mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-15 12:07:12 +07:00
df4d92549f
Not caching dst_entries which cause redirects could be exploited by hosts
on the same subnet, causing a severe DoS attack. This effect aggravated
since commit f886497212
("ipv4: fix dst race in sk_dst_get()").
Lookups causing redirects will be allocated with DST_NOCACHE set which
will force dst_release to free them via RCU. Unfortunately waiting for
RCU grace period just takes too long, we can end up with >1M dst_entries
waiting to be released and the system will run OOM. rcuos threads cannot
catch up under high softirq load.
Attaching the flag to emit a redirect later on to the specific skb allows
us to cache those dst_entries thus reducing the pressure on allocation
and deallocation.
This issue was discovered by Marcelo Leitner.
Cc: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Marcelo Leitner <mleitner@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
156 lines
3.8 KiB
C
156 lines
3.8 KiB
C
/*
|
|
* 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.
|
|
*
|
|
* The IP forwarding functionality.
|
|
*
|
|
* Authors: see ip.c
|
|
*
|
|
* Fixes:
|
|
* Many : Split from ip.c , see ip_input.c for
|
|
* history.
|
|
* Dave Gregorich : NULL ip_rt_put fix for multicast
|
|
* routing.
|
|
* Jos Vos : Add call_out_firewall before sending,
|
|
* use output device for accounting.
|
|
* Jos Vos : Call forward firewall after routing
|
|
* (always use output device).
|
|
* Mike McLagan : Routing by source
|
|
*/
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/skbuff.h>
|
|
#include <linux/ip.h>
|
|
#include <linux/icmp.h>
|
|
#include <linux/netdevice.h>
|
|
#include <linux/slab.h>
|
|
#include <net/sock.h>
|
|
#include <net/ip.h>
|
|
#include <net/tcp.h>
|
|
#include <net/udp.h>
|
|
#include <net/icmp.h>
|
|
#include <linux/tcp.h>
|
|
#include <linux/udp.h>
|
|
#include <linux/netfilter_ipv4.h>
|
|
#include <net/checksum.h>
|
|
#include <linux/route.h>
|
|
#include <net/route.h>
|
|
#include <net/xfrm.h>
|
|
|
|
static bool ip_may_fragment(const struct sk_buff *skb)
|
|
{
|
|
return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) ||
|
|
skb->ignore_df;
|
|
}
|
|
|
|
static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
|
|
{
|
|
if (skb->len <= mtu)
|
|
return false;
|
|
|
|
if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
|
|
return false;
|
|
|
|
return true;
|
|
}
|
|
|
|
|
|
static int ip_forward_finish(struct sk_buff *skb)
|
|
{
|
|
struct ip_options *opt = &(IPCB(skb)->opt);
|
|
|
|
IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS);
|
|
IP_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len);
|
|
|
|
if (unlikely(opt->optlen))
|
|
ip_forward_options(skb);
|
|
|
|
return dst_output(skb);
|
|
}
|
|
|
|
int ip_forward(struct sk_buff *skb)
|
|
{
|
|
u32 mtu;
|
|
struct iphdr *iph; /* Our header */
|
|
struct rtable *rt; /* Route we use */
|
|
struct ip_options *opt = &(IPCB(skb)->opt);
|
|
|
|
/* that should never happen */
|
|
if (skb->pkt_type != PACKET_HOST)
|
|
goto drop;
|
|
|
|
if (skb_warn_if_lro(skb))
|
|
goto drop;
|
|
|
|
if (!xfrm4_policy_check(NULL, XFRM_POLICY_FWD, skb))
|
|
goto drop;
|
|
|
|
if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb))
|
|
return NET_RX_SUCCESS;
|
|
|
|
skb_forward_csum(skb);
|
|
|
|
/*
|
|
* According to the RFC, we must first decrease the TTL field. If
|
|
* that reaches zero, we must reply an ICMP control message telling
|
|
* that the packet's lifetime expired.
|
|
*/
|
|
if (ip_hdr(skb)->ttl <= 1)
|
|
goto too_many_hops;
|
|
|
|
if (!xfrm4_route_forward(skb))
|
|
goto drop;
|
|
|
|
rt = skb_rtable(skb);
|
|
|
|
if (opt->is_strictroute && rt->rt_uses_gateway)
|
|
goto sr_failed;
|
|
|
|
IPCB(skb)->flags |= IPSKB_FORWARDED;
|
|
mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
|
|
if (!ip_may_fragment(skb) && ip_exceeds_mtu(skb, mtu)) {
|
|
IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS);
|
|
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
|
|
htonl(mtu));
|
|
goto drop;
|
|
}
|
|
|
|
/* We are about to mangle packet. Copy it! */
|
|
if (skb_cow(skb, LL_RESERVED_SPACE(rt->dst.dev)+rt->dst.header_len))
|
|
goto drop;
|
|
iph = ip_hdr(skb);
|
|
|
|
/* Decrease ttl after skb cow done */
|
|
ip_decrease_ttl(iph);
|
|
|
|
/*
|
|
* We now generate an ICMP HOST REDIRECT giving the route
|
|
* we calculated.
|
|
*/
|
|
if (IPCB(skb)->flags & IPSKB_DOREDIRECT && !opt->srr &&
|
|
!skb_sec_path(skb))
|
|
ip_rt_send_redirect(skb);
|
|
|
|
skb->priority = rt_tos2priority(iph->tos);
|
|
|
|
return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, skb, skb->dev,
|
|
rt->dst.dev, ip_forward_finish);
|
|
|
|
sr_failed:
|
|
/*
|
|
* Strict routing permits no gatewaying
|
|
*/
|
|
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_SR_FAILED, 0);
|
|
goto drop;
|
|
|
|
too_many_hops:
|
|
/* Tell the sender its packet died... */
|
|
IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_INHDRERRORS);
|
|
icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0);
|
|
drop:
|
|
kfree_skb(skb);
|
|
return NET_RX_DROP;
|
|
}
|