diff options
Diffstat (limited to 'include/net')
56 files changed, 902 insertions, 336 deletions
diff --git a/include/net/act_api.h b/include/net/act_api.h index b18c699681ca..71347a90a9d1 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -23,7 +23,6 @@ struct tc_action_ops; struct tc_action { const struct tc_action_ops *ops; __u32 type; /* for backward compat(TCA_OLD_COMPAT) */ - __u32 order; struct tcf_idrinfo *idrinfo; u32 tcfa_index; @@ -41,6 +40,7 @@ struct tc_action { struct gnet_stats_queue __percpu *cpu_qstats; struct tc_cookie __rcu *act_cookie; struct tcf_chain __rcu *goto_chain; + u32 tcfa_flags; }; #define tcf_index common.tcfa_index #define tcf_refcnt common.tcfa_refcnt @@ -94,7 +94,7 @@ struct tc_action_ops { int (*init)(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **act, int ovr, int bind, bool rtnl_held, struct tcf_proto *tp, - struct netlink_ext_ack *extack); + u32 flags, struct netlink_ext_ack *extack); int (*walk)(struct net *, struct sk_buff *, struct netlink_callback *, int, const struct tc_action_ops *, @@ -154,7 +154,11 @@ int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb, int tcf_idr_search(struct tc_action_net *tn, struct tc_action **a, u32 index); int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, struct tc_action **a, const struct tc_action_ops *ops, - int bind, bool cpustats); + int bind, bool cpustats, u32 flags); +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(struct tc_action_net *tn, struct tc_action *a); void tcf_idr_cleanup(struct tc_action_net *tn, u32 index); @@ -186,6 +190,43 @@ int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], int bind, int ref); int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int); int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int); + +static inline void tcf_action_update_bstats(struct tc_action *a, + struct sk_buff *skb) +{ + if (likely(a->cpu_bstats)) { + bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), skb); + return; + } + spin_lock(&a->tcfa_lock); + bstats_update(&a->tcfa_bstats, skb); + spin_unlock(&a->tcfa_lock); +} + +static inline void tcf_action_inc_drop_qstats(struct tc_action *a) +{ + if (likely(a->cpu_qstats)) { + qstats_drop_inc(this_cpu_ptr(a->cpu_qstats)); + return; + } + spin_lock(&a->tcfa_lock); + qstats_drop_inc(&a->tcfa_qstats); + spin_unlock(&a->tcfa_lock); +} + +static inline void tcf_action_inc_overlimit_qstats(struct tc_action *a) +{ + if (likely(a->cpu_qstats)) { + qstats_overlimit_inc(this_cpu_ptr(a->cpu_qstats)); + return; + } + spin_lock(&a->tcfa_lock); + qstats_overlimit_inc(&a->tcfa_qstats); + spin_unlock(&a->tcfa_lock); +} + +void tcf_action_update_stats(struct tc_action *a, u64 bytes, u32 packets, + bool drop, bool hw); int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int); int tcf_action_check_ctrlact(int action, struct tcf_proto *tp, diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 3f62b347b04a..1bab88184d3c 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -202,11 +202,11 @@ u32 ipv6_addr_label(struct net *net, const struct in6_addr *addr, /* * multicast prototypes (mcast.c) */ -static inline int ipv6_mc_may_pull(struct sk_buff *skb, - unsigned int len) +static inline bool ipv6_mc_may_pull(struct sk_buff *skb, + unsigned int len) { if (skb_transport_offset(skb) + ipv6_transport_len(skb) < len) - return 0; + return false; return pskb_may_pull(skb, len); } diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 80ea0f93d3f7..4206dc6d813f 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -10,7 +10,7 @@ #include <linux/kernel.h> #include <linux/workqueue.h> -#include <linux/vm_sockets.h> +#include <uapi/linux/vm_sockets.h> #include "vsock_addr.h" @@ -27,6 +27,7 @@ extern spinlock_t vsock_table_lock; struct vsock_sock { /* sk must be the first member. */ struct sock sk; + const struct vsock_transport *transport; struct sockaddr_vm local_addr; struct sockaddr_vm remote_addr; /* Links for the global tables of bound and connected sockets. */ @@ -64,16 +65,18 @@ struct vsock_sock { bool sent_request; bool ignore_connecting_rst; + /* Protected by lock_sock(sk) */ + u64 buffer_size; + u64 buffer_min_size; + u64 buffer_max_size; + /* Private to transport. */ void *trans; }; s64 vsock_stream_has_data(struct vsock_sock *vsk); s64 vsock_stream_has_space(struct vsock_sock *vsk); -struct sock *__vsock_create(struct net *net, - struct socket *sock, - struct sock *parent, - gfp_t priority, unsigned short type, int kern); +struct sock *vsock_create_connected(struct sock *parent); /**** TRANSPORT ****/ @@ -88,7 +91,17 @@ struct vsock_transport_send_notify_data { u64 data2; /* Transport-defined. */ }; +/* Transport features flags */ +/* Transport provides host->guest communication */ +#define VSOCK_TRANSPORT_F_H2G 0x00000001 +/* Transport provides guest->host communication */ +#define VSOCK_TRANSPORT_F_G2H 0x00000002 +/* Transport provides DGRAM communication */ +#define VSOCK_TRANSPORT_F_DGRAM 0x00000004 + struct vsock_transport { + struct module *module; + /* Initialize/tear-down socket. */ int (*init)(struct vsock_sock *, struct vsock_sock *); void (*destruct)(struct vsock_sock *); @@ -139,33 +152,23 @@ struct vsock_transport { struct vsock_transport_send_notify_data *); int (*notify_send_post_enqueue)(struct vsock_sock *, ssize_t, struct vsock_transport_send_notify_data *); + /* sk_lock held by the caller */ + void (*notify_buffer_size)(struct vsock_sock *, u64 *); /* Shutdown. */ int (*shutdown)(struct vsock_sock *, int); - /* Buffer sizes. */ - void (*set_buffer_size)(struct vsock_sock *, u64); - void (*set_min_buffer_size)(struct vsock_sock *, u64); - void (*set_max_buffer_size)(struct vsock_sock *, u64); - u64 (*get_buffer_size)(struct vsock_sock *); - u64 (*get_min_buffer_size)(struct vsock_sock *); - u64 (*get_max_buffer_size)(struct vsock_sock *); - /* Addressing. */ u32 (*get_local_cid)(void); }; /**** CORE ****/ -int __vsock_core_init(const struct vsock_transport *t, struct module *owner); -static inline int vsock_core_init(const struct vsock_transport *t) -{ - return __vsock_core_init(t, THIS_MODULE); -} -void vsock_core_exit(void); +int vsock_core_register(const struct vsock_transport *t, int features); +void vsock_core_unregister(const struct vsock_transport *t); /* The transport may downcast this to access transport-specific functions */ -const struct vsock_transport *vsock_core_get_transport(void); +const struct vsock_transport *vsock_core_get_transport(struct vsock_sock *vsk); /**** UTILS ****/ @@ -193,6 +196,8 @@ struct sock *vsock_find_connected_socket(struct sockaddr_vm *src, struct sockaddr_vm *dst); void vsock_remove_sock(struct vsock_sock *vsk); void vsock_for_each_connected_socket(void (*fn)(struct sock *sk)); +int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk); +bool vsock_find_cid(unsigned int cid); /**** TAP ****/ diff --git a/include/net/arp.h b/include/net/arp.h index c8f580a0e6b1..4950191f6b2b 100644 --- a/include/net/arp.h +++ b/include/net/arp.h @@ -57,8 +57,8 @@ static inline void __ipv4_confirm_neigh(struct net_device *dev, u32 key) unsigned long now = jiffies; /* avoid dirtying neighbour */ - if (n->confirmed != now) - n->confirmed = now; + if (READ_ONCE(n->confirmed) != now) + WRITE_ONCE(n->confirmed, now); } rcu_read_unlock_bh(); } diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 4ab2c49423dc..059524b87c4c 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -565,6 +565,7 @@ struct vif_params { * with the get_key() callback, must be in little endian, * length given by @seq_len. * @seq_len: length of @seq. + * @vlan_id: vlan_id for VLAN group key (if nonzero) * @mode: key install mode (RX_TX, NO_TX or SET_TX) */ struct key_params { @@ -572,6 +573,7 @@ struct key_params { const u8 *seq; int key_len; int seq_len; + u16 vlan_id; u32 cipher; enum nl80211_key_mode mode; }; @@ -1124,6 +1126,7 @@ struct sta_txpwr { * (bitmask of BIT(%NL80211_STA_FLAG_...)) * @listen_interval: listen interval or -1 for no change * @aid: AID or zero for no change + * @vlan_id: VLAN ID for station (if nonzero) * @peer_aid: mesh peer AID or zero for no change * @plink_action: plink action to take * @plink_state: set the peer link state for a station @@ -1159,6 +1162,7 @@ struct station_parameters { u32 sta_modify_mask; int listen_interval; u16 aid; + u16 vlan_id; u16 peer_aid; u8 supported_rates_len; u8 plink_action; @@ -2602,6 +2606,13 @@ enum wiphy_params_flags { #define IEEE80211_DEFAULT_AIRTIME_WEIGHT 256 +/* The per TXQ device queue limit in airtime */ +#define IEEE80211_DEFAULT_AQL_TXQ_LIMIT_L 5000 +#define IEEE80211_DEFAULT_AQL_TXQ_LIMIT_H 12000 + +/* The per interface airtime threshold to switch to lower queue limit */ +#define IEEE80211_AQL_THRESHOLD 24000 + /** * struct cfg80211_pmksa - PMK Security Association * @@ -6593,7 +6604,7 @@ struct cfg80211_roam_info { * time it is accessed in __cfg80211_roamed() due to delay in scheduling * rdev->event_work. In case of any failures, the reference is released * either in cfg80211_roamed() or in __cfg80211_romed(), Otherwise, it will be - * released while diconneting from the current bss. + * released while disconnecting from the current bss. */ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, gfp_t gfp); diff --git a/include/net/devlink.h b/include/net/devlink.h index 2116c88663a1..47f87b2fcf63 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -39,7 +39,8 @@ struct devlink { possible_net_t _net; struct mutex lock; u8 reload_failed:1, - reload_enabled:1; + reload_enabled:1, + registered:1; char priv[0] __aligned(NETDEV_ALIGN); }; @@ -401,6 +402,7 @@ enum devlink_param_generic_id { DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN, DEVLINK_PARAM_GENERIC_ID_FW_LOAD_POLICY, DEVLINK_PARAM_GENERIC_ID_RESET_DEV_ON_DRV_PROBE, + DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, /* add new param generic ids above here*/ __DEVLINK_PARAM_GENERIC_ID_MAX, @@ -435,6 +437,9 @@ enum devlink_param_generic_id { "reset_dev_on_drv_probe" #define DEVLINK_PARAM_GENERIC_RESET_DEV_ON_DRV_PROBE_TYPE DEVLINK_PARAM_TYPE_U8 +#define DEVLINK_PARAM_GENERIC_ENABLE_ROCE_NAME "enable_roce" +#define DEVLINK_PARAM_GENERIC_ENABLE_ROCE_TYPE DEVLINK_PARAM_TYPE_BOOL + #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate) \ { \ .id = DEVLINK_PARAM_GENERIC_ID_##_id, \ @@ -507,11 +512,13 @@ enum devlink_health_reporter_state { struct devlink_health_reporter_ops { char *name; int (*recover)(struct devlink_health_reporter *reporter, - void *priv_ctx); + void *priv_ctx, struct netlink_ext_ack *extack); int (*dump)(struct devlink_health_reporter *reporter, - struct devlink_fmsg *fmsg, void *priv_ctx); + struct devlink_fmsg *fmsg, void *priv_ctx, + struct netlink_ext_ack *extack); int (*diagnose)(struct devlink_health_reporter *reporter, - struct devlink_fmsg *fmsg); + struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack); }; /** @@ -567,6 +574,21 @@ enum devlink_trap_generic_id { DEVLINK_TRAP_GENERIC_ID_BLACKHOLE_ROUTE, DEVLINK_TRAP_GENERIC_ID_TTL_ERROR, DEVLINK_TRAP_GENERIC_ID_TAIL_DROP, + DEVLINK_TRAP_GENERIC_ID_NON_IP_PACKET, + DEVLINK_TRAP_GENERIC_ID_UC_DIP_MC_DMAC, + DEVLINK_TRAP_GENERIC_ID_DIP_LB, + DEVLINK_TRAP_GENERIC_ID_SIP_MC, + DEVLINK_TRAP_GENERIC_ID_SIP_LB, + DEVLINK_TRAP_GENERIC_ID_CORRUPTED_IP_HDR, + DEVLINK_TRAP_GENERIC_ID_IPV4_SIP_BC, + DEVLINK_TRAP_GENERIC_ID_IPV6_MC_DIP_RESERVED_SCOPE, + DEVLINK_TRAP_GENERIC_ID_IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE, + DEVLINK_TRAP_GENERIC_ID_MTU_ERROR, + DEVLINK_TRAP_GENERIC_ID_UNRESOLVED_NEIGH, + DEVLINK_TRAP_GENERIC_ID_RPF, + DEVLINK_TRAP_GENERIC_ID_REJECT_ROUTE, + DEVLINK_TRAP_GENERIC_ID_IPV4_LPM_UNICAST_MISS, + DEVLINK_TRAP_GENERIC_ID_IPV6_LPM_UNICAST_MISS, /* Add new generic trap IDs above */ __DEVLINK_TRAP_GENERIC_ID_MAX, @@ -605,6 +627,36 @@ enum devlink_trap_group_generic_id { "ttl_value_is_too_small" #define DEVLINK_TRAP_GENERIC_NAME_TAIL_DROP \ "tail_drop" +#define DEVLINK_TRAP_GENERIC_NAME_NON_IP_PACKET \ + "non_ip" +#define DEVLINK_TRAP_GENERIC_NAME_UC_DIP_MC_DMAC \ + "uc_dip_over_mc_dmac" +#define DEVLINK_TRAP_GENERIC_NAME_DIP_LB \ + "dip_is_loopback_address" +#define DEVLINK_TRAP_GENERIC_NAME_SIP_MC \ + "sip_is_mc" +#define DEVLINK_TRAP_GENERIC_NAME_SIP_LB \ + "sip_is_loopback_address" +#define DEVLINK_TRAP_GENERIC_NAME_CORRUPTED_IP_HDR \ + "ip_header_corrupted" +#define DEVLINK_TRAP_GENERIC_NAME_IPV4_SIP_BC \ + "ipv4_sip_is_limited_bc" +#define DEVLINK_TRAP_GENERIC_NAME_IPV6_MC_DIP_RESERVED_SCOPE \ + "ipv6_mc_dip_reserved_scope" +#define DEVLINK_TRAP_GENERIC_NAME_IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE \ + "ipv6_mc_dip_interface_local_scope" +#define DEVLINK_TRAP_GENERIC_NAME_MTU_ERROR \ + "mtu_value_is_too_small" +#define DEVLINK_TRAP_GENERIC_NAME_UNRESOLVED_NEIGH \ + "unresolved_neigh" +#define DEVLINK_TRAP_GENERIC_NAME_RPF \ + "mc_reverse_path_forwarding" +#define DEVLINK_TRAP_GENERIC_NAME_REJECT_ROUTE \ + "reject_route" +#define DEVLINK_TRAP_GENERIC_NAME_IPV4_LPM_UNICAST_MISS \ + "ipv4_lpm_miss" +#define DEVLINK_TRAP_GENERIC_NAME_IPV6_LPM_UNICAST_MISS \ + "ipv6_lpm_miss" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_L2_DROPS \ "l2_drops" @@ -644,7 +696,7 @@ enum devlink_trap_group_generic_id { } struct devlink_ops { - int (*reload_down)(struct devlink *devlink, + int (*reload_down)(struct devlink *devlink, bool netns_change, struct netlink_ext_ack *extack); int (*reload_up)(struct devlink *devlink, struct netlink_ext_ack *extack); @@ -772,6 +824,8 @@ static inline struct devlink *netdev_to_devlink(struct net_device *dev) struct ib_device; +struct net *devlink_net(const struct devlink *devlink); +void devlink_net_set(struct devlink *devlink, struct net *net); struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size); int devlink_register(struct devlink *devlink, struct device *dev); void devlink_unregister(struct devlink *devlink); @@ -917,8 +971,6 @@ 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); int devlink_fmsg_bool_pair_put(struct devlink_fmsg *fmsg, const char *name, bool value); @@ -931,7 +983,7 @@ int devlink_fmsg_u64_pair_put(struct devlink_fmsg *fmsg, const char *name, int devlink_fmsg_string_pair_put(struct devlink_fmsg *fmsg, const char *name, const char *value); int devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name, - const void *value, u16 value_len); + const void *value, u32 value_len); struct devlink_health_reporter * devlink_health_reporter_create(struct devlink *devlink, diff --git a/include/net/dsa.h b/include/net/dsa.h index 541fb514e31d..6767dc3f66c0 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -42,6 +42,7 @@ struct phylink_link_state; #define DSA_TAG_PROTO_8021Q_VALUE 12 #define DSA_TAG_PROTO_SJA1105_VALUE 13 #define DSA_TAG_PROTO_KSZ8795_VALUE 14 +#define DSA_TAG_PROTO_OCELOT_VALUE 15 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -59,6 +60,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_8021Q = DSA_TAG_PROTO_8021Q_VALUE, DSA_TAG_PROTO_SJA1105 = DSA_TAG_PROTO_SJA1105_VALUE, DSA_TAG_PROTO_KSZ8795 = DSA_TAG_PROTO_KSZ8795_VALUE, + DSA_TAG_PROTO_OCELOT = DSA_TAG_PROTO_OCELOT_VALUE, }; struct packet_type; @@ -94,8 +96,6 @@ struct __dsa_skb_cb { u8 priv[48 - sizeof(struct dsa_skb_cb)]; }; -#define __DSA_SKB_CB(skb) ((struct __dsa_skb_cb *)((skb)->cb)) - #define DSA_SKB_CB(skb) ((struct dsa_skb_cb *)((skb)->cb)) #define DSA_SKB_CB_PRIV(skb) \ @@ -122,15 +122,11 @@ struct dsa_switch_tree { */ struct dsa_platform_data *pd; - /* - * The switch port to which the CPU is attached. - */ - struct dsa_port *cpu_dp; + /* List of switch ports */ + struct list_head ports; - /* - * Data for the individual switch chips. - */ - struct dsa_switch *ds[DSA_MAX_SWITCHES]; + /* List of DSA links composing the routing table */ + struct list_head rtable; }; /* TC matchall action types, only mirroring for now */ @@ -197,6 +193,8 @@ struct dsa_port { struct work_struct xmit_work; struct sk_buff_head xmit_queue; + struct list_head list; + /* * Give the switch driver somewhere to hang its per-port private data * structures (accessible from the tagger). @@ -212,9 +210,24 @@ struct dsa_port { * Original copy of the master netdev net_device_ops */ const struct net_device_ops *orig_ndo_ops; + + bool setup; +}; + +/* TODO: ideally DSA ports would have a single dp->link_dp member, + * and no dst->rtable nor this struct dsa_link would be needed, + * but this would require some more complex tree walking, + * so keep it stupid at the moment and list them all. + */ +struct dsa_link { + struct dsa_port *dp; + struct dsa_port *link_dp; + struct list_head list; }; struct dsa_switch { + bool setup; + struct device *dev; /* @@ -243,13 +256,6 @@ struct dsa_switch { const struct dsa_switch_ops *ops; /* - * An array of which element [a] indicates which port on this - * switch should be used to send packets to that are destined - * for switch a. Can be NULL if there is only one switch chip. - */ - s8 rtable[DSA_MAX_SWITCHES]; - - /* * Slave mii_bus and devices for the individual ports. */ u32 phys_mii_mask; @@ -275,14 +281,19 @@ struct dsa_switch { */ bool vlan_filtering; - /* Dynamically allocated ports, keep last */ size_t num_ports; - struct dsa_port ports[]; }; -static inline const struct dsa_port *dsa_to_port(struct dsa_switch *ds, int p) +static inline struct dsa_port *dsa_to_port(struct dsa_switch *ds, int p) { - return &ds->ports[p]; + struct dsa_switch_tree *dst = ds->dst; + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + if (dp->ds == ds && dp->index == p) + return dp; + + return NULL; } static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p) @@ -317,6 +328,19 @@ static inline u32 dsa_user_ports(struct dsa_switch *ds) return mask; } +/* Return the local port used to reach an arbitrary switch device */ +static inline unsigned int dsa_routing_port(struct dsa_switch *ds, int device) +{ + struct dsa_switch_tree *dst = ds->dst; + struct dsa_link *dl; + + list_for_each_entry(dl, &dst->rtable, list) + if (dl->dp->ds == ds && dl->link_dp->ds->index == device) + return dl->dp->index; + + return ds->num_ports; +} + /* Return the local port used to reach an arbitrary switch port */ static inline unsigned int dsa_towards_port(struct dsa_switch *ds, int device, int port) @@ -324,7 +348,7 @@ static inline unsigned int dsa_towards_port(struct dsa_switch *ds, int device, if (device == ds->index) return port; else - return ds->rtable[device]; + return dsa_routing_port(ds, device); } /* Return the local port used to reach the dedicated CPU port */ @@ -543,6 +567,45 @@ struct dsa_switch_ops { */ netdev_tx_t (*port_deferred_xmit)(struct dsa_switch *ds, int port, struct sk_buff *skb); + /* Devlink parameters */ + int (*devlink_param_get)(struct dsa_switch *ds, u32 id, + struct devlink_param_gset_ctx *ctx); + int (*devlink_param_set)(struct dsa_switch *ds, u32 id, + struct devlink_param_gset_ctx *ctx); +}; + +#define DSA_DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes) \ + DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes, \ + dsa_devlink_param_get, dsa_devlink_param_set, NULL) + +int dsa_devlink_param_get(struct devlink *dl, u32 id, + struct devlink_param_gset_ctx *ctx); +int dsa_devlink_param_set(struct devlink *dl, u32 id, + struct devlink_param_gset_ctx *ctx); +int dsa_devlink_params_register(struct dsa_switch *ds, + const struct devlink_param *params, + size_t params_count); +void dsa_devlink_params_unregister(struct dsa_switch *ds, + const struct devlink_param *params, + size_t params_count); +int dsa_devlink_resource_register(struct dsa_switch *ds, + const char *resource_name, + u64 resource_size, + u64 resource_id, + u64 parent_resource_id, + const struct devlink_resource_size_params *size_params); + +void dsa_devlink_resources_unregister(struct dsa_switch *ds); + +void dsa_devlink_resource_occ_get_register(struct dsa_switch *ds, + u64 resource_id, + devlink_resource_occ_get_t *occ_get, + void *occ_get_priv); +void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds, + u64 resource_id); + +struct dsa_devlink_priv { + struct dsa_switch *ds; }; struct dsa_switch_driver { @@ -570,7 +633,6 @@ static inline bool dsa_can_decode(const struct sk_buff *skb, return false; } -struct dsa_switch *dsa_switch_alloc(struct device *dev, size_t n); void dsa_unregister_switch(struct dsa_switch *ds); int dsa_register_switch(struct dsa_switch *ds); #ifdef CONFIG_PM_SLEEP diff --git a/include/net/dst.h b/include/net/dst.h index fe62fe2eb781..3448cf865ede 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -82,7 +82,7 @@ struct dst_entry { struct dst_metrics { u32 metrics[RTAX_MAX]; refcount_t refcnt; -}; +} __aligned(4); /* Low pointer bits contain DST_METRICS_FLAGS */ extern const struct dst_metrics dst_default_metrics; u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old); @@ -516,7 +516,16 @@ static inline void skb_dst_update_pmtu(struct sk_buff *skb, u32 mtu) struct dst_entry *dst = skb_dst(skb); if (dst && dst->ops->update_pmtu) - dst->ops->update_pmtu(dst, NULL, skb, mtu); + dst->ops->update_pmtu(dst, NULL, skb, mtu, true); +} + +/* update dst pmtu but not do neighbor confirm */ +static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu) +{ + struct dst_entry *dst = skb_dst(skb); + + if (dst && dst->ops->update_pmtu) + dst->ops->update_pmtu(dst, NULL, skb, mtu, false); } static inline void skb_tunnel_check_pmtu(struct sk_buff *skb, @@ -526,7 +535,7 @@ static inline void skb_tunnel_check_pmtu(struct sk_buff *skb, u32 encap_mtu = dst_mtu(encap_dst); if (skb->len > encap_mtu - headroom) - skb_dst_update_pmtu(skb, encap_mtu - headroom); + skb_dst_update_pmtu_no_confirm(skb, encap_mtu - headroom); } #endif /* _NET_DST_H */ diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 5ec645f27ee3..443863c7b8da 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -27,7 +27,8 @@ struct dst_ops { struct dst_entry * (*negative_advice)(struct dst_entry *); void (*link_failure)(struct sk_buff *); void (*update_pmtu)(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu); + struct sk_buff *skb, u32 mtu, + bool confirm_neigh); void (*redirect)(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); int (*local_out)(struct net *net, struct sock *sk, struct sk_buff *skb); diff --git a/include/net/fib_notifier.h b/include/net/fib_notifier.h index c49d7bfb5c30..6d59221ff05a 100644 --- a/include/net/fib_notifier.h +++ b/include/net/fib_notifier.h @@ -8,7 +8,6 @@ struct module; struct fib_notifier_info { - struct net *net; int family; struct netlink_ext_ack *extack; }; @@ -30,19 +29,21 @@ struct fib_notifier_ops { int family; struct list_head list; unsigned int (*fib_seq_read)(struct net *net); - int (*fib_dump)(struct net *net, struct notifier_block *nb); + int (*fib_dump)(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack); struct module *owner; struct rcu_head rcu; }; -int call_fib_notifier(struct notifier_block *nb, struct net *net, +int call_fib_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info); int call_fib_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info); -int register_fib_notifier(struct notifier_block *nb, - void (*cb)(struct notifier_block *nb)); -int unregister_fib_notifier(struct notifier_block *nb); +int register_fib_notifier(struct net *net, struct notifier_block *nb, + void (*cb)(struct notifier_block *nb), + struct netlink_ext_ack *extack); +int unregister_fib_notifier(struct net *net, struct notifier_block *nb); struct fib_notifier_ops * fib_notifier_ops_register(const struct fib_notifier_ops *tmpl, struct net *net); void fib_notifier_ops_unregister(struct fib_notifier_ops *ops); diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 20dcadd8eed9..54e227e6b06a 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -194,7 +194,8 @@ int fib_rules_lookup(struct fib_rules_ops *, struct flowi *, int flags, int fib_default_rule_add(struct fib_rules_ops *, u32 pref, u32 table, u32 flags); bool fib_rule_matchall(const struct fib_rule *rule); -int fib_rules_dump(struct net *net, struct notifier_block *nb, int family); +int fib_rules_dump(struct net *net, struct notifier_block *nb, int family, + struct netlink_ext_ack *extack); unsigned int fib_rules_seq_read(struct net *net, int family); int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 5cd12276ae21..d93017a7ce5c 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -7,6 +7,8 @@ #include <linux/siphash.h> #include <uapi/linux/if_ether.h> +struct sk_buff; + /** * struct flow_dissector_key_control: * @thoff: Transport header offset @@ -46,9 +48,14 @@ struct flow_dissector_key_tags { }; struct flow_dissector_key_vlan { - u16 vlan_id:12, - vlan_dei:1, - vlan_priority:3; + union { + struct { + u16 vlan_id:12, + vlan_dei:1, + vlan_priority:3; + }; + __be16 vlan_tci; + }; __be16 vlan_tpid; }; @@ -157,19 +164,16 @@ struct flow_dissector_key_ports { /** * flow_dissector_key_icmp: - * @ports: type and code of ICMP header - * icmp: ICMP type (high) and code (low) * type: ICMP type * code: ICMP code + * id: session identifier */ struct flow_dissector_key_icmp { - union { - __be16 icmp; - struct { - u8 type; - u8 code; - }; + struct { + u8 type; + u8 code; }; + u16 id; }; /** @@ -204,9 +208,11 @@ struct flow_dissector_key_ip { /** * struct flow_dissector_key_meta: * @ingress_ifindex: ingress ifindex + * @ingress_iftype: ingress interface type */ struct flow_dissector_key_meta { int ingress_ifindex; + u16 ingress_iftype; }; /** @@ -229,6 +235,7 @@ enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_IPV4_ADDRS, /* struct flow_dissector_key_ipv4_addrs */ FLOW_DISSECTOR_KEY_IPV6_ADDRS, /* struct flow_dissector_key_ipv6_addrs */ FLOW_DISSECTOR_KEY_PORTS, /* struct flow_dissector_key_ports */ + FLOW_DISSECTOR_KEY_PORTS_RANGE, /* struct flow_dissector_key_ports */ FLOW_DISSECTOR_KEY_ICMP, /* struct flow_dissector_key_icmp */ FLOW_DISSECTOR_KEY_ETH_ADDRS, /* struct flow_dissector_key_eth_addrs */ FLOW_DISSECTOR_KEY_TIPC, /* struct flow_dissector_key_tipc */ @@ -283,6 +290,8 @@ struct flow_keys { struct flow_dissector_key_vlan cvlan; struct flow_dissector_key_keyid keyid; struct flow_dissector_key_ports ports; + struct flow_dissector_key_icmp icmp; + /* 'addrs' must be the last member */ struct flow_dissector_key_addrs addrs; }; @@ -316,6 +325,9 @@ static inline bool flow_keys_have_l4(const struct flow_keys *keys) } u32 flow_hash_from_keys(struct flow_keys *keys); +void skb_flow_get_icmp_tci(const struct sk_buff *skb, + struct flow_dissector_key_icmp *key_icmp, + void *data, int thoff, int hlen); static inline bool dissector_uses_key(const struct flow_dissector *flow_dissector, enum flow_dissector_key_id key_id) diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 86c567f531f3..c6f7bd22db60 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -380,19 +380,18 @@ static inline void flow_block_init(struct flow_block *flow_block) typedef int flow_indr_block_bind_cb_t(struct net_device *dev, void *cb_priv, enum tc_setup_type type, void *type_data); -typedef void flow_indr_block_ing_cmd_t(struct net_device *dev, - flow_indr_block_bind_cb_t *cb, - void *cb_priv, - enum flow_block_command command); +typedef void flow_indr_block_cmd_t(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, void *cb_priv, + enum flow_block_command command); -struct flow_indr_block_ing_entry { - flow_indr_block_ing_cmd_t *cb; +struct flow_indr_block_entry { + flow_indr_block_cmd_t *cb; struct list_head list; }; -void flow_indr_add_block_ing_cb(struct flow_indr_block_ing_entry *entry); +void flow_indr_add_block_cb(struct flow_indr_block_entry *entry); -void flow_indr_del_block_ing_cb(struct flow_indr_block_ing_entry *entry); +void flow_indr_del_block_cb(struct flow_indr_block_entry *entry); int __flow_indr_block_cb_register(struct net_device *dev, void *cb_priv, flow_indr_block_bind_cb_t *cb, diff --git a/include/net/garp.h b/include/net/garp.h index c41833bd4590..4d9a0c6a2e5f 100644 --- a/include/net/garp.h +++ b/include/net/garp.h @@ -37,7 +37,7 @@ struct garp_skb_cb { static inline struct garp_skb_cb *garp_cb(struct sk_buff *skb) { BUILD_BUG_ON(sizeof(struct garp_skb_cb) > - FIELD_SIZEOF(struct sk_buff, cb)); + sizeof_field(struct sk_buff, cb)); return (struct garp_skb_cb *)skb->cb; } diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h index ca23860adbb9..1424e02cef90 100644 --- a/include/net/gen_stats.h +++ b/include/net/gen_stats.h @@ -7,6 +7,12 @@ #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; struct u64_stats_sync syncp; diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 9292f1c588b7..74950663bb00 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -75,8 +75,6 @@ struct genl_family { struct module *module; }; -struct nlattr **genl_family_attrbuf(const struct genl_family *family); - /** * struct genl_info - receiving information * @snd_seq: sending sequence number @@ -128,6 +126,24 @@ enum genl_validate_flags { }; /** + * struct genl_info - info that is available during dumpit op call + * @family: generic netlink family - for internal genl code usage + * @ops: generic netlink ops - for internal genl code usage + * @attrs: netlink attributes + */ +struct genl_dumpit_info { + const struct genl_family *family; + const struct genl_ops *ops; + struct nlattr **attrs; +}; + +static inline const struct genl_dumpit_info * +genl_dumpit_info(struct netlink_callback *cb) +{ + return cb->data; +} + +/** * struct genl_ops - generic netlink operations * @cmd: command identifier * @internal_flags: flags used by the family diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index af2b4c065a04..d0019d3395cf 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -103,13 +103,19 @@ struct inet_bind_hashbucket { struct hlist_head chain; }; -/* - * Sockets can be hashed in established or listening table +/* Sockets can be hashed in established or listening table. + * We must use different 'nulls' end-of-chain value for all hash buckets : + * A socket might transition from ESTABLISH to LISTEN state without + * RCU grace period. A lookup in ehash table needs to handle this case. */ +#define LISTENING_NULLS_BASE (1U << 29) struct inet_listen_hashbucket { spinlock_t lock; unsigned int count; - struct hlist_head head; + union { + struct hlist_head head; + struct hlist_nulls_head nulls_head; + }; }; /* This is for listening sockets, thus all sockets which possess wildcards. */ diff --git a/include/net/ip.h b/include/net/ip.h index a2c61c36dc4a..5b317c9f4470 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -339,10 +339,10 @@ static inline u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_o void inet_get_local_port_range(struct net *net, int *low, int *high); #ifdef CONFIG_SYSCTL -static inline int inet_is_local_reserved_port(struct net *net, int port) +static inline bool inet_is_local_reserved_port(struct net *net, unsigned short port) { if (!net->ipv4.sysctl_local_reserved_ports) - return 0; + return false; return test_bit(port, net->ipv4.sysctl_local_reserved_ports); } @@ -351,20 +351,20 @@ static inline bool sysctl_dev_name_is_allowed(const char *name) return strcmp(name, "default") != 0 && strcmp(name, "all") != 0; } -static inline int inet_prot_sock(struct net *net) +static inline bool inet_port_requires_bind_service(struct net *net, unsigned short port) { - return net->ipv4.sysctl_ip_prot_sock; + return port < net->ipv4.sysctl_ip_prot_sock; } #else -static inline int inet_is_local_reserved_port(struct net *net, int port) +static inline bool inet_is_local_reserved_port(struct net *net, unsigned short port) { - return 0; + return false; } -static inline int inet_prot_sock(struct net *net) +static inline bool inet_port_requires_bind_service(struct net *net, unsigned short port) { - return PROT_SOCK; + return port < PROT_SOCK; } #endif @@ -760,4 +760,9 @@ int ip_misc_proc_init(void); int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, u8 family, struct netlink_ext_ack *extack); +static inline bool inetdev_valid_mtu(unsigned int mtu) +{ + return likely(mtu >= IPV4_MIN_MTU); +} + #endif /* _IP_H */ diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 4b5656c71abc..f1535f172935 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -90,7 +90,32 @@ struct fib6_gc_args { #ifndef CONFIG_IPV6_SUBTREES #define FIB6_SUBTREE(fn) NULL + +static inline bool fib6_routes_require_src(const struct net *net) +{ + return false; +} + +static inline void fib6_routes_require_src_inc(struct net *net) {} +static inline void fib6_routes_require_src_dec(struct net *net) {} + #else + +static inline bool fib6_routes_require_src(const struct net *net) +{ + return net->ipv6.fib6_routes_require_src > 0; +} + +static inline void fib6_routes_require_src_inc(struct net *net) +{ + net->ipv6.fib6_routes_require_src++; +} + +static inline void fib6_routes_require_src_dec(struct net *net) +{ + net->ipv6.fib6_routes_require_src--; +} + #define FIB6_SUBTREE(fn) (rcu_dereference_protected((fn)->subtree, 1)) #endif @@ -212,6 +237,11 @@ static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst) return ((struct rt6_info *)dst)->rt6i_idev; } +static inline bool fib6_requires_src(const struct fib6_info *rt) +{ + return rt->fib6_src.plen > 0; +} + static inline void fib6_clean_expires(struct fib6_info *f6i) { f6i->fib6_flags &= ~RTF_EXPIRES; @@ -478,7 +508,7 @@ struct ipv6_route_iter { extern const struct seq_operations ipv6_route_seq_ops; -int call_fib6_notifier(struct notifier_block *nb, struct net *net, +int call_fib6_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info); int call_fib6_notifiers(struct net *net, enum fib_event_type event_type, @@ -488,7 +518,8 @@ int __net_init fib6_notifier_init(struct net *net); void __net_exit fib6_notifier_exit(struct net *net); unsigned int fib6_tables_seq_read(struct net *net); -int fib6_tables_dump(struct net *net, struct notifier_block *nb); +int fib6_tables_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack); void fib6_update_sernum(struct net *net, struct fib6_info *rt); void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt); @@ -501,10 +532,16 @@ static inline bool fib6_metric_locked(struct fib6_info *f6i, int metric) } #ifdef CONFIG_IPV6_MULTIPLE_TABLES +static inline bool fib6_has_custom_rules(const struct net *net) +{ + return net->ipv6.fib6_has_custom_rules; +} + int fib6_rules_init(void); void fib6_rules_cleanup(void); bool fib6_rule_default(const struct fib_rule *rule); -int fib6_rules_dump(struct net *net, struct notifier_block *nb); +int fib6_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack); unsigned int fib6_rules_seq_read(struct net *net); static inline bool fib6_rules_early_flow_dissect(struct net *net, @@ -525,6 +562,10 @@ static inline bool fib6_rules_early_flow_dissect(struct net *net, return true; } #else +static inline bool fib6_has_custom_rules(const struct net *net) +{ + return false; +} static inline int fib6_rules_init(void) { return 0; @@ -537,7 +578,8 @@ static inline bool fib6_rule_default(const struct fib_rule *rule) { return true; } -static inline int fib6_rules_dump(struct net *net, struct notifier_block *nb) +static inline int fib6_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { return 0; } diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index ab1ca9e238d2..b9cba41c6d4f 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -219,7 +219,7 @@ struct fib_nh_notifier_info { struct fib_nh *fib_nh; }; -int call_fib4_notifier(struct notifier_block *nb, struct net *net, +int call_fib4_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info); int call_fib4_notifiers(struct net *net, enum fib_event_type event_type, @@ -229,7 +229,8 @@ int __net_init fib4_notifier_init(struct net *net); void __net_exit fib4_notifier_exit(struct net *net); void fib_info_notify_update(struct net *net, struct nl_info *info); -void fib_notify(struct net *net, struct notifier_block *nb); +int fib_notify(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack); struct fib_table { struct hlist_node tb_hlist; @@ -310,12 +311,18 @@ static inline int fib_lookup(struct net *net, const struct flowi4 *flp, return err; } +static inline bool fib4_has_custom_rules(const struct net *net) +{ + return false; +} + static inline bool fib4_rule_default(const struct fib_rule *rule) { return true; } -static inline int fib4_rules_dump(struct net *net, struct notifier_block *nb) +static inline int fib4_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { return 0; } @@ -376,8 +383,14 @@ out: return err; } +static inline bool fib4_has_custom_rules(const struct net *net) +{ + return net->ipv4.fib_has_custom_rules; +} + bool fib4_rule_default(const struct fib_rule *rule); -int fib4_rules_dump(struct net *net, struct notifier_block *nb); +int fib4_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack); unsigned int fib4_rules_seq_read(struct net *net); static inline bool fib4_rules_early_flow_dissect(struct net *net, diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index af645604f328..236503a50759 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -33,8 +33,8 @@ /* Used to memset ipv4 address padding. */ #define IP_TUNNEL_KEY_IPV4_PAD offsetofend(struct ip_tunnel_key, u.ipv4.dst) #define IP_TUNNEL_KEY_IPV4_PAD_LEN \ - (FIELD_SIZEOF(struct ip_tunnel_key, u) - \ - FIELD_SIZEOF(struct ip_tunnel_key, u.ipv4)) + (sizeof_field(struct ip_tunnel_key, u) - \ + sizeof_field(struct ip_tunnel_key, u.ipv4)) struct ip_tunnel_key { __be64 tun_id; @@ -63,7 +63,7 @@ struct ip_tunnel_key { /* Maximum tunnel options length. */ #define IP_TUNNEL_OPTS_MAX \ - GENMASK((FIELD_SIZEOF(struct ip_tunnel_info, \ + GENMASK((sizeof_field(struct ip_tunnel_info, \ options_len) * BITS_PER_BYTE) - 1, 0) struct ip_tunnel_info { diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 078887c8c586..83be2d93b407 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1325,7 +1325,7 @@ void ip_vs_protocol_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_control_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_estimator_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_sync_net_cleanup(struct netns_ipvs *ipvs); -void ip_vs_service_net_cleanup(struct netns_ipvs *ipvs); +void ip_vs_service_nets_cleanup(struct list_head *net_list); /* IPVS application functions * (from ip_vs_app.c) diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 009605c56f20..4e95f6df508c 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -696,6 +696,11 @@ static inline bool ipv6_addr_v4mapped(const struct in6_addr *a) cpu_to_be32(0x0000ffff))) == 0UL; } +static inline bool ipv6_addr_v4mapped_loopback(const struct in6_addr *a) +{ + return ipv6_addr_v4mapped(a) && ipv4_is_loopback(a->s6_addr32[3]); +} + static inline u32 ipv6_portaddr_hash(const struct net *net, const struct in6_addr *addr6, unsigned int port) @@ -1017,7 +1022,7 @@ static inline struct sk_buff *ip6_finish_skb(struct sock *sk) int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6); -struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6, +struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst); struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst, diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index 5c93e942c50b..3e7d2c0e79ca 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -24,8 +24,10 @@ struct ipv6_stub { const struct in6_addr *addr); int (*ipv6_sock_mc_drop)(struct sock *sk, int ifindex, const struct in6_addr *addr); - int (*ipv6_dst_lookup)(struct net *net, struct sock *sk, - struct dst_entry **dst, struct flowi6 *fl6); + struct dst_entry *(*ipv6_dst_lookup_flow)(struct net *net, + const struct sock *sk, + struct flowi6 *fl6, + const struct in6_addr *final_dst); int (*ipv6_route_input)(struct sk_buff *skb); struct fib6_table *(*fib6_get_table)(struct net *net, u32 id); diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 523c6a09e1c8..aa145808e57a 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -312,7 +312,7 @@ struct ieee80211_vif_chanctx_switch { * @BSS_CHANGED_KEEP_ALIVE: keep alive options (idle period or protected * keep alive) changed. * @BSS_CHANGED_MCAST_RATE: Multicast Rate setting changed for this interface - * @BSS_CHANGED_FTM_RESPONDER: fime timing reasurement request responder + * @BSS_CHANGED_FTM_RESPONDER: fine timing measurement request responder * functionality changed for this BSS (AP mode). * @BSS_CHANGED_TWT: TWT status changed * @BSS_CHANGED_HE_OBSS_PD: OBSS Packet Detection status changed. @@ -967,6 +967,7 @@ ieee80211_rate_get_vht_nss(const struct ieee80211_tx_rate *rate) * @band: the band to transmit on (use for checking for races) * @hw_queue: HW queue to put the frame on, skb_get_queue_mapping() gives the AC * @ack_frame_id: internal frame ID for TX status, used internally + * @tx_time_est: TX time estimate in units of 4us, used internally * @control: union part for control data * @control.rates: TX rates array to try * @control.rts_cts_rate_idx: rate for RTS or CTS @@ -1007,7 +1008,8 @@ struct ieee80211_tx_info { u8 hw_queue; - u16 ack_frame_id; + u16 ack_frame_id:6; + u16 tx_time_est:10; union { struct { @@ -1058,8 +1060,24 @@ struct ieee80211_tx_info { }; }; +static inline u16 +ieee80211_info_set_tx_time_est(struct ieee80211_tx_info *info, u16 tx_time_est) +{ + /* We only have 10 bits in tx_time_est, so store airtime + * in increments of 4us and clamp the maximum to 2**12-1 + */ + info->tx_time_est = min_t(u16, tx_time_est, 4095) >> 2; + return info->tx_time_est << 2; +} + +static inline u16 +ieee80211_info_get_tx_time_est(struct ieee80211_tx_info *info) +{ + return info->tx_time_est << 2; +} + /** - * struct ieee80211_tx_status - extended tx staus info for rate control + * struct ieee80211_tx_status - extended tx status info for rate control * * @sta: Station that the packet was transmitted for * @info: Basic tx status information @@ -1702,7 +1720,7 @@ struct wireless_dev *ieee80211_vif_to_wdev(struct ieee80211_vif *vif); * %IEEE80211_KEY_FLAG_SW_MGMT_TX flag to encrypt such frames in SW. * @IEEE80211_KEY_FLAG_GENERATE_IV_MGMT: This flag should be set by the * driver for a CCMP/GCMP key to indicate that is requires IV generation - * only for managment frames (MFP). + * only for management frames (MFP). * @IEEE80211_KEY_FLAG_RESERVE_TAILROOM: This flag should be set by the * driver for a key to indicate that sufficient tailroom must always * be reserved for ICV or MIC, even when HW encryption is enabled. @@ -1998,7 +2016,7 @@ struct ieee80211_sta { * * * If the skb is transmitted as part of a BA agreement, the * A-MSDU maximal size is min(max_amsdu_len, 4065) bytes. - * * If the skb is not part of a BA aggreement, the A-MSDU maximal + * * If the skb is not part of a BA agreement, the A-MSDU maximal * size is min(max_amsdu_len, 7935) bytes. * * Both additional HT limits must be enforced by the low level @@ -2626,7 +2644,7 @@ ieee80211_get_alt_retry_rate(const struct ieee80211_hw *hw, * @hw: the hardware * @skb: the skb * - * Free a transmit skb. Use this funtion when some failure + * Free a transmit skb. Use this function when some failure * to transmit happened and thus status cannot be reported. */ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb); @@ -3095,7 +3113,9 @@ enum ieee80211_filter_flags { * * @IEEE80211_AMPDU_RX_START: start RX aggregation * @IEEE80211_AMPDU_RX_STOP: stop RX aggregation - * @IEEE80211_AMPDU_TX_START: start TX aggregation + * @IEEE80211_AMPDU_TX_START: start TX aggregation, the driver must either + * call ieee80211_start_tx_ba_cb_irqsafe() or return the special + * status %IEEE80211_AMPDU_TX_START_IMMEDIATE. * @IEEE80211_AMPDU_TX_OPERATIONAL: TX aggregation has become operational * @IEEE80211_AMPDU_TX_STOP_CONT: stop TX aggregation but continue transmitting * queued packets, now unaggregated. After all packets are transmitted the @@ -3119,6 +3139,8 @@ enum ieee80211_ampdu_mlme_action { IEEE80211_AMPDU_TX_OPERATIONAL, }; +#define IEEE80211_AMPDU_TX_START_IMMEDIATE 1 + /** * struct ieee80211_ampdu_params - AMPDU action parameters * @@ -3183,13 +3205,13 @@ enum ieee80211_rate_control_changed { * * With the support for multi channel contexts and multi channel operations, * remain on channel operations might be limited/deferred/aborted by other - * flows/operations which have higher priority (and vise versa). + * flows/operations which have higher priority (and vice versa). * Specifying the ROC type can be used by devices to prioritize the ROC * operations compared to other operations/flows. * * @IEEE80211_ROC_TYPE_NORMAL: There are no special requirements for this ROC. * @IEEE80211_ROC_TYPE_MGMT_TX: The remain on channel request is required - * for sending managment frames offchannel. + * for sending management frames offchannel. */ enum ieee80211_roc_type { IEEE80211_ROC_TYPE_NORMAL = 0, @@ -3896,7 +3918,10 @@ struct ieee80211_ops { * * Even ``189`` would be wrong since 1 could be lost again. * - * Returns a negative error code on failure. + * Returns a negative error code on failure. The driver may return + * %IEEE80211_AMPDU_TX_START_IMMEDIATE for %IEEE80211_AMPDU_TX_START + * if the session can start immediately. + * * The callback can sleep. */ int (*ampdu_action)(struct ieee80211_hw *hw, @@ -5557,6 +5582,18 @@ void ieee80211_sta_register_airtime(struct ieee80211_sta *pubsta, u8 tid, u32 tx_airtime, u32 rx_airtime); /** + * ieee80211_txq_airtime_check - check if a txq can send frame to device + * + * @hw: pointer obtained from ieee80211_alloc_hw() + * @txq: pointer obtained from station or virtual interface + * + * Return true if the AQL's airtime limit has not been reached and the txq can + * continue to send more packets to the device. Otherwise return false. + */ +bool +ieee80211_txq_airtime_check(struct ieee80211_hw *hw, struct ieee80211_txq *txq); + +/** * ieee80211_iter_keys - iterate keys programmed into the device * @hw: pointer obtained from ieee80211_alloc_hw() * @vif: virtual interface to iterate, may be %NULL for all @@ -5609,7 +5646,7 @@ void ieee80211_iter_keys_rcu(struct ieee80211_hw *hw, /** * ieee80211_iter_chan_contexts_atomic - iterate channel contexts - * @hw: pointre obtained from ieee80211_alloc_hw(). + * @hw: pointer obtained from ieee80211_alloc_hw(). * @iter: iterator function * @iter_data: data passed to iterator function * @@ -6357,7 +6394,7 @@ ieee80211_return_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq, * again. * * The API ieee80211_txq_may_transmit() also ensures that TXQ list will be - * aligned aginst driver's own round-robin scheduler list. i.e it rotates + * aligned against driver's own round-robin scheduler list. i.e it rotates * the TXQ list till it makes the requested node becomes the first entry * in TXQ list. Thus both the TXQ list and driver's list are in sync. If this * function returns %true, the driver is expected to schedule packets @@ -6415,4 +6452,33 @@ void ieee80211_nan_func_match(struct ieee80211_vif *vif, struct cfg80211_nan_match_params *match, gfp_t gfp); +/** + * ieee80211_calc_rx_airtime - calculate estimated transmission airtime for RX. + * + * This function calculates the estimated airtime usage of a frame based on the + * rate information in the RX status struct and the frame length. + * + * @hw: pointer as obtained from ieee80211_alloc_hw() + * @status: &struct ieee80211_rx_status containing the transmission rate + * information. + * @len: frame length in bytes + */ +u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, + struct ieee80211_rx_status *status, + int len); + +/** + * ieee80211_calc_tx_airtime - calculate estimated transmission airtime for TX. + * + * This function calculates the estimated airtime usage of a frame based on the + * rate information in the TX info struct and the frame length. + * + * @hw: pointer as obtained from ieee80211_alloc_hw() + * @info: &struct ieee80211_tx_info of the frame. + * @len: frame length in bytes + */ +u32 ieee80211_calc_tx_airtime(struct ieee80211_hw *hw, + struct ieee80211_tx_info *info, + int len); + #endif /* MAC80211_H */ diff --git a/include/net/mrp.h b/include/net/mrp.h index ef58b4a07190..1c308c034e1a 100644 --- a/include/net/mrp.h +++ b/include/net/mrp.h @@ -39,7 +39,7 @@ struct mrp_skb_cb { static inline struct mrp_skb_cb *mrp_cb(struct sk_buff *skb) { BUILD_BUG_ON(sizeof(struct mrp_skb_cb) > - FIELD_SIZEOF(struct sk_buff, cb)); + sizeof_field(struct sk_buff, cb)); return (struct mrp_skb_cb *)skb->cb; } diff --git a/include/net/ndisc.h b/include/net/ndisc.h index b2f715ca0567..b5ebeb3b0de0 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -414,8 +414,8 @@ static inline void __ipv6_confirm_neigh(struct net_device *dev, unsigned long now = jiffies; /* avoid dirtying neighbour */ - if (n->confirmed != now) - n->confirmed = now; + if (READ_ONCE(n->confirmed) != now) + WRITE_ONCE(n->confirmed, now); } rcu_read_unlock_bh(); } @@ -431,8 +431,8 @@ static inline void __ipv6_confirm_neigh_stub(struct net_device *dev, unsigned long now = jiffies; /* avoid dirtying neighbour */ - if (n->confirmed != now) - n->confirmed = now; + if (READ_ONCE(n->confirmed) != now) + WRITE_ONCE(n->confirmed, now); } rcu_read_unlock_bh(); } diff --git a/include/net/neighbour.h b/include/net/neighbour.h index b8452cc0e059..8ec77bfdc1a4 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -72,7 +72,6 @@ struct neigh_parms { struct net_device *dev; struct list_head list; int (*neigh_setup)(struct neighbour *); - void (*neigh_cleanup)(struct neighbour *); struct neigh_table *tbl; void *sysctl_table; @@ -468,7 +467,7 @@ static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb do { seq = read_seqbegin(&hh->hh_lock); - hh_len = hh->hh_len; + hh_len = READ_ONCE(hh->hh_len); if (likely(hh_len <= HH_DATA_MOD)) { hh_alen = HH_DATA_MOD; diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index c7e15a213ef2..b8ceaf0cd997 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -36,6 +36,7 @@ #include <linux/ns_common.h> #include <linux/idr.h> #include <linux/skbuff.h> +#include <linux/notifier.h> struct user_namespace; struct proc_dir_entry; @@ -104,6 +105,8 @@ struct net { struct hlist_head *dev_name_head; struct hlist_head *dev_index_head; + struct raw_notifier_head netdev_chain; + /* Note that @hash_mix can be read millions times per second, * it is critical that it is on a read_mostly cache line. */ @@ -326,7 +329,8 @@ static inline struct net *read_pnet(const possible_net_t *pnet) /* Protected by net_rwsem */ #define for_each_net(VAR) \ list_for_each_entry(VAR, &net_namespace_list, list) - +#define for_each_net_continue_reverse(VAR) \ + list_for_each_entry_continue_reverse(VAR, &net_namespace_list, list) #define for_each_net_rcu(VAR) \ list_for_each_entry_rcu(VAR, &net_namespace_list, list) diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index 112a6f40dfaf..5ae5295aa46d 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -43,7 +43,6 @@ enum nf_ct_ext_id { /* Extensions: optional stuff which isn't permanently in struct. */ struct nf_ct_ext { - struct rcu_head rcu; u8 offset[NF_CT_EXT_NUM]; u8 len; char data[0]; @@ -72,15 +71,6 @@ static inline void *__nf_ct_ext_find(const struct nf_conn *ct, u8 id) /* Destroy all relationships */ void nf_ct_ext_destroy(struct nf_conn *ct); -/* Free operation. If you want to free a object referred from private area, - * please implement __nf_ct_ext_free() and call it. - */ -static inline void nf_ct_ext_free(struct nf_conn *ct) -{ - if (ct->ext) - kfree_rcu(ct->ext, rcu); -} - /* Add this type, returns pointer to data or NULL. */ void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp); diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index 44b5a00a9c64..37f0fbefb060 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -81,7 +81,7 @@ struct nf_conn_help { }; #define NF_CT_HELPER_BUILD_BUG_ON(structsize) \ - BUILD_BUG_ON((structsize) > FIELD_SIZEOF(struct nf_conn_help, data)) + BUILD_BUG_ON((structsize) > sizeof_field(struct nf_conn_help, data)) struct nf_conntrack_helper *__nf_conntrack_helper_find(const char *name, u16 l3num, u8 protonum); diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index b37a7d608134..415b8f49d150 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -8,24 +8,43 @@ #include <linux/rcupdate.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_conntrack_tuple_common.h> +#include <net/flow_offload.h> #include <net/dst.h> struct nf_flowtable; +struct nf_flow_rule; +struct flow_offload; +enum flow_offload_tuple_dir; struct nf_flowtable_type { struct list_head list; int family; int (*init)(struct nf_flowtable *ft); + int (*setup)(struct nf_flowtable *ft, + struct net_device *dev, + enum flow_block_command cmd); + int (*action)(struct net *net, + const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct nf_flow_rule *flow_rule); void (*free)(struct nf_flowtable *ft); nf_hookfn *hook; struct module *owner; }; +enum nf_flowtable_flags { + NF_FLOWTABLE_HW_OFFLOAD = 0x1, +}; + struct nf_flowtable { struct list_head list; struct rhashtable rhashtable; + int priority; const struct nf_flowtable_type *type; struct delayed_work gc_work; + unsigned int flags; + struct flow_block flow_block; + possible_net_t net; }; enum flow_offload_tuple_dir { @@ -68,17 +87,31 @@ struct flow_offload_tuple_rhash { #define FLOW_OFFLOAD_DNAT 0x2 #define FLOW_OFFLOAD_DYING 0x4 #define FLOW_OFFLOAD_TEARDOWN 0x8 +#define FLOW_OFFLOAD_HW 0x10 +#define FLOW_OFFLOAD_HW_DYING 0x20 +#define FLOW_OFFLOAD_HW_DEAD 0x40 + +enum flow_offload_type { + NF_FLOW_OFFLOAD_UNSPEC = 0, + NF_FLOW_OFFLOAD_ROUTE, +}; struct flow_offload { struct flow_offload_tuple_rhash tuplehash[FLOW_OFFLOAD_DIR_MAX]; - u32 flags; - union { - /* Your private driver data here. */ - u32 timeout; - }; + struct nf_conn *ct; + u16 flags; + u16 type; + u32 timeout; + struct rcu_head rcu_head; }; #define NF_FLOW_TIMEOUT (30 * HZ) +#define nf_flowtable_time_stamp (u32)jiffies + +static inline __s32 nf_flow_timeout_delta(unsigned int timeout) +{ + return (__s32)(timeout - nf_flowtable_time_stamp); +} struct nf_flow_route { struct { @@ -86,10 +119,12 @@ struct nf_flow_route { } tuple[FLOW_OFFLOAD_DIR_MAX]; }; -struct flow_offload *flow_offload_alloc(struct nf_conn *ct, - struct nf_flow_route *route); +struct flow_offload *flow_offload_alloc(struct nf_conn *ct); void flow_offload_free(struct flow_offload *flow); +int flow_offload_route_init(struct flow_offload *flow, + const struct nf_flow_route *route); + int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow); struct flow_offload_tuple_rhash *flow_offload_lookup(struct nf_flowtable *flow_table, struct flow_offload_tuple *tuple); @@ -123,4 +158,25 @@ unsigned int nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, #define MODULE_ALIAS_NF_FLOWTABLE(family) \ MODULE_ALIAS("nf-flowtable-" __stringify(family)) +void nf_flow_offload_add(struct nf_flowtable *flowtable, + struct flow_offload *flow); +void nf_flow_offload_del(struct nf_flowtable *flowtable, + struct flow_offload *flow); +void nf_flow_offload_stats(struct nf_flowtable *flowtable, + struct flow_offload *flow); + +void nf_flow_table_offload_flush(struct nf_flowtable *flowtable); +int nf_flow_table_offload_setup(struct nf_flowtable *flowtable, + struct net_device *dev, + enum flow_block_command cmd); +int nf_flow_rule_route_ipv4(struct net *net, const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct nf_flow_rule *flow_rule); +int nf_flow_rule_route_ipv6(struct net *net, const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct nf_flow_rule *flow_rule); + +int nf_flow_table_offload_init(void); +void nf_flow_table_offload_exit(void); + #endif /* _NF_FLOW_TABLE_H */ diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 2d0275f13bbf..fe7c50acc681 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -114,7 +114,7 @@ static inline void nft_reg_store8(u32 *dreg, u8 val) *(u8 *)dreg = val; } -static inline u8 nft_reg_load8(u32 *sreg) +static inline u8 nft_reg_load8(const u32 *sreg) { return *(u8 *)sreg; } @@ -125,7 +125,7 @@ static inline void nft_reg_store16(u32 *dreg, u16 val) *(u16 *)dreg = val; } -static inline u16 nft_reg_load16(u32 *sreg) +static inline u16 nft_reg_load16(const u32 *sreg) { return *(u16 *)sreg; } @@ -135,7 +135,7 @@ static inline void nft_reg_store64(u32 *dreg, u64 val) put_unaligned(val, (u64 *)dreg); } -static inline u64 nft_reg_load64(u32 *sreg) +static inline u64 nft_reg_load64(const u32 *sreg) { return get_unaligned((u64 *)sreg); } @@ -964,25 +964,31 @@ struct nft_stats { struct u64_stats_sync syncp; }; +struct nft_hook { + struct list_head list; + struct nf_hook_ops ops; + struct rcu_head rcu; +}; + /** * struct nft_base_chain - nf_tables base chain * * @ops: netfilter hook ops + * @hook_list: list of netfilter hooks (for NFPROTO_NETDEV family) * @type: chain type * @policy: default policy * @stats: per-cpu chain stats * @chain: the chain - * @dev_name: device name that this base chain is attached to (if any) * @flow_block: flow block (for hardware offload) */ struct nft_base_chain { struct nf_hook_ops ops; + struct list_head hook_list; const struct nft_chain_type *type; u8 policy; u8 flags; struct nft_stats __percpu *stats; struct nft_chain chain; - char dev_name[IFNAMSIZ]; struct flow_block flow_block; }; @@ -1147,7 +1153,7 @@ struct nft_object_ops { int nft_register_obj(struct nft_object_type *obj_type); void nft_unregister_obj(struct nft_object_type *obj_type); -#define NFT_FLOWTABLE_DEVICE_MAX 8 +#define NFT_NETDEVICE_MAX 256 /** * struct nft_flowtable - nf_tables flow table @@ -1156,7 +1162,6 @@ void nft_unregister_obj(struct nft_object_type *obj_type); * @table: the table the flow table is contained in * @name: name of this flow table * @hooknum: hook number - * @priority: hook priority * @ops_len: number of hooks in array * @genmask: generation mask * @use: number of references to this flow table @@ -1170,13 +1175,12 @@ struct nft_flowtable { struct nft_table *table; char *name; int hooknum; - int priority; int ops_len; u32 genmask:2, use:30; u64 handle; /* runtime data below here */ - struct nf_hook_ops *ops ____cacheline_aligned; + struct list_head hook_list ____cacheline_aligned; struct nf_flowtable data; }; diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index 7281895fa6d9..2656155b4069 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -41,7 +41,7 @@ struct nft_immediate_expr { */ static inline u32 nft_cmp_fast_mask(unsigned int len) { - return cpu_to_le32(~0U >> (FIELD_SIZEOF(struct nft_cmp_fast_expr, + return cpu_to_le32(~0U >> (sizeof_field(struct nft_cmp_fast_expr, data) * BITS_PER_BYTE - len)); } diff --git a/include/net/netfilter/nf_tables_offload.h b/include/net/netfilter/nf_tables_offload.h index 03cf5856d76f..ea7d1d78b92d 100644 --- a/include/net/netfilter/nf_tables_offload.h +++ b/include/net/netfilter/nf_tables_offload.h @@ -45,6 +45,7 @@ struct nft_flow_key { struct flow_dissector_key_ip ip; struct flow_dissector_key_vlan vlan; struct flow_dissector_key_eth_addrs eth_addrs; + struct flow_dissector_key_meta meta; } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ struct nft_flow_match { diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 022a0fd1a5a4..5ec054473d81 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -83,6 +83,9 @@ struct netns_ipv6 { #ifdef CONFIG_IPV6_MULTIPLE_TABLES unsigned int fib6_rules_require_fldissect; bool fib6_has_custom_rules; +#ifdef CONFIG_IPV6_SUBTREES + unsigned int fib6_routes_require_src; +#endif struct rt6_info *ip6_prohibit_entry; struct rt6_info *ip6_blk_hole_entry; struct fib6_table *fib6_local_tbl; diff --git a/include/net/netns/mib.h b/include/net/netns/mib.h index 830bdf345b17..b5fdb108d602 100644 --- a/include/net/netns/mib.h +++ b/include/net/netns/mib.h @@ -24,6 +24,9 @@ struct netns_mib { #ifdef CONFIG_XFRM_STATISTICS DEFINE_SNMP_STAT(struct linux_xfrm_mib, xfrm_statistics); #endif +#if IS_ENABLED(CONFIG_TLS) + DEFINE_SNMP_STAT(struct linux_tls_mib, tls_statistics); +#endif }; #endif diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h index bdc0f27b8514..d8d02e4188d1 100644 --- a/include/net/netns/sctp.h +++ b/include/net/netns/sctp.h @@ -89,6 +89,12 @@ struct netns_sctp { */ int pf_retrans; + /* Primary.Switchover.Max.Retrans sysctl value + * taken from: + * https://tools.ietf.org/html/rfc7829 + */ + int ps_retrans; + /* * Disable Potentially-Failed feature, the feature is enabled by default * pf_enable - 0 : disable pf @@ -97,6 +103,14 @@ struct netns_sctp { int pf_enable; /* + * Disable Potentially-Failed state exposure, ignored by default + * pf_expose - 0 : compatible with old applications (by default) + * - 1 : disable pf state exposure + * - 2 : enable pf state exposure + */ + int pf_expose; + + /* * Policy for preforming sctp/socket accounting * 0 - do socket level accounting, all assocs share sk_sndbuf * 1 - do sctp accounting, each asoc may use sk_sndbuf bytes diff --git a/include/net/netprio_cgroup.h b/include/net/netprio_cgroup.h index cfc9441ef074..dec7522b6ce1 100644 --- a/include/net/netprio_cgroup.h +++ b/include/net/netprio_cgroup.h @@ -26,7 +26,7 @@ static inline u32 task_netprioidx(struct task_struct *p) rcu_read_lock(); css = task_css(p, net_prio_cgrp_id); - idx = css->cgroup->id; + idx = css->id; rcu_read_unlock(); return idx; } diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 2cbcdbdec254..cfbed00ba7ee 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -34,8 +34,18 @@ #include <linux/ptr_ring.h> #include <linux/dma-direction.h> -#define PP_FLAG_DMA_MAP 1 /* Should page_pool do the DMA map/unmap */ -#define PP_FLAG_ALL PP_FLAG_DMA_MAP +#define PP_FLAG_DMA_MAP BIT(0) /* Should page_pool do the DMA + * map/unmap + */ +#define PP_FLAG_DMA_SYNC_DEV BIT(1) /* If set all pages that the driver gets + * from page_pool will be + * DMA-synced-for-device according to + * the length provided by the device + * driver. + * Please note DMA-sync-for-CPU is still + * device driver responsibility + */ +#define PP_FLAG_ALL (PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV) /* * Fast allocation side cache array/stack @@ -65,12 +75,19 @@ struct page_pool_params { int nid; /* Numa node id to allocate from pages from */ struct device *dev; /* device, for DMA pre-mapping purposes */ enum dma_data_direction dma_dir; /* DMA mapping direction */ + unsigned int max_len; /* max DMA sync memory size */ + unsigned int offset; /* DMA addr offset */ }; struct page_pool { struct page_pool_params p; - u32 pages_state_hold_cnt; + struct delayed_work release_dw; + void (*disconnect)(void *); + unsigned long defer_start; + unsigned long defer_warn; + + u32 pages_state_hold_cnt; /* * Data structure for allocation side @@ -107,6 +124,8 @@ struct page_pool { * refcnt serves purpose is to simplify drivers error handling. */ refcount_t user_cnt; + + u64 destroy_cnt; }; struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp); @@ -129,29 +148,23 @@ inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool) struct page_pool *page_pool_create(const struct page_pool_params *params); -void __page_pool_free(struct page_pool *pool); -static inline void page_pool_free(struct page_pool *pool) -{ - /* When page_pool isn't compiled-in, net/core/xdp.c doesn't - * allow registering MEM_TYPE_PAGE_POOL, but shield linker. - */ #ifdef CONFIG_PAGE_POOL - __page_pool_free(pool); -#endif -} - -/* Drivers use this instead of page_pool_free */ +void page_pool_destroy(struct page_pool *pool); +void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *)); +#else static inline void page_pool_destroy(struct page_pool *pool) { - if (!pool) - return; +} - page_pool_free(pool); +static inline void page_pool_use_xdp_mem(struct page_pool *pool, + void (*disconnect)(void *)) +{ } +#endif /* Never call this directly, use helpers below */ -void __page_pool_put_page(struct page_pool *pool, - struct page *page, bool allow_direct); +void __page_pool_put_page(struct page_pool *pool, struct page *page, + unsigned int dma_sync_size, bool allow_direct); static inline void page_pool_put_page(struct page_pool *pool, struct page *page, bool allow_direct) @@ -160,32 +173,14 @@ static inline void page_pool_put_page(struct page_pool *pool, * allow registering MEM_TYPE_PAGE_POOL, but shield linker. */ #ifdef CONFIG_PAGE_POOL - __page_pool_put_page(pool, page, allow_direct); + __page_pool_put_page(pool, page, -1, allow_direct); #endif } /* Very limited use-cases allow recycle direct */ static inline void page_pool_recycle_direct(struct page_pool *pool, struct page *page) { - __page_pool_put_page(pool, page, true); -} - -/* API user MUST have disconnected alloc-side (not allowed to call - * page_pool_alloc_pages()) before calling this. The free-side can - * still run concurrently, to handle in-flight packet-pages. - * - * A request to shutdown can fail (with false) if there are still - * in-flight packet-pages. - */ -bool __page_pool_request_shutdown(struct page_pool *pool); -static inline bool page_pool_request_shutdown(struct page_pool *pool) -{ - bool safe_to_remove = false; - -#ifdef CONFIG_PAGE_POOL - safe_to_remove = __page_pool_request_shutdown(pool); -#endif - return safe_to_remove; + __page_pool_put_page(pool, page, -1, true); } /* Disconnects a page (from a page_pool). API users can have a need @@ -216,14 +211,16 @@ static inline bool is_page_pool_compiled_in(void) #endif } -static inline void page_pool_get(struct page_pool *pool) -{ - refcount_inc(&pool->user_cnt); -} - static inline bool page_pool_put(struct page_pool *pool) { return refcount_dec_and_test(&pool->user_cnt); } +/* Caller must provide appropriate safe context, e.g. NAPI. */ +void page_pool_update_nid(struct page_pool *pool, int new_nid); +static inline void page_pool_nid_changed(struct page_pool *pool, int new_nid) +{ + if (unlikely(pool->p.nid != new_nid)) + page_pool_update_nid(pool, new_nid); +} #endif /* _NET_PAGE_POOL_H */ diff --git a/include/net/route.h b/include/net/route.h index 6c516840380d..a9c60fc68e36 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -185,6 +185,10 @@ int ip_route_input_rcu(struct sk_buff *skb, __be32 dst, __be32 src, u8 tos, struct net_device *devin, struct fib_result *res); +int ip_route_use_hint(struct sk_buff *skb, __be32 dst, __be32 src, + u8 tos, struct net_device *devin, + const struct sk_buff *hint); + static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src, u8 tos, struct net_device *devin) { diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index d80acda231ae..fceddf89592a 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -149,8 +149,8 @@ static inline bool qdisc_is_percpu_stats(const struct Qdisc *q) static inline bool qdisc_is_empty(const struct Qdisc *qdisc) { if (qdisc_is_percpu_stats(qdisc)) - return qdisc->empty; - return !qdisc->q.qlen; + return READ_ONCE(qdisc->empty); + return !READ_ONCE(qdisc->q.qlen); } static inline bool qdisc_run_begin(struct Qdisc *qdisc) @@ -158,7 +158,7 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc) if (qdisc->flags & TCQ_F_NOLOCK) { if (!spin_trylock(&qdisc->seqlock)) return false; - qdisc->empty = false; + WRITE_ONCE(qdisc->empty, false); } else if (qdisc_is_running(qdisc)) { return false; } @@ -308,6 +308,7 @@ struct tcf_proto_ops { int (*delete)(struct tcf_proto *tp, void *arg, bool *last, bool rtnl_held, struct netlink_ext_ack *); + bool (*delete_empty)(struct tcf_proto *tp); void (*walk)(struct tcf_proto *tp, struct tcf_walker *arg, bool rtnl_held); int (*reoffload)(struct tcf_proto *tp, bool add, @@ -336,6 +337,10 @@ struct tcf_proto_ops { int flags; }; +/* Classifiers setting TCF_PROTO_OPS_DOIT_UNLOCKED in tcf_proto_ops->flags + * are expected to implement tcf_proto_ops->delete_empty(), otherwise race + * conditions can occur when filters are inserted/deleted simultaneously. + */ enum tcf_proto_ops_flags { TCF_PROTO_OPS_DOIT_UNLOCKED = 1, }; @@ -1290,17 +1295,9 @@ void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp, void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc, struct mini_Qdisc __rcu **p_miniq); -static inline void skb_tc_reinsert(struct sk_buff *skb, struct tcf_result *res) +static inline int skb_tc_reinsert(struct sk_buff *skb, struct tcf_result *res) { - struct gnet_stats_queue *stats = res->qstats; - int ret; - - if (res->ingress) - ret = netif_receive_skb(skb); - else - ret = dev_queue_xmit(skb); - if (ret && stats) - qstats_overlimit_inc(res->qstats); + return res->ingress ? netif_receive_skb(skb) : dev_queue_xmit(skb); } #endif diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index 823afc42a3aa..15b4d9aec7ff 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -286,6 +286,18 @@ enum { SCTP_MAX_GABS = 16 }; * functions simpler to write. */ +/* These are the values for pf exposure, UNUSED is to keep compatible with old + * applications by default. + */ +enum { + SCTP_PF_EXPOSE_UNSET, + SCTP_PF_EXPOSE_DISABLE, + SCTP_PF_EXPOSE_ENABLE, +}; +#define SCTP_PF_EXPOSE_MAX SCTP_PF_EXPOSE_ENABLE + +#define SCTP_PS_RETRANS_MAX 0xffff + /* These return values describe the success or failure of a number of * routines which form the lower interface to SCTP_outqueue. */ diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 503fbc3cd819..314a2fa21d6b 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -184,7 +184,8 @@ struct sctp_sock { __u32 flowlabel; __u8 dscp; - int pf_retrans; + __u16 pf_retrans; + __u16 ps_retrans; /* The initial Path MTU to use for new associations. */ __u32 pathmtu; @@ -215,6 +216,7 @@ struct sctp_sock { __u32 adaptation_ind; __u32 pd_point; __u16 nodelay:1, + pf_expose:2, reuse:1, disable_fragments:1, v4mapped:1, @@ -896,7 +898,9 @@ struct sctp_transport { * and will be initialized from the assocs value. This can be changed * using the SCTP_PEER_ADDR_THLDS socket option */ - int pf_retrans; + __u16 pf_retrans; + /* Used for primary path switchover. */ + __u16 ps_retrans; /* PMTU : The current known path MTU. */ __u32 pathmtu; @@ -1239,6 +1243,9 @@ struct sctp_ep_common { /* What socket does this endpoint belong to? */ struct sock *sk; + /* Cache netns and it won't change once set */ + struct net *net; + /* This is where we receive inbound chunks. */ struct sctp_inq inqueue; @@ -1772,7 +1779,9 @@ struct sctp_association { * and will be initialized from the assocs value. This can be * changed using the SCTP_PEER_ADDR_THLDS socket option */ - int pf_retrans; + __u16 pf_retrans; + /* Used for primary path switchover. */ + __u16 ps_retrans; /* Maximum number of times the endpoint will retransmit INIT */ __u16 max_init_attempts; @@ -2053,6 +2062,7 @@ struct sctp_association { __u8 need_ecne:1, /* Need to send an ECNE Chunk? */ temp:1, /* Is it a temporary association? */ + pf_expose:2, /* Expose pf state? */ force_delay:1; __u8 strreset_enable; diff --git a/include/net/sctp/ulpevent.h b/include/net/sctp/ulpevent.h index e1a92c4610f3..0b032b92da0b 100644 --- a/include/net/sctp/ulpevent.h +++ b/include/net/sctp/ulpevent.h @@ -80,13 +80,8 @@ struct sctp_ulpevent *sctp_ulpevent_make_assoc_change( struct sctp_chunk *chunk, gfp_t gfp); -struct sctp_ulpevent *sctp_ulpevent_make_peer_addr_change( - const struct sctp_association *asoc, - const struct sockaddr_storage *aaddr, - int flags, - int state, - int error, - gfp_t gfp); +void sctp_ulpevent_nofity_peer_addr_change(struct sctp_transport *transport, + int state, int error); struct sctp_ulpevent *sctp_ulpevent_make_remote_error( const struct sctp_association *asoc, @@ -100,6 +95,13 @@ struct sctp_ulpevent *sctp_ulpevent_make_send_failed( __u32 error, gfp_t gfp); +struct sctp_ulpevent *sctp_ulpevent_make_send_failed_event( + const struct sctp_association *asoc, + struct sctp_chunk *chunk, + __u16 flags, + __u32 error, + gfp_t gfp); + struct sctp_ulpevent *sctp_ulpevent_make_shutdown_event( const struct sctp_association *asoc, __u16 flags, diff --git a/include/net/smc.h b/include/net/smc.h index bd9c0fb3b577..646feb4bc75f 100644 --- a/include/net/smc.h +++ b/include/net/smc.h @@ -37,6 +37,8 @@ struct smcd_dmb { #define ISM_EVENT_GID 1 #define ISM_EVENT_SWR 2 +#define ISM_ERROR 0xFFFF + struct smcd_event { u32 type; u32 code; @@ -75,6 +77,11 @@ struct smcd_dev { struct workqueue_struct *event_wq; u8 pnetid[SMC_MAX_PNETID_LEN]; bool pnetid_by_user; + struct list_head lgr_list; + spinlock_t lgr_lock; + atomic_t lgr_cnt; + wait_queue_head_t lgrs_deleted; + u8 going_away : 1; }; struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name, diff --git a/include/net/snmp.h b/include/net/snmp.h index cb8ced4380a6..468a67836e2f 100644 --- a/include/net/snmp.h +++ b/include/net/snmp.h @@ -111,6 +111,12 @@ struct linux_xfrm_mib { unsigned long mibs[LINUX_MIB_XFRMMAX]; }; +/* Linux TLS */ +#define LINUX_MIB_TLSMAX __LINUX_MIB_TLSMAX +struct linux_tls_mib { + unsigned long mibs[LINUX_MIB_TLSMAX]; +}; + #define DEFINE_SNMP_STAT(type, name) \ __typeof__(type) __percpu *name #define DEFINE_SNMP_STAT_ATOMIC(type, name) \ diff --git a/include/net/sock.h b/include/net/sock.h index 718e62fbe869..8dff68b4c316 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -66,7 +66,6 @@ #include <net/checksum.h> #include <net/tcp_states.h> #include <linux/net_tstamp.h> -#include <net/smc.h> #include <net/l3mdev.h> /* @@ -723,6 +722,11 @@ static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_h hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list); } +static inline void __sk_nulls_add_node_tail_rcu(struct sock *sk, struct hlist_nulls_head *list) +{ + hlist_nulls_add_tail_rcu(&sk->sk_nulls_node, list); +} + static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) { sock_hold(sk); @@ -860,17 +864,17 @@ static inline gfp_t sk_gfp_mask(const struct sock *sk, gfp_t gfp_mask) static inline void sk_acceptq_removed(struct sock *sk) { - sk->sk_ack_backlog--; + WRITE_ONCE(sk->sk_ack_backlog, sk->sk_ack_backlog - 1); } static inline void sk_acceptq_added(struct sock *sk) { - sk->sk_ack_backlog++; + WRITE_ONCE(sk->sk_ack_backlog, sk->sk_ack_backlog + 1); } static inline bool sk_acceptq_is_full(const struct sock *sk) { - return sk->sk_ack_backlog > sk->sk_max_ack_backlog; + return READ_ONCE(sk->sk_ack_backlog) > READ_ONCE(sk->sk_max_ack_backlog); } /* @@ -900,11 +904,11 @@ static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb) skb_dst_force(skb); if (!sk->sk_backlog.tail) - sk->sk_backlog.head = skb; + WRITE_ONCE(sk->sk_backlog.head, skb); else sk->sk_backlog.tail->next = skb; - sk->sk_backlog.tail = skb; + WRITE_ONCE(sk->sk_backlog.tail, skb); skb->next = NULL; } @@ -1489,7 +1493,7 @@ static inline void sock_release_ownership(struct sock *sk) sk->sk_lock.owned = 0; /* The sk_lock has mutex_unlock() semantics: */ - mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_); + mutex_release(&sk->sk_lock.dep_map, _RET_IP_); } } @@ -1940,8 +1944,8 @@ struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie); static inline void sk_dst_confirm(struct sock *sk) { - if (!sk->sk_dst_pending_confirm) - sk->sk_dst_pending_confirm = 1; + if (!READ_ONCE(sk->sk_dst_pending_confirm)) + WRITE_ONCE(sk->sk_dst_pending_confirm, 1); } static inline void sock_confirm_neigh(struct sk_buff *skb, struct neighbour *n) @@ -1951,10 +1955,10 @@ static inline void sock_confirm_neigh(struct sk_buff *skb, struct neighbour *n) unsigned long now = jiffies; /* avoid dirtying neighbour */ - if (n->confirmed != now) - n->confirmed = now; - if (sk && sk->sk_dst_pending_confirm) - sk->sk_dst_pending_confirm = 0; + if (READ_ONCE(n->confirmed) != now) + WRITE_ONCE(n->confirmed, now); + if (sk && READ_ONCE(sk->sk_dst_pending_confirm)) + WRITE_ONCE(sk->sk_dst_pending_confirm, 0); } } @@ -2306,7 +2310,7 @@ struct sock_skb_cb { * using skb->cb[] would keep using it directly and utilize its * alignement guarantee. */ -#define SOCK_SKB_CB_OFFSET ((FIELD_SIZEOF(struct sk_buff, cb) - \ +#define SOCK_SKB_CB_OFFSET ((sizeof_field(struct sk_buff, cb) - \ sizeof(struct sock_skb_cb))) #define SOCK_SKB_CB(__skb) ((struct sock_skb_cb *)((__skb)->cb + \ @@ -2528,7 +2532,7 @@ static inline bool sk_listener(const struct sock *sk) return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV); } -void sock_enable_timestamp(struct sock *sk, int flag); +void sock_enable_timestamp(struct sock *sk, enum sock_flags flag); int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level, int type); @@ -2584,9 +2588,9 @@ static inline int sk_get_rmem0(const struct sock *sk, const struct proto *proto) */ static inline void sk_pacing_shift_update(struct sock *sk, int val) { - if (!sk || !sk_fullsock(sk) || sk->sk_pacing_shift == val) + if (!sk || !sk_fullsock(sk) || READ_ONCE(sk->sk_pacing_shift) == val) return; - sk->sk_pacing_shift = val; + WRITE_ONCE(sk->sk_pacing_shift, val); } /* if a socket is bound to a device, check that the given device diff --git a/include/net/tcp.h b/include/net/tcp.h index ab4eb5eb5d07..e460ea7f767b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -494,15 +494,16 @@ static inline void tcp_synq_overflow(const struct sock *sk) reuse = rcu_dereference(sk->sk_reuseport_cb); if (likely(reuse)) { last_overflow = READ_ONCE(reuse->synq_overflow_ts); - if (time_after32(now, last_overflow + HZ)) + if (!time_between32(now, last_overflow, + last_overflow + HZ)) WRITE_ONCE(reuse->synq_overflow_ts, now); return; } } - last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; - if (time_after32(now, last_overflow + HZ)) - tcp_sk(sk)->rx_opt.ts_recent_stamp = now; + last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp); + if (!time_between32(now, last_overflow, last_overflow + HZ)) + WRITE_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp, now); } /* syncookies: no recent synqueue overflow on this listening socket? */ @@ -517,13 +518,23 @@ static inline bool tcp_synq_no_recent_overflow(const struct sock *sk) reuse = rcu_dereference(sk->sk_reuseport_cb); if (likely(reuse)) { last_overflow = READ_ONCE(reuse->synq_overflow_ts); - return time_after32(now, last_overflow + - TCP_SYNCOOKIE_VALID); + return !time_between32(now, last_overflow - HZ, + last_overflow + + TCP_SYNCOOKIE_VALID); } } - last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; - return time_after32(now, last_overflow + TCP_SYNCOOKIE_VALID); + last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp); + + /* If last_overflow <= jiffies <= last_overflow + TCP_SYNCOOKIE_VALID, + * then we're under synflood. However, we have to use + * 'last_overflow - HZ' as lower bound. That's because a concurrent + * tcp_synq_overflow() could update .ts_recent_stamp after we read + * jiffies but before we store .ts_recent_stamp into last_overflow, + * which could lead to rejecting a valid syncookie. + */ + return !time_between32(now, last_overflow - HZ, + last_overflow + TCP_SYNCOOKIE_VALID); } static inline u32 tcp_cookie_time(void) @@ -537,7 +548,7 @@ static inline u32 tcp_cookie_time(void) u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th, u16 *mssp); __u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mss); -u64 cookie_init_timestamp(struct request_sock *req); +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, @@ -757,10 +768,16 @@ static inline u32 tcp_time_stamp(const struct tcp_sock *tp) return div_u64(tp->tcp_mstamp, USEC_PER_SEC / TCP_TS_HZ); } +/* Convert a nsec timestamp into TCP TSval timestamp (ms based currently) */ +static inline u32 tcp_ns_to_ts(u64 ns) +{ + return div_u64(ns, NSEC_PER_SEC / TCP_TS_HZ); +} + /* Could use tcp_clock_us() / 1000, but this version uses a single divide */ static inline u32 tcp_time_stamp_raw(void) { - return div_u64(tcp_clock_ns(), NSEC_PER_SEC / TCP_TS_HZ); + return tcp_ns_to_ts(tcp_clock_ns()); } void tcp_mstamp_refresh(struct tcp_sock *tp); @@ -772,7 +789,7 @@ static inline u32 tcp_stamp_us_delta(u64 t1, u64 t0) static inline u32 tcp_skb_timestamp(const struct sk_buff *skb) { - return div_u64(skb->skb_mstamp_ns, NSEC_PER_SEC / TCP_TS_HZ); + return tcp_ns_to_ts(skb->skb_mstamp_ns); } /* provide the departure time in us unit */ @@ -1749,9 +1766,18 @@ static inline bool tcp_skb_is_last(const struct sock *sk, return skb_queue_is_last(&sk->sk_write_queue, skb); } +/** + * tcp_write_queue_empty - test if any payload (or FIN) is available in write queue + * @sk: socket + * + * Since the write queue can have a temporary empty skb in it, + * we must not use "return skb_queue_empty(&sk->sk_write_queue)" + */ static inline bool tcp_write_queue_empty(const struct sock *sk) { - return skb_queue_empty(&sk->sk_write_queue); + const struct tcp_sock *tp = tcp_sk(sk); + + return tp->write_seq == tp->snd_nxt; } static inline bool tcp_rtx_queue_empty(const struct sock *sk) diff --git a/include/net/tls.h b/include/net/tls.h index f4ad831eaa02..df630f5fc723 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -44,6 +44,7 @@ #include <linux/netdevice.h> #include <linux/rcupdate.h> +#include <net/net_namespace.h> #include <net/tcp.h> #include <net/strparser.h> #include <crypto/aead.h> @@ -61,7 +62,6 @@ #define TLS_RECORD_TYPE_DATA 0x17 #define TLS_AAD_SPACE_SIZE 13 -#define TLS_DEVICE_NAME_MAX 32 #define MAX_IV_SIZE 16 #define TLS_MAX_REC_SEQ_SIZE 8 @@ -75,36 +75,14 @@ */ #define TLS_AES_CCM_IV_B0_BYTE 2 -/* - * This structure defines the routines for Inline TLS driver. - * The following routines are optional and filled with a - * null pointer if not defined. - * - * @name: Its the name of registered Inline tls device - * @dev_list: Inline tls device list - * int (*feature)(struct tls_device *device); - * Called to return Inline TLS driver capability - * - * int (*hash)(struct tls_device *device, struct sock *sk); - * This function sets Inline driver for listen and program - * device specific functioanlity as required - * - * void (*unhash)(struct tls_device *device, struct sock *sk); - * This function cleans listen state set by Inline TLS driver - * - * void (*release)(struct kref *kref); - * Release the registered device and allocated resources - * @kref: Number of reference to tls_device - */ -struct tls_device { - char name[TLS_DEVICE_NAME_MAX]; - struct list_head dev_list; - int (*feature)(struct tls_device *device); - int (*hash)(struct tls_device *device, struct sock *sk); - void (*unhash)(struct tls_device *device, struct sock *sk); - void (*release)(struct kref *kref); - struct kref kref; -}; +#define __TLS_INC_STATS(net, field) \ + __SNMP_INC_STATS((net)->mib.tls_statistics, field) +#define TLS_INC_STATS(net, field) \ + SNMP_INC_STATS((net)->mib.tls_statistics, field) +#define __TLS_DEC_STATS(net, field) \ + __SNMP_DEC_STATS((net)->mib.tls_statistics, field) +#define TLS_DEC_STATS(net, field) \ + SNMP_DEC_STATS((net)->mib.tls_statistics, field) enum { TLS_BASE, @@ -122,7 +100,6 @@ struct tls_rec { struct list_head list; int tx_ready; int tx_flags; - int inplace_crypto; struct sk_msg msg_plaintext; struct sk_msg msg_encrypted; @@ -159,7 +136,7 @@ struct tls_sw_context_tx { struct list_head tx_list; atomic_t encrypt_pending; int async_notify; - int async_capable; + u8 async_capable:1; #define BIT_TX_SCHEDULED 0 #define BIT_TX_CLOSING 1 @@ -175,8 +152,8 @@ struct tls_sw_context_rx { struct sk_buff *recv_pkt; u8 control; - int async_capable; - bool decrypted; + u8 async_capable:1; + u8 decrypted:1; atomic_t decrypt_pending; bool async_notify; }; @@ -345,7 +322,10 @@ struct tls_offload_context_rx { #define TLS_OFFLOAD_CONTEXT_SIZE_RX \ (sizeof(struct tls_offload_context_rx) + TLS_DRIVER_STATE_SIZE_RX) +struct tls_context *tls_ctx_create(struct sock *sk); void tls_ctx_free(struct sock *sk, struct tls_context *ctx); +void update_sk_prot(struct sock *sk, struct tls_context *ctx); + int wait_on_pending_writer(struct sock *sk, long *timeo); int tls_sk_query(struct sock *sk, int optname, char __user *optval, int __user *optlen); @@ -396,7 +376,7 @@ int tls_push_sg(struct sock *sk, struct tls_context *ctx, int flags); int tls_push_partial_record(struct sock *sk, struct tls_context *ctx, int flags); -bool tls_free_partial_record(struct sock *sk, struct tls_context *ctx); +void tls_free_partial_record(struct sock *sk, struct tls_context *ctx); static inline struct tls_msg *tls_msg(struct sk_buff *skb) { @@ -630,13 +610,6 @@ tls_offload_rx_resync_set_type(struct sock *sk, enum tls_offload_sync_type type) tls_offload_ctx_rx(tls_ctx)->resync_type = type; } -static inline void tls_offload_tx_resync_request(struct sock *sk) -{ - struct tls_context *tls_ctx = tls_get_ctx(sk); - - WARN_ON(test_and_set_bit(TLS_TX_SYNC_SCHED, &tls_ctx->flags)); -} - /* Driver's seq tracking has to be disabled until resync succeeded */ static inline bool tls_offload_tx_resync_pending(struct sock *sk) { @@ -648,10 +621,11 @@ static inline bool tls_offload_tx_resync_pending(struct sock *sk) return ret; } +int __net_init tls_proc_init(struct net *net); +void __net_exit tls_proc_fini(struct net *net); + int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg, unsigned char *record_type); -void tls_register_device(struct tls_device *device); -void tls_unregister_device(struct tls_device *device); int decrypt_skb(struct sock *sk, struct sk_buff *skb, struct scatterlist *sgout); struct sk_buff *tls_encrypt_skb(struct sk_buff *skb); @@ -672,7 +646,9 @@ void tls_device_free_resources_tx(struct sock *sk); int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx); void tls_device_offload_cleanup_rx(struct sock *sk); void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq); -int tls_device_decrypted(struct sock *sk, struct sk_buff *skb); +void tls_offload_tx_resync_request(struct sock *sk, u32 got_seq, u32 exp_seq); +int tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx, + struct sk_buff *skb, struct strp_msg *rxm); #else static inline void tls_device_init(void) {} static inline void tls_device_cleanup(void) {} @@ -695,7 +671,9 @@ static inline void tls_device_offload_cleanup_rx(struct sock *sk) {} static inline void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq) {} -static inline int tls_device_decrypted(struct sock *sk, struct sk_buff *skb) +static inline int +tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx, + struct sk_buff *skb, struct strp_msg *rxm) { return 0; } diff --git a/include/net/tls_toe.h b/include/net/tls_toe.h new file mode 100644 index 000000000000..b3aa7593ce2c --- /dev/null +++ b/include/net/tls_toe.h @@ -0,0 +1,77 @@ +/* + * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved. + * Copyright (c) 2016-2017, Dave Watson <davejwatson@fb.com>. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/kref.h> +#include <linux/list.h> + +struct sock; + +#define TLS_TOE_DEVICE_NAME_MAX 32 + +/* + * This structure defines the routines for Inline TLS driver. + * The following routines are optional and filled with a + * null pointer if not defined. + * + * @name: Its the name of registered Inline tls device + * @dev_list: Inline tls device list + * int (*feature)(struct tls_toe_device *device); + * Called to return Inline TLS driver capability + * + * int (*hash)(struct tls_toe_device *device, struct sock *sk); + * This function sets Inline driver for listen and program + * device specific functioanlity as required + * + * void (*unhash)(struct tls_toe_device *device, struct sock *sk); + * This function cleans listen state set by Inline TLS driver + * + * void (*release)(struct kref *kref); + * Release the registered device and allocated resources + * @kref: Number of reference to tls_toe_device + */ +struct tls_toe_device { + char name[TLS_TOE_DEVICE_NAME_MAX]; + struct list_head dev_list; + int (*feature)(struct tls_toe_device *device); + int (*hash)(struct tls_toe_device *device, struct sock *sk); + void (*unhash)(struct tls_toe_device *device, struct sock *sk); + void (*release)(struct kref *kref); + struct kref kref; +}; + +int tls_toe_bypass(struct sock *sk); +int tls_toe_hash(struct sock *sk); +void tls_toe_unhash(struct sock *sk); + +void tls_toe_register_device(struct tls_toe_device *device); +void tls_toe_unregister_device(struct tls_toe_device *device); diff --git a/include/net/vsock_addr.h b/include/net/vsock_addr.h index 57d2db5c4bdf..cf8cc140d68d 100644 --- a/include/net/vsock_addr.h +++ b/include/net/vsock_addr.h @@ -8,7 +8,7 @@ #ifndef _VSOCK_ADDR_H_ #define _VSOCK_ADDR_H_ -#include <linux/vm_sockets.h> +#include <uapi/linux/vm_sockets.h> void vsock_addr_init(struct sockaddr_vm *addr, u32 cid, u32 port); int vsock_addr_validate(const struct sockaddr_vm *addr); diff --git a/include/net/x25.h b/include/net/x25.h index ed1acc3044ac..d7d6c2b4ffa7 100644 --- a/include/net/x25.h +++ b/include/net/x25.h @@ -62,7 +62,8 @@ enum { X25_STATE_1, /* Awaiting Call Accepted */ X25_STATE_2, /* Awaiting Clear Confirmation */ X25_STATE_3, /* Data Transfer */ - X25_STATE_4 /* Awaiting Reset Confirmation */ + X25_STATE_4, /* Awaiting Reset Confirmation */ + X25_STATE_5 /* Call Accepted / Call Connected pending */ }; enum { diff --git a/include/net/xdp_priv.h b/include/net/xdp_priv.h index 6a8cba6ea79a..a9d5b7603b89 100644 --- a/include/net/xdp_priv.h +++ b/include/net/xdp_priv.h @@ -12,12 +12,8 @@ struct xdp_mem_allocator { struct page_pool *page_pool; struct zero_copy_allocator *zc_alloc; }; - int disconnect_cnt; - unsigned long defer_start; struct rhash_head node; struct rcu_head rcu; - struct delayed_work defer_wq; - unsigned long defer_warn; }; #endif /* __LINUX_NET_XDP_PRIV_H__ */ diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index c9398ce7960f..e3780e4b74e1 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -69,7 +69,14 @@ struct xdp_umem { /* Nodes are linked in the struct xdp_sock map_list field, and used to * track which maps a certain socket reside in. */ -struct xsk_map; + +struct xsk_map { + struct bpf_map map; + struct list_head __percpu *flush_list; + spinlock_t lock; /* Synchronize map updates */ + struct xdp_sock *xsk_map[]; +}; + struct xsk_map_node { struct list_head node; struct xsk_map *map; @@ -109,8 +116,6 @@ struct xdp_sock { struct xdp_buff; #ifdef CONFIG_XDP_SOCKETS int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp); -int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp); -void xsk_flush(struct xdp_sock *xs); bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs); /* Used from netdev driver */ bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt); @@ -134,6 +139,22 @@ void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs, struct xdp_sock **map_entry); int xsk_map_inc(struct xsk_map *map); void xsk_map_put(struct xsk_map *map); +int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp, + struct xdp_sock *xs); +void __xsk_map_flush(struct bpf_map *map); + +static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, + u32 key) +{ + struct xsk_map *m = container_of(map, struct xsk_map, map); + struct xdp_sock *xs; + + if (key >= map->max_entries) + return NULL; + + xs = READ_ONCE(m->xsk_map[key]); + return xs; +} static inline u64 xsk_umem_extract_addr(u64 addr) { @@ -224,15 +245,6 @@ static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) return -ENOTSUPP; } -static inline int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) -{ - return -ENOTSUPP; -} - -static inline void xsk_flush(struct xdp_sock *xs) -{ -} - static inline bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs) { return false; @@ -357,6 +369,21 @@ static inline u64 xsk_umem_adjust_offset(struct xdp_umem *umem, u64 handle, return 0; } +static inline int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp, + struct xdp_sock *xs) +{ + return -EOPNOTSUPP; +} + +static inline void __xsk_map_flush(struct bpf_map *map) +{ +} + +static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, + u32 key) +{ + return NULL; +} #endif /* CONFIG_XDP_SOCKETS */ #endif /* _LINUX_XDP_SOCK_H */ diff --git a/include/net/xfrm.h b/include/net/xfrm.h index aa08a7a5f6ac..dda3c025452e 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1613,13 +1613,6 @@ static inline int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optv { return -ENOPROTOOPT; } - -static inline int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb) -{ - /* should not happen */ - kfree_skb(skb); - return 0; -} #endif struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif, |