linux-sg2042/net/ipv6/ip6_input.c

595 lines
14 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* IPv6 input
* Linux INET6 implementation
*
* Authors:
* Pedro Roque <roque@di.fc.ul.pt>
* Ian P. Morris <I.P.Morris@soton.ac.uk>
*
* Based in linux/net/ipv4/ip_input.c
*/
/* Changes
*
* Mitsuru KANDA @USAGI and
* YOSHIFUJI Hideaki @USAGI: Remove ipv6_parse_exthdrs().
*/
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/netdevice.h>
#include <linux/in6.h>
#include <linux/icmpv6.h>
#include <linux/mroute6.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/indirect_call_wrapper.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>
#include <net/sock.h>
#include <net/snmp.h>
#include <net/udp.h>
#include <net/ipv6.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/rawv6.h>
#include <net/ndisc.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/xfrm.h>
#include <net/inet_ecn.h>
#include <net/dst_metadata.h>
static void ip6_rcv_finish_core(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
tcp/udp: Make early_demux back namespacified. Commit e21145a9871a ("ipv4: namespacify ip_early_demux sysctl knob") made it possible to enable/disable early_demux on a per-netns basis. Then, we introduced two knobs, tcp_early_demux and udp_early_demux, to switch it for TCP/UDP in commit dddb64bcb346 ("net: Add sysctl to toggle early demux for tcp and udp"). However, the .proc_handler() was wrong and actually disabled us from changing the behaviour in each netns. We can execute early_demux if net.ipv4.ip_early_demux is on and each proto .early_demux() handler is not NULL. When we toggle (tcp|udp)_early_demux, the change itself is saved in each netns variable, but the .early_demux() handler is a global variable, so the handler is switched based on the init_net's sysctl variable. Thus, netns (tcp|udp)_early_demux knobs have nothing to do with the logic. Whether we CAN execute proto .early_demux() is always decided by init_net's sysctl knob, and whether we DO it or not is by each netns ip_early_demux knob. This patch namespacifies (tcp|udp)_early_demux again. For now, the users of the .early_demux() handler are TCP and UDP only, and they are called directly to avoid retpoline. So, we can remove the .early_demux() handler from inet6?_protos and need not dereference them in ip6?_rcv_finish_core(). If another proto needs .early_demux(), we can restore it at that time. Fixes: dddb64bcb346 ("net: Add sysctl to toggle early demux for tcp and udp") Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Link: https://lore.kernel.org/r/20220713175207.7727-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-07-14 01:52:07 +08:00
if (READ_ONCE(net->ipv4.sysctl_ip_early_demux) &&
!skb_dst(skb) && !skb->sk) {
switch (ipv6_hdr(skb)->nexthdr) {
case IPPROTO_TCP:
if (READ_ONCE(net->ipv4.sysctl_tcp_early_demux))
tcp_v6_early_demux(skb);
break;
case IPPROTO_UDP:
if (READ_ONCE(net->ipv4.sysctl_udp_early_demux))
udp_v6_early_demux(skb);
break;
}
}
tcp/udp: Make early_demux back namespacified. Commit e21145a9871a ("ipv4: namespacify ip_early_demux sysctl knob") made it possible to enable/disable early_demux on a per-netns basis. Then, we introduced two knobs, tcp_early_demux and udp_early_demux, to switch it for TCP/UDP in commit dddb64bcb346 ("net: Add sysctl to toggle early demux for tcp and udp"). However, the .proc_handler() was wrong and actually disabled us from changing the behaviour in each netns. We can execute early_demux if net.ipv4.ip_early_demux is on and each proto .early_demux() handler is not NULL. When we toggle (tcp|udp)_early_demux, the change itself is saved in each netns variable, but the .early_demux() handler is a global variable, so the handler is switched based on the init_net's sysctl variable. Thus, netns (tcp|udp)_early_demux knobs have nothing to do with the logic. Whether we CAN execute proto .early_demux() is always decided by init_net's sysctl knob, and whether we DO it or not is by each netns ip_early_demux knob. This patch namespacifies (tcp|udp)_early_demux again. For now, the users of the .early_demux() handler are TCP and UDP only, and they are called directly to avoid retpoline. So, we can remove the .early_demux() handler from inet6?_protos and need not dereference them in ip6?_rcv_finish_core(). If another proto needs .early_demux(), we can restore it at that time. Fixes: dddb64bcb346 ("net: Add sysctl to toggle early demux for tcp and udp") Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Link: https://lore.kernel.org/r/20220713175207.7727-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-07-14 01:52:07 +08:00
if (!skb_valid_dst(skb))
ip6_route_input(skb);
}
int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
/* if ingress device is enslaved to an L3 master device pass the
* skb to its handler for processing
*/
skb = l3mdev_ip6_rcv(skb);
if (!skb)
return NET_RX_SUCCESS;
ip6_rcv_finish_core(net, sk, skb);
return dst_input(skb);
}
static void ip6_sublist_rcv_finish(struct list_head *head)
{
struct sk_buff *skb, *next;
net: ipv6: fix listify ip6_rcv_finish in case of forwarding We need a similar fix for ipv6 as Commit 0761680d5215 ("net: ipv4: fix listify ip_rcv_finish in case of forwarding") does for ipv4. This issue can be reprocuded by syzbot since Commit 323ebb61e32b ("net: use listified RX for handling GRO_NORMAL skbs") on net-next. The call trace was: kernel BUG at include/linux/skbuff.h:2225! RIP: 0010:__skb_pull include/linux/skbuff.h:2225 [inline] RIP: 0010:skb_pull+0xea/0x110 net/core/skbuff.c:1902 Call Trace: sctp_inq_pop+0x2f1/0xd80 net/sctp/inqueue.c:202 sctp_endpoint_bh_rcv+0x184/0x8d0 net/sctp/endpointola.c:385 sctp_inq_push+0x1e4/0x280 net/sctp/inqueue.c:80 sctp_rcv+0x2807/0x3590 net/sctp/input.c:256 sctp6_rcv+0x17/0x30 net/sctp/ipv6.c:1049 ip6_protocol_deliver_rcu+0x2fe/0x1660 net/ipv6/ip6_input.c:397 ip6_input_finish+0x84/0x170 net/ipv6/ip6_input.c:438 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip6_input+0xe4/0x3f0 net/ipv6/ip6_input.c:447 dst_input include/net/dst.h:442 [inline] ip6_sublist_rcv_finish+0x98/0x1e0 net/ipv6/ip6_input.c:84 ip6_list_rcv_finish net/ipv6/ip6_input.c:118 [inline] ip6_sublist_rcv+0x80c/0xcf0 net/ipv6/ip6_input.c:282 ipv6_list_rcv+0x373/0x4b0 net/ipv6/ip6_input.c:316 __netif_receive_skb_list_ptype net/core/dev.c:5049 [inline] __netif_receive_skb_list_core+0x5fc/0x9d0 net/core/dev.c:5097 __netif_receive_skb_list net/core/dev.c:5149 [inline] netif_receive_skb_list_internal+0x7eb/0xe60 net/core/dev.c:5244 gro_normal_list.part.0+0x1e/0xb0 net/core/dev.c:5757 gro_normal_list net/core/dev.c:5755 [inline] gro_normal_one net/core/dev.c:5769 [inline] napi_frags_finish net/core/dev.c:5782 [inline] napi_gro_frags+0xa6a/0xea0 net/core/dev.c:5855 tun_get_user+0x2e98/0x3fa0 drivers/net/tun.c:1974 tun_chr_write_iter+0xbd/0x156 drivers/net/tun.c:2020 Fixes: d8269e2cbf90 ("net: ipv6: listify ipv6_rcv() and ip6_rcv_finish()") Fixes: 323ebb61e32b ("net: use listified RX for handling GRO_NORMAL skbs") Reported-by: syzbot+eb349eeee854e389c36d@syzkaller.appspotmail.com Reported-by: syzbot+4a0643a653ac375612d1@syzkaller.appspotmail.com Signed-off-by: Xin Long <lucien.xin@gmail.com> Acked-by: Edward Cree <ecree@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-23 19:33:03 +08:00
list_for_each_entry_safe(skb, next, head, list) {
skb_list_del_init(skb);
dst_input(skb);
net: ipv6: fix listify ip6_rcv_finish in case of forwarding We need a similar fix for ipv6 as Commit 0761680d5215 ("net: ipv4: fix listify ip_rcv_finish in case of forwarding") does for ipv4. This issue can be reprocuded by syzbot since Commit 323ebb61e32b ("net: use listified RX for handling GRO_NORMAL skbs") on net-next. The call trace was: kernel BUG at include/linux/skbuff.h:2225! RIP: 0010:__skb_pull include/linux/skbuff.h:2225 [inline] RIP: 0010:skb_pull+0xea/0x110 net/core/skbuff.c:1902 Call Trace: sctp_inq_pop+0x2f1/0xd80 net/sctp/inqueue.c:202 sctp_endpoint_bh_rcv+0x184/0x8d0 net/sctp/endpointola.c:385 sctp_inq_push+0x1e4/0x280 net/sctp/inqueue.c:80 sctp_rcv+0x2807/0x3590 net/sctp/input.c:256 sctp6_rcv+0x17/0x30 net/sctp/ipv6.c:1049 ip6_protocol_deliver_rcu+0x2fe/0x1660 net/ipv6/ip6_input.c:397 ip6_input_finish+0x84/0x170 net/ipv6/ip6_input.c:438 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip6_input+0xe4/0x3f0 net/ipv6/ip6_input.c:447 dst_input include/net/dst.h:442 [inline] ip6_sublist_rcv_finish+0x98/0x1e0 net/ipv6/ip6_input.c:84 ip6_list_rcv_finish net/ipv6/ip6_input.c:118 [inline] ip6_sublist_rcv+0x80c/0xcf0 net/ipv6/ip6_input.c:282 ipv6_list_rcv+0x373/0x4b0 net/ipv6/ip6_input.c:316 __netif_receive_skb_list_ptype net/core/dev.c:5049 [inline] __netif_receive_skb_list_core+0x5fc/0x9d0 net/core/dev.c:5097 __netif_receive_skb_list net/core/dev.c:5149 [inline] netif_receive_skb_list_internal+0x7eb/0xe60 net/core/dev.c:5244 gro_normal_list.part.0+0x1e/0xb0 net/core/dev.c:5757 gro_normal_list net/core/dev.c:5755 [inline] gro_normal_one net/core/dev.c:5769 [inline] napi_frags_finish net/core/dev.c:5782 [inline] napi_gro_frags+0xa6a/0xea0 net/core/dev.c:5855 tun_get_user+0x2e98/0x3fa0 drivers/net/tun.c:1974 tun_chr_write_iter+0xbd/0x156 drivers/net/tun.c:2020 Fixes: d8269e2cbf90 ("net: ipv6: listify ipv6_rcv() and ip6_rcv_finish()") Fixes: 323ebb61e32b ("net: use listified RX for handling GRO_NORMAL skbs") Reported-by: syzbot+eb349eeee854e389c36d@syzkaller.appspotmail.com Reported-by: syzbot+4a0643a653ac375612d1@syzkaller.appspotmail.com Signed-off-by: Xin Long <lucien.xin@gmail.com> Acked-by: Edward Cree <ecree@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-23 19:33:03 +08:00
}
}
static bool ip6_can_use_hint(const struct sk_buff *skb,
const struct sk_buff *hint)
{
return hint && !skb_dst(skb) &&
ipv6_addr_equal(&ipv6_hdr(hint)->daddr, &ipv6_hdr(skb)->daddr);
}
static struct sk_buff *ip6_extract_route_hint(const struct net *net,
struct sk_buff *skb)
{
if (fib6_routes_require_src(net) || fib6_has_custom_rules(net))
return NULL;
return skb;
}
static void ip6_list_rcv_finish(struct net *net, struct sock *sk,
struct list_head *head)
{
struct sk_buff *skb, *next, *hint = NULL;
struct dst_entry *curr_dst = NULL;
struct list_head sublist;
INIT_LIST_HEAD(&sublist);
list_for_each_entry_safe(skb, next, head, list) {
struct dst_entry *dst;
net: use skb_list_del_init() to remove from RX sublists list_del() leaves the skb->next pointer poisoned, which can then lead to a crash in e.g. OVS forwarding. For example, setting up an OVS VXLAN forwarding bridge on sfc as per: ======== $ ovs-vsctl show 5dfd9c47-f04b-4aaa-aa96-4fbb0a522a30 Bridge "br0" Port "br0" Interface "br0" type: internal Port "enp6s0f0" Interface "enp6s0f0" Port "vxlan0" Interface "vxlan0" type: vxlan options: {key="1", local_ip="10.0.0.5", remote_ip="10.0.0.4"} ovs_version: "2.5.0" ======== (where 10.0.0.5 is an address on enp6s0f1) and sending traffic across it will lead to the following panic: ======== general protection fault: 0000 [#1] SMP PTI CPU: 5 PID: 0 Comm: swapper/5 Not tainted 4.20.0-rc3-ehc+ #701 Hardware name: Dell Inc. PowerEdge R710/0M233H, BIOS 6.4.0 07/23/2013 RIP: 0010:dev_hard_start_xmit+0x38/0x200 Code: 53 48 89 fb 48 83 ec 20 48 85 ff 48 89 54 24 08 48 89 4c 24 18 0f 84 ab 01 00 00 48 8d 86 90 00 00 00 48 89 f5 48 89 44 24 10 <4c> 8b 33 48 c7 03 00 00 00 00 48 8b 05 c7 d1 b3 00 4d 85 f6 0f 95 RSP: 0018:ffff888627b437e0 EFLAGS: 00010202 RAX: 0000000000000000 RBX: dead000000000100 RCX: ffff88862279c000 RDX: ffff888614a342c0 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffff888618a88000 R08: 0000000000000001 R09: 00000000000003e8 R10: 0000000000000000 R11: ffff888614a34140 R12: 0000000000000000 R13: 0000000000000062 R14: dead000000000100 R15: ffff888616430000 FS: 0000000000000000(0000) GS:ffff888627b40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f6d2bc6d000 CR3: 000000000200a000 CR4: 00000000000006e0 Call Trace: <IRQ> __dev_queue_xmit+0x623/0x870 ? masked_flow_lookup+0xf7/0x220 [openvswitch] ? ep_poll_callback+0x101/0x310 do_execute_actions+0xaba/0xaf0 [openvswitch] ? __wake_up_common+0x8a/0x150 ? __wake_up_common_lock+0x87/0xc0 ? queue_userspace_packet+0x31c/0x5b0 [openvswitch] ovs_execute_actions+0x47/0x120 [openvswitch] ovs_dp_process_packet+0x7d/0x110 [openvswitch] ovs_vport_receive+0x6e/0xd0 [openvswitch] ? dst_alloc+0x64/0x90 ? rt_dst_alloc+0x50/0xd0 ? ip_route_input_slow+0x19a/0x9a0 ? __udp_enqueue_schedule_skb+0x198/0x1b0 ? __udp4_lib_rcv+0x856/0xa30 ? __udp4_lib_rcv+0x856/0xa30 ? cpumask_next_and+0x19/0x20 ? find_busiest_group+0x12d/0xcd0 netdev_frame_hook+0xce/0x150 [openvswitch] __netif_receive_skb_core+0x205/0xae0 __netif_receive_skb_list_core+0x11e/0x220 netif_receive_skb_list+0x203/0x460 ? __efx_rx_packet+0x335/0x5e0 [sfc] efx_poll+0x182/0x320 [sfc] net_rx_action+0x294/0x3c0 __do_softirq+0xca/0x297 irq_exit+0xa6/0xb0 do_IRQ+0x54/0xd0 common_interrupt+0xf/0xf </IRQ> ======== So, in all listified-receive handling, instead pull skbs off the lists with skb_list_del_init(). Fixes: 9af86f933894 ("net: core: fix use-after-free in __netif_receive_skb_list_core") Fixes: 7da517a3bc52 ("net: core: Another step of skb receive list processing") Fixes: a4ca8b7df73c ("net: ipv4: fix drop handling in ip_list_rcv() and ip_list_rcv_finish()") Fixes: d8269e2cbf90 ("net: ipv6: listify ipv6_rcv() and ip6_rcv_finish()") Signed-off-by: Edward Cree <ecree@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-12-05 01:37:57 +08:00
skb_list_del_init(skb);
/* if ingress device is enslaved to an L3 master device pass the
* skb to its handler for processing
*/
skb = l3mdev_ip6_rcv(skb);
if (!skb)
continue;
if (ip6_can_use_hint(skb, hint))
skb_dst_copy(skb, hint);
else
ip6_rcv_finish_core(net, sk, skb);
dst = skb_dst(skb);
if (curr_dst != dst) {
hint = ip6_extract_route_hint(net, skb);
/* dispatch old sublist */
if (!list_empty(&sublist))
ip6_sublist_rcv_finish(&sublist);
/* start new sublist */
INIT_LIST_HEAD(&sublist);
curr_dst = dst;
}
list_add_tail(&skb->list, &sublist);
}
/* dispatch final sublist */
ip6_sublist_rcv_finish(&sublist);
}
static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
struct net *net)
{
enum skb_drop_reason reason;
const struct ipv6hdr *hdr;
u32 pkt_len;
struct inet6_dev *idev;
if (skb->pkt_type == PACKET_OTHERHOST) {
dev_core_stats_rx_otherhost_dropped_inc(skb->dev);
kfree_skb_reason(skb, SKB_DROP_REASON_OTHERHOST);
return NULL;
}
rcu_read_lock();
idev = __in6_dev_get(skb->dev);
__IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_IN, skb->len);
SKB_DR_SET(reason, NOT_SPECIFIED);
if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL ||
!idev || unlikely(idev->cnf.disable_ipv6)) {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
if (idev && unlikely(idev->cnf.disable_ipv6))
SKB_DR_SET(reason, IPV6DISABLED);
goto drop;
}
memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
/*
* Store incoming device index. When the packet will
* be queued, we cannot refer to skb->dev anymore.
*
* BTW, when we send a packet for our own local address on a
* non-loopback interface (e.g. ethX), it is being delivered
* via the loopback interface (lo) here; skb->dev = loopback_dev.
* It, however, should be considered as if it is being
* arrived via the sending interface (ethX), because of the
* nature of scoping architecture. --yoshfuji
*/
IP6CB(skb)->iif = skb_valid_dst(skb) ? ip6_dst_idev(skb_dst(skb))->dev->ifindex : dev->ifindex;
if (unlikely(!pskb_may_pull(skb, sizeof(*hdr))))
goto err;
hdr = ipv6_hdr(skb);
if (hdr->version != 6) {
SKB_DR_SET(reason, UNHANDLED_PROTO);
goto err;
}
__IP6_ADD_STATS(net, idev,
IPSTATS_MIB_NOECTPKTS +
(ipv6_get_dsfield(hdr) & INET_ECN_MASK),
max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs));
/*
* RFC4291 2.5.3
* The loopback address must not be used as the source address in IPv6
* packets that are sent outside of a single node. [..]
* A packet received on an interface with a destination address
* of loopback must be dropped.
*/
if ((ipv6_addr_loopback(&hdr->saddr) ||
ipv6_addr_loopback(&hdr->daddr)) &&
!(dev->flags & IFF_LOOPBACK) &&
!netif_is_l3_master(dev))
goto err;
/* RFC4291 Errata ID: 3480
* Interface-Local scope spans only a single interface on a
* node and is useful only for loopback transmission of
* multicast. Packets with interface-local scope received
* from another node must be discarded.
*/
if (!(skb->pkt_type == PACKET_LOOPBACK ||
dev->flags & IFF_LOOPBACK) &&
ipv6_addr_is_multicast(&hdr->daddr) &&
IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 1)
goto err;
/* If enabled, drop unicast packets that were encapsulated in link-layer
* multicast or broadcast to protected against the so-called "hole-196"
* attack in 802.11 wireless.
*/
if (!ipv6_addr_is_multicast(&hdr->daddr) &&
(skb->pkt_type == PACKET_BROADCAST ||
skb->pkt_type == PACKET_MULTICAST) &&
idev->cnf.drop_unicast_in_l2_multicast) {
SKB_DR_SET(reason, UNICAST_IN_L2_MULTICAST);
goto err;
}
/* RFC4291 2.7
* Nodes must not originate a packet to a multicast address whose scope
* field contains the reserved value 0; if such a packet is received, it
* must be silently dropped.
*/
if (ipv6_addr_is_multicast(&hdr->daddr) &&
IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 0)
goto err;
/*
* RFC4291 2.7
* Multicast addresses must not be used as source addresses in IPv6
* packets or appear in any Routing header.
*/
if (ipv6_addr_is_multicast(&hdr->saddr))
goto err;
skb->transport_header = skb->network_header + sizeof(*hdr);
IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
pkt_len = ntohs(hdr->payload_len);
/* pkt_len may be zero if Jumbo payload option is present */
if (pkt_len || hdr->nexthdr != NEXTHDR_HOP) {
if (pkt_len + sizeof(struct ipv6hdr) > skb->len) {
__IP6_INC_STATS(net,
idev, IPSTATS_MIB_INTRUNCATEDPKTS);
SKB_DR_SET(reason, PKT_TOO_SMALL);
goto drop;
}
if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr)))
goto err;
hdr = ipv6_hdr(skb);
}
if (hdr->nexthdr == NEXTHDR_HOP) {
if (ipv6_parse_hopopts(skb) < 0) {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
rcu_read_unlock();
return NULL;
}
}
rcu_read_unlock();
/* Must drop socket now because of tproxy. */
if (!skb_sk_is_prefetched(skb))
skb_orphan(skb);
return skb;
err:
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
SKB_DR_OR(reason, IP_INHDR);
drop:
rcu_read_unlock();
kfree_skb_reason(skb, reason);
return NULL;
}
int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
{
struct net *net = dev_net(skb->dev);
skb = ip6_rcv_core(skb, dev, net);
if (skb == NULL)
return NET_RX_DROP;
return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING,
net, NULL, skb, dev, NULL,
ip6_rcv_finish);
}
static void ip6_sublist_rcv(struct list_head *head, struct net_device *dev,
struct net *net)
{
NF_HOOK_LIST(NFPROTO_IPV6, NF_INET_PRE_ROUTING, net, NULL,
head, dev, NULL, ip6_rcv_finish);
ip6_list_rcv_finish(net, NULL, head);
}
/* Receive a list of IPv6 packets */
void ipv6_list_rcv(struct list_head *head, struct packet_type *pt,
struct net_device *orig_dev)
{
struct net_device *curr_dev = NULL;
struct net *curr_net = NULL;
struct sk_buff *skb, *next;
struct list_head sublist;
INIT_LIST_HEAD(&sublist);
list_for_each_entry_safe(skb, next, head, list) {
struct net_device *dev = skb->dev;
struct net *net = dev_net(dev);
net: use skb_list_del_init() to remove from RX sublists list_del() leaves the skb->next pointer poisoned, which can then lead to a crash in e.g. OVS forwarding. For example, setting up an OVS VXLAN forwarding bridge on sfc as per: ======== $ ovs-vsctl show 5dfd9c47-f04b-4aaa-aa96-4fbb0a522a30 Bridge "br0" Port "br0" Interface "br0" type: internal Port "enp6s0f0" Interface "enp6s0f0" Port "vxlan0" Interface "vxlan0" type: vxlan options: {key="1", local_ip="10.0.0.5", remote_ip="10.0.0.4"} ovs_version: "2.5.0" ======== (where 10.0.0.5 is an address on enp6s0f1) and sending traffic across it will lead to the following panic: ======== general protection fault: 0000 [#1] SMP PTI CPU: 5 PID: 0 Comm: swapper/5 Not tainted 4.20.0-rc3-ehc+ #701 Hardware name: Dell Inc. PowerEdge R710/0M233H, BIOS 6.4.0 07/23/2013 RIP: 0010:dev_hard_start_xmit+0x38/0x200 Code: 53 48 89 fb 48 83 ec 20 48 85 ff 48 89 54 24 08 48 89 4c 24 18 0f 84 ab 01 00 00 48 8d 86 90 00 00 00 48 89 f5 48 89 44 24 10 <4c> 8b 33 48 c7 03 00 00 00 00 48 8b 05 c7 d1 b3 00 4d 85 f6 0f 95 RSP: 0018:ffff888627b437e0 EFLAGS: 00010202 RAX: 0000000000000000 RBX: dead000000000100 RCX: ffff88862279c000 RDX: ffff888614a342c0 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffff888618a88000 R08: 0000000000000001 R09: 00000000000003e8 R10: 0000000000000000 R11: ffff888614a34140 R12: 0000000000000000 R13: 0000000000000062 R14: dead000000000100 R15: ffff888616430000 FS: 0000000000000000(0000) GS:ffff888627b40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f6d2bc6d000 CR3: 000000000200a000 CR4: 00000000000006e0 Call Trace: <IRQ> __dev_queue_xmit+0x623/0x870 ? masked_flow_lookup+0xf7/0x220 [openvswitch] ? ep_poll_callback+0x101/0x310 do_execute_actions+0xaba/0xaf0 [openvswitch] ? __wake_up_common+0x8a/0x150 ? __wake_up_common_lock+0x87/0xc0 ? queue_userspace_packet+0x31c/0x5b0 [openvswitch] ovs_execute_actions+0x47/0x120 [openvswitch] ovs_dp_process_packet+0x7d/0x110 [openvswitch] ovs_vport_receive+0x6e/0xd0 [openvswitch] ? dst_alloc+0x64/0x90 ? rt_dst_alloc+0x50/0xd0 ? ip_route_input_slow+0x19a/0x9a0 ? __udp_enqueue_schedule_skb+0x198/0x1b0 ? __udp4_lib_rcv+0x856/0xa30 ? __udp4_lib_rcv+0x856/0xa30 ? cpumask_next_and+0x19/0x20 ? find_busiest_group+0x12d/0xcd0 netdev_frame_hook+0xce/0x150 [openvswitch] __netif_receive_skb_core+0x205/0xae0 __netif_receive_skb_list_core+0x11e/0x220 netif_receive_skb_list+0x203/0x460 ? __efx_rx_packet+0x335/0x5e0 [sfc] efx_poll+0x182/0x320 [sfc] net_rx_action+0x294/0x3c0 __do_softirq+0xca/0x297 irq_exit+0xa6/0xb0 do_IRQ+0x54/0xd0 common_interrupt+0xf/0xf </IRQ> ======== So, in all listified-receive handling, instead pull skbs off the lists with skb_list_del_init(). Fixes: 9af86f933894 ("net: core: fix use-after-free in __netif_receive_skb_list_core") Fixes: 7da517a3bc52 ("net: core: Another step of skb receive list processing") Fixes: a4ca8b7df73c ("net: ipv4: fix drop handling in ip_list_rcv() and ip_list_rcv_finish()") Fixes: d8269e2cbf90 ("net: ipv6: listify ipv6_rcv() and ip6_rcv_finish()") Signed-off-by: Edward Cree <ecree@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-12-05 01:37:57 +08:00
skb_list_del_init(skb);
skb = ip6_rcv_core(skb, dev, net);
if (skb == NULL)
continue;
if (curr_dev != dev || curr_net != net) {
/* dispatch old sublist */
if (!list_empty(&sublist))
ip6_sublist_rcv(&sublist, curr_dev, curr_net);
/* start new sublist */
INIT_LIST_HEAD(&sublist);
curr_dev = dev;
curr_net = net;
}
list_add_tail(&skb->list, &sublist);
}
/* dispatch final sublist */
if (!list_empty(&sublist))
ip6_sublist_rcv(&sublist, curr_dev, curr_net);
}
INDIRECT_CALLABLE_DECLARE(int tcp_v6_rcv(struct sk_buff *));
/*
* Deliver the packet to the host
*/
void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr,
bool have_final)
{
const struct inet6_protocol *ipprot;
struct inet6_dev *idev;
unsigned int nhoff;
SKB_DR(reason);
bool raw;
/*
* Parse extension headers
*/
resubmit:
idev = ip6_dst_idev(skb_dst(skb));
nhoff = IP6CB(skb)->nhoff;
if (!have_final) {
if (!pskb_pull(skb, skb_transport_offset(skb)))
goto discard;
nexthdr = skb_network_header(skb)[nhoff];
}
resubmit_final:
raw = raw6_local_deliver(skb, nexthdr);
ipprot = rcu_dereference(inet6_protos[nexthdr]);
if (ipprot) {
int ret;
if (have_final) {
if (!(ipprot->flags & INET6_PROTO_FINAL)) {
/* Once we've seen a final protocol don't
* allow encapsulation on any non-final
* ones. This allows foo in UDP encapsulation
* to work.
*/
goto discard;
}
} else if (ipprot->flags & INET6_PROTO_FINAL) {
const struct ipv6hdr *hdr;
int sdif = inet6_sdif(skb);
struct net_device *dev;
/* Only do this once for first final protocol */
have_final = true;
[NETFILTER]: Add nf_conntrack subsystem. The existing connection tracking subsystem in netfilter can only handle ipv4. There were basically two choices present to add connection tracking support for ipv6. We could either duplicate all of the ipv4 connection tracking code into an ipv6 counterpart, or (the choice taken by these patches) we could design a generic layer that could handle both ipv4 and ipv6 and thus requiring only one sub-protocol (TCP, UDP, etc.) connection tracking helper module to be written. In fact nf_conntrack is capable of working with any layer 3 protocol. The existing ipv4 specific conntrack code could also not deal with the pecularities of doing connection tracking on ipv6, which is also cured here. For example, these issues include: 1) ICMPv6 handling, which is used for neighbour discovery in ipv6 thus some messages such as these should not participate in connection tracking since effectively they are like ARP messages 2) fragmentation must be handled differently in ipv6, because the simplistic "defrag, connection track and NAT, refrag" (which the existing ipv4 connection tracking does) approach simply isn't feasible in ipv6 3) ipv6 extension header parsing must occur at the correct spots before and after connection tracking decisions, and there were no provisions for this in the existing connection tracking design 4) ipv6 has no need for stateful NAT The ipv4 specific conntrack layer is kept around, until all of the ipv4 specific conntrack helpers are ported over to nf_conntrack and it is feature complete. Once that occurs, the old conntrack stuff will get placed into the feature-removal-schedule and we will fully kill it off 6 months later. Signed-off-by: Yasuyuki Kozakai <yasuyuki.kozakai@toshiba.co.jp> Signed-off-by: Harald Welte <laforge@netfilter.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
2005-11-10 08:38:16 +08:00
/* Free reference early: we don't need it any more,
and it may hold ip_conntrack module loaded
indefinitely. */
nf_reset_ct(skb);
[NETFILTER]: Add nf_conntrack subsystem. The existing connection tracking subsystem in netfilter can only handle ipv4. There were basically two choices present to add connection tracking support for ipv6. We could either duplicate all of the ipv4 connection tracking code into an ipv6 counterpart, or (the choice taken by these patches) we could design a generic layer that could handle both ipv4 and ipv6 and thus requiring only one sub-protocol (TCP, UDP, etc.) connection tracking helper module to be written. In fact nf_conntrack is capable of working with any layer 3 protocol. The existing ipv4 specific conntrack code could also not deal with the pecularities of doing connection tracking on ipv6, which is also cured here. For example, these issues include: 1) ICMPv6 handling, which is used for neighbour discovery in ipv6 thus some messages such as these should not participate in connection tracking since effectively they are like ARP messages 2) fragmentation must be handled differently in ipv6, because the simplistic "defrag, connection track and NAT, refrag" (which the existing ipv4 connection tracking does) approach simply isn't feasible in ipv6 3) ipv6 extension header parsing must occur at the correct spots before and after connection tracking decisions, and there were no provisions for this in the existing connection tracking design 4) ipv6 has no need for stateful NAT The ipv4 specific conntrack layer is kept around, until all of the ipv4 specific conntrack helpers are ported over to nf_conntrack and it is feature complete. Once that occurs, the old conntrack stuff will get placed into the feature-removal-schedule and we will fully kill it off 6 months later. Signed-off-by: Yasuyuki Kozakai <yasuyuki.kozakai@toshiba.co.jp> Signed-off-by: Harald Welte <laforge@netfilter.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
2005-11-10 08:38:16 +08:00
skb_postpull_rcsum(skb, skb_network_header(skb),
skb_network_header_len(skb));
hdr = ipv6_hdr(skb);
/* skb->dev passed may be master dev for vrfs. */
if (sdif) {
dev = dev_get_by_index_rcu(net, sdif);
if (!dev)
goto discard;
} else {
dev = skb->dev;
}
if (ipv6_addr_is_multicast(&hdr->daddr) &&
!ipv6_chk_mcast_addr(dev, &hdr->daddr,
&hdr->saddr) &&
!ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb))) {
SKB_DR_SET(reason, IP_INADDRERRORS);
goto discard;
}
}
if (!(ipprot->flags & INET6_PROTO_NOPOLICY) &&
!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
SKB_DR_SET(reason, XFRM_POLICY);
goto discard;
}
ret = INDIRECT_CALL_2(ipprot->handler, tcp_v6_rcv, udpv6_rcv,
skb);
if (ret > 0) {
if (ipprot->flags & INET6_PROTO_FINAL) {
/* Not an extension header, most likely UDP
* encapsulation. Use return value as nexthdr
* protocol not nhoff (which presumably is
* not set by handler).
*/
nexthdr = ret;
goto resubmit_final;
} else {
goto resubmit;
}
} else if (ret == 0) {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
}
} else {
if (!raw) {
if (xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
__IP6_INC_STATS(net, idev,
IPSTATS_MIB_INUNKNOWNPROTOS);
icmpv6_send(skb, ICMPV6_PARAMPROB,
ICMPV6_UNK_NEXTHDR, nhoff);
SKB_DR_SET(reason, IP_NOPROTO);
} else {
SKB_DR_SET(reason, XFRM_POLICY);
}
kfree_skb_reason(skb, reason);
} else {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
consume_skb(skb);
}
}
return;
discard:
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
kfree_skb_reason(skb, reason);
}
static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
skb_clear_delivery_time(skb);
rcu_read_lock();
ip6_protocol_deliver_rcu(net, skb, 0, false);
rcu_read_unlock();
return 0;
}
int ip6_input(struct sk_buff *skb)
{
2015-09-16 09:04:16 +08:00
return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_IN,
dev_net(skb->dev), NULL, skb, skb->dev, NULL,
ip6_input_finish);
}
EXPORT_SYMBOL_GPL(ip6_input);
int ip6_mc_input(struct sk_buff *skb)
{
int sdif = inet6_sdif(skb);
const struct ipv6hdr *hdr;
struct net_device *dev;
bool deliver;
__IP6_UPD_PO_STATS(dev_net(skb_dst(skb)->dev),
__in6_dev_get_safely(skb->dev), IPSTATS_MIB_INMCAST,
skb->len);
/* skb->dev passed may be master dev for vrfs. */
if (sdif) {
rcu_read_lock();
dev = dev_get_by_index_rcu(dev_net(skb->dev), sdif);
if (!dev) {
rcu_read_unlock();
kfree_skb(skb);
return -ENODEV;
}
} else {
dev = skb->dev;
}
hdr = ipv6_hdr(skb);
deliver = ipv6_chk_mcast_addr(dev, &hdr->daddr, NULL);
if (sdif)
rcu_read_unlock();
#ifdef CONFIG_IPV6_MROUTE
/*
* IPv6 multicast router mode is now supported ;)
*/
if (atomic_read(&dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding) &&
!(ipv6_addr_type(&hdr->daddr) &
(IPV6_ADDR_LOOPBACK|IPV6_ADDR_LINKLOCAL)) &&
likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) {
/*
* Okay, we try to forward - split and duplicate
* packets.
*/
struct sk_buff *skb2;
struct inet6_skb_parm *opt = IP6CB(skb);
/* Check for MLD */
if (unlikely(opt->flags & IP6SKB_ROUTERALERT)) {
/* Check if this is a mld message */
u8 nexthdr = hdr->nexthdr;
__be16 frag_off;
int offset;
/* Check if the value of Router Alert
* is for MLD (0x0000).
*/
if (opt->ra == htons(IPV6_OPT_ROUTERALERT_MLD)) {
deliver = false;
if (!ipv6_ext_hdr(nexthdr)) {
/* BUG */
goto out;
}
offset = ipv6_skip_exthdr(skb, sizeof(*hdr),
&nexthdr, &frag_off);
if (offset < 0)
goto out;
if (ipv6_is_mld(skb, nexthdr, offset))
deliver = true;
goto out;
}
/* unknown RA - process it normally */
}
if (deliver)
skb2 = skb_clone(skb, GFP_ATOMIC);
else {
skb2 = skb;
skb = NULL;
}
if (skb2) {
ip6_mr_input(skb2);
}
}
out:
#endif
if (likely(deliver))
ip6_input(skb);
else {
/* discard */
kfree_skb(skb);
}
return 0;
}