linux_old1/include/linux/ipv6.h

375 lines
8.4 KiB
C
Raw Normal View History

#ifndef _IPV6_H
#define _IPV6_H
#include <uapi/linux/ipv6.h>
#define ipv6_optlen(p) (((p)->hdrlen+1) << 3)
#define ipv6_authlen(p) (((p)->hdrlen+2) << 2)
/*
* This structure contains configuration options per IPv6 link.
*/
struct ipv6_devconf {
__s32 forwarding;
__s32 hop_limit;
__s32 mtu6;
__s32 accept_ra;
__s32 accept_redirects;
__s32 autoconf;
__s32 dad_transmits;
__s32 rtr_solicits;
__s32 rtr_solicit_interval;
__s32 rtr_solicit_max_interval;
__s32 rtr_solicit_delay;
__s32 force_mld_version;
__s32 mldv1_unsolicited_report_interval;
__s32 mldv2_unsolicited_report_interval;
__s32 use_tempaddr;
__s32 temp_valid_lft;
__s32 temp_prefered_lft;
__s32 regen_max_retry;
__s32 max_desync_factor;
__s32 max_addresses;
__s32 accept_ra_defrtr;
__s32 accept_ra_min_hop_limit;
__s32 accept_ra_pinfo;
net: ipv6 sysctl option to ignore routes when nexthop link is down Like the ipv4 patch with a similar title, this adds a sysctl to allow the user to change routing behavior based on whether or not the interface associated with the nexthop was an up or down link. The default setting preserves the current behavior, but anyone that enables it will notice that nexthops on down interfaces will no longer be selected: net.ipv6.conf.all.ignore_routes_with_linkdown = 0 net.ipv6.conf.default.ignore_routes_with_linkdown = 0 net.ipv6.conf.lo.ignore_routes_with_linkdown = 0 ... When the above sysctls are set, not only will link status be reported to userspace, but an indication that a nexthop is dead and will not be used is also reported. 1000::/8 via 7000::2 dev p7p1 metric 1024 dead linkdown pref medium 1000::/8 via 8000::2 dev p8p1 metric 1024 pref medium 7000::/8 dev p7p1 proto kernel metric 256 dead linkdown pref medium 8000::/8 dev p8p1 proto kernel metric 256 pref medium 9000::/8 via 8000::2 dev p8p1 metric 2048 pref medium 9000::/8 via 7000::2 dev p7p1 metric 1024 dead linkdown pref medium fe80::/64 dev p7p1 proto kernel metric 256 dead linkdown pref medium fe80::/64 dev p8p1 proto kernel metric 256 pref medium This also adds devconf support and notification when sysctl values change. v2: drop use of rt6i_nhflags since it is not needed right now Signed-off-by: Andy Gospodarek <gospo@cumulusnetworks.com> Signed-off-by: Dinesh Dutt <ddutt@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-13 22:39:01 +08:00
__s32 ignore_routes_with_linkdown;
#ifdef CONFIG_IPV6_ROUTER_PREF
__s32 accept_ra_rtr_pref;
__s32 rtr_probe_interval;
#ifdef CONFIG_IPV6_ROUTE_INFO
__s32 accept_ra_rt_info_max_plen;
#endif
#endif
__s32 proxy_ndp;
__s32 accept_source_route;
__s32 accept_ra_from_local;
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
__s32 optimistic_dad;
net: ipv6: Add a sysctl to make optimistic addresses useful candidates Add a sysctl that causes an interface's optimistic addresses to be considered equivalent to other non-deprecated addresses for source address selection purposes. Preferred addresses will still take precedence over optimistic addresses, subject to other ranking in the source address selection algorithm. This is useful where different interfaces are connected to different networks from different ISPs (e.g., a cell network and a home wifi network). The current behaviour complies with RFC 3484/6724, and it makes sense if the host has only one interface, or has multiple interfaces on the same network (same or cooperating administrative domain(s), but not in the multiple distinct networks case. For example, if a mobile device has an IPv6 address on an LTE network and then connects to IPv6-enabled wifi, while the wifi IPv6 address is undergoing DAD, IPv6 connections will try use the wifi default route with the LTE IPv6 address, and will get stuck until they time out. Also, because optimistic nodes can receive frames, issue an RTM_NEWADDR as soon as DAD starts (with the IFA_F_OPTIMSTIC flag appropriately set). A second RTM_NEWADDR is sent if DAD completes (the address flags have changed), otherwise an RTM_DELADDR is sent. Also: add an entry in ip-sysctl.txt for optimistic_dad. Signed-off-by: Erik Kline <ek@google.com> Acked-by: Lorenzo Colitti <lorenzo@google.com> Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-28 17:11:14 +08:00
__s32 use_optimistic;
#endif
#ifdef CONFIG_IPV6_MROUTE
__s32 mc_forwarding;
#endif
__s32 disable_ipv6;
__s32 drop_unicast_in_l2_multicast;
__s32 accept_dad;
__s32 force_tllao;
__s32 ndisc_notify;
__s32 suppress_frag_ndisc;
__s32 accept_ra_mtu;
__s32 drop_unsolicited_na;
struct ipv6_stable_secret {
bool initialized;
struct in6_addr secret;
} stable_secret;
__s32 use_oif_addrs_only;
net: ipv6: Make address flushing on ifdown optional Currently, all ipv6 addresses are flushed when the interface is configured down, including global, static addresses: $ ip -6 addr show dev eth1 3: eth1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 state UP qlen 1000 inet6 2100:1::2/120 scope global valid_lft forever preferred_lft forever inet6 fe80::e0:f9ff:fe79:34bd/64 scope link valid_lft forever preferred_lft forever $ ip link set dev eth1 down $ ip -6 addr show dev eth1 << nothing; all addresses have been flushed>> Add a new sysctl to make this behavior optional. The new setting defaults to flush all addresses to maintain backwards compatibility. When the set global addresses with no expire times are not flushed on an admin down. The sysctl is per-interface or system-wide for all interfaces $ sysctl -w net.ipv6.conf.eth1.keep_addr_on_down=1 or $ sysctl -w net.ipv6.conf.all.keep_addr_on_down=1 Will keep addresses on eth1 on an admin down. $ ip -6 addr show dev eth1 3: eth1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 state UP qlen 1000 inet6 2100:1::2/120 scope global valid_lft forever preferred_lft forever inet6 fe80::e0:f9ff:fe79:34bd/64 scope link valid_lft forever preferred_lft forever $ ip link set dev eth1 down $ ip -6 addr show dev eth1 3: eth1: <BROADCAST,MULTICAST> mtu 1500 state DOWN qlen 1000 inet6 2100:1::2/120 scope global tentative valid_lft forever preferred_lft forever inet6 fe80::e0:f9ff:fe79:34bd/64 scope link tentative valid_lft forever preferred_lft forever Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 01:25:37 +08:00
__s32 keep_addr_on_down;
__s32 seg6_enabled;
#ifdef CONFIG_IPV6_SEG6_HMAC
__s32 seg6_require_hmac;
#endif
__u32 enhanced_dad;
struct ctl_table_header *sysctl_header;
};
struct ipv6_params {
__s32 disable_ipv6;
__s32 autoconf;
};
extern struct ipv6_params ipv6_defaults;
#include <linux/icmpv6.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <net/inet_sock.h>
static inline struct ipv6hdr *ipv6_hdr(const struct sk_buff *skb)
{
return (struct ipv6hdr *)skb_network_header(skb);
}
static inline struct ipv6hdr *inner_ipv6_hdr(const struct sk_buff *skb)
{
return (struct ipv6hdr *)skb_inner_network_header(skb);
}
static inline struct ipv6hdr *ipipv6_hdr(const struct sk_buff *skb)
{
return (struct ipv6hdr *)skb_transport_header(skb);
}
/*
This structure contains results of exthdrs parsing
as offsets from skb->nh.
*/
struct inet6_skb_parm {
int iif;
__be16 ra;
__u16 dst0;
__u16 srcrt;
__u16 dst1;
__u16 lastopt;
__u16 nhoff;
__u16 flags;
#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
__u16 dsthao;
#endif
netfilter: nf_conntrack_ipv6: improve fragmentation handling The IPv6 conntrack fragmentation currently has a couple of shortcomings. Fragmentes are collected in PREROUTING/OUTPUT, are defragmented, the defragmented packet is then passed to conntrack, the resulting conntrack information is attached to each original fragment and the fragments then continue their way through the stack. Helper invocation occurs in the POSTROUTING hook, at which point only the original fragments are available. The result of this is that fragmented packets are never passed to helpers. This patch improves the situation in the following way: - If a reassembled packet belongs to a connection that has a helper assigned, the reassembled packet is passed through the stack instead of the original fragments. - During defragmentation, the largest received fragment size is stored. On output, the packet is refragmented if required. If the largest received fragment size exceeds the outgoing MTU, a "packet too big" message is generated, thus behaving as if the original fragments were passed through the stack from an outside point of view. - The ipv6_helper() hook function can't receive fragments anymore for connections using a helper, so it is switched to use ipv6_skip_exthdr() instead of the netfilter specific nf_ct_ipv6_skip_exthdr() and the reassembled packets are passed to connection tracking helpers. The result of this is that we can properly track fragmented packets, but still generate ICMPv6 Packet too big messages if we would have before. This patch is also required as a precondition for IPv6 NAT, where NAT helpers might enlarge packets up to a point that they require fragmentation. In that case we can't generate Packet too big messages since the proper MTU can't be calculated in all cases (f.i. when changing textual representation of a variable amount of addresses), so the packet is transparently fragmented iff the original packet or fragments would have fit the outgoing MTU. IPVS parts by Jesper Dangaard Brouer <brouer@redhat.com>. Signed-off-by: Patrick McHardy <kaber@trash.net>
2012-08-27 01:13:58 +08:00
__u16 frag_max_size;
#define IP6SKB_XFRM_TRANSFORMED 1
#define IP6SKB_FORWARDED 2
#define IP6SKB_REROUTED 4
#define IP6SKB_ROUTERALERT 8
#define IP6SKB_FRAGMENTED 16
#define IP6SKB_HOPBYHOP 32
#define IP6SKB_L3SLAVE 64
};
#if defined(CONFIG_NET_L3_MASTER_DEV)
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 11:02:52 +08:00
static inline bool ipv6_l3mdev_skb(__u16 flags)
{
return flags & IP6SKB_L3SLAVE;
}
#else
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 11:02:52 +08:00
static inline bool ipv6_l3mdev_skb(__u16 flags)
{
return false;
}
#endif
#define IP6CB(skb) ((struct inet6_skb_parm*)((skb)->cb))
#define IP6CBMTU(skb) ((struct ip6_mtuinfo *)((skb)->cb))
static inline int inet6_iif(const struct sk_buff *skb)
{
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 11:02:52 +08:00
bool l3_slave = ipv6_l3mdev_skb(IP6CB(skb)->flags);
return l3_slave ? skb->skb_iif : IP6CB(skb)->iif;
}
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 11:02:52 +08:00
/* can not be used in TCP layer after tcp_v6_fill_cb */
static inline bool inet6_exact_dif_match(struct net *net, struct sk_buff *skb)
{
#if defined(CONFIG_NET_L3_MASTER_DEV)
if (!net->ipv4.sysctl_tcp_l3mdev_accept &&
net: tcp: check skb is non-NULL for exact match on lookups Andrey reported the following error report while running the syzkaller fuzzer: general protection fault: 0000 [#1] SMP KASAN Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 0 PID: 648 Comm: syz-executor Not tainted 4.9.0-rc3+ #333 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff8800398c4480 task.stack: ffff88003b468000 RIP: 0010:[<ffffffff83091106>] [< inline >] inet_exact_dif_match include/net/tcp.h:808 RIP: 0010:[<ffffffff83091106>] [<ffffffff83091106>] __inet_lookup_listener+0xb6/0x500 net/ipv4/inet_hashtables.c:219 RSP: 0018:ffff88003b46f270 EFLAGS: 00010202 RAX: 0000000000000004 RBX: 0000000000004242 RCX: 0000000000000001 RDX: 0000000000000000 RSI: ffffc90000e3c000 RDI: 0000000000000054 RBP: ffff88003b46f2d8 R08: 0000000000004000 R09: ffffffff830910e7 R10: 0000000000000000 R11: 000000000000000a R12: ffffffff867fa0c0 R13: 0000000000004242 R14: 0000000000000003 R15: dffffc0000000000 FS: 00007fb135881700(0000) GS:ffff88003ec00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020cc3000 CR3: 000000006d56a000 CR4: 00000000000006f0 Stack: 0000000000000000 000000000601a8c0 0000000000000000 ffffffff00004242 424200003b9083c2 ffff88003def4041 ffffffff84e7e040 0000000000000246 ffff88003a0911c0 0000000000000000 ffff88003a091298 ffff88003b9083ae Call Trace: [<ffffffff831100f4>] tcp_v4_send_reset+0x584/0x1700 net/ipv4/tcp_ipv4.c:643 [<ffffffff83115b1b>] tcp_v4_rcv+0x198b/0x2e50 net/ipv4/tcp_ipv4.c:1718 [<ffffffff83069d22>] ip_local_deliver_finish+0x332/0xad0 net/ipv4/ip_input.c:216 ... MD5 has a code path that calls __inet_lookup_listener with a null skb, so inet{6}_exact_dif_match needs to check skb against null before pulling the flag. Fixes: a04a480d4392 ("net: Require exact match for TCP socket lookups if dif is l3mdev") Reported-by: Andrey Konovalov <andreyknvl@google.com> Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Tested-by: Andrey Konovalov <andreyknvl@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-03 03:08:25 +08:00
skb && ipv6_l3mdev_skb(IP6CB(skb)->flags))
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 11:02:52 +08:00
return true;
#endif
return false;
}
struct tcp6_request_sock {
struct tcp_request_sock tcp6rsk_tcp;
};
struct ipv6_mc_socklist;
struct ipv6_ac_socklist;
struct ipv6_fl_socklist;
struct inet6_cork {
struct ipv6_txoptions *opt;
u8 hop_limit;
u8 tclass;
};
/**
* struct ipv6_pinfo - ipv6 private area
*
* In the struct sock hierarchy (tcp6_sock, upd6_sock, etc)
* this _must_ be the last member, so that inet6_sk_generic
* is able to calculate its offset from the base struct sock
* by using the struct proto->slab_obj_size member. -acme
*/
struct ipv6_pinfo {
struct in6_addr saddr;
struct in6_pktinfo sticky_pktinfo;
const struct in6_addr *daddr_cache;
#ifdef CONFIG_IPV6_SUBTREES
const struct in6_addr *saddr_cache;
#endif
__be32 flow_label;
__u32 frag_size;
/*
* Packed in 16bits.
* Omit one shift by by putting the signed field at MSB.
*/
#if defined(__BIG_ENDIAN_BITFIELD)
__s16 hop_limit:9;
__u16 __unused_1:7;
#else
__u16 __unused_1:7;
__s16 hop_limit:9;
#endif
#if defined(__BIG_ENDIAN_BITFIELD)
/* Packed in 16bits. */
__s16 mcast_hops:9;
__u16 __unused_2:6,
mc_loop:1;
#else
__u16 mc_loop:1,
__unused_2:6;
__s16 mcast_hops:9;
#endif
int ucast_oif;
int mcast_oif;
/* pktoption flags */
union {
struct {
__u16 srcrt:1,
osrcrt:1,
rxinfo:1,
rxoinfo:1,
rxhlim:1,
rxohlim:1,
hopopts:1,
ohopopts:1,
dstopts:1,
odstopts:1,
rxflow:1,
rxtclass:1,
rxpmtu:1,
rxorigdstaddr:1,
recvfragsize:1;
/* 1 bits hole */
} bits;
__u16 all;
} rxopt;
/* sockopt flags */
__u16 recverr:1,
sndflow:1,
repflow:1,
pmtudisc:3,
padding:1, /* 1 bit hole */
srcprefs:3, /* 001: prefer temporary address
* 010: prefer public address
* 100: prefer care-of address
*/
ipv6: Implement automatic flow label generation on transmit Automatically generate flow labels for IPv6 packets on transmit. The flow label is computed based on skb_get_hash. The flow label will only automatically be set when it is zero otherwise (i.e. flow label manager hasn't set one). This supports the transmit side functionality of RFC 6438. Added an IPv6 sysctl auto_flowlabels to enable/disable this behavior system wide, and added IPV6_AUTOFLOWLABEL socket option to enable this functionality per socket. By default, auto flowlabels are disabled to avoid possible conflicts with flow label manager, however if this feature proves useful we may want to enable it by default. It should also be noted that FreeBSD has already implemented automatic flow labels (including the sysctl and socket option). In FreeBSD, automatic flow labels default to enabled. Performance impact: Running super_netperf with 200 flows for TCP_RR and UDP_RR for IPv6. Note that in UDP case, __skb_get_hash will be called for every packet with explains slight regression. In the TCP case the hash is saved in the socket so there is no regression. Automatic flow labels disabled: TCP_RR: 86.53% CPU utilization 127/195/322 90/95/99% latencies 1.40498e+06 tps UDP_RR: 90.70% CPU utilization 118/168/243 90/95/99% latencies 1.50309e+06 tps Automatic flow labels enabled: TCP_RR: 85.90% CPU utilization 128/199/337 90/95/99% latencies 1.40051e+06 UDP_RR 92.61% CPU utilization 115/164/236 90/95/99% latencies 1.4687e+06 Signed-off-by: Tom Herbert <therbert@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-02 12:33:10 +08:00
dontfrag:1,
autoflowlabel:1;
__u8 min_hopcount;
__u8 tclass;
__be32 rcv_flowinfo;
__u32 dst_cookie;
__u32 rx_dst_cookie;
struct ipv6_mc_socklist __rcu *ipv6_mc_list;
struct ipv6_ac_socklist *ipv6_ac_list;
struct ipv6_fl_socklist __rcu *ipv6_fl_list;
struct ipv6_txoptions __rcu *opt;
struct sk_buff *pktoptions;
struct sk_buff *rxpmtu;
struct inet6_cork cork;
};
/* WARNING: don't change the layout of the members in {raw,udp,tcp}6_sock! */
struct raw6_sock {
/* inet_sock has to be the first member of raw6_sock */
struct inet_sock inet;
__u32 checksum; /* perform checksum */
__u32 offset; /* checksum offset */
struct icmp6_filter filter;
__u32 ip6mr_table;
/* ipv6_pinfo has to be the last member of raw6_sock, see inet6_sk_generic */
struct ipv6_pinfo inet6;
};
struct udp6_sock {
struct udp_sock udp;
/* ipv6_pinfo has to be the last member of udp6_sock, see inet6_sk_generic */
struct ipv6_pinfo inet6;
};
struct tcp6_sock {
struct tcp_sock tcp;
/* ipv6_pinfo has to be the last member of tcp6_sock, see inet6_sk_generic */
struct ipv6_pinfo inet6;
};
extern int inet6_sk_rebuild_header(struct sock *sk);
struct tcp6_timewait_sock {
struct tcp_timewait_sock tcp6tw_tcp;
};
#if IS_ENABLED(CONFIG_IPV6)
net: vrf: Fix crash when IPv6 is disabled at boot time Frank Kellermann reported a kernel crash with 4.5.0 when IPv6 is disabled at boot using the kernel option ipv6.disable=1. Using current net-next with the boot option: $ ip link add red type vrf table 1001 Generates: [12210.919584] BUG: unable to handle kernel NULL pointer dereference at 0000000000000748 [12210.921341] IP: [<ffffffff814b30e3>] fib6_get_table+0x2c/0x5a [12210.922537] PGD b79e3067 PUD bb32b067 PMD 0 [12210.923479] Oops: 0000 [#1] SMP [12210.924001] Modules linked in: ipvlan 8021q garp mrp stp llc [12210.925130] CPU: 3 PID: 1177 Comm: ip Not tainted 4.7.0-rc1+ #235 [12210.926168] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014 [12210.928065] task: ffff8800b9ac4640 ti: ffff8800bacac000 task.ti: ffff8800bacac000 [12210.929328] RIP: 0010:[<ffffffff814b30e3>] [<ffffffff814b30e3>] fib6_get_table+0x2c/0x5a [12210.930697] RSP: 0018:ffff8800bacaf888 EFLAGS: 00010202 [12210.931563] RAX: 0000000000000748 RBX: ffffffff81a9e280 RCX: ffff8800b9ac4e28 [12210.932688] RDX: 00000000000000e9 RSI: 0000000000000002 RDI: 0000000000000286 [12210.933820] RBP: ffff8800bacaf898 R08: ffff8800b9ac4df0 R09: 000000000052001b [12210.934941] R10: 00000000657c0000 R11: 000000000000c649 R12: 00000000000003e9 [12210.936032] R13: 00000000000003e9 R14: ffff8800bace7800 R15: ffff8800bb3ec000 [12210.937103] FS: 00007faa1766c700(0000) GS:ffff88013ac00000(0000) knlGS:0000000000000000 [12210.938321] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [12210.939166] CR2: 0000000000000748 CR3: 00000000b79d6000 CR4: 00000000000406e0 [12210.940278] Stack: [12210.940603] ffff8800bb3ec000 ffffffff81a9e280 ffff8800bacaf8c8 ffffffff814b3135 [12210.941818] ffff8800bb3ec000 ffffffff81a9e280 ffffffff81a9e280 ffff8800bace7800 [12210.943040] ffff8800bacaf8f0 ffffffff81397c88 ffff8800bb3ec000 ffffffff81a9e280 [12210.944288] Call Trace: [12210.944688] [<ffffffff814b3135>] fib6_new_table+0x24/0x8a [12210.945516] [<ffffffff81397c88>] vrf_dev_init+0xd4/0x162 [12210.946328] [<ffffffff814091e1>] register_netdevice+0x100/0x396 [12210.947209] [<ffffffff8139823d>] vrf_newlink+0x40/0xb3 [12210.948001] [<ffffffff814187f0>] rtnl_newlink+0x5d3/0x6d5 ... The problem above is due to the fact that the fib hash table is not allocated when IPv6 is disabled at boot. As for the VRF driver it should not do any IPv6 initializations if IPv6 is disabled, so it needs to know if IPv6 is disabled at boot. The disable parameter is private to the IPv6 module, so provide an accessor for modules to determine if IPv6 was disabled at boot time. Fixes: 35402e3136634 ("net: Add IPv6 support to VRF device") Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-10 01:21:00 +08:00
bool ipv6_mod_enabled(void);
static inline struct ipv6_pinfo *inet6_sk(const struct sock *__sk)
{
return sk_fullsock(__sk) ? inet_sk(__sk)->pinet6 : NULL;
}
static inline struct raw6_sock *raw6_sk(const struct sock *sk)
{
return (struct raw6_sock *)sk;
}
static inline void inet_sk_copy_descendant(struct sock *sk_to,
const struct sock *sk_from)
{
int ancestor_size = sizeof(struct inet_sock);
if (sk_from->sk_family == PF_INET6)
ancestor_size += sizeof(struct ipv6_pinfo);
__inet_sk_copy_descendant(sk_to, sk_from, ancestor_size);
}
#define __ipv6_only_sock(sk) (sk->sk_ipv6only)
#define ipv6_only_sock(sk) (__ipv6_only_sock(sk))
#define ipv6_sk_rxinfo(sk) ((sk)->sk_family == PF_INET6 && \
inet6_sk(sk)->rxopt.bits.rxinfo)
static inline const struct in6_addr *inet6_rcv_saddr(const struct sock *sk)
{
if (sk->sk_family == AF_INET6)
return &sk->sk_v6_rcv_saddr;
return NULL;
}
static inline int inet_v6_ipv6only(const struct sock *sk)
{
/* ipv6only field is at same position for timewait and other sockets */
return ipv6_only_sock(sk);
}
#else
#define __ipv6_only_sock(sk) 0
#define ipv6_only_sock(sk) 0
#define ipv6_sk_rxinfo(sk) 0
net: vrf: Fix crash when IPv6 is disabled at boot time Frank Kellermann reported a kernel crash with 4.5.0 when IPv6 is disabled at boot using the kernel option ipv6.disable=1. Using current net-next with the boot option: $ ip link add red type vrf table 1001 Generates: [12210.919584] BUG: unable to handle kernel NULL pointer dereference at 0000000000000748 [12210.921341] IP: [<ffffffff814b30e3>] fib6_get_table+0x2c/0x5a [12210.922537] PGD b79e3067 PUD bb32b067 PMD 0 [12210.923479] Oops: 0000 [#1] SMP [12210.924001] Modules linked in: ipvlan 8021q garp mrp stp llc [12210.925130] CPU: 3 PID: 1177 Comm: ip Not tainted 4.7.0-rc1+ #235 [12210.926168] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014 [12210.928065] task: ffff8800b9ac4640 ti: ffff8800bacac000 task.ti: ffff8800bacac000 [12210.929328] RIP: 0010:[<ffffffff814b30e3>] [<ffffffff814b30e3>] fib6_get_table+0x2c/0x5a [12210.930697] RSP: 0018:ffff8800bacaf888 EFLAGS: 00010202 [12210.931563] RAX: 0000000000000748 RBX: ffffffff81a9e280 RCX: ffff8800b9ac4e28 [12210.932688] RDX: 00000000000000e9 RSI: 0000000000000002 RDI: 0000000000000286 [12210.933820] RBP: ffff8800bacaf898 R08: ffff8800b9ac4df0 R09: 000000000052001b [12210.934941] R10: 00000000657c0000 R11: 000000000000c649 R12: 00000000000003e9 [12210.936032] R13: 00000000000003e9 R14: ffff8800bace7800 R15: ffff8800bb3ec000 [12210.937103] FS: 00007faa1766c700(0000) GS:ffff88013ac00000(0000) knlGS:0000000000000000 [12210.938321] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [12210.939166] CR2: 0000000000000748 CR3: 00000000b79d6000 CR4: 00000000000406e0 [12210.940278] Stack: [12210.940603] ffff8800bb3ec000 ffffffff81a9e280 ffff8800bacaf8c8 ffffffff814b3135 [12210.941818] ffff8800bb3ec000 ffffffff81a9e280 ffffffff81a9e280 ffff8800bace7800 [12210.943040] ffff8800bacaf8f0 ffffffff81397c88 ffff8800bb3ec000 ffffffff81a9e280 [12210.944288] Call Trace: [12210.944688] [<ffffffff814b3135>] fib6_new_table+0x24/0x8a [12210.945516] [<ffffffff81397c88>] vrf_dev_init+0xd4/0x162 [12210.946328] [<ffffffff814091e1>] register_netdevice+0x100/0x396 [12210.947209] [<ffffffff8139823d>] vrf_newlink+0x40/0xb3 [12210.948001] [<ffffffff814187f0>] rtnl_newlink+0x5d3/0x6d5 ... The problem above is due to the fact that the fib hash table is not allocated when IPv6 is disabled at boot. As for the VRF driver it should not do any IPv6 initializations if IPv6 is disabled, so it needs to know if IPv6 is disabled at boot. The disable parameter is private to the IPv6 module, so provide an accessor for modules to determine if IPv6 was disabled at boot time. Fixes: 35402e3136634 ("net: Add IPv6 support to VRF device") Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-10 01:21:00 +08:00
static inline bool ipv6_mod_enabled(void)
{
return false;
}
static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk)
{
return NULL;
}
static inline struct inet6_request_sock *
inet6_rsk(const struct request_sock *rsk)
{
return NULL;
}
static inline struct raw6_sock *raw6_sk(const struct sock *sk)
{
return NULL;
}
#define inet6_rcv_saddr(__sk) NULL
#define tcp_twsk_ipv6only(__sk) 0
#define inet_v6_ipv6only(__sk) 0
#endif /* IS_ENABLED(CONFIG_IPV6) */
#endif /* _IPV6_H */