diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-01-31 14:31:10 -0800 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-01-31 14:31:10 -0800 |
| commit | b2fe5fa68642860e7de76167c3111623aa0d5de1 (patch) | |
| tree | b7f9b89b7039ecefbc35fe3c8e73a6ff972641dd /include/net | |
| parent | a103950e0dd2058df5e8a8d4a915707bdcf205f0 (diff) | |
| parent | a54667f6728c2714a400f3c884727da74b6d1717 (diff) | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
1) Significantly shrink the core networking routing structures. Result
of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf
2) Add netdevsim driver for testing various offloads, from Jakub
Kicinski.
3) Support cross-chip FDB operations in DSA, from Vivien Didelot.
4) Add a 2nd listener hash table for TCP, similar to what was done for
UDP. From Martin KaFai Lau.
5) Add eBPF based queue selection to tun, from Jason Wang.
6) Lockless qdisc support, from John Fastabend.
7) SCTP stream interleave support, from Xin Long.
8) Smoother TCP receive autotuning, from Eric Dumazet.
9) Lots of erspan tunneling enhancements, from William Tu.
10) Add true function call support to BPF, from Alexei Starovoitov.
11) Add explicit support for GRO HW offloading, from Michael Chan.
12) Support extack generation in more netlink subsystems. From Alexander
Aring, Quentin Monnet, and Jakub Kicinski.
13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
Russell King.
14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.
15) Many improvements and simplifications to the NFP driver bpf JIT,
from Jakub Kicinski.
16) Support for ipv6 non-equal cost multipath routing, from Ido
Schimmel.
17) Add resource abstration to devlink, from Arkadi Sharshevsky.
18) Packet scheduler classifier shared filter block support, from Jiri
Pirko.
19) Avoid locking in act_csum, from Davide Caratti.
20) devinet_ioctl() simplifications from Al viro.
21) More TCP bpf improvements from Lawrence Brakmo.
22) Add support for onlink ipv6 route flag, similar to ipv4, from David
Ahern.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
tls: Add support for encryption using async offload accelerator
ip6mr: fix stale iterator
net/sched: kconfig: Remove blank help texts
openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
tcp_nv: fix potential integer overflow in tcpnv_acked
r8169: fix RTL8168EP take too long to complete driver initialization.
qmi_wwan: Add support for Quectel EP06
rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
ipmr: Fix ptrdiff_t print formatting
ibmvnic: Wait for device response when changing MAC
qlcnic: fix deadlock bug
tcp: release sk_frag.page in tcp_disconnect
ipv4: Get the address of interface correctly.
net_sched: gen_estimator: fix lockdep splat
net: macb: Handle HRESP error
net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
ipv6: addrconf: break critical section in addrconf_verify_rtnl()
ipv6: change route cache aging logic
i40e/i40evf: Update DESC_NEEDED value to reflect larger value
bnxt_en: cleanup DIM work on device shutdown
...
Diffstat (limited to 'include/net')
58 files changed, 1459 insertions, 362 deletions
diff --git a/include/net/act_api.h b/include/net/act_api.h index fd08df74c466..6ed9692f20bd 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -86,7 +86,7 @@ struct tc_action_ops { int (*act)(struct sk_buff *, const struct tc_action *, struct tcf_result *); int (*dump)(struct sk_buff *, struct tc_action *, int, int); - void (*cleanup)(struct tc_action *, int bind); + void (*cleanup)(struct tc_action *); int (*lookup)(struct net *, struct tc_action **, u32); int (*init)(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **act, int ovr, @@ -120,12 +120,19 @@ int tc_action_net_init(struct tc_action_net *tn, void tcf_idrinfo_destroy(const struct tc_action_ops *ops, struct tcf_idrinfo *idrinfo); -static inline void tc_action_net_exit(struct tc_action_net *tn) +static inline void tc_action_net_exit(struct list_head *net_list, + unsigned int id) { + struct net *net; + rtnl_lock(); - tcf_idrinfo_destroy(tn->ops, tn->idrinfo); + list_for_each_entry(net, net_list, exit_list) { + struct tc_action_net *tn = net_generic(net, id); + + tcf_idrinfo_destroy(tn->ops, tn->idrinfo); + kfree(tn->idrinfo); + } rtnl_unlock(); - kfree(tn->idrinfo); } int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb, diff --git a/include/net/addrconf.h b/include/net/addrconf.h index b623b65a79d1..c4185a7b0e90 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -180,7 +180,7 @@ static inline int addrconf_finite_timeout(unsigned long timeout) */ int ipv6_addr_label_init(void); void ipv6_addr_label_cleanup(void); -void ipv6_addr_label_rtnl_register(void); +int ipv6_addr_label_rtnl_register(void); u32 ipv6_addr_label(struct net *net, const struct in6_addr *addr, int type, int ifindex); diff --git a/include/net/caif/cfpkt.h b/include/net/caif/cfpkt.h index fe328c52c46b..801489bb14c3 100644 --- a/include/net/caif/cfpkt.h +++ b/include/net/caif/cfpkt.h @@ -32,6 +32,33 @@ void cfpkt_destroy(struct cfpkt *pkt); */ int cfpkt_extr_head(struct cfpkt *pkt, void *data, u16 len); +static inline u8 cfpkt_extr_head_u8(struct cfpkt *pkt) +{ + u8 tmp; + + cfpkt_extr_head(pkt, &tmp, 1); + + return tmp; +} + +static inline u16 cfpkt_extr_head_u16(struct cfpkt *pkt) +{ + __le16 tmp; + + cfpkt_extr_head(pkt, &tmp, 2); + + return le16_to_cpu(tmp); +} + +static inline u32 cfpkt_extr_head_u32(struct cfpkt *pkt) +{ + __le32 tmp; + + cfpkt_extr_head(pkt, &tmp, 4); + + return le32_to_cpu(tmp); +} + /* * Peek header from packet. * Reads data from packet without changing packet. diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index fb94a8bd8ab5..81174f9b8d14 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1775,6 +1775,8 @@ enum cfg80211_signal_type { * by %parent_bssid. * @parent_bssid: the BSS according to which %parent_tsf is set. This is set to * the BSS that requested the scan in which the beacon/probe was received. + * @chains: bitmask for filled values in @chain_signal. + * @chain_signal: per-chain signal strength of last received BSS in dBm. */ struct cfg80211_inform_bss { struct ieee80211_channel *chan; @@ -1783,6 +1785,8 @@ struct cfg80211_inform_bss { u64 boottime_ns; u64 parent_tsf; u8 parent_bssid[ETH_ALEN] __aligned(2); + u8 chains; + s8 chain_signal[IEEE80211_MAX_CHAINS]; }; /** @@ -1826,6 +1830,8 @@ struct cfg80211_bss_ies { * that holds the beacon data. @beacon_ies is still valid, of course, and * points to the same data as hidden_beacon_bss->beacon_ies in that case. * @signal: signal strength value (type depends on the wiphy's signal_type) + * @chains: bitmask for filled values in @chain_signal. + * @chain_signal: per-chain signal strength of last received BSS in dBm. * @priv: private area for driver use, has at least wiphy->bss_priv_size bytes */ struct cfg80211_bss { @@ -1844,6 +1850,8 @@ struct cfg80211_bss { u16 capability; u8 bssid[ETH_ALEN]; + u8 chains; + s8 chain_signal[IEEE80211_MAX_CHAINS]; u8 priv[0] __aligned(sizeof(void *)); }; @@ -2023,6 +2031,9 @@ struct cfg80211_disassoc_request { * @ht_capa: HT Capabilities over-rides. Values set in ht_capa_mask * will be used in ht_capa. Un-supported values will be ignored. * @ht_capa_mask: The bits of ht_capa which are to be used. + * @wep_keys: static WEP keys, if not NULL points to an array of + * CFG80211_MAX_WEP_KEYS WEP keys + * @wep_tx_key: key index (0..3) of the default TX static WEP key */ struct cfg80211_ibss_params { const u8 *ssid; @@ -2039,6 +2050,8 @@ struct cfg80211_ibss_params { int mcast_rate[NUM_NL80211_BANDS]; struct ieee80211_ht_cap ht_capa; struct ieee80211_ht_cap ht_capa_mask; + struct key_params *wep_keys; + int wep_tx_key; }; /** @@ -5577,7 +5590,7 @@ void cfg80211_conn_failed(struct net_device *dev, const u8 *mac_addr, * cfg80211_rx_mgmt - notification of received, unprocessed management frame * @wdev: wireless device receiving the frame * @freq: Frequency on which the frame was received in MHz - * @sig_dbm: signal strength in mBm, or 0 if unknown + * @sig_dbm: signal strength in dBm, or 0 if unknown * @buf: Management frame (header + body) * @len: length of the frame data * @flags: flags, as defined in enum nl80211_rxmgmt_flags @@ -5756,7 +5769,7 @@ void cfg80211_probe_status(struct net_device *dev, const u8 *addr, * @frame: the frame * @len: length of the frame * @freq: frequency the frame was received on - * @sig_dbm: signal strength in mBm, or 0 if unknown + * @sig_dbm: signal strength in dBm, or 0 if unknown * * Use this function to report to userspace when a beacon was * received. It is not useful to call this when there is no diff --git a/include/net/devlink.h b/include/net/devlink.h index b9654e133599..6545b03e97f7 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -26,10 +26,12 @@ struct devlink { struct list_head port_list; struct list_head sb_list; struct list_head dpipe_table_list; + struct list_head resource_list; struct devlink_dpipe_headers *dpipe_headers; const struct devlink_ops *ops; struct device *dev; possible_net_t _net; + struct mutex lock; char priv[0] __aligned(NETDEV_ALIGN); }; @@ -181,6 +183,9 @@ struct devlink_dpipe_table_ops; * @counters_enabled: indicates if counters are active * @counter_control_extern: indicates if counter control is in dpipe or * external tool + * @resource_valid: Indicate that the resource id is valid + * @resource_id: relative resource this table is related to + * @resource_units: number of resource's unit consumed per table's entry * @table_ops: table operations * @rcu: rcu */ @@ -190,6 +195,9 @@ struct devlink_dpipe_table { const char *name; bool counters_enabled; bool counter_control_extern; + bool resource_valid; + u64 resource_id; + u64 resource_units; struct devlink_dpipe_table_ops *table_ops; struct rcu_head rcu; }; @@ -223,7 +231,63 @@ struct devlink_dpipe_headers { unsigned int headers_count; }; +/** + * struct devlink_resource_ops - resource ops + * @occ_get: get the occupied size + * @size_validate: validate the size of the resource before update, reload + * is needed for changes to take place + */ +struct devlink_resource_ops { + u64 (*occ_get)(struct devlink *devlink); + int (*size_validate)(struct devlink *devlink, u64 size, + struct netlink_ext_ack *extack); +}; + +/** + * struct devlink_resource_size_params - resource's size parameters + * @size_min: minimum size which can be set + * @size_max: maximum size which can be set + * @size_granularity: size granularity + * @size_unit: resource's basic unit + */ +struct devlink_resource_size_params { + u64 size_min; + u64 size_max; + u64 size_granularity; + enum devlink_resource_unit unit; +}; + +/** + * struct devlink_resource - devlink resource + * @name: name of the resource + * @id: id, per devlink instance + * @size: size of the resource + * @size_new: updated size of the resource, reload is needed + * @size_valid: valid in case the total size of the resource is valid + * including its children + * @parent: parent resource + * @size_params: size parameters + * @list: parent list + * @resource_list: list of child resources + * @resource_ops: resource ops + */ +struct devlink_resource { + const char *name; + u64 id; + u64 size; + u64 size_new; + bool size_valid; + struct devlink_resource *parent; + struct devlink_resource_size_params *size_params; + struct list_head list; + struct list_head resource_list; + const struct devlink_resource_ops *resource_ops; +}; + +#define DEVLINK_RESOURCE_ID_PARENT_TOP 0 + struct devlink_ops { + int (*reload)(struct devlink *devlink); int (*port_type_set)(struct devlink_port *devlink_port, enum devlink_port_type port_type); int (*port_split)(struct devlink *devlink, unsigned int port_index, @@ -332,6 +396,23 @@ extern struct devlink_dpipe_header devlink_dpipe_header_ethernet; extern struct devlink_dpipe_header devlink_dpipe_header_ipv4; extern struct devlink_dpipe_header devlink_dpipe_header_ipv6; +int devlink_resource_register(struct devlink *devlink, + const char *resource_name, + bool top_hierarchy, + u64 resource_size, + u64 resource_id, + u64 parent_resource_id, + struct devlink_resource_size_params *size_params, + const struct devlink_resource_ops *resource_ops); +void devlink_resources_unregister(struct devlink *devlink, + struct devlink_resource *resource); +int devlink_resource_size_get(struct devlink *devlink, + u64 resource_id, + u64 *p_resource_size); +int devlink_dpipe_table_resource_set(struct devlink *devlink, + const char *table_name, u64 resource_id, + u64 resource_units); + #else static inline struct devlink *devlink_alloc(const struct devlink_ops *ops, @@ -468,6 +549,40 @@ devlink_dpipe_match_put(struct sk_buff *skb, return 0; } +static inline int +devlink_resource_register(struct devlink *devlink, + const char *resource_name, + bool top_hierarchy, + u64 resource_size, + u64 resource_id, + u64 parent_resource_id, + struct devlink_resource_size_params *size_params, + const struct devlink_resource_ops *resource_ops) +{ + return 0; +} + +static inline void +devlink_resources_unregister(struct devlink *devlink, + struct devlink_resource *resource) +{ +} + +static inline int +devlink_resource_size_get(struct devlink *devlink, u64 resource_id, + u64 *p_resource_size) +{ + return -EOPNOTSUPP; +} + +static inline int +devlink_dpipe_table_resource_set(struct devlink *devlink, + const char *table_name, u64 resource_id, + u64 resource_units) +{ + return -EOPNOTSUPP; +} + #endif #endif /* _NET_DEVLINK_H_ */ diff --git a/include/net/dn_route.h b/include/net/dn_route.h index 55df9939bca2..342d2503cba5 100644 --- a/include/net/dn_route.h +++ b/include/net/dn_route.h @@ -69,6 +69,7 @@ int dn_route_rcv(struct sk_buff *skb, struct net_device *dev, */ struct dn_route { struct dst_entry dst; + struct dn_route __rcu *dn_next; struct neighbour *n; diff --git a/include/net/dsa.h b/include/net/dsa.h index 2a05738570d8..6cb602dd970c 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -296,31 +296,39 @@ static inline u32 dsa_user_ports(struct dsa_switch *ds) return mask; } -static inline u8 dsa_upstream_port(struct dsa_switch *ds) +/* 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) { - struct dsa_switch_tree *dst = ds->dst; - - /* - * If this is the root switch (i.e. the switch that connects - * to the CPU), return the cpu port number on this switch. - * Else return the (DSA) port number that connects to the - * switch that is one hop closer to the cpu. - */ - if (dst->cpu_dp->ds == ds) - return dst->cpu_dp->index; + if (device == ds->index) + return port; else - return ds->rtable[dst->cpu_dp->ds->index]; + return ds->rtable[device]; +} + +/* Return the local port used to reach the dedicated CPU port */ +static inline unsigned int dsa_upstream_port(struct dsa_switch *ds, int port) +{ + const struct dsa_port *dp = dsa_to_port(ds, port); + const struct dsa_port *cpu_dp = dp->cpu_dp; + + if (!cpu_dp) + return port; + + return dsa_towards_port(ds, cpu_dp->ds->index, cpu_dp->index); } typedef int dsa_fdb_dump_cb_t(const unsigned char *addr, u16 vid, bool is_static, void *data); struct dsa_switch_ops { +#if IS_ENABLED(CONFIG_NET_DSA_LEGACY) /* * Legacy probing. */ const char *(*probe)(struct device *dsa_dev, struct device *host_dev, int sw_addr, void **priv); +#endif enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds, int port); @@ -412,12 +420,10 @@ struct dsa_switch_ops { */ int (*port_vlan_filtering)(struct dsa_switch *ds, int port, bool vlan_filtering); - int (*port_vlan_prepare)(struct dsa_switch *ds, int port, - const struct switchdev_obj_port_vlan *vlan, - struct switchdev_trans *trans); - void (*port_vlan_add)(struct dsa_switch *ds, int port, - const struct switchdev_obj_port_vlan *vlan, - struct switchdev_trans *trans); + int (*port_vlan_prepare)(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_vlan *vlan); + void (*port_vlan_add)(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_vlan *vlan); int (*port_vlan_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); /* @@ -433,12 +439,10 @@ struct dsa_switch_ops { /* * Multicast database */ - int (*port_mdb_prepare)(struct dsa_switch *ds, int port, - const struct switchdev_obj_port_mdb *mdb, - struct switchdev_trans *trans); - void (*port_mdb_add)(struct dsa_switch *ds, int port, - const struct switchdev_obj_port_mdb *mdb, - struct switchdev_trans *trans); + int (*port_mdb_prepare)(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_mdb *mdb); + void (*port_mdb_add)(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_mdb *mdb); int (*port_mdb_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb); /* @@ -472,11 +476,20 @@ struct dsa_switch_driver { const struct dsa_switch_ops *ops; }; +#if IS_ENABLED(CONFIG_NET_DSA_LEGACY) /* Legacy driver registration */ void register_switch_driver(struct dsa_switch_driver *type); void unregister_switch_driver(struct dsa_switch_driver *type); struct mii_bus *dsa_host_dev_to_mii_bus(struct device *dev); +#else +static inline void register_switch_driver(struct dsa_switch_driver *type) { } +static inline void unregister_switch_driver(struct dsa_switch_driver *type) { } +static inline struct mii_bus *dsa_host_dev_to_mii_bus(struct device *dev) +{ + return NULL; +} +#endif struct net_device *dsa_dev_to_net_device(struct device *dev); /* Keep inline for faster access in hot path */ diff --git a/include/net/dst.h b/include/net/dst.h index d49d607dd2b3..c63d2c37f6e9 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -34,13 +34,9 @@ struct sk_buff; struct dst_entry { struct net_device *dev; - struct rcu_head rcu_head; - struct dst_entry *child; struct dst_ops *ops; unsigned long _metrics; unsigned long expires; - struct dst_entry *path; - struct dst_entry *from; #ifdef CONFIG_XFRM struct xfrm_state *xfrm; #else @@ -59,8 +55,6 @@ struct dst_entry { #define DST_XFRM_QUEUE 0x0040 #define DST_METADATA 0x0080 - short error; - /* A non-zero value of dst->obsolete forces by-hand validation * of the route entry. Positive values are set by the generic * dst layer to indicate that the entry has been forcefully @@ -76,35 +70,24 @@ struct dst_entry { #define DST_OBSOLETE_KILL -2 unsigned short header_len; /* more space at head required */ unsigned short trailer_len; /* space to reserve at tail */ - unsigned short __pad3; -#ifdef CONFIG_IP_ROUTE_CLASSID - __u32 tclassid; -#else - __u32 __pad2; -#endif - -#ifdef CONFIG_64BIT - /* - * Align __refcnt to a 64 bytes alignment - * (L1_CACHE_SIZE would be too much) - */ - long __pad_to_align_refcnt[2]; -#endif /* * __refcnt wants to be on a different cache line from * input/output/ops or performance tanks badly */ - atomic_t __refcnt; /* client references */ +#ifdef CONFIG_64BIT + atomic_t __refcnt; /* 64-bit offset 64 */ +#endif int __use; unsigned long lastuse; struct lwtunnel_state *lwtstate; - union { - struct dst_entry *next; - struct rtable __rcu *rt_next; - struct rt6_info __rcu *rt6_next; - struct dn_route __rcu *dn_next; - }; + struct rcu_head rcu_head; + short error; + short __pad; + __u32 tclassid; +#ifndef CONFIG_64BIT + atomic_t __refcnt; /* 32-bit offset 64 */ +#endif }; struct dst_metrics { @@ -250,7 +233,7 @@ static inline void dst_hold(struct dst_entry *dst) { /* * If your kernel compilation stops here, please check - * __pad_to_align_refcnt declaration in struct dst_entry + * the placement of __refcnt in struct dst_entry */ BUILD_BUG_ON(offsetof(struct dst_entry, __refcnt) & 63); WARN_ON(atomic_inc_not_zero(&dst->__refcnt) == 0); diff --git a/include/net/erspan.h b/include/net/erspan.h index ca94fc86865e..5daa4866412b 100644 --- a/include/net/erspan.h +++ b/include/net/erspan.h @@ -15,7 +15,7 @@ * s, Recur, Flags, Version fields only S (bit 03) is set to 1. The * other fields are set to zero, so only a sequence number follows. * - * ERSPAN Type II header (8 octets [42:49]) + * ERSPAN Version 1 (Type II) header (8 octets [42:49]) * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ @@ -24,11 +24,31 @@ * | Reserved | Index | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * + * + * ERSPAN Version 2 (Type III) header (12 octets [42:49]) + * 0 1 2 3 + * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Ver | VLAN | COS |BSO|T| Session ID | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Timestamp | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | SGT |P| FT | Hw ID |D|Gra|O| + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * + * Platform Specific SubHeader (8 octets, optional) + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Platf ID | Platform Specific Info | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Platform Specific Info | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * * GRE proto ERSPAN type II = 0x88BE, type III = 0x22EB */ -#define ERSPAN_VERSION 0x1 +#include <uapi/linux/erspan.h> +#define ERSPAN_VERSION 0x1 /* ERSPAN type II */ #define VER_MASK 0xf000 #define VLAN_MASK 0x0fff #define COS_MASK 0xe000 @@ -37,6 +57,19 @@ #define ID_MASK 0x03ff #define INDEX_MASK 0xfffff +#define ERSPAN_VERSION2 0x2 /* ERSPAN type III*/ +#define BSO_MASK EN_MASK +#define SGT_MASK 0xffff0000 +#define P_MASK 0x8000 +#define FT_MASK 0x7c00 +#define HWID_MASK 0x03f0 +#define DIR_MASK 0x0008 +#define GRA_MASK 0x0006 +#define O_MASK 0x0001 + +#define HWID_OFFSET 4 +#define DIR_OFFSET 3 + enum erspan_encap_type { ERSPAN_ENCAP_NOVLAN = 0x0, /* originally without VLAN tag */ ERSPAN_ENCAP_ISL = 0x1, /* originally ISL encapsulated */ @@ -44,18 +77,199 @@ enum erspan_encap_type { ERSPAN_ENCAP_INFRAME = 0x3, /* VLAN tag perserved in frame */ }; -struct erspan_metadata { - __be32 index; /* type II */ -}; +#define ERSPAN_V1_MDSIZE 4 +#define ERSPAN_V2_MDSIZE 8 -struct erspanhdr { - __be16 ver_vlan; -#define VER_OFFSET 12 - __be16 session_id; -#define COS_OFFSET 13 -#define EN_OFFSET 11 -#define T_OFFSET 10 - struct erspan_metadata md; +struct erspan_base_hdr { +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u8 vlan_upper:4, + ver:4; + __u8 vlan:8; + __u8 session_id_upper:2, + t:1, + en:2, + cos:3; + __u8 session_id:8; +#elif defined(__BIG_ENDIAN_BITFIELD) + __u8 ver: 4, + vlan_upper:4; + __u8 vlan:8; + __u8 cos:3, + en:2, + t:1, + session_id_upper:2; + __u8 session_id:8; +#else +#error "Please fix <asm/byteorder.h>" +#endif }; +static inline void set_session_id(struct erspan_base_hdr *ershdr, u16 id) +{ + ershdr->session_id = id & 0xff; + ershdr->session_id_upper = (id >> 8) & 0x3; +} + +static inline u16 get_session_id(const struct erspan_base_hdr *ershdr) +{ + return (ershdr->session_id_upper << 8) + ershdr->session_id; +} + +static inline void set_vlan(struct erspan_base_hdr *ershdr, u16 vlan) +{ + ershdr->vlan = vlan & 0xff; + ershdr->vlan_upper = (vlan >> 8) & 0xf; +} + +static inline u16 get_vlan(const struct erspan_base_hdr *ershdr) +{ + return (ershdr->vlan_upper << 8) + ershdr->vlan; +} + +static inline void set_hwid(struct erspan_md2 *md2, u8 hwid) +{ + md2->hwid = hwid & 0xf; + md2->hwid_upper = (hwid >> 4) & 0x3; +} + +static inline u8 get_hwid(const struct erspan_md2 *md2) +{ + return (md2->hwid_upper << 4) + md2->hwid; +} + +static inline int erspan_hdr_len(int version) +{ + return sizeof(struct erspan_base_hdr) + + (version == 1 ? ERSPAN_V1_MDSIZE : ERSPAN_V2_MDSIZE); +} + +static inline u8 tos_to_cos(u8 tos) +{ + u8 dscp, cos; + + dscp = tos >> 2; + cos = dscp >> 3; + return cos; +} + +static inline void erspan_build_header(struct sk_buff *skb, + u32 id, u32 index, + bool truncate, bool is_ipv4) +{ + struct ethhdr *eth = (struct ethhdr *)skb->data; + enum erspan_encap_type enc_type; + struct erspan_base_hdr *ershdr; + struct erspan_metadata *ersmd; + struct qtag_prefix { + __be16 eth_type; + __be16 tci; + } *qp; + u16 vlan_tci = 0; + u8 tos; + + tos = is_ipv4 ? ip_hdr(skb)->tos : + (ipv6_hdr(skb)->priority << 4) + + (ipv6_hdr(skb)->flow_lbl[0] >> 4); + + enc_type = ERSPAN_ENCAP_NOVLAN; + + /* If mirrored packet has vlan tag, extract tci and + * perserve vlan header in the mirrored frame. + */ + if (eth->h_proto == htons(ETH_P_8021Q)) { + qp = (struct qtag_prefix *)(skb->data + 2 * ETH_ALEN); + vlan_tci = ntohs(qp->tci); + enc_type = ERSPAN_ENCAP_INFRAME; + } + + skb_push(skb, sizeof(*ershdr) + ERSPAN_V1_MDSIZE); + ershdr = (struct erspan_base_hdr *)skb->data; + memset(ershdr, 0, sizeof(*ershdr) + ERSPAN_V1_MDSIZE); + + /* Build base header */ + ershdr->ver = ERSPAN_VERSION; + ershdr->cos = tos_to_cos(tos); + ershdr->en = enc_type; + ershdr->t = truncate; + set_vlan(ershdr, vlan_tci); + set_session_id(ershdr, id); + + /* Build metadata */ + ersmd = (struct erspan_metadata *)(ershdr + 1); + ersmd->u.index = htonl(index & INDEX_MASK); +} + +/* ERSPAN GRA: timestamp granularity + * 00b --> granularity = 100 microseconds + * 01b --> granularity = 100 nanoseconds + * 10b --> granularity = IEEE 1588 + * Here we only support 100 microseconds. + */ +static inline __be32 erspan_get_timestamp(void) +{ + u64 h_usecs; + ktime_t kt; + + kt = ktime_get_real(); + h_usecs = ktime_divns(kt, 100 * NSEC_PER_USEC); + + /* ERSPAN base header only has 32-bit, + * so it wraps around 4 days. + */ + return htonl((u32)h_usecs); +} + +static inline void erspan_build_header_v2(struct sk_buff *skb, + u32 id, u8 direction, u16 hwid, + bool truncate, bool is_ipv4) +{ + struct ethhdr *eth = (struct ethhdr *)skb->data; + struct erspan_base_hdr *ershdr; + struct erspan_metadata *md; + struct qtag_prefix { + __be16 eth_type; + __be16 tci; + } *qp; + u16 vlan_tci = 0; + u8 gra = 0; /* 100 usec */ + u8 bso = 0; /* Bad/Short/Oversized */ + u8 sgt = 0; + u8 tos; + + tos = is_ipv4 ? ip_hdr(skb)->tos : + (ipv6_hdr(skb)->priority << 4) + + (ipv6_hdr(skb)->flow_lbl[0] >> 4); + + /* Unlike v1, v2 does not have En field, + * so only extract vlan tci field. + */ + if (eth->h_proto == htons(ETH_P_8021Q)) { + qp = (struct qtag_prefix *)(skb->data + 2 * ETH_ALEN); + vlan_tci = ntohs(qp->tci); + } + + skb_push(skb, sizeof(*ershdr) + ERSPAN_V2_MDSIZE); + ershdr = (struct erspan_base_hdr *)skb->data; + memset(ershdr, 0, sizeof(*ershdr) + ERSPAN_V2_MDSIZE); + + /* Build base header */ + ershdr->ver = ERSPAN_VERSION2; + ershdr->cos = tos_to_cos(tos); + ershdr->en = bso; + ershdr->t = truncate; + set_vlan(ershdr, vlan_tci); + set_session_id(ershdr, id); + + /* Build metadata */ + md = (struct erspan_metadata *)(ershdr + 1); + md->u.md2.timestamp = erspan_get_timestamp(); + md->u.md2.sgt = htons(sgt); + md->u.md2.p = 1; + md->u.md2.ft = 0; + md->u.md2.dir = direction; + md->u.md2.gra = gra; + md->u.md2.o = 0; + set_hwid(&md->u.md2, hwid); +} + #endif diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h index 304f7aa9cc01..0304ba2ae353 100644 --- a/include/net/gen_stats.h +++ b/include/net/gen_stats.h @@ -49,6 +49,9 @@ int gnet_stats_copy_rate_est(struct gnet_dump *d, int gnet_stats_copy_queue(struct gnet_dump *d, struct gnet_stats_queue __percpu *cpu_q, struct gnet_stats_queue *q, __u32 qlen); +void __gnet_stats_copy_queue(struct gnet_stats_queue *qstats, + const struct gnet_stats_queue __percpu *cpu_q, + const struct gnet_stats_queue *q, __u32 qlen); int gnet_stats_copy_app(struct gnet_dump *d, void *st, int len); int gnet_stats_finish_copy(struct gnet_dump *d); diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index ec72cdb5bc39..6692d67e9245 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -77,6 +77,7 @@ struct inet_connection_sock_af_ops { * @icsk_af_ops Operations which are AF_INET{4,6} specific * @icsk_ulp_ops Pluggable ULP control hook * @icsk_ulp_data ULP private data + * @icsk_listen_portaddr_node hash to the portaddr listener hashtable * @icsk_ca_state: Congestion control state * @icsk_retransmits: Number of unrecovered [RTO] timeouts * @icsk_pending: Scheduled timer event @@ -101,6 +102,7 @@ struct inet_connection_sock { const struct inet_connection_sock_af_ops *icsk_af_ops; const struct tcp_ulp_ops *icsk_ulp_ops; void *icsk_ulp_data; + struct hlist_node icsk_listen_portaddr_node; unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu); __u8 icsk_ca_state:6, icsk_ca_setsockopt:1, diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 2dbbbff5e1e3..9141e95529e7 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -111,6 +111,7 @@ struct inet_bind_hashbucket { */ struct inet_listen_hashbucket { spinlock_t lock; + unsigned int count; struct hlist_head head; }; @@ -132,12 +133,13 @@ struct inet_hashinfo { /* Ok, let's try this, I give up, we do need a local binding * TCP hash as well as the others for fast bind/connect. */ + struct kmem_cache *bind_bucket_cachep; struct inet_bind_hashbucket *bhash; - unsigned int bhash_size; - /* 4 bytes hole on 64 bit */ - struct kmem_cache *bind_bucket_cachep; + /* The 2nd listener table hashed by local port and address */ + unsigned int lhash2_mask; + struct inet_listen_hashbucket *lhash2; /* All the above members are written once at bootup and * never written again _or_ are predominantly read-access. @@ -145,14 +147,25 @@ struct inet_hashinfo { * Now align to a new cache line as all the following members * might be often dirty. */ - /* All sockets in TCP_LISTEN state will be in here. This is the only - * table where wildcard'd TCP sockets can exist. Hash function here - * is just local port number. + /* All sockets in TCP_LISTEN state will be in listening_hash. + * This is the only table where wildcard'd TCP sockets can + * exist. listening_hash is only hashed by local port number. + * If lhash2 is initialized, the same socket will also be hashed + * to lhash2 by port and address. */ struct inet_listen_hashbucket listening_hash[INET_LHTABLE_SIZE] ____cacheline_aligned_in_smp; }; +#define inet_lhash2_for_each_icsk_rcu(__icsk, list) \ + hlist_for_each_entry_rcu(__icsk, list, icsk_listen_portaddr_node) + +static inline struct inet_listen_hashbucket * +inet_lhash2_bucket(struct inet_hashinfo *h, u32 hash) +{ + return &h->lhash2[hash & h->lhash2_mask]; +} + static inline struct inet_ehash_bucket *inet_ehash_bucket( struct inet_hashinfo *hashinfo, unsigned int hash) @@ -208,6 +221,10 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child); void inet_put_port(struct sock *sk); void inet_hashinfo_init(struct inet_hashinfo *h); +void inet_hashinfo2_init(struct inet_hashinfo *h, const char *name, + unsigned long numentries, int scale, + unsigned long low_limit, + unsigned long high_limit); bool inet_ehash_insert(struct sock *sk, struct sock *osk); bool inet_ehash_nolisten(struct sock *sk, struct sock *osk); diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 39efb968b7a4..0a671c32d6b9 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -291,6 +291,31 @@ static inline void inet_sk_copy_descendant(struct sock *sk_to, int inet_sk_rebuild_header(struct sock *sk); +/** + * inet_sk_state_load - read sk->sk_state for lockless contexts + * @sk: socket pointer + * + * Paired with inet_sk_state_store(). Used in places we don't hold socket lock: + * tcp_diag_get_info(), tcp_get_info(), tcp_poll(), get_tcp4_sock() ... + */ +static inline int inet_sk_state_load(const struct sock *sk) +{ + /* state change might impact lockless readers. */ + return smp_load_acquire(&sk->sk_state); +} + +/** + * inet_sk_state_store - update sk->sk_state + * @sk: socket pointer + * @newstate: new state + * + * Paired with inet_sk_state_load(). Should be used in contexts where + * state change might impact lockless readers. + */ +void inet_sk_state_store(struct sock *sk, int newstate); + +void inet_sk_set_state(struct sock *sk, int state); + static inline unsigned int __inet_ehashfn(const __be32 laddr, const __u16 lport, const __be32 faddr, diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index 1356fa6a7566..899495589a7e 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -93,8 +93,8 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, struct inet_timewait_death_row *dr, const int state); -void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, - struct inet_hashinfo *hashinfo); +void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, + struct inet_hashinfo *hashinfo); void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm); diff --git a/include/net/ip.h b/include/net/ip.h index af8addbaa3c1..746abff9ce51 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -26,12 +26,14 @@ #include <linux/ip.h> #include <linux/in.h> #include <linux/skbuff.h> +#include <linux/jhash.h> #include <net/inet_sock.h> #include <net/route.h> #include <net/snmp.h> #include <net/flow.h> #include <net/flow_dissector.h> +#include <net/netns/hash.h> #define IPV4_MAX_PMTU 65535U /* RFC 2675, Section 5.1 */ #define IPV4_MIN_MTU 68 /* RFC 791 */ @@ -522,6 +524,13 @@ static inline unsigned int ipv4_addr_hash(__be32 ip) return (__force unsigned int) ip; } +static inline u32 ipv4_portaddr_hash(const struct net *net, + __be32 saddr, + unsigned int port) +{ + return jhash_1word((__force u32)saddr, net_hash_mix(net)) ^ port; +} + bool ip_call_ra_chain(struct sk_buff *skb); /* diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 10c913816032..34ec321d6a03 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -129,6 +129,8 @@ struct rt6_exception { struct rt6_info { struct dst_entry dst; + struct rt6_info __rcu *rt6_next; + struct rt6_info *from; /* * Tail elements of dst_entry (__refcnt etc.) @@ -147,6 +149,7 @@ struct rt6_info { */ struct list_head rt6i_siblings; unsigned int rt6i_nsiblings; + atomic_t rt6i_nh_upper_bound; atomic_t rt6i_ref; @@ -168,19 +171,21 @@ struct rt6_info { u32 rt6i_metric; u32 rt6i_pmtu; /* more non-fragment space at head required */ + int rt6i_nh_weight; unsigned short rt6i_nfheader_len; u8 rt6i_protocol; u8 exception_bucket_flushed:1, - unused:7; + should_flush:1, + unused:6; }; #define for_each_fib6_node_rt_rcu(fn) \ for (rt = rcu_dereference((fn)->leaf); rt; \ - rt = rcu_dereference(rt->dst.rt6_next)) + rt = rcu_dereference(rt->rt6_next)) #define for_each_fib6_walker_rt(w) \ for (rt = (w)->leaf; rt; \ - rt = rcu_dereference_protected(rt->dst.rt6_next, 1)) + rt = rcu_dereference_protected(rt->rt6_next, 1)) static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst) { @@ -203,11 +208,9 @@ static inline void rt6_update_expires(struct rt6_info *rt0, int timeout) { struct rt6_info *rt; - for (rt = rt0; rt && !(rt->rt6i_flags & RTF_EXPIRES); - rt = (struct rt6_info *)rt->dst.from); + for (rt = rt0; rt && !(rt->rt6i_flags & RTF_EXPIRES); rt = rt->from); if (rt && rt != rt0) rt0->dst.expires = rt->dst.expires; - dst_set_expires(&rt0->dst, timeout); rt0->rt6i_flags |= RTF_EXPIRES; } @@ -242,8 +245,8 @@ static inline u32 rt6_get_cookie(const struct rt6_info *rt) u32 cookie = 0; if (rt->rt6i_flags & RTF_PCPU || - (unlikely(!list_empty(&rt->rt6i_uncached)) && rt->dst.from)) - rt = (struct rt6_info *)(rt->dst.from); + (unlikely(!list_empty(&rt->rt6i_uncached)) && rt->from)) + rt = rt->from; rt6_get_cookie_safe(rt, &cookie); @@ -404,6 +407,7 @@ unsigned int fib6_tables_seq_read(struct net *net); int fib6_tables_dump(struct net *net, struct notifier_block *nb); void fib6_update_sernum(struct rt6_info *rt); +void fib6_update_sernum_upto_root(struct net *net, struct rt6_info *rt); #ifdef CONFIG_IPV6_MULTIPLE_TABLES int fib6_rules_init(void); diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 18e442ea93d8..27d23a65f3cd 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -66,6 +66,12 @@ static inline bool rt6_need_strict(const struct in6_addr *daddr) (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); } +static inline bool rt6_qualify_for_ecmp(const struct rt6_info *rt) +{ + return (rt->rt6i_flags & (RTF_GATEWAY|RTF_ADDRCONF|RTF_DYNAMIC)) == + RTF_GATEWAY; +} + void ip6_route_input(struct sk_buff *skb); struct dst_entry *ip6_route_input_lookup(struct net *net, struct net_device *dev, @@ -165,10 +171,13 @@ struct rt6_rtnl_dump_arg { }; int rt6_dump_route(struct rt6_info *rt, void *p_arg); -void rt6_ifdown(struct net *net, struct net_device *dev); void rt6_mtu_change(struct net_device *dev, unsigned int mtu); void rt6_remove_prefsrc(struct inet6_ifaddr *ifp); void rt6_clean_tohost(struct net *net, struct in6_addr *gateway); +void rt6_sync_up(struct net_device *dev, unsigned int nh_flags); +void rt6_disable_ip(struct net_device *dev, unsigned long event); +void rt6_sync_down_dev(struct net_device *dev, unsigned long event); +void rt6_multipath_rebalance(struct rt6_info *rt); static inline const struct rt6_info *skb_rt6_info(const struct sk_buff *skb) { diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index d66f70f63734..236e40ba06bf 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -36,6 +36,10 @@ struct __ip6_tnl_parm { __be32 o_key; __u32 fwmark; + __u32 index; /* ERSPAN type II index */ + __u8 erspan_ver; /* ERSPAN version */ + __u8 dir; /* direction */ + __u16 hwid; /* hwid */ }; /* IPv6 tunnel */ diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 24628f6b09bf..1f16773cfd76 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -116,8 +116,11 @@ struct ip_tunnel { u32 o_seqno; /* The last output seqno */ int tun_hlen; /* Precalculated header length */ - /* This field used only by ERSPAN */ + /* These four fields used only by ERSPAN */ u32 index; /* ERSPAN type II index */ + u8 erspan_ver; /* ERSPAN version */ + u8 dir; /* ERSPAN direction */ + u16 hwid; /* ERSPAN hardware ID */ struct dst_cache dst_cache; diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index ff68cf288f9b..eb0bec043c96 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -69,8 +69,7 @@ struct ip_vs_iphdr { }; static inline void *frag_safe_skb_hp(const struct sk_buff *skb, int offset, - int len, void *buffer, - const struct ip_vs_iphdr *ipvsh) + int len, void *buffer) { return skb_header_pointer(skb, offset, len, buffer); } diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 221238254eb7..8606c9113d3f 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -22,6 +22,7 @@ #include <net/flow.h> #include <net/flow_dissector.h> #include <net/snmp.h> +#include <net/netns/hash.h> #define SIN6_LEN_RFC2133 24 @@ -674,6 +675,22 @@ static inline bool ipv6_addr_v4mapped(const struct in6_addr *a) cpu_to_be32(0x0000ffff))) == 0UL; } +static inline u32 ipv6_portaddr_hash(const struct net *net, + const struct in6_addr *addr6, + unsigned int port) +{ + unsigned int hash, mix = net_hash_mix(net); + + if (ipv6_addr_any(addr6)) + hash = jhash_1word(0, mix); + else if (ipv6_addr_v4mapped(addr6)) + hash = jhash_1word((__force u32)addr6->s6_addr32[3], mix); + else + hash = jhash2((__force u32 *)addr6->s6_addr32, 4, mix); + + return hash ^ port; +} + /* * Check for a RFC 4843 ORCHID address * (Overlay Routable Cryptographic Hash Identifiers) @@ -953,6 +970,8 @@ static inline struct sk_buff *ip6_finish_skb(struct sock *sk) &inet6_sk(sk)->cork); } +unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst); + 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, diff --git a/include/net/mac80211.h b/include/net/mac80211.h index eec143cca1c0..906e90223066 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1552,6 +1552,9 @@ struct wireless_dev *ieee80211_vif_to_wdev(struct ieee80211_vif *vif); * @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. + * @IEEE80211_KEY_FLAG_PUT_MIC_SPACE: This flag should be set by the driver for + * a TKIP key if it only requires MIC space. Do not set together with + * @IEEE80211_KEY_FLAG_GENERATE_MMIC on the same key. */ enum ieee80211_key_flags { IEEE80211_KEY_FLAG_GENERATE_IV_MGMT = BIT(0), @@ -1562,6 +1565,7 @@ enum ieee80211_key_flags { IEEE80211_KEY_FLAG_PUT_IV_SPACE = BIT(5), IEEE80211_KEY_FLAG_RX_MGMT = BIT(6), IEEE80211_KEY_FLAG_RESERVE_TAILROOM = BIT(7), + IEEE80211_KEY_FLAG_PUT_MIC_SPACE = BIT(8), }; /** @@ -1593,8 +1597,8 @@ struct ieee80211_key_conf { u8 icv_len; u8 iv_len; u8 hw_key_idx; - u8 flags; s8 keyidx; + u16 flags; u8 keylen; u8 key[0]; }; @@ -2056,6 +2060,9 @@ struct ieee80211_txq { * The stack will not do fragmentation. * The callback for @set_frag_threshold should be set as well. * + * @IEEE80211_HW_SUPPORTS_TDLS_BUFFER_STA: Hardware supports buffer STA on + * TDLS links. + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -2098,6 +2105,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_TX_FRAG_LIST, IEEE80211_HW_REPORTS_LOW_ACK, IEEE80211_HW_SUPPORTS_TX_FRAG, + IEEE80211_HW_SUPPORTS_TDLS_BUFFER_STA, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 049008493faf..f306b2aa15a4 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -51,7 +51,7 @@ struct net { refcount_t passive; /* To decided when the network * namespace should be freed. */ - atomic_t count; /* To decided when the network + refcount_t count; /* To decided when the network * namespace should be shut down. */ spinlock_t rules_mod_lock; @@ -195,7 +195,7 @@ void __put_net(struct net *net); static inline struct net *get_net(struct net *net) { - atomic_inc(&net->count); + refcount_inc(&net->count); return net; } @@ -206,14 +206,14 @@ static inline struct net *maybe_get_net(struct net *net) * exists. If the reference count is zero this * function fails and returns NULL. */ - if (!atomic_inc_not_zero(&net->count)) + if (!refcount_inc_not_zero(&net->count)) net = NULL; return net; } static inline void put_net(struct net *net) { - if (atomic_dec_and_test(&net->count)) + if (refcount_dec_and_test(&net->count)) __put_net(net); } @@ -225,7 +225,7 @@ int net_eq(const struct net *net1, const struct net *net2) static inline int check_net(const struct net *net) { - return atomic_read(&net->count) != 0; + return refcount_read(&net->count) != 0; } void net_drop_ns(void *); diff --git a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h index 4ed1040bbe4a..73f825732326 100644 --- a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h +++ b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h @@ -13,17 +13,17 @@ const extern struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4; -extern struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4; -extern struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4; -extern struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp; +extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4; +extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4; +extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp; #ifdef CONFIG_NF_CT_PROTO_DCCP -extern struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4; +extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4; #endif #ifdef CONFIG_NF_CT_PROTO_SCTP -extern struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4; +extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4; #endif #ifdef CONFIG_NF_CT_PROTO_UDPLITE -extern struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4; +extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4; #endif int nf_conntrack_ipv4_compat_init(void); diff --git a/include/net/netfilter/ipv6/nf_conntrack_ipv6.h b/include/net/netfilter/ipv6/nf_conntrack_ipv6.h index 9cd55be95853..effa8dfba68c 100644 --- a/include/net/netfilter/ipv6/nf_conntrack_ipv6.h +++ b/include/net/netfilter/ipv6/nf_conntrack_ipv6.h @@ -4,17 +4,17 @@ extern const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6; -extern struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6; -extern struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6; -extern struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6; +extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6; +extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6; +extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6; #ifdef CONFIG_NF_CT_PROTO_DCCP -extern struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6; +extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6; #endif #ifdef CONFIG_NF_CT_PROTO_SCTP -extern struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6; +extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6; #endif #ifdef CONFIG_NF_CT_PROTO_UDPLITE -extern struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6; +extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6; #endif #include <linux/sysctl.h> diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h new file mode 100644 index 000000000000..adf8db44cf86 --- /dev/null +++ b/include/net/netfilter/nf_conntrack_count.h @@ -0,0 +1,17 @@ +#ifndef _NF_CONNTRACK_COUNT_H +#define _NF_CONNTRACK_COUNT_H + +struct nf_conncount_data; + +struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family, + unsigned int keylen); +void nf_conncount_destroy(struct net *net, unsigned int family, + struct nf_conncount_data *data); + +unsigned int nf_conncount_count(struct net *net, + struct nf_conncount_data *data, + const u32 *key, + unsigned int family, + const struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_zone *zone); +#endif diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 7ef56c13698a..a7220eef9aee 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -27,6 +27,9 @@ struct nf_conntrack_l4proto { /* Resolve clashes on insertion races. */ bool allow_clash; + /* protoinfo nlattr size, closes a hole */ + u16 nlattr_size; + /* Try to fill in the third arg: dataoff is offset past network protocol hdr. Return true if possible. */ bool (*pkt_to_tuple)(const struct sk_buff *skb, unsigned int dataoff, @@ -66,8 +69,6 @@ struct nf_conntrack_l4proto { /* convert protoinfo to nfnetink attributes */ int (*to_nlattr)(struct sk_buff *skb, struct nlattr *nla, struct nf_conn *ct); - /* Calculate protoinfo nlattr size */ - int (*nlattr_size)(void); /* convert nfnetlink attributes to protoinfo */ int (*from_nlattr)(struct nlattr *tb[], struct nf_conn *ct); @@ -80,8 +81,6 @@ struct nf_conntrack_l4proto { struct nf_conntrack_tuple *t); const struct nla_policy *nla_policy; - size_t nla_size; - #if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) struct { int (*nlattr_to_obj)(struct nlattr *tb[], @@ -109,7 +108,7 @@ struct nf_conntrack_l4proto { }; /* Existing built-in generic protocol */ -extern struct nf_conntrack_l4proto nf_conntrack_l4proto_generic; +extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic; #define MAX_NF_CT_PROTO 256 @@ -126,18 +125,18 @@ int nf_ct_l4proto_pernet_register_one(struct net *net, void nf_ct_l4proto_pernet_unregister_one(struct net *net, const struct nf_conntrack_l4proto *proto); int nf_ct_l4proto_pernet_register(struct net *net, - struct nf_conntrack_l4proto *const proto[], + const struct nf_conntrack_l4proto *const proto[], unsigned int num_proto); void nf_ct_l4proto_pernet_unregister(struct net *net, - struct nf_conntrack_l4proto *const proto[], + const struct nf_conntrack_l4proto *const proto[], unsigned int num_proto); /* Protocol global registration. */ -int nf_ct_l4proto_register_one(struct nf_conntrack_l4proto *proto); +int nf_ct_l4proto_register_one(const struct nf_conntrack_l4proto *proto); void nf_ct_l4proto_unregister_one(const struct nf_conntrack_l4proto *proto); -int nf_ct_l4proto_register(struct nf_conntrack_l4proto *proto[], +int nf_ct_l4proto_register(const struct nf_conntrack_l4proto * const proto[], unsigned int num_proto); -void nf_ct_l4proto_unregister(struct nf_conntrack_l4proto *proto[], +void nf_ct_l4proto_unregister(const struct nf_conntrack_l4proto * const proto[], unsigned int num_proto); /* Generic netlink helpers */ diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h new file mode 100644 index 000000000000..b22b22082733 --- /dev/null +++ b/include/net/netfilter/nf_flow_table.h @@ -0,0 +1,122 @@ +#ifndef _NF_FLOW_TABLE_H +#define _NF_FLOW_TABLE_H + +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/netdevice.h> +#include <linux/rhashtable.h> +#include <linux/rcupdate.h> +#include <net/dst.h> + +struct nf_flowtable; + +struct nf_flowtable_type { + struct list_head list; + int family; + void (*gc)(struct work_struct *work); + const struct rhashtable_params *params; + nf_hookfn *hook; + struct module *owner; +}; + +struct nf_flowtable { + struct rhashtable rhashtable; + const struct nf_flowtable_type *type; + struct delayed_work gc_work; +}; + +enum flow_offload_tuple_dir { + FLOW_OFFLOAD_DIR_ORIGINAL, + FLOW_OFFLOAD_DIR_REPLY, + __FLOW_OFFLOAD_DIR_MAX = FLOW_OFFLOAD_DIR_REPLY, +}; +#define FLOW_OFFLOAD_DIR_MAX (__FLOW_OFFLOAD_DIR_MAX + 1) + +struct flow_offload_tuple { + union { + struct in_addr src_v4; + struct in6_addr src_v6; + }; + union { + struct in_addr dst_v4; + struct in6_addr dst_v6; + }; + struct { + __be16 src_port; + __be16 dst_port; + }; + + int iifidx; + + u8 l3proto; + u8 l4proto; + u8 dir; + + int oifidx; + + struct dst_entry *dst_cache; +}; + +struct flow_offload_tuple_rhash { + struct rhash_head node; + struct flow_offload_tuple tuple; +}; + +#define FLOW_OFFLOAD_SNAT 0x1 +#define FLOW_OFFLOAD_DNAT 0x2 +#define FLOW_OFFLOAD_DYING 0x4 + +struct flow_offload { + struct flow_offload_tuple_rhash tuplehash[FLOW_OFFLOAD_DIR_MAX]; + u32 flags; + union { + /* Your private driver data here. */ + u32 timeout; + }; +}; + +#define NF_FLOW_TIMEOUT (30 * HZ) + +struct nf_flow_route { + struct { + struct dst_entry *dst; + int ifindex; + } tuple[FLOW_OFFLOAD_DIR_MAX]; +}; + +struct flow_offload *flow_offload_alloc(struct nf_conn *ct, + struct nf_flow_route *route); +void flow_offload_free(struct flow_offload *flow); + +int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow); +void flow_offload_del(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); +int nf_flow_table_iterate(struct nf_flowtable *flow_table, + void (*iter)(struct flow_offload *flow, void *data), + void *data); +void nf_flow_offload_work_gc(struct work_struct *work); +extern const struct rhashtable_params nf_flow_offload_rhash_params; + +void flow_offload_dead(struct flow_offload *flow); + +int nf_flow_snat_port(const struct flow_offload *flow, + struct sk_buff *skb, unsigned int thoff, + u8 protocol, enum flow_offload_tuple_dir dir); +int nf_flow_dnat_port(const struct flow_offload *flow, + struct sk_buff *skb, unsigned int thoff, + u8 protocol, enum flow_offload_tuple_dir dir); + +struct flow_ports { + __be16 source, dest; +}; + +unsigned int nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state); +unsigned int nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state); + +#define MODULE_ALIAS_NF_FLOWTABLE(family) \ + MODULE_ALIAS("nf-flowtable-" __stringify(family)) + +#endif /* _FLOW_OFFLOAD_H */ diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index 814058d0f167..a50a69f5334c 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -25,7 +25,7 @@ struct nf_queue_entry { struct nf_queue_handler { int (*outfn)(struct nf_queue_entry *entry, unsigned int queuenum); - unsigned int (*nf_hook_drop)(struct net *net); + void (*nf_hook_drop)(struct net *net); }; void nf_register_queue_handler(struct net *net, const struct nf_queue_handler *qh); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index fecc6112c768..663b015dace5 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -9,6 +9,7 @@ #include <linux/netfilter/x_tables.h> #include <linux/netfilter/nf_tables.h> #include <linux/u64_stats_sync.h> +#include <net/netfilter/nf_flow_table.h> #include <net/netlink.h> #define NFT_JUMP_STACK_SIZE 16 @@ -54,8 +55,8 @@ static inline void nft_set_pktinfo(struct nft_pktinfo *pkt, pkt->xt.state = state; } -static inline void nft_set_pktinfo_proto_unspec(struct nft_pktinfo *pkt, - struct sk_buff *skb) +static inline void nft_set_pktinfo_unspec(struct nft_pktinfo *pkt, + struct sk_buff *skb) { pkt->tprot_set = false; pkt->tprot = 0; @@ -63,14 +64,6 @@ static inline void nft_set_pktinfo_proto_unspec(struct nft_pktinfo *pkt, pkt->xt.fragoff = 0; } -static inline void nft_set_pktinfo_unspec(struct nft_pktinfo *pkt, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - nft_set_pktinfo(pkt, skb, state); - nft_set_pktinfo_proto_unspec(pkt, skb); -} - /** * struct nft_verdict - nf_tables verdict * @@ -150,22 +143,22 @@ static inline void nft_data_debug(const struct nft_data *data) * struct nft_ctx - nf_tables rule/set context * * @net: net namespace - * @afi: address family info * @table: the table the chain is contained in * @chain: the chain the rule is contained in * @nla: netlink attributes * @portid: netlink portID of the original message * @seq: netlink sequence number + * @family: protocol family * @report: notify via unicast netlink message */ struct nft_ctx { struct net *net; - struct nft_af_info *afi; struct nft_table *table; struct nft_chain *chain; const struct nlattr * const *nla; u32 portid; u32 seq; + u8 family; bool report; }; @@ -381,6 +374,7 @@ void nft_unregister_set(struct nft_set_type *type); * @list: table set list node * @bindings: list of set bindings * @name: name of the set + * @handle: unique handle of the set * @ktype: key type (numeric type defined by userspace, not used in the kernel) * @dtype: data type (verdict or numeric type defined by userspace) * @objtype: object type (see NFT_OBJECT_* definitions) @@ -403,6 +397,7 @@ struct nft_set { struct list_head list; struct list_head bindings; char *name; + u64 handle; u32 ktype; u32 dtype; u32 objtype; @@ -424,6 +419,11 @@ struct nft_set { __attribute__((aligned(__alignof__(u64)))); }; +static inline bool nft_set_is_anonymous(const struct nft_set *set) +{ + return set->flags & NFT_SET_ANONYMOUS; +} + static inline void *nft_set_priv(const struct nft_set *set) { return (void *)set->data; @@ -883,7 +883,7 @@ enum nft_chain_type { * @family: address family * @owner: module owner * @hook_mask: mask of valid hooks - * @hooks: hookfn overrides + * @hooks: array of hook functions */ struct nf_chain_type { const char *name; @@ -905,8 +905,6 @@ struct nft_stats { struct u64_stats_sync syncp; }; -#define NFT_HOOK_OPS_MAX 2 - /** * struct nft_base_chain - nf_tables base chain * @@ -918,7 +916,7 @@ struct nft_stats { * @dev_name: device name that this base chain is attached to (if any) */ struct nft_base_chain { - struct nf_hook_ops ops[NFT_HOOK_OPS_MAX]; + struct nf_hook_ops ops; const struct nf_chain_type *type; u8 policy; u8 flags; @@ -948,10 +946,13 @@ unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv); * @chains: chains in the table * @sets: sets in the table * @objects: stateful objects in the table + * @flowtables: flow tables in the table * @hgenerator: handle generator state + * @handle: table handle * @use: number of chain references to this table * @flags: table flag (see enum nft_table_flags) * @genmask: generation mask + * @afinfo: address family info * @name: name of the table */ struct nft_table { @@ -959,46 +960,16 @@ struct nft_table { struct list_head chains; struct list_head sets; struct list_head objects; + struct list_head flowtables; u64 hgenerator; + u64 handle; u32 use; - u16 flags:14, + u16 family:6, + flags:8, genmask:2; char *name; }; -enum nft_af_flags { - NFT_AF_NEEDS_DEV = (1 << 0), -}; - -/** - * struct nft_af_info - nf_tables address family info - * - * @list: used internally - * @family: address family - * @nhooks: number of hooks in this family - * @owner: module owner - * @tables: used internally - * @flags: family flags - * @nops: number of hook ops in this family - * @hook_ops_init: initialization function for chain hook ops - * @hooks: hookfn overrides for packet validation - */ -struct nft_af_info { - struct list_head list; - int family; - unsigned int nhooks; - struct module *owner; - struct list_head tables; - u32 flags; - unsigned int nops; - void (*hook_ops_init)(struct nf_hook_ops *, - unsigned int); - nf_hookfn *hooks[NF_MAX_HOOKS]; -}; - -int nft_register_afinfo(struct net *, struct nft_af_info *); -void nft_unregister_afinfo(struct net *, struct nft_af_info *); - int nft_register_chain_type(const struct nf_chain_type *); void nft_unregister_chain_type(const struct nf_chain_type *); @@ -1016,9 +987,9 @@ int nft_verdict_dump(struct sk_buff *skb, int type, * @name: name of this stateful object * @genmask: generation mask * @use: number of references to this stateful object - * @data: object data, layout depends on type + * @handle: unique object handle * @ops: object operations - * @data: pointer to object data + * @data: object data, layout depends on type */ struct nft_object { struct list_head list; @@ -1026,6 +997,7 @@ struct nft_object { struct nft_table *table; u32 genmask:2, use:30; + u64 handle; /* runtime data below here */ const struct nft_object_ops *ops ____cacheline_aligned; unsigned char data[] @@ -1097,6 +1069,46 @@ int nft_register_obj(struct nft_object_type *obj_type); void nft_unregister_obj(struct nft_object_type *obj_type); /** + * struct nft_flowtable - nf_tables flow table + * + * @list: flow table list node in table list + * @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 + * @handle: unique object handle + * @data: rhashtable and garbage collector + * @ops: array of hooks + */ +struct nft_flowtable { + struct list_head list; + 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 nf_flowtable data; +}; + +struct nft_flowtable *nf_tables_flowtable_lookup(const struct nft_table *table, + const struct nlattr *nla, + u8 genmask); +void nft_flow_table_iterate(struct net *net, + void (*iter)(struct nf_flowtable *flowtable, void *data), + void *data); + +void nft_register_flowtable_type(struct nf_flowtable_type *type); +void nft_unregister_flowtable_type(struct nf_flowtable_type *type); + +/** * struct nft_traceinfo - nft tracing information and state * * @pkt: pktinfo currently processed @@ -1125,12 +1137,6 @@ void nft_trace_init(struct nft_traceinfo *info, const struct nft_pktinfo *pkt, void nft_trace_notify(struct nft_traceinfo *info); -#define nft_dereference(p) \ - nfnl_dereference(p, NFNL_SUBSYS_NFTABLES) - -#define MODULE_ALIAS_NFT_FAMILY(family) \ - MODULE_ALIAS("nft-afinfo-" __stringify(family)) - #define MODULE_ALIAS_NFT_CHAIN(family, name) \ MODULE_ALIAS("nft-chain-" __stringify(family) "-" name) @@ -1332,4 +1338,11 @@ struct nft_trans_obj { #define nft_trans_obj(trans) \ (((struct nft_trans_obj *)trans->data)->obj) +struct nft_trans_flowtable { + struct nft_flowtable *flowtable; +}; + +#define nft_trans_flowtable(trans) \ + (((struct nft_trans_flowtable *)trans->data)->flowtable) + #endif /* _NET_NF_TABLES_H */ diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h index f0896ba456c4..ed7b511f0a59 100644 --- a/include/net/netfilter/nf_tables_ipv4.h +++ b/include/net/netfilter/nf_tables_ipv4.h @@ -5,15 +5,11 @@ #include <net/netfilter/nf_tables.h> #include <net/ip.h> -static inline void -nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt, - struct sk_buff *skb, - const struct nf_hook_state *state) +static inline void nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt, + struct sk_buff *skb) { struct iphdr *ip; - nft_set_pktinfo(pkt, skb, state); - ip = ip_hdr(pkt->skb); pkt->tprot_set = true; pkt->tprot = ip->protocol; @@ -21,10 +17,8 @@ nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt, pkt->xt.fragoff = ntohs(ip->frag_off) & IP_OFFSET; } -static inline int -__nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt, - struct sk_buff *skb, - const struct nf_hook_state *state) +static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt, + struct sk_buff *skb) { struct iphdr *iph, _iph; u32 len, thoff; @@ -52,16 +46,11 @@ __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt, return 0; } -static inline void -nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt, - struct sk_buff *skb, - const struct nf_hook_state *state) +static inline void nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt, + struct sk_buff *skb) { - nft_set_pktinfo(pkt, skb, state); - if (__nft_set_pktinfo_ipv4_validate(pkt, skb, state) < 0) - nft_set_pktinfo_proto_unspec(pkt, skb); + if (__nft_set_pktinfo_ipv4_validate(pkt, skb) < 0) + nft_set_pktinfo_unspec(pkt, skb); } -extern struct nft_af_info nft_af_ipv4; - #endif diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h index b8065b72f56e..dabe6fdb553a 100644 --- a/include/net/netfilter/nf_tables_ipv6.h +++ b/include/net/netfilter/nf_tables_ipv6.h @@ -5,20 +5,16 @@ #include <linux/netfilter_ipv6/ip6_tables.h> #include <net/ipv6.h> -static inline void -nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt, - struct sk_buff *skb, - const struct nf_hook_state *state) +static inline void nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt, + struct sk_buff *skb) { unsigned int flags = IP6_FH_F_AUTH; int protohdr, thoff = 0; unsigned short frag_off; - nft_set_pktinfo(pkt, skb, state); - protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags); if (protohdr < 0) { - nft_set_pktinfo_proto_unspec(pkt, skb); + nft_set_pktinfo_unspec(pkt, skb); return; } @@ -28,10 +24,8 @@ nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt, pkt->xt.fragoff = frag_off; } -static inline int -__nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt, - struct sk_buff *skb, - const struct nf_hook_state *state) +static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt, + struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IPV6) unsigned int flags = IP6_FH_F_AUTH; @@ -68,16 +62,11 @@ __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt, #endif } -static inline void -nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt, - struct sk_buff *skb, - const struct nf_hook_state *state) +static inline void nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt, + struct sk_buff *skb) { - nft_set_pktinfo(pkt, skb, state); - if (__nft_set_pktinfo_ipv6_validate(pkt, skb, state) < 0) - nft_set_pktinfo_proto_unspec(pkt, skb); + if (__nft_set_pktinfo_ipv6_validate(pkt, skb) < 0) + nft_set_pktinfo_unspec(pkt, skb); } -extern struct nft_af_info nft_af_ipv6; - #endif diff --git a/include/net/netns/can.h b/include/net/netns/can.h index ecf238b8862c..ca9bd9fba5b5 100644 --- a/include/net/netns/can.h +++ b/include/net/netns/can.h @@ -8,7 +8,7 @@ #include <linux/spinlock.h> -struct dev_rcv_lists; +struct can_dev_rcv_lists; struct s_stats; struct s_pstats; @@ -28,7 +28,7 @@ struct netns_can { #endif /* receive filters subscribed for 'all' CAN devices */ - struct dev_rcv_lists *can_rx_alldev_list; + struct can_dev_rcv_lists *can_rx_alldev_list; spinlock_t can_rcvlists_lock; struct timer_list can_stattimer;/* timer for statistics update */ struct s_stats *can_stats; /* packet statistics */ diff --git a/include/net/netns/core.h b/include/net/netns/core.h index 0ad4d0c71228..36c2d998a43c 100644 --- a/include/net/netns/core.h +++ b/include/net/netns/core.h @@ -11,7 +11,10 @@ struct netns_core { int sysctl_somaxconn; - struct prot_inuse __percpu *inuse; +#ifdef CONFIG_PROC_FS + int __percpu *sock_inuse; + struct prot_inuse __percpu *prot_inuse; +#endif }; #endif diff --git a/include/net/netns/netfilter.h b/include/net/netns/netfilter.h index cc00af2ac2d7..ca043342c0eb 100644 --- a/include/net/netns/netfilter.h +++ b/include/net/netns/netfilter.h @@ -17,7 +17,17 @@ struct netns_nf { #ifdef CONFIG_SYSCTL struct ctl_table_header *nf_log_dir_header; #endif - struct nf_hook_entries __rcu *hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; + struct nf_hook_entries __rcu *hooks_ipv4[NF_INET_NUMHOOKS]; + struct nf_hook_entries __rcu *hooks_ipv6[NF_INET_NUMHOOKS]; +#ifdef CONFIG_NETFILTER_FAMILY_ARP + struct nf_hook_entries __rcu *hooks_arp[NF_ARP_NUMHOOKS]; +#endif +#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE + struct nf_hook_entries __rcu *hooks_bridge[NF_INET_NUMHOOKS]; +#endif +#if IS_ENABLED(CONFIG_DECNET) + struct nf_hook_entries __rcu *hooks_decnet[NF_DN_NUMHOOKS]; +#endif #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) bool defrag_ipv4; #endif diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h index 4109b5f3010f..48134353411d 100644 --- a/include/net/netns/nftables.h +++ b/include/net/netns/nftables.h @@ -7,14 +7,8 @@ struct nft_af_info; struct netns_nftables { - struct list_head af_info; + struct list_head tables; struct list_head commit_list; - struct nft_af_info *ipv4; - struct nft_af_info *ipv6; - struct nft_af_info *inet; - struct nft_af_info *arp; - struct nft_af_info *bridge; - struct nft_af_info *netdev; unsigned int base_seq; u8 gencursor; }; diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h index ebc813277662..0db7fb3e4e15 100644 --- a/include/net/netns/sctp.h +++ b/include/net/netns/sctp.h @@ -122,9 +122,12 @@ struct netns_sctp { /* Flag to indicate if PR-CONFIG is enabled. */ int reconf_enable; - /* Flag to idicate if SCTP-AUTH is enabled */ + /* Flag to indicate if SCTP-AUTH is enabled */ int auth_enable; + /* Flag to indicate if stream interleave is enabled */ + int intl_enable; + /* * Policy to control SCTP IPv4 address scoping * 0 - Disable IPv4 address scoping diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 753ac9361154..87406252f0a3 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -29,6 +29,7 @@ struct tcf_block_ext_info { enum tcf_block_binder_type binder_type; tcf_chain_head_change_t *chain_head_change; void *chain_head_change_priv; + u32 block_index; }; struct tcf_block_cb; @@ -38,16 +39,25 @@ bool tcf_queue_work(struct work_struct *work); struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, bool create); void tcf_chain_put(struct tcf_chain *chain); +void tcf_block_netif_keep_dst(struct tcf_block *block); int tcf_block_get(struct tcf_block **p_block, - struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q); + struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q, + struct netlink_ext_ack *extack); int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, - struct tcf_block_ext_info *ei); + struct tcf_block_ext_info *ei, + struct netlink_ext_ack *extack); void tcf_block_put(struct tcf_block *block); void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, struct tcf_block_ext_info *ei); +static inline bool tcf_block_shared(struct tcf_block *block) +{ + return block->index; +} + static inline struct Qdisc *tcf_block_q(struct tcf_block *block) { + WARN_ON(tcf_block_shared(block)); return block->q; } @@ -77,14 +87,16 @@ int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, #else static inline int tcf_block_get(struct tcf_block **p_block, - struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q) + struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q, + struct netlink_ext_ack *extack) { return 0; } static inline int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, - struct tcf_block_ext_info *ei) + struct tcf_block_ext_info *ei, + struct netlink_ext_ack *extack) { return 0; } @@ -364,7 +376,8 @@ tcf_exts_exec(struct sk_buff *skb, struct tcf_exts *exts, int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, struct nlattr *rate_tlv, - struct tcf_exts *exts, bool ovr); + struct tcf_exts *exts, bool ovr, + struct netlink_ext_ack *extack); void tcf_exts_destroy(struct tcf_exts *exts); void tcf_exts_change(struct tcf_exts *dst, struct tcf_exts *src); int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts); @@ -544,13 +557,16 @@ static inline int tcf_valid_offset(const struct sk_buff *skb, #include <net/net_namespace.h> static inline int -tcf_change_indev(struct net *net, struct nlattr *indev_tlv) +tcf_change_indev(struct net *net, struct nlattr *indev_tlv, + struct netlink_ext_ack *extack) { char indev[IFNAMSIZ]; struct net_device *dev; - if (nla_strlcpy(indev, indev_tlv, IFNAMSIZ) >= IFNAMSIZ) + if (nla_strlcpy(indev, indev_tlv, IFNAMSIZ) >= IFNAMSIZ) { + NL_SET_ERR_MSG(extack, "Interface name too long"); return -EINVAL; + } dev = __dev_get_by_name(net, indev); if (!dev) return -ENODEV; @@ -586,17 +602,9 @@ struct tc_cls_common_offload { u32 chain_index; __be16 protocol; u32 prio; + struct netlink_ext_ack *extack; }; -static inline void -tc_cls_common_offload_init(struct tc_cls_common_offload *cls_common, - const struct tcf_proto *tp) -{ - cls_common->chain_index = tp->chain->index; - cls_common->protocol = tp->protocol; - cls_common->prio = tp->prio; -} - struct tc_cls_u32_knode { struct tcf_exts *exts; struct tc_u32_sel *sel; @@ -637,6 +645,31 @@ static inline bool tc_can_offload(const struct net_device *dev) return dev->features & NETIF_F_HW_TC; } +static inline bool tc_can_offload_extack(const struct net_device *dev, + struct netlink_ext_ack *extack) +{ + bool can = tc_can_offload(dev); + + if (!can) + NL_SET_ERR_MSG(extack, "TC offload is disabled on net device"); + + return can; +} + +static inline bool +tc_cls_can_offload_and_chain0(const struct net_device *dev, + struct tc_cls_common_offload *common) +{ + if (!tc_can_offload_extack(dev, common->extack)) + return false; + if (common->chain_index) { + NL_SET_ERR_MSG(common->extack, + "Driver supports only offload of chain 0"); + return false; + } + return true; +} + static inline bool tc_skip_hw(u32 flags) { return (flags & TCA_CLS_FLAGS_SKIP_HW) ? true : false; @@ -664,6 +697,18 @@ static inline bool tc_in_hw(u32 flags) return (flags & TCA_CLS_FLAGS_IN_HW) ? true : false; } +static inline void +tc_cls_common_offload_init(struct tc_cls_common_offload *cls_common, + const struct tcf_proto *tp, u32 flags, + struct netlink_ext_ack *extack) +{ + cls_common->chain_index = tp->chain->index; + cls_common->protocol = tp->protocol; + cls_common->prio = tp->prio; + if (tc_skip_sw(flags)) + cls_common->extack = extack; +} + enum tc_fl_command { TC_CLSFLOWER_REPLACE, TC_CLSFLOWER_DESTROY, @@ -706,7 +751,6 @@ struct tc_cls_bpf_offload { struct bpf_prog *oldprog; const char *name; bool exts_integrated; - u32 gen_flags; }; struct tc_mqprio_qopt_offload { @@ -727,6 +771,11 @@ struct tc_cookie { u32 len; }; +struct tc_qopt_offload_stats { + struct gnet_stats_basic_packed *bstats; + struct gnet_stats_queue *qstats; +}; + enum tc_red_command { TC_RED_REPLACE, TC_RED_DESTROY, @@ -739,9 +788,6 @@ struct tc_red_qopt_offload_params { u32 max; u32 probability; bool is_ecn; -}; -struct tc_red_qopt_offload_stats { - struct gnet_stats_basic_packed *bstats; struct gnet_stats_queue *qstats; }; @@ -751,9 +797,34 @@ struct tc_red_qopt_offload { u32 parent; union { struct tc_red_qopt_offload_params set; - struct tc_red_qopt_offload_stats stats; + struct tc_qopt_offload_stats stats; struct red_stats *xstats; }; }; +enum tc_prio_command { + TC_PRIO_REPLACE, + TC_PRIO_DESTROY, + TC_PRIO_STATS, +}; + +struct tc_prio_qopt_offload_params { + int bands; + u8 priomap[TC_PRIO_MAX + 1]; + /* In case that a prio qdisc is offloaded and now is changed to a + * non-offloadedable config, it needs to update the backlog & qlen + * values to negate the HW backlog & qlen values (and only them). + */ + struct gnet_stats_queue *qstats; +}; + +struct tc_prio_qopt_offload { + enum tc_prio_command command; + u32 handle; + u32 parent; + union { + struct tc_prio_qopt_offload_params replace_params; + struct tc_qopt_offload_stats stats; + }; +}; #endif diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index d1f413f06c72..815b92a23936 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -89,7 +89,8 @@ extern struct Qdisc_ops pfifo_head_drop_qdisc_ops; int fifo_set_limit(struct Qdisc *q, unsigned int limit); struct Qdisc *fifo_create_dflt(struct Qdisc *sch, struct Qdisc_ops *ops, - unsigned int limit); + unsigned int limit, + struct netlink_ext_ack *extack); int register_qdisc(struct Qdisc_ops *qops); int unregister_qdisc(struct Qdisc_ops *qops); @@ -99,22 +100,24 @@ int qdisc_set_default(const char *id); void qdisc_hash_add(struct Qdisc *q, bool invisible); void qdisc_hash_del(struct Qdisc *q); struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle); -struct Qdisc *qdisc_lookup_class(struct net_device *dev, u32 handle); struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, - struct nlattr *tab); + struct nlattr *tab, + struct netlink_ext_ack *extack); void qdisc_put_rtab(struct qdisc_rate_table *tab); void qdisc_put_stab(struct qdisc_size_table *tab); void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc); -int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, - struct net_device *dev, struct netdev_queue *txq, - spinlock_t *root_lock, bool validate); +bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, + struct net_device *dev, struct netdev_queue *txq, + spinlock_t *root_lock, bool validate); void __qdisc_run(struct Qdisc *q); static inline void qdisc_run(struct Qdisc *q) { - if (qdisc_run_begin(q)) + if (qdisc_run_begin(q)) { __qdisc_run(q); + qdisc_run_end(q); + } } static inline __be16 tc_skb_protocol(const struct sk_buff *skb) diff --git a/include/net/route.h b/include/net/route.h index d538e6db1afe..1eb9ce470e25 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -217,7 +217,7 @@ unsigned int inet_addr_type_dev_table(struct net *net, const struct net_device *dev, __be32 addr); void ip_rt_multicast_event(struct in_device *); -int ip_rt_ioctl(struct net *, unsigned int cmd, void __user *arg); +int ip_rt_ioctl(struct net *, unsigned int cmd, struct rtentry *rt); void ip_rt_get_source(u8 *src, struct sk_buff *skb, struct rtable *rt); struct rtable *rt_dst_alloc(struct net_device *dev, unsigned int flags, u16 type, diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index ead018744ff5..14b6b3af8918 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -13,10 +13,10 @@ enum rtnl_link_flags { RTNL_FLAG_DOIT_UNLOCKED = 1, }; -int __rtnl_register(int protocol, int msgtype, - rtnl_doit_func, rtnl_dumpit_func, unsigned int flags); void rtnl_register(int protocol, int msgtype, rtnl_doit_func, rtnl_dumpit_func, unsigned int flags); +int rtnl_register_module(struct module *owner, int protocol, int msgtype, + rtnl_doit_func, rtnl_dumpit_func, unsigned int flags); int rtnl_unregister(int protocol, int msgtype); void rtnl_unregister_all(int protocol); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index becf86aa4ac6..e2ab13687fb9 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -71,6 +71,7 @@ struct Qdisc { * qdisc_tree_decrease_qlen() should stop. */ #define TCQ_F_INVISIBLE 0x80 /* invisible by default in dump */ +#define TCQ_F_NOLOCK 0x100 /* qdisc does not require locking */ #define TCQ_F_OFFLOADED 0x200 /* qdisc is offloaded to HW */ u32 limit; const struct Qdisc_ops *ops; @@ -88,14 +89,14 @@ struct Qdisc { /* * For performance sake on SMP, we put highly modified fields at the end */ - struct sk_buff *gso_skb ____cacheline_aligned_in_smp; + struct sk_buff_head gso_skb ____cacheline_aligned_in_smp; struct qdisc_skb_head q; struct gnet_stats_basic_packed bstats; seqcount_t running; struct gnet_stats_queue qstats; unsigned long state; struct Qdisc *next_sched; - struct sk_buff *skb_bad_txq; + struct sk_buff_head skb_bad_txq; int padded; refcount_t refcnt; @@ -150,19 +151,23 @@ struct Qdisc_class_ops { /* Child qdisc manipulation */ struct netdev_queue * (*select_queue)(struct Qdisc *, struct tcmsg *); int (*graft)(struct Qdisc *, unsigned long cl, - struct Qdisc *, struct Qdisc **); + struct Qdisc *, struct Qdisc **, + struct netlink_ext_ack *extack); struct Qdisc * (*leaf)(struct Qdisc *, unsigned long cl); void (*qlen_notify)(struct Qdisc *, unsigned long); /* Class manipulation routines */ unsigned long (*find)(struct Qdisc *, u32 classid); int (*change)(struct Qdisc *, u32, u32, - struct nlattr **, unsigned long *); + struct nlattr **, unsigned long *, + struct netlink_ext_ack *); int (*delete)(struct Qdisc *, unsigned long); void (*walk)(struct Qdisc *, struct qdisc_walker * arg); /* Filter manipulation */ - struct tcf_block * (*tcf_block)(struct Qdisc *, unsigned long); + struct tcf_block * (*tcf_block)(struct Qdisc *sch, + unsigned long arg, + struct netlink_ext_ack *extack); unsigned long (*bind_tcf)(struct Qdisc *, unsigned long, u32 classid); void (*unbind_tcf)(struct Qdisc *, unsigned long); @@ -187,15 +192,26 @@ struct Qdisc_ops { struct sk_buff * (*dequeue)(struct Qdisc *); struct sk_buff * (*peek)(struct Qdisc *); - int (*init)(struct Qdisc *, struct nlattr *arg); + int (*init)(struct Qdisc *sch, struct nlattr *arg, + struct netlink_ext_ack *extack); void (*reset)(struct Qdisc *); void (*destroy)(struct Qdisc *); - int (*change)(struct Qdisc *, struct nlattr *arg); - void (*attach)(struct Qdisc *); + int (*change)(struct Qdisc *sch, + struct nlattr *arg, + struct netlink_ext_ack *extack); + void (*attach)(struct Qdisc *sch); + int (*change_tx_queue_len)(struct Qdisc *, unsigned int); int (*dump)(struct Qdisc *, struct sk_buff *); int (*dump_stats)(struct Qdisc *, struct gnet_dump *); + void (*ingress_block_set)(struct Qdisc *sch, + u32 block_index); + void (*egress_block_set)(struct Qdisc *sch, + u32 block_index); + u32 (*ingress_block_get)(struct Qdisc *sch); + u32 (*egress_block_get)(struct Qdisc *sch); + struct module *owner; }; @@ -218,14 +234,18 @@ struct tcf_proto_ops { const struct tcf_proto *, struct tcf_result *); int (*init)(struct tcf_proto*); - void (*destroy)(struct tcf_proto*); + void (*destroy)(struct tcf_proto *tp, + struct netlink_ext_ack *extack); void* (*get)(struct tcf_proto*, u32 handle); int (*change)(struct net *net, struct sk_buff *, struct tcf_proto*, unsigned long, u32 handle, struct nlattr **, - void **, bool); - int (*delete)(struct tcf_proto*, void *, bool*); + void **, bool, + struct netlink_ext_ack *); + int (*delete)(struct tcf_proto *tp, void *arg, + bool *last, + struct netlink_ext_ack *); void (*walk)(struct tcf_proto*, struct tcf_walker *arg); void (*bind_class)(void *, u32, unsigned long); @@ -247,8 +267,6 @@ struct tcf_proto { /* All the rest */ u32 prio; - u32 classid; - struct Qdisc *q; void *data; const struct tcf_proto_ops *ops; struct tcf_chain *chain; @@ -267,8 +285,7 @@ typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv); struct tcf_chain { struct tcf_proto __rcu *filter_chain; - tcf_chain_head_change_t *chain_head_change; - void *chain_head_change_priv; + struct list_head filter_chain_list; struct list_head list; struct tcf_block *block; u32 index; /* chain index */ @@ -277,12 +294,33 @@ struct tcf_chain { struct tcf_block { struct list_head chain_list; + u32 index; /* block index for shared blocks */ + unsigned int refcnt; struct net *net; struct Qdisc *q; struct list_head cb_list; - struct work_struct work; + struct list_head owner_list; + bool keep_dst; + unsigned int offloadcnt; /* Number of oddloaded filters */ + unsigned int nooffloaddevcnt; /* Number of devs unable to do offload */ }; +static inline void tcf_block_offload_inc(struct tcf_block *block, u32 *flags) +{ + if (*flags & TCA_CLS_FLAGS_IN_HW) + return; + *flags |= TCA_CLS_FLAGS_IN_HW; + block->offloadcnt++; +} + +static inline void tcf_block_offload_dec(struct tcf_block *block, u32 *flags) +{ + if (!(*flags & TCA_CLS_FLAGS_IN_HW)) + return; + *flags &= ~TCA_CLS_FLAGS_IN_HW; + block->offloadcnt--; +} + static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) { struct qdisc_skb_cb *qcb; @@ -291,11 +329,31 @@ static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) BUILD_BUG_ON(sizeof(qcb->data) < sz); } +static inline int qdisc_qlen_cpu(const struct Qdisc *q) +{ + return this_cpu_ptr(q->cpu_qstats)->qlen; +} + static inline int qdisc_qlen(const struct Qdisc *q) { return q->q.qlen; } +static inline int qdisc_qlen_sum(const struct Qdisc *q) +{ + __u32 qlen = 0; + int i; + + if (q->flags & TCQ_F_NOLOCK) { + for_each_possible_cpu(i) + qlen += per_cpu_ptr(q->cpu_qstats, i)->qlen; + } else { + qlen = q->q.qlen; + } + + return qlen; +} + static inline struct qdisc_skb_cb *qdisc_skb_cb(const struct sk_buff *skb) { return (struct qdisc_skb_cb *)skb->cb; @@ -432,6 +490,7 @@ void qdisc_class_hash_remove(struct Qdisc_class_hash *, void qdisc_class_hash_grow(struct Qdisc *, struct Qdisc_class_hash *); void qdisc_class_hash_destroy(struct Qdisc_class_hash *); +int dev_qdisc_change_tx_queue_len(struct net_device *dev); void dev_init_scheduler(struct net_device *dev); void dev_shutdown(struct net_device *dev); void dev_activate(struct net_device *dev); @@ -444,10 +503,12 @@ void qdisc_destroy(struct Qdisc *qdisc); void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n, unsigned int len); struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, - const struct Qdisc_ops *ops); + const struct Qdisc_ops *ops, + struct netlink_ext_ack *extack); void qdisc_free(struct Qdisc *qdisc); struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, - const struct Qdisc_ops *ops, u32 parentid); + const struct Qdisc_ops *ops, u32 parentid, + struct netlink_ext_ack *extack); void __qdisc_calculate_pkt_len(struct sk_buff *skb, const struct qdisc_size_table *stab); int skb_do_redirect(struct sk_buff *); @@ -633,12 +694,39 @@ static inline void qdisc_qstats_backlog_dec(struct Qdisc *sch, sch->qstats.backlog -= qdisc_pkt_len(skb); } +static inline void qdisc_qstats_cpu_backlog_dec(struct Qdisc *sch, + const struct sk_buff *skb) +{ + this_cpu_sub(sch->cpu_qstats->backlog, qdisc_pkt_len(skb)); +} + static inline void qdisc_qstats_backlog_inc(struct Qdisc *sch, const struct sk_buff *skb) { sch->qstats.backlog += qdisc_pkt_len(skb); } +static inline void qdisc_qstats_cpu_backlog_inc(struct Qdisc *sch, + const struct sk_buff *skb) +{ + this_cpu_add(sch->cpu_qstats->backlog, qdisc_pkt_len(skb)); +} + +static inline void qdisc_qstats_cpu_qlen_inc(struct Qdisc *sch) +{ + this_cpu_inc(sch->cpu_qstats->qlen); +} + +static inline void qdisc_qstats_cpu_qlen_dec(struct Qdisc *sch) +{ + this_cpu_dec(sch->cpu_qstats->qlen); +} + +static inline void qdisc_qstats_cpu_requeues_inc(struct Qdisc *sch) +{ + this_cpu_inc(sch->cpu_qstats->requeues); +} + static inline void __qdisc_qstats_drop(struct Qdisc *sch, int count) { sch->qstats.drops += count; @@ -769,26 +857,30 @@ static inline struct sk_buff *qdisc_peek_head(struct Qdisc *sch) /* generic pseudo peek method for non-work-conserving qdisc */ static inline struct sk_buff *qdisc_peek_dequeued(struct Qdisc *sch) { + struct sk_buff *skb = skb_peek(&sch->gso_skb); + /* we can reuse ->gso_skb because peek isn't called for root qdiscs */ - if (!sch->gso_skb) { - sch->gso_skb = sch->dequeue(sch); - if (sch->gso_skb) { + if (!skb) { + skb = sch->dequeue(sch); + + if (skb) { + __skb_queue_head(&sch->gso_skb, skb); /* it's still part of the queue */ - qdisc_qstats_backlog_inc(sch, sch->gso_skb); + qdisc_qstats_backlog_inc(sch, skb); sch->q.qlen++; } } - return sch->gso_skb; + return skb; } /* use instead of qdisc->dequeue() for all qdiscs queried with ->peek() */ static inline struct sk_buff *qdisc_dequeue_peeked(struct Qdisc *sch) { - struct sk_buff *skb = sch->gso_skb; + struct sk_buff *skb = skb_peek(&sch->gso_skb); if (skb) { - sch->gso_skb = NULL; + skb = __skb_dequeue(&sch->gso_skb); qdisc_qstats_backlog_dec(sch, skb); sch->q.qlen--; } else { @@ -846,6 +938,14 @@ static inline void rtnl_qdisc_drop(struct sk_buff *skb, struct Qdisc *sch) qdisc_qstats_drop(sch); } +static inline int qdisc_drop_cpu(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + __qdisc_drop(skb, to_free); + qdisc_qstats_cpu_drop(sch); + + return NET_XMIT_DROP; +} static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index deaafa9b09cb..20ff237c5eb2 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -145,12 +145,13 @@ SCTP_SUBTYPE_CONSTRUCTOR(OTHER, enum sctp_event_other, other) SCTP_SUBTYPE_CONSTRUCTOR(PRIMITIVE, enum sctp_event_primitive, primitive) -#define sctp_chunk_is_data(a) (a->chunk_hdr->type == SCTP_CID_DATA) +#define sctp_chunk_is_data(a) (a->chunk_hdr->type == SCTP_CID_DATA || \ + a->chunk_hdr->type == SCTP_CID_I_DATA) /* Calculate the actual data size in a data chunk */ -#define SCTP_DATA_SNDSIZE(c) ((int)((unsigned long)(c->chunk_end)\ - - (unsigned long)(c->chunk_hdr)\ - - sizeof(struct sctp_data_chunk))) +#define SCTP_DATA_SNDSIZE(c) ((int)((unsigned long)(c->chunk_end) - \ + (unsigned long)(c->chunk_hdr) - \ + sctp_datachk_len(&c->asoc->stream))) /* Internal error codes */ enum sctp_ierror { diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 608d123ef25f..f7ae6b0a21d0 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -116,7 +116,7 @@ extern struct percpu_counter sctp_sockets_allocated; int sctp_asconf_mgmt(struct sctp_sock *, struct sctp_sockaddr_entry *); struct sk_buff *sctp_skb_recv_datagram(struct sock *, int, int, int *); -int sctp_transport_walk_start(struct rhashtable_iter *iter); +void sctp_transport_walk_start(struct rhashtable_iter *iter); void sctp_transport_walk_stop(struct rhashtable_iter *iter); struct sctp_transport *sctp_transport_get_next(struct net *net, struct rhashtable_iter *iter); @@ -444,13 +444,13 @@ static inline int sctp_frag_point(const struct sctp_association *asoc, int pmtu) int frag = pmtu; frag -= sp->pf->af->net_header_len; - frag -= sizeof(struct sctphdr) + sizeof(struct sctp_data_chunk); + frag -= sizeof(struct sctphdr) + sctp_datachk_len(&asoc->stream); if (asoc->user_frag) frag = min_t(int, frag, asoc->user_frag); frag = SCTP_TRUNC4(min_t(int, frag, SCTP_MAX_CHUNK_LEN - - sizeof(struct sctp_data_chunk))); + sctp_datachk_len(&asoc->stream))); return frag; } diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index 70fb397f65b0..2883c43c5258 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -197,10 +197,14 @@ struct sctp_chunk *sctp_make_cookie_ack(const struct sctp_association *asoc, struct sctp_chunk *sctp_make_cwr(const struct sctp_association *asoc, const __u32 lowest_tsn, const struct sctp_chunk *chunk); -struct sctp_chunk *sctp_make_datafrag_empty(struct sctp_association *asoc, +struct sctp_chunk *sctp_make_idata(const struct sctp_association *asoc, + __u8 flags, int paylen, gfp_t gfp); +struct sctp_chunk *sctp_make_ifwdtsn(const struct sctp_association *asoc, + __u32 new_cum_tsn, size_t nstreams, + struct sctp_ifwdtsn_skip *skiplist); +struct sctp_chunk *sctp_make_datafrag_empty(const struct sctp_association *asoc, const struct sctp_sndrcvinfo *sinfo, - int len, const __u8 flags, - __u16 ssn, gfp_t gfp); + int len, __u8 flags, gfp_t gfp); struct sctp_chunk *sctp_make_ecne(const struct sctp_association *asoc, const __u32 lowest_tsn); struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc); @@ -342,7 +346,7 @@ static inline __u16 sctp_data_size(struct sctp_chunk *chunk) __u16 size; size = ntohs(chunk->chunk_hdr->length); - size -= sizeof(struct sctp_data_chunk); + size -= sctp_datahdr_len(&chunk->asoc->stream); return size; } @@ -358,6 +362,12 @@ static inline __u16 sctp_data_size(struct sctp_chunk *chunk) typecheck(__u32, b) && \ ((__s32)((a) - (b)) <= 0)) +/* Compare two MIDs */ +#define MID_lt(a, b) \ + (typecheck(__u32, a) && \ + typecheck(__u32, b) && \ + ((__s32)((a) - (b)) < 0)) + /* Compare two SSNs */ #define SSN_lt(a,b) \ (typecheck(__u16, a) && \ diff --git a/include/net/sctp/stream_interleave.h b/include/net/sctp/stream_interleave.h new file mode 100644 index 000000000000..6657711c8bc4 --- /dev/null +++ b/include/net/sctp/stream_interleave.h @@ -0,0 +1,61 @@ +/* SCTP kernel implementation + * (C) Copyright Red Hat Inc. 2017 + * + * These are definitions used by the stream schedulers, defined in RFC + * draft ndata (https://tools.ietf.org/html/draft-ietf-tsvwg-sctp-ndata-11) + * + * This SCTP implementation is free software; + * you can redistribute it and/or modify it under the terms of + * the GNU General Public License as published by + * the Free Software Foundation; either version 2, or (at your option) + * any later version. + * + * This SCTP implementation is distributed in the hope that it + * will be useful, but WITHOUT ANY WARRANTY; without even the implied + * ************************ + * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * See the GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. + * + * Please send any bug reports or fixes you make to the + * email addresses: + * lksctp developers <linux-sctp@vger.kernel.org> + * + * Written or modified by: + * Xin Long <lucien.xin@gmail.com> + */ + +#ifndef __sctp_stream_interleave_h__ +#define __sctp_stream_interleave_h__ + +struct sctp_stream_interleave { + __u16 data_chunk_len; + __u16 ftsn_chunk_len; + /* (I-)DATA process */ + struct sctp_chunk *(*make_datafrag)(const struct sctp_association *asoc, + const struct sctp_sndrcvinfo *sinfo, + int len, __u8 flags, gfp_t gfp); + void (*assign_number)(struct sctp_chunk *chunk); + bool (*validate_data)(struct sctp_chunk *chunk); + int (*ulpevent_data)(struct sctp_ulpq *ulpq, + struct sctp_chunk *chunk, gfp_t gfp); + int (*enqueue_event)(struct sctp_ulpq *ulpq, + struct sctp_ulpevent *event); + void (*renege_events)(struct sctp_ulpq *ulpq, + struct sctp_chunk *chunk, gfp_t gfp); + void (*start_pd)(struct sctp_ulpq *ulpq, gfp_t gfp); + void (*abort_pd)(struct sctp_ulpq *ulpq, gfp_t gfp); + /* (I-)FORWARD-TSN process */ + void (*generate_ftsn)(struct sctp_outq *q, __u32 ctsn); + bool (*validate_ftsn)(struct sctp_chunk *chunk); + void (*report_ftsn)(struct sctp_ulpq *ulpq, __u32 ftsn); + void (*handle_ftsn)(struct sctp_ulpq *ulpq, + struct sctp_chunk *chunk); +}; + +void sctp_stream_interleave_init(struct sctp_stream *stream); + +#endif /* __sctp_stream_interleave_h__ */ diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 9a5ccf03a59b..02369e379d35 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -89,6 +89,7 @@ struct sctp_stream; #include <net/sctp/tsnmap.h> #include <net/sctp/ulpevent.h> #include <net/sctp/ulpqueue.h> +#include <net/sctp/stream_interleave.h> /* Structures useful for managing bind/connect. */ @@ -217,6 +218,7 @@ struct sctp_sock { disable_fragments:1, v4mapped:1, frag_interleave:1, + strm_interleave:1, recvrcvinfo:1, recvnxtinfo:1, data_ready_signalled:1; @@ -397,6 +399,28 @@ void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new); #define sctp_ssn_skip(stream, type, sid, ssn) \ ((stream)->type[sid].ssn = ssn + 1) +/* What is the current MID number for this stream? */ +#define sctp_mid_peek(stream, type, sid) \ + ((stream)->type[sid].mid) + +/* Return the next MID number for this stream. */ +#define sctp_mid_next(stream, type, sid) \ + ((stream)->type[sid].mid++) + +/* Skip over this mid and all below. */ +#define sctp_mid_skip(stream, type, sid, mid) \ + ((stream)->type[sid].mid = mid + 1) + +#define sctp_stream_in(asoc, sid) (&(asoc)->stream.in[sid]) + +/* What is the current MID_uo number for this stream? */ +#define sctp_mid_uo_peek(stream, type, sid) \ + ((stream)->type[sid].mid_uo) + +/* Return the next MID_uo number for this stream. */ +#define sctp_mid_uo_next(stream, type, sid) \ + ((stream)->type[sid].mid_uo++) + /* * Pointers to address related SCTP functions. * (i.e. things that depend on the address family.) @@ -574,6 +598,8 @@ struct sctp_chunk { struct sctp_addiphdr *addip_hdr; struct sctp_fwdtsn_hdr *fwdtsn_hdr; struct sctp_authhdr *auth_hdr; + struct sctp_idatahdr *idata_hdr; + struct sctp_ifwdtsn_hdr *ifwdtsn_hdr; } subh; __u8 *chunk_end; @@ -620,6 +646,7 @@ struct sctp_chunk { __u16 rtt_in_progress:1, /* This chunk used for RTT calc? */ has_tsn:1, /* Does this chunk have a TSN yet? */ has_ssn:1, /* Does this chunk have a SSN yet? */ +#define has_mid has_ssn singleton:1, /* Only chunk in the packet? */ end_of_packet:1, /* Last chunk in the packet? */ ecn_ce_done:1, /* Have we processed the ECN CE bit? */ @@ -1073,6 +1100,7 @@ void sctp_retransmit_mark(struct sctp_outq *, struct sctp_transport *, __u8); void sctp_outq_uncork(struct sctp_outq *, gfp_t gfp); void sctp_prsctp_prune(struct sctp_association *asoc, struct sctp_sndrcvinfo *sinfo, int msg_len); +void sctp_generate_fwdtsn(struct sctp_outq *q, __u32 sack_ctsn); /* Uncork and flush an outqueue. */ static inline void sctp_outq_cork(struct sctp_outq *q) { @@ -1357,13 +1385,25 @@ struct sctp_stream_out_ext { }; struct sctp_stream_out { - __u16 ssn; - __u8 state; + union { + __u32 mid; + __u16 ssn; + }; + __u32 mid_uo; struct sctp_stream_out_ext *ext; + __u8 state; }; struct sctp_stream_in { - __u16 ssn; + union { + __u32 mid; + __u16 ssn; + }; + __u32 mid_uo; + __u32 fsn; + __u32 fsn_uo; + char pd_mode; + char pd_mode_uo; }; struct sctp_stream { @@ -1387,11 +1427,32 @@ struct sctp_stream { struct sctp_stream_out_ext *rr_next; }; }; + struct sctp_stream_interleave *si; }; #define SCTP_STREAM_CLOSED 0x00 #define SCTP_STREAM_OPEN 0x01 +static inline __u16 sctp_datachk_len(const struct sctp_stream *stream) +{ + return stream->si->data_chunk_len; +} + +static inline __u16 sctp_datahdr_len(const struct sctp_stream *stream) +{ + return stream->si->data_chunk_len - sizeof(struct sctp_chunkhdr); +} + +static inline __u16 sctp_ftsnchk_len(const struct sctp_stream *stream) +{ + return stream->si->ftsn_chunk_len; +} + +static inline __u16 sctp_ftsnhdr_len(const struct sctp_stream *stream) +{ + return stream->si->ftsn_chunk_len - sizeof(struct sctp_chunkhdr); +} + /* SCTP_GET_ASSOC_STATS counters */ struct sctp_priv_assoc_stats { /* Maximum observed rto in the association during subsequent @@ -1940,6 +2001,7 @@ struct sctp_association { __u8 need_ecne:1, /* Need to send an ECNE Chunk? */ temp:1, /* Is it a temporary association? */ force_delay:1, + intl_enable:1, prsctp_enable:1, reconf_enable:1; diff --git a/include/net/sctp/ulpevent.h b/include/net/sctp/ulpevent.h index 231dc42f1da6..51b4e0626c34 100644 --- a/include/net/sctp/ulpevent.h +++ b/include/net/sctp/ulpevent.h @@ -45,19 +45,29 @@ /* A structure to carry information to the ULP (e.g. Sockets API) */ /* Warning: This sits inside an skb.cb[] area. Be very careful of * growing this structure as it is at the maximum limit now. + * + * sctp_ulpevent is saved in sk->cb(48 bytes), whose last 4 bytes + * have been taken by sock_skb_cb, So here it has to use 'packed' + * to make sctp_ulpevent fit into the rest 44 bytes. */ struct sctp_ulpevent { struct sctp_association *asoc; struct sctp_chunk *chunk; unsigned int rmem_len; - __u32 ppid; + union { + __u32 mid; + __u16 ssn; + }; + union { + __u32 ppid; + __u32 fsn; + }; __u32 tsn; __u32 cumtsn; __u16 stream; - __u16 ssn; __u16 flags; __u16 msg_flags; -}; +} __packed; /* Retrieve the skb this event sits inside of. */ static inline struct sk_buff *sctp_event2skb(const struct sctp_ulpevent *ev) @@ -112,7 +122,8 @@ struct sctp_ulpevent *sctp_ulpevent_make_shutdown_event( struct sctp_ulpevent *sctp_ulpevent_make_pdapi( const struct sctp_association *asoc, - __u32 indication, gfp_t gfp); + __u32 indication, __u32 sid, __u32 seq, + __u32 flags, gfp_t gfp); struct sctp_ulpevent *sctp_ulpevent_make_adaptation_indication( const struct sctp_association *asoc, gfp_t gfp); @@ -140,6 +151,10 @@ struct sctp_ulpevent *sctp_ulpevent_make_stream_change_event( const struct sctp_association *asoc, __u16 flags, __u32 strchange_instrms, __u32 strchange_outstrms, gfp_t gfp); +struct sctp_ulpevent *sctp_make_reassembled_event( + struct net *net, struct sk_buff_head *queue, + struct sk_buff *f_frag, struct sk_buff *l_frag); + void sctp_ulpevent_read_sndrcvinfo(const struct sctp_ulpevent *event, struct msghdr *); void sctp_ulpevent_read_rcvinfo(const struct sctp_ulpevent *event, diff --git a/include/net/sctp/ulpqueue.h b/include/net/sctp/ulpqueue.h index e0dce07b8794..bb0ecba3db2b 100644 --- a/include/net/sctp/ulpqueue.h +++ b/include/net/sctp/ulpqueue.h @@ -45,6 +45,7 @@ struct sctp_ulpq { char pd_mode; struct sctp_association *asoc; struct sk_buff_head reasm; + struct sk_buff_head reasm_uo; struct sk_buff_head lobby; }; @@ -76,11 +77,8 @@ int sctp_clear_pd(struct sock *sk, struct sctp_association *asoc); void sctp_ulpq_skip(struct sctp_ulpq *ulpq, __u16 sid, __u16 ssn); void sctp_ulpq_reasm_flushtsn(struct sctp_ulpq *, __u32); -#endif /* __sctp_ulpqueue_h__ */ - - - - - +__u16 sctp_ulpq_renege_list(struct sctp_ulpq *ulpq, + struct sk_buff_head *list, __u16 needed); +#endif /* __sctp_ulpqueue_h__ */ diff --git a/include/net/sock.h b/include/net/sock.h index c47c635c9d19..63731289186a 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -72,6 +72,7 @@ #include <net/tcp_states.h> #include <linux/net_tstamp.h> #include <net/smc.h> +#include <net/l3mdev.h> /* * This structure really needs to be cleaned up. @@ -1262,6 +1263,7 @@ proto_memory_pressure(struct proto *prot) /* Called with local bh disabled */ void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc); int sock_prot_inuse_get(struct net *net, struct proto *proto); +int sock_inuse_get(struct net *net); #else static inline void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc) @@ -2335,31 +2337,6 @@ static inline bool sk_listener(const struct sock *sk) return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV); } -/** - * sk_state_load - read sk->sk_state for lockless contexts - * @sk: socket pointer - * - * Paired with sk_state_store(). Used in places we do not hold socket lock : - * tcp_diag_get_info(), tcp_get_info(), tcp_poll(), get_tcp4_sock() ... - */ -static inline int sk_state_load(const struct sock *sk) -{ - return smp_load_acquire(&sk->sk_state); -} - -/** - * sk_state_store - update sk->sk_state - * @sk: socket pointer - * @newstate: new state - * - * Paired with sk_state_load(). Should be used in contexts where - * state change might impact lockless readers. - */ -static inline void sk_state_store(struct sock *sk, int newstate) -{ - smp_store_release(&sk->sk_state, newstate); -} - void sock_enable_timestamp(struct sock *sk, int flag); int sock_get_timestamp(struct sock *, struct timeval __user *); int sock_get_timestampns(struct sock *, struct timespec __user *); @@ -2410,4 +2387,34 @@ static inline int sk_get_rmem0(const struct sock *sk, const struct proto *proto) return *proto->sysctl_rmem; } +/* Default TCP Small queue budget is ~1 ms of data (1sec >> 10) + * Some wifi drivers need to tweak it to get more chunks. + * They can use this helper from their ndo_start_xmit() + */ +static inline void sk_pacing_shift_update(struct sock *sk, int val) +{ + if (!sk || !sk_fullsock(sk) || sk->sk_pacing_shift == val) + return; + sk->sk_pacing_shift = val; +} + +/* if a socket is bound to a device, check that the given device + * index is either the same or that the socket is bound to an L3 + * master device and the given device index is also enslaved to + * that L3 master + */ +static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif) +{ + int mdif; + + if (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dif) + return true; + + mdif = l3mdev_master_ifindex_by_index(sock_net(sk), dif); + if (mdif && mdif == sk->sk_bound_dev_if) + return true; + + return false; +} + #endif /* _SOCK_H */ diff --git a/include/net/tc_act/tc_csum.h b/include/net/tc_act/tc_csum.h index 781f3433a0be..9470fd7e4350 100644 --- a/include/net/tc_act/tc_csum.h +++ b/include/net/tc_act/tc_csum.h @@ -6,10 +6,16 @@ #include <net/act_api.h> #include <linux/tc_act/tc_csum.h> +struct tcf_csum_params { + int action; + u32 update_flags; + struct rcu_head rcu; +}; + struct tcf_csum { struct tc_action common; - u32 update_flags; + struct tcf_csum_params __rcu *params; }; #define to_tcf_csum(a) ((struct tcf_csum *)a) @@ -24,7 +30,13 @@ static inline bool is_tcf_csum(const struct tc_action *a) static inline u32 tcf_csum_update_flags(const struct tc_action *a) { - return to_tcf_csum(a)->update_flags; + u32 update_flags; + + rcu_read_lock(); + update_flags = rcu_dereference(to_tcf_csum(a)->params)->update_flags; + rcu_read_unlock(); + + return update_flags; } #endif /* __NET_TC_CSUM_H */ diff --git a/include/net/tc_act/tc_mirred.h b/include/net/tc_act/tc_mirred.h index 21d253c9a8c6..a2e9cbca5c9e 100644 --- a/include/net/tc_act/tc_mirred.h +++ b/include/net/tc_act/tc_mirred.h @@ -8,10 +8,8 @@ struct tcf_mirred { struct tc_action common; int tcfm_eaction; - int tcfm_ifindex; bool tcfm_mac_header_xmit; struct net_device __rcu *tcfm_dev; - struct net *net; struct list_head tcfm_list; }; #define to_mirred(a) ((struct tcf_mirred *)a) @@ -34,9 +32,9 @@ static inline bool is_tcf_mirred_egress_mirror(const struct tc_action *a) return false; } -static inline int tcf_mirred_ifindex(const struct tc_action *a) +static inline struct net_device *tcf_mirred_dev(const struct tc_action *a) { - return to_mirred(a)->tcfm_ifindex; + return rtnl_dereference(to_mirred(a)->tcfm_dev); } #endif /* __NET_TC_MIR_H */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 50b21a49d870..58278669cc55 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -953,6 +953,7 @@ struct rate_sample { u32 prior_in_flight; /* in flight before this ACK */ bool is_app_limited; /* is sample from packet with bubble in pipe? */ bool is_retrans; /* is sample from retransmission? */ + bool is_ack_delayed; /* is this (likely) a delayed ACK? */ }; struct tcp_congestion_ops { @@ -1507,8 +1508,7 @@ int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, /* From tcp_fastopen.c */ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, - struct tcp_fastopen_cookie *cookie, int *syn_loss, - unsigned long *last_syn_loss); + struct tcp_fastopen_cookie *cookie); void tcp_fastopen_cache_set(struct sock *sk, u16 mss, struct tcp_fastopen_cookie *cookie, bool syn_lost, u16 try_exp); @@ -1546,7 +1546,7 @@ extern unsigned int sysctl_tcp_fastopen_blackhole_timeout; void tcp_fastopen_active_disable(struct sock *sk); bool tcp_fastopen_active_should_disable(struct sock *sk); void tcp_fastopen_active_disable_ofo_check(struct sock *sk); -void tcp_fastopen_active_timeout_reset(void); +void tcp_fastopen_active_detect_blackhole(struct sock *sk, bool expired); /* Latencies incurred by various limits for a sender. They are * chronograph-like stats that are mutually exclusive. @@ -2006,17 +2006,21 @@ void tcp_cleanup_ulp(struct sock *sk); * program loaded). */ #ifdef CONFIG_BPF -static inline int tcp_call_bpf(struct sock *sk, int op) +static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args) { struct bpf_sock_ops_kern sock_ops; int ret; - if (sk_fullsock(sk)) + memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); + if (sk_fullsock(sk)) { + sock_ops.is_fullsock = 1; sock_owned_by_me(sk); + } - memset(&sock_ops, 0, sizeof(sock_ops)); sock_ops.sk = sk; sock_ops.op = op; + if (nargs > 0) + memcpy(sock_ops.args, args, nargs * sizeof(*args)); ret = BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops); if (ret == 0) @@ -2025,18 +2029,46 @@ static inline int tcp_call_bpf(struct sock *sk, int op) ret = -1; return ret; } + +static inline int tcp_call_bpf_2arg(struct sock *sk, int op, u32 arg1, u32 arg2) +{ + u32 args[2] = {arg1, arg2}; + + return tcp_call_bpf(sk, op, 2, args); +} + +static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2, + u32 arg3) +{ + u32 args[3] = {arg1, arg2, arg3}; + + return tcp_call_bpf(sk, op, 3, args); +} + #else -static inline int tcp_call_bpf(struct sock *sk, int op) +static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args) { return -EPERM; } + +static inline int tcp_call_bpf_2arg(struct sock *sk, int op, u32 arg1, u32 arg2) +{ + return -EPERM; +} + +static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2, + u32 arg3) +{ + return -EPERM; +} + #endif static inline u32 tcp_timeout_init(struct sock *sk) { int timeout; - timeout = tcp_call_bpf(sk, BPF_SOCK_OPS_TIMEOUT_INIT); + timeout = tcp_call_bpf(sk, BPF_SOCK_OPS_TIMEOUT_INIT, 0, NULL); if (timeout <= 0) timeout = TCP_TIMEOUT_INIT; @@ -2047,7 +2079,7 @@ static inline u32 tcp_rwnd_init_bpf(struct sock *sk) { int rwnd; - rwnd = tcp_call_bpf(sk, BPF_SOCK_OPS_RWND_INIT); + rwnd = tcp_call_bpf(sk, BPF_SOCK_OPS_RWND_INIT, 0, NULL); if (rwnd < 0) rwnd = 0; @@ -2056,7 +2088,7 @@ static inline u32 tcp_rwnd_init_bpf(struct sock *sk) static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk) { - return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN) == 1); + return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN, 0, NULL) == 1); } #if IS_ENABLED(CONFIG_SMC) diff --git a/include/net/tls.h b/include/net/tls.h index 9185e53a743c..4913430ab807 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -36,6 +36,7 @@ #include <linux/types.h> #include <asm/byteorder.h> +#include <linux/crypto.h> #include <linux/socket.h> #include <linux/tcp.h> #include <net/tcp.h> @@ -57,6 +58,7 @@ struct tls_sw_context { struct crypto_aead *aead_send; + struct crypto_wait async_wait; /* Sending context */ char aad_space[TLS_AAD_SPACE_SIZE]; diff --git a/include/net/vxlan.h b/include/net/vxlan.h index f96391e84a8a..ad73d8b3fcc2 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -301,7 +301,7 @@ static inline netdev_features_t vxlan_features_check(struct sk_buff *skb, l4_hdr = ipv6_hdr(skb)->nexthdr; break; default: - return features;; + return features; } if ((l4_hdr == IPPROTO_UDP) && diff --git a/include/net/wext.h b/include/net/wext.h index e51f067fdb3a..aa192a670304 100644 --- a/include/net/wext.h +++ b/include/net/wext.h @@ -7,7 +7,7 @@ struct net; #ifdef CONFIG_WEXT_CORE -int wext_handle_ioctl(struct net *net, struct iwreq *iwr, unsigned int cmd, +int wext_handle_ioctl(struct net *net, unsigned int cmd, void __user *arg); int compat_wext_handle_ioctl(struct net *net, unsigned int cmd, unsigned long arg); @@ -15,7 +15,7 @@ int compat_wext_handle_ioctl(struct net *net, unsigned int cmd, struct iw_statistics *get_wireless_stats(struct net_device *dev); int call_commit_handler(struct net_device *dev); #else -static inline int wext_handle_ioctl(struct net *net, struct iwreq *iwr, unsigned int cmd, +static inline int wext_handle_ioctl(struct net *net, unsigned int cmd, void __user *arg) { return -EINVAL; diff --git a/include/net/xdp.h b/include/net/xdp.h new file mode 100644 index 000000000000..b2362ddfa694 --- /dev/null +++ b/include/net/xdp.h @@ -0,0 +1,48 @@ +/* include/net/xdp.h + * + * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc. + * Released under terms in GPL version 2. See COPYING. + */ +#ifndef __LINUX_NET_XDP_H__ +#define __LINUX_NET_XDP_H__ + +/** + * DOC: XDP RX-queue information + * + * The XDP RX-queue info (xdp_rxq_info) is associated with the driver + * level RX-ring queues. It is information that is specific to how + * the driver have configured a given RX-ring queue. + * + * Each xdp_buff frame received in the driver carry a (pointer) + * reference to this xdp_rxq_info structure. This provides the XDP + * data-path read-access to RX-info for both kernel and bpf-side + * (limited subset). + * + * For now, direct access is only safe while running in NAPI/softirq + * context. Contents is read-mostly and must not be updated during + * driver NAPI/softirq poll. + * + * The driver usage API is a register and unregister API. + * + * The struct is not directly tied to the XDP prog. A new XDP prog + * can be attached as long as it doesn't change the underlying + * RX-ring. If the RX-ring does change significantly, the NIC driver + * naturally need to stop the RX-ring before purging and reallocating + * memory. In that process the driver MUST call unregistor (which + * also apply for driver shutdown and unload). The register API is + * also mandatory during RX-ring setup. + */ + +struct xdp_rxq_info { + struct net_device *dev; + u32 queue_index; + u32 reg_state; +} ____cacheline_aligned; /* perf critical, avoid false-sharing */ + +int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, + struct net_device *dev, u32 queue_index); +void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq); +void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq); +bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq); + +#endif /* __LINUX_NET_XDP_H__ */ diff --git a/include/net/xfrm.h b/include/net/xfrm.h index ae35991b5877..7d2077665c0b 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -968,7 +968,7 @@ static inline bool xfrm_sec_ctx_match(struct xfrm_sec_ctx *s1, struct xfrm_sec_c /* A struct encoding bundle of transformations to apply to some set of flow. * - * dst->child points to the next element of bundle. + * xdst->child points to the next element of bundle. * dst->xfrm points to an instanse of transformer. * * Due to unfortunate limitations of current routing cache, which we @@ -984,6 +984,8 @@ struct xfrm_dst { struct rt6_info rt6; } u; struct dst_entry *route; + struct dst_entry *child; + struct dst_entry *path; struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; int num_pols, num_xfrms; u32 xfrm_genid; @@ -994,7 +996,35 @@ struct xfrm_dst { u32 path_cookie; }; +static inline struct dst_entry *xfrm_dst_path(const struct dst_entry *dst) +{ +#ifdef CONFIG_XFRM + if (dst->xfrm) { + const struct xfrm_dst *xdst = (const struct xfrm_dst *) dst; + + return xdst->path; + } +#endif + return (struct dst_entry *) dst; +} + +static inline struct dst_entry *xfrm_dst_child(const struct dst_entry *dst) +{ +#ifdef CONFIG_XFRM + if (dst->xfrm) { + struct xfrm_dst *xdst = (struct xfrm_dst *) dst; + return xdst->child; + } +#endif + return NULL; +} + #ifdef CONFIG_XFRM +static inline void xfrm_dst_set_child(struct xfrm_dst *xdst, struct dst_entry *child) +{ + xdst->child = child; +} + static inline void xfrm_dst_destroy(struct xfrm_dst *xdst) { xfrm_pols_put(xdst->pols, xdst->num_pols); @@ -1021,6 +1051,7 @@ struct xfrm_offload { #define XFRM_GSO_SEGMENT 16 #define XFRM_GRO 32 #define XFRM_ESP_NO_TRAILER 64 +#define XFRM_DEV_RESUME 128 __u32 status; #define CRYPTO_SUCCESS 1 @@ -1847,34 +1878,53 @@ static inline struct xfrm_state *xfrm_input_state(struct sk_buff *skb) { return skb->sp->xvec[skb->sp->len - 1]; } +#endif + static inline struct xfrm_offload *xfrm_offload(struct sk_buff *skb) { +#ifdef CONFIG_XFRM struct sec_path *sp = skb->sp; if (!sp || !sp->olen || sp->len != sp->olen) return NULL; return &sp->ovec[sp->olen - 1]; -} +#else + return NULL; #endif +} void __net_init xfrm_dev_init(void); #ifdef CONFIG_XFRM_OFFLOAD -int validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features); +void xfrm_dev_resume(struct sk_buff *skb); +void xfrm_dev_backlog(struct softnet_data *sd); +struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features, bool *again); int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, struct xfrm_user_offload *xuo); bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x); +static inline void xfrm_dev_state_advance_esn(struct xfrm_state *x) +{ + struct xfrm_state_offload *xso = &x->xso; + + if (xso->dev && xso->dev->xfrmdev_ops->xdo_dev_state_advance_esn) + xso->dev->xfrmdev_ops->xdo_dev_state_advance_esn(x); +} + static inline bool xfrm_dst_offload_ok(struct dst_entry *dst) { struct xfrm_state *x = dst->xfrm; + struct xfrm_dst *xdst; if (!x || !x->type_offload) return false; - if (x->xso.offload_handle && (x->xso.dev == dst->path->dev) && - !dst->child->xfrm) + xdst = (struct xfrm_dst *) dst; + if (!x->xso.offload_handle && !xdst->child->xfrm) + return true; + if (x->xso.offload_handle && (x->xso.dev == xfrm_dst_path(dst)->dev) && + !xdst->child->xfrm) return true; return false; @@ -1894,15 +1944,24 @@ static inline void xfrm_dev_state_free(struct xfrm_state *x) struct net_device *dev = xso->dev; if (dev && dev->xfrmdev_ops) { - dev->xfrmdev_ops->xdo_dev_state_free(x); + if (dev->xfrmdev_ops->xdo_dev_state_free) + dev->xfrmdev_ops->xdo_dev_state_free(x); xso->dev = NULL; dev_put(dev); } } #else -static inline int validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features) +static inline void xfrm_dev_resume(struct sk_buff *skb) { - return 0; +} + +static inline void xfrm_dev_backlog(struct softnet_data *sd) +{ +} + +static inline struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features, bool *again) +{ + return skb; } static inline int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, struct xfrm_user_offload *xuo) @@ -1923,6 +1982,10 @@ static inline bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x return false; } +static inline void xfrm_dev_state_advance_esn(struct xfrm_state *x) +{ +} + static inline bool xfrm_dst_offload_ok(struct dst_entry *dst) { return false; |