KFENCE: use-after-free read in udp_tunnel_nic_device_sync_work
Subsystems (2)
Hello,
I hit a reproducible use-after-free in the UDP tunnel NIC offload work item. The original local crash was reported by KFENCE as:
KFENCE: use-after-free read in udp_tunnel_nic_device_sync_work
On current mainline, the C reproducer below triggers the same lifetime bug, reported by KASAN before KFENCE samples the object:
BUG: KASAN: slab-use-after-free in __mutex_lock Workqueue: udp_tunnel_nic udp_tunnel_nic_device_sync_work
Tested kernel:
840ef6c78e6a ("Merge tag 'nfs-for-7.2-1' of git://git.linux-nfs.org/projects/anna/linux-nfs")
Linux 7.1.0-11240-g840ef6c78e6a #31 SMP PREEMPT_DYNAMIC
Related syzbot reports:
https://syzkaller.appspot.com/bug?id=8d8fd27ae4339074afe3f456be73b2030d795256
The dashboard currently marks it as invalid, but the same issue is still reproducible for me on current mainline with the C reproducer pasted below.
Crash stack from the latest C reproducer run:
[ 131.757233][ T12] BUG: KASAN: slab-use-after-free in __mutex_lock+0x16d0/0x1d80 [ 131.759738][ T12] Read of size 8 at addr ff11000065dcd2a8 by task kworker/u16:0/12 [ 131.762204][ T12] [ 131.762956][ T12] CPU: 2 UID: 0 PID: 12 Comm: kworker/u16:0 Not tainted 7.1.0-11240-g840ef6c78e6a #31 PREEMPT(full) [ 131.762997][ T12] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 [ 131.763020][ T12] Workqueue: udp_tunnel_nic udp_tunnel_nic_device_sync_work [ 131.763064][ T12] Call Trace: [ 131.763076][ T12] <TASK> [ 131.763089][ T12] dump_stack_lvl+0x116/0x1b0 [ 131.763136][ T12] print_report+0xf1/0x5c0 [ 131.763178][ T12] ? __virt_addr_valid+0x238/0x420 [ 131.763214][ T12] ? __mutex_lock+0x16d0/0x1d80 [ 131.763264][ T12] kasan_report+0xca/0x100 [ 131.763301][ T12] ? __mutex_lock+0x16d0/0x1d80 [ 131.763345][ T12] __mutex_lock+0x16d0/0x1d80 [ 131.763383][ T12] ? udp_tunnel_nic_device_sync_work+0x32/0x9c0 [ 131.763438][ T12] ? __pfx___mutex_lock+0x10/0x10 [ 131.763487][ T12] ? debug_object_deactivate+0x213/0x390 [ 131.763551][ T12] ? udp_tunnel_nic_device_sync_work+0x32/0x9c0 [ 131.763587][ T12] udp_tunnel_nic_device_sync_work+0x32/0x9c0 [ 131.763633][ T12] process_one_work+0x9de/0x1bf0 [ 131.763670][ T12] ? __pfx_udp_tunnel_nic_device_sync_work+0x10/0x10 [ 131.763710][ T12] ? __pfx_process_one_work+0x10/0x10 [ 131.763747][ T12] ? __pfx_udp_tunnel_nic_device_sync_work+0x10/0x10 [ 131.763787][ T12] worker_thread+0x693/0xeb0 [ 131.763823][ T12] ? __pfx_worker_thread+0x10/0x10 [ 131.763855][ T12] kthread+0x38d/0x4a0 [ 131.763903][ T12] ? __pfx_kthread+0x10/0x10 [ 131.763953][ T12] ret_from_fork+0xb09/0xdb0 [ 131.763997][ T12] ? __pfx_ret_from_fork+0x10/0x10 [ 131.764037][ T12] ? __pfx_kthread+0x10/0x10 [ 131.764082][ T12] ? kthread_affine_node+0x210/0x230 [ 131.764131][ T12] ? __switch_to+0x7a7/0x10e0 [ 131.764174][ T12] ? __pfx_kthread+0x10/0x10 [ 131.764221][ T12] ret_from_fork_asm+0x1a/0x30 [ 131.764269][ T12] </TASK> [ 131.764280][ T12] [ 131.810468][ T12] Allocated by task 10356: [ 131.811305][ T12] kasan_save_stack+0x24/0x50 [ 131.812187][ T12] kasan_save_track+0x14/0x30 [ 131.813069][ T12] __kasan_kmalloc+0xaa/0xb0 [ 131.813959][ T12] __kmalloc_noprof+0x345/0x7f0 [ 131.814882][ T12] udp_tunnel_nic_netdevice_event+0x1285/0x1de0 [ 131.816061][ T12] notifier_call_chain+0xbd/0x430 [ 131.817014][ T12] call_netdevice_notifiers_info+0xbe/0x110 [ 131.819862][ T12] register_netdevice+0x197c/0x2440 [ 131.820868][ T12] nsim_create+0xcd5/0x14b0 [ 131.821733][ T12] __nsim_dev_port_add+0x3c2/0x900 [ 131.822701][ T12] nsim_dev_reload_up+0x42c/0x6a0 [ 131.823584][ T12] devlink_reload+0x2e3/0x7b0 [ 131.824421][ T12] devlink_nl_reload_doit+0x541/0x1160 [ 131.825385][ T12] genl_family_rcv_msg_doit+0x1ff/0x2f0 [ 131.826358][ T12] genl_rcv_msg+0x532/0x7e0 [ 131.827159][ T12] netlink_rcv_skb+0x147/0x430 [ 131.828017][ T12] genl_rcv+0x28/0x40 [ 131.828724][ T12] netlink_unicast+0x58d/0x850 [ 131.829582][ T12] netlink_sendmsg+0x88d/0xd90 [ 131.830439][ T12] ____sys_sendmsg+0xa27/0xb90 [ 131.831286][ T12] ___sys_sendmsg+0x11c/0x1b0 [ 131.832106][ T12] __sys_sendmsg+0x142/0x1f0 [ 131.832927][ T12] do_syscall_64+0x11f/0x860 [ 131.833745][ T12] entry_SYSCALL_64_after_hwframe+0x77/0x7f [ 131.834791][ T12] [ 131.835206][ T12] Freed by task 10421: [ 131.835916][ T12] kasan_save_stack+0x24/0x50 [ 131.836742][ T12] kasan_save_track+0x14/0x30 [ 131.837564][ T12] kasan_save_free_info+0x3b/0x60 [ 131.838465][ T12] __kasan_slab_free+0x61/0x80 [ 131.839314][ T12] kfree+0x2ca/0x6d0 [ 131.840008][ T12] udp_tunnel_nic_netdevice_event+0xc24/0x1de0 [ 131.841080][ T12] notifier_call_chain+0xbd/0x430 [ 131.841981][ T12] call_netdevice_notifiers_info+0xbe/0x110 [ 131.843022][ T12] unregister_netdevice_many_notify+0xbab/0x2130 [ 131.844129][ T12] unregister_netdevice_queue+0x305/0x3c0 [ 131.845132][ T12] nsim_destroy+0x231/0x980 [ 131.845960][ T12] __nsim_dev_port_del+0x197/0x2c0 [ 131.846860][ T12] nsim_dev_reload_destroy+0x105/0x490 [ 131.847823][ T12] nsim_dev_reload_down+0x67/0xd0 [ 131.848707][ T12] devlink_reload+0x197/0x7b0 [ 131.849545][ T12] devlink_nl_reload_doit+0x541/0x1160 [ 131.850517][ T12] genl_family_rcv_msg_doit+0x1ff/0x2f0 [ 131.851489][ T12] genl_rcv_msg+0x532/0x7e0 [ 131.852282][ T12] netlink_rcv_skb+0x147/0x430 [ 131.853130][ T12] genl_rcv+0x28/0x40 [ 131.853836][ T12] netlink_unicast+0x58d/0x850 [ 131.854689][ T12] netlink_sendmsg+0x88d/0xd90 [ 131.855497][ T12] ____sys_sendmsg+0xa27/0xb90 [ 131.856293][ T12] ___sys_sendmsg+0x11c/0x1b0 [ 131.857067][ T12] __sys_sendmsg+0x142/0x1f0 [ 131.857826][ T12] do_syscall_64+0x11f/0x860 [ 131.858605][ T12] entry_SYSCALL_64_after_hwframe+0x77/0x7f [ 131.859579][ T12] [ 131.859971][ T12] Last potentially related work creation: [ 131.860910][ T12] kasan_save_stack+0x24/0x50 [ 131.861694][ T12] kasan_record_aux_stack+0xa7/0xc0 [ 131.862563][ T12] insert_work+0x36/0x230 [ 131.863276][ T12] __queue_work+0x474/0x12a0 [ 131.864038][ T12] queue_work_on+0x11c/0x140 [ 131.864800][ T12] __udp_tunnel_nic_del_port+0x2a5/0x350 [ 131.865733][ T12] udp_tunnel_notify_del_rx_port+0x228/0x410 [ 131.866698][ T12] __geneve_sock_release.part.0+0x13b/0x1d0 [ 131.867583][ T12] geneve_sock_release+0x165/0x2c0 [ 131.868346][ T12] geneve_stop+0x19c/0x200 [ 131.869001][ T12] __dev_close_many+0x350/0x720 [ 131.869733][ T12] __dev_change_flags+0x301/0x860 [ 131.870474][ T12] netif_change_flags+0x8e/0x170 [ 131.871208][ T12] do_setlink.constprop.0+0xac0/0x3f80 [ 131.872011][ T12] rtnl_newlink+0x17e7/0x1f30 [ 131.872711][ T12] rtnetlink_rcv_msg+0x9e8/0xfa0 [ 131.873455][ T12] netlink_rcv_skb+0x147/0x430 [ 131.874207][ T12] netlink_unicast+0x58d/0x850 [ 131.874959][ T12] netlink_sendmsg+0x88d/0xd90 [ 131.875685][ T12] ____sys_sendmsg+0xa27/0xb90 [ 131.876406][ T12] ___sys_sendmsg+0x11c/0x1b0 [ 131.877102][ T12] __sys_sendmsg+0x142/0x1f0 [ 131.877803][ T12] do_syscall_64+0x11f/0x860 [ 131.878505][ T12] entry_SYSCALL_64_after_hwframe+0x77/0x7f [ 131.879297][ T12] [ 131.879611][ T12] Second to last potentially related work creation: [ 131.880480][ T12] kasan_save_stack+0x24/0x50 [ 131.881112][ T12] kasan_record_aux_stack+0xa7/0xc0 [ 131.881818][ T12] insert_work+0x36/0x230 [ 131.882403][ T12] __queue_work+0x474/0x12a0 [ 131.883019][ T12] queue_work_on+0x11c/0x140 [ 131.883634][ T12] __udp_tunnel_nic_add_port+0x6e4/0xd90 [ 131.884385][ T12] udp_tunnel_notify_add_rx_port+0x228/0x410 [ 131.885199][ T12] geneve_sock_add+0x7a3/0xb60 [ 131.885844][ T12] geneve_open+0xde/0x1d0 [ 131.886435][ T12] __dev_open+0x3b8/0x900 [ 131.887017][ T12] __dev_change_flags+0x58f/0x860 [ 131.887692][ T12] netif_change_flags+0x8e/0x170 [ 131.888389][ T12] do_setlink.constprop.0+0xac0/0x3f80 [ 131.889130][ T12] rtnl_newlink+0x17e7/0x1f30 [ 131.889774][ T12] rtnetlink_rcv_msg+0x9e8/0xfa0 [ 131.890455][ T12] netlink_rcv_skb+0x147/0x430 [ 131.891065][ T12] netlink_unicast+0x58d/0x850 [ 131.891654][ T12] netlink_sendmsg+0x88d/0xd90 [ 131.892251][ T12] ____sys_sendmsg+0xa27/0xb90 [ 131.892837][ T12] ___sys_sendmsg+0x11c/0x1b0 [ 131.893412][ T12] __sys_sendmsg+0x142/0x1f0 [ 131.893988][ T12] do_syscall_64+0x11f/0x860 [ 131.894559][ T12] entry_SYSCALL_64_after_hwframe+0x77/0x7f [ 131.895275][ T12] [ 131.895564][ T12] The buggy address belongs to the object at ff11000065dcd200 [ 131.895564][ T12] which belongs to the cache kmalloc-256 of size 256 [ 131.897253][ T12] The buggy address is located 168 bytes inside of [ 131.897253][ T12] freed 256-byte region [ff11000065dcd200, ff11000065dcd300) [ 131.898932][ T12] [ 131.899228][ T12] The buggy address belongs to the physical page: [ 131.900013][ T12] page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x65dcc [ 131.901089][ T12] head: order:1 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0 [ 131.902125][ T12] flags: 0xfff00000000040(head|node=0|zone=1|lastcpupid=0x7ff) [ 131.903017][ T12] page_type: f5(slab) [ 131.903477][ T12] raw: 00fff00000000040 ff11000100038b40 dead000000000100 dead000000000122 [ 131.904457][ T12] raw: 0000000000000000 0000000800100010 00000000f5000000 0000000000000000 [ 131.905422][ T12] head: 00fff00000000040 ff11000100038b40 dead000000000100 dead000000000122 [ 131.906405][ T12] head: 0000000000000000 0000000800100010 00000000f5000000 0000000000000000 [ 131.907388][ T12] head: 00fff00000000001 ffffffffffffff81 00000000ffffffff 00000000ffffffff [ 131.908365][ T12] head: ffffffffffffffff 0000000000000000 00000000ffffffff 0000000000000002 [ 131.909334][ T12] page dumped because: kasan: bad access detected [ 131.910076][ T12] page_owner tracks the page as allocated [ 131.910720][ T12] page last allocated via order 1, migratetype Unmovable, gfp_mask 0xd20c0(__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC), pid 9905, tgid 9901 (repro), ts 81743543441, free_ts 81726980842 [ 131.913040][ T12] post_alloc_hook+0xff/0x130 [ 131.913579][ T12] get_page_from_freelist+0xe82/0x2bf0 [ 131.914216][ T12] __alloc_frozen_pages_noprof+0x27b/0x2a00 [ 131.914849][ T12] new_slab+0xad/0x610 [ 131.915190][ T12] refill_objects+0x10e/0x3d0 [ 131.915587][ T12] __pcs_replace_empty_main+0x352/0x670 [ 131.916050][ T12] __kmalloc_noprof+0x65e/0x7f0 [ 131.916458][ T12] ops_init+0x77/0x5f0 [ 131.916799][ T12] setup_net+0x11a/0x3a0 [ 131.917155][ T12] copy_net_ns+0x351/0x7c0 [ 131.917530][ T12] create_new_namespaces+0x3f6/0xac0 [ 131.917984][ T12] copy_namespaces+0x45c/0x580 [ 131.918389][ T12] copy_process+0x3687/0x7d40 [ 131.918788][ T12] kernel_clone+0x1f6/0x910 [ 131.919183][ T12] __do_sys_clone+0xce/0x120 [ 131.919575][ T12] do_syscall_64+0x11f/0x860 [ 131.919969][ T12] page last free pid 9905 tgid 9901 stack trace: [ 131.920496][ T12] __free_frozen_pages+0x74d/0x1110 [ 131.920930][ T12] qlist_free_all+0x4c/0xf0 [ 131.921327][ T12] kasan_quarantine_reduce+0x195/0x1e0 [ 131.921791][ T12] __kasan_slab_alloc+0x67/0x90 [ 131.922202][ T12] kmem_cache_alloc_noprof+0x244/0x690 [ 131.922665][ T12] security_inode_alloc+0x3e/0x2d0 [ 131.923099][ T12] inode_init_always_gfp+0xc77/0xfb0 [ 131.923562][ T12] alloc_inode+0x8e/0x250 [ 131.923930][ T12] new_inode+0x22/0x1d0 [ 131.924284][ T12] __debugfs_create_file+0x10b/0x540 [ 131.924737][ T12] debugfs_create_file_full+0x41/0x60 [ 131.925189][ T12] ref_tracker_dir_debugfs+0x18c/0x2e0 [ 131.925658][ T12] alloc_netdev_mqs+0x31f/0x1600 [ 131.926078][ T12] ip6_tnl_init_net+0x12f/0x4c0 [ 131.926491][ T12] ops_init+0x1e2/0x5f0 [ 131.926843][ T12] setup_net+0x11a/0x3a0 [ 131.927201][ T12] [ 131.927399][ T12] Memory state around the buggy address: [ 131.927873][ T12] ff11000065dcd180: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 131.928542][ T12] ff11000065dcd200: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 131.929231][ T12] >ff11000065dcd280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 131.929902][ T12] ^ [ 131.930375][ T12] ff11000065dcd300: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 131.931050][ T12] ff11000065dcd380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 131.931723][ T12] ================================================================== [ 131.932651][ T12] Kernel panic - not syncing: KASAN: panic_on_warn set ... [ 131.933267][ T12] CPU: 2 UID: 0 PID: 12 Comm: kworker/u16:0 Not tainted 7.1.0-11240-g840ef6c78e6a #31 PREEMPT(full) [ 131.934181][ T12] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 [ 131.934965][ T12] Workqueue: udp_tunnel_nic udp_tunnel_nic_device_sync_work [ 131.935585][ T12] Call Trace: [ 131.935865][ T12] <TASK>
The reproducer creates netdevsim/geneve devices and drives a devlink reload while UDP tunnel offload notifications are being queued. A queued udp_tunnel_nic_device_sync_work item later runs with its embedded work_struct inside struct udp_tunnel_nic, but that struct has already been freed from the NETDEV_UNREGISTER path. The first dereference in the worker is the mutex lock:
udp_tunnel_nic_device_sync_work()
rtnl_lock();
mutex_lock(&utn->lock);KASAN reports the read from the freed object at that mutex access.
Possible root cause analysis:
The lifetime of struct udp_tunnel_nic appears to be guarded only by the utn->work_pending flag, but that flag is not a safe lifetime barrier for the queued work:
udp_tunnel_nic_device_sync()
queue_work(udp_tunnel_nic_workqueue, &utn->work);
utn->work_pending = 1;
udp_tunnel_nic_unregister()
udp_tunnel_nic_flush(dev, utn);
udp_tunnel_nic_unlock(dev);
if (utn->work_pending)
return;
udp_tunnel_nic_free(utn);The work is queued before work_pending is set, so unregister can observe work_pending == 0 and free utn while the work is already queued or starting. Also, work_pending is only a flag in the object being protected; it is not a reference, cancel_work_sync(), or flush_work() style guarantee that the worker no longer owns or can dereference the containing object. Once udp_tunnel_nic_free() runs, the embedded work item can still call container_of(work, struct udp_tunnel_nic, work) and dereference the freed utn, which matches the alloc/free/use stacks above.
A fix should make unregister synchronize with the embedded work or otherwise hold a real lifetime reference while the work is queued/running. In particular, freeing utn based solely on work_pending looks racy.
If you have any questions, please let me know.
Best regards,
Yue
Build/run:
gcc -pthread -static -O2 repro.c -o repro
./repro
C reproducer:
// autogenerated by syzkaller (https://github.com/google/syzkaller)
#define _GNU_SOURCE
#include <arpa/inet.h>
#include <dirent.h>
#include <endian.h>
#include <errno.h>
#include <fcntl.h>
#include <net/if.h>
#include <net/if_arp.h>
#include <netinet/in.h>
#include <pthread.h>
#include <sched.h>
#include <signal.h>
#include <stdarg.h>
#include <stdbool.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/ioctl.h>
#include <sys/mount.h>
#include <sys/prctl.h>
#include <sys/resource.h>
#include <sys/socket.h>
#include <sys/stat.h>
#include <sys/syscall.h>
#include <sys/time.h>
#include <sys/types.h>
#include <sys/uio.h>
#include <sys/wait.h>
#include <time.h>
#include <unistd.h>
#include <linux/capability.h>
#include <linux/futex.h>
#include <linux/genetlink.h>
#include <linux/if_addr.h>
#include <linux/if_ether.h>
#include <linux/if_link.h>
#include <linux/if_tun.h>
#include <linux/in6.h>
#include <linux/ip.h>
#include <linux/neighbour.h>
#include <linux/net.h>
#include <linux/netlink.h>
#include <linux/rtnetlink.h>
#include <linux/tcp.h>
#include <linux/veth.h>
static unsigned long long procid;
static void sleep_ms(uint64_t ms)
{
usleep(ms * 1000);
}static uint64_t current_time_ms(void)
{
struct timespec ts;
if (clock_gettime(CLOCK_MONOTONIC, &ts))
exit(1);
return (uint64_t)ts.tv_sec * 1000 + (uint64_t)ts.tv_nsec / 1000000;
}static void thread_start(void* (*fn)(void*), void* arg)
{
pthread_t th;
pthread_attr_t attr;
pthread_attr_init(&attr);
pthread_attr_setstacksize(&attr, 128 << 10);
int i = 0;
for (; i < 100; i++) {
if (pthread_create(&th, &attr, fn, arg) == 0) {
pthread_attr_destroy(&attr);
return;
}
if (errno == EAGAIN) {
usleep(50);
continue;
}
break;
}
exit(1);
}#define BITMASK(bf_off,bf_len) (((1ull << (bf_len)) - 1) << (bf_off))
#define STORE_BY_BITMASK(type,htobe,addr,val,bf_off,bf_len) *(type*)(addr) = htobe((htobe(*(type*)(addr)) & ~BITMASK((bf_off), (bf_len))) | (((type)(val) << (bf_off)) & BITMASK((bf_off), (bf_len))))
typedef struct {
int state;
} event_t;static void event_init(event_t* ev)
{
ev->state = 0;
}static void event_reset(event_t* ev)
{
ev->state = 0;
}static void event_set(event_t* ev)
{
if (ev->state)
exit(1);
__atomic_store_n(&ev->state, 1, __ATOMIC_RELEASE);
syscall(SYS_futex, &ev->state, FUTEX_WAKE | FUTEX_PRIVATE_FLAG, 1000000);
}static void event_wait(event_t* ev)
{
while (!__atomic_load_n(&ev->state, __ATOMIC_ACQUIRE))
syscall(SYS_futex, &ev->state, FUTEX_WAIT | FUTEX_PRIVATE_FLAG, 0, 0);
}static int event_isset(event_t* ev)
{
return __atomic_load_n(&ev->state, __ATOMIC_ACQUIRE);
}static int event_timedwait(event_t* ev, uint64_t timeout)
{
uint64_t start = current_time_ms();
uint64_t now = start;
for (;;) {
uint64_t remain = timeout - (now - start);
struct timespec ts;
ts.tv_sec = remain / 1000;
ts.tv_nsec = (remain % 1000) * 1000 * 1000;
syscall(SYS_futex, &ev->state, FUTEX_WAIT | FUTEX_PRIVATE_FLAG, 0, &ts);
if (__atomic_load_n(&ev->state, __ATOMIC_ACQUIRE))
return 1;
now = current_time_ms();
if (now - start > timeout)
return 0;
}
}static bool write_file(const char* file, const char* what, ...)
{
char buf[1024];
va_list args;
va_start(args, what);
vsnprintf(buf, sizeof(buf), what, args);
va_end(args);
buf[sizeof(buf) - 1] = 0;
int len = strlen(buf);
int fd = open(file, O_WRONLY | O_CLOEXEC);
if (fd == -1)
return false;
if (write(fd, buf, len) != len) {
int err = errno;
close(fd);
errno = err;
return false;
}
close(fd);
return true;
}struct nlmsg {
char* pos;
int nesting;
struct nlattr* nested[8];
char buf[4096];
};static void netlink_init(struct nlmsg* nlmsg, int typ, int flags,
const void* data, int size)
{
memset(nlmsg, 0, sizeof(*nlmsg));
struct nlmsghdr* hdr = (struct nlmsghdr*)nlmsg->buf;
hdr->nlmsg_type = typ;
hdr->nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK | flags;
memcpy(hdr + 1, data, size);
nlmsg->pos = (char*)(hdr + 1) + NLMSG_ALIGN(size);
}static void netlink_attr(struct nlmsg* nlmsg, int typ,
const void* data, int size)
{
struct nlattr* attr = (struct nlattr*)nlmsg->pos;
attr->nla_len = sizeof(*attr) + size;
attr->nla_type = typ;
if (size > 0)
memcpy(attr + 1, data, size);
nlmsg->pos += NLMSG_ALIGN(attr->nla_len);
}static void netlink_nest(struct nlmsg* nlmsg, int typ)
{
struct nlattr* attr = (struct nlattr*)nlmsg->pos;
attr->nla_type = typ;
nlmsg->pos += sizeof(*attr);
nlmsg->nested[nlmsg->nesting++] = attr;
}static void netlink_done(struct nlmsg* nlmsg)
{
struct nlattr* attr = nlmsg->nested[--nlmsg->nesting];
attr->nla_len = nlmsg->pos - (char*)attr;
}static int netlink_send_ext(struct nlmsg* nlmsg, int sock,
uint16_t reply_type, int* reply_len, bool dofail)
{
if (nlmsg->pos > nlmsg->buf + sizeof(nlmsg->buf) || nlmsg->nesting)
exit(1);
struct nlmsghdr* hdr = (struct nlmsghdr*)nlmsg->buf;
hdr->nlmsg_len = nlmsg->pos - nlmsg->buf;
struct sockaddr_nl addr;
memset(&addr, 0, sizeof(addr));
addr.nl_family = AF_NETLINK;
ssize_t n = sendto(sock, nlmsg->buf, hdr->nlmsg_len, 0, (struct sockaddr*)&addr, sizeof(addr));
if (n != (ssize_t)hdr->nlmsg_len) {
if (dofail)
exit(1);
return -1;
}
n = recv(sock, nlmsg->buf, sizeof(nlmsg->buf), 0);
if (reply_len)
*reply_len = 0;
if (n < 0) {
if (dofail)
exit(1);
return -1;
}
if (n < (ssize_t)sizeof(struct nlmsghdr)) {
errno = EINVAL;
if (dofail)
exit(1);
return -1;
}
if (hdr->nlmsg_type == NLMSG_DONE)
return 0;
if (reply_len && hdr->nlmsg_type == reply_type) {
*reply_len = n;
return 0;
}
if (n < (ssize_t)(sizeof(struct nlmsghdr) + sizeof(struct nlmsgerr))) {
errno = EINVAL;
if (dofail)
exit(1);
return -1;
}
if (hdr->nlmsg_type != NLMSG_ERROR) {
errno = EINVAL;
if (dofail)
exit(1);
return -1;
}
errno = -((struct nlmsgerr*)(hdr + 1))->error;
return -errno;
}static int netlink_send(struct nlmsg* nlmsg, int sock)
{
return netlink_send_ext(nlmsg, sock, 0, NULL, true);
}static int netlink_query_family_id(struct nlmsg* nlmsg, int sock, const char* family_name, bool dofail)
{
struct genlmsghdr genlhdr;
memset(&genlhdr, 0, sizeof(genlhdr));
genlhdr.cmd = CTRL_CMD_GETFAMILY;
netlink_init(nlmsg, GENL_ID_CTRL, 0, &genlhdr, sizeof(genlhdr));
netlink_attr(nlmsg, CTRL_ATTR_FAMILY_NAME, family_name, strnlen(family_name, GENL_NAMSIZ - 1) + 1);
int n = 0;
int err = netlink_send_ext(nlmsg, sock, GENL_ID_CTRL, &n, dofail);
if (err < 0) {
return -1;
}
uint16_t id = 0;
struct nlattr* attr = (struct nlattr*)(nlmsg->buf + NLMSG_HDRLEN + NLMSG_ALIGN(sizeof(genlhdr)));
for (; (char*)attr < nlmsg->buf + n; attr = (struct nlattr*)((char*)attr + NLMSG_ALIGN(attr->nla_len))) {
if (attr->nla_type == CTRL_ATTR_FAMILY_ID) {
id = *(uint16_t*)(attr + 1);
break;
}
}
if (!id) {
errno = EINVAL;
return -1;
}
recv(sock, nlmsg->buf, sizeof(nlmsg->buf), 0);
return id;
}static int netlink_next_msg(struct nlmsg* nlmsg, unsigned int offset,
unsigned int total_len)
{
struct nlmsghdr* hdr = (struct nlmsghdr*)(nlmsg->buf + offset);
if (offset == total_len || offset + hdr->nlmsg_len > total_len)
return -1;
return hdr->nlmsg_len;
}static unsigned int queue_count = 2;
static void netlink_add_device_impl(struct nlmsg* nlmsg, const char* type,
const char* name, bool up)
{
struct ifinfomsg hdr;
memset(&hdr, 0, sizeof(hdr));
if (up)
hdr.ifi_flags = hdr.ifi_change = IFF_UP;
netlink_init(nlmsg, RTM_NEWLINK, NLM_F_EXCL | NLM_F_CREATE, &hdr, sizeof(hdr));
if (name)
netlink_attr(nlmsg, IFLA_IFNAME, name, strlen(name));
netlink_attr(nlmsg, IFLA_NUM_TX_QUEUES, &queue_count, sizeof(queue_count));
netlink_attr(nlmsg, IFLA_NUM_RX_QUEUES, &queue_count, sizeof(queue_count));
netlink_nest(nlmsg, IFLA_LINKINFO);
netlink_attr(nlmsg, IFLA_INFO_KIND, type, strlen(type));
}static void netlink_add_device(struct nlmsg* nlmsg, int sock, const char* type,
const char* name)
{
netlink_add_device_impl(nlmsg, type, name, false);
netlink_done(nlmsg);
int err = netlink_send(nlmsg, sock);
if (err < 0) {
}
}static void netlink_add_veth(struct nlmsg* nlmsg, int sock, const char* name,
const char* peer)
{
netlink_add_device_impl(nlmsg, "veth", name, false);
netlink_nest(nlmsg, IFLA_INFO_DATA);
netlink_nest(nlmsg, VETH_INFO_PEER);
nlmsg->pos += sizeof(struct ifinfomsg);
netlink_attr(nlmsg, IFLA_IFNAME, peer, strlen(peer));
netlink_attr(nlmsg, IFLA_NUM_TX_QUEUES, &queue_count, sizeof(queue_count));
netlink_attr(nlmsg, IFLA_NUM_RX_QUEUES, &queue_count, sizeof(queue_count));
netlink_done(nlmsg);
netlink_done(nlmsg);
netlink_done(nlmsg);
int err = netlink_send(nlmsg, sock);
if (err < 0) {
}
}static void netlink_add_xfrm(struct nlmsg* nlmsg, int sock, const char* name)
{
netlink_add_device_impl(nlmsg, "xfrm", name, true);
netlink_nest(nlmsg, IFLA_INFO_DATA);
int if_id = 1;
netlink_attr(nlmsg, 2, &if_id, sizeof(if_id));
netlink_done(nlmsg);
netlink_done(nlmsg);
int err = netlink_send(nlmsg, sock);
if (err < 0) {
}
}static void netlink_add_hsr(struct nlmsg* nlmsg, int sock, const char* name,
const char* slave1, const char* slave2)
{
netlink_add_device_impl(nlmsg, "hsr", name, false);
netlink_nest(nlmsg, IFLA_INFO_DATA);
int ifindex1 = if_nametoindex(slave1);
netlink_attr(nlmsg, IFLA_HSR_SLAVE1, &ifindex1, sizeof(ifindex1));
int ifindex2 = if_nametoindex(slave2);
netlink_attr(nlmsg, IFLA_HSR_SLAVE2, &ifindex2, sizeof(ifindex2));
netlink_done(nlmsg);
netlink_done(nlmsg);
int err = netlink_send(nlmsg, sock);
if (err < 0) {
}
}static void netlink_add_linked(struct nlmsg* nlmsg, int sock, const char* type, const char* name, const char* link)
{
netlink_add_device_impl(nlmsg, type, name, false);
netlink_done(nlmsg);
int ifindex = if_nametoindex(link);
netlink_attr(nlmsg, IFLA_LINK, &ifindex, sizeof(ifindex));
int err = netlink_send(nlmsg, sock);
if (err < 0) {
}
}static void netlink_add_vlan(struct nlmsg* nlmsg, int sock, const char* name, const char* link, uint16_t id, uint16_t proto)
{
netlink_add_device_impl(nlmsg, "vlan", name, false);
netlink_nest(nlmsg, IFLA_INFO_DATA);
netlink_attr(nlmsg, IFLA_VLAN_ID, &id, sizeof(id));
netlink_attr(nlmsg, IFLA_VLAN_PROTOCOL, &proto, sizeof(proto));
netlink_done(nlmsg);
netlink_done(nlmsg);
int ifindex = if_nametoindex(link);
netlink_attr(nlmsg, IFLA_LINK, &ifindex, sizeof(ifindex));
int err = netlink_send(nlmsg, sock);
if (err < 0) {
}
}static void netlink_add_macvlan(struct nlmsg* nlmsg, int sock, const char* name, const char* link)
{
netlink_add_device_impl(nlmsg, "macvlan", name, false);
netlink_nest(nlmsg, IFLA_INFO_DATA);
uint32_t mode = MACVLAN_MODE_BRIDGE;
netlink_attr(nlmsg, IFLA_MACVLAN_MODE, &mode, sizeof(mode));
netlink_done(nlmsg);
netlink_done(nlmsg);
int ifindex = if_nametoindex(link);
netlink_attr(nlmsg, IFLA_LINK, &ifindex, sizeof(ifindex));
int err = netlink_send(nlmsg, sock);
if (err < 0) {
}
}static void netlink_add_geneve(struct nlmsg* nlmsg, int sock, const char* name, uint32_t vni, struct in_addr* addr4, struct in6_addr* addr6)
{
netlink_add_device_impl(nlmsg, "geneve", name, false);
netlink_nest(nlmsg, IFLA_INFO_DATA);
netlink_attr(nlmsg, IFLA_GENEVE_ID, &vni, sizeof(vni));
if (addr4)
netlink_attr(nlmsg, IFLA_GENEVE_REMOTE, addr4, sizeof(*addr4));
if (addr6)
netlink_attr(nlmsg, IFLA_GENEVE_REMOTE6, addr6, sizeof(*addr6));
netlink_done(nlmsg);
netlink_done(nlmsg);
int err = netlink_send(nlmsg, sock);
if (err < 0) {
}
}#define IFLA_IPVLAN_FLAGS 2
#define IPVLAN_MODE_L3S 2
#undef IPVLAN_F_VEPA
#define IPVLAN_F_VEPA 2
static void netlink_add_ipvlan(struct nlmsg* nlmsg, int sock, const char* name, const char* link, uint16_t mode, uint16_t flags)
{
netlink_add_device_impl(nlmsg, "ipvlan", name, false);
netlink_nest(nlmsg, IFLA_INFO_DATA);
netlink_attr(nlmsg, IFLA_IPVLAN_MODE, &mode, sizeof(mode));
netlink_attr(nlmsg, IFLA_IPVLAN_FLAGS, &flags, sizeof(flags));
netlink_done(nlmsg);
netlink_done(nlmsg);
int ifindex = if_nametoindex(link);
netlink_attr(nlmsg, IFLA_LINK, &ifindex, sizeof(ifindex));
int err = netlink_send(nlmsg, sock);
if (err < 0) {
}
}static void netlink_device_change(struct nlmsg* nlmsg, int sock, const char* name, bool up,
const char* master, const void* mac, int macsize, const char* new_name)
{
struct ifinfomsg hdr;
memset(&hdr, 0, sizeof(hdr));
if (up)
hdr.ifi_flags = hdr.ifi_change = IFF_UP;
hdr.ifi_index = if_nametoindex(name);
netlink_init(nlmsg, RTM_NEWLINK, 0, &hdr, sizeof(hdr));
if (new_name)
netlink_attr(nlmsg, IFLA_IFNAME, new_name, strlen(new_name));
if (master) {
int ifindex = if_nametoindex(master);
netlink_attr(nlmsg, IFLA_MASTER, &ifindex, sizeof(ifindex));
}
if (macsize)
netlink_attr(nlmsg, IFLA_ADDRESS, mac, macsize);
int err = netlink_send(nlmsg, sock);
if (err < 0) {
}
}static int netlink_add_addr(struct nlmsg* nlmsg, int sock, const char* dev,
const void* addr, int addrsize)
{
struct ifaddrmsg hdr;
memset(&hdr, 0, sizeof(hdr));
hdr.ifa_family = addrsize == 4 ? AF_INET : AF_INET6;
hdr.ifa_prefixlen = addrsize == 4 ? 24 : 120;
hdr.ifa_scope = RT_SCOPE_UNIVERSE;
hdr.ifa_index = if_nametoindex(dev);
netlink_init(nlmsg, RTM_NEWADDR, NLM_F_CREATE | NLM_F_REPLACE, &hdr, sizeof(hdr));
netlink_attr(nlmsg, IFA_LOCAL, addr, addrsize);
netlink_attr(nlmsg, IFA_ADDRESS, addr, addrsize);
return netlink_send(nlmsg, sock);
}static void netlink_add_addr4(struct nlmsg* nlmsg, int sock,
const char* dev, const char* addr)
{
struct in_addr in_addr;
inet_pton(AF_INET, addr, &in_addr);
int err = netlink_add_addr(nlmsg, sock, dev, &in_addr, sizeof(in_addr));
if (err < 0) {
}
}static void netlink_add_addr6(struct nlmsg* nlmsg, int sock,
const char* dev, const char* addr)
{
struct in6_addr in6_addr;
inet_pton(AF_INET6, addr, &in6_addr);
int err = netlink_add_addr(nlmsg, sock, dev, &in6_addr, sizeof(in6_addr));
if (err < 0) {
}
}static struct nlmsg nlmsg;
#define DEVLINK_FAMILY_NAME "devlink"
#define DEVLINK_CMD_PORT_GET 5
#define DEVLINK_ATTR_BUS_NAME 1
#define DEVLINK_ATTR_DEV_NAME 2
#define DEVLINK_ATTR_NETDEV_NAME 7
static struct nlmsg nlmsg2;
static void initialize_devlink_ports(const char* bus_name, const char* dev_name,
const char* netdev_prefix)
{
struct genlmsghdr genlhdr;
int len, total_len, id, err, offset;
uint16_t netdev_index;
int sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_GENERIC);
if (sock == -1)
exit(1);
int rtsock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
if (rtsock == -1)
exit(1);
id = netlink_query_family_id(&nlmsg, sock, DEVLINK_FAMILY_NAME, true);
if (id == -1)
goto error;
memset(&genlhdr, 0, sizeof(genlhdr));
genlhdr.cmd = DEVLINK_CMD_PORT_GET;
netlink_init(&nlmsg, id, NLM_F_DUMP, &genlhdr, sizeof(genlhdr));
netlink_attr(&nlmsg, DEVLINK_ATTR_BUS_NAME, bus_name, strlen(bus_name) + 1);
netlink_attr(&nlmsg, DEVLINK_ATTR_DEV_NAME, dev_name, strlen(dev_name) + 1);
err = netlink_send_ext(&nlmsg, sock, id, &total_len, true);
if (err < 0) {
goto error;
}
offset = 0;
netdev_index = 0;
while ((len = netlink_next_msg(&nlmsg, offset, total_len)) != -1) {
struct nlattr* attr = (struct nlattr*)(nlmsg.buf + offset + NLMSG_HDRLEN + NLMSG_ALIGN(sizeof(genlhdr)));
for (; (char*)attr < nlmsg.buf + offset + len; attr = (struct nlattr*)((char*)attr + NLMSG_ALIGN(attr->nla_len))) {
if (attr->nla_type == DEVLINK_ATTR_NETDEV_NAME) {
char* port_name;
char netdev_name[IFNAMSIZ];
port_name = (char*)(attr + 1);
snprintf(netdev_name, sizeof(netdev_name), "%s%d", netdev_prefix, netdev_index);
netlink_device_change(&nlmsg2, rtsock, port_name, true, 0, 0, 0, netdev_name);
break;
}
}
offset += len;
netdev_index++;
}
error:
close(rtsock);
close(sock);
}#define DEV_IPV4 "172.20.20.%d"
#define DEV_IPV6 "fe80::%02x"
#define DEV_MAC 0x00aaaaaaaaaa
static void netdevsim_add(unsigned int addr, unsigned int port_count)
{
write_file("/sys/bus/netdevsim/del_device", "%u", addr);
if (write_file("/sys/bus/netdevsim/new_device", "%u %u", addr, port_count)) {
char buf[32];
snprintf(buf, sizeof(buf), "netdevsim%d", addr);
initialize_devlink_ports("netdevsim", buf, "netdevsim");
}
}#define WG_GENL_NAME "wireguard"
enum wg_cmd {
WG_CMD_GET_DEVICE,
WG_CMD_SET_DEVICE,
};
enum wgdevice_attribute {
WGDEVICE_A_UNSPEC,
WGDEVICE_A_IFINDEX,
WGDEVICE_A_IFNAME,
WGDEVICE_A_PRIVATE_KEY,
WGDEVICE_A_PUBLIC_KEY,
WGDEVICE_A_FLAGS,
WGDEVICE_A_LISTEN_PORT,
WGDEVICE_A_FWMARK,
WGDEVICE_A_PEERS,
};
enum wgpeer_attribute {
WGPEER_A_UNSPEC,
WGPEER_A_PUBLIC_KEY,
WGPEER_A_PRESHARED_KEY,
WGPEER_A_FLAGS,
WGPEER_A_ENDPOINT,
WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL,
WGPEER_A_LAST_HANDSHAKE_TIME,
WGPEER_A_RX_BYTES,
WGPEER_A_TX_BYTES,
WGPEER_A_ALLOWEDIPS,
WGPEER_A_PROTOCOL_VERSION,
};
enum wgallowedip_attribute {
WGALLOWEDIP_A_UNSPEC,
WGALLOWEDIP_A_FAMILY,
WGALLOWEDIP_A_IPADDR,
WGALLOWEDIP_A_CIDR_MASK,
};
static void netlink_wireguard_setup(void)
{
const char ifname_a[] = "wg0";
const char ifname_b[] = "wg1";
const char ifname_c[] = "wg2";
const char private_a[] = "\xa0\x5c\xa8\x4f\x6c\x9c\x8e\x38\x53\xe2\xfd\x7a\x70\xae\x0f\xb2\x0f\xa1\x52\x60\x0c\xb0\x08\x45\x17\x4f\x08\x07\x6f\x8d\x78\x43";
const char private_b[] = "\xb0\x80\x73\xe8\xd4\x4e\x91\xe3\xda\x92\x2c\x22\x43\x82\x44\xbb\x88\x5c\x69\xe2\x69\xc8\xe9\xd8\x35\xb1\x14\x29\x3a\x4d\xdc\x6e";
const char private_c[] = "\xa0\xcb\x87\x9a\x47\xf5\xbc\x64\x4c\x0e\x69\x3f\xa6\xd0\x31\xc7\x4a\x15\x53\xb6\xe9\x01\xb9\xff\x2f\x51\x8c\x78\x04\x2f\xb5\x42";
const char public_a[] = "\x97\x5c\x9d\x81\xc9\x83\xc8\x20\x9e\xe7\x81\x25\x4b\x89\x9f\x8e\xd9\x25\xae\x9f\x09\x23\xc2\x3c\x62\xf5\x3c\x57\xcd\xbf\x69\x1c";
const char public_b[] = "\xd1\x73\x28\x99\xf6\x11\xcd\x89\x94\x03\x4d\x7f\x41\x3d\xc9\x57\x63\x0e\x54\x93\xc2\x85\xac\xa4\x00\x65\xcb\x63\x11\xbe\x69\x6b";
const char public_c[] = "\xf4\x4d\xa3\x67\xa8\x8e\xe6\x56\x4f\x02\x02\x11\x45\x67\x27\x08\x2f\x5c\xeb\xee\x8b\x1b\xf5\xeb\x73\x37\x34\x1b\x45\x9b\x39\x22";
const uint16_t listen_a = 20001;
const uint16_t listen_b = 20002;
const uint16_t listen_c = 20003;
const uint16_t af_inet = AF_INET;
const uint16_t af_inet6 = AF_INET6;
const struct sockaddr_in endpoint_b_v4 = {
.sin_family = AF_INET,
.sin_port = htons(listen_b),
.sin_addr = {htonl(INADDR_LOOPBACK)}};
const struct sockaddr_in endpoint_c_v4 = {
.sin_family = AF_INET,
.sin_port = htons(listen_c),
.sin_addr = {htonl(INADDR_LOOPBACK)}};
struct sockaddr_in6 endpoint_a_v6 = {
.sin6_family = AF_INET6,
.sin6_port = htons(listen_a)};
endpoint_a_v6.sin6_addr = in6addr_loopback;
struct sockaddr_in6 endpoint_c_v6 = {
.sin6_family = AF_INET6,
.sin6_port = htons(listen_c)};
endpoint_c_v6.sin6_addr = in6addr_loopback;
const struct in_addr first_half_v4 = {0};
const struct in_addr second_half_v4 = {(uint32_t)htonl(128 << 24)};
const struct in6_addr first_half_v6 = {{{0}}};
const struct in6_addr second_half_v6 = {{{0x80}}};
const uint8_t half_cidr = 1;
const uint16_t persistent_keepalives[] = {1, 3, 7, 9, 14, 19};
struct genlmsghdr genlhdr = {
.cmd = WG_CMD_SET_DEVICE,
.version = 1};
int sock;
int id, err;
sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_GENERIC);
if (sock == -1) {
return;
}
id = netlink_query_family_id(&nlmsg, sock, WG_GENL_NAME, true);
if (id == -1)
goto error;
netlink_init(&nlmsg, id, 0, &genlhdr, sizeof(genlhdr));
netlink_attr(&nlmsg, WGDEVICE_A_IFNAME, ifname_a, strlen(ifname_a) + 1);
netlink_attr(&nlmsg, WGDEVICE_A_PRIVATE_KEY, private_a, 32);
netlink_attr(&nlmsg, WGDEVICE_A_LISTEN_PORT, &listen_a, 2);
netlink_nest(&nlmsg, NLA_F_NESTED | WGDEVICE_A_PEERS);
netlink_nest(&nlmsg, NLA_F_NESTED | 0);
netlink_attr(&nlmsg, WGPEER_A_PUBLIC_KEY, public_b, 32);
netlink_attr(&nlmsg, WGPEER_A_ENDPOINT, &endpoint_b_v4, sizeof(endpoint_b_v4));
netlink_attr(&nlmsg, WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL, &persistent_keepalives[0], 2);
netlink_nest(&nlmsg, NLA_F_NESTED | WGPEER_A_ALLOWEDIPS);
netlink_nest(&nlmsg, NLA_F_NESTED | 0);
netlink_attr(&nlmsg, WGALLOWEDIP_A_FAMILY, &af_inet, 2);
netlink_attr(&nlmsg, WGALLOWEDIP_A_IPADDR, &first_half_v4, sizeof(first_half_v4));
netlink_attr(&nlmsg, WGALLOWEDIP_A_CIDR_MASK, &half_cidr, 1);
netlink_done(&nlmsg);
netlink_nest(&nlmsg, NLA_F_NESTED | 0);
netlink_attr(&nlmsg, WGALLOWEDIP_A_FAMILY, &af_inet6, 2);
netlink_attr(&nlmsg, WGALLOWEDIP_A_IPADDR, &first_half_v6, sizeof(first_half_v6));
netlink_attr(&nlmsg, WGALLOWEDIP_A_CIDR_MASK, &half_cidr, 1);
netlink_done(&nlmsg);
netlink_done(&nlmsg);
netlink_done(&nlmsg);
netlink_nest(&nlmsg, NLA_F_NESTED | 0);
netlink_attr(&nlmsg, WGPEER_A_PUBLIC_KEY, public_c, 32);
netlink_attr(&nlmsg, WGPEER_A_ENDPOINT, &endpoint_c_v6, sizeof(endpoint_c_v6));
netlink_attr(&nlmsg, WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL, &persistent_keepalives[1], 2);
netlink_nest(&nlmsg, NLA_F_NESTED | WGPEER_A_ALLOWEDIPS);
netlink_nest(&nlmsg, NLA_F_NESTED | 0);
netlink_attr(&nlmsg, WGALLOWEDIP_A_FAMILY, &af_inet, 2);
netlink_attr(&nlmsg, WGALLOWEDIP_A_IPADDR, &second_half_v4, sizeof(second_half_v4));
netlink_attr(&nlmsg, WGALLOWEDIP_A_CIDR_MASK, &half_cidr, 1);
netlink_done(&nlmsg);
netlink_nest(&nlmsg, NLA_F_NESTED | 0);
netlink_attr(&nlmsg, WGALLOWEDIP_A_FAMILY, &af_inet6, 2);
netlink_attr(&nlmsg, WGALLOWEDIP_A_IPADDR, &second_half_v6, sizeof(second_half_v6));
netlink_attr(&nlmsg, WGALLOWEDIP_A_CIDR_MASK, &half_cidr, 1);
netlink_done(&nlmsg);
netlink_done(&nlmsg);
netlink_done(&nlmsg);
netlink_done(&nlmsg);
err = netlink_send(&nlmsg, sock);
if (err < 0) {
}
netlink_init(&nlmsg, id, 0, &genlhdr, sizeof(genlhdr));
netlink_attr(&nlmsg, WGDEVICE_A_IFNAME, ifname_b, strlen(ifname_b) + 1);
netlink_attr(&nlmsg, WGDEVICE_A_PRIVATE_KEY, private_b, 32);
netlink_attr(&nlmsg, WGDEVICE_A_LISTEN_PORT, &listen_b, 2);
netlink_nest(&nlmsg, NLA_F_NESTED | WGDEVICE_A_PEERS);
netlink_nest(&nlmsg, NLA_F_NESTED | 0);
netlink_attr(&nlmsg, WGPEER_A_PUBLIC_KEY, public_a, 32);
netlink_attr(&nlmsg, WGPEER_A_ENDPOINT, &endpoint_a_v6, sizeof(endpoint_a_v6));
netlink_attr(&nlmsg, WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL, &persistent_keepalives[2], 2);
netlink_nest(&nlmsg, NLA_F_NESTED | WGPEER_A_ALLOWEDIPS);
netlink_nest(&nlmsg, NLA_F_NESTED | 0);
netlink_attr(&nlmsg, WGALLOWEDIP_A_FAMILY, &af_inet, 2);
netlink_attr(&nlmsg, WGALLOWEDIP_A_IPADDR, &first_half_v4, sizeof(first_half_v4));
netlink_attr(&nlmsg, WGALLOWEDIP_A_CIDR_MASK, &half_cidr, 1);
netlink_done(&nlmsg);
netlink_nest(&nlmsg, NLA_F_NESTED | 0);
netlink_attr(&nlmsg, WGALLOWEDIP_A_FAMILY, &af_inet6, 2);
netlink_attr(&nlmsg, WGALLOWEDIP_A_IPADDR, &first_half_v6, sizeof(first_half_v6));
netlink_attr(&nlmsg, WGALLOWEDIP_A_CIDR_MASK, &half_cidr, 1);
netlink_done(&nlmsg);
netlink_done(&nlmsg);
netlink_done(&nlmsg);
netlink_nest(&nlmsg, NLA_F_NESTED | 0);
netlink_attr(&nlmsg, WGPEER_A_PUBLIC_KEY, public_c, 32);
netlink_attr(&nlmsg, WGPEER_A_ENDPOINT, &endpoint_c_v4, sizeof(endpoint_c_v4));
netlink_attr(&nlmsg, WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL, &persistent_keepalives[3], 2);
netlink_nest(&nlmsg, NLA_F_NESTED | WGPEER_A_ALLOWEDIPS);
netlink_nest(&nlmsg, NLA_F_NESTED | 0);
netlink_attr(&nlmsg, WGALLOWEDIP_A_FAMILY, &af_inet, 2);
netlink_attr(&nlmsg, WGALLOWEDIP_A_IPADDR, &second_half_v4, sizeof(second_half_v4));
netlink_attr(&nlmsg, WGALLOWEDIP_A_CIDR_MASK, &half_cidr, 1);
netlink_done(&nlmsg);
netlink_nest(&nlmsg, NLA_F_NESTED | 0);
netlink_attr(&nlmsg, WGALLOWEDIP_A_FAMILY, &af_inet6, 2);
netlink_attr(&nlmsg, WGALLOWEDIP_A_IPADDR, &second_half_v6, sizeof(second_half_v6));
netlink_attr(&nlmsg, WGALLOWEDIP_A_CIDR_MASK, &half_cidr, 1);
netlink_done(&nlmsg);
netlink_done(&nlmsg);
netlink_done(&nlmsg);
netlink_done(&nlmsg);
err = netlink_send(&nlmsg, sock);
if (err < 0) {
}
netlink_init(&nlmsg, id, 0, &genlhdr, sizeof(genlhdr));
netlink_attr(&nlmsg, WGDEVICE_A_IFNAME, ifname_c, strlen(ifname_c) + 1);
netlink_attr(&nlmsg, WGDEVICE_A_PRIVATE_KEY, private_c, 32);
netlink_attr(&nlmsg, WGDEVICE_A_LISTEN_PORT, &listen_c, 2);
netlink_nest(&nlmsg, NLA_F_NESTED | WGDEVICE_A_PEERS);
netlink_nest(&nlmsg, NLA_F_NESTED | 0);
netlink_attr(&nlmsg, WGPEER_A_PUBLIC_KEY, public_a, 32);
netlink_attr(&nlmsg, WGPEER_A_ENDPOINT, &endpoint_a_v6, sizeof(endpoint_a_v6));
netlink_attr(&nlmsg, WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL, &persistent_keepalives[4], 2);
netlink_nest(&nlmsg, NLA_F_NESTED | WGPEER_A_ALLOWEDIPS);
netlink_nest(&nlmsg, NLA_F_NESTED | 0);
netlink_attr(&nlmsg, WGALLOWEDIP_A_FAMILY, &af_inet, 2);
netlink_attr(&nlmsg, WGALLOWEDIP_A_IPADDR, &first_half_v4, sizeof(first_half_v4));
netlink_attr(&nlmsg, WGALLOWEDIP_A_CIDR_MASK, &half_cidr, 1);
netlink_done(&nlmsg);
netlink_nest(&nlmsg, NLA_F_NESTED | 0);
netlink_attr(&nlmsg, WGALLOWEDIP_A_FAMILY, &af_inet6, 2);
netlink_attr(&nlmsg, WGALLOWEDIP_A_IPADDR, &first_half_v6, sizeof(first_half_v6));
netlink_attr(&nlmsg, WGALLOWEDIP_A_CIDR_MASK, &half_cidr, 1);
netlink_done(&nlmsg);
netlink_done(&nlmsg);
netlink_done(&nlmsg);
netlink_nest(&nlmsg, NLA_F_NESTED | 0);
netlink_attr(&nlmsg, WGPEER_A_PUBLIC_KEY, public_b, 32);
netlink_attr(&nlmsg, WGPEER_A_ENDPOINT, &endpoint_b_v4, sizeof(endpoint_b_v4));
netlink_attr(&nlmsg, WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL, &persistent_keepalives[5], 2);
netlink_nest(&nlmsg, NLA_F_NESTED | WGPEER_A_ALLOWEDIPS);
netlink_nest(&nlmsg, NLA_F_NESTED | 0);
netlink_attr(&nlmsg, WGALLOWEDIP_A_FAMILY, &af_inet, 2);
netlink_attr(&nlmsg, WGALLOWEDIP_A_IPADDR, &second_half_v4, sizeof(second_half_v4));
netlink_attr(&nlmsg, WGALLOWEDIP_A_CIDR_MASK, &half_cidr, 1);
netlink_done(&nlmsg);
netlink_nest(&nlmsg, NLA_F_NESTED | 0);
netlink_attr(&nlmsg, WGALLOWEDIP_A_FAMILY, &af_inet6, 2);
netlink_attr(&nlmsg, WGALLOWEDIP_A_IPADDR, &second_half_v6, sizeof(second_half_v6));
netlink_attr(&nlmsg, WGALLOWEDIP_A_CIDR_MASK, &half_cidr, 1);
netlink_done(&nlmsg);
netlink_done(&nlmsg);
netlink_done(&nlmsg);
netlink_done(&nlmsg);
err = netlink_send(&nlmsg, sock);
if (err < 0) {
}error:
close(sock); }
static void initialize_netdevices(void)
{
char netdevsim[16];
sprintf(netdevsim, "netdevsim%d", (int)procid);
struct {
const char* type;
const char* dev;
} devtypes[] = {
{"ip6gretap", "ip6gretap0"},
{"bridge", "bridge0"},
{"vcan", "vcan0"},
{"bond", "bond0"},
{"team", "team0"},
{"dummy", "dummy0"},
{"nlmon", "nlmon0"},
{"caif", "caif0"},
{"batadv", "batadv0"},
{"vxcan", "vxcan1"},
{"veth", 0},
{"wireguard", "wg0"},
{"wireguard", "wg1"},
{"wireguard", "wg2"},
};
const char* devmasters[] = {"bridge", "bond", "team", "batadv"};
struct {
const char* name;
int macsize;
bool noipv6;
} devices[] = {
{"lo", ETH_ALEN},
{"sit0", 0},
{"bridge0", ETH_ALEN},
{"vcan0", 0, true},
{"tunl0", 0},
{"gre0", 0},
{"gretap0", ETH_ALEN},
{"ip_vti0", 0},
{"ip6_vti0", 0},
{"ip6tnl0", 0},
{"ip6gre0", 0},
{"ip6gretap0", ETH_ALEN},
{"erspan0", ETH_ALEN},
{"bond0", ETH_ALEN},
{"veth0", ETH_ALEN},
{"veth1", ETH_ALEN},
{"team0", ETH_ALEN},
{"veth0_to_bridge", ETH_ALEN},
{"veth1_to_bridge", ETH_ALEN},
{"veth0_to_bond", ETH_ALEN},
{"veth1_to_bond", ETH_ALEN},
{"veth0_to_team", ETH_ALEN},
{"veth1_to_team", ETH_ALEN},
{"veth0_to_hsr", ETH_ALEN},
{"veth1_to_hsr", ETH_ALEN},
{"hsr0", 0},
{"dummy0", ETH_ALEN},
{"nlmon0", 0},
{"vxcan0", 0, true},
{"vxcan1", 0, true},
{"caif0", ETH_ALEN},
{"batadv0", ETH_ALEN},
{netdevsim, ETH_ALEN},
{"xfrm0", ETH_ALEN},
{"veth0_virt_wifi", ETH_ALEN},
{"veth1_virt_wifi", ETH_ALEN},
{"virt_wifi0", ETH_ALEN},
{"veth0_vlan", ETH_ALEN},
{"veth1_vlan", ETH_ALEN},
{"vlan0", ETH_ALEN},
{"vlan1", ETH_ALEN},
{"macvlan0", ETH_ALEN},
{"macvlan1", ETH_ALEN},
{"ipvlan0", ETH_ALEN},
{"ipvlan1", ETH_ALEN},
{"veth0_macvtap", ETH_ALEN},
{"veth1_macvtap", ETH_ALEN},
{"macvtap0", ETH_ALEN},
{"macsec0", ETH_ALEN},
{"veth0_to_batadv", ETH_ALEN},
{"veth1_to_batadv", ETH_ALEN},
{"batadv_slave_0", ETH_ALEN},
{"batadv_slave_1", ETH_ALEN},
{"geneve0", ETH_ALEN},
{"geneve1", ETH_ALEN},
{"wg0", 0},
{"wg1", 0},
{"wg2", 0},
};
int sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
if (sock == -1)
exit(1);
unsigned i;
for (i = 0; i < sizeof(devtypes) / sizeof(devtypes[0]); i++)
netlink_add_device(&nlmsg, sock, devtypes[i].type, devtypes[i].dev);
for (i = 0; i < sizeof(devmasters) / (sizeof(devmasters[0])); i++) {
char master[32], slave0[32], veth0[32], slave1[32], veth1[32];
sprintf(slave0, "%s_slave_0", devmasters[i]);
sprintf(veth0, "veth0_to_%s", devmasters[i]);
netlink_add_veth(&nlmsg, sock, slave0, veth0);
sprintf(slave1, "%s_slave_1", devmasters[i]);
sprintf(veth1, "veth1_to_%s", devmasters[i]);
netlink_add_veth(&nlmsg, sock, slave1, veth1);
sprintf(master, "%s0", devmasters[i]);
netlink_device_change(&nlmsg, sock, slave0, false, master, 0, 0, NULL);
netlink_device_change(&nlmsg, sock, slave1, false, master, 0, 0, NULL);
}
netlink_add_xfrm(&nlmsg, sock, "xfrm0");
netlink_device_change(&nlmsg, sock, "bridge_slave_0", true, 0, 0, 0, NULL);
netlink_device_change(&nlmsg, sock, "bridge_slave_1", true, 0, 0, 0, NULL);
netlink_add_veth(&nlmsg, sock, "hsr_slave_0", "veth0_to_hsr");
netlink_add_veth(&nlmsg, sock, "hsr_slave_1", "veth1_to_hsr");
netlink_add_hsr(&nlmsg, sock, "hsr0", "hsr_slave_0", "hsr_slave_1");
netlink_device_change(&nlmsg, sock, "hsr_slave_0", true, 0, 0, 0, NULL);
netlink_device_change(&nlmsg, sock, "hsr_slave_1", true, 0, 0, 0, NULL);
netlink_add_veth(&nlmsg, sock, "veth0_virt_wifi", "veth1_virt_wifi");
netlink_add_linked(&nlmsg, sock, "virt_wifi", "virt_wifi0", "veth1_virt_wifi");
netlink_add_veth(&nlmsg, sock, "veth0_vlan", "veth1_vlan");
netlink_add_vlan(&nlmsg, sock, "vlan0", "veth0_vlan", 0, htons(ETH_P_8021Q));
netlink_add_vlan(&nlmsg, sock, "vlan1", "veth0_vlan", 1, htons(ETH_P_8021AD));
netlink_add_macvlan(&nlmsg, sock, "macvlan0", "veth1_vlan");
netlink_add_macvlan(&nlmsg, sock, "macvlan1", "veth1_vlan");
netlink_add_ipvlan(&nlmsg, sock, "ipvlan0", "veth0_vlan", IPVLAN_MODE_L2, 0);
netlink_add_ipvlan(&nlmsg, sock, "ipvlan1", "veth0_vlan", IPVLAN_MODE_L3S, IPVLAN_F_VEPA);
netlink_add_veth(&nlmsg, sock, "veth0_macvtap", "veth1_macvtap");
netlink_add_linked(&nlmsg, sock, "macvtap", "macvtap0", "veth0_macvtap");
netlink_add_linked(&nlmsg, sock, "macsec", "macsec0", "veth1_macvtap");
char addr[32];
sprintf(addr, DEV_IPV4, 14 + 10);
struct in_addr geneve_addr4;
if (inet_pton(AF_INET, addr, &geneve_addr4) <= 0)
exit(1);
struct in6_addr geneve_addr6;
if (inet_pton(AF_INET6, "fc00::01", &geneve_addr6) <= 0)
exit(1);
netlink_add_geneve(&nlmsg, sock, "geneve0", 0, &geneve_addr4, 0);
netlink_add_geneve(&nlmsg, sock, "geneve1", 1, 0, &geneve_addr6);
netdevsim_add((int)procid, 4);
netlink_wireguard_setup();
for (i = 0; i < sizeof(devices) / (sizeof(devices[0])); i++) {
char addr[32];
sprintf(addr, DEV_IPV4, i + 10);
netlink_add_addr4(&nlmsg, sock, devices[i].name, addr);
if (!devices[i].noipv6) {
sprintf(addr, DEV_IPV6, i + 10);
netlink_add_addr6(&nlmsg, sock, devices[i].name, addr);
}
uint64_t macaddr = DEV_MAC + ((i + 10ull) << 40);
netlink_device_change(&nlmsg, sock, devices[i].name, true, 0, &macaddr, devices[i].macsize, NULL);
}
close(sock);
}
static void initialize_netdevices_init(void)
{
int sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
if (sock == -1)
exit(1);
struct {
const char* type;
int macsize;
bool noipv6;
bool noup;
} devtypes[] = {
{"nr", 7, true},
{"rose", 5, true, true},
};
unsigned i;
for (i = 0; i < sizeof(devtypes) / sizeof(devtypes[0]); i++) {
char dev[32], addr[32];
sprintf(dev, "%s%d", devtypes[i].type, (int)procid);
sprintf(addr, "172.30.%d.%d", i, (int)procid + 1);
netlink_add_addr4(&nlmsg, sock, dev, addr);
if (!devtypes[i].noipv6) {
sprintf(addr, "fe88::%02x:%02x", i, (int)procid + 1);
netlink_add_addr6(&nlmsg, sock, dev, addr);
}
int macsize = devtypes[i].macsize;
uint64_t macaddr = 0xbbbbbb + ((unsigned long long)i << (8 * (macsize - 2))) +
(procid << (8 * (macsize - 1)));
netlink_device_change(&nlmsg, sock, dev, !devtypes[i].noup, 0, &macaddr, macsize, NULL);
}
close(sock);}
#define MAX_FDS 30
static long syz_genetlink_get_family_id(volatile long name, volatile long sock_arg)
{
int fd = sock_arg;
if (fd < 0) {
fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_GENERIC);
if (fd == -1) {
return -1;
}
}
struct nlmsg nlmsg_tmp;
int ret = netlink_query_family_id(&nlmsg_tmp, fd, (char*)name, false);
if ((int)sock_arg < 0)
close(fd);
if (ret < 0) {
return -1;
}
return ret;
}static void setup_gadgetfs();
static void setup_binderfs();
static void setup_fusectl();
static void sandbox_common_mount_tmpfs(void)
{
write_file("/proc/sys/fs/mount-max", "100000");
if (mkdir("./syz-tmp", 0777))
exit(1);
if (mount("", "./syz-tmp", "tmpfs", 0, NULL))
exit(1);
if (mkdir("./syz-tmp/newroot", 0777))
exit(1);
if (mkdir("./syz-tmp/newroot/dev", 0700))
exit(1);
unsigned bind_mount_flags = MS_BIND | MS_REC | MS_PRIVATE;
if (mount("/dev", "./syz-tmp/newroot/dev", NULL, bind_mount_flags, NULL))
exit(1);
if (mkdir("./syz-tmp/newroot/proc", 0700))
exit(1);
if (mount("syz-proc", "./syz-tmp/newroot/proc", "proc", 0, NULL))
exit(1);
if (mkdir("./syz-tmp/newroot/selinux", 0700))
exit(1);
const char* selinux_path = "./syz-tmp/newroot/selinux";
if (mount("/selinux", selinux_path, NULL, bind_mount_flags, NULL)) {
if (errno != ENOENT)
exit(1);
if (mount("/sys/fs/selinux", selinux_path, NULL, bind_mount_flags, NULL) && errno != ENOENT)
exit(1);
}
if (mkdir("./syz-tmp/newroot/sys", 0700))
exit(1);
if (mount("/sys", "./syz-tmp/newroot/sys", 0, bind_mount_flags, NULL))
exit(1);
if (mount("/sys/kernel/debug", "./syz-tmp/newroot/sys/kernel/debug", NULL, bind_mount_flags, NULL) && errno != ENOENT)
exit(1);
if (mount("/sys/fs/smackfs", "./syz-tmp/newroot/sys/fs/smackfs", NULL, bind_mount_flags, NULL) && errno != ENOENT)
exit(1);
if (mount("/proc/sys/fs/binfmt_misc", "./syz-tmp/newroot/proc/sys/fs/binfmt_misc", NULL, bind_mount_flags, NULL) && errno != ENOENT)
exit(1);
if (mkdir("./syz-tmp/newroot/syz-inputs", 0700))
exit(1);
if (mount("/syz-inputs", "./syz-tmp/newroot/syz-inputs", NULL, bind_mount_flags | MS_RDONLY, NULL) && errno != ENOENT)
exit(1);
if (mkdir("./syz-tmp/pivot", 0777))
exit(1);
if (syscall(SYS_pivot_root, "./syz-tmp", "./syz-tmp/pivot")) {
if (chdir("./syz-tmp"))
exit(1);
} else {
if (chdir("/"))
exit(1);
if (umount2("./pivot", MNT_DETACH))
exit(1);
}
if (chroot("./newroot"))
exit(1);
if (chdir("/"))
exit(1);
setup_gadgetfs();
setup_binderfs();
setup_fusectl();
}static void setup_gadgetfs()
{
if (mkdir("/dev/gadgetfs", 0777)) {
}
if (mount("gadgetfs", "/dev/gadgetfs", "gadgetfs", 0, NULL)) {
}
}static void setup_fusectl()
{
if (mount(0, "/sys/fs/fuse/connections", "fusectl", 0, 0)) {
}
}static void setup_binderfs()
{
if (mkdir("/dev/binderfs", 0777)) {
}
if (mount("binder", "/dev/binderfs", "binder", 0, NULL)) {
}
if (symlink("/dev/binderfs", "./binderfs")) {
}
}static void loop();
static void sandbox_common()
{
prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0);
if (getppid() == 1)
exit(1);
struct rlimit rlim;
rlim.rlim_cur = rlim.rlim_max = (200 << 20);
setrlimit(RLIMIT_AS, &rlim);
rlim.rlim_cur = rlim.rlim_max = 32 << 20;
setrlimit(RLIMIT_MEMLOCK, &rlim);
rlim.rlim_cur = rlim.rlim_max = 136 << 20;
setrlimit(RLIMIT_FSIZE, &rlim);
rlim.rlim_cur = rlim.rlim_max = 1 << 20;
setrlimit(RLIMIT_STACK, &rlim);
rlim.rlim_cur = rlim.rlim_max = 128 << 20;
setrlimit(RLIMIT_CORE, &rlim);
rlim.rlim_cur = rlim.rlim_max = 256;
setrlimit(RLIMIT_NOFILE, &rlim);
if (unshare(CLONE_NEWNS)) {
}
if (mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, NULL)) {
}
if (unshare(CLONE_NEWIPC)) {
}
if (unshare(0x02000000)) {
}
if (unshare(CLONE_NEWUTS)) {
}
if (unshare(CLONE_SYSVSEM)) {
}
typedef struct {
const char* name;
const char* value;
} sysctl_t;
static const sysctl_t sysctls[] = {
{"/proc/sys/kernel/shmmax", "16777216"},
{"/proc/sys/kernel/shmall", "536870912"},
{"/proc/sys/kernel/shmmni", "1024"},
{"/proc/sys/kernel/msgmax", "8192"},
{"/proc/sys/kernel/msgmni", "1024"},
{"/proc/sys/kernel/msgmnb", "1024"},
{"/proc/sys/kernel/sem", "1024 1048576 500 1024"},
};
unsigned i;
for (i = 0; i < sizeof(sysctls) / sizeof(sysctls[0]); i++)
write_file(sysctls[i].name, sysctls[i].value);
}static int wait_for_loop(int pid)
{
if (pid < 0)
exit(1);
int status = 0;
while (waitpid(-1, &status, __WALL) != pid) {
}
return WEXITSTATUS(status);
}static void drop_caps(void)
{
struct __user_cap_header_struct cap_hdr = {};
struct __user_cap_data_struct cap_data[2] = {};
cap_hdr.version = _LINUX_CAPABILITY_VERSION_3;
cap_hdr.pid = getpid();
if (syscall(SYS_capget, &cap_hdr, &cap_data))
exit(1);
const int drop = (1 << CAP_SYS_PTRACE) | (1 << CAP_SYS_NICE);
cap_data[0].effective &= ~drop;
cap_data[0].permitted &= ~drop;
cap_data[0].inheritable &= ~drop;
if (syscall(SYS_capset, &cap_hdr, &cap_data))
exit(1);
}static int do_sandbox_none(void)
{
if (unshare(CLONE_NEWPID)) {
}
int pid = fork();
if (pid != 0)
return wait_for_loop(pid);
sandbox_common();
drop_caps();
initialize_netdevices_init();
if (unshare(CLONE_NEWNET)) {
}
write_file("/proc/sys/net/ipv4/ping_group_range", "0 65535");
initialize_netdevices();
sandbox_common_mount_tmpfs();
loop();
exit(1);
}static void kill_and_wait(int pid, int* status)
{
kill(-pid, SIGKILL);
kill(pid, SIGKILL);
for (int i = 0; i < 100; i++) {
if (waitpid(-1, status, WNOHANG | __WALL) == pid)
return;
usleep(1000);
}
DIR* dir = opendir("/sys/fs/fuse/connections");
if (dir) {
for (;;) {
struct dirent* ent = readdir(dir);
if (!ent)
break;
if (strcmp(ent->d_name, ".") == 0 || strcmp(ent->d_name, "..") == 0)
continue;
char abort[300];
snprintf(abort, sizeof(abort), "/sys/fs/fuse/connections/%s/abort", ent->d_name);
int fd = open(abort, O_WRONLY);
if (fd == -1) {
continue;
}
if (write(fd, abort, 1) < 0) {
}
close(fd);
}
closedir(dir);
} else {
}
while (waitpid(-1, status, __WALL) != pid) {
}
}static void setup_test()
{
prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0);
setpgrp();
write_file("/proc/self/oom_score_adj", "1000");
}static void close_fds()
{
for (int fd = 3; fd < MAX_FDS; fd++)
close(fd);
}#define USLEEP_FORKED_CHILD (3 * 50 *1000)
static long handle_clone_ret(long ret)
{
if (ret != 0) {
return ret;
}
usleep(USLEEP_FORKED_CHILD);
syscall(__NR_exit, 0);
while (1) {
}
}static long syz_clone(volatile long flags, volatile long stack, volatile long stack_len,
volatile long ptid, volatile long ctid, volatile long tls)
{
long sp = (stack + stack_len) & ~15;
long ret = (long)syscall(__NR_clone, flags & ~CLONE_VM, sp, ptid, ctid, tls);
return handle_clone_ret(ret);
}struct thread_t {
int created, call;
event_t ready, done;
};static struct thread_t threads[16];
static void execute_call(int call);
static int running;
static void* thr(void* arg)
{
struct thread_t* th = (struct thread_t*)arg;
for (;;) {
event_wait(&th->ready);
event_reset(&th->ready);
execute_call(th->call);
__atomic_fetch_sub(&running, 1, __ATOMIC_RELAXED);
event_set(&th->done);
}
return 0;
}static void execute_one(void)
{
if (write(1, "executing program\n", sizeof("executing program\n") - 1)) {
}
int i, call, thread;
for (call = 0; call < 9; call++) {
for (thread = 0; thread < (int)(sizeof(threads) / sizeof(threads[0])); thread++) {
struct thread_t* th = &threads[thread];
if (!th->created) {
th->created = 1;
event_init(&th->ready);
event_init(&th->done);
event_set(&th->done);
thread_start(thr, th);
}
if (!event_isset(&th->done))
continue;
event_reset(&th->done);
th->call = call;
__atomic_fetch_add(&running, 1, __ATOMIC_RELAXED);
event_set(&th->ready);
event_timedwait(&th->done, 50);
break;
}
}
for (i = 0; i < 100 && __atomic_load_n(&running, __ATOMIC_RELAXED); i++)
sleep_ms(1);
close_fds();
}static void execute_one(void);
#define WAIT_FLAGS __WALL
static void loop(void)
{
int iter = 0;
for (;; iter++) {
int pid = fork();
if (pid < 0)
exit(1);
if (pid == 0) {
setup_test();
execute_one();
exit(0);
}
int status = 0;
uint64_t start = current_time_ms();
for (;;) {
sleep_ms(10);
if (waitpid(-1, &status, WNOHANG | WAIT_FLAGS) == pid)
break;
if (current_time_ms() - start < 5000)
continue;
kill_and_wait(pid, &status);
break;
}
}
}uint64_t r[5] = {0xffffffffffffffff, 0x0, 0x0, 0xffffffffffffffff, 0xffffffffffffffff};
void execute_call(int call)
{
intptr_t res = 0;
switch (call) {
case 0:
// socket$nl_generic arguments: [
// domain: const = 0x10 (8 bytes)
// type: const = 0x3 (8 bytes)
// proto: const = 0x10 (4 bytes)
// ]
// returns sock_nl_generic
res = syscall(__NR_socket, /*domain=*/0x10ul, /*type=*/3ul, /*proto=*/0x10);
if (res != -1)
r[0] = res;
break;
case 1:// syz_genetlink_get_family_id$devlink arguments: [
// name: ptr[in, buffer] {
// buffer: {64 65 76 6c 69 6e 6b 00} (length 0x8)
// }
// fd: sock_nl_generic (resource)
// ]
// returns genl_devlink_family_id
memcpy((void*)0x200000000080, "devlink\000", 8); res = -1; res = syz_genetlink_get_family_id(/*name=*/0x200000000080, /*fd=*/-1); if (res != -1) r[1] = res; break; case 2: // gettid arguments: [ // ] // returns pid res = syscall(__NR_gettid); if (res != -1) r[2] = res; break; case 3:
// sendmsg$DEVLINK_CMD_RELOAD arguments: [
// fd: sock_nl_generic (resource)
// msg: ptr[in, msghdr_netlink[netlink_msg_t[genl_devlink_family_id, genlmsghdr_t[DEVLINK_CMD_RELOAD], devlink_reload_policy]]] {
// msghdr_netlink[netlink_msg_t[genl_devlink_family_id, genlmsghdr_t[DEVLINK_CMD_RELOAD], devlink_reload_policy]] {
// addr: nil
// addrlen: len = 0x0 (4 bytes)
// pad = 0x0 (4 bytes)
// vec: ptr[in, iovec[in, netlink_msg_t[genl_devlink_family_id, genlmsghdr_t[DEVLINK_CMD_RELOAD], devlink_reload_policy]]] {
// iovec[in, netlink_msg_t[genl_devlink_family_id, genlmsghdr_t[DEVLINK_CMD_RELOAD], devlink_reload_policy]] {
// addr: ptr[in, netlink_msg_t[genl_devlink_family_id, genlmsghdr_t[DEVLINK_CMD_RELOAD], devlink_reload_policy]] {
// netlink_msg_t[genl_devlink_family_id, genlmsghdr_t[DEVLINK_CMD_RELOAD], devlink_reload_policy] {
// len: len = 0x3c (4 bytes)
// type: genl_devlink_family_id (resource)
// flags: netlink_msg_flags = 0x536ae464467e3e0b (2 bytes)
// seq: int32 = 0x0 (4 bytes)
// pid: int32 = 0x0 (4 bytes)
// payload: genlmsghdr_t[DEVLINK_CMD_RELOAD] {
// cmd: const = 0x25 (1 bytes)
// version: const = 0x0 (1 bytes)
// reserved: const = 0x0 (2 bytes)// }
// attrs: array[devlink_reload_policy] {
// devlink_reload_policy {
// handle: union devlink_handle {
// nsim: devlink_nl_policy$nsim {
// DEVLINK_ATTR_BUS_NAME: nlattr_t[const[DEVLINK_ATTR_BUS_NAME, int16], string["netdevsim"]] {
// nla_len: offsetof = 0xe (2 bytes)
// nla_type: const = 0x1 (2 bytes)
// payload: buffer: {6e 65 74 64 65 76 73 69 6d 00} (length 0xa)
// size: buffer: {} (length 0x0)
// pad = 0x0 (2 bytes)
// }
// DEVLINK_ATTR_DEV_NAME: nlattr_t[const[DEVLINK_ATTR_DEV_NAME, int16], devlink_devname] {
// nla_len: offsetof = 0xf (2 bytes)
// nla_type: const = 0x2 (2 bytes)
// payload: devlink_devname {
// prefix: buffer: {6e 65 74 64 65 76 73 69 6d} (length 0x9)
// id: proc = 0x0 (1 bytes)
// z: const = 0x0 (1 bytes)
// }
// size: buffer: {} (length 0x0)
// pad = 0x0 (1 bytes)// }
// }
// }
// arg: union devlink_nl_policy$reload {
// DEVLINK_ATTR_NETNS_PID: nlattr_t[const[DEVLINK_ATTR_NETNS_PID, int16], pid] {
// nla_len: offsetof = 0x8 (2 bytes)
// nla_type: const = 0x8b (2 bytes)
// payload: pid (resource)
// size: buffer: {} (length 0x0)// }
// }
// }
// }
// }
// }
// len: len = 0x3c (8 bytes)
// }
// } // vlen: const = 0x1 (8 bytes) // ctrl: const = 0x0 (8 bytes) // ctrllen: const = 0x0 (8 bytes) // f: send_flags = 0x0 (4 bytes) // pad = 0x0 (4 bytes)
// }
// }
// f: send_flags = 0x0 (8 bytes)
// ]
*(uint64_t*)0x200000000800 = 0; *(uint32_t*)0x200000000808 = 0; *(uint64_t*)0x200000000810 = 0x200000000380; *(uint64_t*)0x200000000380 = 0x200000000000; *(uint32_t*)0x200000000000 = 0x3c; *(uint16_t*)0x200000000004 = r[1]; *(uint16_t*)0x200000000006 = 0x3e0b; *(uint32_t*)0x200000000008 = 0; *(uint32_t*)0x20000000000c = 0; *(uint8_t*)0x200000000010 = 0x25; *(uint8_t*)0x200000000011 = 0; *(uint16_t*)0x200000000012 = 0; *(uint16_t*)0x200000000014 = 0xe; *(uint16_t*)0x200000000016 = 1; memcpy((void*)0x200000000018, "netdevsim\000", 10); *(uint16_t*)0x200000000024 = 0xf; *(uint16_t*)0x200000000026 = 2; memcpy((void*)0x200000000028, "netdevsim", 9); *(uint8_t*)0x200000000031 = 0x30; *(uint8_t*)0x200000000032 = 0; *(uint16_t*)0x200000000034 = 8; *(uint16_t*)0x200000000036 = 0x8b; *(uint32_t*)0x200000000038 = r[2]; *(uint64_t*)0x200000000388 = 0x3c; *(uint64_t*)0x200000000818 = 1; *(uint64_t*)0x200000000820 = 0; *(uint64_t*)0x200000000828 = 0;
*(uint32_t*)0x200000000830 = 0; syscall(__NR_sendmsg, /*fd=*/r[0], /*msg=*/0x200000000800ul, /*f=*/0ul); break; case 4: // syz_clone arguments: [ // flags: clone_flags = 0x40b04000 (8 bytes) // stack: nil // stack_len: bytesize = 0x0 (8 bytes) // parentid: nil // childtid: nil // tls: nil // ] // returns pid syz_clone(/*flags=CLONE_NEWNET|CLONE_UNTRACED|CLONE_CHILD_CLEARTID|CLONE_PARENT_SETTID|CLONE_VFORK*/0x40b04000, /*stack=*/0, /*stack_len=*/0, /*parentid=*/0, /*childtid=*/0, /*tls=*/0); break; case 5: // socket$netlink arguments: [ // domain: const = 0x10 (8 bytes) // type: const = 0x3 (8 bytes) // proto: netlink_proto = 0x0 (4 bytes) // ] // returns sock_netlink res = syscall(__NR_socket, /*domain=*/0x10ul, /*type=*/3ul, /*proto=*/0); if (res != -1) r[3] = res; break; case 6:
// sendmsg$nl_route arguments: [
// fd: sock_nl_route (resource)
// msg: ptr[in, msghdr_netlink[netlink_msg_route]] {
// msghdr_netlink[netlink_msg_route] {
// addr: nil
// addrlen: len = 0x0 (4 bytes)
// pad = 0x0 (4 bytes)
// vec: ptr[in, iovec[in, netlink_msg_route]] {// iovec[in, netlink_msg_route] {
// addr: ptr[in, netlink_msg_route] {
// union netlink_msg_route {
// newlink: netlink_msg_t[const[RTM_NEWLINK, int16], ifinfomsg[AF_UNSPEC], ifla_policy] {
// len: len = 0x28 (4 bytes)
// type: const = 0x10 (2 bytes)
// flags: netlink_msg_flags = 0x1 (2 bytes)
// seq: int32 = 0x0 (4 bytes)
// pid: int32 = 0x0 (4 bytes)
// payload: ifinfomsg[AF_UNSPEC] {
// ifi_family: const = 0x0 (1 bytes)
// __ifi_pad: const = 0x0 (1 bytes)
// ifi_type: const = 0x0 (2 bytes)
// ifi_index: ifindex (resource)
// ifi_flags: net_device_flags = 0xf0ffff (4 bytes)
// ifi_change: net_device_flags = 0x0 (4 bytes)// }
// attrs: array[ifla_policy] {
// union ifla_policy {
// IFLA_GROUP: nlattr_t[const[IFLA_GROUP, int16], int32] {
// nla_len: offsetof = 0x8 (2 bytes)
// nla_type: const = 0x1b (2 bytes)
// payload: int32 = 0x0 (4 bytes)
// size: buffer: {} (length 0x0)// }
// }
// }
// }
// }
// }
// len: len = 0x28 (8 bytes)
// }
// } // vlen: const = 0x1 (8 bytes) // ctrl: const = 0x0 (8 bytes) // ctrllen: const = 0x0 (8 bytes) // f: send_flags = 0x0 (4 bytes) // pad = 0x0 (4 bytes)
// }
// }
// f: send_flags = 0x0 (8 bytes)
// ]
*(uint64_t*)0x2000000000c0 = 0;
*(uint32_t*)0x2000000000c8 = 0;
*(uint64_t*)0x2000000000d0 = 0x2000000013c0;
*(uint64_t*)0x2000000013c0 = 0x200000000040;
*(uint32_t*)0x200000000040 = 0x28;
*(uint16_t*)0x200000000044 = 0x10;
*(uint16_t*)0x200000000046 = 1;
*(uint32_t*)0x200000000048 = 0;
*(uint32_t*)0x20000000004c = 0;
*(uint8_t*)0x200000000050 = 0;
*(uint8_t*)0x200000000051 = 0;
*(uint16_t*)0x200000000052 = 0;
*(uint32_t*)0x200000000054 = 0;
*(uint32_t*)0x200000000058 = 0xf0ffff;
*(uint32_t*)0x20000000005c = 0;
*(uint16_t*)0x200000000060 = 8;
*(uint16_t*)0x200000000062 = 0x1b;
*(uint32_t*)0x200000000064 = 0;
*(uint64_t*)0x2000000013c8 = 0x28;
*(uint64_t*)0x2000000000d8 = 1;
*(uint64_t*)0x2000000000e0 = 0;
*(uint64_t*)0x2000000000e8 = 0;
*(uint32_t*)0x2000000000f0 = 0; syscall(__NR_sendmsg, /*fd=*/r[3], /*msg=*/0x2000000000c0ul, /*f=*/0ul); break; case 7: // socket$nl_route arguments: [ // domain: const = 0x10 (8 bytes) // type: const = 0x3 (8 bytes) // proto: const = 0x0 (4 bytes) // ] // returns sock_nl_route res = syscall(__NR_socket, /*domain=*/0x10ul, /*type=*/3ul, /*proto=*/0); if (res != -1) r[4] = res; break; case 8:
// sendmsg$nl_route_sched arguments: [
// fd: sock_nl_route (resource)
// msg: ptr[in, msghdr_netlink[netlink_msg_route_sched]] {
// msghdr_netlink[netlink_msg_route_sched] {
// addr: nil
// addrlen: len = 0x0 (4 bytes)
// pad = 0x0 (4 bytes)
// vec: ptr[in, iovec[in, netlink_msg_route_sched]] {// iovec[in, netlink_msg_route_sched] {
// addr: ptr[in, netlink_msg_route_sched] {
// union netlink_msg_route_sched {
// newqdisc: netlink_msg_t[const[RTM_NEWQDISC, int16], tcmsg[AF_UNSPEC], rtm_tca_policy] {
// len: len = 0x54 (4 bytes)
// type: const = 0x10 (2 bytes)
// flags: netlink_msg_flags = 0x1 (2 bytes)
// seq: int32 = 0x0 (4 bytes)
// pid: int32 = 0x0 (4 bytes)
// payload: tcmsg[AF_UNSPEC] {
// family: const = 0x6 (1 bytes)
// tcm__pad1: const = 0x0 (1 bytes)
// tcm__pad2: const = 0x8100 (2 bytes)
// ifindex: ifindex (resource)
// tcm_handle: tcm_handle {// minor: tcm_handle_offsets = 0x0 (2 bytes)
// major: tcm_handle_offsets = 0x0 (2 bytes)
// }
// tcm_parent: tcm_handle {
// minor: tcm_handle_offsets = 0xfff1 (2 bytes)
// major: tcm_handle_offsets = 0x0 (2 bytes)
// }
// tcm_info: tcm_handle {
// minor: tcm_handle_offsets = 0xe (2 bytes)
// major: tcm_handle_offsets = 0x10 (2 bytes)
// }
// }
// attrs: array[rtm_tca_policy] {
// union rtm_tca_policy {
// TCA_EGRESS_BLOCK: nlattr_t[const[TCA_EGRESS_BLOCK, int16], int32] {
// nla_len: offsetof = 0x8 (2 bytes)
// nla_type: const = 0xe (2 bytes)
// payload: int32 = 0x7 (4 bytes)
// size: buffer: {} (length 0x0)// }
// }
// union rtm_tca_policy {
// TCA_STAB: nlattr_tt[const[TCA_STAB, int16:14], 0, 1, array[stab_policy]] {
// nla_len: offsetof = 0x28 (2 bytes)
// nla_type: const = 0x8 (1 bytes)
// NLA_F_NET_BYTEORDER: const = 0x0 (0 bytes)
// NLA_F_NESTED: const = 0x1 (1 bytes)
// payload: array[stab_policy] {
// stab_policy {
// TCA_STAB_BASE: nlattr_t[const[TCA_STAB_BASE, int16], tc_sizespec] {
// nla_len: offsetof = 0x1c (2 bytes)
// nla_type: const = 0x11 (2 bytes)
// payload: tc_sizespec {
// cell_log: int8 = 0x0 (1 bytes)
// size_log: int8 = 0x0 (1 bytes)
// cell_align: int16 = 0x0 (2 bytes)
// overhead: int32 = 0x0 (4 bytes)
// linklayer: linklayer = 0x0 (4 bytes)
// mpu: int32 = 0x5e06209c (4 bytes)
// mtu: int32 = 0x0 (4 bytes)
// tsize: len = 0x2 (4 bytes)// }
// size: buffer: {} (length 0x0)
// }
// TCA_STAB_DATA: nlattr_t[const[TCA_STAB_DATA, int16], array[int16]] {
// nla_len: offsetof = 0x8 (2 bytes)
// nla_type: const = 0x1b (2 bytes)
// payload: array[int16] {// int16 = 0x0 (2 bytes)
// int16 = 0x0 (2 bytes)
// }
// size: buffer: {} (length 0x0)
// }
// }
// }
// size: buffer: {} (length 0x0)
// }
// }
// }
// }
// }
// }
// len: len = 0x54 (8 bytes)
// }
// } // vlen: const = 0x1 (8 bytes) // ctrl: const = 0x0 (8 bytes) // ctrllen: const = 0x0 (8 bytes) // f: send_flags = 0x0 (4 bytes) // pad = 0x0 (4 bytes)
// }
// }
// f: send_flags = 0x0 (8 bytes)
// ]
*(uint64_t*)0x200000000180 = 0; *(uint32_t*)0x200000000188 = 0; *(uint64_t*)0x200000000190 = 0x200000000280; *(uint64_t*)0x200000000280 = 0x2000000001c0; *(uint32_t*)0x2000000001c0 = 0x54; *(uint16_t*)0x2000000001c4 = 0x10; *(uint16_t*)0x2000000001c6 = 1; *(uint32_t*)0x2000000001c8 = 0; *(uint32_t*)0x2000000001cc = 0; *(uint8_t*)0x2000000001d0 = 6; *(uint8_t*)0x2000000001d1 = 0; *(uint16_t*)0x2000000001d2 = 0x8100; *(uint32_t*)0x2000000001d4 = 0; *(uint16_t*)0x2000000001d8 = 0; *(uint16_t*)0x2000000001da = 0; *(uint16_t*)0x2000000001dc = 0xfff1; *(uint16_t*)0x2000000001de = 0; *(uint16_t*)0x2000000001e0 = 0xe; *(uint16_t*)0x2000000001e2 = 0x10; *(uint16_t*)0x2000000001e4 = 8; *(uint16_t*)0x2000000001e6 = 0xe; *(uint32_t*)0x2000000001e8 = 7; *(uint16_t*)0x2000000001ec = 0x28; STORE_BY_BITMASK(uint16_t, , 0x2000000001ee, 8, 0, 14); STORE_BY_BITMASK(uint16_t, , 0x2000000001ef, 0, 6, 1); STORE_BY_BITMASK(uint16_t, , 0x2000000001ef, 1, 7, 1); *(uint16_t*)0x2000000001f0 = 0x1c; *(uint16_t*)0x2000000001f2 = 0x11; *(uint8_t*)0x2000000001f4 = 0; *(uint8_t*)0x2000000001f5 = 0; *(uint16_t*)0x2000000001f6 = 0; *(uint32_t*)0x2000000001f8 = 0; *(uint32_t*)0x2000000001fc = 0; *(uint32_t*)0x200000000200 = 0x5e06209c; *(uint32_t*)0x200000000204 = 0; *(uint32_t*)0x200000000208 = 2; *(uint16_t*)0x20000000020c = 8; *(uint16_t*)0x20000000020e = 0x1b; *(uint16_t*)0x200000000210 = 0; *(uint16_t*)0x200000000212 = 0; *(uint64_t*)0x200000000288 = 0x54; *(uint64_t*)0x200000000198 = 1; *(uint64_t*)0x2000000001a0 = 0; *(uint64_t*)0x2000000001a8 = 0;
*(uint32_t*)0x2000000001b0 = 0; syscall(__NR_sendmsg, /*fd=*/r[4], /*msg=*/0x200000000180ul, /*f=*/0ul); break; }
}
int main(void)
{
syscall(__NR_mmap, /*addr=*/0x1ffffffff000ul, /*len=*/0x1000ul, /*prot=*/0ul, /*flags=MAP_FIXED|MAP_ANONYMOUS|MAP_PRIVATE*/0x32ul, /*fd=*/(intptr_t)-1, /*offset=*/0ul);
syscall(__NR_mmap, /*addr=*/0x200000000000ul, /*len=*/0x1000000ul, /*prot=PROT_WRITE|PROT_READ|PROT_EXEC*/7ul, /*flags=MAP_FIXED|MAP_ANONYMOUS|MAP_PRIVATE*/0x32ul, /*fd=*/(intptr_t)-1, /*offset=*/0ul);
syscall(__NR_mmap, /*addr=*/0x200001000000ul, /*len=*/0x1000ul, /*prot=*/0ul, /*flags=MAP_FIXED|MAP_ANONYMOUS|MAP_PRIVATE*/0x32ul, /*fd=*/(intptr_t)-1, /*offset=*/0ul);
const char* reason;
(void)reason;
do_sandbox_none();
return 0;
}Quoted 11 lines · Yue Sun
Hello,
I hit a reproducible use-after-free in the UDP tunnel NIC offload work item. The original local crash was reported by KFENCE as:
KFENCE: use-after-free read in
udp_tunnel_nic_device_sync_workOn current mainline, the C reproducer below triggers the same lifetime bug, reported by KASAN before KFENCE samples the object:
Quoted 8 lines
BUG: KASAN: slab-use-after-free in __mutex_lock Workqueue: udp_tunnel_nic udp_tunnel_nic_device_sync_workTested kernel:
840ef6c78e6a("Merge tag 'nfs-for-7.2-1' ofgit://git.linux-nfs.org/projects/anna/linux-nfs")
Linux 7.1.0-11240-g840ef6c78e6a #31 SMPPREEMPT_DYNAMIC
Thanks or the report.
Can you test the following patch?
net/ipv4/udp_tunnel_nic.c +0 -0
100644
net/ipv4/udp_tunnel_nic.c +0 -0
@@ -304,8 +304,8 @@ udp_tunnel_nic_device_sync(struct net_device *dev,
struct udp_tunnel_nic *utn)
if (!utn->need_sync)
return;- queue_work(udp_tunnel_nic_workqueue, &utn->work);
utn->work_pending = 1;+ queue_work(udp_tunnel_nic_workqueue, &utn->work);
}
static bool
@@ -866,6 +866,11 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn)
udp_tunnel_nic_lock(dev);
+ if (utn->work_pending) {
+ udp_tunnel_nic_unlock(dev);
+ return;
+ }
+
/* For a shared table remove this dev from the list of sharing devices
* and if there are other devices just detach.
*/
@@ -901,12 +906,6 @@ udp_tunnel_nic_unregister(struct net_device *dev,
struct udp_tunnel_nic *utn)
udp_tunnel_nic_flush(dev, utn);
udp_tunnel_nic_unlock(dev);- /* Wait for the work to be done using the state, netdev core will
- * retry unregister until we give up our reference on this device.
- */
- if (utn->work_pending)
- return;
-
udp_tunnel_nic_free(utn);
release_dev:
dev->udp_tunnel_nic = NULL;Quoted 69 lines · Eric Dumazet
Quoted 11 lines · Yue Sun
Hello,
I hit a reproducible use-after-free in the UDP tunnel NIC offload work item. The original local crash was reported by KFENCE as:
KFENCE: use-after-free read in
udp_tunnel_nic_device_sync_workOn current mainline, the C reproducer below triggers the same lifetime bug, reported by KASAN before KFENCE samples the object:
Quoted 8 lines
BUG: KASAN: slab-use-after-free in __mutex_lock Workqueue: udp_tunnel_nic udp_tunnel_nic_device_sync_workTested kernel:
840ef6c78e6a("Merge tag 'nfs-for-7.2-1' ofgit://git.linux-nfs.org/projects/anna/linux-nfs")
Linux 7.1.0-11240-g840ef6c78e6a #31 SMPPREEMPT_DYNAMICThanks or the report.
Can you test the following patch?
net/ipv4/udp_tunnel_nic.c +0
-0100644
net/ipv4/udp_tunnel_nic.c +1
-1@@ -304,8 +304,8 @@ udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn)if (!utn->need_sync)return ; -queue_work (udp_tunnel_nic_workqueue, &utn->work); utn->work_pending =1 ; +queue_work (udp_tunnel_nic_workqueue, &utn->work); }static bool
net/ipv4/udp_tunnel_nic.c +5
-0@@ -866,6 +866,11 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn)udp_tunnel_nic_lock (dev ); +if (utn->work_pending) { +udp_tunnel_nic_unlock (dev); +return ; + } +/* For a shared table remove this dev from the list of sharing devices * and if there are other devices just detach. */net/ipv4/udp_tunnel_nic.c +0
-6@@ -901,12 +906,6 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn)udp_tunnel_nic_flush (dev ,utn );udp_tunnel_nic_unlock (dev); -/* Wait for the work to be done using the state, netdev core will -* retry unregister until we give up our reference on this device. -*/ -if (utn->work_pending) -return ; -udp_tunnel_nic_free (utn); release_dev:
Quoted 1 line
dev->udp_tunnel_nic = NULL;
I tested the patch, but unfortunately the C reproducer still triggers the same use-after-free for me.
Tested on top of:
840ef6c78e6a ("Merge tag 'nfs-for-7.2-1' ofgit://git.linux-nfs.org/projects/anna/linux-nfs")
I booted the kernel with KASAN/KFENCE enabled and:
panic_on_warn=1 panic_on_oops=1 kfence.sample_interval=1
Then I ran the same C reproducer:
timeout -k 10 360 /root/repro
The VM panicked after about 236 seconds:
[ 236.471119][ T58] BUG: KASAN: slab-use-after-free in __mutex_lock+0x16d0/0x1d80 [ 236.473404][ T58] Read of size 8 at addr ff11000076a63ea8 by task kworker/u16:3/58 [ 236.476455][ T58] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 [ 236.476478][ T58] Workqueue: udp_tunnel_nic udp_tunnel_nic_device_sync_work [ 236.476787][ T58] __mutex_lock+0x16d0/0x1d80 [ 236.477020][ T58] udp_tunnel_nic_device_sync_work+0x32/0x9c0 [ 236.477068][ T58] process_one_work+0x9de/0x1bf0
The allocation/free stacks are still the same shape:
``` Allocated by task 11563: __kmalloc_noprof udp_tunnel_nic_netdevice_event+0x12d8/0x1e80 register_netdevice nsim_create nsim_dev_reload_up devlink_reload Freed by task 11609: kfree udp_tunnel_nic_netdevice_event+0xc26/0x1e80 unregister_netdevice_many_notify nsim_destroy nsim_dev_reload_down devlink_reload Last potentially related work creation: queue_work_on __udp_tunnel_nic_del_port+0x2af/0x320 udp_tunnel_notify_del_rx_port __geneve_sock_release.part.0 geneve_stop Second to last potentially related work creation: queue_work_on __udp_tunnel_nic_add_port+0x6ec/0xd70 udp_tunnel_notify_add_rx_port geneve_open ```
My read of the patch is that it closes the small window where queue_work() can publish the work before utn->work_pending is set, and it also prevents udp_tunnel_nic_unregister() from flushing/freeing the object when work_pending is already set.
However, the test above suggests that work_pending still does not fully protect the lifetime of struct udp_tunnel_nic. The crashing work was still queued through udp_tunnel_nic_device_sync() at line 308, so the patched path was exercised. One suspicious point is that udp_tunnel_nic_device_sync_work() clears utn->work_pending at the beginning of the worker, while the same work item can still interact with replay/add/del-port state. The reproducer can still end up with udp_tunnel_nic_unregister() freeing utn while a udp_tunnel_nic_device_sync_work item later runs and dereferences the freed utn->lock.
So this patch does not seem to be sufficient for this reproducer.
Thanks,
Yue
Quoted 149 lines · Sam Sun
Quoted 69 lines · Eric Dumazet
Quoted 11 lines · Yue Sun
Hello,
I hit a reproducible use-after-free in the UDP tunnel NIC offload work item. The original local crash was reported by KFENCE as:
KFENCE: use-after-free read in
udp_tunnel_nic_device_sync_workOn current mainline, the C reproducer below triggers the same lifetime bug, reported by KASAN before KFENCE samples the object:
Quoted 8 lines
BUG: KASAN: slab-use-after-free in __mutex_lock Workqueue: udp_tunnel_nic udp_tunnel_nic_device_sync_workTested kernel:
840ef6c78e6a("Merge tag 'nfs-for-7.2-1' ofgit://git.linux-nfs.org/projects/anna/linux-nfs")
Linux 7.1.0-11240-g840ef6c78e6a #31 SMPPREEMPT_DYNAMICThanks or the report.
Can you test the following patch?
net/ipv4/udp_tunnel_nic.c +0
-0100644
net/ipv4/udp_tunnel_nic.c +1
-1@@ -304,8 +304,8 @@ udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn)if (!utn->need_sync)return ; -queue_work (udp_tunnel_nic_workqueue, &utn->work); utn->work_pending =1 ; +queue_work (udp_tunnel_nic_workqueue, &utn->work); }static bool
net/ipv4/udp_tunnel_nic.c +5
-0@@ -866,6 +866,11 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn)udp_tunnel_nic_lock (dev ); +if (utn->work_pending) { +udp_tunnel_nic_unlock (dev); +return ; + } +/* For a shared table remove this dev from the list of sharing devices * and if there are other devices just detach. */net/ipv4/udp_tunnel_nic.c +0
-6@@ -901,12 +906,6 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn)udp_tunnel_nic_flush (dev ,utn );udp_tunnel_nic_unlock (dev); -/* Wait for the work to be done using the state, netdev core will -* retry unregister until we give up our reference on this device. -*/ -if (utn->work_pending) -return ; -udp_tunnel_nic_free (utn); release_dev:Quoted 1 line
dev->udp_tunnel_nic = NULL;I tested the patch, but unfortunately the C reproducer still triggers the same use-after-free for me.
Tested on top of:
840ef6c78e6a("Merge tag 'nfs-for-7.2-1' ofgit://git.linux-nfs.org/projects/anna/linux-nfs")I booted the kernel with KASAN/KFENCE enabled and:
panic_on_warn=1 panic_on_oops=1 kfence.sample_interval=1
Then I ran the same C reproducer:
timeout -k 10 360
/root/reproThe VM panicked after about 236 seconds:
[ 236.471119][ T58] BUG: KASAN: slab-use-after-free in __mutex_lock+0x16d0/0x1d80 [ 236.473404][ T58] Read of size 8 at addr ff11000076a63ea8 by task kworker/u16:3/58 [ 236.476455][ T58] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 [ 236.476478][ T58] Workqueue: udp_tunnel_nic udp_tunnel_nic_device_sync_work [ 236.476787][ T58] __mutex_lock+0x16d0/0x1d80 [ 236.477020][ T58] udp_tunnel_nic_device_sync_work+0x32/0x9c0 [ 236.477068][ T58] process_one_work+0x9de/0x1bf0The allocation/free stacks are still the same shape:
``` Allocated by task 11563: __kmalloc_noprof udp_tunnel_nic_netdevice_event+0x12d8/0x1e80 register_netdevice nsim_create nsim_dev_reload_up devlink_reload Freed by task 11609: kfree udp_tunnel_nic_netdevice_event+0xc26/0x1e80 unregister_netdevice_many_notify nsim_destroy nsim_dev_reload_down devlink_reload Last potentially related work creation: queue_work_on __udp_tunnel_nic_del_port+0x2af/0x320 udp_tunnel_notify_del_rx_port __geneve_sock_release.part.0 geneve_stop Second to last potentially related work creation: queue_work_on __udp_tunnel_nic_add_port+0x6ec/0xd70 udp_tunnel_notify_add_rx_port geneve_open ```My read of the patch is that it closes the small window where
queue_work()can publish the work beforeutn->work_pendingis set, and it also preventsudp_tunnel_nic_unregister()from flushing/freeing the object whenwork_pendingis already set.However, the test above suggests that
work_pendingstill does not fully protect the lifetime of structudp_tunnel_nic. The crashing work was still queued throughudp_tunnel_nic_device_sync()at line 308, so the patched path was exercised. One suspicious point is thatudp_tunnel_nic_device_sync_work()clearsutn->work_pendingat the beginning of the worker, while the same work item can still interact with replay/add/del-port state. The reproducer can still end up withudp_tunnel_nic_unregister()freeing utn while audp_tunnel_nic_device_sync_workitem later runs and dereferences the freedutn->lock.
Quoted 2 lines
So this patch does not seem to be sufficient for this reproducer.
Oh well.
u8 need_sync:1;
u8 need_replay:1;
u8 work_pending:1;
These bitfields are not safe, obviously :/
Time to convert them to atomic bit operations.
Quoted 9 lines · Eric Dumazet
Oh well.
u8 need_sync:1;
u8 need_replay:1;
u8 work_pending:1;These bitfields are not safe, obviously :/
Time to convert them to atomic bit operations.
Can you try:
net/ipv4/udp_tunnel_nic.c +0 -0
100644
net/ipv4/udp_tunnel_nic.c +6 -7
@@ -30,9 +30,7 @@ struct udp_tunnel_nic_table_entry {* @work: async work for talking to hardware from process context * @dev: netdev pointer * @lock: protects all fields -* @need_sync: at least one port start changed -* @need_replay: space was freed, we need a replay of all ports -* @work_pending: @work is currently scheduled +* @flags: sync, replay, pending flags * @n_tables: number of tables under @entries * @missed: bitmap of tables which overflown * @entries: table of tables of ports currently offloaded
@@ -44,9 +42,10 @@ struct udp_tunnel_nic {struct mutex lock; - u8 need_sync:1; - u8 need_replay:1; - u8 work_pending:1; +unsigned long flags; +#define UDP_TUNNEL_NIC_NEED_SYNC 0 +#define UDP_TUNNEL_NIC_NEED_REPLAY 1 +#define UDP_TUNNEL_NIC_WORK_PENDING 2unsigned int n_tables;unsigned long missed;
@@ -116,7 +115,7 @@ udp_tunnel_nic_entry_queue(struct udp_tunnel_nic *utn, unsigned int flag) { entry->flags |= flag; - utn->need_sync =1 ; +set_bit (UDP_TUNNEL_NIC_NEED_SYNC , &utn->flags); } static void
@@ -283,7 +282,7 @@ udp_tunnel_nic_device_sync_by_table(struct net_device *dev, static void __udp_tunnel_nic_device_sync(struct net_device *dev, struct
udp_tunnel_nic *utn)
{
- if (!utn->need_sync)
+ if (!test_bit(UDP_TUNNEL_NIC_NEED_SYNC, &utn->flags))
return;
if (dev->udp_tunnel_nic_info->sync_table)
@@ -291,21 +290,24 @@ __udp_tunnel_nic_device_sync(struct net_device
*dev, struct udp_tunnel_nic *utn)
else
udp_tunnel_nic_device_sync_by_port(dev, utn);- utn->need_sync = 0;
+ clear_bit(UDP_TUNNEL_NIC_NEED_SYNC, &utn->flags);
/* Can't replay directly here, in case we come from the tunnel driver's
* notification - trying to replay may deadlock inside tunnel driver.
*/- utn->need_replay = udp_tunnel_nic_should_replay(dev, utn);
+ if (udp_tunnel_nic_should_replay(dev, utn))
+ set_bit(UDP_TUNNEL_NIC_NEED_REPLAY, &utn->flags);
+ else
+ clear_bit(UDP_TUNNEL_NIC_NEED_REPLAY, &utn->flags);
}
static void
udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn) {
- if (!utn->need_sync)
+ if (!test_bit(UDP_TUNNEL_NIC_NEED_SYNC, &utn->flags))
return;
+ set_bit(UDP_TUNNEL_NIC_WORK_PENDING, &utn->flags);
queue_work(udp_tunnel_nic_workqueue, &utn->work);- utn->work_pending = 1;
}
static bool
@@ -348,7 +350,7 @@ udp_tunnel_nic_has_collision(struct net_device *dev, struct udp_tunnel_nic *utn,
if (!udp_tunnel_nic_entry_is_free(entry) &&
entry->port == ti->port &&
entry->type != ti->type) {
- __set_bit(i, &utn->missed);
+ set_bit(i, &utn->missed);
return true;
}
}@@ -483,7 +485,7 @@ udp_tunnel_nic_add_new(struct net_device *dev, struct udp_tunnel_nic *utn,
* are no devices currently which have multiple tables accepting
* the same tunnel type, and false positives are okay. */
- __set_bit(i, &utn->missed);
+ set_bit(i, &utn->missed);
}
return false;@@ -552,7 +554,7 @@ static void __udp_tunnel_nic_reset_ntf(struct net_device *dev)
mutex_lock(&utn->lock);
- utn->need_sync = false;
+ clear_bit(UDP_TUNNEL_NIC_NEED_SYNC, &utn->flags);
for (i = 0; i < utn->n_tables; i++)
for (j = 0; j < info->tables[i].n_entries; j++) {
struct udp_tunnel_nic_table_entry *entry;
@@ -696,8 +698,8 @@ udp_tunnel_nic_flush(struct net_device *dev,
struct udp_tunnel_nic *utn)
for (i = 0; i < utn->n_tables; i++)
memset(utn->entries[i], 0, array_size(info->tables[i].n_entries,
sizeof(**utn->entries)));
- WARN_ON(utn->need_sync);
- utn->need_replay = 0;
+ WARN_ON(test_bit(UDP_TUNNEL_NIC_NEED_SYNC, &utn->flags));
+ clear_bit(UDP_TUNNEL_NIC_NEED_REPLAY, &utn->flags);}
static void
@@ -713,8 +715,8 @@ udp_tunnel_nic_replay(struct net_device *dev, struct udp_tunnel_nic *utn)
for (i = 0; i < utn->n_tables; i++)
for (j = 0; j < info->tables[i].n_entries; j++)
udp_tunnel_nic_entry_freeze_used(&utn->entries[i][j]);
- utn->missed = 0;
- utn->need_replay = 0;
+ bitmap_zero(&utn->missed, UDP_TUNNEL_NIC_MAX_TABLES);
+ clear_bit(UDP_TUNNEL_NIC_NEED_REPLAY, &utn->flags); if (!info->shared) {
udp_tunnel_get_rx_info(dev);
@@ -736,10 +738,10 @@ static void
udp_tunnel_nic_device_sync_work(struct work_struct *work)
rtnl_lock();
mutex_lock(&utn->lock);- utn->work_pending = 0;
+ clear_bit(UDP_TUNNEL_NIC_WORK_PENDING, &utn->flags);
__udp_tunnel_nic_device_sync(utn->dev, utn);- if (utn->need_replay)
+ if (test_bit(UDP_TUNNEL_NIC_NEED_REPLAY, &utn->flags))
udp_tunnel_nic_replay(utn->dev, utn);
mutex_unlock(&utn->lock);@@ -866,6 +868,11 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn)
udp_tunnel_nic_lock(dev);
+ if (test_bit(UDP_TUNNEL_NIC_WORK_PENDING, &utn->flags)) {
+ udp_tunnel_nic_unlock(dev);
+ return;
+ }
+
/* For a shared table remove this dev from the list of sharing devices
* and if there are other devices just detach.
*/
@@ -901,12 +908,6 @@ udp_tunnel_nic_unregister(struct net_device *dev,
struct udp_tunnel_nic *utn)
udp_tunnel_nic_flush(dev, utn);
udp_tunnel_nic_unlock(dev);- /* Wait for the work to be done using the state, netdev core will
- * retry unregister until we give up our reference on this device.
- */
- if (utn->work_pending)
- return;
-
udp_tunnel_nic_free(utn);
release_dev:
dev->udp_tunnel_nic = NULL;Quoted 188 lines · Eric Dumazet
Quoted 9 lines · Eric Dumazet
Oh well.
u8 need_sync:1;
u8 need_replay:1;
u8 work_pending:1;These bitfields are not safe, obviously :/
Time to convert them to atomic bit operations.
Can you try:
net/ipv4/udp_tunnel_nic.c +0
-0100644
net/ipv4/udp_tunnel_nic.c +7
-8@@ -30,9 +30,7 @@ struct udp_tunnel_nic_table_entry {* @work: async work for talking to hardware from process context * @dev: netdev pointer * @lock: protects all fields -* @need_sync: at least one port start changed -* @need_replay: space was freed, we need a replay of all ports -* @work_pending: @work is currently scheduled +* @flags: sync, replay, pending flags * @n_tables: number of tables under @entries * @missed: bitmap of tables which overflown * @entries: table of tables of ports currently offloaded @@ -44,9 +42,10 @@ struct udp_tunnel_nic {struct mutex lock; - u8 need_sync:1; - u8 need_replay:1; - u8 work_pending:1; +unsigned long flags; +#define UDP_TUNNEL_NIC_NEED_SYNC 0 +#define UDP_TUNNEL_NIC_NEED_REPLAY 1 +#define UDP_TUNNEL_NIC_WORK_PENDING 2unsigned int n_tables;unsigned long missed;@@ -116,7 +115,7 @@ udp_tunnel_nic_entry_queue(struct udp_tunnel_nic *utn, unsigned int flag) { entry->flags |= flag; - utn->need_sync =1 ; +set_bit (UDP_TUNNEL_NIC_NEED_SYNC , &utn->flags); } static void@@ -283,7 +282,7 @@ udp_tunnel_nic_device_sync_by_table(struct net_device *dev,static void __udp_tunnel_nic_device_sync (struct net_device *dev,struct udp_tunnel_nic *utn) { -if (!utn->need_sync) +if (!test_bit (UDP_TUNNEL_NIC_NEED_SYNC , &utn->flags))return ;if (dev->udp_tunnel_nic_info->sync_table)net/ipv4/udp_tunnel_nic.c +7
-4@@ -291,21 +290,24 @@ __udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn) elseudp_tunnel_nic_device_sync_by_port (dev, utn); - utn->need_sync =0 ; +clear_bit (UDP_TUNNEL_NIC_NEED_SYNC , &utn->flags);/* Can't replay directly here, in case we come from the tunnel driver's * notification - trying to replay may deadlock inside tunnel driver. */ - utn->need_replay =udp_tunnel_nic_should_replay (dev, utn); +if (udp_tunnel_nic_should_replay (dev, utn)) +set_bit (UDP_TUNNEL_NIC_NEED_REPLAY , &utn->flags); +else +clear_bit (UDP_TUNNEL_NIC_NEED_REPLAY , &utn->flags); }static void udp_tunnel_nic_device_sync (struct net_device *dev,struct udp_tunnel_nic *utn) { -if (!utn->need_sync) +if (!test_bit (UDP_TUNNEL_NIC_NEED_SYNC , &utn->flags))return ; +set_bit (UDP_TUNNEL_NIC_WORK_PENDING , &utn->flags);queue_work (udp_tunnel_nic_workqueue, &utn->work); - utn->work_pending =1 ; }static bool
net/ipv4/udp_tunnel_nic.c +1
-1@@ -348,7 +350,7 @@ udp_tunnel_nic_has_collision(struct net_device *dev, struct udp_tunnel_nic *utn, if (!udp_tunnel_nic_entry_is_free(entry) && entry->port == ti->port && entry->type != ti->type) { -__set_bit (i, &utn->missed); +set_bit (i, &utn->missed);return true; }}net/ipv4/udp_tunnel_nic.c +1
-1@@ -483,7 +485,7 @@ udp_tunnel_nic_add_new(struct net_device *dev,struct udp_tunnel_nic *utn, * are no devices currently which have multiple tables accepting * the same tunnel type, and false positives are okay. */ -__set_bit (i, &utn->missed); +set_bit (i, &utn->missed); }return false;net/ipv4/udp_tunnel_nic.c +1
-1@@ -552,7 +554,7 @@ static void __udp_tunnel_nic_reset_ntf(struct net_device *dev) mutex_lock(&utn->lock); - utn->need_sync = false; +clear_bit (UDP_TUNNEL_NIC_NEED_SYNC , &utn->flags);for (i =0 ; i < utn->n_tables; i++)for (j =0 ; j < info->tables[i].n_entries; j++) {struct udp_tunnel_nic_table_entry *entry;net/ipv4/udp_tunnel_nic.c +2
-2@@ -696,8 +698,8 @@ udp_tunnel_nic_flush(struct net_device *dev, struct udp_tunnel_nic *utn)for (i =0 ; i < utn->n_tables; i++)memset (utn->entries[i],0 ,array_size (info->tables[i].n_entries,sizeof (**utn->entries))); -WARN_ON (utn->need_sync); - utn->need_replay =0 ; +WARN_ON (test_bit (UDP_TUNNEL_NIC_NEED_SYNC , &utn->flags)); +clear_bit (UDP_TUNNEL_NIC_NEED_REPLAY , &utn->flags); }static void
net/ipv4/udp_tunnel_nic.c +2
-2@@ -713,8 +715,8 @@ udp_tunnel_nic_replay(struct net_device *dev, struct udp_tunnel_nic *utn)for (i =0 ; i < utn->n_tables; i++)for (j =0 ; j < info->tables[i].n_entries; j++)udp_tunnel_nic_entry_freeze_used (&utn->entries[i][j]); - utn->missed =0 ; - utn->need_replay =0 ; +bitmap_zero (&utn->missed,UDP_TUNNEL_NIC_MAX_TABLES ); +clear_bit (UDP_TUNNEL_NIC_NEED_REPLAY , &utn->flags);if (!info->shared) {udp_tunnel_get_rx_info(dev);net/ipv4/udp_tunnel_nic.c +2
-2@@ -736,10 +738,10 @@ static void udp_tunnel_nic_device_sync_work(struct work_struct *work)rtnl_lock ();mutex_lock (&utn->lock); - utn->work_pending =0 ; +clear_bit (UDP_TUNNEL_NIC_WORK_PENDING , &utn->flags);__udp_tunnel_nic_device_sync (utn->dev, utn); -if (utn->need_replay) +if (test_bit (UDP_TUNNEL_NIC_NEED_REPLAY , &utn->flags))udp_tunnel_nic_replay (utn->dev, utn);mutex_unlock(&utn->lock);net/ipv4/udp_tunnel_nic.c +5
-0@@ -866,6 +868,11 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn)udp_tunnel_nic_lock (dev ); +if (test_bit (UDP_TUNNEL_NIC_WORK_PENDING , &utn->flags)) { +udp_tunnel_nic_unlock (dev); +return ; + } +/* For a shared table remove this dev from the list of sharing devices * and if there are other devices just detach. */net/ipv4/udp_tunnel_nic.c +0
-6@@ -901,12 +908,6 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn)udp_tunnel_nic_flush (dev ,utn );udp_tunnel_nic_unlock (dev); -/* Wait for the work to be done using the state, netdev core will -* retry unregister until we give up our reference on this device. -*/ -if (utn->work_pending) -return ; -udp_tunnel_nic_free (utn); release_dev:
Quoted 1 line
dev->udp_tunnel_nic = NULL;
I tested this version as well, but it still does not stop the C reproducer on my side.
This time the VM panicked after about 50 seconds on a debugobjects warning:
[ 50.420529][ T9744] ------------[ cut here ]------------ [ 50.421258][ T9744] ODEBUG: free active (active state 0) object: ff110001114b5a00 object type: work_struct hint: udp_tunnel_nic_device_sync_work+0x0/0x940 [ 50.424052][ T9744] WARNING: lib/debugobjects.c:629 at debug_print_object+0x1a0/0x2e0, CPU#0: repro/9744 [ 50.425766][ T9744] Modules linked in: [ 50.426279][ T9744] CPU: 0 UID: 0 PID: 9744 Comm: repro Not tainted 7.1.0-11240-g840ef6c78e6a-dirty #33 PREEMPT(full) [ 50.428614][ T9744] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 [ 50.429661][ T9744] RIP: 0010:debug_print_object+0x1a5/0x2e0 [ 50.430338][ T9744] Code: 89 fa 48 c1 ea 03 80 3c 02 00 0f 85 8a 00 00 00 48 8b 14 ed 60 33 1e 8c 48 83 fd 05 77 47 48 8d 3d e0 0c 1e 0c 41 56 4c 89 e6 <67> 48 0f b9 3a 58 83 05 42 30 14 0c 01 48 83 c4 20 5b 5d 41 5c 41 [ 50.432538][ T9744] RSP: 0018:ffa0000012c8ee60 EFLAGS: 00010293 [ 50.433045][ T9744] RAX: dffffc0000000000 RBX: ffa0000012c8ef40 RCX: 0000000000000000 [ 50.433710][ T9744] RDX: ffffffff8c1e32a0 RSI: ffffffff8c1e2e80 RDI: ffffffff90e31820 [ 50.434390][ T9744] RBP: 0000000000000003 R08: ff110001114b5a00 R09: ffffffff8bae17e0 [ 50.435050][ T9744] R10: ffffffff90d907d7 R11: 0000000000000000 R12: ffffffff8c1e2e80 [ 50.435719][ T9744] R13: ffffffff8bae1820 R14: ffffffff8a0f69e0 R15: ffa0000012c8ef58 [ 50.436393][ T9744] FS: 00007f8430d5b640(0000) GS:ff1100018394a000(0000) knlGS:0000000000000000 [ 50.437149][ T9744] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 50.437749][ T9744] CR2: 00007f422d7b8000 CR3: 000000010b850000 CR4: 0000000000753ef0 [ 50.438404][ T9744] PKRU: 55555554 [ 50.438716][ T9744] Call Trace: [ 50.439004][ T9744] <TASK> [ 50.439277][ T9744] ? __pfx_udp_tunnel_nic_device_sync_work+0x10/0x10 [ 50.439856][ T9744] ? _raw_spin_unlock_irqrestore+0x58/0x70 [ 50.440942][ T9744] debug_check_no_obj_freed+0x3ec/0x520 [ 50.441419][ T9744] ? __udp_tunnel_nic_lock+0x47/0x60 [ 50.441878][ T9744] ? __pfx_debug_check_no_obj_freed+0x10/0x10 [ 50.442403][ T9744] ? kasan_quarantine_put+0x10d/0x230 [ 50.442875][ T9744] ? lockdep_hardirqs_on+0x7c/0x110 [ 50.443325][ T9744] kfree+0x2a0/0x6d0 [ 50.443663][ T9744] ? udp_tunnel_nic_netdevice_event+0xc14/0x1e40 [ 50.444214][ T9744] udp_tunnel_nic_netdevice_event+0xc14/0x1e40 [ 50.444730][ T9744] notifier_call_chain+0xbd/0x430 [ 50.445164][ T9744] ? __pfx_udp_tunnel_nic_netdevice_event+0x10/0x10 [ 50.445729][ T9744] call_netdevice_notifiers_info+0xbe/0x110 [ 50.446236][ T9744] unregister_netdevice_many_notify+0xbab/0x2130 [ 50.446781][ T9744] ? __pfx_unregister_netdevice_many_notify+0x10/0x10 [ 50.447907][ T9744] ? __pfx___mutex_lock+0x10/0x10 [ 50.448351][ T9744] unregister_netdevice_queue+0x305/0x3c0 [ 50.448842][ T9744] ? __pfx_unregister_netdevice_queue+0x10/0x10 [ 50.449369][ T9744] nsim_destroy+0x231/0x980 [ 50.449773][ T9744] __nsim_dev_port_del+0x197/0x2c0 [ 50.450215][ T9744] nsim_dev_reload_destroy+0x105/0x490 [ 50.450677][ T9744] nsim_dev_reload_down+0x67/0xd0 [ 50.451143][ T9744] devlink_reload+0x197/0x7b0 [ 50.451564][ T9744] ? __pfx_devlink_reload+0x10/0x10 [ 50.452020][ T9744] ? security_capable+0x210/0x250 [ 50.452466][ T9744] ? ns_capable+0xe2/0x120 [ 50.452858][ T9744] devlink_nl_reload_doit+0x541/0x1160 [ 50.453323][ T9744] ? __pfx_devlink_nl_reload_doit+0x10/0x10 [ 50.453828][ T9744] ? genl_family_rcv_msg_attrs_parse.constprop.0+0x1e5/0x2f0 [ 50.454458][ T9744] genl_family_rcv_msg_doit+0x1ff/0x2f0 [ 50.454930][ T9744] ? __pfx_genl_family_rcv_msg_doit+0x10/0x10 [ 50.455442][ T9744] ? bpf_lsm_capable+0x9/0x10 [ 50.455845][ T9744] ? security_capable+0x210/0x250 [ 50.456297][ T9744] genl_rcv_msg+0x532/0x7e0 [ 50.456683][ T9744] ? __pfx_genl_rcv_msg+0x10/0x10 [ 50.457115][ T9744] ? __pfx_devlink_nl_pre_doit_dev_lock+0x10/0x10 [ 50.457690][ T9744] ? __pfx_devlink_nl_reload_doit+0x10/0x10 [ 50.458218][ T9744] ? __pfx_devlink_nl_post_doit_dev_lock+0x10/0x10 [ 50.458776][ T9744] ? __lock_acquire+0x476/0x2420 [ 50.459208][ T9744] netlink_rcv_skb+0x147/0x430 [ 50.459633][ T9744] ? __pfx_genl_rcv_msg+0x10/0x10 [ 50.460062][ T9744] ? __pfx_netlink_rcv_skb+0x10/0x10 [ 50.460520][ T9744] ? netlink_deliver_tap+0x1ae/0xd10 [ 50.460976][ T9744] genl_rcv+0x28/0x40 [ 50.461330][ T9744] netlink_unicast+0x58d/0x850 [ 50.461739][ T9744] ? __pfx_netlink_unicast+0x10/0x10 [ 50.462198][ T9744] netlink_sendmsg+0x88d/0xd90 [ 50.462610][ T9744] ? __pfx_netlink_sendmsg+0x10/0x10 [ 50.463092][ T9744] ? __pfx_netlink_sendmsg+0x10/0x10 [ 50.463557][ T9744] ____sys_sendmsg+0xa27/0xb90 [ 50.463982][ T9744] ? __pfx_____sys_sendmsg+0x10/0x10 [ 50.464438][ T9744] ? __pfx_copy_msghdr_from_user+0x10/0x10 [ 50.464938][ T9744] ? find_held_lock+0x2b/0x80 [ 50.465347][ T9744] ? futex_wake+0x4f7/0x5e0 [ 50.465735][ T9744] ___sys_sendmsg+0x11c/0x1b0 [ 50.466129][ T9744] ? __pfx____sys_sendmsg+0x10/0x10 [ 50.466586][ T9744] ? __pfx_futex_wake+0x10/0x10 [ 50.467002][ T9744] ? __fget_files+0x1f1/0x3b0 [ 50.467440][ T9744] ? __fget_files+0x1fb/0x3b0 [ 50.467836][ T9744] ? __lock_acquire+0x450/0x2420 [ 50.468298][ T9744] __sys_sendmsg+0x142/0x1f0 [ 50.468696][ T9744] ? __pfx___sys_sendmsg+0x10/0x10 [ 50.469133][ T9744] ? __cpu_to_node+0x8a/0x130 [ 50.469538][ T9744] do_syscall_64+0x11f/0x860 [ 50.469953][ T9744] entry_SYSCALL_64_after_hwframe+0x77/0x7f [ 50.470454][ T9744] RIP: 0033:0x451a4d [ 50.470783][ T9744] Code: c3 e8 a7 23 00 00 0f 1f 80 00 00 00 00 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48 [ 50.472393][ T9744] RSP: 002b:00007f8430d5b198 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 50.473102][ T9744] RAX: ffffffffffffffda RBX: 00000000004e9440 RCX: 0000000000451a4d [ 50.473761][ T9744] RDX: 0000000000000000 RSI: 0000200000000800 RDI: 0000000000000003 [ 50.474419][ T9744] RBP: 00000000004b66b4 R08: 000000000000006d R09: 0000000000000000 [ 50.475085][ T9744] R10: 0000000000000001 R11: 0000000000000246 R12: 0000200000000280 [ 50.475738][ T9744] R13: 0000200000000190 R14: 0000200000000180 R15: 00000000004e9448 [ 50.476418][ T9744] </TASK> [ 50.476683][ T9744] Kernel panic - not syncing: kernel: panic_on_warn set ... [ 50.477297][ T9744] CPU: 0 UID: 0 PID: 9744 Comm: repro Not tainted 7.1.0-11240-g840ef6c78e6a-dirty #33 PREEMPT(full) [ 50.478201][ T9744] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 [ 50.478952][ T9744] Call Trace: [ 50.479240][ T9744] <TASK> [ 50.479492][ T9744] dump_stack_lvl+0x3d/0x1b0 [ 50.479895][ T9744] vpanic+0x7f2/0xa70 [ 50.480241][ T9744] ? __pfx_vpanic+0x10/0x10 [ 50.480621][ T9744] ? is_bpf_text_address+0x96/0x1a0 [ 50.481070][ T9744] ? debug_print_object+0x1a0/0x2e0 [ 50.481512][ T9744] panic+0xc2/0xd0 [ 50.481844][ T9744] ? __pfx_panic+0x10/0x10 [ 50.482230][ T9744] ? check_panic_on_warn+0x1f/0xc0 [ 50.482673][ T9744] check_panic_on_warn+0xb1/0xc0 [ 50.483102][ T9744] __warn+0x108/0x3f0 [ 50.483460][ T9744] __report_bug+0x42c/0x510 [ 50.483854][ T9744] ? debug_print_object+0x1a0/0x2e0 [ 50.484297][ T9744] ? __pfx___report_bug+0x10/0x10 [ 50.484721][ T9744] ? __kernel_text_address+0xd/0x40 [ 50.485166][ T9744] ? unwind_get_return_address+0x59/0xa0 [ 50.485664][ T9744] report_bug_entry+0xe1/0x280 [ 50.486068][ T9744] ? debug_print_object+0x1a5/0x2e0 [ 50.486508][ T9744] handle_bug+0x428/0x4e0 [ 50.486889][ T9744] exc_invalid_op+0x35/0x80 [ 50.487281][ T9744] asm_exc_invalid_op+0x1a/0x20 [ 50.487693][ T9744] RIP: 0010:debug_print_object+0x1a5/0x2e0 [ 50.488194][ T9744] Code: 89 fa 48 c1 ea 03 80 3c 02 00 0f 85 8a 00 00 00 48 8b 14 ed 60 33 1e 8c 48 83 fd 05 77 47 48 8d 3d e0 0c 1e 0c 41 56 4c 89 e6 <67> 48 0f b9 3a 58 83 05 42 30 14 0c 01 48 83 c4 20 5b 5d 41 5c 41 [ 50.489814][ T9744] RSP: 0018:ffa0000012c8ee60 EFLAGS: 00010293 [ 50.490362][ T9744] RAX: dffffc0000000000 RBX: ffa0000012c8ef40 RCX: 0000000000000000 [ 50.491033][ T9744] RDX: ffffffff8c1e32a0 RSI: ffffffff8c1e2e80 RDI: ffffffff90e31820 [ 50.491698][ T9744] RBP: 0000000000000003 R08: ff110001114b5a00 R09: ffffffff8bae17e0 [ 50.492384][ T9744] R10: ffffffff90d907d7 R11: 0000000000000000 R12: ffffffff8c1e2e80 [ 50.493043][ T9744] R13: ffffffff8bae1820 R14: ffffffff8a0f69e0 R15: ffa0000012c8ef58 [ 50.493718][ T9744] ? __pfx_udp_tunnel_nic_device_sync_work+0x10/0x10 [ 50.494288][ T9744] ? __pfx_udp_tunnel_nic_device_sync_work+0x10/0x10 [ 50.494845][ T9744] ? _raw_spin_unlock_irqrestore+0x58/0x70 [ 50.495347][ T9744] debug_check_no_obj_freed+0x3ec/0x520 [ 50.495825][ T9744] ? __udp_tunnel_nic_lock+0x47/0x60 [ 50.496276][ T9744] ? __pfx_debug_check_no_obj_freed+0x10/0x10 [ 50.496794][ T9744] ? kasan_quarantine_put+0x10d/0x230 [ 50.497266][ T9744] ? lockdep_hardirqs_on+0x7c/0x110 [ 50.497706][ T9744] kfree+0x2a0/0x6d0 [ 50.498038][ T9744] ? udp_tunnel_nic_netdevice_event+0xc14/0x1e40 [ 50.498577][ T9744] udp_tunnel_nic_netdevice_event+0xc14/0x1e40 [ 50.499107][ T9744] notifier_call_chain+0xbd/0x430 [ 50.499544][ T9744] ? __pfx_udp_tunnel_nic_netdevice_event+0x10/0x10 [ 50.500096][ T9744] call_netdevice_notifiers_info+0xbe/0x110 [ 50.500625][ T9744] unregister_netdevice_many_notify+0xbab/0x2130 [ 50.501169][ T9744] ? __pfx_unregister_netdevice_many_notify+0x10/0x10 [ 50.501737][ T9744] ? __pfx___mutex_lock+0x10/0x10 [ 50.502174][ T9744] unregister_netdevice_queue+0x305/0x3c0 [ 50.502660][ T9744] ? __pfx_unregister_netdevice_queue+0x10/0x10 [ 50.503186][ T9744] nsim_destroy+0x231/0x980 [ 50.503564][ T9744] __nsim_dev_port_del+0x197/0x2c0 [ 50.503966][ T9744] nsim_dev_reload_destroy+0x105/0x490 [ 50.504406][ T9744] nsim_dev_reload_down+0x67/0xd0 [ 50.504808][ T9744] devlink_reload+0x197/0x7b0 [ 50.505220][ T9744] ? __pfx_devlink_reload+0x10/0x10 [ 50.505679][ T9744] ? security_capable+0x210/0x250 [ 50.506113][ T9744] ? ns_capable+0xe2/0x120 [ 50.506490][ T9744] devlink_nl_reload_doit+0x541/0x1160 [ 50.506962][ T9744] ? __pfx_devlink_nl_reload_doit+0x10/0x10 [ 50.507471][ T9744] ? genl_family_rcv_msg_attrs_parse.constprop.0+0x1e5/0x2f0 [ 50.508094][ T9744] genl_family_rcv_msg_doit+0x1ff/0x2f0 [ 50.508577][ T9744] ? __pfx_genl_family_rcv_msg_doit+0x10/0x10 [ 50.509098][ T9744] ? bpf_lsm_capable+0x9/0x10 [ 50.509495][ T9744] ? security_capable+0x210/0x250 [ 50.509924][ T9744] genl_rcv_msg+0x532/0x7e0 [ 50.510327][ T9744] ? __pfx_genl_rcv_msg+0x10/0x10 [ 50.510753][ T9744] ? __pfx_devlink_nl_pre_doit_dev_lock+0x10/0x10 [ 50.511291][ T9744] ? __pfx_devlink_nl_reload_doit+0x10/0x10 [ 50.511795][ T9744] ? __pfx_devlink_nl_post_doit_dev_lock+0x10/0x10 [ 50.512365][ T9744] ? __lock_acquire+0x476/0x2420 [ 50.512785][ T9744] netlink_rcv_skb+0x147/0x430 [ 50.513197][ T9744] ? __pfx_genl_rcv_msg+0x10/0x10 [ 50.513627][ T9744] ? __pfx_netlink_rcv_skb+0x10/0x10 [ 50.514090][ T9744] ? netlink_deliver_tap+0x1ae/0xd10 [ 50.514542][ T9744] genl_rcv+0x28/0x40 [ 50.514879][ T9744] netlink_unicast+0x58d/0x850 [ 50.515302][ T9744] ? __pfx_netlink_unicast+0x10/0x10 [ 50.515760][ T9744] netlink_sendmsg+0x88d/0xd90 [ 50.516181][ T9744] ? __pfx_netlink_sendmsg+0x10/0x10 [ 50.516640][ T9744] ? __pfx_netlink_sendmsg+0x10/0x10 [ 50.517109][ T9744] ____sys_sendmsg+0xa27/0xb90 [ 50.517520][ T9744] ? __pfx_____sys_sendmsg+0x10/0x10 [ 50.517965][ T9744] ? __pfx_copy_msghdr_from_user+0x10/0x10 [ 50.518457][ T9744] ? find_held_lock+0x2b/0x80 [ 50.518871][ T9744] ? futex_wake+0x4f7/0x5e0 [ 50.519271][ T9744] ___sys_sendmsg+0x11c/0x1b0 [ 50.519677][ T9744] ? __pfx____sys_sendmsg+0x10/0x10 [ 50.520117][ T9744] ? __pfx_futex_wake+0x10/0x10 [ 50.520542][ T9744] ? __fget_files+0x1f1/0x3b0 [ 50.520945][ T9744] ? __fget_files+0x1fb/0x3b0 [ 50.521347][ T9744] ? __lock_acquire+0x450/0x2420 [ 50.521770][ T9744] __sys_sendmsg+0x142/0x1f0 [ 50.522176][ T9744] ? __pfx___sys_sendmsg+0x10/0x10 [ 50.522617][ T9744] ? __cpu_to_node+0x8a/0x130 [ 50.523021][ T9744] do_syscall_64+0x11f/0x860 [ 50.523417][ T9744] entry_SYSCALL_64_after_hwframe+0x77/0x7f [ 50.523926][ T9744] RIP: 0033:0x451a4d [ 50.524264][ T9744] Code: c3 e8 a7 23 00 00 0f 1f 80 00 00 00 00 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48 [ 50.525868][ T9744] RSP: 002b:00007f8430d5b198 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 50.526579][ T9744] RAX: ffffffffffffffda RBX: 00000000004e9440 RCX: 0000000000451a4d [ 50.527243][ T9744] RDX: 0000000000000000 RSI: 0000200000000800 RDI: 0000000000000003 [ 50.527914][ T9744] RBP: 00000000004b66b4 R08: 000000000000006d R09: 0000000000000000 [ 50.528614][ T9744] R10: 0000000000000001 R11: 0000000000000246 R12: 0000200000000280 [ 50.529305][ T9744] R13: 0000200000000190 R14: 0000200000000180 R15: 00000000004e9448 [ 50.529982][ T9744] </TASK> [ 50.530453][ T9744] Kernel Offset: disabled
Resolved from the patched vmlinux:
udp_tunnel_nic_netdevice_event+0xc14/0x1e40: udp_tunnel_nic_unregister at net/ipv4/udp_tunnel_nic.c:913 udp_tunnel_nic_netdevice_event at net/ipv4/udp_tunnel_nic.c:943
So we are still freeing struct udp_tunnel_nic while its embedded work_struct is active. debugobjects catches this at kfree() before the active work gets a chance to run later and dereference the freed utn.
My read is that the conversion from bitfields to atomic bitops removes the plain bitfield data race, but UDP_TUNNEL_NIC_WORK_PENDING is still only one boolean state. It can represent "some work is pending", but it cannot distinguish between:
idle
queued
running
running and queued again
In particular, the workqueue core clears WORK_STRUCT_PENDING before invoking the worker. At that point the same work item can be queued again by udp_tunnel_nic_device_sync(). If an already running instance later executes:
clear_bit(UDP_TUNNEL_NIC_WORK_PENDING, &utn->flags);
it can still clear the bit that was set for the requeued instance. Then udp_tunnel_nic_unregister() may observe UDP_TUNNEL_NIC_WORK_PENDING clear and free utn, even though debugobjects still sees utn->work as active.
Thanks,
Yue
Quoted 19 lines · Sam Sun
So we are still freeing struct
udp_tunnel_nicwhile its embeddedwork_structis active. debugobjects catches this atkfree()before the active work gets a chance to run later and dereference the freed utn.My read is that the conversion from bitfields to atomic bitops removes the plain bitfield data race, but
UDP_TUNNEL_NIC_WORK_PENDINGis still only one boolean state. It can represent "some work is pending", but it cannot distinguish between:
idle
queued
running
running and queued againIn particular, the workqueue core clears
WORK_STRUCT_PENDINGbefore invoking the worker. At that point the same work item can be queued again byudp_tunnel_nic_device_sync(). If an already running instance later executes:
Quoted 6 lines
clear_bit(UDP_TUNNEL_NIC_WORK_PENDING, &utn->flags);it can still clear the bit that was set for the requeued instance. Then
udp_tunnel_nic_unregister()may observeUDP_TUNNEL_NIC_WORK_PENDINGclear and free utn, even though debugobjects still seesutn->workas active.
-ETOOMANYBUGS
Ok, we could try to convert pending bit to a refcount.
net/ipv4/udp_tunnel_nic.c +0 -0
100644
net/ipv4/udp_tunnel_nic.c +9 -7
@@ -3,6 +3,7 @@#include <linux/ethtool_netlink.h> #include <linux/netdevice.h> +#include <linux/refcount.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/workqueue.h>
@@ -30,9 +31,8 @@ struct udp_tunnel_nic_table_entry {* @work: async work for talking to hardware from process context * @dev: netdev pointer * @lock: protects all fields -* @need_sync: at least one port start changed -* @need_replay: space was freed, we need a replay of all ports -* @work_pending: @work is currently scheduled +* @flags: sync, replay flags +* @refcnt: reference count * @n_tables: number of tables under @entries * @missed: bitmap of tables which overflown * @entries: table of tables of ports currently offloaded
@@ -44,9 +44,11 @@ struct udp_tunnel_nic {struct mutex lock; - u8 need_sync:1; - u8 need_replay:1; - u8 work_pending:1; +unsigned long flags; +#define UDP_TUNNEL_NIC_NEED_SYNC 0 +#define UDP_TUNNEL_NIC_NEED_REPLAY 1 + +refcount_t refcnt;unsigned int n_tables;unsigned long missed;
@@ -116,7 +118,7 @@ udp_tunnel_nic_entry_queue(struct udp_tunnel_nic *utn, unsigned int flag) { entry->flags |= flag; - utn->need_sync =1 ; +set_bit (UDP_TUNNEL_NIC_NEED_SYNC , &utn->flags); } static void
@@ -283,7 +285,7 @@ udp_tunnel_nic_device_sync_by_table(struct net_device *dev, static void __udp_tunnel_nic_device_sync(struct net_device *dev, struct
udp_tunnel_nic *utn)
{
- if (!utn->need_sync)
+ if (!test_bit(UDP_TUNNEL_NIC_NEED_SYNC, &utn->flags))
return;
if (dev->udp_tunnel_nic_info->sync_table)
@@ -291,21 +293,24 @@ __udp_tunnel_nic_device_sync(struct net_device
*dev, struct udp_tunnel_nic *utn)
else
udp_tunnel_nic_device_sync_by_port(dev, utn);- utn->need_sync = 0;
+ clear_bit(UDP_TUNNEL_NIC_NEED_SYNC, &utn->flags);
/* Can't replay directly here, in case we come from the tunnel driver's
* notification - trying to replay may deadlock inside tunnel driver.
*/- utn->need_replay = udp_tunnel_nic_should_replay(dev, utn);
+ if (udp_tunnel_nic_should_replay(dev, utn))
+ set_bit(UDP_TUNNEL_NIC_NEED_REPLAY, &utn->flags);
+ else
+ clear_bit(UDP_TUNNEL_NIC_NEED_REPLAY, &utn->flags);
}
static void
udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn) {
- if (!utn->need_sync)
+ if (!test_bit(UDP_TUNNEL_NIC_NEED_SYNC, &utn->flags))
return;
- queue_work(udp_tunnel_nic_workqueue, &utn->work); - utn->work_pending = 1; + if (queue_work(udp_tunnel_nic_workqueue, &utn->work))
+ refcount_inc(&utn->refcnt);
}
static bool
@@ -348,7 +353,7 @@ udp_tunnel_nic_has_collision(struct net_device *dev, struct udp_tunnel_nic *utn,
if (!udp_tunnel_nic_entry_is_free(entry) &&
entry->port == ti->port &&
entry->type != ti->type) {
- __set_bit(i, &utn->missed);
+ set_bit(i, &utn->missed);
return true;
}
}@@ -483,7 +488,7 @@ udp_tunnel_nic_add_new(struct net_device *dev, struct udp_tunnel_nic *utn,
* are no devices currently which have multiple tables accepting
* the same tunnel type, and false positives are okay. */
- __set_bit(i, &utn->missed);
+ set_bit(i, &utn->missed);
}
return false;@@ -552,7 +557,7 @@ static void __udp_tunnel_nic_reset_ntf(struct net_device *dev)
mutex_lock(&utn->lock);
- utn->need_sync = false;
+ clear_bit(UDP_TUNNEL_NIC_NEED_SYNC, &utn->flags);
for (i = 0; i < utn->n_tables; i++)
for (j = 0; j < info->tables[i].n_entries; j++) {
struct udp_tunnel_nic_table_entry *entry;
@@ -696,8 +701,8 @@ udp_tunnel_nic_flush(struct net_device *dev,
struct udp_tunnel_nic *utn)
for (i = 0; i < utn->n_tables; i++)
memset(utn->entries[i], 0, array_size(info->tables[i].n_entries,
sizeof(**utn->entries)));
- WARN_ON(utn->need_sync);
- utn->need_replay = 0;
+ WARN_ON(test_bit(UDP_TUNNEL_NIC_NEED_SYNC, &utn->flags));
+ clear_bit(UDP_TUNNEL_NIC_NEED_REPLAY, &utn->flags);}
static void
@@ -713,8 +718,8 @@ udp_tunnel_nic_replay(struct net_device *dev, struct udp_tunnel_nic *utn)
for (i = 0; i < utn->n_tables; i++)
for (j = 0; j < info->tables[i].n_entries; j++)
udp_tunnel_nic_entry_freeze_used(&utn->entries[i][j]);
- utn->missed = 0;
- utn->need_replay = 0;
+ bitmap_zero(&utn->missed, UDP_TUNNEL_NIC_MAX_TABLES);
+ clear_bit(UDP_TUNNEL_NIC_NEED_REPLAY, &utn->flags); if (!info->shared) {
udp_tunnel_get_rx_info(dev);
@@ -728,6 +733,25 @@ udp_tunnel_nic_replay(struct net_device *dev,
struct udp_tunnel_nic *utn)
udp_tunnel_nic_entry_unfreeze(&utn->entries[i][j]);}
+static void udp_tunnel_nic_free(struct udp_tunnel_nic *utn) +{
+ unsigned int i;
+
+ for (i = 0; i < utn->n_tables; i++)
+ kfree(utn->entries[i]);
+
+ if (utn->dev)
+ dev_put(utn->dev);
+
+ kfree(utn);
+}
+
+static void udp_tunnel_nic_put(struct udp_tunnel_nic *utn) +{
+ if (refcount_dec_and_test(&utn->refcnt))
+ udp_tunnel_nic_free(utn);
+}
+
static void udp_tunnel_nic_device_sync_work(struct work_struct *work) {
struct udp_tunnel_nic *utn =
@@ -736,14 +760,15 @@ static void udp_tunnel_nic_device_sync_work(struct work_struct *work)
rtnl_lock();
mutex_lock(&utn->lock);- utn->work_pending = 0;
__udp_tunnel_nic_device_sync(utn->dev, utn);- if (utn->need_replay)
+ if (test_bit(UDP_TUNNEL_NIC_NEED_REPLAY, &utn->flags))
udp_tunnel_nic_replay(utn->dev, utn);
mutex_unlock(&utn->lock);
rtnl_unlock();+
+ udp_tunnel_nic_put(utn);
}
static struct udp_tunnel_nic *
@@ -759,6 +784,7 @@ udp_tunnel_nic_alloc(const struct udp_tunnel_nic_info *info,
utn->n_tables = n_tables;
INIT_WORK(&utn->work, udp_tunnel_nic_device_sync_work);
mutex_init(&utn->lock);+ refcount_set(&utn->refcnt, 1);
for (i = 0; i < n_tables; i++) {
utn->entries[i] = kzalloc_objs(*utn->entries[i],
@@ -776,15 +802,6 @@ udp_tunnel_nic_alloc(const struct
udp_tunnel_nic_info *info,
return NULL;}
-static void udp_tunnel_nic_free(struct udp_tunnel_nic *utn) -{
- unsigned int i;
-
- for (i = 0; i < utn->n_tables; i++)
- kfree(utn->entries[i]);
- kfree(utn);
-}
-
static int udp_tunnel_nic_register(struct net_device *dev)
{
const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info;
@@ -863,6 +880,7 @@ static void
udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn)
{
const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info;+ bool last = true;
udp_tunnel_nic_lock(dev);
@@ -889,6 +907,7 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn)
udp_tunnel_drop_rx_info(dev);
utn->dev = first->dev;
udp_tunnel_nic_unlock(dev);
+ last = false;
goto release_dev;
}@@ -901,16 +920,11 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn)
udp_tunnel_nic_flush(dev, utn);
udp_tunnel_nic_unlock(dev);- /* Wait for the work to be done using the state, netdev core will
- * retry unregister until we give up our reference on this device.
- */
- if (utn->work_pending)
- return;
-
- udp_tunnel_nic_free(utn);
+ udp_tunnel_nic_put(utn);
release_dev:
dev->udp_tunnel_nic = NULL;
- dev_put(dev);
+ if (!last)
+ dev_put(dev);
}
static int
Quoted 284 lines · Eric Dumazet
Quoted 19 lines · Sam Sun
So we are still freeing struct
udp_tunnel_nicwhile its embeddedwork_structis active. debugobjects catches this atkfree()before the active work gets a chance to run later and dereference the freed utn.My read is that the conversion from bitfields to atomic bitops removes the plain bitfield data race, but
UDP_TUNNEL_NIC_WORK_PENDINGis still only one boolean state. It can represent "some work is pending", but it cannot distinguish between:
idle
queued
running
running and queued againIn particular, the workqueue core clears
WORK_STRUCT_PENDINGbefore invoking the worker. At that point the same work item can be queued again byudp_tunnel_nic_device_sync(). If an already running instance later executes:Quoted 6 lines
clear_bit(UDP_TUNNEL_NIC_WORK_PENDING, &utn->flags);it can still clear the bit that was set for the requeued instance. Then
udp_tunnel_nic_unregister()may observeUDP_TUNNEL_NIC_WORK_PENDINGclear and free utn, even though debugobjects still seesutn->workas active.
-ETOOMANYBUGSOk, we could try to convert pending bit to a refcount.
net/ipv4/udp_tunnel_nic.c +0
-0100644
net/ipv4/udp_tunnel_nic.c +10
-8@@ -3,6 +3,7 @@#include <linux/ethtool_netlink.h> #include <linux/netdevice.h> +#include <linux/refcount.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/workqueue.h> @@ -30,9 +31,8 @@ struct udp_tunnel_nic_table_entry {* @work: async work for talking to hardware from process context * @dev: netdev pointer * @lock: protects all fields -* @need_sync: at least one port start changed -* @need_replay: space was freed, we need a replay of all ports -* @work_pending: @work is currently scheduled +* @flags: sync, replay flags +* @refcnt: reference count * @n_tables: number of tables under @entries * @missed: bitmap of tables which overflown * @entries: table of tables of ports currently offloaded @@ -44,9 +44,11 @@ struct udp_tunnel_nic {struct mutex lock; - u8 need_sync:1; - u8 need_replay:1; - u8 work_pending:1; +unsigned long flags; +#define UDP_TUNNEL_NIC_NEED_SYNC 0 +#define UDP_TUNNEL_NIC_NEED_REPLAY 1 + +refcount_t refcnt;unsigned int n_tables;unsigned long missed;@@ -116,7 +118,7 @@ udp_tunnel_nic_entry_queue(struct udp_tunnel_nic *utn, unsigned int flag) { entry->flags |= flag; - utn->need_sync =1 ; +set_bit (UDP_TUNNEL_NIC_NEED_SYNC , &utn->flags); } static void@@ -283,7 +285,7 @@ udp_tunnel_nic_device_sync_by_table(struct net_device *dev,static void __udp_tunnel_nic_device_sync (struct net_device *dev,struct udp_tunnel_nic *utn) { -if (!utn->need_sync) +if (!test_bit (UDP_TUNNEL_NIC_NEED_SYNC , &utn->flags))return ;if (dev->udp_tunnel_nic_info->sync_table)net/ipv4/udp_tunnel_nic.c +8
-5@@ -291,21 +293,24 @@ __udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn) elseudp_tunnel_nic_device_sync_by_port (dev, utn); - utn->need_sync =0 ; +clear_bit (UDP_TUNNEL_NIC_NEED_SYNC , &utn->flags);/* Can't replay directly here, in case we come from the tunnel driver's * notification - trying to replay may deadlock inside tunnel driver. */ - utn->need_replay =udp_tunnel_nic_should_replay (dev, utn); +if (udp_tunnel_nic_should_replay (dev, utn)) +set_bit (UDP_TUNNEL_NIC_NEED_REPLAY , &utn->flags); +else +clear_bit (UDP_TUNNEL_NIC_NEED_REPLAY , &utn->flags); }static void udp_tunnel_nic_device_sync (struct net_device *dev,struct udp_tunnel_nic *utn) { -if (!utn->need_sync) +if (!test_bit (UDP_TUNNEL_NIC_NEED_SYNC , &utn->flags))return ; -queue_work (udp_tunnel_nic_workqueue, &utn->work); - utn->work_pending =1 ; +if (queue_work (udp_tunnel_nic_workqueue, &utn->work)) +refcount_inc (&utn->refcnt); }static bool
net/ipv4/udp_tunnel_nic.c +1
-1@@ -348,7 +353,7 @@ udp_tunnel_nic_has_collision(struct net_device *dev, struct udp_tunnel_nic *utn, if (!udp_tunnel_nic_entry_is_free(entry) && entry->port == ti->port && entry->type != ti->type) { -__set_bit (i, &utn->missed); +set_bit (i, &utn->missed);return true; }}net/ipv4/udp_tunnel_nic.c +1
-1@@ -483,7 +488,7 @@ udp_tunnel_nic_add_new(struct net_device *dev,struct udp_tunnel_nic *utn, * are no devices currently which have multiple tables accepting * the same tunnel type, and false positives are okay. */ -__set_bit (i, &utn->missed); +set_bit (i, &utn->missed); }return false;net/ipv4/udp_tunnel_nic.c +1
-1@@ -552,7 +557,7 @@ static void __udp_tunnel_nic_reset_ntf(struct net_device *dev) mutex_lock(&utn->lock); - utn->need_sync = false; +clear_bit (UDP_TUNNEL_NIC_NEED_SYNC , &utn->flags);for (i =0 ; i < utn->n_tables; i++)for (j =0 ; j < info->tables[i].n_entries; j++) {struct udp_tunnel_nic_table_entry *entry;net/ipv4/udp_tunnel_nic.c +2
-2@@ -696,8 +701,8 @@ udp_tunnel_nic_flush(struct net_device *dev, struct udp_tunnel_nic *utn)for (i =0 ; i < utn->n_tables; i++)memset (utn->entries[i],0 ,array_size (info->tables[i].n_entries,sizeof (**utn->entries))); -WARN_ON (utn->need_sync); - utn->need_replay =0 ; +WARN_ON (test_bit (UDP_TUNNEL_NIC_NEED_SYNC , &utn->flags)); +clear_bit (UDP_TUNNEL_NIC_NEED_REPLAY , &utn->flags); }static void
net/ipv4/udp_tunnel_nic.c +2
-2@@ -713,8 +718,8 @@ udp_tunnel_nic_replay(struct net_device *dev, struct udp_tunnel_nic *utn)for (i =0 ; i < utn->n_tables; i++)for (j =0 ; j < info->tables[i].n_entries; j++)udp_tunnel_nic_entry_freeze_used (&utn->entries[i][j]); - utn->missed =0 ; - utn->need_replay =0 ; +bitmap_zero (&utn->missed,UDP_TUNNEL_NIC_MAX_TABLES ); +clear_bit (UDP_TUNNEL_NIC_NEED_REPLAY , &utn->flags);if (!info->shared) {udp_tunnel_get_rx_info(dev);net/ipv4/udp_tunnel_nic.c +19
-0@@ -728,6 +733,25 @@ udp_tunnel_nic_replay(struct net_device *dev, struct udp_tunnel_nic *utn) udp_tunnel_nic_entry_unfreeze(&utn->entries[i][j]); } +static void udp_tunnel_nic_free (struct udp_tunnel_nic *utn) +{ +unsigned int i; + +for (i =0 ; i < utn->n_tables; i++) +kfree (utn->entries[i]); + +if (utn->dev) +dev_put (utn->dev); + +kfree (utn); +} + +static void udp_tunnel_nic_put (struct udp_tunnel_nic *utn) +{ +if (refcount_dec_and_test (&utn->refcnt)) +udp_tunnel_nic_free (utn); +} +static void udp_tunnel_nic_device_sync_work (struct work_struct *work) {struct
udp_tunnel_nic*utn =net/ipv4/udp_tunnel_nic.c +3
-2@@ -736,14 +760,15 @@ static void udp_tunnel_nic_device_sync_work(struct work_struct *work)rtnl_lock ();mutex_lock (&utn->lock); - utn->work_pending =0 ;__udp_tunnel_nic_device_sync (utn->dev, utn); -if (utn->need_replay) +if (test_bit (UDP_TUNNEL_NIC_NEED_REPLAY , &utn->flags))udp_tunnel_nic_replay (utn->dev, utn);mutex_unlock (&utn->lock);rtnl_unlock (); + +udp_tunnel_nic_put (utn); }static struct
udp_tunnel_nic*net/ipv4/udp_tunnel_nic.c +1
-9@@ -759,6 +784,7 @@ udp_tunnel_nic_alloc(const struct udp_tunnel_nic_info *info, utn->n_tables = n_tables;INIT_WORK (&utn->work, udp_tunnel_nic_device_sync_work);mutex_init (&utn->lock); +refcount_set (&utn->refcnt,1 );for (i =0 ; i < n_tables; i++) { utn->entries[i] = kzalloc_objs(*utn->entries[i],@@ -776,15 +802,6 @@ udp_tunnel_nic_alloc(const structudp_tunnel_nic_info *info, return NULL; } -static void udp_tunnel_nic_free (struct udp_tunnel_nic *utn) -{ -unsigned int i; - -for (i =0 ; i < utn->n_tables; i++) -kfree (utn->entries[i]); -kfree (utn); -} -static int udp_tunnel_nic_register (struct net_device *dev) {const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info;net/ipv4/udp_tunnel_nic.c +5
-8@@ -863,6 +880,7 @@ static void udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; +bool last = true;udp_tunnel_nic_lock (dev);@@ -889,6 +907,7 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn)udp_tunnel_drop_rx_info (dev ); utn->dev = first->dev;udp_tunnel_nic_unlock (dev); + last = false; goto release_dev; }@@ -901,16 +920,11 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn)udp_tunnel_nic_flush (dev, utn);udp_tunnel_nic_unlock (dev); -/* Wait for the work to be done using the state, netdev core will -* retry unregister until we give up our reference on this device. -*/ -if (utn->work_pending) -return ; - -udp_tunnel_nic_free (utn); +udp_tunnel_nic_put (utn); release_dev: dev->udp_tunnel_nic =NULL ; -dev_put (dev); +if (!last) +dev_put (dev); }
Quoted 1 line
static int
I tested the refcount version, and I could no longer reproduce the bug with the C reproducer. I think this patch fixes the specific lifetime problem exposed by the reproducer.
Thanks,
Yue
Quoted 6 lines · Sam Sun
I tested the refcount version, and I could no longer reproduce the bug with the C reproducer. I think this patch fixes the specific lifetime problem exposed by the reproducer.
Nice, thanks for testing it. I will cook an official patch then.