linux/include/net/udp.h

536 lines
16 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Definitions for the UDP module.
*
* Version: @(#)udp.h 1.0.2 05/07/93
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
*
* Fixes:
* Alan Cox : Turned on udp checksums. I don't want to
* chase 'memory corruption' bugs that aren't!
*/
#ifndef _UDP_H
#define _UDP_H
#include <linux/list.h>
#include <linux/bug.h>
#include <net/inet_sock.h>
#include <net/sock.h>
#include <net/snmp.h>
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-27 22:10:57 +03:00
#include <net/ip.h>
#include <linux/ipv6.h>
#include <linux/seq_file.h>
#include <linux/poll.h>
#include <linux/indirect_call_wrapper.h>
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-27 22:10:57 +03:00
/**
* struct udp_skb_cb - UDP(-Lite) private variables
*
* @header: private variables used by IPv4/IPv6
* @cscov: checksum coverage length (UDP-Lite only)
* @partial_cov: if set indicates partial csum coverage
*/
struct udp_skb_cb {
union {
struct inet_skb_parm h4;
#if IS_ENABLED(CONFIG_IPV6)
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-27 22:10:57 +03:00
struct inet6_skb_parm h6;
#endif
} header;
__u16 cscov;
__u8 partial_cov;
};
#define UDP_SKB_CB(__skb) ((struct udp_skb_cb *)((__skb)->cb))
/**
* struct udp_hslot - UDP hash slot
*
* @head: head of list of sockets
* @count: number of sockets in 'head' list
* @lock: spinlock protecting changes to head/count
*/
struct udp_hslot {
struct hlist_head head;
int count;
spinlock_t lock;
} __attribute__((aligned(2 * sizeof(long))));
/**
* struct udp_table - UDP table
*
* @hash: hash table, sockets are hashed on (local port)
* @hash2: hash table, sockets are hashed on (local port, local address)
* @mask: number of slots in hash tables, minus 1
* @log: log2(number of slots in hash table)
*/
struct udp_table {
struct udp_hslot *hash;
struct udp_hslot *hash2;
unsigned int mask;
unsigned int log;
};
extern struct udp_table udp_table;
void udp_table_init(struct udp_table *, const char *);
static inline struct udp_hslot *udp_hashslot(struct udp_table *table,
struct net *net, unsigned int num)
{
return &table->hash[udp_hashfn(net, num, table->mask)];
}
/*
* For secondary hash, net_hash_mix() is performed before calling
* udp_hashslot2(), this explains difference with udp_hashslot()
*/
static inline struct udp_hslot *udp_hashslot2(struct udp_table *table,
unsigned int hash)
{
return &table->hash2[hash & table->mask];
}
extern struct proto udp_prot;
extern atomic_long_t udp_memory_allocated;
DECLARE_PER_CPU(int, udp_memory_per_cpu_fw_alloc);
/* sysctl variables for udp */
extern long sysctl_udp_mem[3];
extern int sysctl_udp_rmem_min;
extern int sysctl_udp_wmem_min;
struct sk_buff;
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-27 22:10:57 +03:00
/*
* Generic checksumming routines for UDP(-Lite) v4 and v6
*/
static inline __sum16 __udp_lib_checksum_complete(struct sk_buff *skb)
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-27 22:10:57 +03:00
{
return (UDP_SKB_CB(skb)->cscov == skb->len ?
__skb_checksum_complete(skb) :
__skb_checksum_complete_head(skb, UDP_SKB_CB(skb)->cscov));
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-27 22:10:57 +03:00
}
static inline int udp_lib_checksum_complete(struct sk_buff *skb)
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-27 22:10:57 +03:00
{
return !skb_csum_unnecessary(skb) &&
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-27 22:10:57 +03:00
__udp_lib_checksum_complete(skb);
}
/**
* udp_csum_outgoing - compute UDPv4/v6 checksum over fragments
* @sk: socket we are writing to
* @skb: sk_buff containing the filled-in UDP header
* (checksum field must be zeroed out)
*/
static inline __wsum udp_csum_outgoing(struct sock *sk, struct sk_buff *skb)
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-27 22:10:57 +03:00
{
__wsum csum = csum_partial(skb_transport_header(skb),
sizeof(struct udphdr), 0);
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-27 22:10:57 +03:00
skb_queue_walk(&sk->sk_write_queue, skb) {
csum = csum_add(csum, skb->csum);
}
return csum;
}
static inline __wsum udp_csum(struct sk_buff *skb)
{
__wsum csum = csum_partial(skb_transport_header(skb),
sizeof(struct udphdr), skb->csum);
for (skb = skb_shinfo(skb)->frag_list; skb; skb = skb->next) {
csum = csum_add(csum, skb->csum);
}
return csum;
}
static inline __sum16 udp_v4_check(int len, __be32 saddr,
__be32 daddr, __wsum base)
{
return csum_tcpudp_magic(saddr, daddr, len, IPPROTO_UDP, base);
}
void udp_set_csum(bool nocheck, struct sk_buff *skb,
__be32 saddr, __be32 daddr, int len);
static inline void udp_csum_pull_header(struct sk_buff *skb)
{
if (!skb->csum_valid && skb->ip_summed == CHECKSUM_NONE)
skb->csum = csum_partial(skb->data, sizeof(struct udphdr),
skb->csum);
skb_pull_rcsum(skb, sizeof(struct udphdr));
UDP_SKB_CB(skb)->cscov -= sizeof(struct udphdr);
}
typedef struct sock *(*udp_lookup_t)(const struct sk_buff *skb, __be16 sport,
__be16 dport);
tcp/udp: Make early_demux back namespacified. Commit e21145a9871a ("ipv4: namespacify ip_early_demux sysctl knob") made it possible to enable/disable early_demux on a per-netns basis. Then, we introduced two knobs, tcp_early_demux and udp_early_demux, to switch it for TCP/UDP in commit dddb64bcb346 ("net: Add sysctl to toggle early demux for tcp and udp"). However, the .proc_handler() was wrong and actually disabled us from changing the behaviour in each netns. We can execute early_demux if net.ipv4.ip_early_demux is on and each proto .early_demux() handler is not NULL. When we toggle (tcp|udp)_early_demux, the change itself is saved in each netns variable, but the .early_demux() handler is a global variable, so the handler is switched based on the init_net's sysctl variable. Thus, netns (tcp|udp)_early_demux knobs have nothing to do with the logic. Whether we CAN execute proto .early_demux() is always decided by init_net's sysctl knob, and whether we DO it or not is by each netns ip_early_demux knob. This patch namespacifies (tcp|udp)_early_demux again. For now, the users of the .early_demux() handler are TCP and UDP only, and they are called directly to avoid retpoline. So, we can remove the .early_demux() handler from inet6?_protos and need not dereference them in ip6?_rcv_finish_core(). If another proto needs .early_demux(), we can restore it at that time. Fixes: dddb64bcb346 ("net: Add sysctl to toggle early demux for tcp and udp") Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Link: https://lore.kernel.org/r/20220713175207.7727-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-07-13 20:52:07 +03:00
void udp_v6_early_demux(struct sk_buff *skb);
INDIRECT_CALLABLE_DECLARE(int udpv6_rcv(struct sk_buff *));
struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
netdev_features_t features, bool is_ipv6);
static inline void udp_lib_init_sock(struct sock *sk)
{
struct udp_sock *up = udp_sk(sk);
skb_queue_head_init(&up->reader_queue);
up->forward_threshold = sk->sk_rcvbuf >> 2;
set_bit(SOCK_CUSTOM_SOCKOPT, &sk->sk_socket->flags);
}
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-27 22:10:57 +03:00
/* hash routines shared between UDPv4/6 and UDP-Litev4/6 */
static inline int udp_lib_hash(struct sock *sk)
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-27 22:10:57 +03:00
{
BUG();
return 0;
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-27 22:10:57 +03:00
}
void udp_lib_unhash(struct sock *sk);
void udp_lib_rehash(struct sock *sk, u16 new_hash);
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-27 22:10:57 +03:00
static inline void udp_lib_close(struct sock *sk, long timeout)
{
sk_common_release(sk);
}
int udp_lib_get_port(struct sock *sk, unsigned short snum,
unsigned int hash2_nulladdr);
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-27 22:10:57 +03:00
u32 udp_flow_hashrnd(void);
static inline __be16 udp_flow_src_port(struct net *net, struct sk_buff *skb,
int min, int max, bool use_eth)
{
u32 hash;
if (min >= max) {
/* Use default range */
inet_get_local_port_range(net, &min, &max);
}
hash = skb_get_hash(skb);
if (unlikely(!hash)) {
if (use_eth) {
/* Can't find a normal hash, caller has indicated an
* Ethernet packet so use that to compute a hash.
*/
hash = jhash(skb->data, 2 * ETH_ALEN,
(__force u32) skb->protocol);
} else {
/* Can't derive any sort of hash for the packet, set
* to some consistent random value.
*/
hash = udp_flow_hashrnd();
}
}
/* Since this is being sent on the wire obfuscate hash a bit
* to minimize possbility that any useful information to an
* attacker is leaked. Only upper 16 bits are relevant in the
* computation for 16 bit port value.
*/
hash ^= hash << 16;
return htons((((u64) hash * (max - min)) >> 32) + min);
}
static inline int udp_rqueue_get(struct sock *sk)
{
return sk_rmem_alloc_get(sk) - READ_ONCE(udp_sk(sk)->forward_deficit);
}
net: ensure unbound datagram socket to be chosen when not in a VRF Ensure an unbound datagram skt is chosen when not in a VRF. The check for a device match in compute_score() for UDP must be performed when there is no device match. For this, a failure is returned when there is no device match. This ensures that bound sockets are never selected, even if there is no unbound socket. Allow IPv6 packets to be sent over a datagram skt bound to a VRF. These packets are currently blocked, as flowi6_oif was set to that of the master vrf device, and the ipi6_ifindex is that of the slave device. Allow these packets to be sent by checking the device with ipi6_ifindex has the same L3 scope as that of the bound device of the skt, which is the master vrf device. Note that this check always succeeds if the skt is unbound. Even though the right datagram skt is now selected by compute_score(), a different skt is being returned that is bound to the wrong vrf. The difference between these and stream sockets is the handling of the skt option for SO_REUSEPORT. While the handling when adding a skt for reuse correctly checks that the bound device of the skt is a match, the skts in the hashslot are already incorrect. So for the same hash, a skt for the wrong vrf may be selected for the required port. The root cause is that the skt is immediately placed into a slot when it is created, but when the skt is then bound using SO_BINDTODEVICE, it remains in the same slot. The solution is to move the skt to the correct slot by forcing a rehash. Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com> Reviewed-by: David Ahern <dsahern@gmail.com> Tested-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-07 18:36:04 +03:00
static inline bool udp_sk_bound_dev_eq(struct net *net, int bound_dev_if,
int dif, int sdif)
{
#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
return inet_bound_dev_eq(!!READ_ONCE(net->ipv4.sysctl_udp_l3mdev_accept),
net: ensure unbound datagram socket to be chosen when not in a VRF Ensure an unbound datagram skt is chosen when not in a VRF. The check for a device match in compute_score() for UDP must be performed when there is no device match. For this, a failure is returned when there is no device match. This ensures that bound sockets are never selected, even if there is no unbound socket. Allow IPv6 packets to be sent over a datagram skt bound to a VRF. These packets are currently blocked, as flowi6_oif was set to that of the master vrf device, and the ipi6_ifindex is that of the slave device. Allow these packets to be sent by checking the device with ipi6_ifindex has the same L3 scope as that of the bound device of the skt, which is the master vrf device. Note that this check always succeeds if the skt is unbound. Even though the right datagram skt is now selected by compute_score(), a different skt is being returned that is bound to the wrong vrf. The difference between these and stream sockets is the handling of the skt option for SO_REUSEPORT. While the handling when adding a skt for reuse correctly checks that the bound device of the skt is a match, the skts in the hashslot are already incorrect. So for the same hash, a skt for the wrong vrf may be selected for the required port. The root cause is that the skt is immediately placed into a slot when it is created, but when the skt is then bound using SO_BINDTODEVICE, it remains in the same slot. The solution is to move the skt to the correct slot by forcing a rehash. Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com> Reviewed-by: David Ahern <dsahern@gmail.com> Tested-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-07 18:36:04 +03:00
bound_dev_if, dif, sdif);
#else
return inet_bound_dev_eq(true, bound_dev_if, dif, sdif);
#endif
}
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-27 22:10:57 +03:00
/* net/ipv4/udp.c */
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 <kuniyu@amazon.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-10-06 21:53:47 +03:00
void udp_destruct_common(struct sock *sk);
2016-10-21 14:55:46 +03:00
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);
struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, int *off,
int *err);
static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags,
int *err)
{
int off = 0;
return __skb_recv_udp(sk, flags, &off, err);
}
2016-10-21 14:55:46 +03:00
int udp_v4_early_demux(struct sk_buff *skb);
bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst);
int udp_get_port(struct sock *sk, unsigned short snum,
int (*saddr_cmp)(const struct sock *,
const struct sock *));
int udp_err(struct sk_buff *, u32);
int udp_abort(struct sock *sk, int err);
int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len);
int udp_push_pending_frames(struct sock *sk);
void udp_flush_pending_frames(struct sock *sk);
int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size);
void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst);
int udp_rcv(struct sk_buff *skb);
int udp_ioctl(struct sock *sk, int cmd, unsigned long arg);
2016-10-21 14:55:46 +03:00
int udp_init_sock(struct sock *sk);
bpf: Hooks for sys_connect == The problem == See description of the problem in the initial patch of this patch set. == The solution == The patch provides much more reliable in-kernel solution for the 2nd part of the problem: making outgoing connecttion from desired IP. It adds new attach types `BPF_CGROUP_INET4_CONNECT` and `BPF_CGROUP_INET6_CONNECT` for program type `BPF_PROG_TYPE_CGROUP_SOCK_ADDR` that can be used to override both source and destination of a connection at connect(2) time. Local end of connection can be bound to desired IP using newly introduced BPF-helper `bpf_bind()`. It allows to bind to only IP though, and doesn't support binding to port, i.e. leverages `IP_BIND_ADDRESS_NO_PORT` socket option. There are two reasons for this: * looking for a free port is expensive and can affect performance significantly; * there is no use-case for port. As for remote end (`struct sockaddr *` passed by user), both parts of it can be overridden, remote IP and remote port. It's useful if an application inside cgroup wants to connect to another application inside same cgroup or to itself, but knows nothing about IP assigned to the cgroup. Support is added for IPv4 and IPv6, for TCP and UDP. IPv4 and IPv6 have separate attach types for same reason as sys_bind hooks, i.e. to prevent reading from / writing to e.g. user_ip6 fields when user passes sockaddr_in since it'd be out-of-bound. == Implementation notes == The patch introduces new field in `struct proto`: `pre_connect` that is a pointer to a function with same signature as `connect` but is called before it. The reason is in some cases BPF hooks should be called way before control is passed to `sk->sk_prot->connect`. Specifically `inet_dgram_connect` autobinds socket before calling `sk->sk_prot->connect` and there is no way to call `bpf_bind()` from hooks from e.g. `ip4_datagram_connect` or `ip6_datagram_connect` since it'd cause double-bind. On the other hand `proto.pre_connect` provides a flexible way to add BPF hooks for connect only for necessary `proto` and call them at desired time before `connect`. Since `bpf_bind()` is allowed to bind only to IP and autobind in `inet_dgram_connect` binds only port there is no chance of double-bind. bpf_bind() sets `force_bind_address_no_port` to bind to only IP despite of value of `bind_address_no_port` socket field. bpf_bind() sets `with_lock` to `false` when calling to __inet_bind() and __inet6_bind() since all call-sites, where bpf_bind() is called, already hold socket lock. Signed-off-by: Andrey Ignatov <rdna@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-03-31 01:08:05 +03:00
int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
int __udp_disconnect(struct sock *sk, int flags);
int udp_disconnect(struct sock *sk, int flags);
__poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait);
struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
netdev_features_t features,
bool is_ipv6);
int udp_lib_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen);
int udp_lib_setsockopt(struct sock *sk, int level, int optname,
sockptr_t optval, unsigned int optlen,
int (*push_pending_frames)(struct sock *));
struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
__be32 daddr, __be16 dport, int dif);
struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
__be32 daddr, __be16 dport, int dif, int sdif,
struct udp_table *tbl, struct sk_buff *skb);
struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb,
__be16 sport, __be16 dport);
struct sock *udp6_lib_lookup(struct net *net,
const struct in6_addr *saddr, __be16 sport,
const struct in6_addr *daddr, __be16 dport,
int dif);
struct sock *__udp6_lib_lookup(struct net *net,
const struct in6_addr *saddr, __be16 sport,
const struct in6_addr *daddr, __be16 dport,
int dif, int sdif, struct udp_table *tbl,
struct sk_buff *skb);
struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb,
__be16 sport, __be16 dport);
int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor);
/* UDP uses skb->dev_scratch to cache as much information as possible and avoid
* possibly multiple cache miss on dequeue()
*/
struct udp_dev_scratch {
/* skb->truesize and the stateless bit are embedded in a single field;
* do not use a bitfield since the compiler emits better/smaller code
* this way
*/
u32 _tsize_state;
#if BITS_PER_LONG == 64
/* len and the bit needed to compute skb_csum_unnecessary
* will be on cold cache lines at recvmsg time.
* skb->len can be stored on 16 bits since the udp header has been
* already validated and pulled.
*/
u16 len;
bool is_linear;
bool csum_unnecessary;
#endif
};
static inline struct udp_dev_scratch *udp_skb_scratch(struct sk_buff *skb)
{
return (struct udp_dev_scratch *)&skb->dev_scratch;
}
#if BITS_PER_LONG == 64
static inline unsigned int udp_skb_len(struct sk_buff *skb)
{
return udp_skb_scratch(skb)->len;
}
static inline bool udp_skb_csum_unnecessary(struct sk_buff *skb)
{
return udp_skb_scratch(skb)->csum_unnecessary;
}
static inline bool udp_skb_is_linear(struct sk_buff *skb)
{
return udp_skb_scratch(skb)->is_linear;
}
#else
static inline unsigned int udp_skb_len(struct sk_buff *skb)
{
return skb->len;
}
static inline bool udp_skb_csum_unnecessary(struct sk_buff *skb)
{
return skb_csum_unnecessary(skb);
}
static inline bool udp_skb_is_linear(struct sk_buff *skb)
{
return !skb_is_nonlinear(skb);
}
#endif
static inline int copy_linear_skb(struct sk_buff *skb, int len, int off,
struct iov_iter *to)
{
int n;
n = copy_to_iter(skb->data + off, len, to);
if (n == len)
return 0;
iov_iter_revert(to, n);
return -EFAULT;
}
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-27 22:10:57 +03:00
/*
* SNMP statistics for UDP and UDP-Lite
*/
#define UDP_INC_STATS(net, field, is_udplite) do { \
if (is_udplite) SNMP_INC_STATS((net)->mib.udplite_statistics, field); \
else SNMP_INC_STATS((net)->mib.udp_statistics, field); } while(0)
#define __UDP_INC_STATS(net, field, is_udplite) do { \
if (is_udplite) __SNMP_INC_STATS((net)->mib.udplite_statistics, field); \
else __SNMP_INC_STATS((net)->mib.udp_statistics, field); } while(0)
#define __UDP6_INC_STATS(net, field, is_udplite) do { \
if (is_udplite) __SNMP_INC_STATS((net)->mib.udplite_stats_in6, field);\
else __SNMP_INC_STATS((net)->mib.udp_stats_in6, field); \
} while(0)
#define UDP6_INC_STATS(net, field, __lite) do { \
if (__lite) SNMP_INC_STATS((net)->mib.udplite_stats_in6, field); \
else SNMP_INC_STATS((net)->mib.udp_stats_in6, field); \
} while(0)
#if IS_ENABLED(CONFIG_IPV6)
#define __UDPX_MIB(sk, ipv4) \
({ \
ipv4 ? (IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_statistics : \
sock_net(sk)->mib.udp_statistics) : \
(IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_stats_in6 : \
sock_net(sk)->mib.udp_stats_in6); \
})
#else
#define __UDPX_MIB(sk, ipv4) \
({ \
IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_statistics : \
sock_net(sk)->mib.udp_statistics; \
})
#endif
#define __UDPX_INC_STATS(sk, field) \
__SNMP_INC_STATS(__UDPX_MIB(sk, (sk)->sk_family == AF_INET), field)
#ifdef CONFIG_PROC_FS
struct udp_seq_afinfo {
sa_family_t family;
struct udp_table *udp_table;
};
struct udp_iter_state {
struct seq_net_private p;
int bucket;
struct udp_seq_afinfo *bpf_seq_afinfo;
};
void *udp_seq_start(struct seq_file *seq, loff_t *pos);
void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos);
void udp_seq_stop(struct seq_file *seq, void *v);
extern const struct seq_operations udp_seq_ops;
extern const struct seq_operations udp6_seq_ops;
int udp4_proc_init(void);
void udp4_proc_exit(void);
#endif /* CONFIG_PROC_FS */
int udpv4_offload_init(void);
void udp_init(void);
DECLARE_STATIC_KEY_FALSE(udp_encap_needed_key);
void udp_encap_enable(void);
void udp_encap_disable(void);
#if IS_ENABLED(CONFIG_IPV6)
DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
void udpv6_encap_enable(void);
#endif
static inline struct sk_buff *udp_rcv_segment(struct sock *sk,
struct sk_buff *skb, bool ipv4)
{
netdev_features_t features = NETIF_F_SG;
struct sk_buff *segs;
/* Avoid csum recalculation by skb_segment unless userspace explicitly
* asks for the final checksum values
*/
if (!inet_get_convert_csum(sk))
features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
/* UDP segmentation expects packets of type CHECKSUM_PARTIAL or
* CHECKSUM_NONE in __udp_gso_segment. UDP GRO indeed builds partial
* packets in udp_gro_complete_segment. As does UDP GSO, verified by
* udp_send_skb. But when those packets are looped in dev_loopback_xmit
net: multicast: calculate csum of looped-back and forwarded packets During a testing of an user-space application which transmits UDP multicast datagrams and utilizes multicast routing to send the UDP datagrams out of defined network interfaces, I've found a multicast router does not fill-in UDP checksum into locally produced, looped-back and forwarded UDP datagrams, if an original output NIC the datagrams are sent to has UDP TX checksum offload enabled. The datagrams are sent malformed out of the NIC the datagrams have been forwarded to. It is because: 1. If TX checksum offload is enabled on the output NIC, UDP checksum is not calculated by kernel and is not filled into skb data. 2. dev_loopback_xmit(), which is called solely by ip_mc_finish_output(), sets skb->ip_summed = CHECKSUM_UNNECESSARY unconditionally. 3. Since 35fc92a9 ("[NET]: Allow forwarding of ip_summed except CHECKSUM_COMPLETE"), the ip_summed value is preserved during forwarding. 4. If ip_summed != CHECKSUM_PARTIAL, checksum is not calculated during a packet egress. The minimum fix in dev_loopback_xmit(): 1. Preserves skb->ip_summed CHECKSUM_PARTIAL. This is the case when the original output NIC has TX checksum offload enabled. The effects are: a) If the forwarding destination interface supports TX checksum offloading, the NIC driver is responsible to fill-in the checksum. b) If the forwarding destination interface does NOT support TX checksum offloading, checksums are filled-in by kernel before skb is submitted to the NIC driver. c) For local delivery, checksum validation is skipped as in the case of CHECKSUM_UNNECESSARY, thanks to skb_csum_unnecessary(). 2. Translates ip_summed CHECKSUM_NONE to CHECKSUM_UNNECESSARY. It means, for CHECKSUM_NONE, the behavior is unmodified and is there to skip a looped-back packet local delivery checksum validation. Signed-off-by: Cyril Strejc <cyril.strejc@skoda.cz> Reviewed-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-10-24 23:14:25 +03:00
* their ip_summed CHECKSUM_NONE is changed to CHECKSUM_UNNECESSARY.
* Reset in this specific case, where PARTIAL is both correct and
* required.
*/
if (skb->pkt_type == PACKET_LOOPBACK)
skb->ip_summed = CHECKSUM_PARTIAL;
/* the GSO CB lays after the UDP one, no need to save and restore any
* CB fragment
*/
segs = __skb_gso_segment(skb, features, false);
if (IS_ERR_OR_NULL(segs)) {
int segs_nr = skb_shinfo(skb)->gso_segs;
atomic_add(segs_nr, &sk->sk_drops);
SNMP_ADD_STATS(__UDPX_MIB(sk, ipv4), UDP_MIB_INERRORS, segs_nr);
kfree_skb(skb);
return NULL;
}
consume_skb(skb);
return segs;
}
udp: fixup csum for GSO receive slow path When UDP packets generated locally by a socket with UDP_SEGMENT traverse the following path: UDP tunnel(xmit) -> veth (segmentation) -> veth (gro) -> UDP tunnel (rx) -> UDP socket (no UDP_GRO) ip_summed will be set to CHECKSUM_PARTIAL at creation time and such checksum mode will be preserved in the above path up to the UDP tunnel receive code where we have: __iptunnel_pull_header() -> skb_pull_rcsum() -> skb_postpull_rcsum() -> __skb_postpull_rcsum() The latter will convert the skb to CHECKSUM_NONE. The UDP GSO packet will be later segmented as part of the rx socket receive operation, and will present a CHECKSUM_NONE after segmentation. Additionally the segmented packets UDP CB still refers to the original GSO packet len. Overall that causes unexpected/wrong csum validation errors later in the UDP receive path. We could possibly address the issue with some additional checks and csum mangling in the UDP tunnel code. Since the issue affects only this UDP receive slow path, let's set a suitable csum status there. Note that SKB_GSO_UDP_L4 or SKB_GSO_FRAGLIST packets lacking an UDP encapsulation present a valid checksum when landing to udp_queue_rcv_skb(), as the UDP checksum has been validated by the GRO engine. v2 -> v3: - even more verbose commit message and comments v1 -> v2: - restrict the csum update to the packets strictly needing them - hopefully clarify the commit message and code comments Signed-off-by: Paolo Abeni <pabeni@redhat.com> Reviewed-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-03-30 13:28:49 +03:00
static inline void udp_post_segment_fix_csum(struct sk_buff *skb)
{
/* UDP-lite can't land here - no GRO */
WARN_ON_ONCE(UDP_SKB_CB(skb)->partial_cov);
/* UDP packets generated with UDP_SEGMENT and traversing:
*
* UDP tunnel(xmit) -> veth (segmentation) -> veth (gro) -> UDP tunnel (rx)
*
* can reach an UDP socket with CHECKSUM_NONE, because
* __iptunnel_pull_header() converts CHECKSUM_PARTIAL into NONE.
* SKB_GSO_UDP_L4 or SKB_GSO_FRAGLIST packets with no UDP tunnel will
* have a valid checksum, as the GRO engine validates the UDP csum
* before the aggregation and nobody strips such info in between.
* Instead of adding another check in the tunnel fastpath, we can force
* a valid csum after the segmentation.
* Additionally fixup the UDP CB.
*/
UDP_SKB_CB(skb)->cscov = skb->len;
if (skb->ip_summed == CHECKSUM_NONE && !skb->csum_valid)
skb->csum_valid = 1;
}
#ifdef CONFIG_BPF_SYSCALL
struct sk_psock;
struct proto *udp_bpf_get_proto(struct sock *sk, struct sk_psock *psock);
int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore);
#endif
#endif /* _UDP_H */