diff options
Diffstat (limited to 'include/net')
-rw-r--r-- | include/net/act_api.h | 2 | ||||
-rw-r--r-- | include/net/cfg80211.h | 3 | ||||
-rw-r--r-- | include/net/dropreason-core.h | 6 | ||||
-rw-r--r-- | include/net/inet_sock.h | 5 | ||||
-rw-r--r-- | include/net/ip.h | 8 | ||||
-rw-r--r-- | include/net/ip6_fib.h | 4 | ||||
-rw-r--r-- | include/net/ip_tunnels.h | 11 | ||||
-rw-r--r-- | include/net/mana/mana.h | 46 | ||||
-rw-r--r-- | include/net/netdev_rx_queue.h | 4 | ||||
-rw-r--r-- | include/net/netlink.h | 16 | ||||
-rw-r--r-- | include/net/netns/ipv4.h | 50 | ||||
-rw-r--r-- | include/net/netns/smc.h | 2 | ||||
-rw-r--r-- | include/net/page_pool/helpers.h | 68 | ||||
-rw-r--r-- | include/net/page_pool/types.h | 49 | ||||
-rw-r--r-- | include/net/tcp.h | 22 | ||||
-rw-r--r-- | include/net/tcp_ao.h | 6 | ||||
-rw-r--r-- | include/net/tcp_states.h | 2 | ||||
-rw-r--r-- | include/net/vxlan.h | 33 | ||||
-rw-r--r-- | include/net/xdp_sock.h | 111 | ||||
-rw-r--r-- | include/net/xdp_sock_drv.h | 34 | ||||
-rw-r--r-- | include/net/xsk_buff_pool.h | 8 |
21 files changed, 376 insertions, 114 deletions
diff --git a/include/net/act_api.h b/include/net/act_api.h index 4ae0580b63ca..ea13e1e4a7c2 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -191,7 +191,7 @@ int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index, struct nlattr *est, struct tc_action **a, const struct tc_action_ops *ops, int bind, u32 flags); -void tcf_idr_insert_many(struct tc_action *actions[]); +void tcf_idr_insert_many(struct tc_action *actions[], int init_res[]); void tcf_idr_cleanup(struct tc_action_net *tn, u32 index); int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index, struct tc_action **a, int bind); diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 4ecfb06c413d..1b3345129a95 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2608,6 +2608,8 @@ struct cfg80211_scan_6ghz_params { * @n_6ghz_params: number of 6 GHz params * @scan_6ghz_params: 6 GHz params * @bssid: BSSID to scan for (most commonly, the wildcard BSSID) + * @tsf_report_link_id: for MLO, indicates the link ID of the BSS that should be + * used for TSF reporting. Can be set to -1 to indicate no preference. */ struct cfg80211_scan_request { struct cfg80211_ssid *ssids; @@ -2636,6 +2638,7 @@ struct cfg80211_scan_request { bool scan_6ghz; u32 n_6ghz_params; struct cfg80211_scan_6ghz_params *scan_6ghz_params; + s8 tsf_report_link_id; /* keep last */ struct ieee80211_channel *channels[] __counted_by(n_channels); diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h index 3c70ad53a49c..278e4c7d465c 100644 --- a/include/net/dropreason-core.h +++ b/include/net/dropreason-core.h @@ -86,6 +86,7 @@ FN(IPV6_NDISC_NS_OTHERHOST) \ FN(QUEUE_PURGE) \ FN(TC_ERROR) \ + FN(PACKET_SOCK_ERROR) \ FNe(MAX) /** @@ -379,6 +380,11 @@ enum skb_drop_reason { /** @SKB_DROP_REASON_TC_ERROR: generic internal tc error. */ SKB_DROP_REASON_TC_ERROR, /** + * @SKB_DROP_REASON_PACKET_SOCK_ERROR: generic packet socket errors + * after its filter matches an incoming packet. + */ + SKB_DROP_REASON_PACKET_SOCK_ERROR, + /** * @SKB_DROP_REASON_MAX: the maximum of core drop reasons, which * shouldn't be used as a real 'reason' - only for tracing code gen */ diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 74db6d97cae1..aa86453f6b9b 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -234,10 +234,7 @@ struct inet_sock { int uc_index; int mc_index; __be32 mc_addr; - struct { - __u16 lo; - __u16 hi; - } local_port_range; + u32 local_port_range; /* high << 16 | low */ struct ip_mc_socklist __rcu *mc_list; struct inet_cork_full cork; diff --git a/include/net/ip.h b/include/net/ip.h index 1fc4c8d69e33..b31be912489a 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -349,7 +349,13 @@ static inline u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_o } \ } -void inet_get_local_port_range(const struct net *net, int *low, int *high); +static inline void inet_get_local_port_range(const struct net *net, int *low, int *high) +{ + u32 range = READ_ONCE(net->ipv4.ip_local_ports.range); + + *low = range & 0xffff; + *high = range >> 16; +} void inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high); #ifdef CONFIG_SYSCTL diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 1ba9f4ddf2f6..95ed495c3a40 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -328,8 +328,10 @@ static inline bool fib6_info_hold_safe(struct fib6_info *f6i) static inline void fib6_info_release(struct fib6_info *f6i) { - if (f6i && refcount_dec_and_test(&f6i->fib6_ref)) + if (f6i && refcount_dec_and_test(&f6i->fib6_ref)) { + DEBUG_NET_WARN_ON_ONCE(!hlist_unhashed(&f6i->gc_link)); call_rcu(&f6i->rcu, fib6_info_destroy_rcu); + } } enum fib6_walk_state { diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index f346b4efbc30..2d746f4c9a0a 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -416,6 +416,17 @@ static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph, return 0; } +static inline __be32 ip_tunnel_get_flowlabel(const struct iphdr *iph, + const struct sk_buff *skb) +{ + __be16 payload_protocol = skb_protocol(skb, true); + + if (payload_protocol == htons(ETH_P_IPV6)) + return ip6_flowlabel((const struct ipv6hdr *)iph); + else + return 0; +} + static inline u8 ip_tunnel_get_ttl(const struct iphdr *iph, const struct sk_buff *skb) { diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 6e3e9c1363db..76147feb0d10 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -353,6 +353,25 @@ struct mana_tx_qp { struct mana_ethtool_stats { u64 stop_queue; u64 wake_queue; + u64 hc_rx_discards_no_wqe; + u64 hc_rx_err_vport_disabled; + u64 hc_rx_bytes; + u64 hc_rx_ucast_pkts; + u64 hc_rx_ucast_bytes; + u64 hc_rx_bcast_pkts; + u64 hc_rx_bcast_bytes; + u64 hc_rx_mcast_pkts; + u64 hc_rx_mcast_bytes; + u64 hc_tx_err_gf_disabled; + u64 hc_tx_err_vport_disabled; + u64 hc_tx_err_inval_vportoffset_pkt; + u64 hc_tx_err_vlan_enforcement; + u64 hc_tx_err_eth_type_enforcement; + u64 hc_tx_err_sa_enforcement; + u64 hc_tx_err_sqpdid_enforcement; + u64 hc_tx_err_cqpdid_enforcement; + u64 hc_tx_err_mtu_violation; + u64 hc_tx_err_inval_oob; u64 hc_tx_bytes; u64 hc_tx_ucast_pkts; u64 hc_tx_ucast_bytes; @@ -360,6 +379,7 @@ struct mana_ethtool_stats { u64 hc_tx_bcast_bytes; u64 hc_tx_mcast_pkts; u64 hc_tx_mcast_bytes; + u64 hc_tx_err_gdma; u64 tx_cqe_err; u64 tx_cqe_unknown_type; u64 rx_coalesced_err; @@ -602,8 +622,8 @@ struct mana_query_gf_stat_resp { struct gdma_resp_hdr hdr; u64 reported_stats; /* rx errors/discards */ - u64 discard_rx_nowqe; - u64 err_rx_vport_disabled; + u64 rx_discards_nowqe; + u64 rx_err_vport_disabled; /* rx bytes/packets */ u64 hc_rx_bytes; u64 hc_rx_ucast_pkts; @@ -613,16 +633,16 @@ struct mana_query_gf_stat_resp { u64 hc_rx_mcast_pkts; u64 hc_rx_mcast_bytes; /* tx errors */ - u64 err_tx_gf_disabled; - u64 err_tx_vport_disabled; - u64 err_tx_inval_vport_offset_pkt; - u64 err_tx_vlan_enforcement; - u64 err_tx_ethtype_enforcement; - u64 err_tx_SA_enforecement; - u64 err_tx_SQPDID_enforcement; - u64 err_tx_CQPDID_enforcement; - u64 err_tx_mtu_violation; - u64 err_tx_inval_oob; + u64 tx_err_gf_disabled; + u64 tx_err_vport_disabled; + u64 tx_err_inval_vport_offset_pkt; + u64 tx_err_vlan_enforcement; + u64 tx_err_ethtype_enforcement; + u64 tx_err_SA_enforcement; + u64 tx_err_SQPDID_enforcement; + u64 tx_err_CQPDID_enforcement; + u64 tx_err_mtu_violation; + u64 tx_err_inval_oob; /* tx bytes/packets */ u64 hc_tx_bytes; u64 hc_tx_ucast_pkts; @@ -632,7 +652,7 @@ struct mana_query_gf_stat_resp { u64 hc_tx_mcast_pkts; u64 hc_tx_mcast_bytes; /* tx error */ - u64 err_tx_gdma; + u64 tx_err_gdma; }; /* HW DATA */ /* Configure vPort Rx Steering */ diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h index cdcafb30d437..aa1716fb0e53 100644 --- a/include/net/netdev_rx_queue.h +++ b/include/net/netdev_rx_queue.h @@ -21,6 +21,10 @@ struct netdev_rx_queue { #ifdef CONFIG_XDP_SOCKETS struct xsk_buff_pool *pool; #endif + /* NAPI instance for the queue + * Readers and writers must hold RTNL + */ + struct napi_struct *napi; } ____cacheline_aligned_in_smp; /* diff --git a/include/net/netlink.h b/include/net/netlink.h index 83bdf787aeee..28039e57070a 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -1011,6 +1011,20 @@ static inline struct sk_buff *nlmsg_new(size_t payload, gfp_t flags) } /** + * nlmsg_new_large - Allocate a new netlink message with non-contiguous + * physical memory + * @payload: size of the message payload + * + * The allocated skb is unable to have frag page for shinfo->frags*, + * as the NULL setting for skb->head in netlink_skb_destructor() will + * bypass most of the handling in skb_release_data() + */ +static inline struct sk_buff *nlmsg_new_large(size_t payload) +{ + return netlink_alloc_large_skb(nlmsg_total_size(payload), 0); +} + +/** * nlmsg_end - Finalize a netlink message * @skb: socket buffer the message is stored in * @nlh: netlink message header @@ -1200,7 +1214,7 @@ static inline void *nla_data(const struct nlattr *nla) * nla_len - length of payload * @nla: netlink attribute */ -static inline int nla_len(const struct nlattr *nla) +static inline u16 nla_len(const struct nlattr *nla) { return nla->nla_len - NLA_HDRLEN; } diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 73f43f699199..c356c458b340 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -19,8 +19,7 @@ struct hlist_head; struct fib_table; struct sock; struct local_ports { - seqlock_t lock; - int range[2]; + u32 range; /* high << 16 | low */ bool warned; }; @@ -42,6 +41,38 @@ struct inet_timewait_death_row { struct tcp_fastopen_context; struct netns_ipv4 { + /* Cacheline organization can be found documented in + * Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst. + * Please update the document when adding new fields. + */ + + /* TX readonly hotpath cache lines */ + __cacheline_group_begin(netns_ipv4_read_tx); + u8 sysctl_tcp_early_retrans; + u8 sysctl_tcp_tso_win_divisor; + u8 sysctl_tcp_tso_rtt_log; + u8 sysctl_tcp_autocorking; + int sysctl_tcp_min_snd_mss; + unsigned int sysctl_tcp_notsent_lowat; + int sysctl_tcp_limit_output_bytes; + int sysctl_tcp_min_rtt_wlen; + int sysctl_tcp_wmem[3]; + u8 sysctl_ip_fwd_use_pmtu; + __cacheline_group_end(netns_ipv4_read_tx); + + /* TXRX readonly hotpath cache lines */ + __cacheline_group_begin(netns_ipv4_read_txrx); + u8 sysctl_tcp_moderate_rcvbuf; + __cacheline_group_end(netns_ipv4_read_txrx); + + /* RX readonly hotpath cache line */ + __cacheline_group_begin(netns_ipv4_read_rx); + u8 sysctl_ip_early_demux; + u8 sysctl_tcp_early_demux; + int sysctl_tcp_reordering; + int sysctl_tcp_rmem[3]; + __cacheline_group_end(netns_ipv4_read_rx); + struct inet_timewait_death_row tcp_death_row; struct udp_table *udp_table; @@ -96,17 +127,14 @@ struct netns_ipv4 { u8 sysctl_ip_default_ttl; u8 sysctl_ip_no_pmtu_disc; - u8 sysctl_ip_fwd_use_pmtu; u8 sysctl_ip_fwd_update_priority; u8 sysctl_ip_nonlocal_bind; u8 sysctl_ip_autobind_reuse; /* Shall we try to damage output packets if routing dev changes? */ u8 sysctl_ip_dynaddr; - u8 sysctl_ip_early_demux; #ifdef CONFIG_NET_L3_MASTER_DEV u8 sysctl_raw_l3mdev_accept; #endif - u8 sysctl_tcp_early_demux; u8 sysctl_udp_early_demux; u8 sysctl_nexthop_compat_mode; @@ -119,7 +147,6 @@ struct netns_ipv4 { u8 sysctl_tcp_mtu_probing; int sysctl_tcp_mtu_probe_floor; int sysctl_tcp_base_mss; - int sysctl_tcp_min_snd_mss; int sysctl_tcp_probe_threshold; u32 sysctl_tcp_probe_interval; @@ -135,17 +162,14 @@ struct netns_ipv4 { u8 sysctl_tcp_backlog_ack_defer; u8 sysctl_tcp_pingpong_thresh; - int sysctl_tcp_reordering; u8 sysctl_tcp_retries1; u8 sysctl_tcp_retries2; u8 sysctl_tcp_orphan_retries; u8 sysctl_tcp_tw_reuse; int sysctl_tcp_fin_timeout; - unsigned int sysctl_tcp_notsent_lowat; u8 sysctl_tcp_sack; u8 sysctl_tcp_window_scaling; u8 sysctl_tcp_timestamps; - u8 sysctl_tcp_early_retrans; u8 sysctl_tcp_recovery; u8 sysctl_tcp_thin_linear_timeouts; u8 sysctl_tcp_slow_start_after_idle; @@ -161,21 +185,13 @@ struct netns_ipv4 { u8 sysctl_tcp_frto; u8 sysctl_tcp_nometrics_save; u8 sysctl_tcp_no_ssthresh_metrics_save; - u8 sysctl_tcp_moderate_rcvbuf; - u8 sysctl_tcp_tso_win_divisor; u8 sysctl_tcp_workaround_signed_windows; - int sysctl_tcp_limit_output_bytes; int sysctl_tcp_challenge_ack_limit; - int sysctl_tcp_min_rtt_wlen; u8 sysctl_tcp_min_tso_segs; - u8 sysctl_tcp_tso_rtt_log; - u8 sysctl_tcp_autocorking; u8 sysctl_tcp_reflect_tos; int sysctl_tcp_invalid_ratelimit; int sysctl_tcp_pacing_ss_ratio; int sysctl_tcp_pacing_ca_ratio; - int sysctl_tcp_wmem[3]; - int sysctl_tcp_rmem[3]; unsigned int sysctl_tcp_child_ehash_entries; unsigned long sysctl_tcp_comp_sack_delay_ns; unsigned long sysctl_tcp_comp_sack_slack_ns; diff --git a/include/net/netns/smc.h b/include/net/netns/smc.h index 582212ada3ba..fc752a50f91b 100644 --- a/include/net/netns/smc.h +++ b/include/net/netns/smc.h @@ -22,5 +22,7 @@ struct netns_smc { int sysctl_smcr_testlink_time; int sysctl_wmem; int sysctl_rmem; + int sysctl_max_links_per_lgr; + int sysctl_max_conns_per_lgr; }; #endif diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h index 4ebd544ae977..841e0a930bd7 100644 --- a/include/net/page_pool/helpers.h +++ b/include/net/page_pool/helpers.h @@ -29,7 +29,7 @@ * page allocated from page pool. Page splitting enables memory saving and thus * avoids TLB/cache miss for data access, but there also is some cost to * implement page splitting, mainly some cache line dirtying/bouncing for - * 'struct page' and atomic operation for page->pp_frag_count. + * 'struct page' and atomic operation for page->pp_ref_count. * * The API keeps track of in-flight pages, in order to let API users know when * it is safe to free a page_pool object, the API users must call @@ -55,16 +55,12 @@ #include <net/page_pool/types.h> #ifdef CONFIG_PAGE_POOL_STATS +/* Deprecated driver-facing API, use netlink instead */ int page_pool_ethtool_stats_get_count(void); u8 *page_pool_ethtool_stats_get_strings(u8 *data); u64 *page_pool_ethtool_stats_get(u64 *data, void *stats); -/* - * Drivers that wish to harvest page pool stats and report them to users - * (perhaps via ethtool, debugfs, or another mechanism) can allocate a - * struct page_pool_stats call page_pool_get_stats to get stats for the specified pool. - */ -bool page_pool_get_stats(struct page_pool *pool, +bool page_pool_get_stats(const struct page_pool *pool, struct page_pool_stats *stats); #else static inline int page_pool_ethtool_stats_get_count(void) @@ -214,69 +210,77 @@ inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool) return pool->p.dma_dir; } -/* pp_frag_count represents the number of writers who can update the page - * either by updating skb->data or via DMA mappings for the device. - * We can't rely on the page refcnt for that as we don't know who might be - * holding page references and we can't reliably destroy or sync DMA mappings - * of the fragments. +/** + * page_pool_fragment_page() - split a fresh page into fragments + * @page: page to split + * @nr: references to set + * + * pp_ref_count represents the number of outstanding references to the page, + * which will be freed using page_pool APIs (rather than page allocator APIs + * like put_page()). Such references are usually held by page_pool-aware + * objects like skbs marked for page pool recycling. * - * When pp_frag_count reaches 0 we can either recycle the page if the page - * refcnt is 1 or return it back to the memory allocator and destroy any - * mappings we have. + * This helper allows the caller to take (set) multiple references to a + * freshly allocated page. The page must be freshly allocated (have a + * pp_ref_count of 1). This is commonly done by drivers and + * "fragment allocators" to save atomic operations - either when they know + * upfront how many references they will need; or to take MAX references and + * return the unused ones with a single atomic dec(), instead of performing + * multiple atomic inc() operations. */ static inline void page_pool_fragment_page(struct page *page, long nr) { - atomic_long_set(&page->pp_frag_count, nr); + atomic_long_set(&page->pp_ref_count, nr); } -static inline long page_pool_defrag_page(struct page *page, long nr) +static inline long page_pool_unref_page(struct page *page, long nr) { long ret; - /* If nr == pp_frag_count then we have cleared all remaining + /* If nr == pp_ref_count then we have cleared all remaining * references to the page: * 1. 'n == 1': no need to actually overwrite it. * 2. 'n != 1': overwrite it with one, which is the rare case - * for pp_frag_count draining. + * for pp_ref_count draining. * * The main advantage to doing this is that not only we avoid a atomic * update, as an atomic_read is generally a much cheaper operation than * an atomic update, especially when dealing with a page that may be - * partitioned into only 2 or 3 pieces; but also unify the pp_frag_count + * referenced by only 2 or 3 users; but also unify the pp_ref_count * handling by ensuring all pages have partitioned into only 1 piece * initially, and only overwrite it when the page is partitioned into * more than one piece. */ - if (atomic_long_read(&page->pp_frag_count) == nr) { + if (atomic_long_read(&page->pp_ref_count) == nr) { /* As we have ensured nr is always one for constant case using * the BUILD_BUG_ON(), only need to handle the non-constant case - * here for pp_frag_count draining, which is a rare case. + * here for pp_ref_count draining, which is a rare case. */ BUILD_BUG_ON(__builtin_constant_p(nr) && nr != 1); if (!__builtin_constant_p(nr)) - atomic_long_set(&page->pp_frag_count, 1); + atomic_long_set(&page->pp_ref_count, 1); return 0; } - ret = atomic_long_sub_return(nr, &page->pp_frag_count); + ret = atomic_long_sub_return(nr, &page->pp_ref_count); WARN_ON(ret < 0); - /* We are the last user here too, reset pp_frag_count back to 1 to + /* We are the last user here too, reset pp_ref_count back to 1 to * ensure all pages have been partitioned into 1 piece initially, * this should be the rare case when the last two fragment users call - * page_pool_defrag_page() currently. + * page_pool_unref_page() currently. */ if (unlikely(!ret)) - atomic_long_set(&page->pp_frag_count, 1); + atomic_long_set(&page->pp_ref_count, 1); return ret; } -static inline bool page_pool_is_last_frag(struct page *page) +static inline bool page_pool_is_last_ref(struct page *page) { - /* If page_pool_defrag_page() returns 0, we were the last user */ - return page_pool_defrag_page(page, 1) == 0; + /* If page_pool_unref_page() returns 0, we were the last user */ + return page_pool_unref_page(page, 1) == 0; } /** @@ -301,10 +305,10 @@ static inline void page_pool_put_page(struct page_pool *pool, * allow registering MEM_TYPE_PAGE_POOL, but shield linker. */ #ifdef CONFIG_PAGE_POOL - if (!page_pool_is_last_frag(page)) + if (!page_pool_is_last_ref(page)) return; - page_pool_put_defragged_page(pool, page, dma_sync_size, allow_direct); + page_pool_put_unrefed_page(pool, page, dma_sync_size, allow_direct); #endif } diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index 6fc5134095ed..76481c465375 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -5,6 +5,7 @@ #include <linux/dma-direction.h> #include <linux/ptr_ring.h> +#include <linux/types.h> #define PP_FLAG_DMA_MAP BIT(0) /* Should page_pool do the DMA * map/unmap @@ -48,24 +49,30 @@ struct pp_alloc_cache { * @pool_size: size of the ptr_ring * @nid: NUMA node id to allocate from pages from * @dev: device, for DMA pre-mapping purposes + * @netdev: netdev this pool will serve (leave as NULL if none or multiple) * @napi: NAPI which is the sole consumer of pages, otherwise NULL * @dma_dir: DMA mapping direction * @max_len: max DMA sync memory size for PP_FLAG_DMA_SYNC_DEV * @offset: DMA sync address offset for PP_FLAG_DMA_SYNC_DEV */ struct page_pool_params { - unsigned int flags; - unsigned int order; - unsigned int pool_size; - int nid; - struct device *dev; - struct napi_struct *napi; - enum dma_data_direction dma_dir; - unsigned int max_len; - unsigned int offset; + struct_group_tagged(page_pool_params_fast, fast, + unsigned int flags; + unsigned int order; + unsigned int pool_size; + int nid; + struct device *dev; + struct napi_struct *napi; + enum dma_data_direction dma_dir; + unsigned int max_len; + unsigned int offset; + ); + struct_group_tagged(page_pool_params_slow, slow, + struct net_device *netdev; /* private: used by test code only */ - void (*init_callback)(struct page *page, void *arg); - void *init_arg; + void (*init_callback)(struct page *page, void *arg); + void *init_arg; + ); }; #ifdef CONFIG_PAGE_POOL_STATS @@ -119,7 +126,9 @@ struct page_pool_stats { #endif struct page_pool { - struct page_pool_params p; + struct page_pool_params_fast p; + + bool has_init_callback; long frag_users; struct page *frag_page; @@ -178,6 +187,16 @@ struct page_pool { refcount_t user_cnt; u64 destroy_cnt; + + /* Slow/Control-path information follows */ + struct page_pool_params_slow slow; + /* User-facing fields, protected by page_pools_lock */ + struct { + struct hlist_node list; + u64 detach_time; + u32 napi_id; + u32 id; + } user; }; struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp); @@ -215,9 +234,9 @@ static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data, } #endif -void page_pool_put_defragged_page(struct page_pool *pool, struct page *page, - unsigned int dma_sync_size, - bool allow_direct); +void page_pool_put_unrefed_page(struct page_pool *pool, struct page *page, + unsigned int dma_sync_size, + bool allow_direct); static inline bool is_page_pool_compiled_in(void) { diff --git a/include/net/tcp.h b/include/net/tcp.h index 144ba48bb07b..f5ca4abaee8b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -490,13 +490,14 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb); /* From syncookies.c */ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, struct request_sock *req, - struct dst_entry *dst, u32 tsoff); -int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th, - u32 cookie); + struct dst_entry *dst); +int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th); struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, - const struct tcp_request_sock_ops *af_ops, - struct sock *sk, struct sk_buff *skb); + struct sock *sk, struct sk_buff *skb, + struct tcp_options_received *tcp_opt, + int mss, u32 tsoff); + #ifdef CONFIG_SYN_COOKIES /* Syncookies use a monotonic timer which increments every 60 seconds. @@ -582,12 +583,15 @@ __u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mss); u64 cookie_init_timestamp(struct request_sock *req, u64 now); bool cookie_timestamp_decode(const struct net *net, struct tcp_options_received *opt); -bool cookie_ecn_ok(const struct tcp_options_received *opt, - const struct net *net, const struct dst_entry *dst); + +static inline bool cookie_ecn_ok(const struct net *net, const struct dst_entry *dst) +{ + return READ_ONCE(net->ipv4.sysctl_tcp_ecn) || + dst_feature(dst, RTAX_FEATURE_ECN); +} /* From net/ipv6/syncookies.c */ -int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th, - u32 cookie); +int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th); struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb); u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph, diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h index 647781080613..0f2dcc9e8d46 100644 --- a/include/net/tcp_ao.h +++ b/include/net/tcp_ao.h @@ -271,8 +271,7 @@ void tcp_ao_established(struct sock *sk); void tcp_ao_finish_connect(struct sock *sk, struct sk_buff *skb); void tcp_ao_connect_init(struct sock *sk); void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb, - struct tcp_request_sock *treq, - unsigned short int family, int l3index); + struct request_sock *req, unsigned short int family); #else /* CONFIG_TCP_AO */ static inline int tcp_ao_transmit_skb(struct sock *sk, struct sk_buff *skb, @@ -283,8 +282,7 @@ static inline int tcp_ao_transmit_skb(struct sock *sk, struct sk_buff *skb, } static inline void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb, - struct tcp_request_sock *treq, - unsigned short int family, int l3index) + struct request_sock *req, unsigned short int family) { } diff --git a/include/net/tcp_states.h b/include/net/tcp_states.h index cc00118acca1..d60e8148ff4c 100644 --- a/include/net/tcp_states.h +++ b/include/net/tcp_states.h @@ -22,6 +22,7 @@ enum { TCP_LISTEN, TCP_CLOSING, /* Now a valid state */ TCP_NEW_SYN_RECV, + TCP_BOUND_INACTIVE, /* Pseudo-state for inet_diag */ TCP_MAX_STATES /* Leave at the end! */ }; @@ -43,6 +44,7 @@ enum { TCPF_LISTEN = (1 << TCP_LISTEN), TCPF_CLOSING = (1 << TCP_CLOSING), TCPF_NEW_SYN_RECV = (1 << TCP_NEW_SYN_RECV), + TCPF_BOUND_INACTIVE = (1 << TCP_BOUND_INACTIVE), }; #endif /* _LINUX_TCP_STATES_H */ diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 6a9f8a5f387c..33ba6fc151cf 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -210,22 +210,23 @@ struct vxlan_rdst { }; struct vxlan_config { - union vxlan_addr remote_ip; - union vxlan_addr saddr; - __be32 vni; - int remote_ifindex; - int mtu; - __be16 dst_port; - u16 port_min; - u16 port_max; - u8 tos; - u8 ttl; - __be32 label; - u32 flags; - unsigned long age_interval; - unsigned int addrmax; - bool no_share; - enum ifla_vxlan_df df; + union vxlan_addr remote_ip; + union vxlan_addr saddr; + __be32 vni; + int remote_ifindex; + int mtu; + __be16 dst_port; + u16 port_min; + u16 port_max; + u8 tos; + u8 ttl; + __be32 label; + enum ifla_vxlan_label_policy label_policy; + u32 flags; + unsigned long age_interval; + unsigned int addrmax; + bool no_share; + enum ifla_vxlan_df df; }; enum { diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index f83128007fb0..3cb4dc9bd70e 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -30,6 +30,7 @@ struct xdp_umem { struct user_struct *user; refcount_t users; u8 flags; + u8 tx_metadata_len; bool zc; struct page **pgs; int id; @@ -92,12 +93,105 @@ struct xdp_sock { struct xsk_queue *cq_tmp; /* Only as tmp storage before bind */ }; +/* + * AF_XDP TX metadata hooks for network devices. + * The following hooks can be defined; unless noted otherwise, they are + * optional and can be filled with a null pointer. + * + * void (*tmo_request_timestamp)(void *priv) + * Called when AF_XDP frame requested egress timestamp. + * + * u64 (*tmo_fill_timestamp)(void *priv) + * Called when AF_XDP frame, that had requested egress timestamp, + * received a completion. The hook needs to return the actual HW timestamp. + * + * void (*tmo_request_checksum)(u16 csum_start, u16 csum_offset, void *priv) + * Called when AF_XDP frame requested HW checksum offload. csum_start + * indicates position where checksumming should start. + * csum_offset indicates position where checksum should be stored. + * + */ +struct xsk_tx_metadata_ops { + void (*tmo_request_timestamp)(void *priv); + u64 (*tmo_fill_timestamp)(void *priv); + void (*tmo_request_checksum)(u16 csum_start, u16 csum_offset, void *priv); +}; + #ifdef CONFIG_XDP_SOCKETS int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp); int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp); void __xsk_map_flush(void); +/** + * xsk_tx_metadata_to_compl - Save enough relevant metadata information + * to perform tx completion in the future. + * @meta: pointer to AF_XDP metadata area + * @compl: pointer to output struct xsk_tx_metadata_to_compl + * + * This function should be called by the networking device when + * it prepares AF_XDP egress packet. The value of @compl should be stored + * and passed to xsk_tx_metadata_complete upon TX completion. + */ +static inline void xsk_tx_metadata_to_compl(struct xsk_tx_metadata *meta, + struct xsk_tx_metadata_compl *compl) +{ + if (!meta) + return; + + if (meta->flags & XDP_TXMD_FLAGS_TIMESTAMP) + compl->tx_timestamp = &meta->completion.tx_timestamp; + else + compl->tx_timestamp = NULL; +} + +/** + * xsk_tx_metadata_request - Evaluate AF_XDP TX metadata at submission + * and call appropriate xsk_tx_metadata_ops operation. + * @meta: pointer to AF_XDP metadata area + * @ops: pointer to struct xsk_tx_metadata_ops + * @priv: pointer to driver-private aread + * + * This function should be called by the networking device when + * it prepares AF_XDP egress packet. + */ +static inline void xsk_tx_metadata_request(const struct xsk_tx_metadata *meta, + const struct xsk_tx_metadata_ops *ops, + void *priv) +{ + if (!meta) + return; + + if (ops->tmo_request_timestamp) + if (meta->flags & XDP_TXMD_FLAGS_TIMESTAMP) + ops->tmo_request_timestamp(priv); + + if (ops->tmo_request_checksum) + if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM) + ops->tmo_request_checksum(meta->request.csum_start, + meta->request.csum_offset, priv); +} + +/** + * xsk_tx_metadata_complete - Evaluate AF_XDP TX metadata at completion + * and call appropriate xsk_tx_metadata_ops operation. + * @compl: pointer to completion metadata produced from xsk_tx_metadata_to_compl + * @ops: pointer to struct xsk_tx_metadata_ops + * @priv: pointer to driver-private aread + * + * This function should be called by the networking device upon + * AF_XDP egress completion. + */ +static inline void xsk_tx_metadata_complete(struct xsk_tx_metadata_compl *compl, + const struct xsk_tx_metadata_ops *ops, + void *priv) +{ + if (!compl) + return; + + *compl->tx_timestamp = ops->tmo_fill_timestamp(priv); +} + #else static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) @@ -114,6 +208,23 @@ static inline void __xsk_map_flush(void) { } +static inline void xsk_tx_metadata_to_compl(struct xsk_tx_metadata *meta, + struct xsk_tx_metadata_compl *compl) +{ +} + +static inline void xsk_tx_metadata_request(struct xsk_tx_metadata *meta, + const struct xsk_tx_metadata_ops *ops, + void *priv) +{ +} + +static inline void xsk_tx_metadata_complete(struct xsk_tx_metadata_compl *compl, + const struct xsk_tx_metadata_ops *ops, + void *priv) +{ +} + #endif /* CONFIG_XDP_SOCKETS */ #if defined(CONFIG_XDP_SOCKETS) && defined(CONFIG_DEBUG_NET) diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 1f6fc8c7a84c..81e02de3f453 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -165,6 +165,30 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr) return xp_raw_get_data(pool, addr); } +#define XDP_TXMD_FLAGS_VALID ( \ + XDP_TXMD_FLAGS_TIMESTAMP | \ + XDP_TXMD_FLAGS_CHECKSUM | \ + 0) + +static inline bool xsk_buff_valid_tx_metadata(struct xsk_tx_metadata *meta) +{ + return !(meta->flags & ~XDP_TXMD_FLAGS_VALID); +} + +static inline struct xsk_tx_metadata *xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr) +{ + struct xsk_tx_metadata *meta; + + if (!pool->tx_metadata_len) + return NULL; + + meta = xp_raw_get_data(pool, addr) - pool->tx_metadata_len; + if (unlikely(!xsk_buff_valid_tx_metadata(meta))) + return NULL; /* no way to signal the error to the user */ + + return meta; +} + static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool) { struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp); @@ -324,6 +348,16 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr) return NULL; } +static inline bool xsk_buff_valid_tx_metadata(struct xsk_tx_metadata *meta) +{ + return false; +} + +static inline struct xsk_tx_metadata *xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr) +{ + return NULL; +} + static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool) { } diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index b0bdff26fc88..8d48d37ab7c0 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -33,6 +33,7 @@ struct xdp_buff_xsk { }; #define XSK_CHECK_PRIV_TYPE(t) BUILD_BUG_ON(sizeof(t) > offsetofend(struct xdp_buff_xsk, cb)) +#define XSK_TX_COMPL_FITS(t) BUILD_BUG_ON(sizeof(struct xsk_tx_metadata_compl) > sizeof(t)) struct xsk_dma_map { dma_addr_t *dma_pages; @@ -77,10 +78,12 @@ struct xsk_buff_pool { u32 chunk_size; u32 chunk_shift; u32 frame_len; + u8 tx_metadata_len; /* inherited from umem */ u8 cached_need_wakeup; bool uses_need_wakeup; bool dma_need_sync; bool unaligned; + bool tx_sw_csum; void *addrs; /* Mutual exclusion of the completion ring in the SKB mode. Two cases to protect: * NAPI TX thread and sendmsg error paths in the SKB destructor callback and when @@ -233,4 +236,9 @@ static inline u64 xp_get_handle(struct xdp_buff_xsk *xskb) return xskb->orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT); } +static inline bool xp_tx_metadata_enabled(const struct xsk_buff_pool *pool) +{ + return pool->tx_metadata_len > 0; +} + #endif /* XSK_BUFF_POOL_H_ */ |