kernel_samsung_a53x/net/ipv6/xfrm6_policy.c

318 lines
6.9 KiB
C
Raw Normal View History

2024-06-15 16:02:09 -03:00
// SPDX-License-Identifier: GPL-2.0
/*
* xfrm6_policy.c: based on xfrm4_policy.c
*
* Authors:
* Mitsuru KANDA @USAGI
* Kazunori MIYAZAWA @USAGI
* Kunihiro Ishiguro <kunihiro@ipinfusion.com>
* IPv6 support
* YOSHIFUJI Hideaki
* Split up af-specific portion
*
*/
#include <linux/err.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <net/addrconf.h>
#include <net/dst.h>
#include <net/xfrm.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/ip6_route.h>
#include <net/l3mdev.h>
static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int oif,
const xfrm_address_t *saddr,
const xfrm_address_t *daddr,
u32 mark)
{
struct flowi6 fl6;
struct dst_entry *dst;
int err;
memset(&fl6, 0, sizeof(fl6));
net: Add l3mdev index to flow struct and avoid oif reset for port devices [ Upstream commit 40867d74c374b235e14d839f3a77f26684feefe5 ] The fundamental premise of VRF and l3mdev core code is binding a socket to a device (l3mdev or netdev with an L3 domain) to indicate L3 scope. Legacy code resets flowi_oif to the l3mdev losing any original port device binding. Ben (among others) has demonstrated use cases where the original port device binding is important and needs to be retained. This patch handles that by adding a new entry to the common flow struct that can indicate the l3mdev index for later rule and table matching avoiding the need to reset flowi_oif. In addition to allowing more use cases that require port device binds, this patch brings a few datapath simplications: 1. l3mdev_fib_rule_match is only called when walking fib rules and always after l3mdev_update_flow. That allows an optimization to bail early for non-VRF type uses cases when flowi_l3mdev is not set. Also, only that index needs to be checked for the FIB table id. 2. l3mdev_update_flow can be called with flowi_oif set to a l3mdev (e.g., VRF) device. By resetting flowi_oif only for this case the FLOWI_FLAG_SKIP_NH_OIF flag is not longer needed and can be removed, removing several checks in the datapath. The flowi_iif path can be simplified to only be called if the it is not loopback (loopback can not be assigned to an L3 domain) and the l3mdev index is not already set. 3. Avoid another device lookup in the output path when the fib lookup returns a reject failure. Note: 2 functional tests for local traffic with reject fib rules are updated to reflect the new direct failure at FIB lookup time for ping rather than the failure on packet path. The current code fails like this: HINT: Fails since address on vrf device is out of device scope COMMAND: ip netns exec ns-A ping -c1 -w1 -I eth1 172.16.3.1 ping: Warning: source address might be selected on device other than: eth1 PING 172.16.3.1 (172.16.3.1) from 172.16.3.1 eth1: 56(84) bytes of data. --- 172.16.3.1 ping statistics --- 1 packets transmitted, 0 received, 100% packet loss, time 0ms where the test now directly fails: HINT: Fails since address on vrf device is out of device scope COMMAND: ip netns exec ns-A ping -c1 -w1 -I eth1 172.16.3.1 ping: connect: No route to host Signed-off-by: David Ahern <dsahern@kernel.org> Tested-by: Ben Greear <greearb@candelatech.com> Link: https://lore.kernel.org/r/20220314204551.16369-1-dsahern@kernel.org Signed-off-by: Jakub Kicinski <kuba@kernel.org> Stable-dep-of: 05ef7055debc ("netfilter: fib: check correct rtable in vrf setups") Signed-off-by: Sasha Levin <sashal@kernel.org>
2022-03-14 14:45:51 -06:00
fl6.flowi6_l3mdev = l3mdev_master_ifindex_by_index(net, oif);
2024-06-15 16:02:09 -03:00
fl6.flowi6_mark = mark;
memcpy(&fl6.daddr, daddr, sizeof(fl6.daddr));
if (saddr)
memcpy(&fl6.saddr, saddr, sizeof(fl6.saddr));
dst = ip6_route_output(net, NULL, &fl6);
err = dst->error;
if (dst->error) {
dst_release(dst);
dst = ERR_PTR(err);
}
return dst;
}
static int xfrm6_get_saddr(struct net *net, int oif,
xfrm_address_t *saddr, xfrm_address_t *daddr,
u32 mark)
{
struct dst_entry *dst;
struct net_device *dev;
xfrm6: check ip6_dst_idev() return value in xfrm6_get_saddr() [ Upstream commit d46401052c2d5614da8efea5788532f0401cb164 ] ip6_dst_idev() can return NULL, xfrm6_get_saddr() must act accordingly. syzbot reported: Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] PREEMPT SMP KASAN PTI KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] CPU: 1 PID: 12 Comm: kworker/u8:1 Not tainted 6.10.0-rc2-syzkaller-00383-gb8481381d4e2 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/02/2024 Workqueue: wg-kex-wg1 wg_packet_handshake_send_worker RIP: 0010:xfrm6_get_saddr+0x93/0x130 net/ipv6/xfrm6_policy.c:64 Code: df 48 89 fa 48 c1 ea 03 80 3c 02 00 0f 85 97 00 00 00 4c 8b ab d8 00 00 00 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 <80> 3c 02 00 0f 85 86 00 00 00 4d 8b 6d 00 e8 ca 13 47 01 48 b8 00 RSP: 0018:ffffc90000117378 EFLAGS: 00010246 RAX: dffffc0000000000 RBX: ffff88807b079dc0 RCX: ffffffff89a0d6d7 RDX: 0000000000000000 RSI: ffffffff89a0d6e9 RDI: ffff88807b079e98 RBP: ffff88807ad73248 R08: 0000000000000007 R09: fffffffffffff000 R10: ffff88807b079dc0 R11: 0000000000000007 R12: ffffc90000117480 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff8880b9300000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f4586d00440 CR3: 0000000079042000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> xfrm_get_saddr net/xfrm/xfrm_policy.c:2452 [inline] xfrm_tmpl_resolve_one net/xfrm/xfrm_policy.c:2481 [inline] xfrm_tmpl_resolve+0xa26/0xf10 net/xfrm/xfrm_policy.c:2541 xfrm_resolve_and_create_bundle+0x140/0x2570 net/xfrm/xfrm_policy.c:2835 xfrm_bundle_lookup net/xfrm/xfrm_policy.c:3070 [inline] xfrm_lookup_with_ifid+0x4d1/0x1e60 net/xfrm/xfrm_policy.c:3201 xfrm_lookup net/xfrm/xfrm_policy.c:3298 [inline] xfrm_lookup_route+0x3b/0x200 net/xfrm/xfrm_policy.c:3309 ip6_dst_lookup_flow+0x15c/0x1d0 net/ipv6/ip6_output.c:1256 send6+0x611/0xd20 drivers/net/wireguard/socket.c:139 wg_socket_send_skb_to_peer+0xf9/0x220 drivers/net/wireguard/socket.c:178 wg_socket_send_buffer_to_peer+0x12b/0x190 drivers/net/wireguard/socket.c:200 wg_packet_send_handshake_initiation+0x227/0x360 drivers/net/wireguard/send.c:40 wg_packet_handshake_send_worker+0x1c/0x30 drivers/net/wireguard/send.c:51 process_one_work+0x9fb/0x1b60 kernel/workqueue.c:3231 process_scheduled_works kernel/workqueue.c:3312 [inline] worker_thread+0x6c8/0xf70 kernel/workqueue.c:3393 kthread+0x2c1/0x3a0 kernel/kthread.c:389 ret_from_fork+0x45/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Reviewed-by: David Ahern <dsahern@kernel.org> Link: https://lore.kernel.org/r/20240615154231.234442-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-06-15 15:42:31 +00:00
struct inet6_dev *idev;
2024-06-15 16:02:09 -03:00
dst = xfrm6_dst_lookup(net, 0, oif, NULL, daddr, mark);
if (IS_ERR(dst))
return -EHOSTUNREACH;
xfrm6: check ip6_dst_idev() return value in xfrm6_get_saddr() [ Upstream commit d46401052c2d5614da8efea5788532f0401cb164 ] ip6_dst_idev() can return NULL, xfrm6_get_saddr() must act accordingly. syzbot reported: Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] PREEMPT SMP KASAN PTI KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] CPU: 1 PID: 12 Comm: kworker/u8:1 Not tainted 6.10.0-rc2-syzkaller-00383-gb8481381d4e2 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/02/2024 Workqueue: wg-kex-wg1 wg_packet_handshake_send_worker RIP: 0010:xfrm6_get_saddr+0x93/0x130 net/ipv6/xfrm6_policy.c:64 Code: df 48 89 fa 48 c1 ea 03 80 3c 02 00 0f 85 97 00 00 00 4c 8b ab d8 00 00 00 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 <80> 3c 02 00 0f 85 86 00 00 00 4d 8b 6d 00 e8 ca 13 47 01 48 b8 00 RSP: 0018:ffffc90000117378 EFLAGS: 00010246 RAX: dffffc0000000000 RBX: ffff88807b079dc0 RCX: ffffffff89a0d6d7 RDX: 0000000000000000 RSI: ffffffff89a0d6e9 RDI: ffff88807b079e98 RBP: ffff88807ad73248 R08: 0000000000000007 R09: fffffffffffff000 R10: ffff88807b079dc0 R11: 0000000000000007 R12: ffffc90000117480 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff8880b9300000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f4586d00440 CR3: 0000000079042000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> xfrm_get_saddr net/xfrm/xfrm_policy.c:2452 [inline] xfrm_tmpl_resolve_one net/xfrm/xfrm_policy.c:2481 [inline] xfrm_tmpl_resolve+0xa26/0xf10 net/xfrm/xfrm_policy.c:2541 xfrm_resolve_and_create_bundle+0x140/0x2570 net/xfrm/xfrm_policy.c:2835 xfrm_bundle_lookup net/xfrm/xfrm_policy.c:3070 [inline] xfrm_lookup_with_ifid+0x4d1/0x1e60 net/xfrm/xfrm_policy.c:3201 xfrm_lookup net/xfrm/xfrm_policy.c:3298 [inline] xfrm_lookup_route+0x3b/0x200 net/xfrm/xfrm_policy.c:3309 ip6_dst_lookup_flow+0x15c/0x1d0 net/ipv6/ip6_output.c:1256 send6+0x611/0xd20 drivers/net/wireguard/socket.c:139 wg_socket_send_skb_to_peer+0xf9/0x220 drivers/net/wireguard/socket.c:178 wg_socket_send_buffer_to_peer+0x12b/0x190 drivers/net/wireguard/socket.c:200 wg_packet_send_handshake_initiation+0x227/0x360 drivers/net/wireguard/send.c:40 wg_packet_handshake_send_worker+0x1c/0x30 drivers/net/wireguard/send.c:51 process_one_work+0x9fb/0x1b60 kernel/workqueue.c:3231 process_scheduled_works kernel/workqueue.c:3312 [inline] worker_thread+0x6c8/0xf70 kernel/workqueue.c:3393 kthread+0x2c1/0x3a0 kernel/kthread.c:389 ret_from_fork+0x45/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Reviewed-by: David Ahern <dsahern@kernel.org> Link: https://lore.kernel.org/r/20240615154231.234442-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-06-15 15:42:31 +00:00
idev = ip6_dst_idev(dst);
if (!idev) {
dst_release(dst);
return -EHOSTUNREACH;
}
dev = idev->dev;
2024-06-15 16:02:09 -03:00
ipv6_dev_get_saddr(dev_net(dev), dev, &daddr->in6, 0, &saddr->in6);
dst_release(dst);
return 0;
}
static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
const struct flowi *fl)
{
struct rt6_info *rt = (struct rt6_info *)xdst->route;
xdst->u.dst.dev = dev;
dev_hold(dev);
xdst->u.rt6.rt6i_idev = in6_dev_get(dev);
if (!xdst->u.rt6.rt6i_idev) {
dev_put(dev);
return -ENODEV;
}
/* Sheit... I remember I did this right. Apparently,
* it was magically lost, so this code needs audit */
xdst->u.rt6.rt6i_flags = rt->rt6i_flags & (RTF_ANYCAST |
RTF_LOCAL);
xdst->route_cookie = rt6_get_cookie(rt);
xdst->u.rt6.rt6i_gateway = rt->rt6i_gateway;
xdst->u.rt6.rt6i_dst = rt->rt6i_dst;
xdst->u.rt6.rt6i_src = rt->rt6i_src;
INIT_LIST_HEAD(&xdst->u.rt6.rt6i_uncached);
rt6_uncached_list_add(&xdst->u.rt6);
atomic_inc(&dev_net(dev)->ipv6.rt6_stats->fib_rt_uncache);
return 0;
}
static void xfrm6_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu,
bool confirm_neigh)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
struct dst_entry *path = xdst->route;
path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh);
}
static void xfrm6_redirect(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
struct dst_entry *path = xdst->route;
path->ops->redirect(path, sk, skb);
}
static void xfrm6_dst_destroy(struct dst_entry *dst)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
if (likely(xdst->u.rt6.rt6i_idev))
in6_dev_put(xdst->u.rt6.rt6i_idev);
2024-06-15 16:02:09 -03:00
dst_destroy_metrics_generic(dst);
if (xdst->u.rt6.rt6i_uncached_list)
rt6_uncached_list_del(&xdst->u.rt6);
xfrm_dst_destroy(xdst);
}
static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
int unregister)
{
struct xfrm_dst *xdst;
if (!unregister)
return;
xdst = (struct xfrm_dst *)dst;
if (xdst->u.rt6.rt6i_idev->dev == dev) {
struct inet6_dev *loopback_idev =
in6_dev_get(dev_net(dev)->loopback_dev);
do {
in6_dev_put(xdst->u.rt6.rt6i_idev);
xdst->u.rt6.rt6i_idev = loopback_idev;
in6_dev_hold(loopback_idev);
xdst = (struct xfrm_dst *)xfrm_dst_child(&xdst->u.dst);
} while (xdst->u.dst.xfrm);
__in6_dev_put(loopback_idev);
}
xfrm_dst_ifdown(dst, dev);
}
static struct dst_ops xfrm6_dst_ops_template = {
.family = AF_INET6,
.update_pmtu = xfrm6_update_pmtu,
.redirect = xfrm6_redirect,
.cow_metrics = dst_cow_metrics_generic,
.destroy = xfrm6_dst_destroy,
.ifdown = xfrm6_dst_ifdown,
.local_out = __ip6_local_out,
.gc_thresh = 32768,
};
static const struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
.dst_ops = &xfrm6_dst_ops_template,
.dst_lookup = xfrm6_dst_lookup,
.get_saddr = xfrm6_get_saddr,
.fill_dst = xfrm6_fill_dst,
.blackhole_route = ip6_blackhole_route,
};
static int __init xfrm6_policy_init(void)
{
return xfrm_policy_register_afinfo(&xfrm6_policy_afinfo, AF_INET6);
}
static void xfrm6_policy_fini(void)
{
xfrm_policy_unregister_afinfo(&xfrm6_policy_afinfo);
}
#ifdef CONFIG_SYSCTL
static struct ctl_table xfrm6_policy_table[] = {
{
.procname = "xfrm6_gc_thresh",
.data = &init_net.xfrm.xfrm6_dst_ops.gc_thresh,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{ }
};
static int __net_init xfrm6_net_sysctl_init(struct net *net)
{
struct ctl_table *table;
struct ctl_table_header *hdr;
table = xfrm6_policy_table;
if (!net_eq(net, &init_net)) {
table = kmemdup(table, sizeof(xfrm6_policy_table), GFP_KERNEL);
if (!table)
goto err_alloc;
table[0].data = &net->xfrm.xfrm6_dst_ops.gc_thresh;
}
hdr = register_net_sysctl(net, "net/ipv6", table);
if (!hdr)
goto err_reg;
net->ipv6.sysctl.xfrm6_hdr = hdr;
return 0;
err_reg:
if (!net_eq(net, &init_net))
kfree(table);
err_alloc:
return -ENOMEM;
}
static void __net_exit xfrm6_net_sysctl_exit(struct net *net)
{
struct ctl_table *table;
if (!net->ipv6.sysctl.xfrm6_hdr)
return;
table = net->ipv6.sysctl.xfrm6_hdr->ctl_table_arg;
unregister_net_sysctl_table(net->ipv6.sysctl.xfrm6_hdr);
if (!net_eq(net, &init_net))
kfree(table);
}
#else /* CONFIG_SYSCTL */
static inline int xfrm6_net_sysctl_init(struct net *net)
{
return 0;
}
static inline void xfrm6_net_sysctl_exit(struct net *net)
{
}
#endif
static int __net_init xfrm6_net_init(struct net *net)
{
int ret;
memcpy(&net->xfrm.xfrm6_dst_ops, &xfrm6_dst_ops_template,
sizeof(xfrm6_dst_ops_template));
ret = dst_entries_init(&net->xfrm.xfrm6_dst_ops);
if (ret)
return ret;
ret = xfrm6_net_sysctl_init(net);
if (ret)
dst_entries_destroy(&net->xfrm.xfrm6_dst_ops);
return ret;
}
static void __net_exit xfrm6_net_exit(struct net *net)
{
xfrm6_net_sysctl_exit(net);
dst_entries_destroy(&net->xfrm.xfrm6_dst_ops);
}
static struct pernet_operations xfrm6_net_ops = {
.init = xfrm6_net_init,
.exit = xfrm6_net_exit,
};
int __init xfrm6_init(void)
{
int ret;
ret = xfrm6_policy_init();
if (ret)
goto out;
ret = xfrm6_state_init();
if (ret)
goto out_policy;
ret = xfrm6_protocol_init();
if (ret)
goto out_state;
ret = register_pernet_subsys(&xfrm6_net_ops);
if (ret)
goto out_protocol;
out:
return ret;
out_protocol:
xfrm6_protocol_fini();
out_state:
xfrm6_state_fini();
out_policy:
xfrm6_policy_fini();
goto out;
}
void xfrm6_fini(void)
{
unregister_pernet_subsys(&xfrm6_net_ops);
xfrm6_protocol_fini();
xfrm6_policy_fini();
xfrm6_state_fini();
}