diff options
Diffstat (limited to 'include/net')
-rw-r--r-- | include/net/cfg80211.h | 36 | ||||
-rw-r--r-- | include/net/cfg802154.h | 1 | ||||
-rw-r--r-- | include/net/gro.h | 5 | ||||
-rw-r--r-- | include/net/hotdata.h | 52 | ||||
-rw-r--r-- | include/net/mac80211.h | 36 | ||||
-rw-r--r-- | include/net/netdev_queues.h | 56 | ||||
-rw-r--r-- | include/net/nexthop.h | 29 | ||||
-rw-r--r-- | include/net/protocol.h | 3 | ||||
-rw-r--r-- | include/net/rps.h | 125 | ||||
-rw-r--r-- | include/net/sch_generic.h | 7 | ||||
-rw-r--r-- | include/net/sock.h | 35 |
11 files changed, 334 insertions, 51 deletions
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index f9eada2a26ec..2e2be4fd2bb6 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -6871,13 +6871,45 @@ cfg80211_find_vendor_ie(unsigned int oui, int oui_type, } /** + * enum cfg80211_rnr_iter_ret - reduced neighbor report iteration state + * @RNR_ITER_CONTINUE: continue iterating with the next entry + * @RNR_ITER_BREAK: break iteration and return success + * @RNR_ITER_ERROR: break iteration and return error + */ +enum cfg80211_rnr_iter_ret { + RNR_ITER_CONTINUE, + RNR_ITER_BREAK, + RNR_ITER_ERROR, +}; + +/** + * cfg80211_iter_rnr - iterate reduced neighbor report entries + * @elems: the frame elements to iterate RNR elements and then + * their entries in + * @elems_len: length of the elements + * @iter: iteration function, see also &enum cfg80211_rnr_iter_ret + * for the return value + * @iter_data: additional data passed to the iteration function + * Return: %true on success (after successfully iterating all entries + * or if the iteration function returned %RNR_ITER_BREAK), + * %false on error (iteration function returned %RNR_ITER_ERROR + * or elements were malformed.) + */ +bool cfg80211_iter_rnr(const u8 *elems, size_t elems_len, + enum cfg80211_rnr_iter_ret + (*iter)(void *data, u8 type, + const struct ieee80211_neighbor_ap_info *info, + const u8 *tbtt_info, u8 tbtt_info_len), + void *iter_data); + +/** * cfg80211_defragment_element - Defrag the given element data into a buffer * * @elem: the element to defragment * @ies: elements where @elem is contained * @ieslen: length of @ies - * @data: buffer to store element data - * @data_len: length of @data + * @data: buffer to store element data, or %NULL to just determine size + * @data_len: length of @data, or 0 * @frag_id: the element ID of fragments * * Return: length of @data, or -EINVAL on error diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index cd95711b12b8..76d2cd2e2b30 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -401,6 +401,7 @@ struct ieee802154_llsec_key { struct ieee802154_llsec_key_entry { struct list_head list; + struct rcu_head rcu; struct ieee802154_llsec_key_id id; struct ieee802154_llsec_key *key; diff --git a/include/net/gro.h b/include/net/gro.h index 2b58671a6549..d6fc8fbd3730 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -9,6 +9,7 @@ #include <net/ip6_checksum.h> #include <linux/skbuff.h> #include <net/udp.h> +#include <net/hotdata.h> struct napi_gro_cb { union { @@ -446,7 +447,7 @@ static inline void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb, { list_add_tail(&skb->list, &napi->rx_list); napi->rx_count += segs; - if (napi->rx_count >= READ_ONCE(gro_normal_batch)) + if (napi->rx_count >= READ_ONCE(net_hotdata.gro_normal_batch)) gro_normal_list(napi); } @@ -493,6 +494,4 @@ static inline void inet6_get_iif_sdif(const struct sk_buff *skb, int *iif, int * #endif } -extern struct list_head offload_base; - #endif /* _NET_IPV6_GRO_H */ diff --git a/include/net/hotdata.h b/include/net/hotdata.h new file mode 100644 index 000000000000..003667a1efd6 --- /dev/null +++ b/include/net/hotdata.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _NET_HOTDATA_H +#define _NET_HOTDATA_H + +#include <linux/types.h> +#include <linux/netdevice.h> +#include <net/protocol.h> + +/* Read mostly data used in network fast paths. */ +struct net_hotdata { +#if IS_ENABLED(CONFIG_INET) + struct packet_offload ip_packet_offload; + struct net_offload tcpv4_offload; + struct net_protocol tcp_protocol; + struct net_offload udpv4_offload; + struct net_protocol udp_protocol; + struct packet_offload ipv6_packet_offload; + struct net_offload tcpv6_offload; +#if IS_ENABLED(CONFIG_IPV6) + struct inet6_protocol tcpv6_protocol; + struct inet6_protocol udpv6_protocol; +#endif + struct net_offload udpv6_offload; +#endif + struct list_head offload_base; + struct list_head ptype_all; + struct kmem_cache *skbuff_cache; + struct kmem_cache *skbuff_fclone_cache; + struct kmem_cache *skb_small_head_cache; +#ifdef CONFIG_RPS + struct rps_sock_flow_table __rcu *rps_sock_flow_table; + u32 rps_cpu_mask; +#endif + int gro_normal_batch; + int netdev_budget; + int netdev_budget_usecs; + int tstamp_prequeue; + int max_backlog; + int dev_tx_weight; + int dev_rx_weight; +}; + +#define inet_ehash_secret net_hotdata.tcp_protocol.secret +#define udp_ehash_secret net_hotdata.udp_protocol.secret +#define inet6_ehash_secret net_hotdata.tcpv6_protocol.secret +#define tcp_ipv6_hash_secret net_hotdata.tcpv6_offload.secret +#define udp6_ehash_secret net_hotdata.udpv6_protocol.secret +#define udp_ipv6_hash_secret net_hotdata.udpv6_offload.secret + +extern struct net_hotdata net_hotdata; + +#endif /* _NET_HOTDATA_H */ diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 56c6ecb2c10a..353488ab94a2 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1763,8 +1763,9 @@ struct ieee80211_conf { * @chandef: the new channel to switch to * @count: the number of TBTT's until the channel switch event * @delay: maximum delay between the time the AP transmitted the last beacon in - * current channel and the expected time of the first beacon in the new - * channel, expressed in TU. + * current channel and the expected time of the first beacon in the new + * channel, expressed in TU. + * @link_id: the link ID of the link doing the channel switch, 0 for non-MLO */ struct ieee80211_channel_switch { u64 timestamp; @@ -1772,6 +1773,7 @@ struct ieee80211_channel_switch { bool block_tx; struct cfg80211_chan_def chandef; u8 count; + u8 link_id; u32 delay; }; @@ -2011,6 +2013,21 @@ static inline bool ieee80211_vif_is_mld(const struct ieee80211_vif *vif) return vif->valid_links != 0; } +/** + * ieee80211_vif_link_active - check if a given link is active + * @vif: the vif + * @link_id: the link ID to check + * Return: %true if the vif is an MLD and the link is active, or if + * the vif is not an MLD and the link ID is 0; %false otherwise. + */ +static inline bool ieee80211_vif_link_active(const struct ieee80211_vif *vif, + unsigned int link_id) +{ + if (!ieee80211_vif_is_mld(vif)) + return link_id == 0; + return vif->active_links & BIT(link_id); +} + #define for_each_vif_active_link(vif, link, link_id) \ for (link_id = 0; link_id < ARRAY_SIZE((vif)->link_conf); link_id++) \ if ((!(vif)->active_links || \ @@ -2761,6 +2778,11 @@ struct ieee80211_txq { * @IEEE80211_HW_DISALLOW_PUNCTURING: HW requires disabling puncturing in EHT * and connecting with a lower bandwidth instead * + * @IEEE80211_HW_HANDLES_QUIET_CSA: HW/driver handles quieting for CSA, so + * no need to stop queues. This really should be set by a driver that + * implements MLO, so operation can continue on other links when one + * link is switching. + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -2819,6 +2841,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_DETECTS_COLOR_COLLISION, IEEE80211_HW_MLO_MCAST_MULTI_LINK_TX, IEEE80211_HW_DISALLOW_PUNCTURING, + IEEE80211_HW_HANDLES_QUIET_CSA, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS @@ -4251,7 +4274,7 @@ struct ieee80211_prep_tx_info { * after a channel switch procedure is completed, allowing the * driver to go back to a normal configuration. * @abort_channel_switch: This is an optional callback that is called - * when channel switch procedure was completed, allowing the + * when channel switch procedure was aborted, allowing the * driver to go back to a normal configuration. * @channel_switch_rx_beacon: This is an optional callback that is called * when channel switch procedure is in progress and additional beacon with @@ -4647,7 +4670,8 @@ struct ieee80211_ops { struct ieee80211_vif *vif, struct ieee80211_bss_conf *link_conf); void (*abort_channel_switch)(struct ieee80211_hw *hw, - struct ieee80211_vif *vif); + struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf); void (*channel_switch_rx_beacon)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_channel_switch *ch_switch); @@ -5912,6 +5936,7 @@ void ieee80211_remove_key(struct ieee80211_key_conf *keyconf); * ieee80211_gtk_rekey_add - add a GTK key from rekeying during WoWLAN * @vif: the virtual interface to add the key on * @keyconf: new key data + * @link_id: the link id of the key or -1 for non-MLO * * When GTK rekeying was done while the system was suspended, (a) new * key(s) will be available. These will be needed by mac80211 for proper @@ -5939,7 +5964,8 @@ void ieee80211_remove_key(struct ieee80211_key_conf *keyconf); */ struct ieee80211_key_conf * ieee80211_gtk_rekey_add(struct ieee80211_vif *vif, - struct ieee80211_key_conf *keyconf); + struct ieee80211_key_conf *keyconf, + int link_id); /** * ieee80211_gtk_rekey_notify - notify userspace supplicant of rekeying diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h index 8b8ed4e13d74..1ec408585373 100644 --- a/include/net/netdev_queues.h +++ b/include/net/netdev_queues.h @@ -4,6 +4,62 @@ #include <linux/netdevice.h> +/* See the netdev.yaml spec for definition of each statistic */ +struct netdev_queue_stats_rx { + u64 bytes; + u64 packets; + u64 alloc_fail; +}; + +struct netdev_queue_stats_tx { + u64 bytes; + u64 packets; +}; + +/** + * struct netdev_stat_ops - netdev ops for fine grained stats + * @get_queue_stats_rx: get stats for a given Rx queue + * @get_queue_stats_tx: get stats for a given Tx queue + * @get_base_stats: get base stats (not belonging to any live instance) + * + * Query stats for a given object. The values of the statistics are undefined + * on entry (specifically they are *not* zero-initialized). Drivers should + * assign values only to the statistics they collect. Statistics which are not + * collected must be left undefined. + * + * Queue objects are not necessarily persistent, and only currently active + * queues are queried by the per-queue callbacks. This means that per-queue + * statistics will not generally add up to the total number of events for + * the device. The @get_base_stats callback allows filling in the delta + * between events for currently live queues and overall device history. + * When the statistics for the entire device are queried, first @get_base_stats + * is issued to collect the delta, and then a series of per-queue callbacks. + * Only statistics which are set in @get_base_stats will be reported + * at the device level, meaning that unlike in queue callbacks, setting + * a statistic to zero in @get_base_stats is a legitimate thing to do. + * This is because @get_base_stats has a second function of designating which + * statistics are in fact correct for the entire device (e.g. when history + * for some of the events is not maintained, and reliable "total" cannot + * be provided). + * + * Device drivers can assume that when collecting total device stats, + * the @get_base_stats and subsequent per-queue calls are performed + * "atomically" (without releasing the rtnl_lock). + * + * Device drivers are encouraged to reset the per-queue statistics when + * number of queues change. This is because the primary use case for + * per-queue statistics is currently to detect traffic imbalance. + */ +struct netdev_stat_ops { + void (*get_queue_stats_rx)(struct net_device *dev, int idx, + struct netdev_queue_stats_rx *stats); + void (*get_queue_stats_tx)(struct net_device *dev, int idx, + struct netdev_queue_stats_tx *stats); + void (*get_base_stats)(struct net_device *dev, + struct netdev_queue_stats_rx *rx, + struct netdev_queue_stats_tx *tx); +}; + /** * DOC: Lockless queue stopping / waking helpers. * diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 77e99cba60ad..7ec9cc80f11c 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -47,6 +47,8 @@ struct nh_config { bool nh_grp_res_has_idle_timer; bool nh_grp_res_has_unbalanced_timer; + bool nh_hw_stats; + struct nlattr *nh_encap; u16 nh_encap_type; @@ -95,8 +97,14 @@ struct nh_res_table { struct nh_res_bucket nh_buckets[] __counted_by(num_nh_buckets); }; +struct nh_grp_entry_stats { + u64_stats_t packets; + struct u64_stats_sync syncp; +}; + struct nh_grp_entry { struct nexthop *nh; + struct nh_grp_entry_stats __percpu *stats; u8 weight; union { @@ -114,6 +122,7 @@ struct nh_grp_entry { struct list_head nh_list; struct nexthop *nh_parent; /* nexthop of group with this entry */ + u64 packets_hw; }; struct nh_group { @@ -124,6 +133,7 @@ struct nh_group { bool resilient; bool fdb_nh; bool has_v4; + bool hw_stats; struct nh_res_table __rcu *res_table; struct nh_grp_entry nh_entries[] __counted_by(num_nh); @@ -157,6 +167,7 @@ enum nexthop_event_type { NEXTHOP_EVENT_REPLACE, NEXTHOP_EVENT_RES_TABLE_PRE_REPLACE, NEXTHOP_EVENT_BUCKET_REPLACE, + NEXTHOP_EVENT_HW_STATS_REPORT_DELTA, }; enum nh_notifier_info_type { @@ -164,6 +175,7 @@ enum nh_notifier_info_type { NH_NOTIFIER_INFO_TYPE_GRP, NH_NOTIFIER_INFO_TYPE_RES_TABLE, NH_NOTIFIER_INFO_TYPE_RES_BUCKET, + NH_NOTIFIER_INFO_TYPE_GRP_HW_STATS, }; struct nh_notifier_single_info { @@ -187,6 +199,7 @@ struct nh_notifier_grp_entry_info { struct nh_notifier_grp_info { u16 num_nh; bool is_fdb; + bool hw_stats; struct nh_notifier_grp_entry_info nh_entries[] __counted_by(num_nh); }; @@ -200,9 +213,21 @@ struct nh_notifier_res_bucket_info { struct nh_notifier_res_table_info { u16 num_nh_buckets; + bool hw_stats; struct nh_notifier_single_info nhs[] __counted_by(num_nh_buckets); }; +struct nh_notifier_grp_hw_stats_entry_info { + u32 id; + u64 packets; +}; + +struct nh_notifier_grp_hw_stats_info { + u16 num_nh; + bool hw_stats_used; + struct nh_notifier_grp_hw_stats_entry_info stats[] __counted_by(num_nh); +}; + struct nh_notifier_info { struct net *net; struct netlink_ext_ack *extack; @@ -213,6 +238,7 @@ struct nh_notifier_info { struct nh_notifier_grp_info *nh_grp; struct nh_notifier_res_table_info *nh_res_table; struct nh_notifier_res_bucket_info *nh_res_bucket; + struct nh_notifier_grp_hw_stats_info *nh_grp_hw_stats; }; }; @@ -225,6 +251,9 @@ void nexthop_bucket_set_hw_flags(struct net *net, u32 id, u16 bucket_index, bool offload, bool trap); void nexthop_res_grp_activity_update(struct net *net, u32 id, u16 num_buckets, unsigned long *activity); +void nh_grp_hw_stats_report_delta(struct nh_notifier_grp_hw_stats_info *info, + unsigned int nh_idx, + u64 delta_packets); /* caller is holding rcu or rtnl; no reference taken to nexthop */ struct nexthop *nexthop_find_by_id(struct net *net, u32 id); diff --git a/include/net/protocol.h b/include/net/protocol.h index 6aef8cb11cc8..b2499f88f8f8 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -46,6 +46,7 @@ struct net_protocol { * socket lookup? */ icmp_strict_tag_validation:1; + u32 secret; }; #if IS_ENABLED(CONFIG_IPV6) @@ -59,6 +60,7 @@ struct inet6_protocol { __be32 info); unsigned int flags; /* INET6_PROTO_xxx */ + u32 secret; }; #define INET6_PROTO_NOPOLICY 0x1 @@ -68,6 +70,7 @@ struct inet6_protocol { struct net_offload { struct offload_callbacks callbacks; unsigned int flags; /* Flags used by IPv6 for now */ + u32 secret; }; /* This should be set for any extension header which is compatible with GSO. */ #define INET6_PROTO_GSO_EXTHDR 0x1 diff --git a/include/net/rps.h b/include/net/rps.h new file mode 100644 index 000000000000..7660243e905b --- /dev/null +++ b/include/net/rps.h @@ -0,0 +1,125 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _NET_RPS_H +#define _NET_RPS_H + +#include <linux/types.h> +#include <linux/static_key.h> +#include <net/sock.h> +#include <net/hotdata.h> + +#ifdef CONFIG_RPS + +extern struct static_key_false rps_needed; +extern struct static_key_false rfs_needed; + +/* + * This structure holds an RPS map which can be of variable length. The + * map is an array of CPUs. + */ +struct rps_map { + unsigned int len; + struct rcu_head rcu; + u16 cpus[]; +}; +#define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + ((_num) * sizeof(u16))) + +/* + * The rps_dev_flow structure contains the mapping of a flow to a CPU, the + * tail pointer for that CPU's input queue at the time of last enqueue, and + * a hardware filter index. + */ +struct rps_dev_flow { + u16 cpu; + u16 filter; + unsigned int last_qtail; +}; +#define RPS_NO_FILTER 0xffff + +/* + * The rps_dev_flow_table structure contains a table of flow mappings. + */ +struct rps_dev_flow_table { + unsigned int mask; + struct rcu_head rcu; + struct rps_dev_flow flows[]; +}; +#define RPS_DEV_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_dev_flow_table) + \ + ((_num) * sizeof(struct rps_dev_flow))) + +/* + * The rps_sock_flow_table contains mappings of flows to the last CPU + * on which they were processed by the application (set in recvmsg). + * Each entry is a 32bit value. Upper part is the high-order bits + * of flow hash, lower part is CPU number. + * rps_cpu_mask is used to partition the space, depending on number of + * possible CPUs : rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1 + * For example, if 64 CPUs are possible, rps_cpu_mask = 0x3f, + * meaning we use 32-6=26 bits for the hash. + */ +struct rps_sock_flow_table { + u32 mask; + + u32 ents[] ____cacheline_aligned_in_smp; +}; +#define RPS_SOCK_FLOW_TABLE_SIZE(_num) (offsetof(struct rps_sock_flow_table, ents[_num])) + +#define RPS_NO_CPU 0xffff + +static inline void rps_record_sock_flow(struct rps_sock_flow_table *table, + u32 hash) +{ + unsigned int index = hash & table->mask; + u32 val = hash & ~net_hotdata.rps_cpu_mask; + + /* We only give a hint, preemption can change CPU under us */ + val |= raw_smp_processor_id(); + + /* The following WRITE_ONCE() is paired with the READ_ONCE() + * here, and another one in get_rps_cpu(). + */ + if (READ_ONCE(table->ents[index]) != val) + WRITE_ONCE(table->ents[index], val); +} + +#endif /* CONFIG_RPS */ + +static inline void sock_rps_record_flow_hash(__u32 hash) +{ +#ifdef CONFIG_RPS + struct rps_sock_flow_table *sock_flow_table; + + if (!hash) + return; + rcu_read_lock(); + sock_flow_table = rcu_dereference(net_hotdata.rps_sock_flow_table); + if (sock_flow_table) + rps_record_sock_flow(sock_flow_table, hash); + rcu_read_unlock(); +#endif +} + +static inline void sock_rps_record_flow(const struct sock *sk) +{ +#ifdef CONFIG_RPS + if (static_branch_unlikely(&rfs_needed)) { + /* Reading sk->sk_rxhash might incur an expensive cache line + * miss. + * + * TCP_ESTABLISHED does cover almost all states where RFS + * might be useful, and is cheaper [1] than testing : + * IPv4: inet_sk(sk)->inet_daddr + * IPv6: ipv6_addr_any(&sk->sk_v6_daddr) + * OR an additional socket flag + * [1] : sk_state and sk_prot are in the same cache line. + */ + if (sk->sk_state == TCP_ESTABLISHED) { + /* This READ_ONCE() is paired with the WRITE_ONCE() + * from sock_rps_save_rxhash() and sock_rps_reset_rxhash(). + */ + sock_rps_record_flow_hash(READ_ONCE(sk->sk_rxhash)); + } + } +#endif +} + +#endif /* _NET_RPS_H */ diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 934fdb977551..cefe0c4bdae3 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -238,12 +238,7 @@ static inline bool qdisc_may_bulk(const struct Qdisc *qdisc) static inline int qdisc_avail_bulklimit(const struct netdev_queue *txq) { -#ifdef CONFIG_BQL - /* Non-BQL migrated drivers will return 0, too. */ - return dql_avail(&txq->dql); -#else - return 0; -#endif + return netdev_queue_dql_avail(txq); } struct Qdisc_class_ops { diff --git a/include/net/sock.h b/include/net/sock.h index 09a0cde8bf52..b5e00702acc1 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1117,41 +1117,6 @@ static inline void sk_incoming_cpu_update(struct sock *sk) WRITE_ONCE(sk->sk_incoming_cpu, cpu); } -static inline void sock_rps_record_flow_hash(__u32 hash) -{ -#ifdef CONFIG_RPS - struct rps_sock_flow_table *sock_flow_table; - - rcu_read_lock(); - sock_flow_table = rcu_dereference(rps_sock_flow_table); - rps_record_sock_flow(sock_flow_table, hash); - rcu_read_unlock(); -#endif -} - -static inline void sock_rps_record_flow(const struct sock *sk) -{ -#ifdef CONFIG_RPS - if (static_branch_unlikely(&rfs_needed)) { - /* Reading sk->sk_rxhash might incur an expensive cache line - * miss. - * - * TCP_ESTABLISHED does cover almost all states where RFS - * might be useful, and is cheaper [1] than testing : - * IPv4: inet_sk(sk)->inet_daddr - * IPv6: ipv6_addr_any(&sk->sk_v6_daddr) - * OR an additional socket flag - * [1] : sk_state and sk_prot are in the same cache line. - */ - if (sk->sk_state == TCP_ESTABLISHED) { - /* This READ_ONCE() is paired with the WRITE_ONCE() - * from sock_rps_save_rxhash() and sock_rps_reset_rxhash(). - */ - sock_rps_record_flow_hash(READ_ONCE(sk->sk_rxhash)); - } - } -#endif -} static inline void sock_rps_save_rxhash(struct sock *sk, const struct sk_buff *skb) |