwidth; + struct hci_coding_format in_coding_format; + struct hci_coding_format out_coding_format; + __le16 in_coded_data_size; + __le16 out_coded_data_size; + __u8 in_pcm_data_format; + __u8 out_pcm_data_format; + __u8 in_pcm_sample_payload_msb_pos; + __u8 out_pcm_sample_payload_msb_pos; + __u8 in_data_path; + __u8 out_data_path; + __u8 in_transport_unit_size; + __u8 out_transport_unit_size; + __le16 max_latency; + __le16 pkt_type; + __u8 retrans_effort; +} __packed; + struct hci_rp_logical_link_cancel { __u8 status; __u8 phy_handle; @@ -1250,6 +1286,14 @@ struct hci_rp_read_local_oob_ext_data { __u8 rand256[16]; } __packed; +#define HCI_CONFIGURE_DATA_PATH 0x0c83 +struct hci_op_configure_data_path { + __u8 direction; + __u8 data_path_id; + __u8 vnd_len; + __u8 vnd_data[]; +} __packed; + #define HCI_OP_READ_LOCAL_VERSION 0x1001 struct hci_rp_read_local_version { __u8 status; @@ -1307,6 +1351,28 @@ struct hci_rp_read_data_block_size { } __packed; #define HCI_OP_READ_LOCAL_CODECS 0x100b +struct hci_std_codecs { + __u8 num; + __u8 codec[]; +} __packed; + +struct hci_vnd_codec { + /* company id */ + __le16 cid; + /* vendor codec id */ + __le16 vid; +} __packed; + +struct hci_vnd_codecs { + __u8 num; + struct hci_vnd_codec codec[]; +} __packed; + +struct hci_rp_read_local_supported_codecs { + __u8 status; + struct hci_std_codecs std_codecs; + struct hci_vnd_codecs vnd_codecs; +} __packed; #define HCI_OP_READ_LOCAL_PAIRING_OPTS 0x100c struct hci_rp_read_local_pairing_opts { @@ -1315,6 +1381,54 @@ struct hci_rp_read_local_pairing_opts { __u8 max_key_size; } __packed; +#define HCI_OP_READ_LOCAL_CODECS_V2 0x100d +struct hci_std_codec_v2 { + __u8 id; + __u8 transport; +} __packed; + +struct hci_std_codecs_v2 { + __u8 num; + struct hci_std_codec_v2 codec[]; +} __packed; + +struct hci_vnd_codec_v2 { + __u8 id; + __le16 cid; + __le16 vid; + __u8 transport; +} __packed; + +struct hci_vnd_codecs_v2 { + __u8 num; + struct hci_vnd_codec_v2 codec[]; +} __packed; + +struct hci_rp_read_local_supported_codecs_v2 { + __u8 status; + struct hci_std_codecs_v2 std_codecs; + struct hci_vnd_codecs_v2 vendor_codecs; +} __packed; + +#define HCI_OP_READ_LOCAL_CODEC_CAPS 0x100e +struct hci_op_read_local_codec_caps { + __u8 id; + __le16 cid; + __le16 vid; + __u8 transport; + __u8 direction; +} __packed; + +struct hci_codec_caps { + __u8 len; + __u8 data[]; +} __packed; + +struct hci_rp_read_local_codec_caps { + __u8 status; + __u8 num_caps; +} __packed; + #define HCI_OP_READ_PAGE_SCAN_ACTIVITY 0x0c1b struct hci_rp_read_page_scan_activity { __u8 status; @@ -2551,6 +2665,9 @@ static inline struct hci_sco_hdr *hci_sco_hdr(const struct sk_buff *skb) #define hci_iso_data_len(h) ((h) & 0x3fff) #define hci_iso_data_flags(h) ((h) >> 14) +/* codec transport types */ +#define HCI_TRANSPORT_SCO_ESCO 0x01 + /* le24 support */ static inline void hci_cpu_to_le24(__u32 val, __u8 dst[3]) { diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index a7360c8c72f8..dd8840e70e25 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -131,6 +131,17 @@ struct bdaddr_list { u8 bdaddr_type; }; +struct codec_list { + struct list_head list; + u8 id; + __u16 cid; + __u16 vid; + u8 transport; + u8 num_caps; + u32 len; + struct hci_codec_caps caps[]; +}; + struct bdaddr_list_with_irk { struct list_head list; bdaddr_t bdaddr; @@ -536,6 +547,7 @@ struct hci_dev { struct list_head pend_le_conns; struct list_head pend_le_reports; struct list_head blocked_keys; + struct list_head local_codecs; struct hci_dev_stats stat; @@ -605,7 +617,12 @@ struct hci_dev { int (*set_diag)(struct hci_dev *hdev, bool enable); int (*set_bdaddr)(struct hci_dev *hdev, const bdaddr_t *bdaddr); void (*cmd_timeout)(struct hci_dev *hdev); - bool (*prevent_wake)(struct hci_dev *hdev); + bool (*wakeup)(struct hci_dev *hdev); + int (*set_quality_report)(struct hci_dev *hdev, bool enable); + int (*get_data_path_id)(struct hci_dev *hdev, __u8 *data_path); + int (*get_codec_config_data)(struct hci_dev *hdev, __u8 type, + struct bt_codec *codec, __u8 *vnd_len, + __u8 **vnd_data); }; #define HCI_PHY_HANDLE(handle) (handle & 0xff) @@ -699,6 +716,7 @@ struct hci_conn { struct amp_mgr *amp_mgr; struct hci_conn *link; + struct bt_codec codec; void (*connect_cfm_cb) (struct hci_conn *conn, u8 status); void (*security_cfm_cb) (struct hci_conn *conn, u8 status); @@ -760,6 +778,7 @@ extern struct mutex hci_cb_list_lock; hci_dev_clear_flag(hdev, HCI_LE_ADV); \ hci_dev_clear_flag(hdev, HCI_LL_RPA_RESOLUTION);\ hci_dev_clear_flag(hdev, HCI_PERIODIC_INQ); \ + hci_dev_clear_flag(hdev, HCI_QUALITY_REPORT); \ } while (0) /* ----- HCI interface to upper protocols ----- */ @@ -1099,13 +1118,14 @@ struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst, u16 conn_timeout, enum conn_reasons conn_reason); struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, - u8 dst_type, u8 sec_level, u16 conn_timeout, - u8 role, bdaddr_t *direct_rpa); + u8 dst_type, bool dst_resolved, u8 sec_level, + u16 conn_timeout, u8 role, + bdaddr_t *direct_rpa); struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, u8 sec_level, u8 auth_type, enum conn_reasons conn_reason); struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst, - __u16 setting); + __u16 setting, struct bt_codec *codec); 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, @@ -1360,6 +1380,8 @@ int hci_set_adv_instance_data(struct hci_dev *hdev, u8 instance, u16 scan_rsp_len, u8 *scan_rsp_data); int hci_remove_adv_instance(struct hci_dev *hdev, u8 instance); void hci_adv_instances_set_rpa_expired(struct hci_dev *hdev, bool rpa_expired); +u32 hci_adv_instance_flags(struct hci_dev *hdev, u8 instance); +bool hci_adv_instance_is_scannable(struct hci_dev *hdev, u8 instance); void hci_adv_monitors_clear(struct hci_dev *hdev); void hci_free_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor); @@ -1442,6 +1464,9 @@ void hci_conn_del_sysfs(struct hci_conn *conn); /* Use LL Privacy based address resolution if supported */ #define use_ll_privacy(dev) ((dev)->le_features[0] & HCI_LE_LL_PRIVACY) +/* Use enhanced synchronous connection if command is supported */ +#define enhanced_sco_capable(dev) ((dev)->commands[29] & 0x08) + /* Use ext scanning if set ext scan param and ext scan enable is supported */ #define use_ext_scan(dev) (((dev)->commands[37] & 0x20) && \ ((dev)->commands[37] & 0x40)) @@ -1609,43 +1634,6 @@ static inline void hci_role_switch_cfm(struct hci_conn *conn, __u8 status, mutex_unlock(&hci_cb_list_lock); } -static inline void *eir_get_data(u8 *eir, size_t eir_len, u8 type, - size_t *data_len) -{ - size_t parsed = 0; - - if (eir_len < 2) - return NULL; - - while (parsed < eir_len - 1) { - u8 field_len = eir[0]; - - if (field_len == 0) - break; - - parsed += field_len + 1; - - if (parsed > eir_len) - break; - - if (eir[1] != type) { - eir += field_len + 1; - continue; - } - - /* Zero length data */ - if (field_len == 1) - return NULL; - - if (data_len) - *data_len = field_len - 1; - - return &eir[2]; - } - - return NULL; -} - static inline bool hci_bdaddr_is_rpa(bdaddr_t *bdaddr, u8 addr_type) { if (addr_type != ADDR_LE_DEV_RANDOM) @@ -1867,4 +1855,9 @@ void hci_copy_identity_address(struct hci_dev *hdev, bdaddr_t *bdaddr, #define SCO_AIRMODE_CVSD 0x0000 #define SCO_AIRMODE_TRANSP 0x0003 +#define LOCAL_CODEC_ACL_MASK BIT(0) +#define LOCAL_CODEC_SCO_MASK BIT(1) + +#define TRANSPORT_TYPE_MAX 0x04 + #endif /* __HCI_CORE_H */ diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 40296ed976a9..4202c609bb0b 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -130,7 +130,8 @@ static inline void skb_mark_napi_id(struct sk_buff *skb, static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL - WRITE_ONCE(sk->sk_napi_id, skb->napi_id); + if (unlikely(READ_ONCE(sk->sk_napi_id) != skb->napi_id)) + WRITE_ONCE(sk->sk_napi_id, skb->napi_id); #endif sk_rx_queue_set(sk, skb); } diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 27336fc70467..423f97b982ff 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -740,6 +740,22 @@ struct cfg80211_tid_config { }; /** + * struct cfg80211_fils_aad - FILS AAD data + * @macaddr: STA MAC address + * @kek: FILS KEK + * @kek_len: FILS KEK length + * @snonce: STA Nonce + * @anonce: AP Nonce + */ +struct cfg80211_fils_aad { + const u8 *macaddr; + const u8 *kek; + u8 kek_len; + const u8 *snonce; + const u8 *anonce; +}; + +/** * cfg80211_get_chandef_type - return old channel type from chandef * @chandef: the channel definition * @@ -1041,6 +1057,36 @@ struct cfg80211_crypto_settings { }; /** + * struct cfg80211_mbssid_config - AP settings for multi bssid + * + * @tx_wdev: pointer to the transmitted interface in the MBSSID set + * @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 index; + bool ema; +}; + +/** + * struct cfg80211_mbssid_elems - Multiple BSSID elements + * + * @cnt: Number of elements in array %elems. + * + * @elem: Array of multiple BSSID element(s) to be added into Beacon frames. + * @elem.data: Data for multiple BSSID elements. + * @elem.len: Length of data. + */ +struct cfg80211_mbssid_elems { + u8 cnt; + struct { + const u8 *data; + size_t len; + } elem[]; +}; + +/** * struct cfg80211_beacon_data - beacon data * @head: head portion of beacon (before TIM IE) * or %NULL if not changed @@ -1058,6 +1104,7 @@ struct cfg80211_crypto_settings { * @assocresp_ies_len: length of assocresp_ies in octets * @probe_resp_len: length of probe response template (@probe_resp) * @probe_resp: probe response template (AP mode only) + * @mbssid_ies: multiple BSSID elements * @ftm_responder: enable FTM responder functionality; -1 for no change * (which also implies no change in LCI/civic location data) * @lci: Measurement Report element content, starting with Measurement Token @@ -1075,6 +1122,7 @@ struct cfg80211_beacon_data { const u8 *probe_resp; const u8 *lci; const u8 *civicloc; + struct cfg80211_mbssid_elems *mbssid_ies; s8 ftm_responder; size_t head_len, tail_len; @@ -1189,6 +1237,7 @@ enum cfg80211_ap_settings_flags { * @he_oper: HE operation IE (or %NULL if HE isn't enabled) * @fils_discovery: FILS discovery transmission parameters * @unsol_bcast_probe_resp: Unsolicited broadcast probe response parameters + * @mbssid_config: AP settings for multiple bssid */ struct cfg80211_ap_settings { struct cfg80211_chan_def chandef; @@ -1221,6 +1270,7 @@ struct cfg80211_ap_settings { struct cfg80211_he_bss_color he_bss_color; struct cfg80211_fils_discovery fils_discovery; struct cfg80211_unsol_bcast_probe_resp unsol_bcast_probe_resp; + struct cfg80211_mbssid_config mbssid_config; }; /** @@ -4018,6 +4068,10 @@ struct mgmt_frame_regs { * @set_sar_specs: Update the SAR (TX power) settings. * * @color_change: Initiate a color change. + * + * @set_fils_aad: Set FILS AAD data to the AP driver so that the driver can use + * those to decrypt (Re)Association Request and encrypt (Re)Association + * Response frame. */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -4348,6 +4402,8 @@ struct cfg80211_ops { int (*color_change)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_color_change_settings *params); + int (*set_fils_aad)(struct wiphy *wiphy, struct net_device *dev, + struct cfg80211_fils_aad *fils_aad); }; /* @@ -4981,6 +5037,13 @@ struct wiphy_iftype_akm_suites { * %NL80211_TID_CONFIG_ATTR_RETRY_LONG attributes * @sar_capa: SAR control capabilities * @rfkill: a pointer to the rfkill structure + * + * @mbssid_max_interfaces: maximum number of interfaces supported by the driver + * in a multiple BSSID set. This field must be set to a non-zero value + * by the driver to advertise MBSSID support. + * @ema_max_profile_periodicity: maximum profile periodicity supported by + * the driver. Setting this field to a non-zero value indicates that the + * driver supports enhanced multi-BSSID advertisements (EMA AP). */ struct wiphy { struct mutex mtx; @@ -5125,6 +5188,9 @@ struct wiphy { struct rfkill *rfkill; + u8 mbssid_max_interfaces; + u8 ema_max_profile_periodicity; + char priv[] __aligned(NETDEV_ALIGN); }; @@ -5490,7 +5556,7 @@ struct wireless_dev { unsigned long unprot_beacon_reported; }; -static inline u8 *wdev_address(struct wireless_dev *wdev) +static inline const u8 *wdev_address(struct wireless_dev *wdev) { if (wdev->netdev) return wdev->netdev->dev_addr; @@ -6309,6 +6375,17 @@ static inline void cfg80211_gen_new_bssid(const u8 *bssid, u8 max_bssid, } /** + * cfg80211_get_ies_channel_number - returns the channel number from ies + * @ie: IEs + * @ielen: length of IEs + * @band: enum nl80211_band of the channel + * + * Returns 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); + +/** * cfg80211_is_element_inherited - returns if element ID should be inherited * @element: element to check * @non_inherit_element: non inheritance element diff --git a/include/net/codel.h b/include/net/codel.h index a6e428f80135..a6c9e34e62b8 100644 --- a/include/net/codel.h +++ b/include/net/codel.h @@ -102,6 +102,9 @@ static inline u32 codel_time_to_us(codel_time_t val) * @interval: width of moving time window * @mtu: device mtu, or minimal queue backlog in bytes. * @ecn: is Explicit Congestion Notification enabled + * @ce_threshold_selector: apply ce_threshold to packets matching this value + * in the diffserv/ECN byte of the IP header + * @ce_threshold_mask: mask to apply to ce_threshold_selector comparison */ struct codel_params { codel_time_t target; @@ -109,6 +112,8 @@ struct codel_params { codel_time_t interval; u32 mtu; bool ecn; + u8 ce_threshold_selector; + u8 ce_threshold_mask; }; /** diff --git a/include/net/codel_impl.h b/include/net/codel_impl.h index d289b91dcd65..137d40d8cbeb 100644 --- a/include/net/codel_impl.h +++ b/include/net/codel_impl.h @@ -54,6 +54,8 @@ static void codel_params_init(struct codel_params *params) params->interval = MS2TIME(100); params->target = MS2TIME(5); params->ce_threshold = CODEL_DISABLED_THRESHOLD; + params->ce_threshold_mask = 0; + params->ce_threshold_selector = 0; params->ecn = false; } @@ -246,9 +248,19 @@ static struct sk_buff *codel_dequeue(void *ctx, vars->rec_inv_sqrt); } end: - if (skb && codel_time_after(vars->ldelay, params->ce_threshold) && - INET_ECN_set_ce(skb)) - stats->ce_mark++; + if (skb && codel_time_after(vars->ldelay, params->ce_threshold)) { + bool set_ce = true; + + if (params->ce_threshold_mask) { + int dsfield = skb_get_dsfield(skb); + + set_ce = (dsfield >= 0 && + (((u8)dsfield & params->ce_threshold_mask) == + params->ce_threshold_selector)); + } + if (set_ce && INET_ECN_set_ce(skb)) + stats->ce_mark++; + } return skb; } diff --git a/include/net/datalink.h b/include/net/datalink.h index a9663229b913..d9b7faaa539f 100644 --- a/include/net/datalink.h +++ b/include/net/datalink.h @@ -12,7 +12,7 @@ struct datalink_proto { int (*rcvfunc)(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *); int (*request)(struct datalink_proto *, struct sk_buff *, - unsigned char *); + const unsigned char *); struct list_head node; }; diff --git a/include/net/devlink.h b/include/net/devlink.h index 154cf0dbca37..aab3d007c577 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -21,45 +21,7 @@ #include <linux/xarray.h> #include <linux/firmware.h> -#define DEVLINK_RELOAD_STATS_ARRAY_SIZE \ - (__DEVLINK_RELOAD_LIMIT_MAX * __DEVLINK_RELOAD_ACTION_MAX) - -struct devlink_dev_stats { - u32 reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; - u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; -}; - -struct devlink_ops; - -struct devlink { - u32 index; - struct list_head port_list; - struct list_head rate_list; - struct list_head sb_list; - struct list_head dpipe_table_list; - struct list_head resource_list; - struct list_head param_list; - struct list_head region_list; - struct list_head reporter_list; - struct mutex reporters_lock; /* protects reporter_list */ - struct devlink_dpipe_headers *dpipe_headers; - struct list_head trap_list; - struct list_head trap_group_list; - struct list_head trap_policer_list; - const struct devlink_ops *ops; - struct xarray snapshot_ids; - struct devlink_dev_stats stats; - struct device *dev; - possible_net_t _net; - struct mutex lock; /* Serializes access to devlink instance specific objects such as - * port, sb, dpipe, resource, params, region, traps and more. - */ - u8 reload_failed:1, - reload_enabled:1; - refcount_t refcount; - struct completion comp; - char priv[0] __aligned(NETDEV_ALIGN); -}; +struct devlink; struct devlink_port_phys_attrs { u32 port_number; /* Same value as "split group". @@ -506,7 +468,6 @@ struct devlink_param_item { const struct devlink_param *param; union devlink_param_value driverinit_value; bool driverinit_value_valid; - bool published; }; enum devlink_param_generic_id { @@ -1224,6 +1185,11 @@ enum devlink_trap_group_generic_id { .min_burst = _min_burst, \ } +enum { + /* device supports reload operations */ + DEVLINK_F_RELOAD = 1UL << 0, +}; + struct devlink_ops { /** * @supported_flash_update_params: @@ -1520,34 +1486,9 @@ struct devlink_ops { struct netlink_ext_ack *extack); }; -static inline void *devlink_priv(struct devlink *devlink) -{ - BUG_ON(!devlink); - return &devlink->priv; -} - -static inline struct devlink *priv_to_devlink(void *priv) -{ - BUG_ON(!priv); - return container_of(priv, struct devlink, priv); -} - -static inline struct devlink_port * -netdev_to_devlink_port(struct net_device *dev) -{ - if (dev->netdev_ops->ndo_get_devlink_port) - return dev->netdev_ops->ndo_get_devlink_port(dev); - return NULL; -} - -static inline struct devlink *netdev_to_devlink(struct net_device *dev) -{ - struct devlink_port *devlink_port = netdev_to_devlink_port(dev); - - if (devlink_port) - return devlink_port->devlink; - return NULL; -} +void *devlink_priv(struct devlink *devlink); +struct devlink *priv_to_devlink(void *priv); +struct device *devlink_to_dev(const struct devlink *devlink); struct ib_device; @@ -1566,10 +1507,9 @@ static inline struct devlink *devlink_alloc(const struct devlink_ops *ops, { return devlink_alloc_ns(ops, priv_size, &init_net, dev); } -int devlink_register(struct devlink *devlink); +void devlink_set_features(struct devlink *devlink, u64 features); +void devlink_register(struct devlink *devlink); void devlink_unregister(struct devlink *devlink); -void devlink_reload_enable(struct devlink *devlink); -void devlink_reload_disable(struct devlink *devlink); void devlink_free(struct devlink *devlink); int devlink_port_register(struct devlink *devlink, struct devlink_port *devlink_port, @@ -1651,34 +1591,11 @@ int devlink_param_register(struct devlink *devlink, const struct devlink_param *param); void devlink_param_unregister(struct devlink *devlink, const struct devlink_param *param); -void devlink_params_publish(struct devlink *devlink); -void devlink_params_unpublish(struct devlink *devlink); -void devlink_param_publish(struct devlink *devlink, - const struct devlink_param *param); -void devlink_param_unpublish(struct devlink *devlink, - const struct devlink_param *param); -int devlink_port_params_register(struct devlink_port *devlink_port, - const struct devlink_param *params, - size_t params_count); -void devlink_port_params_unregister(struct devlink_port *devlink_port, - const struct devlink_param *params, - size_t params_count); int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, union devlink_param_value *init_val); int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, union devlink_param_value init_val); -int -devlink_port_param_driverinit_value_get(struct devlink_port *devlink_port, - u32 param_id, - union devlink_param_value *init_val); -int devlink_port_param_driverinit_value_set(struct devlink_port *devlink_port, - u32 param_id, - union devlink_param_value init_val); void devlink_param_value_changed(struct devlink *devlink, u32 param_id); -void devlink_port_param_value_changed(struct devlink_port *devlink_port, - u32 param_id); -void devlink_param_value_str_fill(union devlink_param_value *dst_val, - const char *src); struct devlink_region * devlink_region_create(struct devlink *devlink, const struct devlink_region_ops *ops, @@ -1723,10 +1640,7 @@ int devlink_fmsg_binary_pair_nest_start(struct devlink_fmsg *fmsg, const char *name); int devlink_fmsg_binary_pair_nest_end(struct devlink_fmsg *fmsg); -int devlink_fmsg_bool_put(struct devlink_fmsg *fmsg, bool value); -int devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value); int devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value); -int devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value); int devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value); int devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, u16 value_len); @@ -1812,9 +1726,12 @@ devlink_trap_policers_unregister(struct devlink *devlink, #if IS_ENABLED(CONFIG_NET_DEVLINK) -void devlink_compat_running_version(struct net_device *dev, +struct devlink *__must_check devlink_try_get(struct devlink *devlink); +void devlink_put(struct devlink *devlink); + +void devlink_compat_running_version(struct devlink *devlink, char *buf, size_t len); -int devlink_compat_flash_update(struct net_device *dev, const char *file_name); +int devlink_compat_flash_update(struct devlink *devlink, const char *file_name); int devlink_compat_phys_port_name_get(struct net_device *dev, char *name, size_t len); int devlink_compat_switch_id_get(struct net_device *dev, @@ -1822,13 +1739,22 @@ int devlink_compat_switch_id_get(struct net_device *dev, #else +static inline struct devlink *devlink_try_get(struct devlink *devlink) +{ + return NULL; +} + +static inline void devlink_put(struct devlink *devlink) +{ +} + static inline void -devlink_compat_running_version(struct net_device *dev, char *buf, size_t len) +devlink_compat_running_version(struct devlink *devlink, char *buf, size_t len) { } static inline int -devlink_compat_flash_update(struct net_device *dev, const char *file_name) +devlink_compat_flash_update(struct devlink *devlink, const char *file_name) { return -EOPNOTSUPP; } diff --git a/include/net/dn.h b/include/net/dn.h index 56ab0726c641..ba9655b0098a 100644 --- a/include/net/dn.h +++ b/include/net/dn.h @@ -166,7 +166,7 @@ struct dn_skb_cb { int iif; }; -static inline __le16 dn_eth2dn(unsigned char *ethaddr) +static inline __le16 dn_eth2dn(const unsigned char *ethaddr) { return get_unaligned((__le16 *)(ethaddr + 4)); } diff --git a/include/net/dsa.h b/include/net/dsa.h index d784e76113b8..eff5c44ba377 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -51,6 +51,7 @@ struct phylink_link_state; #define DSA_TAG_PROTO_SEVILLE_VALUE 21 #define DSA_TAG_PROTO_BRCM_LEGACY_VALUE 22 #define DSA_TAG_PROTO_SJA1110_VALUE 23 +#define DSA_TAG_PROTO_RTL8_4_VALUE 24 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -77,6 +78,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_OCELOT_8021Q = DSA_TAG_PROTO_OCELOT_8021Q_VALUE, DSA_TAG_PROTO_SEVILLE = DSA_TAG_PROTO_SEVILLE_VALUE, DSA_TAG_PROTO_SJA1110 = DSA_TAG_PROTO_SJA1110_VALUE, + DSA_TAG_PROTO_RTL8_4 = DSA_TAG_PROTO_RTL8_4_VALUE, }; struct dsa_switch; @@ -285,6 +287,7 @@ struct dsa_port { /* List of MAC addresses that must be forwarded on this port. * These are only valid on CPU ports and DSA links. */ + struct mutex addr_lists_lock; struct list_head fdbs; struct list_head mdbs; @@ -472,14 +475,41 @@ static inline bool dsa_is_user_port(struct dsa_switch *ds, int p) return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_USER; } +#define dsa_tree_for_each_user_port(_dp, _dst) \ + list_for_each_entry((_dp), &(_dst)->ports, list) \ + if (dsa_port_is_user((_dp))) + +#define dsa_switch_for_each_port(_dp, _ds) \ + list_for_each_entry((_dp), &(_ds)->dst->ports, list) \ + if ((_dp)->ds == (_ds)) + +#define dsa_switch_for_each_port_safe(_dp, _next, _ds) \ + list_for_each_entry_safe((_dp), (_next), &(_ds)->dst->ports, list) \ + if ((_dp)->ds == (_ds)) + +#define dsa_switch_for_each_port_continue_reverse(_dp, _ds) \ + list_for_each_entry_continue_reverse((_dp), &(_ds)->dst->ports, list) \ + if ((_dp)->ds == (_ds)) + +#define dsa_switch_for_each_available_port(_dp, _ds) \ + dsa_switch_for_each_port((_dp), (_ds)) \ + if (!dsa_port_is_unused((_dp))) + +#define dsa_switch_for_each_user_port(_dp, _ds) \ + dsa_switch_for_each_port((_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))) + static inline u32 dsa_user_ports(struct dsa_switch *ds) { + struct dsa_port *dp; u32 mask = 0; - int p; - for (p = 0; p < ds->num_ports; p++) - if (dsa_is_user_port(ds, p)) - mask |= BIT(p); + dsa_switch_for_each_user_port(dp, ds) + mask |= BIT(dp->index); return mask; } @@ -615,6 +645,8 @@ struct dsa_switch_ops { /* * PHYLINK integration */ + void (*phylink_get_interfaces)(struct dsa_switch *ds, int port, + unsigned long *supported_interfaces); void (*phylink_validate)(struct dsa_switch *ds, int port, unsigned long *supported, struct phylink_link_state *state); @@ -645,6 +677,12 @@ struct dsa_switch_ops { int (*get_sset_count)(struct dsa_switch *ds, int port, int sset); void (*get_ethtool_phy_stats)(struct dsa_switch *ds, int port, uint64_t *data); + void (*get_eth_phy_stats)(struct dsa_switch *ds, int port, + struct ethtool_eth_phy_stats *phy_stats); + void (*get_eth_mac_stats)(struct dsa_switch *ds, int port, + struct ethtool_eth_mac_stats *mac_stats); + void (*get_eth_ctrl_stats)(struct dsa_switch *ds, int port, + struct ethtool_eth_ctrl_stats *ctrl_stats); void (*get_stats64)(struct dsa_switch *ds, int port, struct rtnl_link_stats64 *s); void (*self_test)(struct dsa_switch *ds, int port, diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index ffd386ea0dbb..aa33e1092e2c 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -287,6 +287,7 @@ enum flow_dissector_key_id { #define FLOW_DISSECTOR_F_PARSE_1ST_FRAG BIT(0) #define FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL BIT(1) #define FLOW_DISSECTOR_F_STOP_AT_ENCAP BIT(2) +#define FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP BIT(3) struct flow_dissector_key { enum flow_dissector_key_id key_id; diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h index 1424e02cef90..7aa2b8e1fb29 100644 --- a/include/net/gen_stats.h +++ b/include/net/gen_stats.h @@ -7,14 +7,17 @@ #include <linux/rtnetlink.h> #include <linux/pkt_sched.h> -/* Note: this used to be in include/uapi/linux/gen_stats.h */ -struct gnet_stats_basic_packed { - __u64 bytes; - __u64 packets; -}; - -struct gnet_stats_basic_cpu { - struct gnet_stats_basic_packed bstats; +/* Throughput stats. + * Must be initialized beforehand with gnet_stats_basic_sync_init(). + * + * If no reads can ever occur parallel to writes (e.g. stack-allocated + * bstats), then the internal stat values can be written to and read + * from directly. Otherwise, use _bstats_set/update() for writes and + * gnet_stats_add_basic() for reads. + */ +struct gnet_stats_basic_sync { + u64_stats_t bytes; + u64_stats_t packets; struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); @@ -34,6 +37,7 @@ struct gnet_dump { struct tc_stats tc_stats; }; +void gnet_stats_basic_sync_init(struct gnet_stats_basic_sync *b); int gnet_stats_start_copy(struct sk_buff *skb, int type, spinlock_t *lock, struct gnet_dump *d, int padattr); @@ -42,41 +46,38 @@ int gnet_stats_start_copy_compat(struct sk_buff *skb, int type, spinlock_t *lock, struct gnet_dump *d, int padattr); -int gnet_stats_copy_basic(const seqcount_t *running, - struct gnet_dump *d, - struct gnet_stats_basic_cpu __percpu *cpu, - struct gnet_stats_basic_packed *b); -void __gnet_stats_copy_basic(const seqcount_t *running, - struct gnet_stats_basic_packed *bstats, - struct gnet_stats_basic_cpu __percpu *cpu, - struct gnet_stats_basic_packed *b); -int gnet_stats_copy_basic_hw(const seqcount_t *running, - struct gnet_dump *d, - struct gnet_stats_basic_cpu __percpu *cpu, - struct gnet_stats_basic_packed *b); +int gnet_stats_copy_basic(struct gnet_dump *d, + struct gnet_stats_basic_sync __percpu *cpu, + struct gnet_stats_basic_sync *b, bool running); +void gnet_stats_add_basic(struct gnet_stats_basic_sync *bstats, + struct gnet_stats_basic_sync __percpu *cpu, + struct gnet_stats_basic_sync *b, bool running); +int gnet_stats_copy_basic_hw(struct gnet_dump *d, + struct gnet_stats_basic_sync __percpu *cpu, + struct gnet_stats_basic_sync *b, bool running); int gnet_stats_copy_rate_est(struct gnet_dump *d, struct net_rate_estimator __rcu **ptr); int gnet_stats_copy_queue(struct gnet_dump *d, struct gnet_stats_queue __percpu *cpu_q, struct gnet_stats_queue *q, __u32 qlen); -void __gnet_stats_copy_queue(struct gnet_stats_queue *qstats, - const struct gnet_stats_queue __percpu *cpu_q, - const struct gnet_stats_queue *q, __u32 qlen); +void gnet_stats_add_queue(struct gnet_stats_queue *qstats, + const struct gnet_stats_queue __percpu *cpu_q, + const struct gnet_stats_queue *q); int gnet_stats_copy_app(struct gnet_dump *d, void *st, int len); int gnet_stats_finish_copy(struct gnet_dump *d); -int gen_new_estimator(struct gnet_stats_basic_packed *bstats, - struct gnet_stats_basic_cpu __percpu *cpu_bstats, +int gen_new_estimator(struct gnet_stats_basic_sync *bstats, + struct gnet_stats_basic_sync __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *lock, - seqcount_t *running, struct nlattr *opt); + bool running, struct nlattr *opt); void gen_kill_estimator(struct net_rate_estimator __rcu **ptr); -int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, - struct gnet_stats_basic_cpu __percpu *cpu_bstats, +int gen_replace_estimator(struct gnet_stats_basic_sync *bstats, + struct gnet_stats_basic_sync __percpu *cpu_bstats, struct net_rate_estimator __rcu **ptr, spinlock_t *lock, - seqcount_t *running, struct nlattr *opt); + bool running, struct nlattr *opt); bool gen_estimator_active(struct net_rate_estimator __rcu **ptr); bool gen_estimator_read(struct net_rate_estimator __rcu **ptr, struct gnet_stats_rate_est64 *sample); diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index b06c2d02ec84..fa6a87246a7b 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -289,7 +289,7 @@ static inline void inet_csk_prepare_for_destroy_sock(struct sock *sk) { /* The below has to be done to allow calling inet_csk_destroy_sock */ sock_set_flag(sk, SOCK_DEAD); - percpu_counter_inc(sk->sk_prot->orphan_count); + this_cpu_inc(*sk->sk_prot->orphan_count); } void inet_csk_destroy_sock(struct sock *sk); diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h index ba77f47ef61e..ea32393464a2 100644 --- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -188,6 +188,23 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb) return 0; } +static inline int skb_get_dsfield(struct sk_buff *skb) +{ + switch (skb_protocol(skb, true)) { + case cpu_to_be16(ETH_P_IP): + if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) + break; + return ipv4_get_dsfield(ip_hdr(skb)); + + case cpu_to_be16(ETH_P_IPV6): + if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr))) + break; + return ipv6_get_dsfield(ipv6_hdr(skb)); + } + + return -1; +} + static inline int INET_ECN_set_ect1(struct sk_buff *skb) { switch (skb_protocol(skb, true)) { diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 89163ef8cf4b..9e1111f5915b 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -207,11 +207,10 @@ struct inet_sock { __be32 inet_saddr; __s16 uc_ttl; __u16 cmsg_flags; + struct ip_options_rcu __rcu *inet_opt; __be16 inet_sport; __u16 inet_id; - struct ip_options_rcu __rcu *inet_opt; - int rx_dst_ifindex; __u8 tos; __u8 min_ttl; __u8 mc_ttl; diff --git a/include/net/ioam6.h b/include/net/ioam6.h index 3c2993bc48c8..3f45ba37a2c6 100644 --- a/include/net/ioam6.h +++ b/include/net/ioam6.h @@ -56,7 +56,8 @@ static inline struct ioam6_pernet_data *ioam6_pernet(struct net *net) struct ioam6_namespace *ioam6_namespace(struct net *net, __be16 id); void ioam6_fill_trace_data(struct sk_buff *skb, struct ioam6_namespace *ns, - struct ioam6_trace_hdr *trace); + struct ioam6_trace_hdr *trace, + bool is_input); int ioam6_init(void); void ioam6_exit(void); diff --git a/include/net/ip.h b/include/net/ip.h index 9192444f2964..b71e88507c4a 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -24,6 +24,7 @@ #include <linux/skbuff.h> #include <linux/jhash.h> #include <linux/sockptr.h> +#include <linux/static_key.h> #include <net/inet_sock.h> #include <net/route.h> @@ -291,7 +292,11 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, #define NET_ADD_STATS(net, field, adnd) SNMP_ADD_STATS((net)->mib.net_statistics, field, adnd) #define __NET_ADD_STATS(net, field, adnd) __SNMP_ADD_STATS((net)->mib.net_statistics, field, adnd) -u64 snmp_get_cpu_field(void __percpu *mib, int cpu, int offct); +static inline u64 snmp_get_cpu_field(void __percpu *mib, int cpu, int offt) +{ + return *(((unsigned long *)per_cpu_ptr(mib, cpu)) + offt); +} + unsigned long snmp_fold_field(void __percpu *mib, int offt); #if BITS_PER_LONG==32 u64 snmp_get_cpu_field64(void __percpu *mib, int cpu, int offct, @@ -746,6 +751,7 @@ void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk, struct sk_buff *skb, int tlen, int offset); int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, bool allow_ipv6); +DECLARE_STATIC_KEY_FALSE(ip4_min_ttl); int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 7cb5a1aace40..ff1804a0c469 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -931,6 +931,7 @@ struct netns_ipvs { int sysctl_conn_reuse_mode; int sysctl_schedule_icmp; int sysctl_ignore_tunneled; + int sysctl_run_estimation; /* ip_vs_lblc */ int sysctl_lblc_expiration; @@ -1071,6 +1072,11 @@ static inline int sysctl_cache_bypass(struct netns_ipvs *ipvs) return ipvs->sysctl_cache_bypass; } +static inline int sysctl_run_estimation(struct netns_ipvs *ipvs) +{ + return ipvs->sysctl_run_estimation; +} + #else static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs) @@ -1163,6 +1169,11 @@ static inline int sysctl_cache_bypass(struct netns_ipvs *ipvs) return 0; } +static inline int sysctl_run_estimation(struct netns_ipvs *ipvs) +{ + return 1; +} + #endif /* IPVS core functions diff --git a/include/net/ipv6.h b/include/net/ipv6.h index f2d0ecc257bb..c19bf51ded1d 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1092,6 +1092,7 @@ struct in6_addr *fl6_update_dst(struct flowi6 *fl6, /* * socket options (ipv6_sockglue.c) */ +DECLARE_STATIC_KEY_FALSE(ip6_min_hopcount); int ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); diff --git a/include/net/llc.h b/include/net/llc.h index df282d9b4017..fd1f9a3fd8dd 100644 --- a/include/net/llc.h +++ b/include/net/llc.h @@ -133,7 +133,7 @@ static inline void llc_sap_put(struct llc_sap *sap) struct llc_sap *llc_sap_find(unsigned char sap_value); int llc_build_and_send_ui_pkt(struct llc_sap *sap, struct sk_buff *skb, - unsigned char *dmac, unsigned char dsap); + const unsigned char *dmac, unsigned char dsap); void llc_sap_handler(struct llc_sap *sap, struct sk_buff *skb); void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb); diff --git a/include/net/llc_if.h b/include/net/llc_if.h index 8d5c543cd620..c72570a21a4f 100644 --- a/include/net/llc_if.h +++ b/include/net/llc_if.h @@ -62,7 +62,8 @@ #define LLC_STATUS_CONFLICT 7 /* disconnect conn */ #define LLC_STATUS_RESET_DONE 8 /* */ -int llc_establish_connection(struct sock *sk, u8 *lmac, u8 *dmac, u8 dsap); +int llc_establish_connection(struct sock *sk, const u8 *lmac, u8 *dmac, + u8 dsap); int llc_build_and_send_pkt(struct sock *sk, struct sk_buff *skb); int llc_send_disc(struct sock *sk); #endif /* LLC_IF_H */ diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 618d1f427cb2..dd757f0987b0 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -632,6 +632,10 @@ struct ieee80211_fils_discovery { * @s1g: BSS is S1G BSS (affects Association Request format). * @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. + * @pwr_reduction: power constraint of BSS. */ struct ieee80211_bss_conf { const u8 *bssid; @@ -702,6 +706,10 @@ struct ieee80211_bss_conf { u32 unsol_bcast_probe_resp_interval; bool s1g; 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; + u8 pwr_reduction; }; /** @@ -1715,6 +1723,7 @@ enum ieee80211_offload_flags { * write-protected by sdata_lock and local->mtx so holding either is fine * for read access. * @color_change_color: the bss color that will be used after the change. + * @mbssid_tx_vif: Pointer to the transmitting interface if MBSSID is enabled. */ struct ieee80211_vif { enum nl80211_iftype type; @@ -1746,6 +1755,8 @@ struct ieee80211_vif { bool color_change_active; u8 color_change_color; + struct ieee80211_vif *mbssid_tx_vif; + /* must be last */ u8 drv_priv[] __aligned(sizeof(void *)); }; diff --git a/include/net/mctp.h b/include/net/mctp.h index ffd2c23bd76d..7e35ec79b909 100644 --- a/include/net/mctp.h +++ b/include/net/mctp.h @@ -11,6 +11,7 @@ #include <linux/bits.h> #include <linux/mctp.h> +#include <linux/netdevice.h> #include <net/net_namespace.h> #include <net/sock.h> @@ -58,39 +59,53 @@ struct mctp_sock { mctp_eid_t bind_addr; __u8 bind_type; + /* sendmsg()/recvmsg() uses struct sockaddr_mctp_ext */ + bool addr_ext; + /* list of mctp_sk_key, for incoming tag lookup. updates protected * by sk->net->keys_lock */ struct hlist_head keys; + + /* mechanism for expiring allocated keys; will release an allocated + * tag, and any netdev state for a request/response pairing + */ + struct timer_list key_expiry; }; /* Key for matching incoming packets to sockets or reassembly contexts. * Packets are matched on (src,dest,tag). * - * Lifetime requirements: + * Lifetime / locking requirements: + * + * - individual key data (ie, the struct itself) is protected by key->lock; + * changes must be made with that lock held. + * + * - the lookup fields: peer_addr, local_addr and tag are set before the + * key is added to lookup lists, and never updated. * - * - keys are free()ed via RCU + * - A ref to the key must be held (throuh key->refs) if a pointer to the + * key is to be accessed after key->lock is released. * * - a mctp_sk_key contains a reference to a struct sock; this is valid * for the life of the key. On sock destruction (through unhash), the key is - * removed from lists (see below), and will not be observable after a RCU - * grace period. - * - * any RX occurring within that grace period may still queue to the socket, - * but will hit the SOCK_DEAD case before the socket is freed. + * removed from lists (see below), and marked invalid. * * - these mctp_sk_keys appear on two lists: * 1) the struct mctp_sock->keys list * 2) the struct netns_mctp->keys list * - * updates to either list are performed under the netns_mctp->keys - * lock. + * presences on these lists requires a (single) refcount to be held; both + * lists are updated as a single operation. + * + * Updates and lookups in either list are performed under the + * netns_mctp->keys lock. Lookup functions will need to lock the key and + * take a reference before unlocking the keys_lock. Consequently, the list's + * keys_lock *cannot* be acquired with the individual key->lock held. * * - a key may have a sk_buff attached as part of an in-progress message - * reassembly (->reasm_head). The reassembly context is protected by - * reasm_lock, which may be acquired with the keys lock (above) held, if - * necessary. Consequently, keys lock *cannot* be acquired with the - * reasm_lock held. + * reassembly (->reasm_head). The reasm data is protected by the individual + * key->lock. * * - there are two destruction paths for a mctp_sk_key: * @@ -101,6 +116,8 @@ struct mctp_sock { * the (complete) reply, or during reassembly errors. Here, we clean up * the reassembly context (marking reasm_dead, to prevent another from * starting), and remove the socket from the netns & socket lists. + * + * - through an expiry timeout, on a per-socket timer */ struct mctp_sk_key { mctp_eid_t peer_addr; @@ -116,20 +133,40 @@ struct mctp_sk_key { /* per-socket list */ struct hlist_node sklist; + /* lock protects against concurrent updates to the reassembly and + * expiry data below. + */ + spinlock_t lock; + + /* Keys are referenced during the output path, which may sleep */ + refcount_t refs; + /* incoming fragment reassembly context */ - spinlock_t reasm_lock; struct sk_buff *reasm_head; struct sk_buff **reasm_tailp; bool reasm_dead; u8 last_seq; - struct rcu_head rcu; + /* key validity */ + bool valid; + + /* expiry timeout; valid (above) cleared on expiry */ + unsigned long expiry; + + /* free to use for device flow state tracking. Initialised to + * zero on initial key creation + */ + unsigned long dev_flow_state; + struct mctp_dev *dev; }; struct mctp_skb_cb { unsigned int magic; unsigned int net; + int ifindex; /* extended/direct addressing if set */ mctp_eid_t src; + unsigned char halen; + unsigned char haddr[MAX_ADDR_LEN]; }; /* skb control-block accessors with a little extra debugging for initial @@ -153,10 +190,18 @@ static inline struct mctp_skb_cb *mctp_cb(struct sk_buff *skb) { struct mctp_skb_cb *cb = (void *)skb->cb; + BUILD_BUG_ON(sizeof(struct mctp_skb_cb) > sizeof(skb->cb)); WARN_ON(cb->magic != 0x4d435450); return (void *)(skb->cb); } +/* If CONFIG_MCTP_FLOWS, we may add one of these as a SKB extension, + * indicating the flow to the device driver. + */ +struct mctp_flow { + struct mctp_sk_key *key; +}; + /* Route definition. * * These are held in the pernet->mctp.routes list, with RCU protection for @@ -165,8 +210,7 @@ static inline struct mctp_skb_cb *mctp_cb(struct sk_buff *skb) * * Updates to the route table are performed under rtnl; all reads under RCU, * so routes cannot be referenced over a RCU grace period. Specifically: A - * caller cannot block between mctp_route_lookup and passing the route to - * mctp_do_route. + * caller cannot block between mctp_route_lookup and mctp_route_release() */ struct mctp_route { mctp_eid_t min, max; @@ -186,11 +230,11 @@ struct mctp_route { struct mctp_route *mctp_route_lookup(struct net *net, unsigned int dnet, mctp_eid_t daddr); -int mctp_do_route(struct mctp_route *rt, struct sk_buff *skb); - int mctp_local_output(struct sock *sk, struct mctp_route *rt, struct sk_buff *skb, mctp_eid_t daddr, u8 req_tag); +void mctp_key_unref(struct mctp_sk_key *key); + /* routing <--> device interface */ unsigned int mctp_default_net(struct net *net); int mctp_default_net_set(struct net *net, unsigned int index); diff --git a/include/net/mctpdevice.h b/include/net/mctpdevice.h index 71a11012fac7..5c0d04b5c12c 100644 --- a/include/net/mctpdevice.h +++ b/include/net/mctpdevice.h @@ -14,11 +14,17 @@ #include <linux/types.h> #include <linux/refcount.h> +struct mctp_sk_key; + struct mctp_dev { struct net_device *dev; + refcount_t refs; + unsigned int net; + const struct mctp_netdev_ops *ops; + /* Only modified under RTNL. Reads have addrs_lock held */ u8 *addrs; size_t num_addrs; @@ -27,9 +33,24 @@ struct mctp_dev { struct rcu_head rcu; }; +struct mctp_netdev_ops { + void (*release_flow)(struct mctp_dev *dev, + struct mctp_sk_key *key); +}; + #define MCTP_INITIAL_DEFAULT_NET 1 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); +void mctp_unregister_netdev(struct net_device *dev); + +void mctp_dev_hold(struct mctp_dev *mdev); +void mctp_dev_put(struct mctp_dev *mdev); + +void mctp_dev_set_key(struct mctp_dev *dev, struct mctp_sk_key *key); +void mctp_dev_release_key(struct mctp_dev *dev, struct mctp_sk_key *key); + #endif /* __NET_MCTPDEVICE_H */ diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 3214848402ec..a925349b4b89 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -12,6 +12,8 @@ #include <linux/tcp.h> #include <linux/types.h> +struct mptcp_info; +struct mptcp_sock; struct seq_file; /* MPTCP sk_buff extension data */ @@ -125,6 +127,8 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb); void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, struct mptcp_out_options *opts); +void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info); + /* move the skb extension owership, with the assumption that 'to' is * newly allocated */ diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 38e4094960ce..04341d86585d 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -137,7 +137,7 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev, u8 *opt, int opt_len, struct ndisc_options *ndopts); -void __ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data, +void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data, int data_len, int pad); #define NDISC_OPS_REDIRECT_DATA_SPACE 2 diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 22ced1381ede..38a0c1d24570 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -144,17 +144,18 @@ struct neighbour { struct timer_list timer; unsigned long used; atomic_t probes; - __u8 flags; - __u8 nud_state; - __u8 type; - __u8 dead; + u8 nud_state; + u8 type; + u8 dead; u8 protocol; + u32 flags; seqlock_t ha_lock; unsigned char ha[ALIGN(MAX_ADDR_LEN, sizeof(unsigned long))] __aligned(8); struct hh_cache hh; int (*output)(struct neighbour *, struct sk_buff *); const struct neigh_ops *ops; struct list_head gc_list; + struct list_head managed_list; struct rcu_head rcu; struct net_device *dev; u8 primary_key[0]; @@ -172,7 +173,7 @@ struct pneigh_entry { struct pneigh_entry *next; possible_net_t net; struct net_device *dev; - u8 flags; + u32 flags; u8 protocol; u8 key[]; }; @@ -216,11 +217,13 @@ struct neigh_table { int gc_thresh3; unsigned long last_flush; struct delayed_work gc_work; + struct delayed_work managed_work; struct timer_list proxy_timer; struct sk_buff_head proxy_queue; atomic_t entries; atomic_t gc_entries; struct list_head gc_list; + struct list_head managed_list; rwlock_t lock; unsigned long last_rand; struct neigh_statistics __percpu *stats; @@ -250,12 +253,21 @@ static inline void *neighbour_priv(const struct neighbour *n) } /* flags for neigh_update() */ -#define NEIGH_UPDATE_F_OVERRIDE 0x00000001 -#define NEIGH_UPDATE_F_WEAK_OVERRIDE 0x00000002 -#define NEIGH_UPDATE_F_OVERRIDE_ISROUTER 0x00000004 -#define NEIGH_UPDATE_F_EXT_LEARNED 0x20000000 -#define NEIGH_UPDATE_F_ISROUTER 0x40000000 -#define NEIGH_UPDATE_F_ADMIN 0x80000000 +#define NEIGH_UPDATE_F_OVERRIDE BIT(0) +#define NEIGH_UPDATE_F_WEAK_OVERRIDE BIT(1) +#define NEIGH_UPDATE_F_OVERRIDE_ISROUTER BIT(2) +#define NEIGH_UPDATE_F_USE BIT(3) +#define NEIGH_UPDATE_F_MANAGED BIT(4) +#define NEIGH_UPDATE_F_EXT_LEARNED BIT(5) +#define NEIGH_UPDATE_F_ISROUTER BIT(6) +#define NEIGH_UPDATE_F_ADMIN BIT(7) + +/* In-kernel representation for NDA_FLAGS_EXT flags: */ +#define NTF_OLD_MASK 0xff +#define NTF_EXT_SHIFT 8 +#define NTF_EXT_MASK (NTF_EXT_MANAGED) + +#define NTF_MANAGED (NTF_EXT_MANAGED << NTF_EXT_SHIFT) extern const struct nla_policy nda_policy[]; @@ -504,10 +516,15 @@ static inline int neigh_output(struct neighbour *n, struct sk_buff *skb, { const struct hh_cache *hh = &n->hh; - if ((n->nud_state & NUD_CONNECTED) && hh->hh_len && !skip_cache) + /* n->nud_state and hh->hh_len could be changed under us. + * neigh_hh_output() is taking care of the race later. + */ + if (!skip_cache && + (READ_ONCE(n->nud_state) & NUD_CONNECTED) && + READ_ONCE(hh->hh_len)) return neigh_hh_output(hh, skb); - else - return n->output(n, skb); + + return n->output(n, skb); } static inline struct neighbour * diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index a16171c5fd9e..a0d9e0b47ab8 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -21,13 +21,19 @@ struct module; #define NFT_JUMP_STACK_SIZE 16 +enum { + NFT_PKTINFO_L4PROTO = (1 << 0), + NFT_PKTINFO_INNER = (1 << 1), +}; + struct nft_pktinfo { struct sk_buff *skb; const struct nf_hook_state *state; - bool tprot_set; + u8 flags; u8 tprot; u16 fragoff; unsigned int thoff; + unsigned int inneroff; }; static inline struct sock *nft_sk(const struct nft_pktinfo *pkt) @@ -75,7 +81,7 @@ static inline void nft_set_pktinfo(struct nft_pktinfo *pkt, static inline void nft_set_pktinfo_unspec(struct nft_pktinfo *pkt) { - pkt->tprot_set = false; + pkt->flags = 0; pkt->tprot = 0; pkt->thoff = 0; pkt->fragoff = 0; diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h index eb4c094cd54d..c4a6147b0ef8 100644 --- a/include/net/netfilter/nf_tables_ipv4.h +++ b/include/net/netfilter/nf_tables_ipv4.h @@ -10,7 +10,7 @@ static inline void nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt) struct iphdr *ip; ip = ip_hdr(pkt->skb); - pkt->tprot_set = true; + pkt->flags = NFT_PKTINFO_L4PROTO; pkt->tprot = ip->protocol; pkt->thoff = ip_hdrlen(pkt->skb); pkt->fragoff = ntohs(ip->frag_off) & IP_OFFSET; @@ -36,7 +36,7 @@ static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt) else if (len < thoff) return -1; - pkt->tprot_set = true; + pkt->flags = NFT_PKTINFO_L4PROTO; pkt->tprot = iph->protocol; pkt->thoff = thoff; pkt->fragoff = ntohs(iph->frag_off) & IP_OFFSET; @@ -71,7 +71,7 @@ static inline int nft_set_pktinfo_ipv4_ingress(struct nft_pktinfo *pkt) goto inhdr_error; } - pkt->tprot_set = true; + pkt->flags = NFT_PKTINFO_L4PROTO; pkt->tprot = iph->protocol; pkt->thoff = thoff; pkt->fragoff = ntohs(iph->frag_off) & IP_OFFSET; @@ -82,4 +82,5 @@ inhdr_error: __IP_INC_STATS(nft_net(pkt), IPSTATS_MIB_INHDRERRORS); return -1; } + #endif diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h index 7595e02b00ba..ec7eaeaf4f04 100644 --- a/include/net/netfilter/nf_tables_ipv6.h +++ b/include/net/netfilter/nf_tables_ipv6.h @@ -18,7 +18,7 @@ static inline void nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt) return; } - pkt->tprot_set = true; + pkt->flags = NFT_PKTINFO_L4PROTO; pkt->tprot = protohdr; pkt->thoff = thoff; pkt->fragoff = frag_off; @@ -50,7 +50,7 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt) if (protohdr < 0) return -1; - pkt->tprot_set = true; + pkt->flags = NFT_PKTINFO_L4PROTO; pkt->tprot = protohdr; pkt->thoff = thoff; pkt->fragoff = frag_off; @@ -96,7 +96,7 @@ static inline int nft_set_pktinfo_ipv6_ingress(struct nft_pktinfo *pkt) if (protohdr < 0) goto inhdr_error; - pkt->tprot_set = true; + pkt->flags = NFT_PKTINFO_L4PROTO; pkt->tprot = protohdr; pkt->thoff = thoff; pkt->fragoff = frag_off; diff --git a/include/net/netfilter/xt_rateest.h b/include/net/netfilter/xt_rateest.h index 832ab69efda5..4c3809e141f4 100644 --- a/include/net/netfilter/xt_rateest.h +++ b/include/net/netfilter/xt_rateest.h @@ -6,7 +6,7 @@ struct xt_rateest { /* keep lock and bstats on same cache line to speedup xt_rateest_tg() */ - struct gnet_stats_basic_packed bstats; + struct gnet_stats_basic_sync bstats; spinlock_t lock; diff --git a/include/net/page_pool.h b/include/net/page_pool.h index a4082406a003..3855f069627f 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -216,24 +216,14 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, page_pool_put_full_page(pool, page, true); } -#define PAGE_POOL_DMA_USE_PP_FRAG_COUNT \ - (sizeof(dma_addr_t) > sizeof(unsigned long)) - static inline dma_addr_t page_pool_get_dma_addr(struct page *page) { - dma_addr_t ret = page->dma_addr; - - if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) - ret |= (dma_addr_t)page->dma_addr_upper << 16 << 16; - - return ret; + return page->dma_addr; } static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr) { page->dma_addr = addr; - if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) - page->dma_addr_upper = upper_32_bits(addr); } static inline void page_pool_set_frag_count(struct page *page, long nr) diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 83a6d0792180..193f88ebf629 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -765,7 +765,7 @@ struct tc_cookie { }; struct tc_qopt_offload_stats { - struct gnet_stats_basic_packed *bstats; + struct gnet_stats_basic_sync *bstats; struct gnet_stats_queue *qstats; }; @@ -885,7 +885,7 @@ struct tc_gred_qopt_offload_params { }; struct tc_gred_qopt_offload_stats { - struct gnet_stats_basic_packed bstats[MAX_DPs]; + struct gnet_stats_basic_sync bstats[MAX_DPs]; struct gnet_stats_queue qstats[MAX_DPs]; struct red_stats *xstats[MAX_DPs]; }; @@ -977,6 +977,7 @@ enum tc_tbf_command { TC_TBF_REPLACE, TC_TBF_DESTROY, TC_TBF_STATS, + TC_TBF_GRAFT, }; struct tc_tbf_qopt_offload_replace_params { @@ -992,6 +993,7 @@ struct tc_tbf_qopt_offload { union { struct tc_tbf_qopt_offload_replace_params replace_params; struct tc_qopt_offload_stats stats; + u32 child_handle; }; }; diff --git a/include/net/rose.h b/include/net/rose.h index cf517d306a28..0f0a4ce0fee7 100644 --- a/include/net/rose.h +++ b/include/net/rose.h @@ -162,8 +162,8 @@ extern int sysctl_rose_link_fail_timeout; extern int sysctl_rose_maximum_vcs; extern int sysctl_rose_window_size; -int rosecmp(rose_address *, rose_address *); -int rosecmpm(rose_address *, rose_address *, unsigned short); +int rosecmp(const rose_address *, const rose_address *); +int rosecmpm(const rose_address *, const rose_address *, unsigned short); char *rose2asc(char *buf, const rose_address *); struct sock *rose_find_socket(unsigned int, struct rose_neigh *); void rose_kill_by_neigh(struct rose_neigh *); @@ -205,8 +205,8 @@ extern const struct seq_operations rose_node_seqops; extern struct seq_operations rose_route_seqops; void rose_add_loopback_neigh(void); -int __must_check rose_add_loopback_node(rose_address *); -void rose_del_loopback_node(rose_address *); +int __must_check rose_add_loopback_node(const rose_address *); +void rose_del_loopback_node(const rose_address *); void rose_rt_device_down(struct net_device *); void rose_link_device_down(struct net_device *); struct net_device *rose_dev_first(void); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index c0069ac00e62..22179b2fda72 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -40,6 +40,13 @@ enum qdisc_state_t { __QDISC_STATE_DRAINING, }; +enum qdisc_state2_t { + /* Only for !TCQ_F_NOLOCK qdisc. Never access it directly. + * Use qdisc_run_begin/end() or qdisc_is_running() instead. + */ + __QDISC_STATE2_RUNNING, +}; + #define QDISC_STATE_MISSED BIT(__QDISC_STATE_MISSED) #define QDISC_STATE_DRAINING BIT(__QDISC_STATE_DRAINING) @@ -97,7 +104,7 @@ struct Qdisc { struct netdev_queue *dev_queue; struct net_rate_estimator __rcu *rate_est; - struct gnet_stats_basic_cpu __percpu *cpu_bstats; + struct gnet_stats_basic_sync __percpu *cpu_bstats; struct gnet_stats_queue __percpu *cpu_qstats; int pad; refcount_t refcnt; @@ -107,10 +114,10 @@ struct Qdisc { */ struct sk_buff_head gso_skb ____cacheline_aligned_in_smp; struct qdisc_skb_head q; - struct gnet_stats_basic_packed bstats; - seqcount_t running; + struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; unsigned long state; + unsigned long state2; /* must be written under qdisc spinlock */ struct Qdisc *next_sched; struct sk_buff_head skb_bad_txq; @@ -143,11 +150,15 @@ static inline struct Qdisc *qdisc_refcount_inc_nz(struct Qdisc *qdisc) return NULL; } +/* For !TCQ_F_NOLOCK qdisc: callers must either call this within a qdisc + * root_lock section, or provide their own memory barriers -- ordering + * against qdisc_run_begin/end() atomic bit operations. + */ static inline bool qdisc_is_running(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) return spin_is_locked(&qdisc->seqlock); - return (raw_read_seqcount(&qdisc->running) & 1) ? true : false; + return test_bit(__QDISC_STATE2_RUNNING, &qdisc->state2); } static inline bool nolock_qdisc_is_empty(const struct Qdisc *qdisc) @@ -167,6 +178,9 @@ static inline bool qdisc_is_empty(const struct Qdisc *qdisc) return !READ_ONCE(qdisc->q.qlen); } +/* For !TCQ_F_NOLOCK qdisc, qdisc_run_begin/end() must be invoked with + * the qdisc root lock acquired. + */ static inline bool qdisc_run_begin(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) { @@ -206,15 +220,8 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc) * after it releases the lock at the end of qdisc_run_end(). */ return spin_trylock(&qdisc->seqlock); - } else if (qdisc_is_running(qdisc)) { - return false; } - /* Variant of write_seqcount_begin() telling lockdep a trylock - * was attempted. - */ - raw_write_seqcount_begin(&qdisc->running); - seqcount_acquire(&qdisc->running.dep_map, 0, 1, _RET_IP_); - return true; + return !__test_and_set_bit(__QDISC_STATE2_RUNNING, &qdisc->state2); } static inline void qdisc_run_end(struct Qdisc *qdisc) @@ -226,7 +233,7 @@ static inline void qdisc_run_end(struct Qdisc *qdisc) &qdisc->state))) __netif_schedule(qdisc); } else { - write_seqcount_end(&qdisc->running); + __clear_bit(__QDISC_STATE2_RUNNING, &qdisc->state2); } } @@ -308,6 +315,8 @@ struct Qdisc_ops { struct netlink_ext_ack *extack); void (*attach)(struct Qdisc *sch); int (*change_tx_queue_len)(struct Qdisc *, unsigned int); + void (*change_real_num_tx)(struct Qdisc *sch, + unsigned int new_real_tx); int (*dump)(struct Qdisc *, struct sk_buff *); int (*dump_stats)(struct Qdisc *, struct gnet_dump *); @@ -590,14 +599,6 @@ static inline spinlock_t *qdisc_root_sleeping_lock(const struct Qdisc *qdisc) return qdisc_lock(root); } -static inline seqcount_t *qdisc_root_sleeping_running(const struct Qdisc *qdisc) -{ - struct Qdisc *root = qdisc_root_sleeping(qdisc); - - ASSERT_RTNL(); - return &root->running; -} - static inline struct net_device *qdisc_dev(const struct Qdisc *qdisc) { return qdisc->dev_queue->dev; @@ -684,6 +685,8 @@ void qdisc_class_hash_grow(struct Qdisc *, struct Qdisc_class_hash *); void qdisc_class_hash_destroy(struct Qdisc_class_hash *); int dev_qdisc_change_tx_queue_len(struct net_device *dev); +void dev_qdisc_change_real_num_tx(struct net_device *dev, + unsigned int new_real_tx); void dev_init_scheduler(struct net_device *dev); void dev_shutdown(struct net_device *dev); void dev_activate(struct net_device *dev); @@ -845,14 +848,16 @@ static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, return sch->enqueue(skb, sch, to_free); } -static inline void _bstats_update(struct gnet_stats_basic_packed *bstats, +static inline void _bstats_update(struct gnet_stats_basic_sync *bstats, __u64 bytes, __u32 packets) { - bstats->bytes += bytes; - bstats->packets += packets; + u64_stats_update_begin(&bstats->syncp); + u64_stats_add(&bstats->bytes, bytes); + u64_stats_add(&bstats->packets, packets); + u64_stats_update_end(&bstats->syncp); } -static inline void bstats_update(struct gnet_stats_basic_packed *bstats, +static inline void bstats_update(struct gnet_stats_basic_sync *bstats, const struct sk_buff *skb) { _bstats_update(bstats, @@ -860,26 +865,10 @@ static inline void bstats_update(struct gnet_stats_basic_packed *bstats, skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1); } -static inline void _bstats_cpu_update(struct gnet_stats_basic_cpu *bstats, - __u64 bytes, __u32 packets) -{ - u64_stats_update_begin(&bstats->syncp); - _bstats_update(&bstats->bstats, bytes, packets); - u64_stats_update_end(&bstats->syncp); -} - -static inline void bstats_cpu_update(struct gnet_stats_basic_cpu *bstats, - const struct sk_buff *skb) -{ - u64_stats_update_begin(&bstats->syncp); - bstats_update(&bstats->bstats, skb); - u64_stats_update_end(&bstats->syncp); -} - static inline void qdisc_bstats_cpu_update(struct Qdisc *sch, const struct sk_buff *skb) { - bstats_cpu_update(this_cpu_ptr(sch->cpu_bstats), skb); + bstats_update(this_cpu_ptr(sch->cpu_bstats), skb); } static inline void qdisc_bstats_update(struct Qdisc *sch, @@ -968,10 +957,9 @@ static inline void qdisc_qstats_qlen_backlog(struct Qdisc *sch, __u32 *qlen, __u32 *backlog) { struct gnet_stats_queue qstats = { 0 }; - __u32 len = qdisc_qlen_sum(sch); - __gnet_stats_copy_queue(&qstats, sch->cpu_qstats, &sch->qstats, len); - *qlen = qstats.qlen; + gnet_stats_add_queue(&qstats, sch->cpu_qstats, &sch->qstats); + *qlen = qstats.qlen + qdisc_qlen(sch); *backlog = qstats.backlog; } @@ -1312,15 +1300,15 @@ void psched_ppscfg_precompute(struct psched_pktrate *r, u64 pktrate64); struct mini_Qdisc { struct tcf_proto *filter_list; struct tcf_block *block; - struct gnet_stats_basic_cpu __percpu *cpu_bstats; + struct gnet_stats_basic_sync __percpu *cpu_bstats; struct gnet_stats_queue __percpu *cpu_qstats; - struct rcu_head rcu; + unsigned long rcu_state; }; static inline void mini_qdisc_bstats_cpu_update(struct mini_Qdisc *miniq, const struct sk_buff *skb) { - bstats_cpu_update(this_cpu_ptr(miniq->cpu_bstats), skb); + bstats_update(this_cpu_ptr(miniq->cpu_bstats), skb); } static inline void mini_qdisc_qstats_cpu_drop(struct mini_Qdisc *miniq) @@ -1341,6 +1329,8 @@ void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc, void mini_qdisc_pair_block_init(struct mini_Qdisc_pair *miniqp, struct tcf_block *block); +void mq_change_real_num_tx(struct Qdisc *sch, unsigned int new_real_tx); + int sch_frag_xmit_hook(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb)); #endif diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 69bab88ad66b..189fdb9db162 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -626,7 +626,8 @@ static inline __u32 sctp_min_frag_point(struct sctp_sock *sp, __u16 datasize) static inline int sctp_transport_pl_hlen(struct sctp_transport *t) { - return __sctp_mtu_payload(sctp_sk(t->asoc->base.sk), t, 0, 0); + return __sctp_mtu_payload(sctp_sk(t->asoc->base.sk), t, 0, 0) - + sizeof(struct sctphdr); } static inline void sctp_transport_pl_reset(struct sctp_transport *t) @@ -653,12 +654,10 @@ static inline void sctp_transport_pl_update(struct sctp_transport *t) if (t->pl.state == SCTP_PL_DISABLED) return; - if (del_timer(&t->probe_timer)) - sctp_transport_put(t); - t->pl.state = SCTP_PL_BASE; t->pl.pmtu = SCTP_BASE_PLPMTU; t->pl.probe_size = SCTP_BASE_PLPMTU; + sctp_transport_reset_probe_timer(t); } static inline bool sctp_transport_pl_enabled(struct sctp_transport *t) diff --git a/include/net/sock.h b/include/net/sock.h index 463f390d90b3..b32906e1ab55 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -259,10 +259,11 @@ struct bpf_local_storage; * @sk_rcvbuf: size of receive buffer in bytes * @sk_wq: sock wait queue and async head * @sk_rx_dst: receive input route used by early demux + * @sk_rx_dst_ifindex: ifindex for @sk_rx_dst + * @sk_rx_dst_cookie: cookie for @sk_rx_dst * @sk_dst_cache: destination cache * @sk_dst_pending_confirm: need to confirm neighbour * @sk_policy: flow policy - * @sk_rx_skb_cache: cache copy of recently accessed RX skb * @sk_receive_queue: incoming packets * @sk_wmem_alloc: transmit queue bytes committed * @sk_tsq_flags: TCP Small Queues flags @@ -270,6 +271,7 @@ struct bpf_local_storage; * @sk_omem_alloc: "o" is "option" or "other" * @sk_wmem_queued: persistent queue size * @sk_forward_alloc: space allocated forward + * @sk_reserved_mem: space reserved and non-reclaimable for the socket * @sk_napi_id: id of the last napi context to receive data for sk * @sk_ll_usec: usecs to busypoll when there is no data * @sk_allocation: allocation mode @@ -329,7 +331,6 @@ struct bpf_local_storage; * @sk_peek_off: current peek_offset value * @sk_send_head: front of stuff to transmit * @tcp_rtx_queue: TCP re-transmit queue [union with @sk_send_head] - * @sk_tx_skb_cache: cache copy of recently accessed TX skb * @sk_security: used by security modules * @sk_mark: generic packet mark * @sk_cgrp_data: cgroup data for this cgroup @@ -394,7 +395,6 @@ struct sock { atomic_t sk_drops; int sk_rcvlowat; struct sk_buff_head sk_error_queue; - struct sk_buff *sk_rx_skb_cache; struct sk_buff_head sk_receive_queue; /* * The backlog queue is special, it is always used with @@ -413,6 +413,7 @@ struct sock { #define sk_rmem_alloc sk_backlog.rmem_alloc int sk_forward_alloc; + u32 sk_reserved_mem; #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sk_ll_usec; /* ===== mostly read cache line ===== */ @@ -431,6 +432,9 @@ struct sock { struct xfrm_policy __rcu *sk_policy[2]; #endif struct dst_entry *sk_rx_dst; + int sk_rx_dst_ifindex; + u32 sk_rx_dst_cookie; + struct dst_entry __rcu *sk_dst_cache; atomic_t sk_omem_alloc; int sk_sndbuf; @@ -443,7 +447,6 @@ struct sock { struct sk_buff *sk_send_head; struct rb_root tcp_rtx_queue; }; - struct sk_buff *sk_tx_skb_cache; struct sk_buff_head sk_write_queue; __s32 sk_peek_off; int sk_write_pending; @@ -1207,6 +1210,8 @@ struct proto { unsigned int inuse_idx; #endif + int (*forward_alloc_get)(const struct sock *sk); + bool (*stream_memory_free)(const struct sock *sk, int wake); bool (*sock_is_readable)(struct sock *sk); /* Memory pressure */ @@ -1214,6 +1219,7 @@ struct proto { void (*leave_memory_pressure)(struct sock *sk); atomic_long_t *memory_allocated; /* Current allocated memory. */ struct percpu_counter *sockets_allocated; /* Current number of sockets. */ + /* * Pressure flag: try to collapse. * Technical note: it is used by multiple contexts non atomically. @@ -1237,7 +1243,7 @@ struct proto { unsigned int useroffset; /* Usercopy region offset */ unsigned int usersize; /* Usercopy region size */ - struct percpu_counter *orphan_count; + unsigned int __percpu *orphan_count; struct request_sock_ops *rsk_prot; struct timewait_sock_ops *twsk_prot; @@ -1291,20 +1297,22 @@ static inline void sk_refcnt_debug_release(const struct sock *sk) 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 (!sk->sk_prot->forward_alloc_get) + return sk->sk_forward_alloc; + + return sk->sk_prot->forward_alloc_get(sk); +} + 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)) return false; -#ifdef CONFIG_INET return sk->sk_prot->stream_memory_free ? - INDIRECT_CALL_1(sk->sk_prot->stream_memory_free, - tcp_stream_memory_free, - sk, wake) : true; -#else - return sk->sk_prot->stream_memory_free ? - sk->sk_prot->stream_memory_free(sk, wake) : true; -#endif + INDIRECT_CALL_INET_1(sk->sk_prot->stream_memory_free, + tcp_stream_memory_free, sk, wake) : true; } static inline bool sk_stream_memory_free(const struct sock *sk) @@ -1518,20 +1526,49 @@ sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) skb_pfmemalloc(skb); } +static inline int sk_unused_reserved_mem(const struct sock *sk) +{ + int unused_mem; + + if (likely(!sk->sk_reserved_mem)) + return 0; + + unused_mem = sk->sk_reserved_mem - sk->sk_wmem_queued - + atomic_read(&sk->sk_rmem_alloc); + + return unused_mem > 0 ? unused_mem : 0; +} + static inline void sk_mem_reclaim(struct sock *sk) { + int reclaimable; + if (!sk_has_account(sk)) return; - if (sk->sk_forward_alloc >= SK_MEM_QUANTUM) - __sk_mem_reclaim(sk, sk->sk_forward_alloc); + + reclaimable = sk->sk_forward_alloc - sk_unused_reserved_mem(sk); + + if (reclaimable >= SK_MEM_QUANTUM) + __sk_mem_reclaim(sk, reclaimable); +} + +static inline void sk_mem_reclaim_final(struct sock *sk) +{ + sk->sk_reserved_mem = 0; + sk_mem_reclaim(sk); } static inline void sk_mem_reclaim_partial(struct sock *sk) { + int reclaimable; + if (!sk_has_account(sk)) return; - if (sk->sk_forward_alloc > SK_MEM_QUANTUM) - __sk_mem_reclaim(sk, sk->sk_forward_alloc - 1); + + reclaimable = sk->sk_forward_alloc - sk_unused_reserved_mem(sk); + + if (reclaimable > SK_MEM_QUANTUM) + __sk_mem_reclaim(sk, reclaimable - 1); } static inline void sk_mem_charge(struct sock *sk, int size) @@ -1541,11 +1578,19 @@ static inline void sk_mem_charge(struct sock *sk, int size) sk->sk_forward_alloc -= size; } +/* the following macros control memory reclaiming in sk_mem_uncharge() + */ +#define SK_RECLAIM_THRESHOLD (1 << 21) +#define SK_RECLAIM_CHUNK (1 << 20) + static inline void sk_mem_uncharge(struct sock *sk, int size) { + int reclaimable; + if (!sk_has_account(sk)) return; sk->sk_forward_alloc += size; + reclaimable = sk->sk_forward_alloc - sk_unused_reserved_mem(sk); /* Avoid a possible overflow. * TCP send queues can make this happen, if sk_mem_reclaim() @@ -1554,23 +1599,8 @@ static inline void sk_mem_uncharge(struct sock *sk, int size) * If we reach 2 MBytes, reclaim 1 MBytes right now, there is * no need to hold that much forward allocation anyway. */ - if (unlikely(sk->sk_forward_alloc >= 1 << 21)) - __sk_mem_reclaim(sk, 1 << 20); -} - -DECLARE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key); -static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb) -{ - sk_wmem_queued_add(sk, -skb->truesize); - sk_mem_uncharge(sk, skb->truesize); - if (static_branch_unlikely(&tcp_tx_skb_cache_key) && - !sk->sk_tx_skb_cache && !skb_cloned(skb)) { - skb_ext_reset(skb); - skb_zcopy_clear(skb, true); - sk->sk_tx_skb_cache = skb; - return; - } - __kfree_skb(skb); + if (unlikely(reclaimable >= SK_RECLAIM_THRESHOLD)) + __sk_mem_reclaim(sk, SK_RECLAIM_CHUNK); } static inline void sock_release_ownership(struct sock *sk) @@ -1889,10 +1919,8 @@ static inline void sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb) if (skb_rx_queue_recorded(skb)) { u16 rx_queue = skb_get_rx_queue(skb); - if (WARN_ON_ONCE(rx_queue == NO_QUEUE_MAPPING)) - return; - - sk->sk_rx_queue_mapping = rx_queue; + if (unlikely(READ_ONCE(sk->sk_rx_queue_mapping) != rx_queue)) + WRITE_ONCE(sk->sk_rx_queue_mapping, rx_queue); } #endif } @@ -1900,15 +1928,19 @@ static inline void sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb) static inline void sk_rx_queue_clear(struct sock *sk) { #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING - sk->sk_rx_queue_mapping = NO_QUEUE_MAPPING; + WRITE_ONCE(sk->sk_rx_queue_mapping, NO_QUEUE_MAPPING); #endif } static inline int sk_rx_queue_get(const struct sock *sk) { #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING - if (sk && sk->sk_rx_queue_mapping != NO_QUEUE_MAPPING) - return sk->sk_rx_queue_mapping; + if (sk) { + int res = READ_ONCE(sk->sk_rx_queue_mapping); + + if (res != NO_QUEUE_MAPPING) + return res; + } #endif return -1; @@ -2388,13 +2420,11 @@ static inline void sk_stream_moderate_sndbuf(struct sock *sk) return; val = min(sk->sk_sndbuf, sk->sk_wmem_queued >> 1); + val = max_t(u32, val, sk_unused_reserved_mem(sk)); WRITE_ONCE(sk->sk_sndbuf, max_t(u32, val, SOCK_MIN_SNDBUF)); } -struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, - bool force_schedule); - /** * sk_page_frag - return an appropriate page_frag * @sk: socket @@ -2608,7 +2638,6 @@ static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags) &skb_shinfo(skb)->tskey); } -DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key); /** * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from @@ -2620,12 +2649,6 @@ DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key); static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb) { __skb_unlink(skb, &sk->sk_receive_queue); - if (static_branch_unlikely(&tcp_rx_skb_cache_key) && - !sk->sk_rx_skb_cache) { - sk->sk_rx_skb_cache = skb; - skb_orphan(skb); - return; - } __kfree_skb(skb); } @@ -2820,6 +2843,10 @@ void sock_set_sndtimeo(struct sock *sk, s64 secs); int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len); +int sock_get_timeout(long timeo, void *optval, bool old_timeval); +int sock_copy_user_timeval(struct __kernel_sock_timeval *tv, + sockptr_t optval, int optlen, bool old_timeval); + static inline bool sk_is_readable(struct sock *sk) { if (sk->sk_prot->sock_is_readable) diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 60d806b6a5ae..d353793dfeb5 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -299,28 +299,16 @@ void switchdev_port_fwd_mark_set(struct net_device *dev, struct net_device *group_dev, bool joining); -int switchdev_handle_fdb_add_to_device(struct net_device *dev, +int switchdev_handle_fdb_event_to_device(struct net_device *dev, unsigned long event, const struct switchdev_notifier_fdb_info *fdb_info, bool (*check_cb)(const struct net_device *dev), bool (*foreign_dev_check_cb)(const struct net_device *dev, const struct net_device *foreign_dev), - int (*add_cb)(struct net_device *dev, - const struct net_device *orig_dev, const void *ctx, + int (*mod_cb)(struct net_device *dev, struct net_device *orig_dev, + unsigned long event, const void *ctx, const struct switchdev_notifier_fdb_info *fdb_info), - int (*lag_add_cb)(struct net_device *dev, - const struct net_device *orig_dev, const void *ctx, - const struct switchdev_notifier_fdb_info *fdb_info)); - -int switchdev_handle_fdb_del_to_device(struct net_device *dev, - const struct switchdev_notifier_fdb_info *fdb_info, - bool (*check_cb)(const struct net_device *dev), - bool (*foreign_dev_check_cb)(const struct net_device *dev, - const struct net_device *foreign_dev), - int (*del_cb)(struct net_device *dev, - const struct net_device *orig_dev, const void *ctx, - const struct switchdev_notifier_fdb_info *fdb_info), - int (*lag_del_cb)(struct net_device *dev, - const struct net_device *orig_dev, const void *ctx, + int (*lag_mod_cb)(struct net_device *dev, struct net_device *orig_dev, + unsigned long event, const void *ctx, const struct switchdev_notifier_fdb_info *fdb_info)); int switchdev_handle_port_obj_add(struct net_device *dev, @@ -426,32 +414,16 @@ call_switchdev_blocking_notifiers(unsigned long val, } static inline int -switchdev_handle_fdb_add_to_device(struct net_device *dev, - const struct switchdev_notifier_fdb_info *fdb_info, - bool (*check_cb)(const struct net_device *dev), - bool (*foreign_dev_check_cb)(const struct net_device *dev, - const struct net_device *foreign_dev), - int (*add_cb)(struct net_device *dev, - const struct net_device *orig_dev, const void *ctx, - const struct switchdev_notifier_fdb_info *fdb_info), - int (*lag_add_cb)(struct net_device *dev, - const struct net_device *orig_dev, const void *ctx, - const struct switchdev_notifier_fdb_info *fdb_info)) -{ - return 0; -} - -static inline int -switchdev_handle_fdb_del_to_device(struct net_device *dev, +switchdev_handle_fdb_event_to_device(struct net_device *dev, unsigned long event, const struct switchdev_notifier_fdb_info *fdb_info, bool (*check_cb)(const struct net_device *dev), bool (*foreign_dev_check_cb)(const struct net_device *dev, const struct net_device *foreign_dev), - int (*del_cb)(struct net_device *dev, - const struct net_device *orig_dev, const void *ctx, + int (*mod_cb)(struct net_device *dev, struct net_device *orig_dev, + unsigned long event, const void *ctx, const struct switchdev_notifier_fdb_info *fdb_info), - int (*lag_del_cb)(struct net_device *dev, - const struct net_device *orig_dev, const void *ctx, + int (*lag_mod_cb)(struct net_device *dev, struct net_device *orig_dev, + unsigned long event, const void *ctx, const struct switchdev_notifier_fdb_info *fdb_info)) { return 0; diff --git a/include/net/tcp.h b/include/net/tcp.h index 60c384569e9c..70972f3ac8fa 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -48,7 +48,9 @@ extern struct inet_hashinfo tcp_hashinfo; -extern struct percpu_counter tcp_orphan_count; +DECLARE_PER_CPU(unsigned int, tcp_orphan_count); +int tcp_orphan_count_sum(void); + void tcp_time_wait(struct sock *sk, int state, int timeo); #define MAX_TCP_HEADER L1_CACHE_ALIGN(128 + MAX_HEADER) @@ -288,21 +290,15 @@ static inline bool tcp_out_of_memory(struct sock *sk) return false; } -void sk_forced_mem_schedule(struct sock *sk, int size); - -static inline bool tcp_too_many_orphans(struct sock *sk, int shift) +static inline void tcp_wmem_free_skb(struct sock *sk, struct sk_buff *skb) { - struct percpu_counter *ocp = sk->sk_prot->orphan_count; - int orphans = percpu_counter_read_positive(ocp); - - if (orphans << shift > sysctl_tcp_max_orphans) { - orphans = percpu_counter_sum_positive(ocp); - if (orphans << shift > sysctl_tcp_max_orphans) - return true; - } - return false; + sk_wmem_queued_add(sk, -skb->truesize); + sk_mem_uncharge(sk, skb->truesize); + __kfree_skb(skb); } +void sk_forced_mem_schedule(struct sock *sk, int size); + bool tcp_check_oom(struct sock *sk, int shift); @@ -322,7 +318,7 @@ void tcp_shutdown(struct sock *sk, int how); int tcp_v4_early_demux(struct sk_buff *skb); int tcp_v4_rcv(struct sk_buff *skb); -void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb); +void tcp_remove_empty_skb(struct sock *sk); int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw); int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size); @@ -330,8 +326,6 @@ int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset, size_t size, int flags); -struct sk_buff *tcp_build_frag(struct sock *sk, int size_goal, int flags, - struct page *page, int offset, size_t *size); ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, size_t size, int flags); int tcp_send_mss(struct sock *sk, int *size_goal, int flags); @@ -350,6 +344,8 @@ void tcp_twsk_destructor(struct sock *sk); ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); +struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, + bool force_schedule); void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks); static inline void tcp_dec_quickack_mode(struct sock *sk, @@ -581,6 +577,8 @@ __u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mss); #endif /* tcp_output.c */ +void tcp_skb_entail(struct sock *sk, struct sk_buff *skb); +void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb); void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, int nonagle); int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs); @@ -874,10 +872,11 @@ struct tcp_skb_cb { __u32 ack_seq; /* Sequence number ACK'd */ union { struct { +#define TCPCB_DELIVERED_CE_MASK ((1U<<20) - 1) /* There is space for up to 24 bytes */ - __u32 in_flight:30,/* Bytes in flight at transmit */ - is_app_limited:1, /* cwnd not fully used? */ - unused:1; + __u32 is_app_limited:1, /* cwnd not fully used? */ + delivered_ce:20, + unused:11; /* pkts S/ACKed so far upon tx of skb, incl retrans: */ __u32 delivered; /* start of send pipeline phase */ @@ -1029,7 +1028,9 @@ struct ack_sample { struct rate_sample { u64 prior_mstamp; /* starting timestamp for interval */ u32 prior_delivered; /* tp->delivered at "prior_mstamp" */ + u32 prior_delivered_ce;/* tp->delivered_ce at "prior_mstamp" */ s32 delivered; /* number of packets delivered over interval */ + s32 delivered_ce; /* number of packets delivered w/ CE marks*/ long interval_us; /* time for tp->delivered to incr "delivered" */ u32 snd_interval_us; /* snd interval for delivered packets */ u32 rcv_interval_us; /* rcv interval for delivered packets */ @@ -1418,6 +1419,17 @@ static inline int tcp_full_space(const struct sock *sk) return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf)); } +static inline void tcp_adjust_rcv_ssthresh(struct sock *sk) +{ + int unused_mem = sk_unused_reserved_mem(sk); + struct tcp_sock *tp = tcp_sk(sk); + + tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); + if (unused_mem) + tp->rcv_ssthresh = max_t(u32, tp->rcv_ssthresh, + tcp_win_from_space(sk, unused_mem)); +} + void tcp_cleanup_rbuf(struct sock *sk, int copied); /* We provision sk_rcvbuf around 200% of sk_rcvlowat. @@ -1870,7 +1882,7 @@ static inline void tcp_rtx_queue_unlink_and_free(struct sk_buff *skb, struct soc { list_del(&skb->tcp_tsorted_anchor); tcp_rtx_queue_unlink(skb, sk); - sk_wmem_free_skb(sk, skb); + tcp_wmem_free_skb(sk, skb); } static inline void tcp_push_pending_frames(struct sock *sk) diff --git a/include/net/tls.h b/include/net/tls.h index 1fffb206f09f..526cb2c3b724 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -66,7 +66,7 @@ #define MAX_IV_SIZE 16 #define TLS_MAX_REC_SEQ_SIZE 8 -/* For AES-CCM, the full 16-bytes of IV is made of '4' fields of given sizes. +/* For CCM mode, the full 16-bytes of IV is made of '4' fields of given sizes. * * IV[16] = b0[1] || implicit nonce[4] || explicit nonce[8] || length[3] * @@ -74,6 +74,7 @@ * Hence b0 contains (3 - 1) = 2. */ #define TLS_AES_CCM_IV_B0_BYTE 2 +#define TLS_SM4_CCM_IV_B0_BYTE 2 #define __TLS_INC_STATS(net, field) \ __SNMP_INC_STATS((net)->mib.tls_statistics, field) @@ -220,6 +221,8 @@ union tls_crypto_context { struct tls12_crypto_info_aes_gcm_128 aes_gcm_128; struct tls12_crypto_info_aes_gcm_256 aes_gcm_256; struct tls12_crypto_info_chacha20_poly1305 chacha20_poly1305; + struct tls12_crypto_info_sm4_gcm sm4_gcm; + struct tls12_crypto_info_sm4_ccm sm4_ccm; }; }; diff --git a/include/net/xdp.h b/include/net/xdp.h index ad5b02dcb6f4..447f9b1578f3 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -15,13 +15,13 @@ * level RX-ring queues. It is information that is specific to how * the driver have configured a given RX-ring queue. * - * Each xdp_buff frame received in the driver carry a (pointer) + * Each xdp_buff frame received in the driver carries a (pointer) * reference to this xdp_rxq_info structure. This provides the XDP * data-path read-access to RX-info for both kernel and bpf-side * (limited subset). * * For now, direct access is only safe while running in NAPI/softirq - * context. Contents is read-mostly and must not be updated during + * context. Contents are read-mostly and must not be updated during * driver NAPI/softirq poll. * * The driver usage API is a register and unregister API. @@ -30,8 +30,8 @@ * can be attached as long as it doesn't change the underlying * RX-ring. If the RX-ring does change significantly, the NIC driver * naturally need to stop the RX-ring before purging and reallocating - * memory. In that process the driver MUST call unregistor (which - * also apply for driver shutdown and unload). The register API is + * memory. In that process the driver MUST call unregister (which + * also applies for driver shutdown and unload). The register API is * also mandatory during RX-ring setup. */ diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 4e295541e396..443d45951564 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -77,6 +77,12 @@ static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool) return xp_alloc(pool); } +/* Returns as many entries as possible up to max. 0 <= N <= max. */ +static inline u32 xsk_buff_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max) +{ + return xp_alloc_batch(pool, xdp, max); +} + static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count) { return xp_can_alloc(pool, count); @@ -89,6 +95,13 @@ static inline void xsk_buff_free(struct xdp_buff *xdp) xp_free(xskb); } +static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size) +{ + xdp->data = xdp->data_hard_start + XDP_PACKET_HEADROOM; + xdp->data_meta = xdp->data; + xdp->data_end = xdp->data + size; +} + static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool, u64 addr) { @@ -212,6 +225,11 @@ static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool) return NULL; } +static inline u32 xsk_buff_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max) +{ + return 0; +} + static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count) { return false; @@ -221,6 +239,10 @@ static inline void xsk_buff_free(struct xdp_buff *xdp) { } +static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size) +{ +} + static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool, u64 addr) { diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 7a9a23e7a604..ddeefc4a1040 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -7,6 +7,7 @@ #include <linux/if_xdp.h> #include <linux/types.h> #include <linux/dma-mapping.h> +#include <linux/bpf.h> #include <net/xdp.h> struct xsk_buff_pool; @@ -23,7 +24,6 @@ struct xdp_buff_xsk { dma_addr_t dma; dma_addr_t frame_dma; struct xsk_buff_pool *pool; - bool unaligned; u64 orig_addr; struct list_head free_list_node; }; @@ -67,6 +67,7 @@ struct xsk_buff_pool { u32 free_heads_cnt; u32 headroom; u32 chunk_size; + u32 chunk_shift; u32 frame_len; u8 cached_need_wakeup; bool uses_need_wakeup; @@ -81,6 +82,13 @@ struct xsk_buff_pool { struct xdp_buff_xsk *free_heads[]; }; +/* Masks for xdp_umem_page flags. + * The low 12-bits of the addr will be 0 since this is the page address, so we + * can use them for flags. + */ +#define XSK_NEXT_PG_CONTIG_SHIFT 0 +#define XSK_NEXT_PG_CONTIG_MASK BIT_ULL(XSK_NEXT_PG_CONTIG_SHIFT) + /* AF_XDP core. */ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, struct xdp_umem *umem); @@ -89,7 +97,6 @@ int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev, int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem, struct net_device *dev, u16 queue_id); void xp_destroy(struct xsk_buff_pool *pool); -void xp_release(struct xdp_buff_xsk *xskb); void xp_get_pool(struct xsk_buff_pool *pool); bool xp_put_pool(struct xsk_buff_pool *pool); void xp_clear_dev(struct xsk_buff_pool *pool); @@ -99,12 +106,28 @@ void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs); /* AF_XDP, and XDP core. */ 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; +} + +static inline void xp_init_xskb_dma(struct xdp_buff_xsk *xskb, struct xsk_buff_pool *pool, + dma_addr_t *dma_pages, u64 addr) +{ + xskb->frame_dma = (dma_pages[addr >> PAGE_SHIFT] & ~XSK_NEXT_PG_CONTIG_MASK) + + (addr & ~PAGE_MASK); + xskb->dma = xskb->frame_dma + pool->headroom + XDP_PACKET_HEADROOM; +} + /* AF_XDP ZC drivers, via xdp_sock_buff.h */ void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq); int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev, unsigned long attrs, struct page **pages, u32 nr_pages); void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs); struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool); +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); @@ -180,4 +203,25 @@ static inline u64 xp_unaligned_add_offset_to_addr(u64 addr) xp_unaligned_extract_offset(addr); } +static inline u32 xp_aligned_extract_idx(struct xsk_buff_pool *pool, u64 addr) +{ + return xp_aligned_extract_addr(pool, addr) >> pool->chunk_shift; +} + +static inline void xp_release(struct xdp_buff_xsk *xskb) +{ + if (xskb->pool->unaligned) + xskb->pool->free_heads[xskb->pool->free_heads_cnt++] = xskb; +} + +static inline u64 xp_get_handle(struct xdp_buff_xsk *xskb) +{ + u64 offset = xskb->xdp.data - xskb->xdp.data_hard_start; + + offset += xskb->pool->headroom; + if (!xskb->pool->unaligned) + return xskb->orig_addr + offset; + return xskb->orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT); +} + #endif /* XSK_BUFF_POOL_H_ */ |