WSL2-Linux-Kernel/include/net/ip.h

793 строки
22 KiB
C
Исходник Постоянная ссылка Обычный вид История

/* 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 IP module.
*
* Version: @(#)ip.h 1.0.2 05/07/93
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Alan Cox, <gw4pts@gw4pts.ampr.org>
*
* Changes:
* Mike McLagan : Routing by source
*/
#ifndef _IP_H
#define _IP_H
#include <linux/types.h>
#include <linux/ip.h>
#include <linux/in.h>
#include <linux/skbuff.h>
#include <linux/jhash.h>
#include <linux/sockptr.h>
#include <net/inet_sock.h>
#include <net/route.h>
#include <net/snmp.h>
#include <net/flow.h>
#include <net/flow_dissector.h>
#include <net/netns/hash.h>
#include <net/lwtunnel.h>
#define IPV4_MAX_PMTU 65535U /* RFC 2675, Section 5.1 */
#define IPV4_MIN_MTU 68 /* RFC 791 */
ipv4: Allow amount of dirty memory from fib resizing to be controllable fib_trie implementation calls synchronize_rcu when a certain amount of pages are dirty from freed entries. The number of pages was determined experimentally in 2009 (commit c3059477fce2d). At the current setting, synchronize_rcu is called often -- 51 times in a second in one test with an average of an 8 msec delay adding a fib entry. The total impact is a lot of slow down modifying the fib. This is seen in the output of 'time' - the difference between real time and sys+user. For example, using 720,022 single path routes and 'ip -batch'[1]: $ time ./ip -batch ipv4/routes-1-hops real 0m14.214s user 0m2.513s sys 0m6.783s So roughly 35% of the actual time to install the routes is from the ip command getting scheduled out, most notably due to synchronize_rcu (this is observed using 'perf sched timehist'). This patch makes the amount of dirty memory configurable between 64k where the synchronize_rcu is called often (small, low end systems that are memory sensitive) to 64M where synchronize_rcu is called rarely during a large FIB change (for high end systems with lots of memory). The default is 512kB which corresponds to the current setting of 128 pages with a 4kB page size. As an example, at 16MB the worst interval shows 4 calls to synchronize_rcu in a second blocking for up to 30 msec in a single instance, and a total of almost 100 msec across the 4 calls in the second. The trade off is allowing FIB entries to consume more memory in a given time window but but with much better fib insertion rates (~30% increase in prefixes/sec). With this patch and net.ipv4.fib_sync_mem set to 16MB, the same batch file runs in: $ time ./ip -batch ipv4/routes-1-hops real 0m9.692s user 0m2.491s sys 0m6.769s So the dead time is reduced to about 1/2 second or <5% of the real time. [1] 'ip' modified to not request ACK messages which improves route insertion times by about 20% Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 19:18:59 +03:00
extern unsigned int sysctl_fib_sync_mem;
extern unsigned int sysctl_fib_sync_mem_min;
extern unsigned int sysctl_fib_sync_mem_max;
struct sock;
struct inet_skb_parm {
int iif;
struct ip_options opt; /* Compiled IP options */
net: Require exact match for TCP socket lookups if dif is l3mdev Currently, socket lookups for l3mdev (vrf) use cases can match a socket that is bound to a port but not a device (ie., a global socket). If the sysctl tcp_l3mdev_accept is not set this leads to ack packets going out based on the main table even though the packet came in from an L3 domain. The end result is that the connection does not establish creating confusion for users since the service is running and a socket shows in ss output. Fix by requiring an exact dif to sk_bound_dev_if match if the skb came through an interface enslaved to an l3mdev device and the tcp_l3mdev_accept is not set. skb's through an l3mdev interface are marked by setting a flag in inet{6}_skb_parm. The IPv6 variant is already set; this patch adds the flag for IPv4. Using an skb flag avoids a device lookup on the dif. The flag is set in the VRF driver using the IP{6}CB macros. For IPv4, the inet_skb_parm struct is moved in the cb per commit 971f10eca186, so the match function in the TCP stack needs to use TCP_SKB_CB. For IPv6, the move is done after the socket lookup, so IP6CB is used. The flags field in inet_skb_parm struct needs to be increased to add another flag. There is currently a 1-byte hole following the flags, so it can be expanded to u16 without increasing the size of the struct. Fixes: 193125dbd8eb ("net: Introduce VRF device driver") Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-17 06:02:52 +03:00
u16 flags;
#define IPSKB_FORWARDED BIT(0)
#define IPSKB_XFRM_TUNNEL_SIZE BIT(1)
#define IPSKB_XFRM_TRANSFORMED BIT(2)
#define IPSKB_FRAG_COMPLETE BIT(3)
#define IPSKB_REROUTED BIT(4)
#define IPSKB_DOREDIRECT BIT(5)
2015-05-22 17:32:51 +03:00
#define IPSKB_FRAG_PMTU BIT(6)
#define IPSKB_L3SLAVE BIT(7)
2022-05-13 23:34:02 +03:00
#define IPSKB_NOPOLICY BIT(8)
#define IPSKB_MULTIPATH BIT(9)
u16 frag_max_size;
};
net: Require exact match for TCP socket lookups if dif is l3mdev Currently, socket lookups for l3mdev (vrf) use cases can match a socket that is bound to a port but not a device (ie., a global socket). If the sysctl tcp_l3mdev_accept is not set this leads to ack packets going out based on the main table even though the packet came in from an L3 domain. The end result is that the connection does not establish creating confusion for users since the service is running and a socket shows in ss output. Fix by requiring an exact dif to sk_bound_dev_if match if the skb came through an interface enslaved to an l3mdev device and the tcp_l3mdev_accept is not set. skb's through an l3mdev interface are marked by setting a flag in inet{6}_skb_parm. The IPv6 variant is already set; this patch adds the flag for IPv4. Using an skb flag avoids a device lookup on the dif. The flag is set in the VRF driver using the IP{6}CB macros. For IPv4, the inet_skb_parm struct is moved in the cb per commit 971f10eca186, so the match function in the TCP stack needs to use TCP_SKB_CB. For IPv6, the move is done after the socket lookup, so IP6CB is used. The flags field in inet_skb_parm struct needs to be increased to add another flag. There is currently a 1-byte hole following the flags, so it can be expanded to u16 without increasing the size of the struct. Fixes: 193125dbd8eb ("net: Introduce VRF device driver") Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-17 06:02:52 +03:00
static inline bool ipv4_l3mdev_skb(u16 flags)
{
return !!(flags & IPSKB_L3SLAVE);
}
static inline unsigned int ip_hdrlen(const struct sk_buff *skb)
{
return ip_hdr(skb)->ihl * 4;
}
struct ipcm_cookie {
struct sockcm_cookie sockc;
__be32 addr;
int oif;
struct ip_options_rcu *opt;
__u8 protocol;
__u8 ttl;
__s16 tos;
char priority;
udp: generate gso with UDP_SEGMENT Support generic segmentation offload for udp datagrams. Callers can concatenate and send at once the payload of multiple datagrams with the same destination. To set segment size, the caller sets socket option UDP_SEGMENT to the length of each discrete payload. This value must be smaller than or equal to the relevant MTU. A follow-up patch adds cmsg UDP_SEGMENT to specify segment size on a per send call basis. Total byte length may then exceed MTU. If not an exact multiple of segment size, the last segment will be shorter. The implementation adds a gso_size field to the udp socket, ip(v6) cmsg cookie and inet_cork structure to be able to set the value at setsockopt or cmsg time and to work with both lockless and corked paths. Initial benchmark numbers show UDP GSO about as expensive as TCP GSO. tcp tso 3197 MB/s 54232 msg/s 54232 calls/s 6,457,754,262 cycles tcp gso 1765 MB/s 29939 msg/s 29939 calls/s 11,203,021,806 cycles tcp without tso/gso * 739 MB/s 12548 msg/s 12548 calls/s 11,205,483,630 cycles udp 876 MB/s 14873 msg/s 624666 calls/s 11,205,777,429 cycles udp gso 2139 MB/s 36282 msg/s 36282 calls/s 11,204,374,561 cycles [*] after reverting commit 0a6b2a1dc2a2 ("tcp: switch to GSO being always on") Measured total system cycles ('-a') for one core while pinning both the network receive path and benchmark process to that core: perf stat -a -C 12 -e cycles \ ./udpgso_bench_tx -C 12 -4 -D "$DST" -l 4 Note the reduction in calls/s with GSO. Bytes per syscall drops increases from 1470 to 61818. Signed-off-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-26 20:42:17 +03:00
__u16 gso_size;
};
static inline void ipcm_init(struct ipcm_cookie *ipcm)
{
*ipcm = (struct ipcm_cookie) { .tos = -1 };
}
static inline void ipcm_init_sk(struct ipcm_cookie *ipcm,
const struct inet_sock *inet)
{
ipcm_init(ipcm);
ipcm->sockc.mark = inet->sk.sk_mark;
ipcm->sockc.tsflags = inet->sk.sk_tsflags;
ipcm->oif = inet->sk.sk_bound_dev_if;
ipcm->addr = inet->inet_saddr;
ipcm->protocol = inet->inet_num;
}
#define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb))
#define PKTINFO_SKB_CB(skb) ((struct in_pktinfo *)((skb)->cb))
/* return enslaved device index if relevant */
static inline int inet_sdif(const struct sk_buff *skb)
{
#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
if (skb && ipv4_l3mdev_skb(IPCB(skb)->flags))
return IPCB(skb)->iif;
#endif
return 0;
}
/* Special input handler for packets caught by router alert option.
They are selected only by protocol field, and then processed likely
local ones; but only if someone wants them! Otherwise, router
not running rsvpd will kill RSVP.
It is user level problem, what it will make with them.
I have no idea, how it will masquearde or NAT them (it is joke, joke :-)),
but receiver should be enough clever f.e. to forward mtrace requests,
sent to multicast group to reach destination designated router.
*/
struct ip_ra_chain {
struct ip_ra_chain __rcu *next;
struct sock *sk;
union {
void (*destructor)(struct sock *);
struct sock *saved_sk;
};
struct rcu_head rcu;
};
/* IP flags. */
#define IP_CE 0x8000 /* Flag: "Congestion" */
#define IP_DF 0x4000 /* Flag: "Don't Fragment" */
#define IP_MF 0x2000 /* Flag: "More Fragments" */
#define IP_OFFSET 0x1FFF /* "Fragment Offset" part */
#define IP_FRAG_TIME (30 * HZ) /* fragment lifetime */
struct msghdr;
struct net_device;
struct packet_type;
struct rtable;
struct sockaddr;
int igmp_mc_init(void);
/*
* Functions provided by ip.c
*/
int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,
__be32 saddr, __be32 daddr,
struct ip_options_rcu *opt, u8 tos);
int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
struct net_device *orig_dev);
void ip_list_rcv(struct list_head *head, struct packet_type *pt,
struct net_device *orig_dev);
int ip_local_deliver(struct sk_buff *skb);
void ip_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int proto);
int ip_mr_input(struct sk_buff *skb);
int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb);
int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb);
int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
int (*output)(struct net *, struct sock *, struct sk_buff *));
struct ip_fraglist_iter {
struct sk_buff *frag;
struct iphdr *iph;
int offset;
unsigned int hlen;
};
void ip_fraglist_init(struct sk_buff *skb, struct iphdr *iph,
unsigned int hlen, struct ip_fraglist_iter *iter);
void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter);
static inline struct sk_buff *ip_fraglist_next(struct ip_fraglist_iter *iter)
{
struct sk_buff *skb = iter->frag;
iter->frag = skb->next;
skb_mark_not_on_list(skb);
return skb;
}
struct ip_frag_state {
bool DF;
unsigned int hlen;
unsigned int ll_rs;
unsigned int mtu;
unsigned int left;
int offset;
int ptr;
__be16 not_last_frag;
};
void ip_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int ll_rs,
unsigned int mtu, bool DF, struct ip_frag_state *state);
struct sk_buff *ip_frag_next(struct sk_buff *skb,
struct ip_frag_state *state);
void ip_send_check(struct iphdr *ip);
int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
__u8 tos);
void ip_init(void);
int ip_append_data(struct sock *sk, struct flowi4 *fl4,
int getfrag(void *from, char *to, int offset, int len,
int odd, struct sk_buff *skb),
void *from, int len, int protolen,
struct ipcm_cookie *ipc,
struct rtable **rt,
unsigned int flags);
int ip_generic_getfrag(void *from, char *to, int offset, int len, int odd,
struct sk_buff *skb);
ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
int offset, size_t size, int flags);
struct sk_buff *__ip_make_skb(struct sock *sk, struct flowi4 *fl4,
struct sk_buff_head *queue,
struct inet_cork *cork);
int ip_send_skb(struct net *net, struct sk_buff *skb);
int ip_push_pending_frames(struct sock *sk, struct flowi4 *fl4);
void ip_flush_pending_frames(struct sock *sk);
struct sk_buff *ip_make_skb(struct sock *sk, struct flowi4 *fl4,
int getfrag(void *from, char *to, int offset,
int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
struct ipcm_cookie *ipc, struct rtable **rtp,
struct inet_cork *cork, unsigned int flags);
int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl);
static inline struct sk_buff *ip_finish_skb(struct sock *sk, struct flowi4 *fl4)
{
return __ip_make_skb(sk, fl4, &sk->sk_write_queue, &inet_sk(sk)->cork.base);
}
static inline __u8 get_rttos(struct ipcm_cookie* ipc, struct inet_sock *inet)
{
return (ipc->tos != -1) ? RT_TOS(ipc->tos) : RT_TOS(inet->tos);
}
static inline __u8 get_rtconn_flags(struct ipcm_cookie* ipc, struct sock* sk)
{
return (ipc->tos != -1) ? RT_CONN_FLAGS_TOS(sk, ipc->tos) : RT_CONN_FLAGS(sk);
}
/* datagram.c */
int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
void ip4_datagram_release_cb(struct sock *sk);
struct ip_reply_arg {
struct kvec iov[1];
int flags;
__wsum csum;
int csumoffset; /* u16 offset of csum in iov[0].iov_base */
/* -1 if not needed */
int bound_dev_if;
u8 tos;
kuid_t uid;
};
#define IP_REPLY_ARG_NOSRCCHECK 1
static inline __u8 ip_reply_arg_flowi_flags(const struct ip_reply_arg *arg)
{
return (arg->flags & IP_REPLY_ARG_NOSRCCHECK) ? FLOWI_FLAG_ANYSRC : 0;
}
void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
const struct ip_options *sopt,
__be32 daddr, __be32 saddr,
const struct ip_reply_arg *arg,
unsigned int len, u64 transmit_time);
#define IP_INC_STATS(net, field) SNMP_INC_STATS64((net)->mib.ip_statistics, field)
#define __IP_INC_STATS(net, field) __SNMP_INC_STATS64((net)->mib.ip_statistics, field)
#define IP_ADD_STATS(net, field, val) SNMP_ADD_STATS64((net)->mib.ip_statistics, field, val)
#define __IP_ADD_STATS(net, field, val) __SNMP_ADD_STATS64((net)->mib.ip_statistics, field, val)
#define IP_UPD_PO_STATS(net, field, val) SNMP_UPD_PO_STATS64((net)->mib.ip_statistics, field, val)
#define __IP_UPD_PO_STATS(net, field, val) __SNMP_UPD_PO_STATS64((net)->mib.ip_statistics, field, val)
#define NET_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.net_statistics, field)
#define __NET_INC_STATS(net, field) __SNMP_INC_STATS((net)->mib.net_statistics, field)
#define NET_ADD_STATS(net, field, adnd) SNMP_ADD_STATS((net)->mib.net_statistics, field, adnd)
#define __NET_ADD_STATS(net, field, adnd) __SNMP_ADD_STATS((net)->mib.net_statistics, field, adnd)
u64 snmp_get_cpu_field(void __percpu *mib, int cpu, int offct);
unsigned long snmp_fold_field(void __percpu *mib, int offt);
#if BITS_PER_LONG==32
u64 snmp_get_cpu_field64(void __percpu *mib, int cpu, int offct,
size_t syncp_offset);
u64 snmp_fold_field64(void __percpu *mib, int offt, size_t sync_off);
#else
static inline u64 snmp_get_cpu_field64(void __percpu *mib, int cpu, int offct,
size_t syncp_offset)
{
return snmp_get_cpu_field(mib, cpu, offct);
}
static inline u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_off)
{
return snmp_fold_field(mib, offt);
}
#endif
#define snmp_get_cpu_field64_batch(buff64, stats_list, mib_statistic, offset) \
{ \
int i, c; \
for_each_possible_cpu(c) { \
for (i = 0; stats_list[i].name; i++) \
buff64[i] += snmp_get_cpu_field64( \
mib_statistic, \
c, stats_list[i].entry, \
offset); \
} \
}
#define snmp_get_cpu_field_batch(buff, stats_list, mib_statistic) \
{ \
int i, c; \
for_each_possible_cpu(c) { \
for (i = 0; stats_list[i].name; i++) \
buff[i] += snmp_get_cpu_field( \
mib_statistic, \
c, stats_list[i].entry); \
} \
}
void inet_get_local_port_range(struct net *net, int *low, int *high);
#ifdef CONFIG_SYSCTL
static inline bool inet_is_local_reserved_port(struct net *net, unsigned short port)
{
if (!net->ipv4.sysctl_local_reserved_ports)
return false;
return test_bit(port, net->ipv4.sysctl_local_reserved_ports);
}
static inline bool sysctl_dev_name_is_allowed(const char *name)
{
return strcmp(name, "default") != 0 && strcmp(name, "all") != 0;
}
static inline bool inet_port_requires_bind_service(struct net *net, unsigned short port)
{
return port < READ_ONCE(net->ipv4.sysctl_ip_prot_sock);
}
#else
static inline bool inet_is_local_reserved_port(struct net *net, unsigned short port)
{
return false;
}
static inline bool inet_port_requires_bind_service(struct net *net, unsigned short port)
{
return port < PROT_SOCK;
}
#endif
__be32 inet_current_timestamp(void);
/* From inetpeer.c */
extern int inet_peer_threshold;
extern int inet_peer_minttl;
extern int inet_peer_maxttl;
void ipfrag_init(void);
void ip_static_sysctl_init(void);
#define IP4_REPLY_MARK(net, mark) \
(READ_ONCE((net)->ipv4.sysctl_fwmark_reflect) ? (mark) : 0)
static inline bool ip_is_fragment(const struct iphdr *iph)
{
return (iph->frag_off & htons(IP_MF | IP_OFFSET)) != 0;
}
#ifdef CONFIG_INET
#include <net/dst.h>
/* The function in 2.2 was invalid, producing wrong result for
* check=0xFEFF. It was noticed by Arthur Skawina _year_ ago. --ANK(000625) */
static inline
int ip_decrease_ttl(struct iphdr *iph)
{
u32 check = (__force u32)iph->check;
check += (__force u32)htons(0x0100);
iph->check = (__force __sum16)(check + (check>=0xFFFF));
return --iph->ttl;
}
static inline int ip_mtu_locked(const struct dst_entry *dst)
{
const struct rtable *rt = (const struct rtable *)dst;
return rt->rt_mtu_locked || dst_metric_locked(dst, RTAX_MTU);
}
static inline
int ip_dont_fragment(const struct sock *sk, const struct dst_entry *dst)
{
u8 pmtudisc = READ_ONCE(inet_sk(sk)->pmtudisc);
return pmtudisc == IP_PMTUDISC_DO ||
(pmtudisc == IP_PMTUDISC_WANT &&
!ip_mtu_locked(dst));
}
ipv4: introduce ip_dst_mtu_maybe_forward and protect forwarding path against pmtu spoofing While forwarding we should not use the protocol path mtu to calculate the mtu for a forwarded packet but instead use the interface mtu. We mark forwarded skbs in ip_forward with IPSKB_FORWARDED, which was introduced for multicast forwarding. But as it does not conflict with our usage in unicast code path it is perfect for reuse. I moved the functions ip_sk_accept_pmtu, ip_sk_use_pmtu and ip_skb_dst_mtu along with the new ip_dst_mtu_maybe_forward to net/ip.h to fix circular dependencies because of IPSKB_FORWARDED. Because someone might have written a software which does probe destinations manually and expects the kernel to honour those path mtus I introduced a new per-namespace "ip_forward_use_pmtu" knob so someone can disable this new behaviour. We also still use mtus which are locked on a route for forwarding. The reason for this change is, that path mtus information can be injected into the kernel via e.g. icmp_err protocol handler without verification of local sockets. As such, this could cause the IPv4 forwarding path to wrongfully emit fragmentation needed notifications or start to fragment packets along a path. Tunnel and ipsec output paths clear IPCB again, thus IPSKB_FORWARDED won't be set and further fragmentation logic will use the path mtu to determine the fragmentation size. They also recheck packet size with help of path mtu discovery and report appropriate errors. Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: David Miller <davem@davemloft.net> Cc: John Heffner <johnwheffner@gmail.com> Cc: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-09 13:01:15 +04:00
static inline bool ip_sk_accept_pmtu(const struct sock *sk)
{
return inet_sk(sk)->pmtudisc != IP_PMTUDISC_INTERFACE &&
inet_sk(sk)->pmtudisc != IP_PMTUDISC_OMIT;
ipv4: introduce ip_dst_mtu_maybe_forward and protect forwarding path against pmtu spoofing While forwarding we should not use the protocol path mtu to calculate the mtu for a forwarded packet but instead use the interface mtu. We mark forwarded skbs in ip_forward with IPSKB_FORWARDED, which was introduced for multicast forwarding. But as it does not conflict with our usage in unicast code path it is perfect for reuse. I moved the functions ip_sk_accept_pmtu, ip_sk_use_pmtu and ip_skb_dst_mtu along with the new ip_dst_mtu_maybe_forward to net/ip.h to fix circular dependencies because of IPSKB_FORWARDED. Because someone might have written a software which does probe destinations manually and expects the kernel to honour those path mtus I introduced a new per-namespace "ip_forward_use_pmtu" knob so someone can disable this new behaviour. We also still use mtus which are locked on a route for forwarding. The reason for this change is, that path mtus information can be injected into the kernel via e.g. icmp_err protocol handler without verification of local sockets. As such, this could cause the IPv4 forwarding path to wrongfully emit fragmentation needed notifications or start to fragment packets along a path. Tunnel and ipsec output paths clear IPCB again, thus IPSKB_FORWARDED won't be set and further fragmentation logic will use the path mtu to determine the fragmentation size. They also recheck packet size with help of path mtu discovery and report appropriate errors. Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: David Miller <davem@davemloft.net> Cc: John Heffner <johnwheffner@gmail.com> Cc: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-09 13:01:15 +04:00
}
static inline bool ip_sk_use_pmtu(const struct sock *sk)
{
return inet_sk(sk)->pmtudisc < IP_PMTUDISC_PROBE;
}
static inline bool ip_sk_ignore_df(const struct sock *sk)
{
return inet_sk(sk)->pmtudisc < IP_PMTUDISC_DO ||
inet_sk(sk)->pmtudisc == IP_PMTUDISC_OMIT;
}
ipv4: introduce ip_dst_mtu_maybe_forward and protect forwarding path against pmtu spoofing While forwarding we should not use the protocol path mtu to calculate the mtu for a forwarded packet but instead use the interface mtu. We mark forwarded skbs in ip_forward with IPSKB_FORWARDED, which was introduced for multicast forwarding. But as it does not conflict with our usage in unicast code path it is perfect for reuse. I moved the functions ip_sk_accept_pmtu, ip_sk_use_pmtu and ip_skb_dst_mtu along with the new ip_dst_mtu_maybe_forward to net/ip.h to fix circular dependencies because of IPSKB_FORWARDED. Because someone might have written a software which does probe destinations manually and expects the kernel to honour those path mtus I introduced a new per-namespace "ip_forward_use_pmtu" knob so someone can disable this new behaviour. We also still use mtus which are locked on a route for forwarding. The reason for this change is, that path mtus information can be injected into the kernel via e.g. icmp_err protocol handler without verification of local sockets. As such, this could cause the IPv4 forwarding path to wrongfully emit fragmentation needed notifications or start to fragment packets along a path. Tunnel and ipsec output paths clear IPCB again, thus IPSKB_FORWARDED won't be set and further fragmentation logic will use the path mtu to determine the fragmentation size. They also recheck packet size with help of path mtu discovery and report appropriate errors. Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: David Miller <davem@davemloft.net> Cc: John Heffner <johnwheffner@gmail.com> Cc: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-09 13:01:15 +04:00
static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
bool forwarding)
{
const struct rtable *rt = container_of(dst, struct rtable, dst);
ipv4: introduce ip_dst_mtu_maybe_forward and protect forwarding path against pmtu spoofing While forwarding we should not use the protocol path mtu to calculate the mtu for a forwarded packet but instead use the interface mtu. We mark forwarded skbs in ip_forward with IPSKB_FORWARDED, which was introduced for multicast forwarding. But as it does not conflict with our usage in unicast code path it is perfect for reuse. I moved the functions ip_sk_accept_pmtu, ip_sk_use_pmtu and ip_skb_dst_mtu along with the new ip_dst_mtu_maybe_forward to net/ip.h to fix circular dependencies because of IPSKB_FORWARDED. Because someone might have written a software which does probe destinations manually and expects the kernel to honour those path mtus I introduced a new per-namespace "ip_forward_use_pmtu" knob so someone can disable this new behaviour. We also still use mtus which are locked on a route for forwarding. The reason for this change is, that path mtus information can be injected into the kernel via e.g. icmp_err protocol handler without verification of local sockets. As such, this could cause the IPv4 forwarding path to wrongfully emit fragmentation needed notifications or start to fragment packets along a path. Tunnel and ipsec output paths clear IPCB again, thus IPSKB_FORWARDED won't be set and further fragmentation logic will use the path mtu to determine the fragmentation size. They also recheck packet size with help of path mtu discovery and report appropriate errors. Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: David Miller <davem@davemloft.net> Cc: John Heffner <johnwheffner@gmail.com> Cc: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-09 13:01:15 +04:00
struct net *net = dev_net(dst->dev);
net/ipv4: always honour route mtu during forwarding Documentation/networking/ip-sysctl.txt:46 says: ip_forward_use_pmtu - BOOLEAN By default we don't trust protocol path MTUs while forwarding because they could be easily forged and can lead to unwanted fragmentation by the router. You only need to enable this if you have user-space software which tries to discover path mtus by itself and depends on the kernel honoring this information. This is normally not the case. Default: 0 (disabled) Possible values: 0 - disabled 1 - enabled Which makes it pretty clear that setting it to 1 is a potential security/safety/DoS issue, and yet it is entirely reasonable to want forwarded traffic to honour explicitly administrator configured route mtus (instead of defaulting to device mtu). Indeed, I can't think of a single reason why you wouldn't want to. Since you configured a route mtu you probably know better... It is pretty common to have a higher device mtu to allow receiving large (jumbo) frames, while having some routes via that interface (potentially including the default route to the internet) specify a lower mtu. Note that ipv6 forwarding uses device mtu unless the route is locked (in which case it will use the route mtu). This approach is not usable for IPv4 where an 'mtu lock' on a route also has the side effect of disabling TCP path mtu discovery via disabling the IPv4 DF (don't frag) bit on all outgoing frames. I'm not aware of a way to lock a route from an IPv6 RA, so that also potentially seems wrong. Signed-off-by: Maciej Żenczykowski <maze@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Willem de Bruijn <willemb@google.com> Cc: Lorenzo Colitti <lorenzo@google.com> Cc: Sunmeet Gill (Sunny) <sgill@quicinc.com> Cc: Vinay Paradkar <vparadka@qti.qualcomm.com> Cc: Tyler Wear <twear@quicinc.com> Cc: David Ahern <dsahern@kernel.org> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-09-23 23:18:15 +03:00
unsigned int mtu;
ipv4: introduce ip_dst_mtu_maybe_forward and protect forwarding path against pmtu spoofing While forwarding we should not use the protocol path mtu to calculate the mtu for a forwarded packet but instead use the interface mtu. We mark forwarded skbs in ip_forward with IPSKB_FORWARDED, which was introduced for multicast forwarding. But as it does not conflict with our usage in unicast code path it is perfect for reuse. I moved the functions ip_sk_accept_pmtu, ip_sk_use_pmtu and ip_skb_dst_mtu along with the new ip_dst_mtu_maybe_forward to net/ip.h to fix circular dependencies because of IPSKB_FORWARDED. Because someone might have written a software which does probe destinations manually and expects the kernel to honour those path mtus I introduced a new per-namespace "ip_forward_use_pmtu" knob so someone can disable this new behaviour. We also still use mtus which are locked on a route for forwarding. The reason for this change is, that path mtus information can be injected into the kernel via e.g. icmp_err protocol handler without verification of local sockets. As such, this could cause the IPv4 forwarding path to wrongfully emit fragmentation needed notifications or start to fragment packets along a path. Tunnel and ipsec output paths clear IPCB again, thus IPSKB_FORWARDED won't be set and further fragmentation logic will use the path mtu to determine the fragmentation size. They also recheck packet size with help of path mtu discovery and report appropriate errors. Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: David Miller <davem@davemloft.net> Cc: John Heffner <johnwheffner@gmail.com> Cc: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-09 13:01:15 +04:00
if (READ_ONCE(net->ipv4.sysctl_ip_fwd_use_pmtu) ||
ip_mtu_locked(dst) ||
!forwarding) {
mtu = rt->rt_pmtu;
if (mtu && time_before(jiffies, rt->dst.expires))
goto out;
}
ipv4: introduce ip_dst_mtu_maybe_forward and protect forwarding path against pmtu spoofing While forwarding we should not use the protocol path mtu to calculate the mtu for a forwarded packet but instead use the interface mtu. We mark forwarded skbs in ip_forward with IPSKB_FORWARDED, which was introduced for multicast forwarding. But as it does not conflict with our usage in unicast code path it is perfect for reuse. I moved the functions ip_sk_accept_pmtu, ip_sk_use_pmtu and ip_skb_dst_mtu along with the new ip_dst_mtu_maybe_forward to net/ip.h to fix circular dependencies because of IPSKB_FORWARDED. Because someone might have written a software which does probe destinations manually and expects the kernel to honour those path mtus I introduced a new per-namespace "ip_forward_use_pmtu" knob so someone can disable this new behaviour. We also still use mtus which are locked on a route for forwarding. The reason for this change is, that path mtus information can be injected into the kernel via e.g. icmp_err protocol handler without verification of local sockets. As such, this could cause the IPv4 forwarding path to wrongfully emit fragmentation needed notifications or start to fragment packets along a path. Tunnel and ipsec output paths clear IPCB again, thus IPSKB_FORWARDED won't be set and further fragmentation logic will use the path mtu to determine the fragmentation size. They also recheck packet size with help of path mtu discovery and report appropriate errors. Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: David Miller <davem@davemloft.net> Cc: John Heffner <johnwheffner@gmail.com> Cc: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-09 13:01:15 +04:00
net/ipv4: always honour route mtu during forwarding Documentation/networking/ip-sysctl.txt:46 says: ip_forward_use_pmtu - BOOLEAN By default we don't trust protocol path MTUs while forwarding because they could be easily forged and can lead to unwanted fragmentation by the router. You only need to enable this if you have user-space software which tries to discover path mtus by itself and depends on the kernel honoring this information. This is normally not the case. Default: 0 (disabled) Possible values: 0 - disabled 1 - enabled Which makes it pretty clear that setting it to 1 is a potential security/safety/DoS issue, and yet it is entirely reasonable to want forwarded traffic to honour explicitly administrator configured route mtus (instead of defaulting to device mtu). Indeed, I can't think of a single reason why you wouldn't want to. Since you configured a route mtu you probably know better... It is pretty common to have a higher device mtu to allow receiving large (jumbo) frames, while having some routes via that interface (potentially including the default route to the internet) specify a lower mtu. Note that ipv6 forwarding uses device mtu unless the route is locked (in which case it will use the route mtu). This approach is not usable for IPv4 where an 'mtu lock' on a route also has the side effect of disabling TCP path mtu discovery via disabling the IPv4 DF (don't frag) bit on all outgoing frames. I'm not aware of a way to lock a route from an IPv6 RA, so that also potentially seems wrong. Signed-off-by: Maciej Żenczykowski <maze@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Willem de Bruijn <willemb@google.com> Cc: Lorenzo Colitti <lorenzo@google.com> Cc: Sunmeet Gill (Sunny) <sgill@quicinc.com> Cc: Vinay Paradkar <vparadka@qti.qualcomm.com> Cc: Tyler Wear <twear@quicinc.com> Cc: David Ahern <dsahern@kernel.org> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-09-23 23:18:15 +03:00
/* 'forwarding = true' case should always honour route mtu */
mtu = dst_metric_raw(dst, RTAX_MTU);
if (mtu)
goto out;
mtu = READ_ONCE(dst->dev->mtu);
if (unlikely(ip_mtu_locked(dst))) {
if (rt->rt_uses_gateway && mtu > 576)
mtu = 576;
}
out:
mtu = min_t(unsigned int, mtu, IP_MAX_MTU);
net/ipv4: always honour route mtu during forwarding Documentation/networking/ip-sysctl.txt:46 says: ip_forward_use_pmtu - BOOLEAN By default we don't trust protocol path MTUs while forwarding because they could be easily forged and can lead to unwanted fragmentation by the router. You only need to enable this if you have user-space software which tries to discover path mtus by itself and depends on the kernel honoring this information. This is normally not the case. Default: 0 (disabled) Possible values: 0 - disabled 1 - enabled Which makes it pretty clear that setting it to 1 is a potential security/safety/DoS issue, and yet it is entirely reasonable to want forwarded traffic to honour explicitly administrator configured route mtus (instead of defaulting to device mtu). Indeed, I can't think of a single reason why you wouldn't want to. Since you configured a route mtu you probably know better... It is pretty common to have a higher device mtu to allow receiving large (jumbo) frames, while having some routes via that interface (potentially including the default route to the internet) specify a lower mtu. Note that ipv6 forwarding uses device mtu unless the route is locked (in which case it will use the route mtu). This approach is not usable for IPv4 where an 'mtu lock' on a route also has the side effect of disabling TCP path mtu discovery via disabling the IPv4 DF (don't frag) bit on all outgoing frames. I'm not aware of a way to lock a route from an IPv6 RA, so that also potentially seems wrong. Signed-off-by: Maciej Żenczykowski <maze@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Willem de Bruijn <willemb@google.com> Cc: Lorenzo Colitti <lorenzo@google.com> Cc: Sunmeet Gill (Sunny) <sgill@quicinc.com> Cc: Vinay Paradkar <vparadka@qti.qualcomm.com> Cc: Tyler Wear <twear@quicinc.com> Cc: David Ahern <dsahern@kernel.org> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-09-23 23:18:15 +03:00
return mtu - lwtunnel_headroom(dst->lwtstate, mtu);
ipv4: introduce ip_dst_mtu_maybe_forward and protect forwarding path against pmtu spoofing While forwarding we should not use the protocol path mtu to calculate the mtu for a forwarded packet but instead use the interface mtu. We mark forwarded skbs in ip_forward with IPSKB_FORWARDED, which was introduced for multicast forwarding. But as it does not conflict with our usage in unicast code path it is perfect for reuse. I moved the functions ip_sk_accept_pmtu, ip_sk_use_pmtu and ip_skb_dst_mtu along with the new ip_dst_mtu_maybe_forward to net/ip.h to fix circular dependencies because of IPSKB_FORWARDED. Because someone might have written a software which does probe destinations manually and expects the kernel to honour those path mtus I introduced a new per-namespace "ip_forward_use_pmtu" knob so someone can disable this new behaviour. We also still use mtus which are locked on a route for forwarding. The reason for this change is, that path mtus information can be injected into the kernel via e.g. icmp_err protocol handler without verification of local sockets. As such, this could cause the IPv4 forwarding path to wrongfully emit fragmentation needed notifications or start to fragment packets along a path. Tunnel and ipsec output paths clear IPCB again, thus IPSKB_FORWARDED won't be set and further fragmentation logic will use the path mtu to determine the fragmentation size. They also recheck packet size with help of path mtu discovery and report appropriate errors. Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: David Miller <davem@davemloft.net> Cc: John Heffner <johnwheffner@gmail.com> Cc: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-09 13:01:15 +04:00
}
static inline unsigned int ip_skb_dst_mtu(struct sock *sk,
const struct sk_buff *skb)
ipv4: introduce ip_dst_mtu_maybe_forward and protect forwarding path against pmtu spoofing While forwarding we should not use the protocol path mtu to calculate the mtu for a forwarded packet but instead use the interface mtu. We mark forwarded skbs in ip_forward with IPSKB_FORWARDED, which was introduced for multicast forwarding. But as it does not conflict with our usage in unicast code path it is perfect for reuse. I moved the functions ip_sk_accept_pmtu, ip_sk_use_pmtu and ip_skb_dst_mtu along with the new ip_dst_mtu_maybe_forward to net/ip.h to fix circular dependencies because of IPSKB_FORWARDED. Because someone might have written a software which does probe destinations manually and expects the kernel to honour those path mtus I introduced a new per-namespace "ip_forward_use_pmtu" knob so someone can disable this new behaviour. We also still use mtus which are locked on a route for forwarding. The reason for this change is, that path mtus information can be injected into the kernel via e.g. icmp_err protocol handler without verification of local sockets. As such, this could cause the IPv4 forwarding path to wrongfully emit fragmentation needed notifications or start to fragment packets along a path. Tunnel and ipsec output paths clear IPCB again, thus IPSKB_FORWARDED won't be set and further fragmentation logic will use the path mtu to determine the fragmentation size. They also recheck packet size with help of path mtu discovery and report appropriate errors. Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: David Miller <davem@davemloft.net> Cc: John Heffner <johnwheffner@gmail.com> Cc: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-09 13:01:15 +04:00
{
unsigned int mtu;
if (!sk || !sk_fullsock(sk) || ip_sk_use_pmtu(sk)) {
ipv4: introduce ip_dst_mtu_maybe_forward and protect forwarding path against pmtu spoofing While forwarding we should not use the protocol path mtu to calculate the mtu for a forwarded packet but instead use the interface mtu. We mark forwarded skbs in ip_forward with IPSKB_FORWARDED, which was introduced for multicast forwarding. But as it does not conflict with our usage in unicast code path it is perfect for reuse. I moved the functions ip_sk_accept_pmtu, ip_sk_use_pmtu and ip_skb_dst_mtu along with the new ip_dst_mtu_maybe_forward to net/ip.h to fix circular dependencies because of IPSKB_FORWARDED. Because someone might have written a software which does probe destinations manually and expects the kernel to honour those path mtus I introduced a new per-namespace "ip_forward_use_pmtu" knob so someone can disable this new behaviour. We also still use mtus which are locked on a route for forwarding. The reason for this change is, that path mtus information can be injected into the kernel via e.g. icmp_err protocol handler without verification of local sockets. As such, this could cause the IPv4 forwarding path to wrongfully emit fragmentation needed notifications or start to fragment packets along a path. Tunnel and ipsec output paths clear IPCB again, thus IPSKB_FORWARDED won't be set and further fragmentation logic will use the path mtu to determine the fragmentation size. They also recheck packet size with help of path mtu discovery and report appropriate errors. Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: David Miller <davem@davemloft.net> Cc: John Heffner <johnwheffner@gmail.com> Cc: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-09 13:01:15 +04:00
bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED;
ipv4: introduce ip_dst_mtu_maybe_forward and protect forwarding path against pmtu spoofing While forwarding we should not use the protocol path mtu to calculate the mtu for a forwarded packet but instead use the interface mtu. We mark forwarded skbs in ip_forward with IPSKB_FORWARDED, which was introduced for multicast forwarding. But as it does not conflict with our usage in unicast code path it is perfect for reuse. I moved the functions ip_sk_accept_pmtu, ip_sk_use_pmtu and ip_skb_dst_mtu along with the new ip_dst_mtu_maybe_forward to net/ip.h to fix circular dependencies because of IPSKB_FORWARDED. Because someone might have written a software which does probe destinations manually and expects the kernel to honour those path mtus I introduced a new per-namespace "ip_forward_use_pmtu" knob so someone can disable this new behaviour. We also still use mtus which are locked on a route for forwarding. The reason for this change is, that path mtus information can be injected into the kernel via e.g. icmp_err protocol handler without verification of local sockets. As such, this could cause the IPv4 forwarding path to wrongfully emit fragmentation needed notifications or start to fragment packets along a path. Tunnel and ipsec output paths clear IPCB again, thus IPSKB_FORWARDED won't be set and further fragmentation logic will use the path mtu to determine the fragmentation size. They also recheck packet size with help of path mtu discovery and report appropriate errors. Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: David Miller <davem@davemloft.net> Cc: John Heffner <johnwheffner@gmail.com> Cc: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-09 13:01:15 +04:00
return ip_dst_mtu_maybe_forward(skb_dst(skb), forwarding);
}
mtu = min(READ_ONCE(skb_dst(skb)->dev->mtu), IP_MAX_MTU);
return mtu - lwtunnel_headroom(skb_dst(skb)->lwtstate, mtu);
ipv4: introduce ip_dst_mtu_maybe_forward and protect forwarding path against pmtu spoofing While forwarding we should not use the protocol path mtu to calculate the mtu for a forwarded packet but instead use the interface mtu. We mark forwarded skbs in ip_forward with IPSKB_FORWARDED, which was introduced for multicast forwarding. But as it does not conflict with our usage in unicast code path it is perfect for reuse. I moved the functions ip_sk_accept_pmtu, ip_sk_use_pmtu and ip_skb_dst_mtu along with the new ip_dst_mtu_maybe_forward to net/ip.h to fix circular dependencies because of IPSKB_FORWARDED. Because someone might have written a software which does probe destinations manually and expects the kernel to honour those path mtus I introduced a new per-namespace "ip_forward_use_pmtu" knob so someone can disable this new behaviour. We also still use mtus which are locked on a route for forwarding. The reason for this change is, that path mtus information can be injected into the kernel via e.g. icmp_err protocol handler without verification of local sockets. As such, this could cause the IPv4 forwarding path to wrongfully emit fragmentation needed notifications or start to fragment packets along a path. Tunnel and ipsec output paths clear IPCB again, thus IPSKB_FORWARDED won't be set and further fragmentation logic will use the path mtu to determine the fragmentation size. They also recheck packet size with help of path mtu discovery and report appropriate errors. Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: David Miller <davem@davemloft.net> Cc: John Heffner <johnwheffner@gmail.com> Cc: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-09 13:01:15 +04:00
}
struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx,
int fc_mx_len,
struct netlink_ext_ack *extack);
static inline void ip_fib_metrics_put(struct dst_metrics *fib_metrics)
{
if (fib_metrics != &dst_default_metrics &&
refcount_dec_and_test(&fib_metrics->refcnt))
kfree(fib_metrics);
}
/* ipv4 and ipv6 both use refcounted metrics if it is not the default */
static inline
void ip_dst_init_metrics(struct dst_entry *dst, struct dst_metrics *fib_metrics)
{
dst_init_metrics(dst, fib_metrics->metrics, true);
if (fib_metrics != &dst_default_metrics) {
dst->_metrics |= DST_METRICS_REFCOUNTED;
refcount_inc(&fib_metrics->refcnt);
}
}
static inline
void ip_dst_metrics_put(struct dst_entry *dst)
{
struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst);
if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt))
kfree(p);
}
ip: make IP identifiers less predictable In "Counting Packets Sent Between Arbitrary Internet Hosts", Jeffrey and Jedidiah describe ways exploiting linux IP identifier generation to infer whether two machines are exchanging packets. With commit 73f156a6e8c1 ("inetpeer: get rid of ip_id_count"), we changed IP id generation, but this does not really prevent this side-channel technique. This patch adds a random amount of perturbation so that IP identifiers for a given destination [1] are no longer monotonically increasing after an idle period. Note that prandom_u32_max(1) returns 0, so if generator is used at most once per jiffy, this patch inserts no hole in the ID suite and do not increase collision probability. This is jiffies based, so in the worst case (HZ=1000), the id can rollover after ~65 seconds of idle time, which should be fine. We also change the hash used in __ip_select_ident() to not only hash on daddr, but also saddr and protocol, so that ICMP probes can not be used to infer information for other protocols. For IPv6, adds saddr into the hash as well, but not nexthdr. If I ping the patched target, we can see ID are now hard to predict. 21:57:11.008086 IP (...) A > target: ICMP echo request, seq 1, length 64 21:57:11.010752 IP (... id 2081 ...) target > A: ICMP echo reply, seq 1, length 64 21:57:12.013133 IP (...) A > target: ICMP echo request, seq 2, length 64 21:57:12.015737 IP (... id 3039 ...) target > A: ICMP echo reply, seq 2, length 64 21:57:13.016580 IP (...) A > target: ICMP echo request, seq 3, length 64 21:57:13.019251 IP (... id 3437 ...) target > A: ICMP echo reply, seq 3, length 64 [1] TCP sessions uses a per flow ID generator not changed by this patch. Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Jeffrey Knockel <jeffk@cs.unm.edu> Reported-by: Jedidiah R. Crandall <crandall@cs.unm.edu> Cc: Willy Tarreau <w@1wt.eu> Cc: Hannes Frederic Sowa <hannes@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-26 10:58:10 +04:00
u32 ip_idents_reserve(u32 hash, int segs);
void __ip_select_ident(struct net *net, struct iphdr *iph, int segs);
static inline void ip_select_ident_segs(struct net *net, struct sk_buff *skb,
struct sock *sk, int segs)
{
struct iphdr *iph = ip_hdr(skb);
/* We had many attacks based on IPID, use the private
* generator as much as we can.
*/
if (sk && inet_sk(sk)->inet_daddr) {
iph->id = htons(inet_sk(sk)->inet_id);
inet_sk(sk)->inet_id += segs;
return;
}
if ((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) {
iph->id = 0;
} else {
/* Unfortunately we need the big hammer to get a suitable IPID */
__ip_select_ident(net, iph, segs);
}
}
static inline void ip_select_ident(struct net *net, struct sk_buff *skb,
struct sock *sk)
{
ip_select_ident_segs(net, skb, sk, 1);
}
static inline __wsum inet_compute_pseudo(struct sk_buff *skb, int proto)
{
return csum_tcpudp_nofold(ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
skb->len, proto, 0);
}
/* copy IPv4 saddr & daddr to flow_keys, possibly using 64bit load/store
* Equivalent to : flow->v4addrs.src = iph->saddr;
* flow->v4addrs.dst = iph->daddr;
*/
static inline void iph_to_flow_copy_v4addrs(struct flow_keys *flow,
const struct iphdr *iph)
{
BUILD_BUG_ON(offsetof(typeof(flow->addrs), v4addrs.dst) !=
offsetof(typeof(flow->addrs), v4addrs.src) +
sizeof(flow->addrs.v4addrs.src));
net: use struct_group to copy ip/ipv6 header addresses [ Upstream commit 58e0be1ef6118c5352b56a4d06e974c5599993a5 ] kernel test robot reported warnings when build bonding module with make W=1 O=build_dir ARCH=x86_64 SHELL=/bin/bash drivers/net/bonding/: from ../drivers/net/bonding/bond_main.c:35: In function ‘fortify_memcpy_chk’, inlined from ‘iph_to_flow_copy_v4addrs’ at ../include/net/ip.h:566:2, inlined from ‘bond_flow_ip’ at ../drivers/net/bonding/bond_main.c:3984:3: ../include/linux/fortify-string.h:413:25: warning: call to ‘__read_overflow2_field’ declared with attribute warning: detected read beyond size of f ield (2nd parameter); maybe use struct_group()? [-Wattribute-warning] 413 | __read_overflow2_field(q_size_field, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ In function ‘fortify_memcpy_chk’, inlined from ‘iph_to_flow_copy_v6addrs’ at ../include/net/ipv6.h:900:2, inlined from ‘bond_flow_ip’ at ../drivers/net/bonding/bond_main.c:3994:3: ../include/linux/fortify-string.h:413:25: warning: call to ‘__read_overflow2_field’ declared with attribute warning: detected read beyond size of f ield (2nd parameter); maybe use struct_group()? [-Wattribute-warning] 413 | __read_overflow2_field(q_size_field, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ This is because we try to copy the whole ip/ip6 address to the flow_key, while we only point the to ip/ip6 saddr. Note that since these are UAPI headers, __struct_group() is used to avoid the compiler warnings. Reported-by: kernel test robot <lkp@intel.com> Fixes: c3f8324188fa ("net: Add full IPv6 addresses to flow_keys") Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Link: https://lore.kernel.org/r/20221115142400.1204786-1-liuhangbin@gmail.com Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2022-11-15 17:24:00 +03:00
memcpy(&flow->addrs.v4addrs, &iph->addrs, sizeof(flow->addrs.v4addrs));
flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
}
static inline __wsum inet_gro_compute_pseudo(struct sk_buff *skb, int proto)
{
const struct iphdr *iph = skb_gro_network_header(skb);
return csum_tcpudp_nofold(iph->saddr, iph->daddr,
skb_gro_len(skb), proto, 0);
}
/*
* Map a multicast IP onto multicast MAC for type ethernet.
*/
static inline void ip_eth_mc_map(__be32 naddr, char *buf)
{
__u32 addr=ntohl(naddr);
buf[0]=0x01;
buf[1]=0x00;
buf[2]=0x5e;
buf[5]=addr&0xFF;
addr>>=8;
buf[4]=addr&0xFF;
addr>>=8;
buf[3]=addr&0x7F;
}
/*
* Map a multicast IP onto multicast MAC for type IP-over-InfiniBand.
* Leave P_Key as 0 to be filled in by driver.
*/
static inline void ip_ib_mc_map(__be32 naddr, const unsigned char *broadcast, char *buf)
{
__u32 addr;
unsigned char scope = broadcast[5] & 0xF;
buf[0] = 0; /* Reserved */
buf[1] = 0xff; /* Multicast QPN */
buf[2] = 0xff;
buf[3] = 0xff;
addr = ntohl(naddr);
buf[4] = 0xff;
buf[5] = 0x10 | scope; /* scope from broadcast address */
buf[6] = 0x40; /* IPv4 signature */
buf[7] = 0x1b;
buf[8] = broadcast[8]; /* P_Key */
buf[9] = broadcast[9];
buf[10] = 0;
buf[11] = 0;
buf[12] = 0;
buf[13] = 0;
buf[14] = 0;
buf[15] = 0;
buf[19] = addr & 0xff;
addr >>= 8;
buf[18] = addr & 0xff;
addr >>= 8;
buf[17] = addr & 0xff;
addr >>= 8;
buf[16] = addr & 0x0f;
}
static inline void ip_ipgre_mc_map(__be32 naddr, const unsigned char *broadcast, char *buf)
{
if ((broadcast[0] | broadcast[1] | broadcast[2] | broadcast[3]) != 0)
memcpy(buf, broadcast, 4);
else
memcpy(buf, &naddr, sizeof(naddr));
}
#if IS_ENABLED(CONFIG_IPV6)
#include <linux/ipv6.h>
#endif
static __inline__ void inet_reset_saddr(struct sock *sk)
{
inet_sk(sk)->inet_rcv_saddr = inet_sk(sk)->inet_saddr = 0;
#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family == PF_INET6) {
struct ipv6_pinfo *np = inet6_sk(sk);
memset(&np->saddr, 0, sizeof(np->saddr));
memset(&sk->sk_v6_rcv_saddr, 0, sizeof(sk->sk_v6_rcv_saddr));
}
#endif
}
#endif
static inline unsigned int ipv4_addr_hash(__be32 ip)
{
return (__force unsigned int) ip;
}
static inline u32 ipv4_portaddr_hash(const struct net *net,
__be32 saddr,
unsigned int port)
{
return jhash_1word((__force u32)saddr, net_hash_mix(net)) ^ port;
}
bool ip_call_ra_chain(struct sk_buff *skb);
/*
* Functions provided by ip_fragment.c
*/
enum ip_defrag_users {
IP_DEFRAG_LOCAL_DELIVER,
IP_DEFRAG_CALL_RA_CHAIN,
IP_DEFRAG_CONNTRACK_IN,
__IP_DEFRAG_CONNTRACK_IN_END = IP_DEFRAG_CONNTRACK_IN + USHRT_MAX,
IP_DEFRAG_CONNTRACK_OUT,
__IP_DEFRAG_CONNTRACK_OUT_END = IP_DEFRAG_CONNTRACK_OUT + USHRT_MAX,
IP_DEFRAG_CONNTRACK_BRIDGE_IN,
__IP_DEFRAG_CONNTRACK_BRIDGE_IN = IP_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX,
IP_DEFRAG_VS_IN,
IP_DEFRAG_VS_OUT,
IP_DEFRAG_VS_FWD,
IP_DEFRAG_AF_PACKET,
IP_DEFRAG_MACVLAN,
};
/* Return true if the value of 'user' is between 'lower_bond'
* and 'upper_bond' inclusively.
*/
static inline bool ip_defrag_user_in_between(u32 user,
enum ip_defrag_users lower_bond,
enum ip_defrag_users upper_bond)
{
return user >= lower_bond && user <= upper_bond;
}
int ip_defrag(struct net *net, struct sk_buff *skb, u32 user);
#ifdef CONFIG_INET
struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user);
#else
static inline struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
{
return skb;
}
#endif
/*
* Functions provided by ip_forward.c
*/
int ip_forward(struct sk_buff *skb);
/*
* Functions provided by ip_options.c
*/
void ip_options_build(struct sk_buff *skb, struct ip_options *opt,
__be32 daddr, struct rtable *rt, int is_frag);
int __ip_options_echo(struct net *net, struct ip_options *dopt,
struct sk_buff *skb, const struct ip_options *sopt);
static inline int ip_options_echo(struct net *net, struct ip_options *dopt,
struct sk_buff *skb)
{
return __ip_options_echo(net, dopt, skb, &IPCB(skb)->opt);
}
void ip_options_fragment(struct sk_buff *skb);
int __ip_options_compile(struct net *net, struct ip_options *opt,
struct sk_buff *skb, __be32 *info);
int ip_options_compile(struct net *net, struct ip_options *opt,
struct sk_buff *skb);
int ip_options_get(struct net *net, struct ip_options_rcu **optp,
sockptr_t data, int optlen);
void ip_options_undo(struct ip_options *opt);
void ip_forward_options(struct sk_buff *skb);
int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev);
/*
* Functions provided by ip_sockglue.c
*/
void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb);
void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk,
struct sk_buff *skb, int tlen, int offset);
int ip_cmsg_send(struct sock *sk, struct msghdr *msg,
struct ipcm_cookie *ipc, bool allow_ipv6);
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,
int __user *optlen);
int ip_ra_control(struct sock *sk, unsigned char on,
void (*destructor)(struct sock *));
int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len);
void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port,
u32 info, u8 *payload);
void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport,
u32 info);
static inline void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb)
{
ip_cmsg_recv_offset(msg, skb->sk, skb, 0, 0);
}
bool icmp_global_allow(void);
extern int sysctl_icmp_msgs_per_sec;
extern int sysctl_icmp_msgs_burst;
#ifdef CONFIG_PROC_FS
int ip_misc_proc_init(void);
#endif
int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, u8 family,
struct netlink_ext_ack *extack);
inet: protect against too small mtu values. syzbot was once again able to crash a host by setting a very small mtu on loopback device. Let's make inetdev_valid_mtu() available in include/net/ip.h, and use it in ip_setup_cork(), so that we protect both ip_append_page() and __ip_append_data() Also add a READ_ONCE() when the device mtu is read. Pairs this lockless read with one WRITE_ONCE() in __dev_set_mtu(), even if other code paths might write over this field. Add a big comment in include/linux/netdevice.h about dev->mtu needing READ_ONCE()/WRITE_ONCE() annotations. Hopefully we will add the missing ones in followup patches. [1] refcount_t: saturated; leaking memory. WARNING: CPU: 0 PID: 9464 at lib/refcount.c:22 refcount_warn_saturate+0x138/0x1f0 lib/refcount.c:22 Kernel panic - not syncing: panic_on_warn set ... CPU: 0 PID: 9464 Comm: syz-executor850 Not tainted 5.4.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x197/0x210 lib/dump_stack.c:118 panic+0x2e3/0x75c kernel/panic.c:221 __warn.cold+0x2f/0x3e kernel/panic.c:582 report_bug+0x289/0x300 lib/bug.c:195 fixup_bug arch/x86/kernel/traps.c:174 [inline] fixup_bug arch/x86/kernel/traps.c:169 [inline] do_error_trap+0x11b/0x200 arch/x86/kernel/traps.c:267 do_invalid_op+0x37/0x50 arch/x86/kernel/traps.c:286 invalid_op+0x23/0x30 arch/x86/entry/entry_64.S:1027 RIP: 0010:refcount_warn_saturate+0x138/0x1f0 lib/refcount.c:22 Code: 06 31 ff 89 de e8 c8 f5 e6 fd 84 db 0f 85 6f ff ff ff e8 7b f4 e6 fd 48 c7 c7 e0 71 4f 88 c6 05 56 a6 a4 06 01 e8 c7 a8 b7 fd <0f> 0b e9 50 ff ff ff e8 5c f4 e6 fd 0f b6 1d 3d a6 a4 06 31 ff 89 RSP: 0018:ffff88809689f550 EFLAGS: 00010286 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffffff815e4336 RDI: ffffed1012d13e9c RBP: ffff88809689f560 R08: ffff88809c50a3c0 R09: fffffbfff15d31b1 R10: fffffbfff15d31b0 R11: ffffffff8ae98d87 R12: 0000000000000001 R13: 0000000000040100 R14: ffff888099041104 R15: ffff888218d96e40 refcount_add include/linux/refcount.h:193 [inline] skb_set_owner_w+0x2b6/0x410 net/core/sock.c:1999 sock_wmalloc+0xf1/0x120 net/core/sock.c:2096 ip_append_page+0x7ef/0x1190 net/ipv4/ip_output.c:1383 udp_sendpage+0x1c7/0x480 net/ipv4/udp.c:1276 inet_sendpage+0xdb/0x150 net/ipv4/af_inet.c:821 kernel_sendpage+0x92/0xf0 net/socket.c:3794 sock_sendpage+0x8b/0xc0 net/socket.c:936 pipe_to_sendpage+0x2da/0x3c0 fs/splice.c:458 splice_from_pipe_feed fs/splice.c:512 [inline] __splice_from_pipe+0x3ee/0x7c0 fs/splice.c:636 splice_from_pipe+0x108/0x170 fs/splice.c:671 generic_splice_sendpage+0x3c/0x50 fs/splice.c:842 do_splice_from fs/splice.c:861 [inline] direct_splice_actor+0x123/0x190 fs/splice.c:1035 splice_direct_to_actor+0x3b4/0xa30 fs/splice.c:990 do_splice_direct+0x1da/0x2a0 fs/splice.c:1078 do_sendfile+0x597/0xd00 fs/read_write.c:1464 __do_sys_sendfile64 fs/read_write.c:1525 [inline] __se_sys_sendfile64 fs/read_write.c:1511 [inline] __x64_sys_sendfile64+0x1dd/0x220 fs/read_write.c:1511 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x441409 Code: e8 ac e8 ff ff 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 eb 08 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fffb64c4f78 EFLAGS: 00000246 ORIG_RAX: 0000000000000028 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 0000000000441409 RDX: 0000000000000000 RSI: 0000000000000006 RDI: 0000000000000005 RBP: 0000000000073b8a R08: 0000000000000010 R09: 0000000000000010 R10: 0000000000010001 R11: 0000000000000246 R12: 0000000000402180 R13: 0000000000402210 R14: 0000000000000000 R15: 0000000000000000 Kernel Offset: disabled Rebooting in 86400 seconds.. Fixes: 1470ddf7f8ce ("inet: Remove explicit write references to sk/inet in ip_append_data") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-12-06 07:43:46 +03:00
static inline bool inetdev_valid_mtu(unsigned int mtu)
{
return likely(mtu >= IPV4_MIN_MTU);
}
void ip_sock_set_freebind(struct sock *sk);
int ip_sock_set_mtu_discover(struct sock *sk, int val);
void ip_sock_set_pktinfo(struct sock *sk);
void ip_sock_set_recverr(struct sock *sk);
void ip_sock_set_tos(struct sock *sk, int val);
#endif /* _IP_H */