From 6e116280b41b0cbfd90dfe9fa66e07ff348d50d5 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Mon, 25 Jul 2022 10:51:30 +0200 Subject: net: netfilter: Remove ifdefs for code shared by BPF and ctnetlink The current ifdefry for code shared by the BPF and ctnetlink side looks ugly. As per Pablo's request, simplify this by unconditionally compiling in the code. This can be revisited when the shared code between the two grows further. Suggested-by: Pablo Neira Ayuso Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20220725085130.11553-1-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/net/netfilter/nf_conntrack_core.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/net') diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 3cd3a6e631aa..b2b9de70d9f4 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -86,10 +86,6 @@ extern spinlock_t nf_conntrack_expect_lock; /* ctnetlink code shared by both ctnetlink and nf_conntrack_bpf */ -#if (IS_BUILTIN(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \ - (IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES) || \ - IS_ENABLED(CONFIG_NF_CT_NETLINK)) - static inline void __nf_ct_set_timeout(struct nf_conn *ct, u64 timeout) { if (timeout > INT_MAX) @@ -101,6 +97,4 @@ int __nf_ct_change_timeout(struct nf_conn *ct, u64 cta_timeout); void __nf_ct_change_status(struct nf_conn *ct, unsigned long on, unsigned long off); int nf_ct_change_status_common(struct nf_conn *ct, unsigned int status); -#endif - #endif /* _NF_CONNTRACK_CORE_H */ -- cgit v1.2.3 From 52327d2e3996f2cac7df6de02623fd8d80fb4c85 Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Mon, 15 Aug 2022 11:04:17 +0800 Subject: net: sched: remove the unused return value of unregister_qdisc Return value of unregister_qdisc is unused, remove it. Signed-off-by: Zhengchao Shao Link: https://lore.kernel.org/r/20220815030417.271894-1-shaozhengchao@huawei.com Signed-off-by: Jakub Kicinski --- include/net/pkt_sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 3372a1f67cf4..29f65632ebc5 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -100,7 +100,7 @@ struct Qdisc *fifo_create_dflt(struct Qdisc *sch, struct Qdisc_ops *ops, struct netlink_ext_ack *extack); int register_qdisc(struct Qdisc_ops *qops); -int unregister_qdisc(struct Qdisc_ops *qops); +void unregister_qdisc(struct Qdisc_ops *qops); void qdisc_get_default(char *id, size_t len); int qdisc_set_default(const char *id); -- cgit v1.2.3 From 24426654ed3ae83d1127511891fb782c54f49203 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 16 Aug 2022 23:17:17 -0700 Subject: bpf: net: Avoid sk_setsockopt() taking sk lock when called from bpf Most of the code in bpf_setsockopt(SOL_SOCKET) are duplicated from the sk_setsockopt(). The number of supported optnames are increasing ever and so as the duplicated code. One issue in reusing sk_setsockopt() is that the bpf prog has already acquired the sk lock. This patch adds a has_current_bpf_ctx() to tell if the sk_setsockopt() is called from a bpf prog. The bpf prog calling bpf_setsockopt() is either running in_task() or in_serving_softirq(). Both cases have the current->bpf_ctx initialized. Thus, the has_current_bpf_ctx() only needs to test !!current->bpf_ctx. This patch also adds sockopt_{lock,release}_sock() helpers for sk_setsockopt() to use. These helpers will test has_current_bpf_ctx() before acquiring/releasing the lock. They are in EXPORT_SYMBOL for the ipv6 module to use in a latter patch. Note on the change in sock_setbindtodevice(). sockopt_lock_sock() is done in sock_setbindtodevice() instead of doing the lock_sock in sock_bindtoindex(..., lock_sk = true). Reviewed-by: Stanislav Fomichev Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20220817061717.4175589-1-kafai@fb.com Signed-off-by: Alexei Starovoitov --- include/net/sock.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index 05a1bbdf5805..352b9458fdc6 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1749,6 +1749,9 @@ static inline void unlock_sock_fast(struct sock *sk, bool slow) } } +void sockopt_lock_sock(struct sock *sk); +void sockopt_release_sock(struct sock *sk); + /* Used by processes to "lock" a socket state, so that * interrupts and bottom half handlers won't change it * from under us. It essentially blocks any incoming -- cgit v1.2.3 From e42c7beee71d0d84a6193357e3525d0cf2a3e168 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 16 Aug 2022 23:17:23 -0700 Subject: bpf: net: Consider has_current_bpf_ctx() when testing capable() in sk_setsockopt() When bpf program calling bpf_setsockopt(SOL_SOCKET), it could be run in softirq and doesn't make sense to do the capable check. There was a similar situation in bpf_setsockopt(TCP_CONGESTION). In commit 8d650cdedaab ("tcp: fix tcp_set_congestion_control() use from bpf hook"), tcp_set_congestion_control(..., cap_net_admin) was added to skip the cap check for bpf prog. This patch adds sockopt_ns_capable() and sockopt_capable() for the sk_setsockopt() to use. They will consider the has_current_bpf_ctx() before doing the ns_capable() and capable() test. They are in EXPORT_SYMBOL for the ipv6 module to use in a latter patch. Suggested-by: Stanislav Fomichev Reviewed-by: Stanislav Fomichev Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20220817061723.4175820-1-kafai@fb.com Signed-off-by: Alexei Starovoitov --- include/net/sock.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index 352b9458fdc6..13089d88a2e2 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1751,6 +1751,8 @@ static inline void unlock_sock_fast(struct sock *sk, bool slow) void sockopt_lock_sock(struct sock *sk); void sockopt_release_sock(struct sock *sk); +bool sockopt_ns_capable(struct user_namespace *ns, int cap); +bool sockopt_capable(int cap); /* Used by processes to "lock" a socket state, so that * interrupts and bottom half handlers won't change it -- cgit v1.2.3 From 29003875bd5bab262a29d1c6e76a2124bd07e4c2 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 16 Aug 2022 23:18:04 -0700 Subject: bpf: Change bpf_setsockopt(SOL_SOCKET) to reuse sk_setsockopt() After the prep work in the previous patches, this patch removes most of the dup code from bpf_setsockopt(SOL_SOCKET) and reuses them from sk_setsockopt(). The sock ptr test is added to the SO_RCVLOWAT because the sk->sk_socket could be NULL in some of the bpf hooks. The existing optname white-list is refactored into a new function sol_socket_setsockopt(). Reviewed-by: Stanislav Fomichev Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20220817061804.4178920-1-kafai@fb.com Signed-off-by: Alexei Starovoitov --- include/net/sock.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index 13089d88a2e2..ee44b424d952 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1828,6 +1828,8 @@ void sock_pfree(struct sk_buff *skb); #define sock_edemux sock_efree #endif +int sk_setsockopt(struct sock *sk, int level, int optname, + sockptr_t optval, unsigned int optlen); int sock_setsockopt(struct socket *sock, int level, int op, sockptr_t optval, unsigned int optlen); -- cgit v1.2.3 From 0c751f7071ef98d334ed06ca3f8f4cc1f7458cf5 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 16 Aug 2022 23:18:19 -0700 Subject: bpf: Change bpf_setsockopt(SOL_TCP) to reuse do_tcp_setsockopt() After the prep work in the previous patches, this patch removes all the dup code from bpf_setsockopt(SOL_TCP) and reuses the do_tcp_setsockopt(). The existing optname white-list is refactored into a new function sol_tcp_setsockopt(). The sol_tcp_setsockopt() also calls the bpf_sol_tcp_setsockopt() to handle the TCP_BPF_XXX specific optnames. bpf_setsockopt(TCP_SAVE_SYN) now also allows a value 2 to save the eth header also and it comes for free from do_tcp_setsockopt(). Reviewed-by: Stanislav Fomichev Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20220817061819.4180146-1-kafai@fb.com Signed-off-by: Alexei Starovoitov --- include/net/tcp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index d10962b9f0d0..c03a50c72f40 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -405,6 +405,8 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); bool tcp_bpf_bypass_getsockopt(int level, int optname); +int do_tcp_setsockopt(struct sock *sk, int level, int optname, + sockptr_t optval, unsigned int optlen); int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); void tcp_set_keepalive(struct sock *sk, int val); -- cgit v1.2.3 From ee7f1e1302f5cb29168f70827c12855f1d8c9845 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 16 Aug 2022 23:18:26 -0700 Subject: bpf: Change bpf_setsockopt(SOL_IP) to reuse do_ip_setsockopt() After the prep work in the previous patches, this patch removes the dup code from bpf_setsockopt(SOL_IP) and reuses the implementation in do_ip_setsockopt(). The existing optname white-list is refactored into a new function sol_ip_setsockopt(). NOTE, the current bpf_setsockopt(IP_TOS) is quite different from the the do_ip_setsockopt(IP_TOS). For example, it does not take the INET_ECN_MASK into the account for tcp and also does not adjust sk->sk_priority. It looks like the current bpf_setsockopt(IP_TOS) was referencing the IPV6_TCLASS implementation instead of IP_TOS. This patch tries to rectify that by using the do_ip_setsockopt(IP_TOS). While this is a behavior change, the do_ip_setsockopt(IP_TOS) behavior is arguably what the user is expecting. At least, the INET_ECN_MASK bits should be masked out for tcp. Reviewed-by: Stanislav Fomichev Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20220817061826.4180990-1-kafai@fb.com Signed-off-by: Alexei Starovoitov --- include/net/ip.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/ip.h b/include/net/ip.h index 1c979fd1904c..34fa5b0f0a0e 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -743,6 +743,8 @@ void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk, int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, bool allow_ipv6); DECLARE_STATIC_KEY_FALSE(ip4_min_ttl); +int do_ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, + unsigned int optlen); int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, -- cgit v1.2.3 From 75b64b68ee3f9fe90ad8f21e5c5c92de58abf725 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 16 Aug 2022 23:18:34 -0700 Subject: bpf: Change bpf_setsockopt(SOL_IPV6) to reuse do_ipv6_setsockopt() After the prep work in the previous patches, this patch removes the dup code from bpf_setsockopt(SOL_IPV6) and reuses the implementation in do_ipv6_setsockopt(). ipv6 could be compiled as a module. Like how other code solved it with stubs in ipv6_stubs.h, this patch adds the do_ipv6_setsockopt to the ipv6_bpf_stub. The current bpf_setsockopt(IPV6_TCLASS) does not take the INET_ECN_MASK into the account for tcp. The do_ipv6_setsockopt(IPV6_TCLASS) will handle it correctly. The existing optname white-list is refactored into a new function sol_ipv6_setsockopt(). After this last SOL_IPV6 dup code removal, the __bpf_setsockopt() is simplified enough that the extra "{ }" around the if statement can be removed. Reviewed-by: Stanislav Fomichev Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20220817061834.4181198-1-kafai@fb.com Signed-off-by: Alexei Starovoitov --- include/net/ipv6.h | 2 ++ include/net/ipv6_stubs.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/net') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index de9dcc5652c4..c110d9032083 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1156,6 +1156,8 @@ struct in6_addr *fl6_update_dst(struct flowi6 *fl6, */ DECLARE_STATIC_KEY_FALSE(ip6_min_hopcount); +int do_ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, + unsigned int optlen); int ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int ipv6_getsockopt(struct sock *sk, int level, int optname, diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index 45e0339be6fa..8692698b01cf 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -81,6 +81,8 @@ struct ipv6_bpf_stub { const struct in6_addr *daddr, __be16 dport, int dif, int sdif, struct udp_table *tbl, struct sk_buff *skb); + int (*ipv6_setsockopt)(struct sock *sk, int level, int optname, + sockptr_t optval, unsigned int optlen); }; extern const struct ipv6_bpf_stub *ipv6_bpf_stub __read_mostly; -- cgit v1.2.3 From 5d81757835859760a38a54a87eff856d4e578836 Mon Sep 17 00:00:00 2001 From: Emeel Hakim Date: Thu, 18 Aug 2022 18:32:30 +0300 Subject: net: macsec: Expose MACSEC_SALT_LEN definition to user space Expose MACSEC_SALT_LEN definition to user space to be used in various user space applications such as iproute. Iproute will use this as part of adding macsec extended packet number support. Reviewed-by: Raed Salem Reviewed-by: Sabrina Dubroca Signed-off-by: Emeel Hakim Link: https://lore.kernel.org/r/20220818153229.4721-1-ehakim@nvidia.com Signed-off-by: Jakub Kicinski --- include/net/macsec.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/net') diff --git a/include/net/macsec.h b/include/net/macsec.h index d6fa6b97f6ef..73780aa73644 100644 --- a/include/net/macsec.h +++ b/include/net/macsec.h @@ -14,7 +14,6 @@ #define MACSEC_DEFAULT_PN_LEN 4 #define MACSEC_XPN_PN_LEN 8 -#define MACSEC_SALT_LEN 12 #define MACSEC_NUM_AN 4 /* 2 bits for the association number */ typedef u64 __bitwise sci_t; -- cgit v1.2.3 From 1202cdd665315c525b5237e96e0bedc76d7e754f Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Wed, 17 Aug 2022 17:43:21 -0700 Subject: Remove DECnet support from kernel DECnet is an obsolete network protocol that receives more attention from kernel janitors than users. It belongs in computer protocol history museum not in Linux kernel. It has been "Orphaned" in kernel since 2010. The iproute2 support for DECnet was dropped in 5.0 release. The documentation link on Sourceforge says it is abandoned there as well. Leave the UAPI alone to keep userspace programs compiling. This means that there is still an empty neighbour table for AF_DECNET. The table of /proc/sys/net entries was updated to match current directories and reformatted to be alphabetical. Signed-off-by: Stephen Hemminger Acked-by: David Ahern Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/net/dn.h | 231 ------------------------------------------ include/net/dn_dev.h | 200 ------------------------------------ include/net/dn_fib.h | 169 ------------------------------ include/net/dn_neigh.h | 32 ------ include/net/dn_nsp.h | 201 ------------------------------------ include/net/dn_route.h | 118 --------------------- include/net/netns/netfilter.h | 3 - 7 files changed, 954 deletions(-) delete mode 100644 include/net/dn.h delete mode 100644 include/net/dn_dev.h delete mode 100644 include/net/dn_fib.h delete mode 100644 include/net/dn_neigh.h delete mode 100644 include/net/dn_nsp.h delete mode 100644 include/net/dn_route.h (limited to 'include/net') diff --git a/include/net/dn.h b/include/net/dn.h deleted file mode 100644 index ba9655b0098a..000000000000 --- a/include/net/dn.h +++ /dev/null @@ -1,231 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _NET_DN_H -#define _NET_DN_H - -#include -#include -#include -#include -#include - -struct dn_scp /* Session Control Port */ -{ - unsigned char state; -#define DN_O 1 /* Open */ -#define DN_CR 2 /* Connect Receive */ -#define DN_DR 3 /* Disconnect Reject */ -#define DN_DRC 4 /* Discon. Rej. Complete*/ -#define DN_CC 5 /* Connect Confirm */ -#define DN_CI 6 /* Connect Initiate */ -#define DN_NR 7 /* No resources */ -#define DN_NC 8 /* No communication */ -#define DN_CD 9 /* Connect Delivery */ -#define DN_RJ 10 /* Rejected */ -#define DN_RUN 11 /* Running */ -#define DN_DI 12 /* Disconnect Initiate */ -#define DN_DIC 13 /* Disconnect Complete */ -#define DN_DN 14 /* Disconnect Notificat */ -#define DN_CL 15 /* Closed */ -#define DN_CN 16 /* Closed Notification */ - - __le16 addrloc; - __le16 addrrem; - __u16 numdat; - __u16 numoth; - __u16 numoth_rcv; - __u16 numdat_rcv; - __u16 ackxmt_dat; - __u16 ackxmt_oth; - __u16 ackrcv_dat; - __u16 ackrcv_oth; - __u8 flowrem_sw; - __u8 flowloc_sw; -#define DN_SEND 2 -#define DN_DONTSEND 1 -#define DN_NOCHANGE 0 - __u16 flowrem_dat; - __u16 flowrem_oth; - __u16 flowloc_dat; - __u16 flowloc_oth; - __u8 services_rem; - __u8 services_loc; - __u8 info_rem; - __u8 info_loc; - - __u16 segsize_rem; - __u16 segsize_loc; - - __u8 nonagle; - __u8 multi_ireq; - __u8 accept_mode; - unsigned long seg_total; /* Running total of current segment */ - - struct optdata_dn conndata_in; - struct optdata_dn conndata_out; - struct optdata_dn discdata_in; - struct optdata_dn discdata_out; - struct accessdata_dn accessdata; - - struct sockaddr_dn addr; /* Local address */ - struct sockaddr_dn peer; /* Remote address */ - - /* - * In this case the RTT estimation is not specified in the - * docs, nor is any back off algorithm. Here we follow well - * known tcp algorithms with a few small variations. - * - * snd_window: Max number of packets we send before we wait for - * an ack to come back. This will become part of a - * more complicated scheme when we support flow - * control. - * - * nsp_srtt: Round-Trip-Time (x8) in jiffies. This is a rolling - * average. - * nsp_rttvar: Round-Trip-Time-Varience (x4) in jiffies. This is the - * varience of the smoothed average (but calculated in - * a simpler way than for normal statistical varience - * calculations). - * - * nsp_rxtshift: Backoff counter. Value is zero normally, each time - * a packet is lost is increases by one until an ack - * is received. Its used to index an array of backoff - * multipliers. - */ -#define NSP_MIN_WINDOW 1 -#define NSP_MAX_WINDOW (0x07fe) - unsigned long max_window; - unsigned long snd_window; -#define NSP_INITIAL_SRTT (HZ) - unsigned long nsp_srtt; -#define NSP_INITIAL_RTTVAR (HZ*3) - unsigned long nsp_rttvar; -#define NSP_MAXRXTSHIFT 12 - unsigned long nsp_rxtshift; - - /* - * Output queues, one for data, one for otherdata/linkservice - */ - struct sk_buff_head data_xmit_queue; - struct sk_buff_head other_xmit_queue; - - /* - * Input queue for other data - */ - struct sk_buff_head other_receive_queue; - int other_report; - - /* - * Stuff to do with the slow timer - */ - unsigned long stamp; /* time of last transmit */ - unsigned long persist; - int (*persist_fxn)(struct sock *sk); - unsigned long keepalive; - void (*keepalive_fxn)(struct sock *sk); - -}; - -static inline struct dn_scp *DN_SK(struct sock *sk) -{ - return (struct dn_scp *)(sk + 1); -} - -/* - * src,dst : Source and Destination DECnet addresses - * hops : Number of hops through the network - * dst_port, src_port : NSP port numbers - * services, info : Useful data extracted from conninit messages - * rt_flags : Routing flags byte - * nsp_flags : NSP layer flags byte - * segsize : Size of segment - * segnum : Number, for data, otherdata and linkservice - * xmit_count : Number of times we've transmitted this skb - * stamp : Time stamp of most recent transmission, used in RTT calculations - * iif: Input interface number - * - * As a general policy, this structure keeps all addresses in network - * byte order, and all else in host byte order. Thus dst, src, dst_port - * and src_port are in network order. All else is in host order. - * - */ -#define DN_SKB_CB(skb) ((struct dn_skb_cb *)(skb)->cb) -struct dn_skb_cb { - __le16 dst; - __le16 src; - __u16 hops; - __le16 dst_port; - __le16 src_port; - __u8 services; - __u8 info; - __u8 rt_flags; - __u8 nsp_flags; - __u16 segsize; - __u16 segnum; - __u16 xmit_count; - unsigned long stamp; - int iif; -}; - -static inline __le16 dn_eth2dn(const unsigned char *ethaddr) -{ - return get_unaligned((__le16 *)(ethaddr + 4)); -} - -static inline __le16 dn_saddr2dn(struct sockaddr_dn *saddr) -{ - return *(__le16 *)saddr->sdn_nodeaddr; -} - -static inline void dn_dn2eth(unsigned char *ethaddr, __le16 addr) -{ - __u16 a = le16_to_cpu(addr); - ethaddr[0] = 0xAA; - ethaddr[1] = 0x00; - ethaddr[2] = 0x04; - ethaddr[3] = 0x00; - ethaddr[4] = (__u8)(a & 0xff); - ethaddr[5] = (__u8)(a >> 8); -} - -static inline void dn_sk_ports_copy(struct flowidn *fld, struct dn_scp *scp) -{ - fld->fld_sport = scp->addrloc; - fld->fld_dport = scp->addrrem; -} - -unsigned int dn_mss_from_pmtu(struct net_device *dev, int mtu); -void dn_register_sysctl(void); -void dn_unregister_sysctl(void); - -#define DN_MENUVER_ACC 0x01 -#define DN_MENUVER_USR 0x02 -#define DN_MENUVER_PRX 0x04 -#define DN_MENUVER_UIC 0x08 - -struct sock *dn_sklist_find_listener(struct sockaddr_dn *addr); -struct sock *dn_find_by_skb(struct sk_buff *skb); -#define DN_ASCBUF_LEN 9 -char *dn_addr2asc(__u16, char *); -int dn_destroy_timer(struct sock *sk); - -int dn_sockaddr2username(struct sockaddr_dn *addr, unsigned char *buf, - unsigned char type); -int dn_username2sockaddr(unsigned char *data, int len, struct sockaddr_dn *addr, - unsigned char *type); - -void dn_start_slow_timer(struct sock *sk); -void dn_stop_slow_timer(struct sock *sk); - -extern __le16 decnet_address; -extern int decnet_debug_level; -extern int decnet_time_wait; -extern int decnet_dn_count; -extern int decnet_di_count; -extern int decnet_dr_count; -extern int decnet_no_fc_max_cwnd; - -extern long sysctl_decnet_mem[3]; -extern int sysctl_decnet_wmem[3]; -extern int sysctl_decnet_rmem[3]; - -#endif /* _NET_DN_H */ diff --git a/include/net/dn_dev.h b/include/net/dn_dev.h deleted file mode 100644 index bec303ea8367..000000000000 --- a/include/net/dn_dev.h +++ /dev/null @@ -1,200 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _NET_DN_DEV_H -#define _NET_DN_DEV_H - -#include - -struct dn_dev; - -struct dn_ifaddr { - struct dn_ifaddr __rcu *ifa_next; - struct dn_dev *ifa_dev; - __le16 ifa_local; - __le16 ifa_address; - __u32 ifa_flags; - __u8 ifa_scope; - char ifa_label[IFNAMSIZ]; - struct rcu_head rcu; -}; - -#define DN_DEV_S_RU 0 /* Run - working normally */ -#define DN_DEV_S_CR 1 /* Circuit Rejected */ -#define DN_DEV_S_DS 2 /* Data Link Start */ -#define DN_DEV_S_RI 3 /* Routing Layer Initialize */ -#define DN_DEV_S_RV 4 /* Routing Layer Verify */ -#define DN_DEV_S_RC 5 /* Routing Layer Complete */ -#define DN_DEV_S_OF 6 /* Off */ -#define DN_DEV_S_HA 7 /* Halt */ - - -/* - * The dn_dev_parms structure contains the set of parameters - * for each device (hence inclusion in the dn_dev structure) - * and an array is used to store the default types of supported - * device (in dn_dev.c). - * - * The type field matches the ARPHRD_ constants and is used in - * searching the list for supported devices when new devices - * come up. - * - * The mode field is used to find out if a device is broadcast, - * multipoint, or pointopoint. Please note that DECnet thinks - * different ways about devices to the rest of the kernel - * so the normal IFF_xxx flags are invalid here. For devices - * which can be any combination of the previously mentioned - * attributes, you can set this on a per device basis by - * installing an up() routine. - * - * The device state field, defines the initial state in which the - * device will come up. In the dn_dev structure, it is the actual - * state. - * - * Things have changed here. I've killed timer1 since it's a user space - * issue for a user space routing deamon to sort out. The kernel does - * not need to be bothered with it. - * - * Timers: - * t2 - Rate limit timer, min time between routing and hello messages - * t3 - Hello timer, send hello messages when it expires - * - * Callbacks: - * up() - Called to initialize device, return value can veto use of - * device with DECnet. - * down() - Called to turn device off when it goes down - * timer3() - Called once for each ifaddr when timer 3 goes off - * - * sysctl - Hook for sysctl things - * - */ -struct dn_dev_parms { - int type; /* ARPHRD_xxx */ - int mode; /* Broadcast, Unicast, Mulitpoint */ -#define DN_DEV_BCAST 1 -#define DN_DEV_UCAST 2 -#define DN_DEV_MPOINT 4 - int state; /* Initial state */ - int forwarding; /* 0=EndNode, 1=L1Router, 2=L2Router */ - unsigned long t2; /* Default value of t2 */ - unsigned long t3; /* Default value of t3 */ - int priority; /* Priority to be a router */ - char *name; /* Name for sysctl */ - int (*up)(struct net_device *); - void (*down)(struct net_device *); - void (*timer3)(struct net_device *, struct dn_ifaddr *ifa); - void *sysctl; -}; - - -struct dn_dev { - struct dn_ifaddr __rcu *ifa_list; - struct net_device *dev; - struct dn_dev_parms parms; - char use_long; - struct timer_list timer; - unsigned long t3; - struct neigh_parms *neigh_parms; - __u8 addr[ETH_ALEN]; - struct neighbour *router; /* Default router on circuit */ - struct neighbour *peer; /* Peer on pointopoint links */ - unsigned long uptime; /* Time device went up in jiffies */ -}; - -struct dn_short_packet { - __u8 msgflg; - __le16 dstnode; - __le16 srcnode; - __u8 forward; -} __packed; - -struct dn_long_packet { - __u8 msgflg; - __u8 d_area; - __u8 d_subarea; - __u8 d_id[6]; - __u8 s_area; - __u8 s_subarea; - __u8 s_id[6]; - __u8 nl2; - __u8 visit_ct; - __u8 s_class; - __u8 pt; -} __packed; - -/*------------------------- DRP - Routing messages ---------------------*/ - -struct endnode_hello_message { - __u8 msgflg; - __u8 tiver[3]; - __u8 id[6]; - __u8 iinfo; - __le16 blksize; - __u8 area; - __u8 seed[8]; - __u8 neighbor[6]; - __le16 timer; - __u8 mpd; - __u8 datalen; - __u8 data[2]; -} __packed; - -struct rtnode_hello_message { - __u8 msgflg; - __u8 tiver[3]; - __u8 id[6]; - __u8 iinfo; - __le16 blksize; - __u8 priority; - __u8 area; - __le16 timer; - __u8 mpd; -} __packed; - - -void dn_dev_init(void); -void dn_dev_cleanup(void); - -int dn_dev_ioctl(unsigned int cmd, void __user *arg); - -void dn_dev_devices_off(void); -void dn_dev_devices_on(void); - -void dn_dev_init_pkt(struct sk_buff *skb); -void dn_dev_veri_pkt(struct sk_buff *skb); -void dn_dev_hello(struct sk_buff *skb); - -void dn_dev_up(struct net_device *); -void dn_dev_down(struct net_device *); - -int dn_dev_set_default(struct net_device *dev, int force); -struct net_device *dn_dev_get_default(void); -int dn_dev_bind_default(__le16 *addr); - -int register_dnaddr_notifier(struct notifier_block *nb); -int unregister_dnaddr_notifier(struct notifier_block *nb); - -static inline int dn_dev_islocal(struct net_device *dev, __le16 addr) -{ - struct dn_dev *dn_db; - struct dn_ifaddr *ifa; - int res = 0; - - rcu_read_lock(); - dn_db = rcu_dereference(dev->dn_ptr); - if (dn_db == NULL) { - printk(KERN_DEBUG "dn_dev_islocal: Called for non DECnet device\n"); - goto out; - } - - for (ifa = rcu_dereference(dn_db->ifa_list); - ifa != NULL; - ifa = rcu_dereference(ifa->ifa_next)) - if ((addr ^ ifa->ifa_local) == 0) { - res = 1; - break; - } -out: - rcu_read_unlock(); - return res; -} - -#endif /* _NET_DN_DEV_H */ diff --git a/include/net/dn_fib.h b/include/net/dn_fib.h deleted file mode 100644 index 1929a3cd5ebe..000000000000 --- a/include/net/dn_fib.h +++ /dev/null @@ -1,169 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _NET_DN_FIB_H -#define _NET_DN_FIB_H - -#include -#include -#include -#include - -extern const struct nla_policy rtm_dn_policy[]; - -struct dn_fib_res { - struct fib_rule *r; - struct dn_fib_info *fi; - unsigned char prefixlen; - unsigned char nh_sel; - unsigned char type; - unsigned char scope; -}; - -struct dn_fib_nh { - struct net_device *nh_dev; - unsigned int nh_flags; - unsigned char nh_scope; - int nh_weight; - int nh_power; - int nh_oif; - __le16 nh_gw; -}; - -struct dn_fib_info { - struct dn_fib_info *fib_next; - struct dn_fib_info *fib_prev; - refcount_t fib_treeref; - refcount_t fib_clntref; - int fib_dead; - unsigned int fib_flags; - int fib_protocol; - __le16 fib_prefsrc; - __u32 fib_priority; - __u32 fib_metrics[RTAX_MAX]; - int fib_nhs; - int fib_power; - struct dn_fib_nh fib_nh[0]; -#define dn_fib_dev fib_nh[0].nh_dev -}; - - -#define DN_FIB_RES_RESET(res) ((res).nh_sel = 0) -#define DN_FIB_RES_NH(res) ((res).fi->fib_nh[(res).nh_sel]) - -#define DN_FIB_RES_PREFSRC(res) ((res).fi->fib_prefsrc ? : __dn_fib_res_prefsrc(&res)) -#define DN_FIB_RES_GW(res) (DN_FIB_RES_NH(res).nh_gw) -#define DN_FIB_RES_DEV(res) (DN_FIB_RES_NH(res).nh_dev) -#define DN_FIB_RES_OIF(res) (DN_FIB_RES_NH(res).nh_oif) - -typedef struct { - __le16 datum; -} dn_fib_key_t; - -typedef struct { - __le16 datum; -} dn_fib_hash_t; - -typedef struct { - __u16 datum; -} dn_fib_idx_t; - -struct dn_fib_node { - struct dn_fib_node *fn_next; - struct dn_fib_info *fn_info; -#define DN_FIB_INFO(f) ((f)->fn_info) - dn_fib_key_t fn_key; - u8 fn_type; - u8 fn_scope; - u8 fn_state; -}; - - -struct dn_fib_table { - struct hlist_node hlist; - u32 n; - - int (*insert)(struct dn_fib_table *t, struct rtmsg *r, - struct nlattr *attrs[], struct nlmsghdr *n, - struct netlink_skb_parms *req); - int (*delete)(struct dn_fib_table *t, struct rtmsg *r, - struct nlattr *attrs[], struct nlmsghdr *n, - struct netlink_skb_parms *req); - int (*lookup)(struct dn_fib_table *t, const struct flowidn *fld, - struct dn_fib_res *res); - int (*flush)(struct dn_fib_table *t); - int (*dump)(struct dn_fib_table *t, struct sk_buff *skb, struct netlink_callback *cb); - - unsigned char data[]; -}; - -#ifdef CONFIG_DECNET_ROUTER -/* - * dn_fib.c - */ -void dn_fib_init(void); -void dn_fib_cleanup(void); - -int dn_fib_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); -struct dn_fib_info *dn_fib_create_info(const struct rtmsg *r, - struct nlattr *attrs[], - const struct nlmsghdr *nlh, int *errp); -int dn_fib_semantic_match(int type, struct dn_fib_info *fi, - const struct flowidn *fld, struct dn_fib_res *res); -void dn_fib_release_info(struct dn_fib_info *fi); -void dn_fib_flush(void); -void dn_fib_select_multipath(const struct flowidn *fld, struct dn_fib_res *res); - -/* - * dn_tables.c - */ -struct dn_fib_table *dn_fib_get_table(u32 n, int creat); -struct dn_fib_table *dn_fib_empty_table(void); -void dn_fib_table_init(void); -void dn_fib_table_cleanup(void); - -/* - * dn_rules.c - */ -void dn_fib_rules_init(void); -void dn_fib_rules_cleanup(void); -unsigned int dnet_addr_type(__le16 addr); -int dn_fib_lookup(struct flowidn *fld, struct dn_fib_res *res); - -int dn_fib_dump(struct sk_buff *skb, struct netlink_callback *cb); - -void dn_fib_free_info(struct dn_fib_info *fi); - -static inline void dn_fib_info_put(struct dn_fib_info *fi) -{ - if (refcount_dec_and_test(&fi->fib_clntref)) - dn_fib_free_info(fi); -} - -static inline void dn_fib_res_put(struct dn_fib_res *res) -{ - if (res->fi) - dn_fib_info_put(res->fi); - if (res->r) - fib_rule_put(res->r); -} - -#else /* Endnode */ - -#define dn_fib_init() do { } while(0) -#define dn_fib_cleanup() do { } while(0) - -#define dn_fib_lookup(fl, res) (-ESRCH) -#define dn_fib_info_put(fi) do { } while(0) -#define dn_fib_select_multipath(fl, res) do { } while(0) -#define dn_fib_rules_policy(saddr,res,flags) (0) -#define dn_fib_res_put(res) do { } while(0) - -#endif /* CONFIG_DECNET_ROUTER */ - -static inline __le16 dnet_make_mask(int n) -{ - if (n) - return cpu_to_le16(~((1 << (16 - n)) - 1)); - return cpu_to_le16(0); -} - -#endif /* _NET_DN_FIB_H */ diff --git a/include/net/dn_neigh.h b/include/net/dn_neigh.h deleted file mode 100644 index 1f7df98bfc33..000000000000 --- a/include/net/dn_neigh.h +++ /dev/null @@ -1,32 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _NET_DN_NEIGH_H -#define _NET_DN_NEIGH_H - -#include - -/* - * The position of the first two fields of - * this structure are critical - SJW - */ -struct dn_neigh { - struct neighbour n; - __le16 addr; - unsigned long flags; -#define DN_NDFLAG_R1 0x0001 /* Router L1 */ -#define DN_NDFLAG_R2 0x0002 /* Router L2 */ -#define DN_NDFLAG_P3 0x0004 /* Phase III Node */ - unsigned long blksize; - __u8 priority; -}; - -void dn_neigh_init(void); -void dn_neigh_cleanup(void); -int dn_neigh_router_hello(struct net *net, struct sock *sk, struct sk_buff *skb); -int dn_neigh_endnode_hello(struct net *net, struct sock *sk, struct sk_buff *skb); -void dn_neigh_pointopoint_hello(struct sk_buff *skb); -int dn_neigh_elist(struct net_device *dev, unsigned char *ptr, int n); -int dn_to_neigh_output(struct net *net, struct sock *sk, struct sk_buff *skb); - -extern struct neigh_table dn_neigh_table; - -#endif /* _NET_DN_NEIGH_H */ diff --git a/include/net/dn_nsp.h b/include/net/dn_nsp.h deleted file mode 100644 index a4a18fee0b7c..000000000000 --- a/include/net/dn_nsp.h +++ /dev/null @@ -1,201 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -#ifndef _NET_DN_NSP_H -#define _NET_DN_NSP_H -/****************************************************************************** - (c) 1995-1998 E.M. Serrat emserrat@geocities.com - -*******************************************************************************/ -/* dn_nsp.c functions prototyping */ -#include -#include -#include - -struct sk_buff; -struct sk_buff_head; - -void dn_nsp_send_data_ack(struct sock *sk); -void dn_nsp_send_oth_ack(struct sock *sk); -void dn_send_conn_ack(struct sock *sk); -void dn_send_conn_conf(struct sock *sk, gfp_t gfp); -void dn_nsp_send_disc(struct sock *sk, unsigned char type, - unsigned short reason, gfp_t gfp); -void dn_nsp_return_disc(struct sk_buff *skb, unsigned char type, - unsigned short reason); -void dn_nsp_send_link(struct sock *sk, unsigned char lsflags, char fcval); -void dn_nsp_send_conninit(struct sock *sk, unsigned char flags); - -void dn_nsp_output(struct sock *sk); -int dn_nsp_check_xmit_queue(struct sock *sk, struct sk_buff *skb, - struct sk_buff_head *q, unsigned short acknum); -void dn_nsp_queue_xmit(struct sock *sk, struct sk_buff *skb, gfp_t gfp, - int oob); -unsigned long dn_nsp_persist(struct sock *sk); -int dn_nsp_xmit_timeout(struct sock *sk); - -int dn_nsp_rx(struct sk_buff *); -int dn_nsp_backlog_rcv(struct sock *sk, struct sk_buff *skb); - -struct sk_buff *dn_alloc_skb(struct sock *sk, int size, gfp_t pri); -struct sk_buff *dn_alloc_send_skb(struct sock *sk, size_t *size, int noblock, - long timeo, int *err); - -#define NSP_REASON_OK 0 /* No error */ -#define NSP_REASON_NR 1 /* No resources */ -#define NSP_REASON_UN 2 /* Unrecognised node name */ -#define NSP_REASON_SD 3 /* Node shutting down */ -#define NSP_REASON_ID 4 /* Invalid destination end user */ -#define NSP_REASON_ER 5 /* End user lacks resources */ -#define NSP_REASON_OB 6 /* Object too busy */ -#define NSP_REASON_US 7 /* Unspecified error */ -#define NSP_REASON_TP 8 /* Third-Party abort */ -#define NSP_REASON_EA 9 /* End user has aborted the link */ -#define NSP_REASON_IF 10 /* Invalid node name format */ -#define NSP_REASON_LS 11 /* Local node shutdown */ -#define NSP_REASON_LL 32 /* Node lacks logical-link resources */ -#define NSP_REASON_LE 33 /* End user lacks logical-link resources */ -#define NSP_REASON_UR 34 /* Unacceptable RQSTRID or PASSWORD field */ -#define NSP_REASON_UA 36 /* Unacceptable ACCOUNT field */ -#define NSP_REASON_TM 38 /* End user timed out logical link */ -#define NSP_REASON_NU 39 /* Node unreachable */ -#define NSP_REASON_NL 41 /* No-link message */ -#define NSP_REASON_DC 42 /* Disconnect confirm */ -#define NSP_REASON_IO 43 /* Image data field overflow */ - -#define NSP_DISCINIT 0x38 -#define NSP_DISCCONF 0x48 - -/*------------------------- NSP - messages ------------------------------*/ -/* Data Messages */ -/*---------------*/ - -/* Data Messages (data segment/interrupt/link service) */ - -struct nsp_data_seg_msg { - __u8 msgflg; - __le16 dstaddr; - __le16 srcaddr; -} __packed; - -struct nsp_data_opt_msg { - __le16 acknum; - __le16 segnum; - __le16 lsflgs; -} __packed; - -struct nsp_data_opt_msg1 { - __le16 acknum; - __le16 segnum; -} __packed; - - -/* Acknowledgment Message (data/other data) */ -struct nsp_data_ack_msg { - __u8 msgflg; - __le16 dstaddr; - __le16 srcaddr; - __le16 acknum; -} __packed; - -/* Connect Acknowledgment Message */ -struct nsp_conn_ack_msg { - __u8 msgflg; - __le16 dstaddr; -} __packed; - - -/* Connect Initiate/Retransmit Initiate/Connect Confirm */ -struct nsp_conn_init_msg { - __u8 msgflg; -#define NSP_CI 0x18 /* Connect Initiate */ -#define NSP_RCI 0x68 /* Retrans. Conn Init */ - __le16 dstaddr; - __le16 srcaddr; - __u8 services; -#define NSP_FC_NONE 0x00 /* Flow Control None */ -#define NSP_FC_SRC 0x04 /* Seg Req. Count */ -#define NSP_FC_SCMC 0x08 /* Sess. Control Mess */ -#define NSP_FC_MASK 0x0c /* FC type mask */ - __u8 info; - __le16 segsize; -} __packed; - -/* Disconnect Initiate/Disconnect Confirm */ -struct nsp_disconn_init_msg { - __u8 msgflg; - __le16 dstaddr; - __le16 srcaddr; - __le16 reason; -} __packed; - - - -struct srcobj_fmt { - __u8 format; - __u8 task; - __le16 grpcode; - __le16 usrcode; - __u8 dlen; -} __packed; - -/* - * A collection of functions for manipulating the sequence - * numbers used in NSP. Similar in operation to the functions - * of the same name in TCP. - */ -static __inline__ int dn_before(__u16 seq1, __u16 seq2) -{ - seq1 &= 0x0fff; - seq2 &= 0x0fff; - - return (int)((seq1 - seq2) & 0x0fff) > 2048; -} - - -static __inline__ int dn_after(__u16 seq1, __u16 seq2) -{ - seq1 &= 0x0fff; - seq2 &= 0x0fff; - - return (int)((seq2 - seq1) & 0x0fff) > 2048; -} - -static __inline__ int dn_equal(__u16 seq1, __u16 seq2) -{ - return ((seq1 ^ seq2) & 0x0fff) == 0; -} - -static __inline__ int dn_before_or_equal(__u16 seq1, __u16 seq2) -{ - return (dn_before(seq1, seq2) || dn_equal(seq1, seq2)); -} - -static __inline__ void seq_add(__u16 *seq, __u16 off) -{ - (*seq) += off; - (*seq) &= 0x0fff; -} - -static __inline__ int seq_next(__u16 seq1, __u16 seq2) -{ - return dn_equal(seq1 + 1, seq2); -} - -/* - * Can we delay the ack ? - */ -static __inline__ int sendack(__u16 seq) -{ - return (int)((seq & 0x1000) ? 0 : 1); -} - -/* - * Is socket congested ? - */ -static __inline__ int dn_congested(struct sock *sk) -{ - return atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1); -} - -#define DN_MAX_NSP_DATA_HEADER (11) - -#endif /* _NET_DN_NSP_H */ diff --git a/include/net/dn_route.h b/include/net/dn_route.h deleted file mode 100644 index 88c0300236cc..000000000000 --- a/include/net/dn_route.h +++ /dev/null @@ -1,118 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -#ifndef _NET_DN_ROUTE_H -#define _NET_DN_ROUTE_H - -/****************************************************************************** - (c) 1995-1998 E.M. Serrat emserrat@geocities.com - -*******************************************************************************/ - -#include -#include - -struct sk_buff *dn_alloc_skb(struct sock *sk, int size, gfp_t pri); -int dn_route_output_sock(struct dst_entry __rcu **pprt, struct flowidn *, - struct sock *sk, int flags); -int dn_cache_dump(struct sk_buff *skb, struct netlink_callback *cb); -void dn_rt_cache_flush(int delay); -int dn_route_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt, struct net_device *orig_dev); - -/* Masks for flags field */ -#define DN_RT_F_PID 0x07 /* Mask for packet type */ -#define DN_RT_F_PF 0x80 /* Padding Follows */ -#define DN_RT_F_VER 0x40 /* Version =0 discard packet if ==1 */ -#define DN_RT_F_IE 0x20 /* Intra Ethernet, Reserved in short pkt */ -#define DN_RT_F_RTS 0x10 /* Packet is being returned to sender */ -#define DN_RT_F_RQR 0x08 /* Return packet to sender upon non-delivery */ - -/* Mask for types of routing packets */ -#define DN_RT_PKT_MSK 0x06 -/* Types of routing packets */ -#define DN_RT_PKT_SHORT 0x02 /* Short routing packet */ -#define DN_RT_PKT_LONG 0x06 /* Long routing packet */ - -/* Mask for control/routing selection */ -#define DN_RT_PKT_CNTL 0x01 /* Set to 1 if a control packet */ -/* Types of control packets */ -#define DN_RT_CNTL_MSK 0x0f /* Mask for control packets */ -#define DN_RT_PKT_INIT 0x01 /* Initialisation packet */ -#define DN_RT_PKT_VERI 0x03 /* Verification Message */ -#define DN_RT_PKT_HELO 0x05 /* Hello and Test Message */ -#define DN_RT_PKT_L1RT 0x07 /* Level 1 Routing Message */ -#define DN_RT_PKT_L2RT 0x09 /* Level 2 Routing Message */ -#define DN_RT_PKT_ERTH 0x0b /* Ethernet Router Hello */ -#define DN_RT_PKT_EEDH 0x0d /* Ethernet EndNode Hello */ - -/* Values for info field in hello message */ -#define DN_RT_INFO_TYPE 0x03 /* Type mask */ -#define DN_RT_INFO_L1RT 0x02 /* L1 Router */ -#define DN_RT_INFO_L2RT 0x01 /* L2 Router */ -#define DN_RT_INFO_ENDN 0x03 /* EndNode */ -#define DN_RT_INFO_VERI 0x04 /* Verification Reqd. */ -#define DN_RT_INFO_RJCT 0x08 /* Reject Flag, Reserved */ -#define DN_RT_INFO_VFLD 0x10 /* Verification Failed, Reserved */ -#define DN_RT_INFO_NOML 0x20 /* No Multicast traffic accepted */ -#define DN_RT_INFO_BLKR 0x40 /* Blocking Requested */ - -/* - * The fl structure is what we used to look up the route. - * The rt_saddr & rt_daddr entries are the same as key.saddr & key.daddr - * except for local input routes, where the rt_saddr = fl.fld_dst and - * rt_daddr = fl.fld_src to allow the route to be used for returning - * packets to the originating host. - */ -struct dn_route { - struct dst_entry dst; - struct dn_route __rcu *dn_next; - - struct neighbour *n; - - struct flowidn fld; - - __le16 rt_saddr; - __le16 rt_daddr; - __le16 rt_gateway; - __le16 rt_local_src; /* Source used for forwarding packets */ - __le16 rt_src_map; - __le16 rt_dst_map; - - unsigned int rt_flags; - unsigned int rt_type; -}; - -static inline bool dn_is_input_route(struct dn_route *rt) -{ - return rt->fld.flowidn_iif != 0; -} - -static inline bool dn_is_output_route(struct dn_route *rt) -{ - return rt->fld.flowidn_iif == 0; -} - -void dn_route_init(void); -void dn_route_cleanup(void); - -#include -#include - -static inline void dn_rt_send(struct sk_buff *skb) -{ - dev_queue_xmit(skb); -} - -static inline void dn_rt_finish_output(struct sk_buff *skb, char *dst, char *src) -{ - struct net_device *dev = skb->dev; - - if ((dev->type != ARPHRD_ETHER) && (dev->type != ARPHRD_LOOPBACK)) - dst = NULL; - - if (dev_hard_header(skb, dev, ETH_P_DNA_RT, dst, src, skb->len) >= 0) - dn_rt_send(skb); - else - kfree_skb(skb); -} - -#endif /* _NET_DN_ROUTE_H */ diff --git a/include/net/netns/netfilter.h b/include/net/netns/netfilter.h index b593f95e9991..02bbdc577f8e 100644 --- a/include/net/netns/netfilter.h +++ b/include/net/netns/netfilter.h @@ -24,9 +24,6 @@ struct netns_nf { #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) unsigned int defrag_ipv4_users; #endif -- cgit v1.2.3 From e38f22c860edb7804b4722ac2332f7c51b9c6b72 Mon Sep 17 00:00:00 2001 From: Arseniy Krasnov Date: Fri, 19 Aug 2022 05:25:19 +0000 Subject: vsock: SO_RCVLOWAT transport set callback This adds transport specific callback for SO_RCVLOWAT, because in some transports it may be difficult to know current available number of bytes ready to read. Thus, when SO_RCVLOWAT is set, transport may reject it. Signed-off-by: Arseniy Krasnov Signed-off-by: Paolo Abeni --- include/net/af_vsock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 1c53c4c4d88f..d609a088cb27 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -135,6 +135,7 @@ struct vsock_transport { u64 (*stream_rcvhiwat)(struct vsock_sock *); bool (*stream_is_active)(struct vsock_sock *); bool (*stream_allow)(u32 cid, u32 port); + int (*set_rcvlowat)(struct vsock_sock *vsk, int val); /* SEQ_PACKET. */ ssize_t (*seqpacket_dequeue)(struct vsock_sock *vsk, struct msghdr *msg, -- cgit v1.2.3 From f2fdcf67aceb1a7d5e0661cb7ca95cda68d3014a Mon Sep 17 00:00:00 2001 From: Arseniy Krasnov Date: Fri, 19 Aug 2022 05:36:52 +0000 Subject: vsock: add API call for data ready This adds 'vsock_data_ready()' which must be called by transport to kick sleeping data readers. It checks for SO_RCVLOWAT value before waking user, thus preventing spurious wake ups. Based on 'tcp_data_ready()' logic. Signed-off-by: Arseniy Krasnov Reviewed-by: Stefano Garzarella Signed-off-by: Paolo Abeni --- include/net/af_vsock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index d609a088cb27..568a87c5e0d0 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -78,6 +78,7 @@ struct vsock_sock { s64 vsock_stream_has_data(struct vsock_sock *vsk); s64 vsock_stream_has_space(struct vsock_sock *vsk); struct sock *vsock_create_connected(struct sock *parent); +void vsock_data_ready(struct sock *sk); /**** TRANSPORT ****/ -- cgit v1.2.3 From 5dc760d1208200daaf49a2ff56a0e7dfa2d80bb2 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 19 Aug 2022 20:48:18 +0300 Subject: net: dsa: use dsa_tree_for_each_cpu_port in dsa_tree_{setup,teardown}_master More logic will be added to dsa_tree_setup_master() and dsa_tree_teardown_master() in upcoming changes. Reduce the indentation by one level in these functions by introducing and using a dedicated iterator for CPU ports of a tree. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: Paolo Abeni --- include/net/dsa.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/net') diff --git a/include/net/dsa.h b/include/net/dsa.h index b902b31bebce..f2ce12860546 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -559,6 +559,10 @@ static inline bool dsa_is_user_port(struct dsa_switch *ds, int p) list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_is_user((_dp))) +#define dsa_tree_for_each_cpu_port(_dp, _dst) \ + list_for_each_entry((_dp), &(_dst)->ports, list) \ + if (dsa_port_is_cpu((_dp))) + #define dsa_switch_for_each_port(_dp, _ds) \ list_for_each_entry((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) -- cgit v1.2.3 From 0bf73255d3a3cf3b0416e95f2c9f7c53095c2e1a Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Wed, 24 Aug 2022 09:36:21 +0800 Subject: netlink: fix some kernel-doc comments Modify the comment of input parameter of nlmsg_ and nla_ function. Signed-off-by: Zhengchao Shao Link: https://lore.kernel.org/r/20220824013621.365103-1-shaozhengchao@huawei.com Signed-off-by: Jakub Kicinski --- include/net/netlink.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/netlink.h b/include/net/netlink.h index 7a2a9d3144ba..e658d18afa67 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -741,6 +741,7 @@ static inline int __nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen, * @hdrlen: length of family specific header * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected + * @policy: validation policy * @extack: extended ACK report struct * * See nla_parse() @@ -760,6 +761,7 @@ static inline int nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen, * @hdrlen: length of family specific header * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected + * @policy: validation policy * @extack: extended ACK report struct * * See nla_parse_deprecated() @@ -779,6 +781,7 @@ static inline int nlmsg_parse_deprecated(const struct nlmsghdr *nlh, int hdrlen, * @hdrlen: length of family specific header * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected + * @policy: validation policy * @extack: extended ACK report struct * * See nla_parse_deprecated_strict() @@ -814,7 +817,6 @@ static inline struct nlattr *nlmsg_find_attr(const struct nlmsghdr *nlh, * @len: length of attribute stream * @maxtype: maximum attribute type to be expected * @policy: validation policy - * @validate: validation strictness * @extack: extended ACK report struct * * Validates all attributes in the specified attribute stream against the -- cgit v1.2.3 From 28044fc1d4953b07acec0da4d2fc4784c57ea6fb Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Mon, 22 Aug 2022 11:10:21 -0700 Subject: net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong Signed-off-by: Jakub Kicinski --- include/net/inet_connection_sock.h | 3 ++ include/net/inet_hashtables.h | 80 +++++++++++++++++++++++++++++++++++++- include/net/sock.h | 14 +++++++ 3 files changed, 95 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index ee88f0f1350f..c2b15f7e5516 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -25,6 +25,7 @@ #undef INET_CSK_CLEAR_TIMERS struct inet_bind_bucket; +struct inet_bind2_bucket; struct tcp_congestion_ops; /* @@ -57,6 +58,7 @@ struct inet_connection_sock_af_ops { * * @icsk_accept_queue: FIFO of established children * @icsk_bind_hash: Bind node + * @icsk_bind2_hash: Bind node in the bhash2 table * @icsk_timeout: Timeout * @icsk_retransmit_timer: Resend (no ack) * @icsk_rto: Retransmit timeout @@ -83,6 +85,7 @@ struct inet_connection_sock { struct inet_sock icsk_inet; struct request_sock_queue icsk_accept_queue; struct inet_bind_bucket *icsk_bind_hash; + struct inet_bind2_bucket *icsk_bind2_hash; unsigned long icsk_timeout; struct timer_list icsk_retransmit_timer; struct timer_list icsk_delack_timer; diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index e9cf2157ed8a..44a419b9e3d5 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -23,6 +23,7 @@ #include #include +#include #include #include #include @@ -90,7 +91,28 @@ struct inet_bind_bucket { struct hlist_head owners; }; -static inline struct net *ib_net(struct inet_bind_bucket *ib) +struct inet_bind2_bucket { + possible_net_t ib_net; + int l3mdev; + unsigned short port; + union { +#if IS_ENABLED(CONFIG_IPV6) + struct in6_addr v6_rcv_saddr; +#endif + __be32 rcv_saddr; + }; + /* Node in the bhash2 inet_bind_hashbucket chain */ + struct hlist_node node; + /* List of sockets hashed to this bucket */ + struct hlist_head owners; +}; + +static inline struct net *ib_net(const struct inet_bind_bucket *ib) +{ + return read_pnet(&ib->ib_net); +} + +static inline struct net *ib2_net(const struct inet_bind2_bucket *ib) { return read_pnet(&ib->ib_net); } @@ -133,7 +155,14 @@ struct inet_hashinfo { * TCP hash as well as the others for fast bind/connect. */ struct kmem_cache *bind_bucket_cachep; + /* This bind table is hashed by local port */ struct inet_bind_hashbucket *bhash; + struct kmem_cache *bind2_bucket_cachep; + /* This bind table is hashed by local port and sk->sk_rcv_saddr (ipv4) + * or sk->sk_v6_rcv_saddr (ipv6). This 2nd bind table is used + * primarily for expediting bind conflict resolution. + */ + struct inet_bind_hashbucket *bhash2; unsigned int bhash_size; /* The 2nd listener table hashed by local port and address */ @@ -182,14 +211,61 @@ inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net, void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket *tb); +bool inet_bind_bucket_match(const struct inet_bind_bucket *tb, + const struct net *net, unsigned short port, + int l3mdev); + +struct inet_bind2_bucket * +inet_bind2_bucket_create(struct kmem_cache *cachep, struct net *net, + struct inet_bind_hashbucket *head, + unsigned short port, int l3mdev, + const struct sock *sk); + +void inet_bind2_bucket_destroy(struct kmem_cache *cachep, + struct inet_bind2_bucket *tb); + +struct inet_bind2_bucket * +inet_bind2_bucket_find(const struct inet_bind_hashbucket *head, + const struct net *net, + unsigned short port, int l3mdev, + const struct sock *sk); + +bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb, + const struct net *net, unsigned short port, + int l3mdev, const struct sock *sk); + static inline u32 inet_bhashfn(const struct net *net, const __u16 lport, const u32 bhash_size) { return (lport + net_hash_mix(net)) & (bhash_size - 1); } +static inline struct inet_bind_hashbucket * +inet_bhashfn_portaddr(const struct inet_hashinfo *hinfo, const struct sock *sk, + const struct net *net, unsigned short port) +{ + u32 hash; + +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6) + hash = ipv6_portaddr_hash(net, &sk->sk_v6_rcv_saddr, port); + else +#endif + hash = ipv4_portaddr_hash(net, sk->sk_rcv_saddr, port); + return &hinfo->bhash2[hash & (hinfo->bhash_size - 1)]; +} + +struct inet_bind_hashbucket * +inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, int port); + +/* This should be called whenever a socket's sk_rcv_saddr (ipv4) or + * sk_v6_rcv_saddr (ipv6) changes after it has been binded. The socket's + * rcv_saddr field should already have been updated when this is called. + */ +int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct sock *sk); + void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, - const unsigned short snum); + struct inet_bind2_bucket *tb2, unsigned short port); /* Caller must disable local BH processing. */ int __inet_inherit_port(const struct sock *sk, struct sock *child); diff --git a/include/net/sock.h b/include/net/sock.h index d08cfe190a78..ca469980e006 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -348,6 +348,7 @@ struct sk_filter; * @sk_txtime_report_errors: set report errors mode for SO_TXTIME * @sk_txtime_unused: unused txtime flags * @ns_tracker: tracker for netns reference + * @sk_bind2_node: bind node in the bhash2 table */ struct sock { /* @@ -537,6 +538,7 @@ struct sock { #endif struct rcu_head sk_rcu; netns_tracker ns_tracker; + struct hlist_node sk_bind2_node; }; enum sk_pacing { @@ -870,6 +872,16 @@ static inline void sk_add_bind_node(struct sock *sk, hlist_add_head(&sk->sk_bind_node, list); } +static inline void __sk_del_bind2_node(struct sock *sk) +{ + __hlist_del(&sk->sk_bind2_node); +} + +static inline void sk_add_bind2_node(struct sock *sk, struct hlist_head *list) +{ + hlist_add_head(&sk->sk_bind2_node, list); +} + #define sk_for_each(__sk, list) \ hlist_for_each_entry(__sk, list, sk_node) #define sk_for_each_rcu(__sk, list) \ @@ -887,6 +899,8 @@ static inline void sk_add_bind_node(struct sock *sk, hlist_for_each_entry_safe(__sk, tmp, list, sk_node) #define sk_for_each_bound(__sk, list) \ hlist_for_each_entry(__sk, list, sk_bind_node) +#define sk_for_each_bound_bhash2(__sk, list) \ + hlist_for_each_entry(__sk, list, sk_bind2_node) /** * sk_for_each_entry_offset_rcu - iterate over a list at a given struct offset -- cgit v1.2.3 From 35ffb66547295c72650978f9c28e670e014d0957 Mon Sep 17 00:00:00 2001 From: Richard Gobert Date: Tue, 23 Aug 2022 09:10:49 +0200 Subject: net: gro: skb_gro_header helper function Introduce a simple helper function to replace a common pattern. When accessing the GRO header, we fetch the pointer from frag0, then test its validity and fetch it from the skb when necessary. This leads to the pattern skb_gro_header_fast -> skb_gro_header_hard -> skb_gro_header_slow recurring many times throughout GRO code. This patch replaces these patterns with a single inlined function call, improving code readability. Signed-off-by: Richard Gobert Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20220823071034.GA56142@debian Signed-off-by: Paolo Abeni --- include/net/gro.h | 33 ++++++++++++++++++--------------- 1 file changed, 18 insertions(+), 15 deletions(-) (limited to 'include/net') diff --git a/include/net/gro.h b/include/net/gro.h index 867656b0739c..5bf15c212434 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -160,6 +160,17 @@ static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen, return skb->data + offset; } +static inline void *skb_gro_header(struct sk_buff *skb, + unsigned int hlen, unsigned int offset) +{ + void *ptr; + + ptr = skb_gro_header_fast(skb, offset); + if (skb_gro_header_hard(skb, hlen)) + ptr = skb_gro_header_slow(skb, hlen, offset); + return ptr; +} + static inline void *skb_gro_network_header(struct sk_buff *skb) { return (NAPI_GRO_CB(skb)->frag0 ?: skb->data) + @@ -301,12 +312,9 @@ static inline void *skb_gro_remcsum_process(struct sk_buff *skb, void *ptr, return ptr; } - ptr = skb_gro_header_fast(skb, off); - if (skb_gro_header_hard(skb, off + plen)) { - ptr = skb_gro_header_slow(skb, off + plen, off); - if (!ptr) - return NULL; - } + ptr = skb_gro_header(skb, off + plen, off); + if (!ptr) + return NULL; delta = remcsum_adjust(ptr + hdrlen, NAPI_GRO_CB(skb)->csum, start, offset); @@ -329,12 +337,9 @@ static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, if (!grc->delta) return; - ptr = skb_gro_header_fast(skb, grc->offset); - if (skb_gro_header_hard(skb, grc->offset + sizeof(u16))) { - ptr = skb_gro_header_slow(skb, plen, grc->offset); - if (!ptr) - return; - } + ptr = skb_gro_header(skb, plen, grc->offset); + if (!ptr) + return; remcsum_unadjust((__sum16 *)ptr, grc->delta); } @@ -405,9 +410,7 @@ static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb) off = skb_gro_offset(skb); hlen = off + sizeof(*uh); - uh = skb_gro_header_fast(skb, off); - if (skb_gro_header_hard(skb, hlen)) - uh = skb_gro_header_slow(skb, hlen, off); + uh = skb_gro_header(skb, hlen, off); return uh; } -- cgit v1.2.3 From 9d2bb84d54a40361c7008b33a60dc24f78724746 Mon Sep 17 00:00:00 2001 From: Shaul Triebitz Date: Tue, 2 Aug 2022 15:22:42 +0300 Subject: wifi: cfg80211: add link id to txq params The Tx queue parameters are per link, so add the link ID from nl80211 parameters to the API. While at it, lock the wdev when calling into the driver so it (and we) can check the link ID appropriately. Signed-off-by: Shaul Triebitz Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 908d58393484..1d393e09a632 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2316,6 +2316,7 @@ struct ocb_setup { * @cwmax: Maximum contention window [a value of the form 2^n-1 in the range * 1..32767] * @aifs: Arbitration interframe space [0..255] + * @link_id: link_id or -1 for non-MLD */ struct ieee80211_txq_params { enum nl80211_ac ac; @@ -2323,6 +2324,7 @@ struct ieee80211_txq_params { u16 cwmin; u16 cwmax; u8 aifs; + int link_id; }; /** -- cgit v1.2.3 From e7a7b84e33178db4a839c5e1773247be17597c1f Mon Sep 17 00:00:00 2001 From: Veerendranath Jakkam Date: Sat, 30 Jul 2022 10:56:43 +0530 Subject: wifi: cfg80211: Add link_id parameter to various key operations for MLO Add support for various key operations on MLD by adding new parameter link_id. Pass the link_id received from userspace to driver for add_key, get_key, del_key, set_default_key, set_default_mgmt_key and set_default_beacon_key to support configuring keys specific to each MLO link. Userspace must not specify link ID for MLO pairwise key since it is common for all the MLO links. Signed-off-by: Veerendranath Jakkam Link: https://lore.kernel.org/r/20220730052643.1959111-4-quic_vjakkam@quicinc.com Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 37 +++++++++++++++++++++++++------------ 1 file changed, 25 insertions(+), 12 deletions(-) (limited to 'include/net') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 1d393e09a632..ffbc65a9b00b 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -3931,22 +3931,33 @@ struct mgmt_frame_regs { * @del_intf_link: Remove an MLO link from the given interface. * * @add_key: add a key with the given parameters. @mac_addr will be %NULL - * when adding a group key. + * when adding a group key. @link_id will be -1 for non-MLO connection. + * For MLO connection, @link_id will be >= 0 for group key and -1 for + * pairwise key, @mac_addr will be peer's MLD address for MLO pairwise key. * * @get_key: get information about the key with the given parameters. * @mac_addr will be %NULL when requesting information for a group * key. All pointers given to the @callback function need not be valid * after it returns. This function should return an error if it is * not possible to retrieve the key, -ENOENT if it doesn't exist. + * @link_id will be -1 for non-MLO connection. For MLO connection, + * @link_id will be >= 0 for group key and -1 for pairwise key, @mac_addr + * will be peer's MLD address for MLO pairwise key. * * @del_key: remove a key given the @mac_addr (%NULL for a group key) - * and @key_index, return -ENOENT if the key doesn't exist. + * and @key_index, return -ENOENT if the key doesn't exist. @link_id will + * be -1 for non-MLO connection. For MLO connection, @link_id will be >= 0 + * for group key and -1 for pairwise key, @mac_addr will be peer's MLD + * address for MLO pairwise key. * - * @set_default_key: set the default key on an interface + * @set_default_key: set the default key on an interface. @link_id will be >= 0 + * for MLO connection and -1 for non-MLO connection. * - * @set_default_mgmt_key: set the default management frame key on an interface + * @set_default_mgmt_key: set the default management frame key on an interface. + * @link_id will be >= 0 for MLO connection and -1 for non-MLO connection. * - * @set_default_beacon_key: set the default Beacon frame key on an interface + * @set_default_beacon_key: set the default Beacon frame key on an interface. + * @link_id will be >= 0 for MLO connection and -1 for non-MLO connection. * * @set_rekey_data: give the data necessary for GTK rekeying to the driver * @@ -4295,22 +4306,24 @@ struct cfg80211_ops { unsigned int link_id); int (*add_key)(struct wiphy *wiphy, struct net_device *netdev, - u8 key_index, bool pairwise, const u8 *mac_addr, - struct key_params *params); + int link_id, u8 key_index, bool pairwise, + const u8 *mac_addr, struct key_params *params); int (*get_key)(struct wiphy *wiphy, struct net_device *netdev, - u8 key_index, bool pairwise, const u8 *mac_addr, - void *cookie, + int link_id, u8 key_index, bool pairwise, + const u8 *mac_addr, void *cookie, void (*callback)(void *cookie, struct key_params*)); int (*del_key)(struct wiphy *wiphy, struct net_device *netdev, - u8 key_index, bool pairwise, const u8 *mac_addr); + int link_id, u8 key_index, bool pairwise, + const u8 *mac_addr); int (*set_default_key)(struct wiphy *wiphy, - struct net_device *netdev, + struct net_device *netdev, int link_id, u8 key_index, bool unicast, bool multicast); int (*set_default_mgmt_key)(struct wiphy *wiphy, - struct net_device *netdev, + struct net_device *netdev, int link_id, u8 key_index); int (*set_default_beacon_key)(struct wiphy *wiphy, struct net_device *netdev, + int link_id, u8 key_index); int (*start_ap)(struct wiphy *wiphy, struct net_device *dev, -- cgit v1.2.3 From ccdde7c74ffd7e8bdd3cf685bbfa41231c8e3131 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 17 Aug 2022 11:17:01 +0200 Subject: wifi: mac80211: properly implement MLO key handling Implement key installation and lookup (on TX and RX) for MLO, so we can use multiple GTKs/IGTKs/BIGTKs. Co-authored-by: Ilan Peer Signed-off-by: Ilan Peer Signed-off-by: Johannes Berg --- include/net/mac80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index f198af600b5e..7951400e509b 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1975,6 +1975,7 @@ enum ieee80211_key_flags { * - Temporal Authenticator Rx MIC Key (64 bits) * @icv_len: The ICV length for this key type * @iv_len: The IV length for this key type + * @link_id: the link ID for MLO, or -1 for non-MLO or pairwise keys */ struct ieee80211_key_conf { atomic64_t tx_pn; @@ -1984,6 +1985,7 @@ struct ieee80211_key_conf { u8 hw_key_idx; s8 keyidx; u16 flags; + s8 link_id; u8 keylen; u8 key[]; }; -- cgit v1.2.3 From ea9d807b56428d65cf43030cbd7ae5a580077147 Mon Sep 17 00:00:00 2001 From: Vasanthakumar Thiagarajan Date: Wed, 17 Aug 2022 16:12:12 +0530 Subject: wifi: mac80211: add link information in ieee80211_rx_status In MLO, when the address translation from link to MLD is done in fw/hw, it is necessary to be able to have some information on the link on which the frame has been received. Extend the rx API to include link_id and a valid flag in ieee80211_rx_status. Also make chanes to mac80211 rx APIs to make use of the reported link_id after sanity checks. Signed-off-by: Vasanthakumar Thiagarajan Link: https://lore.kernel.org/r/20220817104213.2531-2-quic_vthiagar@quicinc.com Signed-off-by: Johannes Berg --- include/net/mac80211.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 7951400e509b..b38927e33d10 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1480,6 +1480,10 @@ enum mac80211_rx_encoding { * each A-MPDU but the same for each subframe within one A-MPDU * @ampdu_delimiter_crc: A-MPDU delimiter CRC * @zero_length_psdu_type: radiotap type of the 0-length PSDU + * @link_valid: if the link which is identified by @link_id is valid. This flag + * is set only when connection is MLO. + * @link_id: id of the link used to receive the packet. This is used along with + * @link_valid. */ struct ieee80211_rx_status { u64 mactime; @@ -1504,6 +1508,7 @@ struct ieee80211_rx_status { s8 chain_signal[IEEE80211_MAX_CHAINS]; u8 ampdu_delimiter_crc; u8 zero_length_psdu_type; + u8 link_valid:1, link_id:4; }; static inline u32 -- cgit v1.2.3 From c73993b865bf0b2ea1cbb3e9616f18a6508fc49c Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 19 Aug 2022 13:12:38 +0200 Subject: wifi: mac80211: maintain link_id in link_sta To helper drivers if they e.g. have a lookup of the link_sta pointer, add the link ID to the link_sta structure. Signed-off-by: Johannes Berg --- include/net/mac80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index b38927e33d10..ffd0ebbff294 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2135,6 +2135,7 @@ struct ieee80211_sta_txpwr { * @addr: MAC address of the Link STA. For non-MLO STA this is same as the addr * in ieee80211_sta. For MLO Link STA this addr can be same or different * from addr in ieee80211_sta (representing MLD STA addr) + * @link_id: the link ID for this link STA (0 for deflink) * @supp_rates: Bitmap of supported rates * @ht_cap: HT capabilities of this STA; restricted to our own capabilities * @vht_cap: VHT capabilities of this STA; restricted to our own capabilities @@ -2151,6 +2152,7 @@ struct ieee80211_sta_txpwr { */ struct ieee80211_link_sta { u8 addr[ETH_ALEN]; + u8 link_id; u32 supp_rates[NUM_NL80211_BANDS]; struct ieee80211_sta_ht_cap ht_cap; -- cgit v1.2.3 From b8c9024e0ed03c5feb29bd1086a1eb799f3fff44 Mon Sep 17 00:00:00 2001 From: Veerendranath Jakkam Date: Fri, 22 Jul 2022 18:41:42 +0530 Subject: wifi: cfg80211: Add link_id to cfg80211_ch_switch_started_notify() Add link_id parameter to cfg80211_ch_switch_started_notify() to allow driver to indicate on which link channel switch started on MLD. Send the data to userspace so it knows as well. Signed-off-by: Veerendranath Jakkam Link: https://lore.kernel.org/r/20220722131143.3438042-1-quic_vjakkam@quicinc.com Link: https://lore.kernel.org/r/20220722131143.3438042-2-quic_vjakkam@quicinc.com [squash two patches] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index ffbc65a9b00b..e09ff87146c1 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -8281,6 +8281,7 @@ void cfg80211_ch_switch_notify(struct net_device *dev, * cfg80211_ch_switch_started_notify - notify channel switch start * @dev: the device on which the channel switch started * @chandef: the future channel definition + * @link_id: the link ID for MLO, must be 0 for non-MLO * @count: the number of TBTTs until the channel switch happens * @quiet: whether or not immediate quiet was requested by the AP * @@ -8290,7 +8291,8 @@ void cfg80211_ch_switch_notify(struct net_device *dev, */ void cfg80211_ch_switch_started_notify(struct net_device *dev, struct cfg80211_chan_def *chandef, - u8 count, bool quiet); + unsigned int link_id, u8 count, + bool quiet); /** * ieee80211_operating_class_to_band - convert operating class to band -- cgit v1.2.3 From c19d893fbf3f2f8fa864ae39652c7fee939edde2 Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Wed, 24 Aug 2022 08:52:31 +0800 Subject: net: sched: delete duplicate cleanup of backlog and qlen qdisc_reset() is clearing qdisc->q.qlen and qdisc->qstats.backlog _after_ calling qdisc->ops->reset. There is no need to clear them again in the specific reset function. Signed-off-by: Zhengchao Shao Link: https://lore.kernel.org/r/20220824005231.345727-1-shaozhengchao@huawei.com Signed-off-by: Paolo Abeni --- include/net/sch_generic.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/net') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index ec693fe7c553..f2958fb5ae08 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -1137,7 +1137,6 @@ static inline void __qdisc_reset_queue(struct qdisc_skb_head *qh) static inline void qdisc_reset_queue(struct Qdisc *sch) { __qdisc_reset_queue(&sch->q); - sch->qstats.backlog = 0; } static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new, -- cgit v1.2.3 From bb67012331f7f07ff325877fbbb430bc515d371e Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 24 Aug 2022 14:20:09 +0200 Subject: net: devlink: extend info_get() version put to indicate a flash component Whenever the driver is called by his info_get() op, it may put multiple version names and values to the netlink message. Extend by additional helper devlink_info_version_running/stored_put_ext() that allows to specify a version type that indicates when particular version name represents a flash component. This is going to be used in follow-up patch calling info_get() during flash update command checking if version with this the version type exists. Signed-off-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/net') diff --git a/include/net/devlink.h b/include/net/devlink.h index 119ed1ffb988..f50a002e5023 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1714,15 +1714,31 @@ int devlink_info_driver_name_put(struct devlink_info_req *req, const char *name); int devlink_info_board_serial_number_put(struct devlink_info_req *req, const char *bsn); + +enum devlink_info_version_type { + DEVLINK_INFO_VERSION_TYPE_NONE, + DEVLINK_INFO_VERSION_TYPE_COMPONENT, /* May be used as flash update + * component by name. + */ +}; + int devlink_info_version_fixed_put(struct devlink_info_req *req, const char *version_name, const char *version_value); int devlink_info_version_stored_put(struct devlink_info_req *req, const char *version_name, const char *version_value); +int devlink_info_version_stored_put_ext(struct devlink_info_req *req, + const char *version_name, + const char *version_value, + enum devlink_info_version_type version_type); int devlink_info_version_running_put(struct devlink_info_req *req, const char *version_name, const char *version_value); +int devlink_info_version_running_put_ext(struct devlink_info_req *req, + const char *version_name, + const char *version_value, + enum devlink_info_version_type version_type); int devlink_fmsg_obj_nest_start(struct devlink_fmsg *fmsg); int devlink_fmsg_obj_nest_end(struct devlink_fmsg *fmsg); -- cgit v1.2.3 From f94b606325c194adadaee2265b4db990802c4850 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 24 Aug 2022 14:20:11 +0200 Subject: net: devlink: limit flash component name to match version returned by info_get() Limit the acceptance of component name passed to cmd_flash_update() to match one of the versions returned by info_get(), marked by version type. This makes things clearer and enforces 1:1 mapping between exposed version and accepted flash component. Check VERSION_TYPE_COMPONENT version type during cmd_flash_update() execution by calling info_get() with different "req" context. That causes info_get() to lookup the component name instead of filling-up the netlink message. Remove "UPDATE_COMPONENT" flag which becomes used. Signed-off-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/devlink.h b/include/net/devlink.h index f50a002e5023..1f7026011856 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -624,8 +624,7 @@ struct devlink_flash_update_params { u32 overwrite_mask; }; -#define DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT BIT(0) -#define DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK BIT(1) +#define DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK BIT(0) struct devlink_region; struct devlink_info_req; -- cgit v1.2.3 From c249ea9b4309cf3250c5bbb42a05d38d0ed9071c Mon Sep 17 00:00:00 2001 From: Brian Gix Date: Fri, 5 Aug 2022 16:42:32 -0700 Subject: Bluetooth: Move Adv Instance timer to hci_sync The Advertising Instance expiration timer adv_instance_expire was handled with the deprecated hci_request mechanism, rather than it's replacement: hci_sync. Signed-off-by: Brian Gix Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_sync.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h index 3843f5060c73..aea950440b9d 100644 --- a/include/net/bluetooth/hci_sync.h +++ b/include/net/bluetooth/hci_sync.h @@ -72,7 +72,8 @@ int hci_start_per_adv_sync(struct hci_dev *hdev, u8 instance, u8 data_len, int hci_remove_advertising_sync(struct hci_dev *hdev, struct sock *sk, u8 instance, bool force); int hci_disable_advertising_sync(struct hci_dev *hdev); - +int hci_clear_adv_instance_sync(struct hci_dev *hdev, struct sock *sk, + u8 instance, bool force); int hci_update_passive_scan_sync(struct hci_dev *hdev); int hci_update_passive_scan(struct hci_dev *hdev); int hci_read_rssi_sync(struct hci_dev *hdev, __le16 handle); -- cgit v1.2.3 From 3fe318ee72c54506534f51b4b4dfb19e0e0df2db Mon Sep 17 00:00:00 2001 From: Brian Gix Date: Fri, 5 Aug 2022 16:42:34 -0700 Subject: Bluetooth: move hci_get_random_address() to hci_sync This function has no dependencies on the deprecated hci_request mechanism, so has been moved unchanged to hci_sync.c Signed-off-by: Brian Gix Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_sync.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/net') diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h index aea950440b9d..b6b975c2ed3e 100644 --- a/include/net/bluetooth/hci_sync.h +++ b/include/net/bluetooth/hci_sync.h @@ -16,6 +16,7 @@ struct hci_cmd_sync_work_entry { hci_cmd_sync_work_destroy_t destroy; }; +struct adv_info; /* Function with sync suffix shall not be called with hdev->lock held as they * wait the command to complete and in the meantime an event could be received * which could attempt to acquire hdev->lock causing a deadlock. @@ -51,6 +52,10 @@ int hci_update_class_sync(struct hci_dev *hdev); int hci_update_name_sync(struct hci_dev *hdev); int hci_write_ssp_mode_sync(struct hci_dev *hdev, u8 mode); +int hci_get_random_address(struct hci_dev *hdev, bool require_privacy, + bool use_rpa, struct adv_info *adv_instance, + u8 *own_addr_type, bdaddr_t *rand_addr); + int hci_update_random_address_sync(struct hci_dev *hdev, bool require_privacy, bool rpa, u8 *own_addr_type); -- cgit v1.2.3 From 651cd3d65b0f76a2198fcf3a80ce5d53dd267717 Mon Sep 17 00:00:00 2001 From: Brian Gix Date: Fri, 5 Aug 2022 16:42:35 -0700 Subject: Bluetooth: convert hci_update_adv_data to hci_sync hci_update_adv_data() is called from hci_event and hci_core due to events from the controller. The prior function used the deprecated hci_request method, and the new one uses hci_sync.c Signed-off-by: Brian Gix Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_sync.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h index b6b975c2ed3e..17f5a4c32f36 100644 --- a/include/net/bluetooth/hci_sync.h +++ b/include/net/bluetooth/hci_sync.h @@ -61,6 +61,7 @@ int hci_update_random_address_sync(struct hci_dev *hdev, bool require_privacy, int hci_update_scan_rsp_data_sync(struct hci_dev *hdev, u8 instance); int hci_update_adv_data_sync(struct hci_dev *hdev, u8 instance); +int hci_update_adv_data(struct hci_dev *hdev, u8 instance); int hci_schedule_adv_instance_sync(struct hci_dev *hdev, u8 instance, bool force); -- cgit v1.2.3 From 44387d1736c40a74085be354e2b5f37ca0689608 Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Wed, 24 Aug 2022 17:10:03 +0800 Subject: net: sched: remove unnecessary init of qdisc skb head The memory allocated by using kzallloc_node and kcalloc has been cleared. Therefore, the structure members of the new qdisc are 0. So there's no need to explicitly assign a value of 0. Signed-off-by: Zhengchao Shao Signed-off-by: David S. Miller --- include/net/sch_generic.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/net') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index f2958fb5ae08..7dc83400bde4 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -940,13 +940,6 @@ static inline void qdisc_purge_queue(struct Qdisc *sch) qdisc_tree_reduce_backlog(sch, qlen, backlog); } -static inline void qdisc_skb_head_init(struct qdisc_skb_head *qh) -{ - qh->head = NULL; - qh->tail = NULL; - qh->qlen = 0; -} - static inline void __qdisc_enqueue_tail(struct sk_buff *skb, struct qdisc_skb_head *qh) { -- cgit v1.2.3 From 5182a5d48c3d1992b2db8748f96914e07eee0956 Mon Sep 17 00:00:00 2001 From: Eyal Birger Date: Fri, 26 Aug 2022 14:46:58 +0300 Subject: net: allow storing xfrm interface metadata in metadata_dst XFRM interfaces provide the association of various XFRM transformations to a netdevice using an 'if_id' identifier common to both the XFRM data structures (polcies, states) and the interface. The if_id is configured by the controlling entity (usually the IKE daemon) and can be used by the administrator to define logical relations between different connections. For example, different connections can share the if_id identifier so that they pass through the same interface, . However, currently it is not possible for connections using a different if_id to use the same interface while retaining the logical separation between them, without using additional criteria such as skb marks or different traffic selectors. When having a large number of connections, it is useful to have a the logical separation offered by the if_id identifier but use a single network interface. Similar to the way collect_md mode is used in IP tunnels. This patch attempts to enable different configuration mechanisms - such as ebpf programs, LWT encapsulations, and TC - to attach metadata to skbs which would carry the if_id. This way a single xfrm interface in collect_md mode can demux traffic based on this configuration on tx and provide this metadata on rx. The XFRM metadata is somewhat similar to ip tunnel metadata in that it has an "id", and shares similar configuration entities (bpf, tc, ...), however, it does not necessarily represent an IP tunnel or use other ip tunnel information, and also has an optional "link" property which can be used for affecting underlying routing decisions. Additional xfrm related criteria may also be added in the future. Therefore, a new metadata type is introduced, to be used in subsequent patches in the xfrm interface and configuration entities. Reviewed-by: Nikolay Aleksandrov Reviewed-by: Nicolas Dichtel Signed-off-by: Eyal Birger Signed-off-by: Steffen Klassert --- include/net/dst_metadata.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/net') diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index adab27ba1ecb..e4b059908cc7 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -9,6 +9,7 @@ enum metadata_type { METADATA_IP_TUNNEL, METADATA_HW_PORT_MUX, + METADATA_XFRM, }; struct hw_port_info { @@ -16,12 +17,18 @@ struct hw_port_info { u32 port_id; }; +struct xfrm_md_info { + u32 if_id; + int link; +}; + struct metadata_dst { struct dst_entry dst; enum metadata_type type; union { struct ip_tunnel_info tun_info; struct hw_port_info port_info; + struct xfrm_md_info xfrm_info; } u; }; @@ -53,6 +60,16 @@ skb_tunnel_info(const struct sk_buff *skb) return NULL; } +static inline struct xfrm_md_info *skb_xfrm_md_info(const struct sk_buff *skb) +{ + struct metadata_dst *md_dst = skb_metadata_dst(skb); + + if (md_dst && md_dst->type == METADATA_XFRM) + return &md_dst->u.xfrm_info; + + return NULL; +} + static inline bool skb_valid_dst(const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); @@ -82,6 +99,9 @@ static inline int skb_metadata_dst_cmp(const struct sk_buff *skb_a, return memcmp(&a->u.tun_info, &b->u.tun_info, sizeof(a->u.tun_info) + a->u.tun_info.options_len); + case METADATA_XFRM: + return memcmp(&a->u.xfrm_info, &b->u.xfrm_info, + sizeof(a->u.xfrm_info)); default: return 1; } -- cgit v1.2.3 From abc340b38ba25cd6c7aa2c0bd9150d30738c82d0 Mon Sep 17 00:00:00 2001 From: Eyal Birger Date: Fri, 26 Aug 2022 14:46:59 +0300 Subject: xfrm: interface: support collect metadata mode This commit adds support for 'collect_md' mode on xfrm interfaces. Each net can have one collect_md device, created by providing the IFLA_XFRM_COLLECT_METADATA flag at creation. This device cannot be altered and has no if_id or link device attributes. On transmit to this device, the if_id is fetched from the attached dst metadata on the skb. If exists, the link property is also fetched from the metadata. The dst metadata type used is METADATA_XFRM which holds these properties. On the receive side, xfrmi_rcv_cb() populates a dst metadata for each packet received and attaches it to the skb. The if_id used in this case is fetched from the xfrm state, and the link is fetched from the incoming device. This information can later be used by upper layers such as tc, ebpf, and ip rules. Because the skb is scrubed in xfrmi_rcv_cb(), the attachment of the dst metadata is postponed until after scrubing. Similarly, xfrm_input() is adapted to avoid dropping metadata dsts by only dropping 'valid' (skb_valid_dst(skb) == true) dsts. Policy matching on packets arriving from collect_md xfrmi devices is done by using the xfrm state existing in the skb's sec_path. The xfrm_if_cb.decode_cb() interface implemented by xfrmi_decode_session() is changed to keep the details of the if_id extraction tucked away in xfrm_interface.c. Reviewed-by: Nicolas Dichtel Reviewed-by: Nikolay Aleksandrov Signed-off-by: Eyal Birger Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 6e8fa98f786f..28b988577ed2 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -312,9 +312,15 @@ struct km_event { struct net *net; }; +struct xfrm_if_decode_session_result { + struct net *net; + u32 if_id; +}; + struct xfrm_if_cb { - struct xfrm_if *(*decode_session)(struct sk_buff *skb, - unsigned short family); + bool (*decode_session)(struct sk_buff *skb, + unsigned short family, + struct xfrm_if_decode_session_result *res); }; void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb); @@ -985,6 +991,7 @@ void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev); struct xfrm_if_parms { int link; /* ifindex of underlying L2 interface */ u32 if_id; /* interface identifyer */ + bool collect_md; }; struct xfrm_if { -- cgit v1.2.3 From 2c2493b9da9166478fe072e3054f8a5741dadb02 Mon Sep 17 00:00:00 2001 From: Eyal Birger Date: Fri, 26 Aug 2022 14:47:00 +0300 Subject: xfrm: lwtunnel: add lwtunnel support for xfrm interfaces in collect_md mode Allow specifying the xfrm interface if_id and link as part of a route metadata using the lwtunnel infrastructure. This allows for example using a single xfrm interface in collect_md mode as the target of multiple routes each specifying a different if_id. With the appropriate changes to iproute2, considering an xfrm device ipsec1 in collect_md mode one can for example add a route specifying an if_id like so: ip route add dev ipsec1 encap xfrm if_id 1 In which case traffic routed to the device via this route would use if_id in the xfrm interface policy lookup. Or in the context of vrf, one can also specify the "link" property: ip route add dev ipsec1 encap xfrm if_id 1 link_dev eth15 Note: LWT_XFRM_LINK uses NLA_U32 similar to IFLA_XFRM_LINK even though internally "link" is signed. This is consistent with other _LINK attributes in other devices as well as in bpf and should not have an effect as device indexes can't be negative. Reviewed-by: Nicolas Dichtel Reviewed-by: Nikolay Aleksandrov Signed-off-by: Eyal Birger Signed-off-by: Steffen Klassert --- include/net/dst_metadata.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/net') diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index e4b059908cc7..57f75960fa28 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -60,13 +60,24 @@ skb_tunnel_info(const struct sk_buff *skb) return NULL; } +static inline struct xfrm_md_info *lwt_xfrm_info(struct lwtunnel_state *lwt) +{ + return (struct xfrm_md_info *)lwt->data; +} + static inline struct xfrm_md_info *skb_xfrm_md_info(const struct sk_buff *skb) { struct metadata_dst *md_dst = skb_metadata_dst(skb); + struct dst_entry *dst; if (md_dst && md_dst->type == METADATA_XFRM) return &md_dst->u.xfrm_info; + dst = skb_dst(skb); + if (dst && dst->lwtstate && + dst->lwtstate->type == LWTUNNEL_ENCAP_XFRM) + return lwt_xfrm_info(dst->lwtstate); + return NULL; } -- cgit v1.2.3 From 9c5d03d362519f36cd551aec596388f895c93d2d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 24 Aug 2022 17:18:30 -0700 Subject: genetlink: start to validate reserved header bytes We had historically not checked that genlmsghdr.reserved is 0 on input which prevents us from using those precious bytes in the future. One use case would be to extend the cmd field, which is currently just 8 bits wide and 256 is not a lot of commands for some core families. To make sure that new families do the right thing by default put the onus of opting out of validation on existing families. Signed-off-by: Jakub Kicinski Acked-by: Paul Moore (NetLabel) Signed-off-by: David S. Miller --- include/net/genetlink.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/net') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 56a50e1c51b9..a4827b5e1e07 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -39,6 +39,8 @@ struct genl_info; * undo operations done by pre_doit, for example release locks * @mcgrps: multicast groups used by this family * @n_mcgrps: number of multicast groups + * @resv_start_op: first operation for which reserved fields of the header + * can be validated, new families should leave this field at zero * @mcgrp_offset: starting number of multicast group IDs in this family * (private) * @ops: the operations supported by this family @@ -58,6 +60,7 @@ struct genl_family { u8 n_ops; u8 n_small_ops; u8 n_mcgrps; + u8 resv_start_op; const struct nla_policy *policy; int (*pre_doit)(const struct genl_ops *ops, struct sk_buff *skb, -- cgit v1.2.3 From 45dca15759643806660e9285e6af8a1ba3c76c82 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 25 Aug 2022 20:09:32 -0700 Subject: netlink: add helpers for extack attr presence checking Being able to check attribute presence and set extack if not on one line is handy, add helpers. Reviewed-by: Johannes Berg Signed-off-by: Jakub Kicinski Signed-off-by: Paolo Abeni --- include/net/genetlink.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/net') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index a4827b5e1e07..8f780170e2f8 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -110,6 +110,13 @@ static inline void genl_info_net_set(struct genl_info *info, struct net *net) #define GENL_SET_ERR_MSG(info, msg) NL_SET_ERR_MSG((info)->extack, msg) +/* Report that a root attribute is missing */ +#define GENL_REQ_ATTR_CHECK(info, attr) ({ \ + struct genl_info *__info = (info); \ + \ + NL_REQ_ATTR_CHECK(__info->extack, NULL, __info->attrs, (attr)); \ +}) + enum genl_validate_flags { GENL_DONT_VALIDATE_STRICT = BIT(0), GENL_DONT_VALIDATE_DUMP = BIT(1), -- cgit v1.2.3 From 146ecbac1d327e7ed2153cfb3ef880166dc2b312 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 26 Aug 2022 10:27:30 +0200 Subject: net: devlink: stub port params cmds for they are unused internally Follow-up the removal of unused internal api of port params made by commit 42ded61aa75e ("devlink: Delete not used port parameters APIs") and stub the commands and add extack message to tell the user what is going on. If later on port params are needed, could be easily re-introduced, but until then it is a dead code. Signed-off-by: Jiri Pirko Reviewed-by: Jakub Kicinski Link: https://lore.kernel.org/r/20220826082730.1399735-1-jiri@resnulli.us Signed-off-by: Paolo Abeni --- include/net/devlink.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/net') diff --git a/include/net/devlink.h b/include/net/devlink.h index 1f7026011856..264aa98e6da6 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -118,7 +118,6 @@ struct devlink_rate { struct devlink_port { struct list_head list; - struct list_head param_list; struct list_head region_list; struct devlink *devlink; unsigned int index; -- cgit v1.2.3 From 1a942de092c0b96216864fedcb4d8822ce3fc12e Mon Sep 17 00:00:00 2001 From: Brian Gix Date: Tue, 16 Aug 2022 09:41:20 -0700 Subject: Bluetooth: Move hci_abort_conn to hci_conn.c hci_abort_conn() is a wrapper around a number of DISCONNECT and CREATE_CONN_CANCEL commands that was being invoked from hci_request request queues, which are now deprecated. There are two versions: hci_abort_conn() which can be invoked from the hci_event thread, and hci_abort_conn_sync() which can be invoked within a hci_sync cmd chain. Signed-off-by: Brian Gix Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index e7862903187d..932153e68864 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -2075,6 +2075,7 @@ int mgmt_phy_configuration_changed(struct hci_dev *hdev, struct sock *skip); void mgmt_adv_monitor_device_lost(struct hci_dev *hdev, u16 handle, bdaddr_t *bdaddr, u8 addr_type); +int hci_abort_conn(struct hci_conn *conn, u8 reason); u8 hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, u16 to_multiplier); void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __le64 rand, -- cgit v1.2.3 From 4516c873e3b55856012ddd6db9d4366ce3c60c5d Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Tue, 30 Aug 2022 17:22:55 +0800 Subject: net: sched: gred/red: remove unused variables in struct red_stats The variable "other" in the struct red_stats is not used. Remove it. Signed-off-by: Zhengchao Shao Signed-off-by: Jakub Kicinski --- include/net/red.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/net') diff --git a/include/net/red.h b/include/net/red.h index be11dbd26492..454ac2b65d8c 100644 --- a/include/net/red.h +++ b/include/net/red.h @@ -122,7 +122,6 @@ struct red_stats { u32 forced_drop; /* Forced drops, qavg > max_thresh */ u32 forced_mark; /* Forced marks, qavg > max_thresh */ u32 pdrop; /* Drops due to queue limits */ - u32 other; /* Drops due to drop() calls */ }; struct red_parms { -- cgit v1.2.3 From 8254393663f9b8cb8b84cdce1abb118833c22a54 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Thu, 1 Sep 2022 20:06:20 -0700 Subject: net: ieee802154: Fix compilation error when CONFIG_IEEE802154_NL802154_EXPERIMENTAL is disabled When CONFIG_IEEE802154_NL802154_EXPERIMENTAL is disabled, NL802154_CMD_DEL_SEC_LEVEL is undefined and results in a compilation error: net/ieee802154/nl802154.c:2503:19: error: 'NL802154_CMD_DEL_SEC_LEVEL' undeclared here (not in a function); did you mean 'NL802154_CMD_SET_CCA_ED_LEVEL'? 2503 | .resv_start_op = NL802154_CMD_DEL_SEC_LEVEL + 1, | ^~~~~~~~~~~~~~~~~~~~~~~~~~ | NL802154_CMD_SET_CCA_ED_LEVEL Unhide the experimental commands, having them defined in an enum makes no difference. Fixes: 9c5d03d36251 ("genetlink: start to validate reserved header bytes") Signed-off-by: Gal Pressman Acked-by: Stefan Schmidt Tested-by: Sudip Mukherjee Link: https://lore.kernel.org/r/20220902030620.2737091-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/net/nl802154.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/nl802154.h b/include/net/nl802154.h index 145acb8f2509..f5850b569c52 100644 --- a/include/net/nl802154.h +++ b/include/net/nl802154.h @@ -58,9 +58,6 @@ enum nl802154_commands { NL802154_CMD_SET_WPAN_PHY_NETNS, - /* add new commands above here */ - -#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL NL802154_CMD_SET_SEC_PARAMS, NL802154_CMD_GET_SEC_KEY, /* can dump */ NL802154_CMD_NEW_SEC_KEY, @@ -74,7 +71,8 @@ enum nl802154_commands { NL802154_CMD_GET_SEC_LEVEL, /* can dump */ NL802154_CMD_NEW_SEC_LEVEL, NL802154_CMD_DEL_SEC_LEVEL, -#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ + + /* add new commands above here */ /* used to define NL802154_CMD_MAX below */ __NL802154_CMD_AFTER_LAST, -- cgit v1.2.3 From 6dadbe4bac68309eb46ab0f30e8ff47a789df49a Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 1 Sep 2022 17:28:53 -0700 Subject: bpf: net: Change do_ipv6_getsockopt() to take the sockptr_t argument Similar to the earlier patch that changes sk_getsockopt() to take the sockptr_t argument . This patch also changes do_ipv6_getsockopt() to take the sockptr_t argument such that a latter patch can make bpf_getsockopt(SOL_IPV6) to reuse do_ipv6_getsockopt(). Note on the change in ip6_mc_msfget(). This function is to return an array of sockaddr_storage in optval. This function is shared between ipv6_get_msfilter() and compat_ipv6_get_msfilter(). However, the sockaddr_storage is stored at different offset of the optval because of the difference between group_filter and compat_group_filter. Thus, a new 'ss_offset' argument is added to ip6_mc_msfget(). Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20220902002853.2892532-1-kafai@fb.com Signed-off-by: Alexei Starovoitov --- include/net/ipv6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index c110d9032083..a4f24573ed7a 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1209,7 +1209,7 @@ int ip6_mc_source(int add, int omode, struct sock *sk, int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf, struct sockaddr_storage *list); int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, - struct sockaddr_storage __user *p); + sockptr_t optval, size_t ss_offset); #ifdef CONFIG_PROC_FS int ac6_proc_init(struct net *net); -- cgit v1.2.3 From 65ddc82d3b96be5555a36de4e2b4547433a00532 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 1 Sep 2022 17:29:12 -0700 Subject: bpf: Change bpf_getsockopt(SOL_SOCKET) to reuse sk_getsockopt() This patch changes bpf_getsockopt(SOL_SOCKET) to reuse sk_getsockopt(). It removes all duplicated code from bpf_getsockopt(SOL_SOCKET). Before this patch, there were some optnames available to bpf_setsockopt(SOL_SOCKET) but missing in bpf_getsockopt(SOL_SOCKET). It surprises users from time to time. For example, SO_REUSEADDR, SO_KEEPALIVE, SO_RCVLOWAT, and SO_MAX_PACING_RATE. This patch automatically closes this gap without duplicating more code. The only exception is SO_BINDTODEVICE because it needs to acquire a blocking lock. Thus, SO_BINDTODEVICE is not supported. Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20220902002912.2894040-1-kafai@fb.com Signed-off-by: Alexei Starovoitov --- include/net/sock.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index ee44b424d952..ea7965524133 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1833,6 +1833,8 @@ int sk_setsockopt(struct sock *sk, int level, int optname, int sock_setsockopt(struct socket *sock, int level, int op, sockptr_t optval, unsigned int optlen); +int sk_getsockopt(struct sock *sk, int level, int optname, + sockptr_t optval, sockptr_t optlen); int sock_getsockopt(struct socket *sock, int level, int op, char __user *optval, int __user *optlen); int sock_gettstamp(struct socket *sock, void __user *userstamp, -- cgit v1.2.3 From 273b7f0fb44847c41814a59901977be284daa447 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 1 Sep 2022 17:29:18 -0700 Subject: bpf: Change bpf_getsockopt(SOL_TCP) to reuse do_tcp_getsockopt() This patch changes bpf_getsockopt(SOL_TCP) to reuse do_tcp_getsockopt(). It removes the duplicated code from bpf_getsockopt(SOL_TCP). Before this patch, there were some optnames available to bpf_setsockopt(SOL_TCP) but missing in bpf_getsockopt(SOL_TCP). For example, TCP_NODELAY, TCP_MAXSEG, TCP_KEEPIDLE, TCP_KEEPINTVL, and a few more. It surprises users from time to time. This patch automatically closes this gap without duplicating more code. bpf_getsockopt(TCP_SAVED_SYN) does not free the saved_syn, so it stays in sol_tcp_sockopt(). For string name value like TCP_CONGESTION, bpf expects it is always null terminated, so sol_tcp_sockopt() decrements optlen by one before calling do_tcp_getsockopt() and the 'if (optlen < saved_optlen) memset(..,0,..);' in __bpf_getsockopt() will always do a null termination. Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20220902002918.2894511-1-kafai@fb.com Signed-off-by: Alexei Starovoitov --- include/net/tcp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index c03a50c72f40..735e957f7f4b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -402,6 +402,8 @@ void tcp_init_sock(struct sock *sk); void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb); __poll_t tcp_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); +int do_tcp_getsockopt(struct sock *sk, int level, + int optname, sockptr_t optval, sockptr_t optlen); int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); bool tcp_bpf_bypass_getsockopt(int level, int optname); -- cgit v1.2.3 From fd969f25fe24be515278d28cbf86dde39be8a495 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 1 Sep 2022 17:29:25 -0700 Subject: bpf: Change bpf_getsockopt(SOL_IP) to reuse do_ip_getsockopt() This patch changes bpf_getsockopt(SOL_IP) to reuse do_ip_getsockopt() and remove the duplicated code. Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20220902002925.2895416-1-kafai@fb.com Signed-off-by: Alexei Starovoitov --- include/net/ip.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/ip.h b/include/net/ip.h index 34fa5b0f0a0e..038097c2a152 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -747,6 +747,8 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); +int do_ip_getsockopt(struct sock *sk, int level, int optname, + sockptr_t optval, sockptr_t optlen); int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); int ip_ra_control(struct sock *sk, unsigned char on, -- cgit v1.2.3 From 38566ec06f52250c4abaa7447aae676e0b881c46 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 1 Sep 2022 17:29:31 -0700 Subject: bpf: Change bpf_getsockopt(SOL_IPV6) to reuse do_ipv6_getsockopt() This patch changes bpf_getsockopt(SOL_IPV6) to reuse do_ipv6_getsockopt(). It removes the duplicated code from bpf_getsockopt(SOL_IPV6). This also makes bpf_getsockopt(SOL_IPV6) supporting the same set of optnames as in bpf_setsockopt(SOL_IPV6). In particular, this adds IPV6_AUTOFLOWLABEL support to bpf_getsockopt(SOL_IPV6). ipv6 could be compiled as a module. Like how other code solved it with stubs in ipv6_stubs.h, this patch adds the do_ipv6_getsockopt to the ipv6_bpf_stub. Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20220902002931.2896218-1-kafai@fb.com Signed-off-by: Alexei Starovoitov --- include/net/ipv6.h | 2 ++ include/net/ipv6_stubs.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/net') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index a4f24573ed7a..d664ba5812d8 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1160,6 +1160,8 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval unsigned int optlen); int ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); +int do_ipv6_getsockopt(struct sock *sk, int level, int optname, + sockptr_t optval, sockptr_t optlen); int ipv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index 8692698b01cf..c48186bf4737 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -83,6 +83,8 @@ struct ipv6_bpf_stub { struct sk_buff *skb); int (*ipv6_setsockopt)(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); + int (*ipv6_getsockopt)(struct sock *sk, int level, int optname, + sockptr_t optval, sockptr_t optlen); }; extern const struct ipv6_bpf_stub *ipv6_bpf_stub __read_mostly; -- cgit v1.2.3 From 261ce8879578f42bc1ff3385ff1be8e31d6fb160 Mon Sep 17 00:00:00 2001 From: Benjamin Berg Date: Fri, 2 Sep 2022 16:12:41 +0200 Subject: wifi: mac80211: make smps_mode per-link The SMPS power save mode needs to be per-link rather than being shared for all links. As such, move it into struct ieee80211_link_sta. Signed-off-by: Benjamin Berg Signed-off-by: Johannes Berg --- include/net/mac80211.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index ffd0ebbff294..d4e1d73d88cc 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2136,6 +2136,7 @@ struct ieee80211_sta_txpwr { * in ieee80211_sta. For MLO Link STA this addr can be same or different * from addr in ieee80211_sta (representing MLD STA addr) * @link_id: the link ID for this link STA (0 for deflink) + * @smps_mode: current SMPS mode (off, static or dynamic) * @supp_rates: Bitmap of supported rates * @ht_cap: HT capabilities of this STA; restricted to our own capabilities * @vht_cap: VHT capabilities of this STA; restricted to our own capabilities @@ -2153,6 +2154,7 @@ struct ieee80211_sta_txpwr { struct ieee80211_link_sta { u8 addr[ETH_ALEN]; u8 link_id; + enum ieee80211_smps_mode smps_mode; u32 supp_rates[NUM_NL80211_BANDS]; struct ieee80211_sta_ht_cap ht_cap; @@ -2191,7 +2193,6 @@ struct ieee80211_link_sta { * if wme is supported. The bits order is like in * IEEE80211_WMM_IE_STA_QOSINFO_AC_*. * @max_sp: max Service Period. Only valid if wme is supported. - * @smps_mode: current SMPS mode (off, static or dynamic) * @rates: rate control selection table * @tdls: indicates whether the STA is a TDLS peer * @tdls_initiator: indicates the STA is an initiator of the TDLS link. Only @@ -2226,7 +2227,6 @@ struct ieee80211_sta { bool wme; u8 uapsd_queues; u8 max_sp; - enum ieee80211_smps_mode smps_mode; struct ieee80211_sta_rates __rcu *rates; bool tdls; bool tdls_initiator; -- cgit v1.2.3 From efe9c2bfd1a82894e455514a68dc794556fbd463 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 2 Sep 2022 16:12:42 +0200 Subject: wifi: mac80211: isolate driver from inactive links In order to let the driver select active links and properly make multi-link connections, as a first step isolate the driver from inactive links, and set the active links to be only the association link for client-side interfaces. For AP side nothing changes since APs always have to have all their links active. To simplify things, update the for_each_sta_active_link() API to include the appropriate vif pointer. This also implies not allocating a chanctx for an inactive link, which requires a few more changes. Since we now no longer try to program multiple links to the driver, remove the check in the MLME code. Signed-off-by: Johannes Berg --- include/net/mac80211.h | 30 ++++++++++++++++-------------- 1 file changed, 16 insertions(+), 14 deletions(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index d4e1d73d88cc..20a2f25a38fa 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1799,6 +1799,9 @@ struct ieee80211_vif_cfg { * @link_conf: in case of MLD, the per-link BSS configuration, * indexed by link ID * @valid_links: bitmap of valid links, or 0 for non-MLO. + * @active_links: The bitmap of active links, or 0 for non-MLO. + * The driver shouldn't change this directly, but use the + * API calls meant for that purpose. * @addr: address of this interface * @p2p: indicates whether this AP or STA interface is a p2p * interface, i.e. a GO or p2p-sta respectively @@ -1834,7 +1837,7 @@ struct ieee80211_vif { struct ieee80211_vif_cfg cfg; struct ieee80211_bss_conf bss_conf; struct ieee80211_bss_conf __rcu *link_conf[IEEE80211_MLD_MAX_NUM_LINKS]; - u16 valid_links; + u16 valid_links, active_links; u8 addr[ETH_ALEN] __aligned(2); bool p2p; @@ -1861,12 +1864,11 @@ struct ieee80211_vif { u8 drv_priv[] __aligned(sizeof(void *)); }; -/* FIXME: for now loop over all the available links; later will be changed - * to loop only over the active links. - */ -#define for_each_vif_active_link(vif, link, link_id) \ - for (link_id = 0; link_id < ARRAY_SIZE((vif)->link_conf); link_id++) \ - if ((link = rcu_dereference((vif)->link_conf[link_id]))) +#define for_each_vif_active_link(vif, link, link_id) \ + for (link_id = 0; link_id < ARRAY_SIZE((vif)->link_conf); link_id++) \ + if ((!(vif)->active_links || \ + (vif)->active_links & BIT(link_id)) && \ + (link = rcu_dereference((vif)->link_conf[link_id]))) static inline bool ieee80211_vif_is_mesh(struct ieee80211_vif *vif) { @@ -2264,13 +2266,13 @@ struct ieee80211_sta { u8 drv_priv[] __aligned(sizeof(void *)); }; -/* FIXME: need to loop only over links which are active and check the actual - * lock - */ -#define for_each_sta_active_link(sta, link_sta, link_id) \ - for (link_id = 0; link_id < ARRAY_SIZE((sta)->link); link_id++) \ - if (((link_sta) = rcu_dereference_protected((sta)->link[link_id],\ - 1))) \ +/* FIXME: check the locking correctly */ +#define for_each_sta_active_link(vif, sta, link_sta, link_id) \ + for (link_id = 0; link_id < ARRAY_SIZE((sta)->link); link_id++) \ + if ((!(vif)->active_links || \ + (vif)->active_links & BIT(link_id)) && \ + ((link_sta) = rcu_dereference_protected((sta)->link[link_id],\ + 1))) /** * enum sta_notify_cmd - sta notify command -- cgit v1.2.3 From ffa9598ecb93630a45564b95ae17362b819b38de Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 2 Sep 2022 16:12:43 +0200 Subject: wifi: mac80211: add ieee80211_find_sta_by_link_addrs API Add a new API function ieee80211_find_sta_by_link_addrs() that looks up the STA and link ID based on interface and station link addresses. We're going to use it for mac80211-hwsim to track on the AP side which links are active. Signed-off-by: Johannes Berg --- include/net/mac80211.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 20a2f25a38fa..954cc029a9f9 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -5986,6 +5986,22 @@ struct ieee80211_sta *ieee80211_find_sta_by_ifaddr(struct ieee80211_hw *hw, const u8 *addr, const u8 *localaddr); +/** + * ieee80211_find_sta_by_link_addrs - find STA by link addresses + * @hw: pointer as obtained from ieee80211_alloc_hw() + * @addr: remote station's link address + * @localaddr: local link address, use %NULL for any (but avoid that) + * @link_id: pointer to obtain the link ID if the STA is found, + * may be %NULL if the link ID is not needed + * + * Obtain the STA by link address, must use RCU protection. + */ +struct ieee80211_sta * +ieee80211_find_sta_by_link_addrs(struct ieee80211_hw *hw, + const u8 *addr, + const u8 *localaddr, + unsigned int *link_id); + /** * ieee80211_sta_block_awake - block station from waking up * @hw: the hardware -- cgit v1.2.3 From 0ab26380d98655f0aab720704debfa2ac522cefd Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 2 Sep 2022 16:12:47 +0200 Subject: wifi: mac80211: extend ieee80211_nullfunc_get() for MLO Add a link_id parameter to ieee80211_nullfunc_get() to be able to obtain a correctly addressed frame. Signed-off-by: Johannes Berg --- include/net/mac80211.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 954cc029a9f9..bfa6a1625c5c 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -5298,6 +5298,9 @@ struct sk_buff *ieee80211_pspoll_get(struct ieee80211_hw *hw, * ieee80211_nullfunc_get - retrieve a nullfunc template * @hw: pointer obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * @link_id: If the vif is an MLD, get a frame with the link addresses + * for the given link ID. For a link_id < 0 you get a frame with + * MLD addresses, however useful that might be. * @qos_ok: QoS NDP is acceptable to the caller, this should be set * if at all possible * @@ -5315,7 +5318,7 @@ struct sk_buff *ieee80211_pspoll_get(struct ieee80211_hw *hw, */ struct sk_buff *ieee80211_nullfunc_get(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - bool qos_ok); + int link_id, bool qos_ok); /** * ieee80211_probereq_get - retrieve a Probe Request template -- cgit v1.2.3 From 65fd846cb3f94ae63134fbd0f32564cf82539eaa Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 2 Sep 2022 16:12:52 +0200 Subject: wifi: mac80211: add vif/sta link RCU dereference macros Add macros (and an exported function) to allow checking some link RCU protected accesses that are happening in callbacks from mac80211 and are thus under the correct lock. Signed-off-by: Johannes Berg --- include/net/mac80211.h | 31 ++++++++++++++++++++++++++++--- 1 file changed, 28 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index bfa6a1625c5c..d9e7f62cc972 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -1901,6 +1902,19 @@ struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev); */ struct wireless_dev *ieee80211_vif_to_wdev(struct ieee80211_vif *vif); +/** + * lockdep_vif_mutex_held - for lockdep checks on link poiners + * @vif: the interface to check + */ +static inline bool lockdep_vif_mutex_held(struct ieee80211_vif *vif) +{ + return lockdep_is_held(&ieee80211_vif_to_wdev(vif)->mtx); +} + +#define link_conf_dereference_protected(vif, link_id) \ + rcu_dereference_protected((vif)->link_conf[link_id], \ + lockdep_vif_mutex_held(vif)) + /** * enum ieee80211_key_flags - key flags * @@ -2266,13 +2280,24 @@ struct ieee80211_sta { u8 drv_priv[] __aligned(sizeof(void *)); }; -/* FIXME: check the locking correctly */ +#ifdef CONFIG_LOCKDEP +bool lockdep_sta_mutex_held(struct ieee80211_sta *pubsta); +#else +static inline bool lockdep_sta_mutex_held(struct ieee80211_sta *pubsta) +{ + return true; +} +#endif + +#define link_sta_dereference_protected(sta, link_id) \ + rcu_dereference_protected((sta)->link[link_id], \ + lockdep_sta_mutex_held(sta)) + #define for_each_sta_active_link(vif, sta, link_sta, link_id) \ for (link_id = 0; link_id < ARRAY_SIZE((sta)->link); link_id++) \ if ((!(vif)->active_links || \ (vif)->active_links & BIT(link_id)) && \ - ((link_sta) = rcu_dereference_protected((sta)->link[link_id],\ - 1))) + ((link_sta) = link_sta_dereference_protected(sta, link_id))) /** * enum sta_notify_cmd - sta notify command -- cgit v1.2.3 From 4c51541ddb78cef2da9c4c30006c0d9d06ea9a77 Mon Sep 17 00:00:00 2001 From: Benjamin Berg Date: Fri, 2 Sep 2022 16:12:54 +0200 Subject: wifi: mac80211: keep A-MSDU data in sta and per-link The A-MSDU data needs to be stored per-link and aggregated into a single value for the station. Add a new struct ieee_80211_sta_aggregates in order to store this data and a new function ieee80211_sta_recalc_aggregates to update the current data for the STA. Note that in the non MLO case the pointer in ieee80211_sta will directly reference the data in deflink.agg, which means that recalculation may be skipped in that case. Signed-off-by: Benjamin Berg Signed-off-by: Johannes Berg --- include/net/mac80211.h | 68 +++++++++++++++++++++++++++++++++++--------------- 1 file changed, 48 insertions(+), 20 deletions(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index d9e7f62cc972..873e81a45a97 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2143,6 +2143,34 @@ struct ieee80211_sta_txpwr { enum nl80211_tx_power_setting type; }; +/** + * struct ieee80211_sta_aggregates - info that is aggregated from active links + * + * Used for any per-link data that needs to be aggregated and updated in the + * main &struct ieee80211_sta when updated or the active links change. + * + * @max_amsdu_len: indicates the maximal length of an A-MSDU in bytes. + * This field is always valid for packets with a VHT preamble. + * For packets with a HT preamble, additional limits apply: + * + * * If the skb is transmitted as part of a BA agreement, the + * A-MSDU maximal size is min(max_amsdu_len, 4065) bytes. + * * If the skb is not part of a BA agreement, the A-MSDU maximal + * size is min(max_amsdu_len, 7935) bytes. + * + * Both additional HT limits must be enforced by the low level + * driver. This is defined by the spec (IEEE 802.11-2012 section + * 8.3.2.2 NOTE 2). + * @max_rc_amsdu_len: Maximum A-MSDU size in bytes recommended by rate control. + * @max_tid_amsdu_len: Maximum A-MSDU size in bytes for this TID + */ +struct ieee80211_sta_aggregates { + u16 max_amsdu_len; + + u16 max_rc_amsdu_len; + u16 max_tid_amsdu_len[IEEE80211_NUM_TIDS]; +}; + /** * struct ieee80211_link_sta - station Link specific info * All link specific info for a STA link for a non MLD STA(single) @@ -2179,6 +2207,8 @@ struct ieee80211_link_sta { struct ieee80211_he_6ghz_capa he_6ghz_capa; struct ieee80211_sta_eht_cap eht_cap; + struct ieee80211_sta_aggregates agg; + u8 rx_nss; enum ieee80211_sta_rx_bandwidth bandwidth; struct ieee80211_sta_txpwr txpwr; @@ -2218,9 +2248,10 @@ struct ieee80211_link_sta { * @max_amsdu_subframes: indicates the maximal number of MSDUs in a single * A-MSDU. Taken from the Extended Capabilities element. 0 means * unlimited. + * @cur: currently valid data as aggregated from the active links + * For non MLO STA it will point to the deflink data. For MLO STA + * ieee80211_sta_recalc_aggregates() must be called to update it. * @support_p2p_ps: indicates whether the STA supports P2P PS mechanism or not. - * @max_rc_amsdu_len: Maximum A-MSDU size in bytes recommended by rate control. - * @max_tid_amsdu_len: Maximum A-MSDU size in bytes for this TID * @txq: per-TID data TX queues (if driver uses the TXQ abstraction); note that * the last entry (%IEEE80211_NUM_TIDS) is used for non-data frames * @deflink: This holds the default link STA information, for non MLO STA all link @@ -2250,25 +2281,9 @@ struct ieee80211_sta { bool mlo; u8 max_amsdu_subframes; - /** - * @max_amsdu_len: - * indicates the maximal length of an A-MSDU in bytes. - * This field is always valid for packets with a VHT preamble. - * For packets with a HT preamble, additional limits apply: - * - * * If the skb is transmitted as part of a BA agreement, the - * A-MSDU maximal size is min(max_amsdu_len, 4065) bytes. - * * If the skb is not part of a BA agreement, the A-MSDU maximal - * size is min(max_amsdu_len, 7935) bytes. - * - * Both additional HT limits must be enforced by the low level - * driver. This is defined by the spec (IEEE 802.11-2012 section - * 8.3.2.2 NOTE 2). - */ - u16 max_amsdu_len; + struct ieee80211_sta_aggregates *cur; + bool support_p2p_ps; - u16 max_rc_amsdu_len; - u16 max_tid_amsdu_len[IEEE80211_NUM_TIDS]; struct ieee80211_txq *txq[IEEE80211_NUM_TIDS + 1]; @@ -6105,6 +6120,19 @@ void ieee80211_sta_eosp(struct ieee80211_sta *pubsta); */ void ieee80211_send_eosp_nullfunc(struct ieee80211_sta *pubsta, int tid); +/** + * ieee80211_sta_recalc_aggregates - recalculate aggregate data after a change + * @pubsta: the station + * + * Call this function after changing a per-link aggregate data as referenced in + * &struct ieee80211_sta_aggregates by accessing the agg field of + * &struct ieee80211_link_sta. + * + * With non MLO the data in deflink will be referenced directly. In that case + * there is no need to call this function. + */ +void ieee80211_sta_recalc_aggregates(struct ieee80211_sta *pubsta); + /** * ieee80211_sta_register_airtime - register airtime usage for a sta/tid * -- cgit v1.2.3 From 3d901102922723eedce6ef10ebd03315a7abb8a5 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 2 Sep 2022 16:12:56 +0200 Subject: wifi: mac80211: implement link switching Implement an API function and debugfs file to switch active links. Also provide an async version of the API so drivers can call it in arbitrary contexts, e.g. while in the authorized callback. Signed-off-by: Johannes Berg --- include/net/mac80211.h | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 873e81a45a97..ac2bad57933f 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -7184,4 +7184,45 @@ static inline bool ieee80211_is_tx_data(struct sk_buff *skb) ieee80211_is_data(hdr->frame_control); } +/** + * ieee80211_set_active_links - set active links in client mode + * @vif: interface to set active links on + * @active_links: the new active links bitmap + * + * This changes the active links on an interface. The interface + * must be in client mode (in AP mode, all links are always active), + * and @active_links must be a subset of the vif's valid_links. + * + * If a link is switched off and another is switched on at the same + * time (e.g. active_links going from 0x1 to 0x10) then you will get + * a sequence of calls like + * - change_vif_links(0x11) + * - unassign_vif_chanctx(link_id=0) + * - change_sta_links(0x11) for each affected STA (the AP) + * (TDLS connections on now inactive links should be torn down) + * - remove group keys on the old link (link_id 0) + * - add new group keys (GTK/IGTK/BIGTK) on the new link (link_id 4) + * - change_sta_links(0x10) for each affected STA (the AP) + * - assign_vif_chanctx(link_id=4) + * - change_vif_links(0x10) + * + * Note: This function acquires some mac80211 locks and must not + * be called with any driver locks held that could cause a + * lock dependency inversion. Best call it without locks. + */ +int ieee80211_set_active_links(struct ieee80211_vif *vif, u16 active_links); + +/** + * ieee80211_set_active_links_async - asynchronously set active links + * @vif: interface to set active links on + * @active_links: the new active links bitmap + * + * See ieee80211_set_active_links() for more information, the only + * difference here is that the link change is triggered async and + * can be called in any context, but the link switch will only be + * completed after it returns. + */ +void ieee80211_set_active_links_async(struct ieee80211_vif *vif, + u16 active_links); + #endif /* MAC80211_H */ -- cgit v1.2.3 From b338d91703fae6f6afd67f3f75caa3b8f36ddef3 Mon Sep 17 00:00:00 2001 From: Brian Gix Date: Thu, 1 Sep 2022 12:19:13 -0700 Subject: Bluetooth: Implement support for Mesh The patch adds state bits, storage and HCI command chains for sending and receiving Bluetooth Mesh advertising packets, and delivery to requesting user space processes. It specifically creates 4 new MGMT commands and 2 new MGMT events: MGMT_OP_SET_MESH_RECEIVER - Sets passive scan parameters and a list of AD Types which will trigger Mesh Packet Received events MGMT_OP_MESH_READ_FEATURES - Returns information on how many outbound Mesh packets can be simultaneously queued, and what the currently queued handles are. MGMT_OP_MESH_SEND - Command to queue a specific outbound Mesh packet, with the number of times it should be sent, and the BD Addr to use. Discrete advertisments are added to the ADV Instance list. MGMT_OP_MESH_SEND_CANCEL - Command to cancel a prior outbound message request. MGMT_EV_MESH_DEVICE_FOUND - Event to deliver entire received Mesh Advertisement packet, along with timing information. MGMT_EV_MESH_PACKET_CMPLT - Event to indicate that an outbound packet is no longer queued for delivery. Signed-off-by: Brian Gix Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/bluetooth.h | 1 + include/net/bluetooth/hci.h | 3 +++ include/net/bluetooth/hci_core.h | 16 ++++++++++-- include/net/bluetooth/mgmt.h | 52 +++++++++++++++++++++++++++++++++++++++ 4 files changed, 70 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index e72f3b247b5e..bcc5a4cd2c17 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -627,6 +627,7 @@ static inline bool iso_enabled(void) int mgmt_init(void); void mgmt_exit(void); +void mgmt_cleanup(struct sock *sk); void bt_sock_reclassify_lock(struct sock *sk, int proto); diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index cf29511b25a8..b3ade687531f 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -354,6 +354,9 @@ enum { HCI_LE_SIMULTANEOUS_ROLES, HCI_CMD_DRAIN_WORKQUEUE, + HCI_MESH, + HCI_MESH_SENDING, + __HCI_NUM_FLAGS, }; diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 932153e68864..c54bc71254af 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -238,6 +238,7 @@ struct adv_info { bool enabled; bool pending; bool periodic; + __u8 mesh; __u8 instance; __u32 flags; __u16 timeout; @@ -372,6 +373,8 @@ struct hci_dev { __u8 le_resolv_list_size; __u8 le_num_of_adv_sets; __u8 le_states[8]; + __u8 mesh_ad_types[16]; + __u8 mesh_send_ref; __u8 commands[64]; __u8 hci_ver; __u16 hci_rev; @@ -511,6 +514,7 @@ struct hci_dev { struct list_head cmd_sync_work_list; struct mutex cmd_sync_work_lock; struct work_struct cmd_sync_cancel_work; + struct work_struct reenable_adv_work; __u16 discov_timeout; struct delayed_work discov_off; @@ -561,6 +565,7 @@ struct hci_dev { struct hci_conn_hash conn_hash; + struct list_head mesh_pending; struct list_head mgmt_pending; struct list_head reject_list; struct list_head accept_list; @@ -614,6 +619,8 @@ struct hci_dev { struct delayed_work rpa_expired; bdaddr_t rpa; + struct delayed_work mesh_send_done; + enum { INTERLEAVE_SCAN_NONE, INTERLEAVE_SCAN_NO_FILTER, @@ -1576,7 +1583,8 @@ struct adv_info *hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags, u16 adv_data_len, u8 *adv_data, u16 scan_rsp_len, u8 *scan_rsp_data, u16 timeout, u16 duration, s8 tx_power, - u32 min_interval, u32 max_interval); + u32 min_interval, u32 max_interval, + u8 mesh_handle); struct adv_info *hci_add_per_instance(struct hci_dev *hdev, u8 instance, u32 flags, u8 data_len, u8 *data, u32 min_interval, u32 max_interval); @@ -1997,6 +2005,9 @@ void hci_mgmt_chan_unregister(struct hci_mgmt_chan *c); #define DISCOV_LE_FAST_ADV_INT_MAX 0x00F0 /* 150 msec */ #define DISCOV_LE_PER_ADV_INT_MIN 0x00A0 /* 200 msec */ #define DISCOV_LE_PER_ADV_INT_MAX 0x00A0 /* 200 msec */ +#define DISCOV_LE_ADV_MESH_MIN 0x00A0 /* 100 msec */ +#define DISCOV_LE_ADV_MESH_MAX 0x00A0 /* 100 msec */ +#define INTERVAL_TO_MS(x) (((x) * 10) / 0x10) #define NAME_RESOLVE_DURATION msecs_to_jiffies(10240) /* 10.24 sec */ @@ -2048,7 +2059,8 @@ void mgmt_start_discovery_complete(struct hci_dev *hdev, u8 status); void mgmt_stop_discovery_complete(struct hci_dev *hdev, u8 status); void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 *dev_class, s8 rssi, u32 flags, - u8 *eir, u16 eir_len, u8 *scan_rsp, u8 scan_rsp_len); + u8 *eir, u16 eir_len, u8 *scan_rsp, u8 scan_rsp_len, + u64 instant); void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, s8 rssi, u8 *name, u8 name_len); void mgmt_discovering(struct hci_dev *hdev, u8 discovering); diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 7c1ad0f6fcec..743f6f59dff8 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -837,6 +837,42 @@ struct mgmt_cp_add_adv_patterns_monitor_rssi { struct mgmt_adv_pattern patterns[]; } __packed; #define MGMT_ADD_ADV_PATTERNS_MONITOR_RSSI_SIZE 8 +#define MGMT_OP_SET_MESH_RECEIVER 0x0057 +struct mgmt_cp_set_mesh { + __u8 enable; + __le16 window; + __le16 period; + __u8 num_ad_types; + __u8 ad_types[]; +} __packed; +#define MGMT_SET_MESH_RECEIVER_SIZE 6 + +#define MGMT_OP_MESH_READ_FEATURES 0x0058 +#define MGMT_MESH_READ_FEATURES_SIZE 0 +#define MESH_HANDLES_MAX 3 +struct mgmt_rp_mesh_read_features { + __le16 index; + __u8 max_handles; + __u8 used_handles; + __u8 handles[MESH_HANDLES_MAX]; +} __packed; + +#define MGMT_OP_MESH_SEND 0x0059 +struct mgmt_cp_mesh_send { + struct mgmt_addr_info addr; + __le64 instant; + __le16 delay; + __u8 cnt; + __u8 adv_data_len; + __u8 adv_data[]; +} __packed; +#define MGMT_MESH_SEND_SIZE 19 + +#define MGMT_OP_MESH_SEND_CANCEL 0x005A +struct mgmt_cp_mesh_send_cancel { + __u8 handle; +} __packed; +#define MGMT_MESH_SEND_CANCEL_SIZE 1 #define MGMT_EV_CMD_COMPLETE 0x0001 struct mgmt_ev_cmd_complete { @@ -1120,3 +1156,19 @@ struct mgmt_ev_adv_monitor_device_lost { __le16 monitor_handle; struct mgmt_addr_info addr; } __packed; + +#define MGMT_EV_MESH_DEVICE_FOUND 0x0031 +struct mgmt_ev_mesh_device_found { + struct mgmt_addr_info addr; + __s8 rssi; + __le64 instant; + __le32 flags; + __le16 eir_len; + __u8 eir[]; +} __packed; + + +#define MGMT_EV_MESH_PACKET_CMPLT 0x0032 +struct mgmt_ev_mesh_pkt_cmplt { + __u8 handle; +} __packed; -- cgit v1.2.3 From af6bcc1921ff0b644d2d750c0e3a88623b7211f5 Mon Sep 17 00:00:00 2001 From: Brian Gix Date: Thu, 1 Sep 2022 12:19:14 -0700 Subject: Bluetooth: Add experimental wrapper for MGMT based mesh This introduces a "Mesh UUID" and an Experimental Feature bit to the hdev mask, and depending all underlying Mesh functionality on it. Signed-off-by: Brian Gix Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index b3ade687531f..e004ba04a9ae 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -354,6 +354,7 @@ enum { HCI_LE_SIMULTANEOUS_ROLES, HCI_CMD_DRAIN_WORKQUEUE, + HCI_MESH_EXPERIMENTAL, HCI_MESH, HCI_MESH_SENDING, -- cgit v1.2.3 From 08724ef69907214ce622344fe4945412e38368f0 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 5 Sep 2022 12:09:36 +0200 Subject: netlink: introduce NLA_POLICY_MAX_BE netlink allows to specify allowed ranges for integer types. Unfortunately, nfnetlink passes integers in big endian, so the existing NLA_POLICY_MAX() cannot be used. At the moment, nfnetlink users, such as nf_tables, need to resort to programmatic checking via helpers such as nft_parse_u32_check(). This is both cumbersome and error prone. This adds NLA_POLICY_MAX_BE which adds range check support for BE16, BE32 and BE64 integers. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/net/netlink.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/net') diff --git a/include/net/netlink.h b/include/net/netlink.h index e658d18afa67..4418b1981e31 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -325,6 +325,7 @@ struct nla_policy { struct netlink_range_validation_signed *range_signed; struct { s16 min, max; + u8 network_byte_order:1; }; int (*validate)(const struct nlattr *attr, struct netlink_ext_ack *extack); @@ -418,6 +419,14 @@ struct nla_policy { .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_MAX, \ .max = _max, \ + .network_byte_order = 0, \ +} + +#define NLA_POLICY_MAX_BE(tp, _max) { \ + .type = NLA_ENSURE_UINT_TYPE(tp), \ + .validation_type = NLA_VALIDATE_MAX, \ + .max = _max, \ + .network_byte_order = 1, \ } #define NLA_POLICY_MASK(tp, _mask) { \ -- cgit v1.2.3 From 0a28bfd4971fd570d1f3e4653b21415becefc92c Mon Sep 17 00:00:00 2001 From: Lior Nahmanson Date: Mon, 5 Sep 2022 22:21:13 -0700 Subject: net/macsec: Add MACsec skb_metadata_dst Tx Data path support In the current MACsec offload implementation, MACsec interfaces shares the same MAC address by default. Therefore, HW can't distinguish from which MACsec interface the traffic originated from. MACsec stack will use skb_metadata_dst to store the SCI value, which is unique per Macsec interface, skb_metadat_dst will be used by the offloading device driver to associate the SKB with the corresponding offloaded interface (SCI). Signed-off-by: Lior Nahmanson Reviewed-by: Raed Salem Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/net/dst_metadata.h | 10 ++++++++++ include/net/macsec.h | 4 ++++ 2 files changed, 14 insertions(+) (limited to 'include/net') diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index adab27ba1ecb..22a6924bf6da 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -4,11 +4,13 @@ #include #include +#include #include enum metadata_type { METADATA_IP_TUNNEL, METADATA_HW_PORT_MUX, + METADATA_MACSEC, }; struct hw_port_info { @@ -16,12 +18,17 @@ struct hw_port_info { u32 port_id; }; +struct macsec_info { + sci_t sci; +}; + struct metadata_dst { struct dst_entry dst; enum metadata_type type; union { struct ip_tunnel_info tun_info; struct hw_port_info port_info; + struct macsec_info macsec_info; } u; }; @@ -82,6 +89,9 @@ static inline int skb_metadata_dst_cmp(const struct sk_buff *skb_a, return memcmp(&a->u.tun_info, &b->u.tun_info, sizeof(a->u.tun_info) + a->u.tun_info.options_len); + case METADATA_MACSEC: + return memcmp(&a->u.macsec_info, &b->u.macsec_info, + sizeof(a->u.macsec_info)); default: return 1; } diff --git a/include/net/macsec.h b/include/net/macsec.h index 73780aa73644..8494953fb0de 100644 --- a/include/net/macsec.h +++ b/include/net/macsec.h @@ -19,6 +19,8 @@ typedef u64 __bitwise sci_t; typedef u32 __bitwise ssci_t; +struct metadata_dst; + typedef union salt { struct { u32 ssci; @@ -182,6 +184,7 @@ struct macsec_tx_sa { * @scb: single copy broadcast flag * @sa: array of secure associations * @stats: stats for this TXSC + * @md_dst: MACsec offload metadata dst */ struct macsec_tx_sc { bool active; @@ -192,6 +195,7 @@ struct macsec_tx_sc { bool scb; struct macsec_tx_sa __rcu *sa[MACSEC_NUM_AN]; struct pcpu_tx_sc_stats __percpu *stats; + struct metadata_dst *md_dst; }; /** -- cgit v1.2.3 From b1671253c6015841f6cabd39730fa42fb6d3d407 Mon Sep 17 00:00:00 2001 From: Lior Nahmanson Date: Mon, 5 Sep 2022 22:21:15 -0700 Subject: net/macsec: Move some code for sharing with various drivers that implements offload Move some MACsec infrastructure like defines and functions, in order to avoid code duplication for future drivers which implements MACsec offload. Signed-off-by: Lior Nahmanson Reviewed-by: Raed Salem Reviewed-by: Jiri Pirko Reviewed-by: Ben Ben-Ishay Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/net/macsec.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/net') diff --git a/include/net/macsec.h b/include/net/macsec.h index 8494953fb0de..871599b11707 100644 --- a/include/net/macsec.h +++ b/include/net/macsec.h @@ -16,6 +16,20 @@ #define MACSEC_NUM_AN 4 /* 2 bits for the association number */ +#define MACSEC_SCI_LEN 8 +#define MACSEC_PORT_ES (htons(0x0001)) + +#define MACSEC_TCI_VERSION 0x80 +#define MACSEC_TCI_ES 0x40 /* end station */ +#define MACSEC_TCI_SC 0x20 /* SCI present */ +#define MACSEC_TCI_SCB 0x10 /* epon */ +#define MACSEC_TCI_E 0x08 /* encryption */ +#define MACSEC_TCI_C 0x04 /* changed text */ +#define MACSEC_AN_MASK 0x03 /* association number */ +#define MACSEC_TCI_CONFID (MACSEC_TCI_E | MACSEC_TCI_C) + +#define MACSEC_DEFAULT_ICV_LEN 16 + typedef u64 __bitwise sci_t; typedef u32 __bitwise ssci_t; @@ -292,5 +306,12 @@ struct macsec_ops { }; void macsec_pn_wrapped(struct macsec_secy *secy, struct macsec_tx_sa *tx_sa); +static inline bool macsec_send_sci(const struct macsec_secy *secy) +{ + const struct macsec_tx_sc *tx_sc = &secy->tx_sc; + + return tx_sc->send_sci || + (secy->n_rx_sc > 1 && !tx_sc->end_station && !tx_sc->scb); +} #endif /* _NET_MACSEC_H_ */ -- cgit v1.2.3 From c92c27171040554cfda7a3fc925e9dbcb5b4a698 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 6 Sep 2022 17:20:35 +0200 Subject: netfilter: nat: move repetitive nat port reserve loop to a helper Almost all nat helpers reserve an expecation port the same way: Try the port inidcated by the peer, then move to next port if that port is already in use. We can squash this into a helper. Suggested-by: Pablo Neira Ayuso Signed-off-by: Florian Westphal --- include/net/netfilter/nf_nat_helper.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/netfilter/nf_nat_helper.h b/include/net/netfilter/nf_nat_helper.h index efae84646353..44c421b9be85 100644 --- a/include/net/netfilter/nf_nat_helper.h +++ b/include/net/netfilter/nf_nat_helper.h @@ -38,4 +38,5 @@ bool nf_nat_mangle_udp_packet(struct sk_buff *skb, struct nf_conn *ct, * to port ct->master->saved_proto. */ void nf_nat_follow_master(struct nf_conn *ct, struct nf_conntrack_expect *this); +u16 nf_nat_exp_find_port(struct nf_conntrack_expect *exp, u16 port); #endif -- cgit v1.2.3 From 2a40f883781d6cbbf547ed13b0cec2f9808d839d Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Thu, 8 Sep 2022 13:57:50 -0700 Subject: Bluetooth: Fix HCIGETDEVINFO regression Recent changes breaks HCIGETDEVINFO since it changes the size of hci_dev_info. Fixes: 26afbd826ee3 ("Bluetooth: Add initial implementation of CIS connections") Reported-by: Marek Szyprowski Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_sock.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/net') diff --git a/include/net/bluetooth/hci_sock.h b/include/net/bluetooth/hci_sock.h index 0520e21ab698..9949870f7d78 100644 --- a/include/net/bluetooth/hci_sock.h +++ b/include/net/bluetooth/hci_sock.h @@ -124,8 +124,6 @@ struct hci_dev_info { __u16 acl_pkts; __u16 sco_mtu; __u16 sco_pkts; - __u16 iso_mtu; - __u16 iso_pkts; struct hci_dev_stats stat; }; -- cgit v1.2.3 From acd0a7ab6334f35c3720120d53f79eb8e9b3ac2e Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Thu, 8 Sep 2022 12:14:33 +0800 Subject: net: sched: act: move global static variable net_id to tc_action_ops Each tc action module has a corresponding net_id, so put net_id directly into the structure tc_action_ops. Signed-off-by: Zhengchao Shao Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/act_api.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/act_api.h b/include/net/act_api.h index 9cf6870b526e..61f2ceb3939e 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -111,6 +111,7 @@ struct tc_action_ops { struct list_head head; char kind[IFNAMSIZ]; enum tca_id id; /* identifier should match kind */ + unsigned int net_id; size_t size; struct module *owner; int (*act)(struct sk_buff *, const struct tc_action *, -- cgit v1.2.3 From 35e60f1aadf6c02d77fdf42180fbf205aec7e8fc Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Thu, 8 Sep 2022 13:57:50 -0700 Subject: Bluetooth: Fix HCIGETDEVINFO regression Recent changes breaks HCIGETDEVINFO since it changes the size of hci_dev_info. Fixes: 26afbd826ee3 ("Bluetooth: Add initial implementation of CIS connections") Reported-by: Marek Szyprowski Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_sock.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/net') diff --git a/include/net/bluetooth/hci_sock.h b/include/net/bluetooth/hci_sock.h index 0520e21ab698..9949870f7d78 100644 --- a/include/net/bluetooth/hci_sock.h +++ b/include/net/bluetooth/hci_sock.h @@ -124,8 +124,6 @@ struct hci_dev_info { __u16 acl_pkts; __u16 sco_mtu; __u16 sco_pkts; - __u16 iso_mtu; - __u16 iso_pkts; struct hci_dev_stats stat; }; -- cgit v1.2.3 From 864b656f82ccd433d3e38149c3673d295ad64bf6 Mon Sep 17 00:00:00 2001 From: Daniel Xu Date: Wed, 7 Sep 2022 10:40:40 -0600 Subject: bpf: Add support for writing to nf_conn:mark Support direct writes to nf_conn:mark from TC and XDP prog types. This is useful when applications want to store per-connection metadata. This is also particularly useful for applications that run both bpf and iptables/nftables because the latter can trivially access this metadata. One example use case would be if a bpf prog is responsible for advanced packet classification and iptables/nftables is later used for routing due to pre-existing/legacy code. Signed-off-by: Daniel Xu Link: https://lore.kernel.org/r/ebca06dea366e3e7e861c12f375a548cc4c61108.1662568410.git.dxu@dxuuu.xyz Signed-off-by: Alexei Starovoitov --- include/net/netfilter/nf_conntrack_bpf.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/net') diff --git a/include/net/netfilter/nf_conntrack_bpf.h b/include/net/netfilter/nf_conntrack_bpf.h index a473b56842c5..a61a93d1c6dc 100644 --- a/include/net/netfilter/nf_conntrack_bpf.h +++ b/include/net/netfilter/nf_conntrack_bpf.h @@ -3,13 +3,22 @@ #ifndef _NF_CONNTRACK_BPF_H #define _NF_CONNTRACK_BPF_H +#include #include #include +#include #if (IS_BUILTIN(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \ (IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) extern int register_nf_conntrack_bpf(void); +extern void cleanup_nf_conntrack_bpf(void); + +extern struct mutex nf_conn_btf_access_lock; +extern int (*nfct_bsa)(struct bpf_verifier_log *log, const struct btf *btf, + const struct btf_type *t, int off, int size, + enum bpf_access_type atype, u32 *next_btf_id, + enum bpf_type_flag *flag); #else @@ -18,6 +27,20 @@ static inline int register_nf_conntrack_bpf(void) return 0; } +static inline void cleanup_nf_conntrack_bpf(void) +{ +} + +static inline int nf_conntrack_btf_struct_access(struct bpf_verifier_log *log, + const struct btf *btf, + const struct btf_type *t, int off, + int size, enum bpf_access_type atype, + u32 *next_btf_id, + enum bpf_type_flag *flag) +{ + return -EACCES; +} + #endif #endif /* _NF_CONNTRACK_BPF_H */ -- cgit v1.2.3 From 94160108a70c8af17fa1484a37e05181c0e094af Mon Sep 17 00:00:00 2001 From: Haimin Zhang Date: Thu, 8 Sep 2022 20:19:27 +0800 Subject: net/ieee802154: fix uninit value bug in dgram_sendmsg There is uninit value bug in dgram_sendmsg function in net/ieee802154/socket.c when the length of valid data pointed by the msg->msg_name isn't verified. We introducing a helper function ieee802154_sockaddr_check_size to check namelen. First we check there is addr_type in ieee802154_addr_sa. Then, we check namelen according to addr_type. Also fixed in raw_bind, dgram_bind, dgram_connect. Signed-off-by: Haimin Zhang Signed-off-by: David S. Miller --- include/net/ieee802154_netdev.h | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) (limited to 'include/net') diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h index d0d188c3294b..a8994f307fc3 100644 --- a/include/net/ieee802154_netdev.h +++ b/include/net/ieee802154_netdev.h @@ -15,6 +15,22 @@ #ifndef IEEE802154_NETDEVICE_H #define IEEE802154_NETDEVICE_H +#define IEEE802154_REQUIRED_SIZE(struct_type, member) \ + (offsetof(typeof(struct_type), member) + \ + sizeof(((typeof(struct_type) *)(NULL))->member)) + +#define IEEE802154_ADDR_OFFSET \ + offsetof(typeof(struct sockaddr_ieee802154), addr) + +#define IEEE802154_MIN_NAMELEN (IEEE802154_ADDR_OFFSET + \ + IEEE802154_REQUIRED_SIZE(struct ieee802154_addr_sa, addr_type)) + +#define IEEE802154_NAMELEN_SHORT (IEEE802154_ADDR_OFFSET + \ + IEEE802154_REQUIRED_SIZE(struct ieee802154_addr_sa, short_addr)) + +#define IEEE802154_NAMELEN_LONG (IEEE802154_ADDR_OFFSET + \ + IEEE802154_REQUIRED_SIZE(struct ieee802154_addr_sa, hwaddr)) + #include #include #include @@ -165,6 +181,27 @@ static inline void ieee802154_devaddr_to_raw(void *raw, __le64 addr) memcpy(raw, &temp, IEEE802154_ADDR_LEN); } +static inline int +ieee802154_sockaddr_check_size(struct sockaddr_ieee802154 *daddr, int len) +{ + struct ieee802154_addr_sa *sa; + + sa = &daddr->addr; + if (len < IEEE802154_MIN_NAMELEN) + return -EINVAL; + switch (sa->addr_type) { + case IEEE802154_ADDR_SHORT: + if (len < IEEE802154_NAMELEN_SHORT) + return -EINVAL; + break; + case IEEE802154_ADDR_LONG: + if (len < IEEE802154_NAMELEN_LONG) + return -EINVAL; + break; + } + return 0; +} + static inline void ieee802154_addr_from_sa(struct ieee802154_addr *a, const struct ieee802154_addr_sa *sa) { -- cgit v1.2.3 From 1d9a143ee3408349700f44a9197b7ae0e4faae5d Mon Sep 17 00:00:00 2001 From: Benjamin Poirier Date: Wed, 7 Sep 2022 16:56:39 +0900 Subject: net: bonding: Share lacpdu_mcast_addr definition There are already a few definitions of arrays containing MULTICAST_LACPDU_ADDR and the next patch will add one more use. These all contain the same constant data so define one common instance for all bonding code. Signed-off-by: Benjamin Poirier Signed-off-by: David S. Miller --- include/net/bond_3ad.h | 2 -- include/net/bonding.h | 3 +++ 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index be2992e6de5d..a016f275cb01 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -15,8 +15,6 @@ #define PKT_TYPE_LACPDU cpu_to_be16(ETH_P_SLOW) #define AD_TIMER_INTERVAL 100 /*msec*/ -#define MULTICAST_LACPDU_ADDR {0x01, 0x80, 0xC2, 0x00, 0x00, 0x02} - #define AD_LACP_SLOW 0 #define AD_LACP_FAST 1 diff --git a/include/net/bonding.h b/include/net/bonding.h index afd606df149a..e999f851738b 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -786,6 +786,9 @@ extern struct rtnl_link_ops bond_link_ops; /* exported from bond_sysfs_slave.c */ extern const struct sysfs_ops slave_sysfs_ops; +/* exported from bond_3ad.c */ +extern const u8 lacpdu_mcast_addr[]; + static inline netdev_tx_t bond_tx_drop(struct net_device *dev, struct sk_buff *skb) { dev_core_stats_tx_dropped_inc(dev); -- cgit v1.2.3 From dda2fa08a13c688bed320ef2e4ba541abb4d6c17 Mon Sep 17 00:00:00 2001 From: Wojciech Drewek Date: Thu, 8 Sep 2022 10:16:41 -0700 Subject: flow_dissector: Add L2TPv3 dissectors Allow to dissect L2TPv3 specific field which is: - session ID (32 bits) L2TPv3 might be transported over IP or over UDP, this implementation is only about L2TPv3 over IP. IP protocol carries L2TPv3 when ip_proto is IPPROTO_L2TP (115). Acked-by: Guillaume Nault Signed-off-by: Wojciech Drewek Signed-off-by: Tony Nguyen Signed-off-by: Paolo Abeni --- include/net/flow_dissector.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/net') diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 6c74812d64b2..5ccf52ef8809 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -289,6 +289,14 @@ struct flow_dissector_key_pppoe { __be16 type; }; +/** + * struct flow_dissector_key_l2tpv3: + * @session_id: identifier for a l2tp session + */ +struct flow_dissector_key_l2tpv3 { + __be32 session_id; +}; + enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */ FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */ @@ -320,6 +328,7 @@ enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_HASH, /* struct flow_dissector_key_hash */ FLOW_DISSECTOR_KEY_NUM_OF_VLANS, /* struct flow_dissector_key_num_of_vlans */ FLOW_DISSECTOR_KEY_PPPOE, /* struct flow_dissector_key_pppoe */ + FLOW_DISSECTOR_KEY_L2TPV3, /* struct flow_dissector_key_l2tpv3 */ FLOW_DISSECTOR_KEY_MAX, }; -- cgit v1.2.3 From 2c1befaced504a125d1ab7479684a9208879d350 Mon Sep 17 00:00:00 2001 From: Wojciech Drewek Date: Thu, 8 Sep 2022 10:16:43 -0700 Subject: flow_offload: Introduce flow_match_l2tpv3 Allow to offload L2TPv3 filters by adding flow_rule_match_l2tpv3. Drivers can extract L2TPv3 specific fields from now on. Signed-off-by: Wojciech Drewek Signed-off-by: Tony Nguyen Signed-off-by: Paolo Abeni --- include/net/flow_offload.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/net') diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 2a9a9e42e7fd..e343f9f8363e 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -80,6 +80,10 @@ struct flow_match_pppoe { struct flow_dissector_key_pppoe *key, *mask; }; +struct flow_match_l2tpv3 { + struct flow_dissector_key_l2tpv3 *key, *mask; +}; + struct flow_rule; void flow_rule_match_meta(const struct flow_rule *rule, @@ -128,6 +132,8 @@ void flow_rule_match_ct(const struct flow_rule *rule, struct flow_match_ct *out); void flow_rule_match_pppoe(const struct flow_rule *rule, struct flow_match_pppoe *out); +void flow_rule_match_l2tpv3(const struct flow_rule *rule, + struct flow_match_l2tpv3 *out); enum flow_action_id { FLOW_ACTION_ACCEPT = 0, -- cgit v1.2.3 From 8f6a19c0316deb48cdfdc5335de9a6d7db5b7b62 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 11 Sep 2022 04:06:58 +0300 Subject: net: dsa: introduce dsa_port_get_master() There is a desire to support for DSA masters in a LAG. That configuration is intended to work by simply enslaving the master to a bonding/team device. But the physical DSA master (the LAG slave) still has a dev->dsa_ptr, and that cpu_dp still corresponds to the physical CPU port. However, we would like to be able to retrieve the LAG that's the upper of the physical DSA master. In preparation for that, introduce a helper called dsa_port_get_master() that replaces all occurrences of the dp->cpu_dp->master pattern. The distinction between LAG and non-LAG will be made later within the helper itself. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: Paolo Abeni --- include/net/dsa.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/net') diff --git a/include/net/dsa.h b/include/net/dsa.h index f2ce12860546..23eac1bda843 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -718,6 +718,11 @@ static inline bool dsa_port_offloads_lag(struct dsa_port *dp, return dsa_port_lag_dev_get(dp) == lag->dev; } +static inline struct net_device *dsa_port_to_master(const struct dsa_port *dp) +{ + return dp->cpu_dp->master; +} + static inline struct net_device *dsa_port_to_bridge_port(const struct dsa_port *dp) { -- cgit v1.2.3 From 95f510d0b792f308d3d748242fe960c35bdc2c62 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 11 Sep 2022 04:06:59 +0300 Subject: net: dsa: allow the DSA master to be seen and changed through rtnetlink Some DSA switches have multiple CPU ports, which can be used to improve CPU termination throughput, but DSA, through dsa_tree_setup_cpu_ports(), sets up only the first one, leading to suboptimal use of hardware. The desire is to not change the default configuration but to permit the user to create a dynamic mapping between individual user ports and the CPU port that they are served by, configurable through rtnetlink. It is also intended to permit load balancing between CPU ports, and in that case, the foreseen model is for the DSA master to be a bonding interface whose lowers are the physical DSA masters. To that end, we create a struct rtnl_link_ops for DSA user ports with the "dsa" kind. We expose the IFLA_DSA_MASTER link attribute that contains the ifindex of the newly desired DSA master. Signed-off-by: Vladimir Oltean Signed-off-by: Paolo Abeni --- include/net/dsa.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/net') diff --git a/include/net/dsa.h b/include/net/dsa.h index 23eac1bda843..3f717c3fcba0 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -559,6 +559,10 @@ static inline bool dsa_is_user_port(struct dsa_switch *ds, int p) list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_is_user((_dp))) +#define dsa_tree_for_each_user_port_continue_reverse(_dp, _dst) \ + list_for_each_entry_continue_reverse((_dp), &(_dst)->ports, list) \ + if (dsa_port_is_user((_dp))) + #define dsa_tree_for_each_cpu_port(_dp, _dst) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_is_cpu((_dp))) @@ -830,6 +834,10 @@ struct dsa_switch_ops { int (*connect_tag_protocol)(struct dsa_switch *ds, enum dsa_tag_protocol proto); + int (*port_change_master)(struct dsa_switch *ds, int port, + struct net_device *master, + struct netlink_ext_ack *extack); + /* Optional switch-wide initialization and destruction methods */ int (*setup)(struct dsa_switch *ds); void (*teardown)(struct dsa_switch *ds); -- cgit v1.2.3 From 2e359b00a11715c7a89d7448e6e4cb4d84543520 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 11 Sep 2022 04:07:03 +0300 Subject: net: dsa: propagate extack to port_lag_join Drivers could refuse to offload a LAG configuration for a variety of reasons, mainly having to do with its TX type. Additionally, since DSA masters may now also be LAG interfaces, and this will translate into a call to port_lag_join on the CPU ports, there may be extra restrictions there. Propagate the netlink extack to this DSA method in order for drivers to give a meaningful error message back to the user. Signed-off-by: Vladimir Oltean Signed-off-by: Paolo Abeni --- include/net/dsa.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/dsa.h b/include/net/dsa.h index 3f717c3fcba0..1c80e75b3cad 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -1094,7 +1094,8 @@ struct dsa_switch_ops { int port); int (*crosschip_lag_join)(struct dsa_switch *ds, int sw_index, int port, struct dsa_lag lag, - struct netdev_lag_upper_info *info); + struct netdev_lag_upper_info *info, + struct netlink_ext_ack *extack); int (*crosschip_lag_leave)(struct dsa_switch *ds, int sw_index, int port, struct dsa_lag lag); @@ -1169,7 +1170,8 @@ struct dsa_switch_ops { int (*port_lag_change)(struct dsa_switch *ds, int port); int (*port_lag_join)(struct dsa_switch *ds, int port, struct dsa_lag lag, - struct netdev_lag_upper_info *info); + struct netdev_lag_upper_info *info, + struct netlink_ext_ack *extack); int (*port_lag_leave)(struct dsa_switch *ds, int port, struct dsa_lag lag); -- cgit v1.2.3 From acc43b7bf52a015221d989164c2600c1e1f28790 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 11 Sep 2022 04:07:04 +0300 Subject: net: dsa: allow masters to join a LAG There are 2 ways in which a DSA user port may become handled by 2 CPU ports in a LAG: (1) its current DSA master joins a LAG ip link del bond0 && ip link add bond0 type bond mode 802.3ad ip link set eno2 master bond0 When this happens, all user ports with "eno2" as DSA master get automatically migrated to "bond0" as DSA master. (2) it is explicitly configured as such by the user # Before, the DSA master was eno3 ip link set swp0 type dsa master bond0 The design of this configuration is that the LAG device dynamically becomes a DSA master through dsa_master_setup() when the first physical DSA master becomes a LAG slave, and stops being so through dsa_master_teardown() when the last physical DSA master leaves. A LAG interface is considered as a valid DSA master only if it contains existing DSA masters, and no other lower interfaces. Therefore, we mainly rely on method (1) to enter this configuration. Each physical DSA master (LAG slave) retains its dev->dsa_ptr for when it becomes a standalone DSA master again. But the LAG master also has a dev->dsa_ptr, and this is actually duplicated from one of the physical LAG slaves, and therefore needs to be balanced when LAG slaves come and go. To the switch driver, putting DSA masters in a LAG is seen as putting their associated CPU ports in a LAG. We need to prepare cross-chip host FDB notifiers for CPU ports in a LAG, by calling the driver's ->lag_fdb_add method rather than ->port_fdb_add. Signed-off-by: Vladimir Oltean Signed-off-by: Paolo Abeni --- include/net/dsa.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/net') diff --git a/include/net/dsa.h b/include/net/dsa.h index 1c80e75b3cad..d777eac5694f 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -300,6 +300,9 @@ struct dsa_port { u8 master_admin_up:1; u8 master_oper_up:1; + /* Valid only on user ports */ + u8 cpu_port_in_lag:1; + u8 setup:1; struct device_node *dn; @@ -724,6 +727,9 @@ static inline bool dsa_port_offloads_lag(struct dsa_port *dp, static inline struct net_device *dsa_port_to_master(const struct dsa_port *dp) { + if (dp->cpu_port_in_lag) + return dsa_port_lag_dev_get(dp->cpu_dp); + return dp->cpu_dp->master; } @@ -811,6 +817,12 @@ dsa_tree_offloads_bridge_dev(struct dsa_switch_tree *dst, return false; } +static inline bool dsa_port_tree_same(const struct dsa_port *a, + const struct dsa_port *b) +{ + return a->ds->dst == b->ds->dst; +} + typedef int dsa_fdb_dump_cb_t(const unsigned char *addr, u16 vid, bool is_static, void *data); struct dsa_switch_ops { -- cgit v1.2.3 From e9bd0cca09d13ac2f08d25e195203e42d4ad1ce8 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 7 Sep 2022 18:10:18 -0700 Subject: tcp: Don't allocate tcp_death_row outside of struct netns_ipv4. We will soon introduce an optional per-netns ehash and access hash tables via net->ipv4.tcp_death_row->hashinfo instead of &tcp_hashinfo in most places. It could harm the fast path because dereferences of two fields in net and tcp_death_row might incur two extra cache line misses. To save one dereference, let's place tcp_death_row back in netns_ipv4 and fetch hashinfo via net->ipv4.tcp_death_row"."hashinfo. Note tcp_death_row was initially placed in netns_ipv4, and commit fbb8295248e1 ("tcp: allocate tcp_death_row outside of struct netns_ipv4") changed it to a pointer so that we can fire TIME_WAIT timers after freeing net. However, we don't do so after commit 04c494e68a13 ("Revert "tcp/dccp: get rid of inet_twsk_purge()""), so we need not define tcp_death_row as a pointer. Also, we move refcount_dec_and_test(&tw_refcount) from tcp_sk_exit() to tcp_sk_exit_batch() as a debug check. Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/net/netns/ipv4.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 6320a76cefdc..2c7df93e3403 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -34,6 +34,7 @@ struct inet_hashinfo; struct inet_timewait_death_row { refcount_t tw_refcount; + /* Padding to avoid false sharing, tw_refcount can be often written */ struct inet_hashinfo *hashinfo ____cacheline_aligned_in_smp; int sysctl_max_tw_buckets; }; @@ -41,7 +42,7 @@ struct inet_timewait_death_row { struct tcp_fastopen_context; struct netns_ipv4 { - struct inet_timewait_death_row *tcp_death_row; + struct inet_timewait_death_row tcp_death_row; #ifdef CONFIG_SYSCTL struct ctl_table_header *forw_hdr; -- cgit v1.2.3 From 429e42c1c54e0d9bfe880195f7d4a8fd5a727194 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 7 Sep 2022 18:10:19 -0700 Subject: tcp: Set NULL to sk->sk_prot->h.hashinfo. We will soon introduce an optional per-netns ehash. This means we cannot use the global sk->sk_prot->h.hashinfo to fetch a TCP hashinfo. Instead, set NULL to sk->sk_prot->h.hashinfo for TCP and get a proper hashinfo from net->ipv4.tcp_death_row.hashinfo. Note that we need not use sk->sk_prot->h.hashinfo if DCCP is disabled. Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/net/inet_hashtables.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/net') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 44a419b9e3d5..520dd894b73d 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -170,6 +170,16 @@ struct inet_hashinfo { struct inet_listen_hashbucket *lhash2; }; +static inline struct inet_hashinfo *tcp_or_dccp_get_hashinfo(const struct sock *sk) +{ +#if IS_ENABLED(CONFIG_IP_DCCP) + return sk->sk_prot->h.hashinfo ? : + sock_net(sk)->ipv4.tcp_death_row.hashinfo; +#else + return sock_net(sk)->ipv4.tcp_death_row.hashinfo; +#endif +} + static inline struct inet_listen_hashbucket * inet_lhash2_bucket(struct inet_hashinfo *h, u32 hash) { -- cgit v1.2.3 From edc12f032a5a1633474db566878ce0012e7ca2f5 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 7 Sep 2022 18:10:21 -0700 Subject: tcp: Save unnecessary inet_twsk_purge() calls. While destroying netns, we call inet_twsk_purge() in tcp_sk_exit_batch() and tcpv6_net_exit_batch() for AF_INET and AF_INET6. These commands trigger the kernel to walk through the potentially big ehash twice even though the netns has no TIME_WAIT sockets. # ip netns add test # ip netns del test or # unshare -n /bin/true >/dev/null When tw_refcount is 1, we need not call inet_twsk_purge() at least for the net. We can save such unneeded iterations if all netns in net_exit_list have no TIME_WAIT sockets. This change eliminates the tax by the additional unshare() described in the next patch to guarantee the per-netns ehash size. Tested: # mount -t debugfs none /sys/kernel/debug/ # echo cleanup_net > /sys/kernel/debug/tracing/set_ftrace_filter # echo inet_twsk_purge >> /sys/kernel/debug/tracing/set_ftrace_filter # echo function > /sys/kernel/debug/tracing/current_tracer # cat ./add_del_unshare.sh for i in `seq 1 40` do (for j in `seq 1 100` ; do unshare -n /bin/true >/dev/null ; done) & done wait; # ./add_del_unshare.sh Before the patch: # cat /sys/kernel/debug/tracing/trace_pipe kworker/u128:0-8 [031] ...1. 174.162765: cleanup_net <-process_one_work kworker/u128:0-8 [031] ...1. 174.240796: inet_twsk_purge <-cleanup_net kworker/u128:0-8 [032] ...1. 174.244759: inet_twsk_purge <-tcp_sk_exit_batch kworker/u128:0-8 [034] ...1. 174.290861: cleanup_net <-process_one_work kworker/u128:0-8 [039] ...1. 175.245027: inet_twsk_purge <-cleanup_net kworker/u128:0-8 [046] ...1. 175.290541: inet_twsk_purge <-tcp_sk_exit_batch kworker/u128:0-8 [037] ...1. 175.321046: cleanup_net <-process_one_work kworker/u128:0-8 [024] ...1. 175.941633: inet_twsk_purge <-cleanup_net kworker/u128:0-8 [025] ...1. 176.242539: inet_twsk_purge <-tcp_sk_exit_batch After: # cat /sys/kernel/debug/tracing/trace_pipe kworker/u128:0-8 [038] ...1. 428.116174: cleanup_net <-process_one_work kworker/u128:0-8 [038] ...1. 428.262532: cleanup_net <-process_one_work kworker/u128:0-8 [030] ...1. 429.292645: cleanup_net <-process_one_work Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/net/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index 735e957f7f4b..27e8d378c70a 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -346,6 +346,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb); void tcp_rcv_space_adjust(struct sock *sk); int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp); void tcp_twsk_destructor(struct sock *sk); +void tcp_twsk_purge(struct list_head *net_exit_list, int family); ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); -- cgit v1.2.3 From d1e5e6408b305ff78b825d437df8d3f77e82a4be Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 7 Sep 2022 18:10:22 -0700 Subject: tcp: Introduce optional per-netns ehash. The more sockets we have in the hash table, the longer we spend looking up the socket. While running a number of small workloads on the same host, they penalise each other and cause performance degradation. The root cause might be a single workload that consumes much more resources than the others. It often happens on a cloud service where different workloads share the same computing resource. On EC2 c5.24xlarge instance (196 GiB memory and 524288 (1Mi / 2) ehash entries), after running iperf3 in different netns, creating 24Mi sockets without data transfer in the root netns causes about 10% performance regression for the iperf3's connection. thash_entries sockets length Gbps 524288 1 1 50.7 24Mi 48 45.1 It is basically related to the length of the list of each hash bucket. For testing purposes to see how performance drops along the length, I set 131072 (1Mi / 8) to thash_entries, and here's the result. thash_entries sockets length Gbps 131072 1 1 50.7 1Mi 8 49.9 2Mi 16 48.9 4Mi 32 47.3 8Mi 64 44.6 16Mi 128 40.6 24Mi 192 36.3 32Mi 256 32.5 40Mi 320 27.0 48Mi 384 25.0 To resolve the socket lookup degradation, we introduce an optional per-netns hash table for TCP, but it's just ehash, and we still share the global bhash, bhash2 and lhash2. With a smaller ehash, we can look up non-listener sockets faster and isolate such noisy neighbours. In addition, we can reduce lock contention. We can control the ehash size by a new sysctl knob. However, depending on workloads, it will require very sensitive tuning, so we disable the feature by default (net.ipv4.tcp_child_ehash_entries == 0). Moreover, we can fall back to using the global ehash in case we fail to allocate enough memory for a new ehash. The maximum size is 16Mi, which is large enough that even if we have 48Mi sockets, the average list length is 3, and regression would be less than 1%. We can check the current ehash size by another read-only sysctl knob, net.ipv4.tcp_ehash_entries. A negative value means the netns shares the global ehash (per-netns ehash is disabled or failed to allocate memory). # dmesg | cut -d ' ' -f 5- | grep "established hash" TCP established hash table entries: 524288 (order: 10, 4194304 bytes, vmalloc hugepage) # sysctl net.ipv4.tcp_ehash_entries net.ipv4.tcp_ehash_entries = 524288 # can be changed by thash_entries # sysctl net.ipv4.tcp_child_ehash_entries net.ipv4.tcp_child_ehash_entries = 0 # disabled by default # ip netns add test1 # ip netns exec test1 sysctl net.ipv4.tcp_ehash_entries net.ipv4.tcp_ehash_entries = -524288 # share the global ehash # sysctl -w net.ipv4.tcp_child_ehash_entries=100 net.ipv4.tcp_child_ehash_entries = 100 # ip netns add test2 # ip netns exec test2 sysctl net.ipv4.tcp_ehash_entries net.ipv4.tcp_ehash_entries = 128 # own a per-netns ehash with 2^n buckets When more than two processes in the same netns create per-netns ehash concurrently with different sizes, we need to guarantee the size in one of the following ways: 1) Share the global ehash and create per-netns ehash First, unshare() with tcp_child_ehash_entries==0. It creates dedicated netns sysctl knobs where we can safely change tcp_child_ehash_entries and clone()/unshare() to create a per-netns ehash. 2) Control write on sysctl by BPF We can use BPF_PROG_TYPE_CGROUP_SYSCTL to allow/deny read/write on sysctl knobs. Note that the global ehash allocated at the boot time is spread over available NUMA nodes, but inet_pernet_hashinfo_alloc() will allocate pages for each per-netns ehash depending on the current process's NUMA policy. By default, the allocation is done in the local node only, so the per-netns hash table could fully reside on a random node. Thus, depending on the NUMA policy the netns is created with and the CPU the current thread is running on, we could see some performance differences for highly optimised networking applications. Note also that the default values of two sysctl knobs depend on the ehash size and should be tuned carefully: tcp_max_tw_buckets : tcp_child_ehash_entries / 2 tcp_max_syn_backlog : max(128, tcp_child_ehash_entries / 128) As a bonus, we can dismantle netns faster. Currently, while destroying netns, we call inet_twsk_purge(), which walks through the global ehash. It can be potentially big because it can have many sockets other than TIME_WAIT in all netns. Splitting ehash changes that situation, where it's only necessary for inet_twsk_purge() to clean up TIME_WAIT sockets in each netns. With regard to this, we do not free the per-netns ehash in inet_twsk_kill() to avoid UAF while iterating the per-netns ehash in inet_twsk_purge(). Instead, we do it in tcp_sk_exit_batch() after calling tcp_twsk_purge() to keep it protocol-family-independent. In the future, we could optimise ehash lookup/iteration further by removing netns comparison for the per-netns ehash. Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/net/inet_hashtables.h | 6 ++++++ include/net/netns/ipv4.h | 1 + 2 files changed, 7 insertions(+) (limited to 'include/net') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 520dd894b73d..9121ccab1fa1 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -168,6 +168,8 @@ struct inet_hashinfo { /* The 2nd listener table hashed by local port and address */ unsigned int lhash2_mask; struct inet_listen_hashbucket *lhash2; + + bool pernet; }; static inline struct inet_hashinfo *tcp_or_dccp_get_hashinfo(const struct sock *sk) @@ -214,6 +216,10 @@ static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo) hashinfo->ehash_locks = NULL; } +struct inet_hashinfo *inet_pernet_hashinfo_alloc(struct inet_hashinfo *hashinfo, + unsigned int ehash_entries); +void inet_pernet_hashinfo_free(struct inet_hashinfo *hashinfo); + struct inet_bind_bucket * inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net, struct inet_bind_hashbucket *head, diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 2c7df93e3403..1b8004679445 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -171,6 +171,7 @@ struct netns_ipv4 { int sysctl_tcp_pacing_ca_ratio; int sysctl_tcp_wmem[3]; int sysctl_tcp_rmem[3]; + unsigned int sysctl_tcp_child_ehash_entries; unsigned long sysctl_tcp_comp_sack_delay_ns; unsigned long sysctl_tcp_comp_sack_slack_ns; int sysctl_max_syn_backlog; -- cgit v1.2.3 From 52bdae37c92ae10d47d54bd7cd39e0a17547ebfa Mon Sep 17 00:00:00 2001 From: Daniel Xu Date: Tue, 20 Sep 2022 08:15:22 -0600 Subject: bpf: Remove unused btf_struct_access stub This stub was not being used anywhere. Signed-off-by: Daniel Xu Link: https://lore.kernel.org/r/590e7bd6172ffe0f3d7b51cd40e8ded941aaf7e8.1663683114.git.dxu@dxuuu.xyz Signed-off-by: Martin KaFai Lau --- include/net/netfilter/nf_conntrack_bpf.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/net') diff --git a/include/net/netfilter/nf_conntrack_bpf.h b/include/net/netfilter/nf_conntrack_bpf.h index a61a93d1c6dc..9c07d2d59da5 100644 --- a/include/net/netfilter/nf_conntrack_bpf.h +++ b/include/net/netfilter/nf_conntrack_bpf.h @@ -3,8 +3,6 @@ #ifndef _NF_CONNTRACK_BPF_H #define _NF_CONNTRACK_BPF_H -#include -#include #include #include @@ -31,16 +29,6 @@ static inline void cleanup_nf_conntrack_bpf(void) { } -static inline int nf_conntrack_btf_struct_access(struct bpf_verifier_log *log, - const struct btf *btf, - const struct btf_type *t, int off, - int size, enum bpf_access_type atype, - u32 *next_btf_id, - enum bpf_type_flag *flag) -{ - return -EACCES; -} - #endif #endif /* _NF_CONNTRACK_BPF_H */ -- cgit v1.2.3 From 5a090aa35038e3dad1ee334e3c509c39e7599bb4 Mon Sep 17 00:00:00 2001 From: Daniel Xu Date: Tue, 20 Sep 2022 08:15:23 -0600 Subject: bpf: Rename nfct_bsa to nfct_btf_struct_access The former name was a little hard to guess. Signed-off-by: Daniel Xu Link: https://lore.kernel.org/r/73adc72385c8b162391fbfb404f0b6d4c5cc55d7.1663683114.git.dxu@dxuuu.xyz Signed-off-by: Martin KaFai Lau --- include/net/netfilter/nf_conntrack_bpf.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/netfilter/nf_conntrack_bpf.h b/include/net/netfilter/nf_conntrack_bpf.h index 9c07d2d59da5..1199d4f8e019 100644 --- a/include/net/netfilter/nf_conntrack_bpf.h +++ b/include/net/netfilter/nf_conntrack_bpf.h @@ -13,10 +13,10 @@ extern int register_nf_conntrack_bpf(void); extern void cleanup_nf_conntrack_bpf(void); extern struct mutex nf_conn_btf_access_lock; -extern int (*nfct_bsa)(struct bpf_verifier_log *log, const struct btf *btf, - const struct btf_type *t, int off, int size, - enum bpf_access_type atype, u32 *next_btf_id, - enum bpf_type_flag *flag); +extern int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, const struct btf *btf, + const struct btf_type *t, int off, int size, + enum bpf_access_type atype, u32 *next_btf_id, + enum bpf_type_flag *flag); #else -- cgit v1.2.3 From fdf214978a71b2749d26f6da2b1d51d9ac23831d Mon Sep 17 00:00:00 2001 From: Daniel Xu Date: Tue, 20 Sep 2022 08:15:24 -0600 Subject: bpf: Move nf_conn extern declarations to filter.h We're seeing the following new warnings on netdev/build_32bit and netdev/build_allmodconfig_warn CI jobs: ../net/core/filter.c:8608:1: warning: symbol 'nf_conn_btf_access_lock' was not declared. Should it be static? ../net/core/filter.c:8611:5: warning: symbol 'nfct_bsa' was not declared. Should it be static? Fix by ensuring extern declaration is present while compiling filter.o. Fixes: 864b656f82cc ("bpf: Add support for writing to nf_conn:mark") Signed-off-by: Daniel Xu Link: https://lore.kernel.org/r/2bd2e0283df36d8a4119605878edb1838d144174.1663683114.git.dxu@dxuuu.xyz Signed-off-by: Martin KaFai Lau --- include/net/netfilter/nf_conntrack_bpf.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/net') diff --git a/include/net/netfilter/nf_conntrack_bpf.h b/include/net/netfilter/nf_conntrack_bpf.h index 1199d4f8e019..c8b80add1142 100644 --- a/include/net/netfilter/nf_conntrack_bpf.h +++ b/include/net/netfilter/nf_conntrack_bpf.h @@ -4,7 +4,6 @@ #define _NF_CONNTRACK_BPF_H #include -#include #if (IS_BUILTIN(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \ (IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) @@ -12,12 +11,6 @@ extern int register_nf_conntrack_bpf(void); extern void cleanup_nf_conntrack_bpf(void); -extern struct mutex nf_conn_btf_access_lock; -extern int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, const struct btf *btf, - const struct btf_type *t, int off, int size, - enum bpf_access_type atype, u32 *next_btf_id, - enum bpf_type_flag *flag); - #else static inline int register_nf_conntrack_bpf(void) -- cgit v1.2.3 From fe0df81df51eb932a83e0c3844106ac6c0f914db Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Fri, 16 Sep 2022 10:02:43 +0800 Subject: net/sched: cls_api: add helper for tc cls walker stats dump The walk implementation of most tc cls modules is basically the same. That is, the values of count and skip are checked first. If count is greater than or equal to skip, the registered fn function is executed. Otherwise, increase the value of count. So we can reconstruct them. Signed-off-by: Zhengchao Shao Reviewed-by: Jamal Hadi Salim Reviewed-by: Victor Nogueira Tested-by: Victor Nogueira Signed-off-by: Jakub Kicinski --- include/net/pkt_cls.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/net') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index d9d90e6925e1..d376c995d906 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -81,6 +81,19 @@ int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode); +static inline bool tc_cls_stats_dump(struct tcf_proto *tp, + struct tcf_walker *arg, + void *filter) +{ + if (arg->count >= arg->skip && arg->fn(tp, filter, arg) < 0) { + arg->stop = 1; + return false; + } + + arg->count++; + return true; +} + #else static inline bool tcf_block_shared(struct tcf_block *block) { -- cgit v1.2.3 From 1d14b30b5a5e52da93467af7c1dca08f124186df Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Mon, 19 Sep 2022 13:06:27 +0000 Subject: net: sched: remove unused tcf_result extension Added by: commit e5cf1baf92cb ("act_mirred: use TC_ACT_REINSERT when possible") but no longer useful. Signed-off-by: Jamal Hadi Salim Link: https://lore.kernel.org/r/20220919130627.3551233-1-jhs@mojatatu.com Signed-off-by: Jakub Kicinski --- include/net/sch_generic.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/net') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 7dc83400bde4..32819299937d 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -326,11 +326,6 @@ struct tcf_result { }; const struct tcf_proto *goto_tp; - /* used in the skb_tc_reinsert function */ - struct { - bool ingress; - struct gnet_stats_queue *qstats; - }; }; }; -- cgit v1.2.3 From adb5c33e4d4c83fb848a402e2191fbf3e2bf50d1 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Wed, 14 Sep 2022 19:04:03 +0200 Subject: xfrm: add extack support to xfrm_dev_state_add Signed-off-by: Sabrina Dubroca Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 28b988577ed2..9c1cccf85f12 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1886,7 +1886,8 @@ 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); + struct xfrm_user_offload *xuo, + struct netlink_ext_ack *extack); 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) @@ -1949,7 +1950,7 @@ static inline struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_fea return skb; } -static inline int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, struct xfrm_user_offload *xuo) +static inline int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, struct xfrm_user_offload *xuo, struct netlink_ext_ack *extack) { return 0; } -- cgit v1.2.3 From 741f9a1064985512567eca1552643738ecfb5cc5 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Wed, 14 Sep 2022 19:04:05 +0200 Subject: xfrm: add extack to __xfrm_init_state Signed-off-by: Sabrina Dubroca Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 9c1cccf85f12..f427a74d571b 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1582,7 +1582,8 @@ void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si); u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq); int xfrm_init_replay(struct xfrm_state *x); u32 xfrm_state_mtu(struct xfrm_state *x, int mtu); -int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload); +int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload, + struct netlink_ext_ack *extack); int xfrm_init_state(struct xfrm_state *x); int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); int xfrm_input_resume(struct sk_buff *skb, int nexthdr); -- cgit v1.2.3 From 1cf9a3ae3e2de359471a7036f48ac59e48b15256 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Wed, 14 Sep 2022 19:04:06 +0200 Subject: xfrm: add extack support to xfrm_init_replay Signed-off-by: Sabrina Dubroca Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index f427a74d571b..c504d07bcb7c 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1580,7 +1580,7 @@ int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_vali void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si); void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si); u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq); -int xfrm_init_replay(struct xfrm_state *x); +int xfrm_init_replay(struct xfrm_state *x, struct netlink_ext_ack *extack); u32 xfrm_state_mtu(struct xfrm_state *x, int mtu); int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload, struct netlink_ext_ack *extack); -- cgit v1.2.3 From 77eee32514314209961af5c2982e871ecb364445 Mon Sep 17 00:00:00 2001 From: Wen Gu Date: Tue, 20 Sep 2022 17:52:21 +0800 Subject: net/smc: Introduce a specific sysctl for TEST_LINK time SMC-R tests the viability of link by sending out TEST_LINK LLC messages over RoCE fabric when connections on link have been idle for a time longer than keepalive interval (testlink time). But using tcp_keepalive_time as testlink time maybe not quite suitable because it is default no less than two hours[1], which is too long for single link to find peer dead. The active host will still use peer-dead link (QP) sending messages, and can't find out until get IB_WC_RETRY_EXC_ERR error CQEs, which takes more time than TEST_LINK timeout (SMC_LLC_WAIT_TIME) normally. So this patch introduces a independent sysctl for SMC-R to set link keepalive time, in order to detect link down in time. The default value is 30 seconds. [1] https://www.rfc-editor.org/rfc/rfc1122#page-101 Signed-off-by: Wen Gu Signed-off-by: Paolo Abeni --- include/net/netns/smc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/netns/smc.h b/include/net/netns/smc.h index 2adbe2b245df..d295e2c10dca 100644 --- a/include/net/netns/smc.h +++ b/include/net/netns/smc.h @@ -19,5 +19,6 @@ struct netns_smc { #endif unsigned int sysctl_autocorking_size; unsigned int sysctl_smcr_buf_type; + int sysctl_smcr_testlink_time; }; #endif -- cgit v1.2.3 From 0227f058aa29f5ab6f6ec79c3a36ae41f1e03a13 Mon Sep 17 00:00:00 2001 From: Tony Lu Date: Tue, 20 Sep 2022 17:52:22 +0800 Subject: net/smc: Unbind r/w buffer size from clcsock and make them tunable Currently, SMC uses smc->sk.sk_{rcv|snd}buf to create buffers for send buffer and RMB. And the values of buffer size are from tcp_{w|r}mem in clcsock. The buffer size from TCP socket doesn't fit SMC well. Generally, buffers are usually larger than TCP for SMC-R/-D to get higher performance, for they are different underlay devices and paths. So this patch unbinds buffer size from TCP, and introduces two sysctl knobs to tune them independently. Also, these knobs are per net namespace and work for containers. Signed-off-by: Tony Lu Signed-off-by: Paolo Abeni --- include/net/netns/smc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/netns/smc.h b/include/net/netns/smc.h index d295e2c10dca..582212ada3ba 100644 --- a/include/net/netns/smc.h +++ b/include/net/netns/smc.h @@ -20,5 +20,7 @@ struct netns_smc { unsigned int sysctl_autocorking_size; unsigned int sysctl_smcr_buf_type; int sysctl_smcr_testlink_time; + int sysctl_wmem; + int sysctl_rmem; }; #endif -- cgit v1.2.3 From 60240bc26114543fcbfcd8a28466e67e77b20388 Mon Sep 17 00:00:00 2001 From: Jalal Mostafa Date: Wed, 21 Sep 2022 13:57:01 +0000 Subject: xsk: Inherit need_wakeup flag for shared sockets The flag for need_wakeup is not set for xsks with `XDP_SHARED_UMEM` flag and of different queue ids and/or devices. They should inherit the flag from the first socket buffer pool since no flags can be specified once `XDP_SHARED_UMEM` is specified. Fixes: b5aea28dca134 ("xsk: Add shared umem support between queue ids") Signed-off-by: Jalal Mostafa Signed-off-by: Daniel Borkmann Acked-by: Magnus Karlsson Link: https://lore.kernel.org/bpf/20220921135701.10199-1-jalal.a.mostapha@gmail.com --- include/net/xsk_buff_pool.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 647722e847b4..f787c3f524b0 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -95,7 +95,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, struct xdp_umem *umem); int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev, u16 queue_id, u16 flags); -int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem, +int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_sock *umem_xs, struct net_device *dev, u16 queue_id); int xp_alloc_tx_descs(struct xsk_buff_pool *pool, struct xdp_sock *xs); void xp_destroy(struct xsk_buff_pool *pool); -- cgit v1.2.3 From 2d2c5ea24243eb3ed12f232b2aef43981fa15360 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Tue, 20 Sep 2022 16:01:47 +0300 Subject: net/tls: Describe ciphers sizes by const structs Introduce cipher sizes descriptor. It helps reducing the amount of code duplications and repeated switch/cases that assigns the proper sizes according to the cipher type. Signed-off-by: Tariq Toukan Signed-off-by: Gal Pressman Signed-off-by: Jakub Kicinski --- include/net/tls.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/net') diff --git a/include/net/tls.h b/include/net/tls.h index cb205f9d9473..154949c7b0c8 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -51,6 +51,16 @@ struct tls_rec; +struct tls_cipher_size_desc { + unsigned int iv; + unsigned int key; + unsigned int salt; + unsigned int tag; + unsigned int rec_seq; +}; + +extern const struct tls_cipher_size_desc tls_cipher_size_desc[]; + /* Maximum data size carried in a TLS record */ #define TLS_MAX_PAYLOAD_SIZE ((size_t)1 << 14) -- cgit v1.2.3 From d7a68e564e29bcd1c70d76d9e2f65591e6183f46 Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Wed, 21 Sep 2022 10:41:04 +0800 Subject: net/sched: sch_api: add helper for tc qdisc walker stats dump MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The walk implementation of most qdisc class modules is basically the same. That is, the values of count and skip are checked first. If count is greater than or equal to skip, the registered fn function is executed. Otherwise, increase the value of count. So we can reconstruct them. Signed-off-by: Zhengchao Shao Acked-by: Toke Høiland-Jørgensen Signed-off-by: Jakub Kicinski --- include/net/pkt_sched.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/net') diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 29f65632ebc5..2ff80cd04c5c 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -222,4 +222,17 @@ static inline struct tc_skb_cb *tc_skb_cb(const struct sk_buff *skb) return cb; } +static inline bool tc_qdisc_stats_dump(struct Qdisc *sch, + unsigned long cl, + struct qdisc_walker *arg) +{ + if (arg->count >= arg->skip && arg->fn(sch, cl, arg) < 0) { + arg->stop = 1; + return false; + } + + arg->count++; + return true; +} + #endif -- cgit v1.2.3 From 99383f1298ee25901b1f6a665bdcc3344acb2382 Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Wed, 21 Sep 2022 15:51:18 +0200 Subject: net: macsec: remove the prepare flag from the MACsec offloading context Now that the MACsec offloading preparation phase was removed from the MACsec core implementation as well as from drivers implementing it, we can safely remove the flag representing it. Signed-off-by: Antoine Tenart Signed-off-by: Jakub Kicinski --- include/net/macsec.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/net') diff --git a/include/net/macsec.h b/include/net/macsec.h index 871599b11707..5b9c61c4d3a6 100644 --- a/include/net/macsec.h +++ b/include/net/macsec.h @@ -271,8 +271,6 @@ struct macsec_context { struct macsec_rx_sa_stats *rx_sa_stats; struct macsec_dev_stats *dev_stats; } stats; - - u8 prepare:1; }; /** -- cgit v1.2.3 From c8f01a4a54473f88f8cc0d9046ec9eb5a99815d5 Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Thu, 22 Sep 2022 16:38:55 +0800 Subject: neighbour: Remove unused inline function neigh_key_eq16() All uses of neigh_key_eq16() have been removed since commit 1202cdd66531 ("Remove DECnet support from kernel"), so remove it. Signed-off-by: Gaosheng Cui Signed-off-by: Jakub Kicinski --- include/net/neighbour.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/net') diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 3827a6b395fd..20745cf7ae1a 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -276,11 +276,6 @@ static inline void *neighbour_priv(const struct neighbour *n) extern const struct nla_policy nda_policy[]; -static inline bool neigh_key_eq16(const struct neighbour *n, const void *pkey) -{ - return *(const u16 *)n->primary_key == *(const u16 *)pkey; -} - static inline bool neigh_key_eq32(const struct neighbour *n, const void *pkey) { return *(const u32 *)n->primary_key == *(const u32 *)pkey; -- cgit v1.2.3 From d6755f37abfd009e7ca3520c319c93d14cae54b3 Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Thu, 22 Sep 2022 16:38:56 +0800 Subject: net: Remove unused inline function sk_nulls_node_init() All uses of sk_nulls_node_init() have been removed since commit dbca1596bbb0 ("ping: convert to RCU lookups, get rid of rwlock"), so remove it. Signed-off-by: Gaosheng Cui Signed-off-by: Jakub Kicinski --- include/net/sock.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index 96a31026e35d..08038a385ef2 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -744,11 +744,6 @@ static inline void sk_node_init(struct hlist_node *node) node->pprev = NULL; } -static inline void sk_nulls_node_init(struct hlist_nulls_node *node) -{ - node->pprev = NULL; -} - static inline void __sk_del_node(struct sock *sk) { __hlist_del(&sk->sk_node); -- cgit v1.2.3 From 0b81882ddf8ac2743f657afb001beec7fc3929af Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Thu, 22 Sep 2022 16:38:57 +0800 Subject: net: Remove unused inline function dst_hold_and_use() All uses of dst_hold_and_use() have been removed since commit 1202cdd66531 ("Remove DECnet support from kernel"), so remove it. Signed-off-by: Gaosheng Cui Signed-off-by: Jakub Kicinski --- include/net/dst.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/net') diff --git a/include/net/dst.h b/include/net/dst.h index 6aa252c3fc55..00b479ce6b99 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -239,12 +239,6 @@ static inline void dst_use_noref(struct dst_entry *dst, unsigned long time) } } -static inline void dst_hold_and_use(struct dst_entry *dst, unsigned long time) -{ - dst_hold(dst); - dst_use_noref(dst, time); -} - static inline struct dst_entry *dst_clone(struct dst_entry *dst) { if (dst) -- cgit v1.2.3 From b860a1b964be7917ed3dcaa674ec0a2ba0a62aa0 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Fri, 23 Sep 2022 14:48:00 +0200 Subject: xdp: Adjust xdp_frame layout to avoid using bitfields Practical experience (and advice from Alexei) tell us that bitfields in structs lead to un-optimized assembly code. I've verified this change does lead to better x86_64 assembly, both via objdump and playing with code snippets in godbolt.org. Using scripts/bloat-o-meter shows the code size is reduced with 24 bytes for xdp_convert_buff_to_frame() that gets inlined e.g. in i40e_xmit_xdp_tx_ring() which were used for microbenchmarking. Microbenchmarking results do show improvements, but very small and varying between 0.5 to 2 nanosec improvement per packet. The member @metasize is changed from u8 to u32. Future users of this area could split this into two u16 fields. I've also benchmarked with two u16 fields showing equal performance gains and code size reduction. The moved member @frame_sz doesn't change sizeof struct due to existing padding. Like xdp_buff member @frame_sz is placed next to @flags, which allows compiler to optimize assignment of these. Signed-off-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/r/166393728005.2213882.4162674859542409548.stgit@firesoul Signed-off-by: Jakub Kicinski --- include/net/xdp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/xdp.h b/include/net/xdp.h index 04c852c7a77f..55dbc68bfffc 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -164,13 +164,13 @@ struct xdp_frame { void *data; u16 len; u16 headroom; - u32 metasize:8; - u32 frame_sz:24; + u32 metasize; /* uses lower 8-bits */ /* Lifetime of xdp_rxq_info is limited to NAPI/enqueue time, * while mem info is valid on remote CPU. */ struct xdp_mem_info mem; struct net_device *dev_rx; /* used by cpumap */ + u32 frame_sz; u32 flags; /* supported values defined in xdp_buff_flags */ }; -- cgit v1.2.3 From 63a8bf85568b30438431d4d78afb2fde4a280760 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 26 Sep 2022 18:02:20 -0500 Subject: netns: Replace zero-length array with DECLARE_FLEX_ARRAY() helper Zero-length arrays are deprecated and we are moving towards adopting C99 flexible-array members, instead. So, replace zero-length arrays declarations in anonymous union with the new DECLARE_FLEX_ARRAY() helper macro. This helper allows for flexible-array members in unions. Link: https://github.com/KSPP/linux/issues/193 Link: https://github.com/KSPP/linux/issues/225 Link: https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html Signed-off-by: Gustavo A. R. Silva Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/YzIvfGXxfjdXmIS3@work Signed-off-by: Jakub Kicinski --- include/net/netns/generic.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/netns/generic.h b/include/net/netns/generic.h index 7ce68183f6e1..00c399edeed1 100644 --- a/include/net/netns/generic.h +++ b/include/net/netns/generic.h @@ -33,7 +33,7 @@ struct net_generic { struct rcu_head rcu; } s; - void *ptr[0]; + DECLARE_FLEX_ARRAY(void *, ptr); }; }; -- cgit v1.2.3 From 3242abeb8da7071fa40d32346ed36343bee33b80 Mon Sep 17 00:00:00 2001 From: Benjamin Hesmans Date: Mon, 26 Sep 2022 16:27:37 -0700 Subject: tcp: export tcp_sendmsg_fastopen It will be used to support TCP FastOpen with MPTCP in the following commit. Acked-by: Paolo Abeni Reviewed-by: Matthieu Baerts Co-developed-by: Dmytro Shytyi Signed-off-by: Dmytro Shytyi Signed-off-by: Benjamin Hesmans Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- include/net/tcp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index 27e8d378c70a..4f71cc15ff8e 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -327,6 +327,8 @@ void tcp_remove_empty_skb(struct sock *sk); int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw); int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size); +int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, + size_t size, struct ubuf_info *uarg); int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset, -- cgit v1.2.3 From 5456262d2baa43c38e0c770543d5a31b0942f41c Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Mon, 26 Sep 2022 17:25:44 -0700 Subject: net: Fix incorrect address comparison when searching for a bind2 bucket The v6_rcv_saddr and rcv_saddr are inside a union in the 'struct inet_bind2_bucket'. When searching a bucket by following the bhash2 hashtable chain, eg. inet_bind2_bucket_match, it is only using the sk->sk_family and there is no way to check if the inet_bind2_bucket has a v6 or v4 address in the union. This leads to an uninit-value KMSAN report in [0] and also potentially incorrect matches. This patch fixes it by adding a family member to the inet_bind2_bucket and then tests 'sk->sk_family != tb->family' before matching the sk's address to the tb's address. Cc: Joanne Koong Fixes: 28044fc1d495 ("net: Add a bhash2 table hashed by port and address") Signed-off-by: Martin KaFai Lau Reviewed-by: Eric Dumazet Tested-by: Alexander Potapenko Link: https://lore.kernel.org/r/20220927002544.3381205-1-kafai@fb.com Signed-off-by: Jakub Kicinski --- include/net/inet_hashtables.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/net') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 9121ccab1fa1..3af1e927247d 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -95,6 +95,9 @@ struct inet_bind2_bucket { possible_net_t ib_net; int l3mdev; unsigned short port; +#if IS_ENABLED(CONFIG_IPV6) + unsigned short family; +#endif union { #if IS_ENABLED(CONFIG_IPV6) struct in6_addr v6_rcv_saddr; -- cgit v1.2.3 From e1e10b44cf284248fb099681f48cc723564a1cc8 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Tue, 27 Sep 2022 17:45:29 +0200 Subject: xfrm: pass extack down to xfrm_type ->init_state Signed-off-by: Sabrina Dubroca Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index c504d07bcb7c..dbc81f5eb553 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -405,7 +405,8 @@ struct xfrm_type { #define XFRM_TYPE_LOCAL_COADDR 4 #define XFRM_TYPE_REMOTE_COADDR 8 - int (*init_state)(struct xfrm_state *x); + int (*init_state)(struct xfrm_state *x, + struct netlink_ext_ack *extack); void (*destructor)(struct xfrm_state *); int (*input)(struct xfrm_state *, struct sk_buff *skb); int (*output)(struct xfrm_state *, struct sk_buff *pskb); -- cgit v1.2.3 From 6ee55320520e31f5dae637e928d5792352b22776 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Tue, 27 Sep 2022 17:45:33 +0200 Subject: xfrm: ipcomp: add extack to ipcomp{4,6}_init_state And the shared helper ipcomp_init_state. Signed-off-by: Sabrina Dubroca Signed-off-by: Steffen Klassert --- include/net/ipcomp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/ipcomp.h b/include/net/ipcomp.h index c31108295079..8660a2a6d1fc 100644 --- a/include/net/ipcomp.h +++ b/include/net/ipcomp.h @@ -22,7 +22,7 @@ struct xfrm_state; int ipcomp_input(struct xfrm_state *x, struct sk_buff *skb); int ipcomp_output(struct xfrm_state *x, struct sk_buff *skb); void ipcomp_destroy(struct xfrm_state *x); -int ipcomp_init_state(struct xfrm_state *x); +int ipcomp_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack); static inline struct ip_comp_hdr *ip_comp_hdr(const struct sk_buff *skb) { -- cgit v1.2.3 From aac4daa8941ea6566563ac001e9e5d4e54a674e2 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 28 Sep 2022 12:51:57 +0300 Subject: net/sched: query offload capabilities through ndo_setup_tc() When adding optional new features to Qdisc offloads, existing drivers must reject the new configuration until they are coded up to act on it. Since modifying all drivers in lockstep with the changes in the Qdisc can create problems of its own, it would be nice if there existed an automatic opt-in mechanism for offloading optional features. Jakub proposes that we multiplex one more kind of call through ndo_setup_tc(): one where the driver populates a Qdisc-specific capability structure. First user will be taprio in further changes. Here we are introducing the definitions for the base functionality. Link: https://patchwork.kernel.org/project/netdevbpf/patch/20220923163310.3192733-3-vladimir.oltean@nxp.com/ Suggested-by: Jakub Kicinski Co-developed-by: Jakub Kicinski Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/net/pkt_sched.h | 5 +++++ include/net/sch_generic.h | 3 +++ 2 files changed, 8 insertions(+) (limited to 'include/net') diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 2ff80cd04c5c..34600292fdfb 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -141,6 +141,11 @@ static inline struct net *qdisc_net(struct Qdisc *q) return dev_net(q->dev_queue->dev); } +struct tc_query_caps_base { + enum tc_setup_type type; + void *caps; +}; + struct tc_cbs_qopt_offload { u8 enable; s32 queue; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 32819299937d..d5517719af4e 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -677,6 +677,9 @@ qdisc_offload_graft_helper(struct net_device *dev, struct Qdisc *sch, { } #endif +void qdisc_offload_query_caps(struct net_device *dev, + enum tc_setup_type type, + void *caps, size_t caps_len); struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, struct netlink_ext_ack *extack); -- cgit v1.2.3 From a54fc09e4cba3004443aa05979f8c678196c8226 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 28 Sep 2022 12:51:58 +0300 Subject: net/sched: taprio: allow user input of per-tc max SDU IEEE 802.1Q clause 12.29.1.1 "The queueMaxSDUTable structure and data types" and 8.6.8.4 "Enhancements for scheduled traffic" talk about the existence of a per traffic class limitation of maximum frame sizes, with a fallback on the port-based MTU. As far as I am able to understand, the 802.1Q Service Data Unit (SDU) represents the MAC Service Data Unit (MSDU, i.e. L2 payload), excluding any number of prepended VLAN headers which may be otherwise present in the MSDU. Therefore, the queueMaxSDU is directly comparable to the device MTU (1500 means L2 payload sizes are accepted, or frame sizes of 1518 octets, or 1522 plus one VLAN header). Drivers which offload this are directly responsible of translating into other units of measurement. To keep the fast path checks optimized, we keep 2 arrays in the qdisc, one for max_sdu translated into frame length (so that it's comparable to skb->len), and another for offloading and for dumping back to the user. Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/net/pkt_sched.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/net') diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 34600292fdfb..38207873eda6 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -160,6 +160,10 @@ struct tc_etf_qopt_offload { s32 queue; }; +struct tc_taprio_caps { + bool supports_queue_max_sdu:1; +}; + struct tc_taprio_sched_entry { u8 command; /* TC_TAPRIO_CMD_* */ @@ -173,6 +177,7 @@ struct tc_taprio_qopt_offload { ktime_t base_time; u64 cycle_time; u64 cycle_time_extension; + u32 max_sdu[TC_MAX_QUEUE]; size_t num_entries; struct tc_taprio_sched_entry entries[]; -- cgit v1.2.3 From f4ce91ce12a7c6ead19b128ffa8cff6e3ded2a14 Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Wed, 28 Sep 2022 16:03:31 -0400 Subject: tcp: fix tcp_cwnd_validate() to not forget is_cwnd_limited This commit fixes a bug in the tracking of max_packets_out and is_cwnd_limited. This bug can cause the connection to fail to remember that is_cwnd_limited is true, causing the connection to fail to grow cwnd when it should, causing throughput to be lower than it should be. The following event sequence is an example that triggers the bug: (a) The connection is cwnd_limited, but packets_out is not at its peak due to TSO deferral deciding not to send another skb yet. In such cases the connection can advance max_packets_seq and set tp->is_cwnd_limited to true and max_packets_out to a small number. (b) Then later in the round trip the connection is pacing-limited (not cwnd-limited), and packets_out is larger. In such cases the connection would raise max_packets_out to a bigger number but (unexpectedly) flip tp->is_cwnd_limited from true to false. This commit fixes that bug. One straightforward fix would be to separately track (a) the next window after max_packets_out reaches a maximum, and (b) the next window after tp->is_cwnd_limited is set to true. But this would require consuming an extra u32 sequence number. Instead, to save space we track only the most important information. Specifically, we track the strongest available signal of the degree to which the cwnd is fully utilized: (1) If the connection is cwnd-limited then we remember that fact for the current window. (2) If the connection not cwnd-limited then we track the maximum number of outstanding packets in the current window. In particular, note that the new logic cannot trigger the buggy (a)/(b) sequence above because with the new logic a condition where tp->packets_out > tp->max_packets_out can only trigger an update of tp->is_cwnd_limited if tp->is_cwnd_limited is false. This first showed up in a testing of a BBRv2 dev branch, but this buggy behavior highlighted a general issue with the tcp_cwnd_validate() logic that can cause cwnd to fail to increase at the proper rate for any TCP congestion control, including Reno or CUBIC. Fixes: ca8a22634381 ("tcp: make cwnd-limited checks measurement-based, and gentler") Signed-off-by: Neal Cardwell Signed-off-by: Kevin(Yudong) Yang Signed-off-by: Yuchung Cheng Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index d10962b9f0d0..95c1d51393ac 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1295,11 +1295,14 @@ static inline bool tcp_is_cwnd_limited(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); + if (tp->is_cwnd_limited) + return true; + /* If in slow start, ensure cwnd grows to twice what was ACKed. */ if (tcp_in_slow_start(tp)) return tcp_snd_cwnd(tp) < 2 * tp->max_packets_out; - return tp->is_cwnd_limited; + return false; } /* BBR congestion control needs pacing. -- cgit v1.2.3 From 9ca66afe73da16cd2c529e6770cc5aea0c4454df Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Thu, 29 Sep 2022 00:21:41 -0700 Subject: xsk: Expose min chunk size to drivers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Drivers should be aware of the range of valid UMEM chunk sizes to be able to allocate their internal structures of an appropriate size. It will be used by mlx5e in the following patches. Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan CC: "Björn Töpel" CC: Magnus Karlsson CC: Maciej Fijalkowski Signed-off-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- include/net/xdp_sock_drv.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/net') diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 0e58c38ce0c1..6406faa3d57d 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -9,6 +9,9 @@ #include #include +#define XDP_UMEM_MIN_CHUNK_SHIFT 11 +#define XDP_UMEM_MIN_CHUNK_SIZE (1 << XDP_UMEM_MIN_CHUNK_SHIFT) + #ifdef CONFIG_XDP_SOCKETS void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries); -- cgit v1.2.3 From f2f1675836015e79ba9720d4f7f02441fd0bb5e5 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Thu, 29 Sep 2022 00:21:47 -0700 Subject: xsk: Remove unused xsk_buff_discard MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The previous commit removed the last usage of xsk_buff_discard in mlx5e, so the function that is no longer used can be removed. Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan CC: "Björn Töpel" CC: Magnus Karlsson CC: Maciej Fijalkowski Signed-off-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- include/net/xdp_sock_drv.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/net') diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 6406faa3d57d..9c0d860609ba 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -107,13 +107,6 @@ static inline void xsk_buff_free(struct xdp_buff *xdp) xp_free(xskb); } -static inline void xsk_buff_discard(struct xdp_buff *xdp) -{ - struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp); - - xp_release(xskb); -} - static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size) { xdp->data = xdp->data_hard_start + XDP_PACKET_HEADROOM; -- cgit v1.2.3 From 081adcfe930e4b01a55eaa329b2e453a442f35a9 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 29 Sep 2022 09:28:57 +0200 Subject: net: devlink: introduce a flag to indicate devlink port being registered Instead of relying on devlink pointer not being initialized, introduce an extra flag to indicate if devlink port is registered. This is needed as later on devlink pointer is going to be initialized even in case devlink port is not registered yet. Signed-off-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/devlink.h b/include/net/devlink.h index 264aa98e6da6..bcacd8dab297 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -129,7 +129,8 @@ struct devlink_port { void *type_dev; struct devlink_port_attrs attrs; u8 attrs_set:1, - switch_port:1; + switch_port:1, + registered:1; struct delayed_work type_warn_dw; struct list_head reporter_list; struct mutex reporters_lock; /* Protects reporter_list */ -- cgit v1.2.3 From ae3bbc04d4bfef5d0332cd4edda3ac8f714cea23 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 29 Sep 2022 09:28:58 +0200 Subject: net: devlink: add port_init/fini() helpers to allow pre-register/post-unregister functions Lifetime of some of the devlink objects, like regions, is currently forced to be different for devlink instance and devlink port instance (per-port regions). The reason is that for devlink ports, the internal structures initialization happens only after devlink_port_register() is called. To resolve this inconsistency, introduce new set of helpers to allow driver to initialize devlink pointer and region list before devlink_register() is called. That allows port regions to be created before devlink port registration and destroyed after devlink port unregistration. Signed-off-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/devlink.h b/include/net/devlink.h index bcacd8dab297..ba6b8b094943 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -130,7 +130,8 @@ struct devlink_port { struct devlink_port_attrs attrs; u8 attrs_set:1, switch_port:1, - registered:1; + registered:1, + initialized:1; struct delayed_work type_warn_dw; struct list_head reporter_list; struct mutex reporters_lock; /* Protects reporter_list */ @@ -1563,6 +1564,9 @@ void devlink_set_features(struct devlink *devlink, u64 features); void devlink_register(struct devlink *devlink); void devlink_unregister(struct devlink *devlink); void devlink_free(struct devlink *devlink); +void devlink_port_init(struct devlink *devlink, + struct devlink_port *devlink_port); +void devlink_port_fini(struct devlink_port *devlink_port); int devl_port_register(struct devlink *devlink, struct devlink_port *devlink_port, unsigned int port_index); -- cgit v1.2.3 From 61e4a51621587c939672d6a9354f6d0aa3d4e131 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 29 Sep 2022 09:29:02 +0200 Subject: net: dsa: remove bool devlink_port_setup Since dsa_port_devlink_setup() and dsa_port_devlink_teardown() are already called from code paths which only execute once per port (due to the existing bool dp->setup), keeping another dp->devlink_port_setup is redundant, because we can already manage to balance the calls properly (and not call teardown when setup was never called, or call setup twice, or things like that). Signed-off-by: Vladimir Oltean Signed-off-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/net') diff --git a/include/net/dsa.h b/include/net/dsa.h index d777eac5694f..ee369670e20e 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -294,8 +294,6 @@ struct dsa_port { u8 lag_tx_enabled:1; - u8 devlink_port_setup:1; - /* Master state bits, valid only on CPU ports */ u8 master_admin_up:1; u8 master_oper_up:1; -- cgit v1.2.3 From 402963e34a707e4a8f1854ed86437bc375d65766 Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Tue, 27 Sep 2022 20:48:54 +0800 Subject: net: sched: cls_api: introduce tc_cls_bind_class() helper All the bind_class callback duplicate the same logic, this patch introduces tc_cls_bind_class() helper for common usage. Signed-off-by: Zhengchao Shao Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/net') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index d376c995d906..4cabb32a2ad9 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -210,6 +210,18 @@ tcf_unbind_filter(struct tcf_proto *tp, struct tcf_result *r) __tcf_unbind_filter(q, r); } +static inline void tc_cls_bind_class(u32 classid, unsigned long cl, + void *q, struct tcf_result *res, + unsigned long base) +{ + if (res->classid == classid) { + if (cl) + __tcf_bind_filter(q, res, base); + else + __tcf_unbind_filter(q, res); + } +} + struct tcf_exts { #ifdef CONFIG_NET_CLS_ACT __u32 type; /* for backward compat(TCA_OLD_COMPAT) */ -- cgit v1.2.3 From 537dd2d9fb9f4aa7939fb4fcf552ebe4f497bd7e Mon Sep 17 00:00:00 2001 From: Liu Jian Date: Thu, 29 Sep 2022 21:52:02 +0800 Subject: net: Add helper function to parse netlink msg of ip_tunnel_encap Add ip_tunnel_netlink_encap_parms to parse netlink msg of ip_tunnel_encap. Reduces duplicate code, no actual functional changes. Signed-off-by: Liu Jian Signed-off-by: David S. Miller --- include/net/ip_tunnels.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/net') diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index ced80e2f8b58..51da2957cf48 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -302,6 +302,9 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm *p, __u32 fwmark); void ip_tunnel_setup(struct net_device *dev, unsigned int net_id); +bool ip_tunnel_netlink_encap_parms(struct nlattr *data[], + struct ip_tunnel_encap *encap); + extern const struct header_ops ip_tunnel_header_ops; __be16 ip_tunnel_parse_protocol(const struct sk_buff *skb); -- cgit v1.2.3 From b86fca800a6a3d439c454b462f7f067a18234e60 Mon Sep 17 00:00:00 2001 From: Liu Jian Date: Thu, 29 Sep 2022 21:52:03 +0800 Subject: net: Add helper function to parse netlink msg of ip_tunnel_parm Add ip_tunnel_netlink_parms to parse netlink msg of ip_tunnel_parm. Reduces duplicate code, no actual functional changes. Signed-off-by: Liu Jian Signed-off-by: David S. Miller --- include/net/ip_tunnels.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/net') diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 51da2957cf48..fca357679816 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -305,6 +305,9 @@ void ip_tunnel_setup(struct net_device *dev, unsigned int net_id); bool ip_tunnel_netlink_encap_parms(struct nlattr *data[], struct ip_tunnel_encap *encap); +void ip_tunnel_netlink_parms(struct nlattr *data[], + struct ip_tunnel_parm *parms); + extern const struct header_ops ip_tunnel_header_ops; __be16 ip_tunnel_parse_protocol(const struct sk_buff *skb); -- cgit v1.2.3 From 9bc61c04ff6cce6a3756b86e6b34914f7b39d734 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Fri, 30 Sep 2022 16:37:30 +0200 Subject: net: Remove DECnet leftovers from flow.h. DECnet was removed by commit 1202cdd66531 ("Remove DECnet support from kernel"). Let's also revome its flow structure. Compile-tested only (allmodconfig). Signed-off-by: Guillaume Nault Acked-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/net/flow.h | 26 -------------------------- 1 file changed, 26 deletions(-) (limited to 'include/net') diff --git a/include/net/flow.h b/include/net/flow.h index 987bd511d652..2f0da4f0318b 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -54,11 +54,6 @@ union flowi_uli { __u8 code; } icmpt; - struct { - __le16 dport; - __le16 sport; - } dnports; - __be32 gre_key; struct { @@ -156,27 +151,11 @@ struct flowi6 { __u32 mp_hash; } __attribute__((__aligned__(BITS_PER_LONG/8))); -struct flowidn { - struct flowi_common __fl_common; -#define flowidn_oif __fl_common.flowic_oif -#define flowidn_iif __fl_common.flowic_iif -#define flowidn_mark __fl_common.flowic_mark -#define flowidn_scope __fl_common.flowic_scope -#define flowidn_proto __fl_common.flowic_proto -#define flowidn_flags __fl_common.flowic_flags - __le16 daddr; - __le16 saddr; - union flowi_uli uli; -#define fld_sport uli.ports.sport -#define fld_dport uli.ports.dport -} __attribute__((__aligned__(BITS_PER_LONG/8))); - struct flowi { union { struct flowi_common __fl_common; struct flowi4 ip4; struct flowi6 ip6; - struct flowidn dn; } u; #define flowi_oif u.__fl_common.flowic_oif #define flowi_iif u.__fl_common.flowic_iif @@ -211,11 +190,6 @@ static inline struct flowi_common *flowi6_to_flowi_common(struct flowi6 *fl6) return &(fl6->__fl_common); } -static inline struct flowi *flowidn_to_flowi(struct flowidn *fldn) -{ - return container_of(fldn, struct flowi, u.dn); -} - __u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys); #endif -- cgit v1.2.3 From 820dc0523e05c12810bb6bf4e56ce26e4c1948a2 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 30 Sep 2022 00:38:43 +0200 Subject: net: netfilter: move bpf_ct_set_nat_info kfunc in nf_nat_bpf.c Remove circular dependency between nf_nat module and nf_conntrack one moving bpf_ct_set_nat_info kfunc in nf_nat_bpf.c Fixes: 0fabd2aa199f ("net: netfilter: add bpf_ct_set_nat_info kfunc helper") Suggested-by: Kumar Kartikeya Dwivedi Tested-by: Nathan Chancellor Tested-by: Yauheni Kaliuta Signed-off-by: Lorenzo Bianconi Acked-by: John Fastabend Link: https://lore.kernel.org/r/51a65513d2cda3eeb0754842e8025ab3966068d8.1664490511.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/net/netfilter/nf_conntrack_bpf.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/net') diff --git a/include/net/netfilter/nf_conntrack_bpf.h b/include/net/netfilter/nf_conntrack_bpf.h index c8b80add1142..2d0da478c8e0 100644 --- a/include/net/netfilter/nf_conntrack_bpf.h +++ b/include/net/netfilter/nf_conntrack_bpf.h @@ -4,6 +4,11 @@ #define _NF_CONNTRACK_BPF_H #include +#include + +struct nf_conn___init { + struct nf_conn ct; +}; #if (IS_BUILTIN(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \ (IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) @@ -24,4 +29,18 @@ static inline void cleanup_nf_conntrack_bpf(void) #endif +#if (IS_BUILTIN(CONFIG_NF_NAT) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \ + (IS_MODULE(CONFIG_NF_NAT) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) + +extern int register_nf_nat_bpf(void); + +#else + +static inline int register_nf_nat_bpf(void) +{ + return 0; +} + +#endif + #endif /* _NF_CONNTRACK_BPF_H */ -- cgit v1.2.3 From 58d331312bf78a10740fc3c6c370c98e8c53fa6b Mon Sep 17 00:00:00 2001 From: Christian Schoenebeck Date: Fri, 15 Jul 2022 23:32:30 +0200 Subject: 9p: add P9_ERRMAX for 9p2000 and 9p2000.u Add P9_ERRMAX macro to 9P protocol header which reflects the maximum error string length of Rerror replies for 9p2000 and 9p2000.u protocol versions. Unfortunately a maximum error string length is not defined by the 9p2000 spec, picking 128 as value for now, as this seems to be a common max. size for POSIX error strings in practice. 9p2000.L protocol version uses Rlerror replies instead which does not contain an error string. Link: https://lkml.kernel.org/r/3f23191d21032e7c14852b1e1a4ae26417a36739.1657920926.git.linux_oss@crudebyte.com Signed-off-by: Christian Schoenebeck Signed-off-by: Dominique Martinet --- include/net/9p/9p.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/net') diff --git a/include/net/9p/9p.h b/include/net/9p/9p.h index 24a509f559ee..13abe013af21 100644 --- a/include/net/9p/9p.h +++ b/include/net/9p/9p.h @@ -331,6 +331,9 @@ enum p9_qid_t { /* size of header for zero copy read/write */ #define P9_ZC_HDR_SZ 4096 +/* maximum length of an error string */ +#define P9_ERRMAX 128 + /** * struct p9_qid - file system entity information * @type: 8-bit type &p9_qid_t -- cgit v1.2.3 From 01d205d936ae18532e14814808592b926aacc6d5 Mon Sep 17 00:00:00 2001 From: Christian Schoenebeck Date: Fri, 15 Jul 2022 23:33:09 +0200 Subject: net/9p: add 'pooled_rbuffers' flag to struct p9_trans_module This is a preparatory change for the subsequent patch: the RDMA transport pulls the buffers for its 9p response messages from a shared pool. [1] So this case has to be considered when choosing an appropriate response message size in the subsequent patch. Link: https://lore.kernel.org/all/Ys3jjg52EIyITPua@codewreck.org/ [1] Link: https://lkml.kernel.org/r/79d24310226bc4eb037892b5c097ec4ad4819a03.1657920926.git.linux_oss@crudebyte.com Signed-off-by: Christian Schoenebeck Signed-off-by: Dominique Martinet --- include/net/9p/transport.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/net') diff --git a/include/net/9p/transport.h b/include/net/9p/transport.h index ff842f963071..766ec07c9599 100644 --- a/include/net/9p/transport.h +++ b/include/net/9p/transport.h @@ -19,6 +19,10 @@ * @list: used to maintain a list of currently available transports * @name: the human-readable name of the transport * @maxsize: transport provided maximum packet size + * @pooled_rbuffers: currently only set for RDMA transport which pulls the + * response buffers from a shared pool, and accordingly + * we're less flexible when choosing the response message + * size in this case * @def: set if this transport should be considered the default * @create: member function to create a new connection on this transport * @close: member function to discard a connection on this transport @@ -38,6 +42,7 @@ struct p9_trans_module { struct list_head list; char *name; /* name of transport */ int maxsize; /* max message size of transport */ + bool pooled_rbuffers; int def; /* this transport should be default */ struct module *owner; int (*create)(struct p9_client *client, -- cgit v1.2.3 From 30393181fdbc1608cc683b4ee99dcce05ffcc8c7 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 5 Oct 2022 22:02:37 -0400 Subject: net: ieee802154: return -EINVAL for unknown addr type This patch adds handling to return -EINVAL for an unknown addr type. The current behaviour is to return 0 as successful but the size of an unknown addr type is not defined and should return an error like -EINVAL. Fixes: 94160108a70c ("net/ieee802154: fix uninit value bug in dgram_sendmsg") Signed-off-by: Alexander Aring Signed-off-by: David S. Miller --- include/net/ieee802154_netdev.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h index a8994f307fc3..03b64bf876a4 100644 --- a/include/net/ieee802154_netdev.h +++ b/include/net/ieee802154_netdev.h @@ -185,21 +185,27 @@ static inline int ieee802154_sockaddr_check_size(struct sockaddr_ieee802154 *daddr, int len) { struct ieee802154_addr_sa *sa; + int ret = 0; sa = &daddr->addr; if (len < IEEE802154_MIN_NAMELEN) return -EINVAL; switch (sa->addr_type) { + case IEEE802154_ADDR_NONE: + break; case IEEE802154_ADDR_SHORT: if (len < IEEE802154_NAMELEN_SHORT) - return -EINVAL; + ret = -EINVAL; break; case IEEE802154_ADDR_LONG: if (len < IEEE802154_NAMELEN_LONG) - return -EINVAL; + ret = -EINVAL; + break; + default: + ret = -EINVAL; break; } - return 0; + return ret; } static inline void ieee802154_addr_from_sa(struct ieee802154_addr *a, -- cgit v1.2.3 From a251c17aa558d8e3128a528af5cf8b9d7caae4fd Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 5 Oct 2022 17:43:22 +0200 Subject: treewide: use get_random_u32() when possible MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The prandom_u32() function has been a deprecated inline wrapper around get_random_u32() for several releases now, and compiles down to the exact same code. Replace the deprecated wrapper with a direct call to the real function. The same also applies to get_random_int(), which is just a wrapper around get_random_u32(). This was done as a basic find and replace. Reviewed-by: Greg Kroah-Hartman Reviewed-by: Kees Cook Reviewed-by: Yury Norov Reviewed-by: Jan Kara # for ext4 Acked-by: Toke Høiland-Jørgensen # for sch_cake Acked-by: Chuck Lever # for nfsd Acked-by: Jakub Kicinski Acked-by: Mika Westerberg # for thunderbolt Acked-by: Darrick J. Wong # for xfs Acked-by: Helge Deller # for parisc Acked-by: Heiko Carstens # for s390 Signed-off-by: Jason A. Donenfeld --- include/net/netfilter/nf_queue.h | 2 +- include/net/red.h | 2 +- include/net/sock.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index 980daa6e1e3a..c81021ab07aa 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -43,7 +43,7 @@ void nf_queue_entry_free(struct nf_queue_entry *entry); static inline void init_hashrandom(u32 *jhash_initval) { while (*jhash_initval == 0) - *jhash_initval = prandom_u32(); + *jhash_initval = get_random_u32(); } static inline u32 hash_v4(const struct iphdr *iph, u32 initval) diff --git a/include/net/red.h b/include/net/red.h index 454ac2b65d8c..425364de0df7 100644 --- a/include/net/red.h +++ b/include/net/red.h @@ -363,7 +363,7 @@ static inline unsigned long red_calc_qavg(const struct red_parms *p, static inline u32 red_random(const struct red_parms *p) { - return reciprocal_divide(prandom_u32(), p->max_P_reciprocal); + return reciprocal_divide(get_random_u32(), p->max_P_reciprocal); } static inline int red_mark_probability(const struct red_parms *p, diff --git a/include/net/sock.h b/include/net/sock.h index 08038a385ef2..9e464f6409a7 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2109,7 +2109,7 @@ static inline kuid_t sock_net_uid(const struct net *net, const struct sock *sk) static inline u32 net_tx_rndhash(void) { - u32 v = prandom_u32(); + u32 v = get_random_u32(); return v ?: 1; } -- cgit v1.2.3 From 21985f43376cee092702d6cb963ff97a9d2ede68 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Thu, 6 Oct 2022 11:53:46 -0700 Subject: udp: Call inet6_destroy_sock() in setsockopt(IPV6_ADDRFORM). Commit 4b340ae20d0e ("IPv6: Complete IPV6_DONTFRAG support") forgot to add a change to free inet6_sk(sk)->rxpmtu while converting an IPv6 socket into IPv4 with IPV6_ADDRFORM. After conversion, sk_prot is changed to udp_prot and ->destroy() never cleans it up, resulting in a memory leak. This is due to the discrepancy between inet6_destroy_sock() and IPV6_ADDRFORM, so let's call inet6_destroy_sock() from IPV6_ADDRFORM to remove the difference. However, this is not enough for now because rxpmtu can be changed without lock_sock() after commit 03485f2adcde ("udpv6: Add lockless sendmsg() support"). We will fix this case in the following patch. Note we will rename inet6_destroy_sock() to inet6_cleanup_sock() and remove unnecessary inet6_destroy_sock() calls in sk_prot->destroy() in the future. Fixes: 4b340ae20d0e ("IPv6: Complete IPV6_DONTFRAG support") Signed-off-by: Kuniyuki Iwashima Signed-off-by: Jakub Kicinski --- include/net/ipv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index d664ba5812d8..335a49ecd8a0 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1182,6 +1182,7 @@ void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info); void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu); +void inet6_cleanup_sock(struct sock *sk); int inet6_release(struct socket *sock); int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); int inet6_getname(struct socket *sock, struct sockaddr *uaddr, -- cgit v1.2.3 From d38afeec26ed4739c640bf286c270559aab2ba5f Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Thu, 6 Oct 2022 11:53:47 -0700 Subject: tcp/udp: Call inet6_destroy_sock() in IPv6 sk->sk_destruct(). Originally, inet6_sk(sk)->XXX were changed under lock_sock(), so we were able to clean them up by calling inet6_destroy_sock() during the IPv6 -> IPv4 conversion by IPV6_ADDRFORM. However, commit 03485f2adcde ("udpv6: Add lockless sendmsg() support") added a lockless memory allocation path, which could cause a memory leak: setsockopt(IPV6_ADDRFORM) sendmsg() +-----------------------+ +-------+ - do_ipv6_setsockopt(sk, ...) - udpv6_sendmsg(sk, ...) - sockopt_lock_sock(sk) ^._ called via udpv6_prot - lock_sock(sk) before WRITE_ONCE() - WRITE_ONCE(sk->sk_prot, &tcp_prot) - inet6_destroy_sock() - if (!corkreq) - sockopt_release_sock(sk) - ip6_make_skb(sk, ...) - release_sock(sk) ^._ lockless fast path for the non-corking case - __ip6_append_data(sk, ...) - ipv6_local_rxpmtu(sk, ...) - xchg(&np->rxpmtu, skb) ^._ rxpmtu is never freed. - goto out_no_dst; - lock_sock(sk) For now, rxpmtu is only the case, but not to miss the future change and a similar bug fixed in commit e27326009a3d ("net: ping6: Fix memleak in ipv6_renew_options()."), let's set a new function to IPv6 sk->sk_destruct() and call inet6_cleanup_sock() there. Since the conversion does not change sk->sk_destruct(), we can guarantee that we can clean up IPv6 resources finally. We can now remove all inet6_destroy_sock() calls from IPv6 protocol specific ->destroy() functions, but such changes are invasive to backport. So they can be posted as a follow-up later for net-next. Fixes: 03485f2adcde ("udpv6: Add lockless sendmsg() support") Signed-off-by: Kuniyuki Iwashima Signed-off-by: Jakub Kicinski --- include/net/ipv6.h | 1 + include/net/udp.h | 2 +- include/net/udplite.h | 8 -------- 3 files changed, 2 insertions(+), 9 deletions(-) (limited to 'include/net') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 335a49ecd8a0..37943ba3a73c 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1183,6 +1183,7 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info); void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu); void inet6_cleanup_sock(struct sock *sk); +void inet6_sock_destruct(struct sock *sk); int inet6_release(struct socket *sock); int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); int inet6_getname(struct socket *sock, struct sockaddr *uaddr, diff --git a/include/net/udp.h b/include/net/udp.h index 5ee88ddf79c3..fee053bcd17c 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -247,7 +247,7 @@ static inline bool udp_sk_bound_dev_eq(struct net *net, int bound_dev_if, } /* net/ipv4/udp.c */ -void udp_destruct_sock(struct sock *sk); +void udp_destruct_common(struct sock *sk); void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len); int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb); void udp_skb_destructor(struct sock *sk, struct sk_buff *skb); diff --git a/include/net/udplite.h b/include/net/udplite.h index 0143b373602e..299c14ce2bb9 100644 --- a/include/net/udplite.h +++ b/include/net/udplite.h @@ -25,14 +25,6 @@ static __inline__ int udplite_getfrag(void *from, char *to, int offset, return copy_from_iter_full(to, len, &msg->msg_iter) ? 0 : -EFAULT; } -/* Designate sk as UDP-Lite socket */ -static inline int udplite_sk_init(struct sock *sk) -{ - udp_init_sock(sk); - udp_sk(sk)->pcflag = UDPLITE_BIT; - return 0; -} - /* * Checksumming routines */ -- cgit v1.2.3