Hello,
syzbot found the following issue on:
HEAD commit: 2c3b09aac00d Add linux-next specific files for 20240214
git tree: linux-next
console output: https://syzkaller.appspot.com/x/log.txt?x=1793a064180000
kernel config: https://syzkaller.appspot.com/x/.config?x=176d2dcbf8ba7017
dashboard link: https://syzkaller.appspot.com/bug?extid=a2e2735f09ebb9d95bd1
compiler: Debian clang version 15.0.6, GNU ld (GNU Binutils for Debian) 2.40
Unfortunately, I don't have any reproducer for this issue yet.
Downloadable assets:
disk image: https://storage.googleapis.com/syzbot-assets/ac51042b61c6/disk-2c3b09aa.raw.xz
vmlinux: https://storage.googleapis.com/syzbot-assets/012344301c35/vmlinux-2c3b09aa.xz
kernel image: https://storage.googleapis.com/syzbot-assets/cba3c3e5cd7c/bzImage-2c3b09aa.xz
IMPORTANT: if you fix the issue, please add the following tag to the commit:
Reported-by: [email protected]
==================================================================
BUG: KASAN: slab-use-after-free in compare_netdev_and_ip drivers/infiniband/core/cma.c:473 [inline]
BUG: KASAN: slab-use-after-free in cma_add_id_to_tree drivers/infiniband/core/cma.c:513 [inline]
BUG: KASAN: slab-use-after-free in rdma_resolve_route+0x23f7/0x3150 drivers/infiniband/core/cma.c:3379
Read of size 4 at addr ffff88808dcf6184 by task syz-executor.4/11929
CPU: 1 PID: 11929 Comm: syz-executor.4 Not tainted 6.8.0-rc4-next-20240214-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/25/2024
Call Trace:
<TASK>
__dump_stack lib/dump_stack.c:88 [inline]
dump_stack_lvl+0x241/0x360 lib/dump_stack.c:114
print_address_description mm/kasan/report.c:377 [inline]
print_report+0x169/0x550 mm/kasan/report.c:488
kasan_report+0x143/0x180 mm/kasan/report.c:601
compare_netdev_and_ip drivers/infiniband/core/cma.c:473 [inline]
cma_add_id_to_tree drivers/infiniband/core/cma.c:513 [inline]
rdma_resolve_route+0x23f7/0x3150 drivers/infiniband/core/cma.c:3379
ucma_resolve_route+0x1ba/0x330 drivers/infiniband/core/ucma.c:745
ucma_write+0x2df/0x430 drivers/infiniband/core/ucma.c:1743
vfs_write+0x2a4/0xcb0 fs/read_write.c:588
ksys_write+0x1a0/0x2c0 fs/read_write.c:643
do_syscall_64+0xfb/0x240
entry_SYSCALL_64_after_hwframe+0x6d/0x75
RIP: 0033:0x7f4eae47dda9
Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 e1 20 00 00 90 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
RSP: 002b:00007f4eaf2cd0c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 00007f4eae5abf80 RCX: 00007f4eae47dda9
RDX: 0000000000000010 RSI: 0000000020000440 RDI: 0000000000000003
RBP: 00007f4eae4ca47a R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 000000000000000b R14: 00007f4eae5abf80 R15: 00007fff93bb3dc8
</TASK>
Allocated by task 11919:
kasan_save_stack mm/kasan/common.c:47 [inline]
kasan_save_track+0x3f/0x80 mm/kasan/common.c:68
poison_kmalloc_redzone mm/kasan/common.c:370 [inline]
__kasan_kmalloc+0x98/0xb0 mm/kasan/common.c:387
kasan_kmalloc include/linux/kasan.h:211 [inline]
kmalloc_trace+0x1d9/0x360 mm/slub.c:4013
kmalloc include/linux/slab.h:590 [inline]
kzalloc include/linux/slab.h:711 [inline]
__rdma_create_id+0x65/0x590 drivers/infiniband/core/cma.c:993
rdma_create_user_id+0x83/0xc0 drivers/infiniband/core/cma.c:1049
ucma_create_id+0x2d0/0x500 drivers/infiniband/core/ucma.c:463
ucma_write+0x2df/0x430 drivers/infiniband/core/ucma.c:1743
vfs_write+0x2a4/0xcb0 fs/read_write.c:588
ksys_write+0x1a0/0x2c0 fs/read_write.c:643
do_syscall_64+0xfb/0x240
entry_SYSCALL_64_after_hwframe+0x6d/0x75
Freed by task 11915:
kasan_save_stack mm/kasan/common.c:47 [inline]
kasan_save_track+0x3f/0x80 mm/kasan/common.c:68
kasan_save_free_info+0x40/0x50 mm/kasan/generic.c:586
poison_slab_object+0xa6/0xe0 mm/kasan/common.c:240
__kasan_slab_free+0x37/0x60 mm/kasan/common.c:256
kasan_slab_free include/linux/kasan.h:184 [inline]
slab_free_hook mm/slub.c:2122 [inline]
slab_free mm/slub.c:4296 [inline]
kfree+0x14a/0x380 mm/slub.c:4406
ucma_close_id drivers/infiniband/core/ucma.c:186 [inline]
ucma_destroy_private_ctx+0x14e/0xc10 drivers/infiniband/core/ucma.c:578
ucma_close+0xfc/0x170 drivers/infiniband/core/ucma.c:1808
__fput+0x429/0x8a0 fs/file_table.c:411
__do_sys_close fs/open.c:1557 [inline]
__se_sys_close fs/open.c:1542 [inline]
__x64_sys_close+0x7f/0x110 fs/open.c:1542
do_syscall_64+0xfb/0x240
entry_SYSCALL_64_after_hwframe+0x6d/0x75
The buggy address belongs to the object at ffff88808dcf6000
which belongs to the cache kmalloc-2k of size 2048
The buggy address is located 388 bytes inside of
freed 2048-byte region [ffff88808dcf6000, ffff88808dcf6800)
The buggy address belongs to the physical page:
page:ffffea0002373c00 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x8dcf0
head:ffffea0002373c00 order:3 entire_mapcount:0 nr_pages_mapped:0 pincount:0
flags: 0xfff80000000840(slab|head|node=0|zone=1|lastcpupid=0xfff)
page_type: 0xffffffff()
raw: 00fff80000000840 ffff888014c42000 dead000000000100 dead000000000122
raw: 0000000000000000 0000000000080008 00000001ffffffff 0000000000000000
page dumped because: kasan: bad access detected
page_owner tracks the page as allocated
page last allocated via order 3, migratetype Unmovable, gfp_mask 0xd20c0(__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC), pid 5149, tgid 5149 (kworker/1:4), ts 205905084555, free_ts 0
set_page_owner include/linux/page_owner.h:31 [inline]
post_alloc_hook+0x1ea/0x210 mm/page_alloc.c:1533
prep_new_page mm/page_alloc.c:1540 [inline]
get_page_from_freelist+0x33ea/0x3580 mm/page_alloc.c:3311
__alloc_pages+0x256/0x6a0 mm/page_alloc.c:4567
__alloc_pages_node include/linux/gfp.h:238 [inline]
alloc_pages_node include/linux/gfp.h:261 [inline]
alloc_slab_page+0x5f/0x160 mm/slub.c:2191
allocate_slab mm/slub.c:2354 [inline]
new_slab+0x84/0x2f0 mm/slub.c:2407
___slab_alloc+0xc73/0x1260 mm/slub.c:3541
__slab_alloc mm/slub.c:3626 [inline]
__slab_alloc_node mm/slub.c:3679 [inline]
slab_alloc_node mm/slub.c:3851 [inline]
__do_kmalloc_node mm/slub.c:3981 [inline]
__kmalloc_node_track_caller+0x2d4/0x4e0 mm/slub.c:4002
kmalloc_reserve+0xf3/0x260 net/core/skbuff.c:582
__alloc_skb+0x1b1/0x420 net/core/skbuff.c:651
alloc_skb include/linux/skbuff.h:1296 [inline]
alloc_skb_with_frags+0xc3/0x780 net/core/skbuff.c:6394
sock_alloc_send_pskb+0x91a/0xa60 net/core/sock.c:2794
sock_alloc_send_skb include/net/sock.h:1855 [inline]
mld_newpack+0x1c3/0xa90 net/ipv6/mcast.c:1746
add_grhead net/ipv6/mcast.c:1849 [inline]
add_grec+0x1492/0x19a0 net/ipv6/mcast.c:1987
mld_send_cr net/ipv6/mcast.c:2113 [inline]
mld_ifc_work+0x6bf/0xb30 net/ipv6/mcast.c:2650
process_one_work kernel/workqueue.c:3146 [inline]
process_scheduled_works+0x9d7/0x1730 kernel/workqueue.c:3226
worker_thread+0x86d/0xd70 kernel/workqueue.c:3307
page_owner free stack trace missing
Memory state around the buggy address:
ffff88808dcf6080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
ffff88808dcf6100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff88808dcf6180: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
^
ffff88808dcf6200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
ffff88808dcf6280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================
---
This report is generated by a bot. It may contain errors.
See https://goo.gl/tpsmEJ for more information about syzbot.
syzbot engineers can be reached at [email protected].
syzbot will keep track of this issue. See:
https://goo.gl/tpsmEJ#status for how to communicate with syzbot.
If the report is already addressed, let syzbot know by replying with:
#syz fix: exact-commit-title
If you want to overwrite report's subsystems, reply with:
#syz set subsystems: new-subsystem
(See the list of subsystem names on the web dashboard)
If the report is a duplicate of another one, reply with:
#syz dup: exact-subject-of-another-report
If you want to undo deduplication, reply with:
#syz undup
在 2024/2/23 18:51, syzbot 写道:
> Hello,
>
> syzbot found the following issue on:
>
> HEAD commit: 2c3b09aac00d Add linux-next specific files for 20240214
> git tree: linux-next
> console output: https://syzkaller.appspot.com/x/log.txt?x=1793a064180000
> kernel config: https://syzkaller.appspot.com/x/.config?x=176d2dcbf8ba7017
> dashboard link: https://syzkaller.appspot.com/bug?extid=a2e2735f09ebb9d95bd1
> compiler: Debian clang version 15.0.6, GNU ld (GNU Binutils for Debian) 2.40
>
> Unfortunately, I don't have any reproducer for this issue yet.
>
> Downloadable assets:
> disk image: https://storage.googleapis.com/syzbot-assets/ac51042b61c6/disk-2c3b09aa.raw.xz
> vmlinux: https://storage.googleapis.com/syzbot-assets/012344301c35/vmlinux-2c3b09aa.xz
> kernel image: https://storage.googleapis.com/syzbot-assets/cba3c3e5cd7c/bzImage-2c3b09aa.xz
>
> IMPORTANT: if you fix the issue, please add the following tag to the commit:
> Reported-by: [email protected]
>
> ==================================================================
> BUG: KASAN: slab-use-after-free in compare_netdev_and_ip drivers/infiniband/core/cma.c:473 [inline]
> BUG: KASAN: slab-use-after-free in cma_add_id_to_tree drivers/infiniband/core/cma.c:513 [inline]
> BUG: KASAN: slab-use-after-free in rdma_resolve_route+0x23f7/0x3150 drivers/infiniband/core/cma.c:3379
> Read of size 4 at addr ffff88808dcf6184 by task syz-executor.4/11929
I delved into the source code (cma.c), it seems that the spinlock
id_table_lock protects id_priv as below when id_priv is used:
468 static int compare_netdev_and_ip(int ifindex_a, struct sockaddr *sa,
469 struct id_table_entry *entry_b)
470 {
471 struct rdma_id_private *id_priv = list_first_entry(
472 &entry_b->id_list, struct rdma_id_private,
id_list_entry);
473 int ifindex_b = id_priv->id.route.addr.dev_addr.bound_dev_if;
474 struct sockaddr *sb = cma_dst_addr(id_priv);
But when id_priv is freed. No id_table_lock is used to protect id_priv
as below.
2067 static void destroy_id_handler_unlock(struct rdma_id_private *id_priv)
2068 __releases(&idprv->handler_mutex)
2069 {
2070 enum rdma_cm_state state;
2071 unsigned long flags;
2072
2073 trace_cm_id_destroy(id_priv);
2074
2075 /*
2076 * Setting the state to destroyed under the handler mutex
provides a
2077 * fence against calling handler callbacks. If this is
invoked due to
2078 * the failure of a handler callback then it guarentees
that no future
2079 * handlers will be called.
2080 */
2081 lockdep_assert_held(&id_priv->handler_mutex);
2082 spin_lock_irqsave(&id_priv->lock, flags);
2083 state = id_priv->state;
2084 id_priv->state = RDMA_CM_DESTROYING;
2085 spin_unlock_irqrestore(&id_priv->lock, flags);
2086 mutex_unlock(&id_priv->handler_mutex);
2087 _destroy_id(id_priv, state);
2088 }
As such, This causes id_priv to get out of sync.
So a dirty and quick solution should be:
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 1e2cd7c8716e..5cf034494898 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -2084,7 +2084,9 @@ static void destroy_id_handler_unlock(struct
rdma_id_private *id_priv)
id_priv->state = RDMA_CM_DESTROYING;
spin_unlock_irqrestore(&id_priv->lock, flags);
mutex_unlock(&id_priv->handler_mutex);
+ spin_lock_irqsave(&id_table_lock, flags);
_destroy_id(id_priv, state);
+ spin_unlock_irqrestore(&id_table_lock, flags);
}
That is, the spinlock id_table_lock is used when id_priv is freed.
And in the function compare_netdev_and_ip, when id_priv is NULL, the
function compare_netdev_and_ip returns directly.
RDMA stack is big and complicated. This is just my 2 cents. Please
comment. Thanks a lot.
Zhu Yanjun
>
> CPU: 1 PID: 11929 Comm: syz-executor.4 Not tainted 6.8.0-rc4-next-20240214-syzkaller #0
> Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/25/2024
> Call Trace:
> <TASK>
> __dump_stack lib/dump_stack.c:88 [inline]
> dump_stack_lvl+0x241/0x360 lib/dump_stack.c:114
> print_address_description mm/kasan/report.c:377 [inline]
> print_report+0x169/0x550 mm/kasan/report.c:488
> kasan_report+0x143/0x180 mm/kasan/report.c:601
> compare_netdev_and_ip drivers/infiniband/core/cma.c:473 [inline]
> cma_add_id_to_tree drivers/infiniband/core/cma.c:513 [inline]
> rdma_resolve_route+0x23f7/0x3150 drivers/infiniband/core/cma.c:3379
> ucma_resolve_route+0x1ba/0x330 drivers/infiniband/core/ucma.c:745
> ucma_write+0x2df/0x430 drivers/infiniband/core/ucma.c:1743
> vfs_write+0x2a4/0xcb0 fs/read_write.c:588
> ksys_write+0x1a0/0x2c0 fs/read_write.c:643
> do_syscall_64+0xfb/0x240
> entry_SYSCALL_64_after_hwframe+0x6d/0x75
> RIP: 0033:0x7f4eae47dda9
> Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 e1 20 00 00 90 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
> RSP: 002b:00007f4eaf2cd0c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
> RAX: ffffffffffffffda RBX: 00007f4eae5abf80 RCX: 00007f4eae47dda9
> RDX: 0000000000000010 RSI: 0000000020000440 RDI: 0000000000000003
> RBP: 00007f4eae4ca47a R08: 0000000000000000 R09: 0000000000000000
> R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
> R13: 000000000000000b R14: 00007f4eae5abf80 R15: 00007fff93bb3dc8
> </TASK>
>
> Allocated by task 11919:
> kasan_save_stack mm/kasan/common.c:47 [inline]
> kasan_save_track+0x3f/0x80 mm/kasan/common.c:68
> poison_kmalloc_redzone mm/kasan/common.c:370 [inline]
> __kasan_kmalloc+0x98/0xb0 mm/kasan/common.c:387
> kasan_kmalloc include/linux/kasan.h:211 [inline]
> kmalloc_trace+0x1d9/0x360 mm/slub.c:4013
> kmalloc include/linux/slab.h:590 [inline]
> kzalloc include/linux/slab.h:711 [inline]
> __rdma_create_id+0x65/0x590 drivers/infiniband/core/cma.c:993
> rdma_create_user_id+0x83/0xc0 drivers/infiniband/core/cma.c:1049
> ucma_create_id+0x2d0/0x500 drivers/infiniband/core/ucma.c:463
> ucma_write+0x2df/0x430 drivers/infiniband/core/ucma.c:1743
> vfs_write+0x2a4/0xcb0 fs/read_write.c:588
> ksys_write+0x1a0/0x2c0 fs/read_write.c:643
> do_syscall_64+0xfb/0x240
> entry_SYSCALL_64_after_hwframe+0x6d/0x75
>
> Freed by task 11915:
> kasan_save_stack mm/kasan/common.c:47 [inline]
> kasan_save_track+0x3f/0x80 mm/kasan/common.c:68
> kasan_save_free_info+0x40/0x50 mm/kasan/generic.c:586
> poison_slab_object+0xa6/0xe0 mm/kasan/common.c:240
> __kasan_slab_free+0x37/0x60 mm/kasan/common.c:256
> kasan_slab_free include/linux/kasan.h:184 [inline]
> slab_free_hook mm/slub.c:2122 [inline]
> slab_free mm/slub.c:4296 [inline]
> kfree+0x14a/0x380 mm/slub.c:4406
> ucma_close_id drivers/infiniband/core/ucma.c:186 [inline]
> ucma_destroy_private_ctx+0x14e/0xc10 drivers/infiniband/core/ucma.c:578
> ucma_close+0xfc/0x170 drivers/infiniband/core/ucma.c:1808
> __fput+0x429/0x8a0 fs/file_table.c:411
> __do_sys_close fs/open.c:1557 [inline]
> __se_sys_close fs/open.c:1542 [inline]
> __x64_sys_close+0x7f/0x110 fs/open.c:1542
> do_syscall_64+0xfb/0x240
> entry_SYSCALL_64_after_hwframe+0x6d/0x75
>
> The buggy address belongs to the object at ffff88808dcf6000
> which belongs to the cache kmalloc-2k of size 2048
> The buggy address is located 388 bytes inside of
> freed 2048-byte region [ffff88808dcf6000, ffff88808dcf6800)
>
> The buggy address belongs to the physical page:
> page:ffffea0002373c00 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x8dcf0
> head:ffffea0002373c00 order:3 entire_mapcount:0 nr_pages_mapped:0 pincount:0
> flags: 0xfff80000000840(slab|head|node=0|zone=1|lastcpupid=0xfff)
> page_type: 0xffffffff()
> raw: 00fff80000000840 ffff888014c42000 dead000000000100 dead000000000122
> raw: 0000000000000000 0000000000080008 00000001ffffffff 0000000000000000
> page dumped because: kasan: bad access detected
> page_owner tracks the page as allocated
> page last allocated via order 3, migratetype Unmovable, gfp_mask 0xd20c0(__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC), pid 5149, tgid 5149 (kworker/1:4), ts 205905084555, free_ts 0
> set_page_owner include/linux/page_owner.h:31 [inline]
> post_alloc_hook+0x1ea/0x210 mm/page_alloc.c:1533
> prep_new_page mm/page_alloc.c:1540 [inline]
> get_page_from_freelist+0x33ea/0x3580 mm/page_alloc.c:3311
> __alloc_pages+0x256/0x6a0 mm/page_alloc.c:4567
> __alloc_pages_node include/linux/gfp.h:238 [inline]
> alloc_pages_node include/linux/gfp.h:261 [inline]
> alloc_slab_page+0x5f/0x160 mm/slub.c:2191
> allocate_slab mm/slub.c:2354 [inline]
> new_slab+0x84/0x2f0 mm/slub.c:2407
> ___slab_alloc+0xc73/0x1260 mm/slub.c:3541
> __slab_alloc mm/slub.c:3626 [inline]
> __slab_alloc_node mm/slub.c:3679 [inline]
> slab_alloc_node mm/slub.c:3851 [inline]
> __do_kmalloc_node mm/slub.c:3981 [inline]
> __kmalloc_node_track_caller+0x2d4/0x4e0 mm/slub.c:4002
> kmalloc_reserve+0xf3/0x260 net/core/skbuff.c:582
> __alloc_skb+0x1b1/0x420 net/core/skbuff.c:651
> alloc_skb include/linux/skbuff.h:1296 [inline]
> alloc_skb_with_frags+0xc3/0x780 net/core/skbuff.c:6394
> sock_alloc_send_pskb+0x91a/0xa60 net/core/sock.c:2794
> sock_alloc_send_skb include/net/sock.h:1855 [inline]
> mld_newpack+0x1c3/0xa90 net/ipv6/mcast.c:1746
> add_grhead net/ipv6/mcast.c:1849 [inline]
> add_grec+0x1492/0x19a0 net/ipv6/mcast.c:1987
> mld_send_cr net/ipv6/mcast.c:2113 [inline]
> mld_ifc_work+0x6bf/0xb30 net/ipv6/mcast.c:2650
> process_one_work kernel/workqueue.c:3146 [inline]
> process_scheduled_works+0x9d7/0x1730 kernel/workqueue.c:3226
> worker_thread+0x86d/0xd70 kernel/workqueue.c:3307
> page_owner free stack trace missing
>
> Memory state around the buggy address:
> ffff88808dcf6080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
> ffff88808dcf6100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>> ffff88808dcf6180: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
> ^
> ffff88808dcf6200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
> ffff88808dcf6280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
> ==================================================================
>
>
> ---
> This report is generated by a bot. It may contain errors.
> See https://goo.gl/tpsmEJ for more information about syzbot.
> syzbot engineers can be reached at [email protected].
>
> syzbot will keep track of this issue. See:
> https://goo.gl/tpsmEJ#status for how to communicate with syzbot.
>
> If the report is already addressed, let syzbot know by replying with:
> #syz fix: exact-commit-title
>
> If you want to overwrite report's subsystems, reply with:
> #syz set subsystems: new-subsystem
> (See the list of subsystem names on the web dashboard)
>
> If the report is a duplicate of another one, reply with:
> #syz dup: exact-subject-of-another-report
>
> If you want to undo deduplication, reply with:
> #syz undup
在 2024/2/24 10:12, Zhu Yanjun 写道:
> 在 2024/2/23 18:51, syzbot 写道:
>> Hello,
>>
>> syzbot found the following issue on:
>>
>> HEAD commit: 2c3b09aac00d Add linux-next specific files for 20240214
>> git tree: linux-next
>> console output: https://syzkaller.appspot.com/x/log.txt?x=1793a064180000
>> kernel config:
>> https://syzkaller.appspot.com/x/.config?x=176d2dcbf8ba7017
>> dashboard link:
>> https://syzkaller.appspot.com/bug?extid=a2e2735f09ebb9d95bd1
>> compiler: Debian clang version 15.0.6, GNU ld (GNU Binutils for
>> Debian) 2.40
>>
>> Unfortunately, I don't have any reproducer for this issue yet.
>>
>> Downloadable assets:
>> disk image:
>> https://storage.googleapis.com/syzbot-assets/ac51042b61c6/disk-2c3b09aa.raw.xz
>> vmlinux:
>> https://storage.googleapis.com/syzbot-assets/012344301c35/vmlinux-2c3b09aa.xz
>> kernel image:
>> https://storage.googleapis.com/syzbot-assets/cba3c3e5cd7c/bzImage-2c3b09aa.xz
>>
>> IMPORTANT: if you fix the issue, please add the following tag to the
>> commit:
>> Reported-by: [email protected]
>>
>> ==================================================================
>> BUG: KASAN: slab-use-after-free in compare_netdev_and_ip
>> drivers/infiniband/core/cma.c:473 [inline]
>> BUG: KASAN: slab-use-after-free in cma_add_id_to_tree
>> drivers/infiniband/core/cma.c:513 [inline]
>> BUG: KASAN: slab-use-after-free in rdma_resolve_route+0x23f7/0x3150
>> drivers/infiniband/core/cma.c:3379
>> Read of size 4 at addr ffff88808dcf6184 by task syz-executor.4/11929
>
> I delved into the source code (cma.c), it seems that the spinlock
> id_table_lock protects id_priv as below when id_priv is used:
>
> 468 static int compare_netdev_and_ip(int ifindex_a, struct sockaddr *sa,
> 469 struct id_table_entry *entry_b)
> 470 {
> 471 struct rdma_id_private *id_priv = list_first_entry(
> 472 &entry_b->id_list, struct rdma_id_private,
> id_list_entry);
> 473 int ifindex_b = id_priv->id.route.addr.dev_addr.bound_dev_if;
> 474 struct sockaddr *sb = cma_dst_addr(id_priv);
>
> But when id_priv is freed. No id_table_lock is used to protect id_priv
> as below.
>
> 2067 static void destroy_id_handler_unlock(struct rdma_id_private *id_priv)
> 2068 __releases(&idprv->handler_mutex)
> 2069 {
> 2070 enum rdma_cm_state state;
> 2071 unsigned long flags;
> 2072
> 2073 trace_cm_id_destroy(id_priv);
> 2074
> 2075 /*
> 2076 * Setting the state to destroyed under the handler mutex
> provides a
> 2077 * fence against calling handler callbacks. If this is
> invoked due to
> 2078 * the failure of a handler callback then it guarentees
> that no future
> 2079 * handlers will be called.
> 2080 */
> 2081 lockdep_assert_held(&id_priv->handler_mutex);
> 2082 spin_lock_irqsave(&id_priv->lock, flags);
> 2083 state = id_priv->state;
> 2084 id_priv->state = RDMA_CM_DESTROYING;
> 2085 spin_unlock_irqrestore(&id_priv->lock, flags);
> 2086 mutex_unlock(&id_priv->handler_mutex);
> 2087 _destroy_id(id_priv, state);
> 2088 }
>
> As such, This causes id_priv to get out of sync.
> So a dirty and quick solution should be:
>
> diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
> index 1e2cd7c8716e..5cf034494898 100644
> --- a/drivers/infiniband/core/cma.c
> +++ b/drivers/infiniband/core/cma.c
> @@ -2084,7 +2084,9 @@ static void destroy_id_handler_unlock(struct
> rdma_id_private *id_priv)
> id_priv->state = RDMA_CM_DESTROYING;
> spin_unlock_irqrestore(&id_priv->lock, flags);
> mutex_unlock(&id_priv->handler_mutex);
> + spin_lock_irqsave(&id_table_lock, flags);
Please ignore.
id_table_lock is used in cma_remove_id_from_tree. This will cause spin
lock embeded.
> _destroy_id(id_priv, state);
> + spin_unlock_irqrestore(&id_table_lock, flags);
> }
>
> That is, the spinlock id_table_lock is used when id_priv is freed.
>
> And in the function compare_netdev_and_ip, when id_priv is NULL, the
> function compare_netdev_and_ip returns directly.
>
> RDMA stack is big and complicated. This is just my 2 cents. Please
> comment. Thanks a lot.
>
> Zhu Yanjun
>
>>
>> CPU: 1 PID: 11929 Comm: syz-executor.4 Not tainted
>> 6.8.0-rc4-next-20240214-syzkaller #0
>> Hardware name: Google Google Compute Engine/Google Compute Engine,
>> BIOS Google 01/25/2024
>> Call Trace:
>> <TASK>
>> __dump_stack lib/dump_stack.c:88 [inline]
>> dump_stack_lvl+0x241/0x360 lib/dump_stack.c:114
>> print_address_description mm/kasan/report.c:377 [inline]
>> print_report+0x169/0x550 mm/kasan/report.c:488
>> kasan_report+0x143/0x180 mm/kasan/report.c:601
>> compare_netdev_and_ip drivers/infiniband/core/cma.c:473 [inline]
>> cma_add_id_to_tree drivers/infiniband/core/cma.c:513 [inline]
>> rdma_resolve_route+0x23f7/0x3150 drivers/infiniband/core/cma.c:3379
>> ucma_resolve_route+0x1ba/0x330 drivers/infiniband/core/ucma.c:745
>> ucma_write+0x2df/0x430 drivers/infiniband/core/ucma.c:1743
>> vfs_write+0x2a4/0xcb0 fs/read_write.c:588
>> ksys_write+0x1a0/0x2c0 fs/read_write.c:643
>> do_syscall_64+0xfb/0x240
>> entry_SYSCALL_64_after_hwframe+0x6d/0x75
>> RIP: 0033:0x7f4eae47dda9
>> Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 e1 20 00 00 90 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
>> RSP: 002b:00007f4eaf2cd0c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
>> RAX: ffffffffffffffda RBX: 00007f4eae5abf80 RCX: 00007f4eae47dda9
>> RDX: 0000000000000010 RSI: 0000000020000440 RDI: 0000000000000003
>> RBP: 00007f4eae4ca47a R08: 0000000000000000 R09: 0000000000000000
>> R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
>> R13: 000000000000000b R14: 00007f4eae5abf80 R15: 00007fff93bb3dc8
>> </TASK>
>>
>> Allocated by task 11919:
>> kasan_save_stack mm/kasan/common.c:47 [inline]
>> kasan_save_track+0x3f/0x80 mm/kasan/common.c:68
>> poison_kmalloc_redzone mm/kasan/common.c:370 [inline]
>> __kasan_kmalloc+0x98/0xb0 mm/kasan/common.c:387
>> kasan_kmalloc include/linux/kasan.h:211 [inline]
>> kmalloc_trace+0x1d9/0x360 mm/slub.c:4013
>> kmalloc include/linux/slab.h:590 [inline]
>> kzalloc include/linux/slab.h:711 [inline]
>> __rdma_create_id+0x65/0x590 drivers/infiniband/core/cma.c:993
>> rdma_create_user_id+0x83/0xc0 drivers/infiniband/core/cma.c:1049
>> ucma_create_id+0x2d0/0x500 drivers/infiniband/core/ucma.c:463
>> ucma_write+0x2df/0x430 drivers/infiniband/core/ucma.c:1743
>> vfs_write+0x2a4/0xcb0 fs/read_write.c:588
>> ksys_write+0x1a0/0x2c0 fs/read_write.c:643
>> do_syscall_64+0xfb/0x240
>> entry_SYSCALL_64_after_hwframe+0x6d/0x75
>>
>> Freed by task 11915:
>> kasan_save_stack mm/kasan/common.c:47 [inline]
>> kasan_save_track+0x3f/0x80 mm/kasan/common.c:68
>> kasan_save_free_info+0x40/0x50 mm/kasan/generic.c:586
>> poison_slab_object+0xa6/0xe0 mm/kasan/common.c:240
>> __kasan_slab_free+0x37/0x60 mm/kasan/common.c:256
>> kasan_slab_free include/linux/kasan.h:184 [inline]
>> slab_free_hook mm/slub.c:2122 [inline]
>> slab_free mm/slub.c:4296 [inline]
>> kfree+0x14a/0x380 mm/slub.c:4406
>> ucma_close_id drivers/infiniband/core/ucma.c:186 [inline]
>> ucma_destroy_private_ctx+0x14e/0xc10 drivers/infiniband/core/ucma.c:578
>> ucma_close+0xfc/0x170 drivers/infiniband/core/ucma.c:1808
>> __fput+0x429/0x8a0 fs/file_table.c:411
>> __do_sys_close fs/open.c:1557 [inline]
>> __se_sys_close fs/open.c:1542 [inline]
>> __x64_sys_close+0x7f/0x110 fs/open.c:1542
>> do_syscall_64+0xfb/0x240
>> entry_SYSCALL_64_after_hwframe+0x6d/0x75
>>
>> The buggy address belongs to the object at ffff88808dcf6000
>> which belongs to the cache kmalloc-2k of size 2048
>> The buggy address is located 388 bytes inside of
>> freed 2048-byte region [ffff88808dcf6000, ffff88808dcf6800)
>>
>> The buggy address belongs to the physical page:
>> page:ffffea0002373c00 refcount:1 mapcount:0 mapping:0000000000000000
>> index:0x0 pfn:0x8dcf0
>> head:ffffea0002373c00 order:3 entire_mapcount:0 nr_pages_mapped:0
>> pincount:0
>> flags: 0xfff80000000840(slab|head|node=0|zone=1|lastcpupid=0xfff)
>> page_type: 0xffffffff()
>> raw: 00fff80000000840 ffff888014c42000 dead000000000100 dead000000000122
>> raw: 0000000000000000 0000000000080008 00000001ffffffff 0000000000000000
>> page dumped because: kasan: bad access detected
>> page_owner tracks the page as allocated
>> page last allocated via order 3, migratetype Unmovable, gfp_mask
>> 0xd20c0(__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC), pid 5149, tgid 5149 (kworker/1:4), ts 205905084555, free_ts 0
>> set_page_owner include/linux/page_owner.h:31 [inline]
>> post_alloc_hook+0x1ea/0x210 mm/page_alloc.c:1533
>> prep_new_page mm/page_alloc.c:1540 [inline]
>> get_page_from_freelist+0x33ea/0x3580 mm/page_alloc.c:3311
>> __alloc_pages+0x256/0x6a0 mm/page_alloc.c:4567
>> __alloc_pages_node include/linux/gfp.h:238 [inline]
>> alloc_pages_node include/linux/gfp.h:261 [inline]
>> alloc_slab_page+0x5f/0x160 mm/slub.c:2191
>> allocate_slab mm/slub.c:2354 [inline]
>> new_slab+0x84/0x2f0 mm/slub.c:2407
>> ___slab_alloc+0xc73/0x1260 mm/slub.c:3541
>> __slab_alloc mm/slub.c:3626 [inline]
>> __slab_alloc_node mm/slub.c:3679 [inline]
>> slab_alloc_node mm/slub.c:3851 [inline]
>> __do_kmalloc_node mm/slub.c:3981 [inline]
>> __kmalloc_node_track_caller+0x2d4/0x4e0 mm/slub.c:4002
>> kmalloc_reserve+0xf3/0x260 net/core/skbuff.c:582
>> __alloc_skb+0x1b1/0x420 net/core/skbuff.c:651
>> alloc_skb include/linux/skbuff.h:1296 [inline]
>> alloc_skb_with_frags+0xc3/0x780 net/core/skbuff.c:6394
>> sock_alloc_send_pskb+0x91a/0xa60 net/core/sock.c:2794
>> sock_alloc_send_skb include/net/sock.h:1855 [inline]
>> mld_newpack+0x1c3/0xa90 net/ipv6/mcast.c:1746
>> add_grhead net/ipv6/mcast.c:1849 [inline]
>> add_grec+0x1492/0x19a0 net/ipv6/mcast.c:1987
>> mld_send_cr net/ipv6/mcast.c:2113 [inline]
>> mld_ifc_work+0x6bf/0xb30 net/ipv6/mcast.c:2650
>> process_one_work kernel/workqueue.c:3146 [inline]
>> process_scheduled_works+0x9d7/0x1730 kernel/workqueue.c:3226
>> worker_thread+0x86d/0xd70 kernel/workqueue.c:3307
>> page_owner free stack trace missing
>>
>> Memory state around the buggy address:
>> ffff88808dcf6080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>> ffff88808dcf6100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>>> ffff88808dcf6180: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>> ^
>> ffff88808dcf6200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>> ffff88808dcf6280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>> ==================================================================
>>
>>
>> ---
>> This report is generated by a bot. It may contain errors.
>> See https://goo.gl/tpsmEJ for more information about syzbot.
>> syzbot engineers can be reached at [email protected].
>>
>> syzbot will keep track of this issue. See:
>> https://goo.gl/tpsmEJ#status for how to communicate with syzbot.
>>
>> If the report is already addressed, let syzbot know by replying with:
>> #syz fix: exact-commit-title
>>
>> If you want to overwrite report's subsystems, reply with:
>> #syz set subsystems: new-subsystem
>> (See the list of subsystem names on the web dashboard)
>>
>> If the report is a duplicate of another one, reply with:
>> #syz dup: exact-subject-of-another-report
>>
>> If you want to undo deduplication, reply with:
>> #syz undup
>
> #syz test: https://github.com/zhuyj/linux.git linux_6.8_rc4_rdma_cm
This crash does not have a reproducer. I cannot test it.
>
> 在 2024/2/23 18:51, syzbot 写道:
>> Hello,
>>
>> syzbot found the following issue on:
>>
>> HEAD commit: 2c3b09aac00d Add linux-next specific files for 20240214
>> git tree: linux-next
>> console output: https://syzkaller.appspot.com/x/log.txt?x=1793a064180000
>> kernel config: https://syzkaller.appspot.com/x/.config?x=176d2dcbf8ba7017
>> dashboard link: https://syzkaller.appspot.com/bug?extid=a2e2735f09ebb9d95bd1
>> compiler: Debian clang version 15.0.6, GNU ld (GNU Binutils for Debian) 2.40
>>
>> Unfortunately, I don't have any reproducer for this issue yet.
>>
>> Downloadable assets:
>> disk image: https://storage.googleapis.com/syzbot-assets/ac51042b61c6/disk-2c3b09aa.raw.xz
>> vmlinux: https://storage.googleapis.com/syzbot-assets/012344301c35/vmlinux-2c3b09aa.xz
>> kernel image: https://storage.googleapis.com/syzbot-assets/cba3c3e5cd7c/bzImage-2c3b09aa.xz
>>
>> IMPORTANT: if you fix the issue, please add the following tag to the commit:
>> Reported-by: [email protected]
>>
>> ==================================================================
>> BUG: KASAN: slab-use-after-free in compare_netdev_and_ip drivers/infiniband/core/cma.c:473 [inline]
>> BUG: KASAN: slab-use-after-free in cma_add_id_to_tree drivers/infiniband/core/cma.c:513 [inline]
>> BUG: KASAN: slab-use-after-free in rdma_resolve_route+0x23f7/0x3150 drivers/infiniband/core/cma.c:3379
>> Read of size 4 at addr ffff88808dcf6184 by task syz-executor.4/11929
>>
>> CPU: 1 PID: 11929 Comm: syz-executor.4 Not tainted 6.8.0-rc4-next-20240214-syzkaller #0
>> Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/25/2024
>> Call Trace:
>> <TASK>
>> __dump_stack lib/dump_stack.c:88 [inline]
>> dump_stack_lvl+0x241/0x360 lib/dump_stack.c:114
>> print_address_description mm/kasan/report.c:377 [inline]
>> print_report+0x169/0x550 mm/kasan/report.c:488
>> kasan_report+0x143/0x180 mm/kasan/report.c:601
>> compare_netdev_and_ip drivers/infiniband/core/cma.c:473 [inline]
>> cma_add_id_to_tree drivers/infiniband/core/cma.c:513 [inline]
>> rdma_resolve_route+0x23f7/0x3150 drivers/infiniband/core/cma.c:3379
>> ucma_resolve_route+0x1ba/0x330 drivers/infiniband/core/ucma.c:745
>> ucma_write+0x2df/0x430 drivers/infiniband/core/ucma.c:1743
>> vfs_write+0x2a4/0xcb0 fs/read_write.c:588
>> ksys_write+0x1a0/0x2c0 fs/read_write.c:643
>> do_syscall_64+0xfb/0x240
>> entry_SYSCALL_64_after_hwframe+0x6d/0x75
>> RIP: 0033:0x7f4eae47dda9
>> Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 e1 20 00 00 90 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
>> RSP: 002b:00007f4eaf2cd0c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
>> RAX: ffffffffffffffda RBX: 00007f4eae5abf80 RCX: 00007f4eae47dda9
>> RDX: 0000000000000010 RSI: 0000000020000440 RDI: 0000000000000003
>> RBP: 00007f4eae4ca47a R08: 0000000000000000 R09: 0000000000000000
>> R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
>> R13: 000000000000000b R14: 00007f4eae5abf80 R15: 00007fff93bb3dc8
>> </TASK>
>>
>> Allocated by task 11919:
>> kasan_save_stack mm/kasan/common.c:47 [inline]
>> kasan_save_track+0x3f/0x80 mm/kasan/common.c:68
>> poison_kmalloc_redzone mm/kasan/common.c:370 [inline]
>> __kasan_kmalloc+0x98/0xb0 mm/kasan/common.c:387
>> kasan_kmalloc include/linux/kasan.h:211 [inline]
>> kmalloc_trace+0x1d9/0x360 mm/slub.c:4013
>> kmalloc include/linux/slab.h:590 [inline]
>> kzalloc include/linux/slab.h:711 [inline]
>> __rdma_create_id+0x65/0x590 drivers/infiniband/core/cma.c:993
>> rdma_create_user_id+0x83/0xc0 drivers/infiniband/core/cma.c:1049
>> ucma_create_id+0x2d0/0x500 drivers/infiniband/core/ucma.c:463
>> ucma_write+0x2df/0x430 drivers/infiniband/core/ucma.c:1743
>> vfs_write+0x2a4/0xcb0 fs/read_write.c:588
>> ksys_write+0x1a0/0x2c0 fs/read_write.c:643
>> do_syscall_64+0xfb/0x240
>> entry_SYSCALL_64_after_hwframe+0x6d/0x75
>>
>> Freed by task 11915:
>> kasan_save_stack mm/kasan/common.c:47 [inline]
>> kasan_save_track+0x3f/0x80 mm/kasan/common.c:68
>> kasan_save_free_info+0x40/0x50 mm/kasan/generic.c:586
>> poison_slab_object+0xa6/0xe0 mm/kasan/common.c:240
>> __kasan_slab_free+0x37/0x60 mm/kasan/common.c:256
>> kasan_slab_free include/linux/kasan.h:184 [inline]
>> slab_free_hook mm/slub.c:2122 [inline]
>> slab_free mm/slub.c:4296 [inline]
>> kfree+0x14a/0x380 mm/slub.c:4406
>> ucma_close_id drivers/infiniband/core/ucma.c:186 [inline]
>> ucma_destroy_private_ctx+0x14e/0xc10 drivers/infiniband/core/ucma.c:578
>> ucma_close+0xfc/0x170 drivers/infiniband/core/ucma.c:1808
>> __fput+0x429/0x8a0 fs/file_table.c:411
>> __do_sys_close fs/open.c:1557 [inline]
>> __se_sys_close fs/open.c:1542 [inline]
>> __x64_sys_close+0x7f/0x110 fs/open.c:1542
>> do_syscall_64+0xfb/0x240
>> entry_SYSCALL_64_after_hwframe+0x6d/0x75
>>
>> The buggy address belongs to the object at ffff88808dcf6000
>> which belongs to the cache kmalloc-2k of size 2048
>> The buggy address is located 388 bytes inside of
>> freed 2048-byte region [ffff88808dcf6000, ffff88808dcf6800)
>>
>> The buggy address belongs to the physical page:
>> page:ffffea0002373c00 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x8dcf0
>> head:ffffea0002373c00 order:3 entire_mapcount:0 nr_pages_mapped:0 pincount:0
>> flags: 0xfff80000000840(slab|head|node=0|zone=1|lastcpupid=0xfff)
>> page_type: 0xffffffff()
>> raw: 00fff80000000840 ffff888014c42000 dead000000000100 dead000000000122
>> raw: 0000000000000000 0000000000080008 00000001ffffffff 0000000000000000
>> page dumped because: kasan: bad access detected
>> page_owner tracks the page as allocated
>> page last allocated via order 3, migratetype Unmovable, gfp_mask 0xd20c0(__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC), pid 5149, tgid 5149 (kworker/1:4), ts 205905084555, free_ts 0
>> set_page_owner include/linux/page_owner.h:31 [inline]
>> post_alloc_hook+0x1ea/0x210 mm/page_alloc.c:1533
>> prep_new_page mm/page_alloc.c:1540 [inline]
>> get_page_from_freelist+0x33ea/0x3580 mm/page_alloc.c:3311
>> __alloc_pages+0x256/0x6a0 mm/page_alloc.c:4567
>> __alloc_pages_node include/linux/gfp.h:238 [inline]
>> alloc_pages_node include/linux/gfp.h:261 [inline]
>> alloc_slab_page+0x5f/0x160 mm/slub.c:2191
>> allocate_slab mm/slub.c:2354 [inline]
>> new_slab+0x84/0x2f0 mm/slub.c:2407
>> ___slab_alloc+0xc73/0x1260 mm/slub.c:3541
>> __slab_alloc mm/slub.c:3626 [inline]
>> __slab_alloc_node mm/slub.c:3679 [inline]
>> slab_alloc_node mm/slub.c:3851 [inline]
>> __do_kmalloc_node mm/slub.c:3981 [inline]
>> __kmalloc_node_track_caller+0x2d4/0x4e0 mm/slub.c:4002
>> kmalloc_reserve+0xf3/0x260 net/core/skbuff.c:582
>> __alloc_skb+0x1b1/0x420 net/core/skbuff.c:651
>> alloc_skb include/linux/skbuff.h:1296 [inline]
>> alloc_skb_with_frags+0xc3/0x780 net/core/skbuff.c:6394
>> sock_alloc_send_pskb+0x91a/0xa60 net/core/sock.c:2794
>> sock_alloc_send_skb include/net/sock.h:1855 [inline]
>> mld_newpack+0x1c3/0xa90 net/ipv6/mcast.c:1746
>> add_grhead net/ipv6/mcast.c:1849 [inline]
>> add_grec+0x1492/0x19a0 net/ipv6/mcast.c:1987
>> mld_send_cr net/ipv6/mcast.c:2113 [inline]
>> mld_ifc_work+0x6bf/0xb30 net/ipv6/mcast.c:2650
>> process_one_work kernel/workqueue.c:3146 [inline]
>> process_scheduled_works+0x9d7/0x1730 kernel/workqueue.c:3226
>> worker_thread+0x86d/0xd70 kernel/workqueue.c:3307
>> page_owner free stack trace missing
>>
>> Memory state around the buggy address:
>> ffff88808dcf6080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>> ffff88808dcf6100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>>> ffff88808dcf6180: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>> ^
>> ffff88808dcf6200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>> ffff88808dcf6280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>> ==================================================================
>>
>>
>> ---
>> This report is generated by a bot. It may contain errors.
>> See https://goo.gl/tpsmEJ for more information about syzbot.
>> syzbot engineers can be reached at [email protected].
>>
>> syzbot will keep track of this issue. See:
>> https://goo.gl/tpsmEJ#status for how to communicate with syzbot.
>>
>> If the report is already addressed, let syzbot know by replying with:
>> #syz fix: exact-commit-title
>>
>> If you want to overwrite report's subsystems, reply with:
>> #syz set subsystems: new-subsystem
>> (See the list of subsystem names on the web dashboard)
>>
>> If the report is a duplicate of another one, reply with:
>> #syz dup: exact-subject-of-another-report
>>
>> If you want to undo deduplication, reply with:
>> #syz undup
>
> #syz test: https://github.com/zhuyj/linux.git linux_6.8_rc4_rdma_cm
This crash does not have a reproducer. I cannot test it.
>
> 在 2024/2/26 17:37, Zhu Yanjun 写道:
>> 在 2024/2/23 18:51, syzbot 写道:
>>> Hello,
>>>
>>> syzbot found the following issue on:
>>>
>>> HEAD commit: 2c3b09aac00d Add linux-next specific files for 20240214
>>> git tree: linux-next
>>> console output: https://syzkaller.appspot.com/x/log.txt?x=1793a064180000
>>> kernel config:
>>> https://syzkaller.appspot.com/x/.config?x=176d2dcbf8ba7017
>>> dashboard link:
>>> https://syzkaller.appspot.com/bug?extid=a2e2735f09ebb9d95bd1
>>> compiler: Debian clang version 15.06, GNU ld (GNU Binutils for
>>> Debian) 2.40
>>>
>>> Unfortunately, I don't have any reproducer for this issue yet.
>>>
>>> Downloadable assets:
>>> disk image:
>>> https://storage.googleapis.com/syzbot-assets/ac51042b61c6/disk-2c3b09aaraw.xz
>>> vmlinux:
>>> https://storage.googleapis.com/syzbot-assets/012344301c35/vmlinux-2c3b09aa.xz
>>> kernel image:
>>> https://storage.googleapis.com/syzbot-assets/cba3c3e5cd7c/bzImage-2c3b09aa.xz
>>>
>>> IMPORTANT: if you fix the issue, please add the following tag to the
>>> commit:
>>> Reported-by: [email protected]
>>>
>>> ==================================================================
>>> BUG: KASAN: slab-use-after-free in compare_netdev_and_ip
>>> drivers/infiniband/core/cma.c:473 [inline]
>>> BUG: KASAN: slab-use-after-free in cma_add_id_to_tree
>>> drivers/infiniband/core/cma.c:513 [inline]
>>> BUG: KASAN: slab-use-after-free in rdma_resolve_route+0x23f7/0x3150
>>> drivers/infiniband/core/cma.c:3379
>>> Read of size 4 at addr ffff88808dcf6184 by task syz-executor.4/11929
>>>
>>> CPU: 1 PID: 11929 Comm: syz-executor.4 Not tainted
>>> 6.8.0-rc4-next-20240214-syzkaller #0
>>> Hardware name: Google Google Compute Engine/Google Compute Engine,
>>> BIOS Google 01/25/2024
>>> Call Trace:
>>> <TASK>
>>> __dump_stack lib/dump_stack.c:88 [inline]
>>> dump_stack_lvl+0x241/0x360 lib/dump_stack.c:114
>>> print_address_description mm/kasan/report.c:377 [inline]
>>> print_report+0x169/0x550 mm/kasan/report.c:488
>>> kasan_report+0x143/0x180 mm/kasan/report.c:601
>>> compare_netdev_and_ip drivers/infiniband/core/cma.c:473 [inline]
>>> cma_add_id_to_tree drivers/infiniband/core/cma.c:513 [inline]
>>> rdma_resolve_route+0x23f7/0x3150 drivers/infiniband/core/cma.c:3379
>>> ucma_resolve_route+0x1ba/0x330 drivers/infiniband/core/ucma.c:745
>>> ucma_write+0x2df/0x430 drivers/infiniband/core/ucma.c:1743
>>> vfs_write+0x2a4/0xcb0 fs/read_write.c:588
>>> ksys_write+0x1a0/0x2c0 fs/read_write.c:643
>>> do_syscall_64+0xfb/0x240
>>> entry_SYSCALL_64_after_hwframe+0x6d/0x75
>>> RIP: 0033:0x7f4eae47dda9
>>> Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 e1 20 00 00 90 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
>>> RSP: 002b:00007f4eaf2cd0c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
>>> RAX: ffffffffffffffda RBX: 00007f4eae5abf80 RCX: 00007f4eae47dda9
>>> RDX: 0000000000000010 RSI: 0000000020000440 RDI: 0000000000000003
>>> RBP: 00007f4eae4ca47a R08: 0000000000000000 R09: 0000000000000000
>>> R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
>>> R13: 000000000000000b R14: 00007f4eae5abf80 R15: 00007fff93bb3dc8
>>> </TASK>
>>>
>>> Allocated by task 11919:
>>> kasan_save_stack mm/kasan/common.c:47 [inline]
>>> kasan_save_track+0x3f/0x80 mm/kasan/common.c:68
>>> poison_kmalloc_redzone mm/kasan/common.c:370 [inline]
>>> __kasan_kmalloc+0x98/0xb0 mm/kasan/common.c:387
>>> kasan_kmalloc include/linux/kasan.h:211 [inline]
>>> kmalloc_trace+0x1d9/0x360 mm/slub.c:4013
>>> kmalloc include/linux/slab.h:590 [inline]
>>> kzalloc include/linux/slab.h:711 [inline]
>>> __rdma_create_id+0x65/0x590 drivers/infiniband/core/cma.c:993
>>> rdma_create_user_id+0x83/0xc0 drivers/infiniband/core/cma.c:1049
>>> ucma_create_id+0x2d0/0x500 drivers/infiniband/core/ucma.c:463
>>> ucma_write+0x2df/0x430 drivers/infiniband/core/ucma.c:1743
>>> vfs_write+0x2a4/0xcb0 fs/read_write.c:588
>>> ksys_write+0x1a0/0x2c0 fs/read_write.c:643
>>> do_syscall_64+0xfb/0x240
>>> entry_SYSCALL_64_after_hwframe+0x6d/0x75
>>>
>>> Freed by task 11915:
>>> kasan_save_stack mm/kasan/common.c:47 [inline]
>>> kasan_save_track+0x3f/0x80 mm/kasan/common.c:68
>>> kasan_save_free_info+0x40/0x50 mm/kasan/generic.c:586
>>> poison_slab_object+0xa6/0xe0 mm/kasan/common.c:240
>>> __kasan_slab_free+0x37/0x60 mm/kasan/common.c:256
>>> kasan_slab_free include/linux/kasan.h:184 [inline]
>>> slab_free_hook mm/slub.c:2122 [inline]
>>> slab_free mm/slub.c:4296 [inline]
>>> kfree+0x14a/0x380 mm/slub.c:4406
>>> ucma_close_id drivers/infiniband/core/ucma.c:186 [inline]
>>> ucma_destroy_private_ctx+0x14e/0xc10
>>> drivers/infiniband/core/ucma.c:578
>>> ucma_close+0xfc/0x170 drivers/infiniband/core/ucma.c:1808
>>> __fput+0x429/0x8a0 fs/file_table.c:411
>>> __do_sys_close fs/open.c:1557 [inline]
>>> __se_sys_close fs/open.c:1542 [inline]
>>> __x64_sys_close+0x7f/0x110 fs/open.c:1542
>>> do_syscall_64+0xfb/0x240
>>> entry_SYSCALL_64_after_hwframe+0x6d/0x75
>>>
>>> The buggy address belongs to the object at ffff88808dcf6000
>>> which belongs to the cache kmalloc-2k of size 2048
>>> The buggy address is located 388 bytes inside of
>>> freed 2048-byte region [ffff88808dcf6000, ffff88808dcf6800)
>>>
>>> The buggy address belongs to the physical page:
>>> page:ffffea0002373c00 refcount:1 mapcount:0 mapping:0000000000000000
>>> index:0x0 pfn:0x8dcf0
>>> head:ffffea0002373c00 order:3 entire_mapcount:0 nr_pages_mapped:0
>>> pincount:0
>>> flags: 0xfff80000000840(slab|head|node=0|zone=1|lastcpupid=0xfff)
>>> page_type: 0xffffffff()
>>> raw: 00fff80000000840 ffff888014c42000 dead000000000100 dead000000000122
>>> raw: 0000000000000000 0000000000080008 00000001ffffffff 0000000000000000
>>> page dumped because: kasan: bad access detected
>>> page_owner tracks the page as allocated
>>> page last allocated via order 3, migratetype Unmovable, gfp_mask
>>> 0xd20c0(__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC),
>>> pid 5149, tgid 5149 (kworker/1:4), ts 205905084555, free_ts 0
>>> set_page_owner include/linux/page_owner.h:31 [inline]
>>> post_alloc_hook+0x1ea/0x210 mm/page_alloc.c:1533
>>> prep_new_page mm/page_alloc.c:1540 [inline]
>>> get_page_from_freelist+0x33ea/0x3580 mm/page_alloc.c:3311
>>> __alloc_pages+0x256/0x6a0 mm/page_alloc.c:4567
>>> __alloc_pages_node include/linux/gfp.h:238 [inline]
>>> alloc_pages_node include/linux/gfp.h:261 [inline]
>>> alloc_slab_page+0x5f/0x160 mm/slub.c:2191
>>> allocate_slab mm/slub.c:2354 [inline]
>>> new_slab+0x84/0x2f0 mm/slub.c:2407
>>> ___slab_alloc+0xc73/0x1260 mm/slub.c:3541
>>> __slab_alloc mm/slub.c:3626 [inline]
>>> __slab_alloc_node mm/slub.c:3679 [inline]
>>> slab_alloc_node mm/slub.c:3851 [inline]
>>> __do_kmalloc_node mm/slub.c:3981 [inline]
>>> __kmalloc_node_track_caller+0x2d4/0x4e0 mm/slub.c:4002
>>> kmalloc_reserve+0xf3/0x260 net/core/skbuff.c:582
>>> __alloc_skb+0x1b1/0x420 net/core/skbuff.c:651
>>> alloc_skb include/linux/skbuff.h:1296 [inline]
>>> alloc_skb_with_frags+0xc3/0x780 net/core/skbuff.c:6394
>>> sock_alloc_send_pskb+0x91a/0xa60 net/core/sock.c:2794
>>> sock_alloc_send_skb include/net/sock.h:1855 [inline]
>>> mld_newpack+0x1c3/0xa90 net/ipv6/mcast.c:1746
>>> add_grhead net/ipv6/mcast.c:1849 [inline]
>>> add_grec+0x1492/0x19a0 net/ipv6/mcast.c:1987
>>> mld_send_cr net/ipv6/mcast.c:2113 [inline]
>>> mld_ifc_work+0x6bf/0xb30 net/ipv6/mcast.c:2650
>>> process_one_work kernel/workqueue.c:3146 [inline]
>>> process_scheduled_works+0x9d7/0x1730 kernel/workqueue.c:3226
>>> worker_thread+0x86d/0xd70 kernel/workqueue.c:3307
>>> page_owner free stack trace missing
>>>
>>> Memory state around the buggy address:
>>> ffff88808dcf6080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>>> ffff88808dcf6100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>>>> ffff88808dcf6180: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>>> ^
>>> ffff88808dcf6200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>>> ffff88808dcf6280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>>> ==================================================================
>>>
>>>
>>> ---
>>> This report is generated by a bot. It may contain errors.
>>> See https://goo.gl/tpsmEJ for more information about syzbot.
>>> syzbot engineers can be reached at [email protected].
>>>
>>> syzbot will keep track of this issue. See:
>>> https://goo.gl/tpsmEJ#status for how to communicate with syzbot.
>>>
>>> If the report is already addressed, let syzbot know by replying with:
>>> #syz fix: exact-commit-title
>>>
>>> If you want to overwrite report's subsystems, reply with:
>>> #syz set subsystems: new-subsystem
>>> (See the list of subsystem names on the web dashboard)
>>>
>>> If the report is a duplicate of another one, reply with:
>>> #syz dup: exact-subject-of-another-report
>>>
>>> If you want to undo deduplication, reply with:
>>> #syz undup
>>
Hello, Yanjun I reproduced this bug and comfired, it may help your to
test your patch.
As always, I uploaded it here.
If you fix this issue, please add the following tag to the reporter or
reproducer:
Reported-by: xingwei lee <[email protected]>
Reported-by: sam sun <[email protected]>
I use the same configuation with syzbot dashboard.
kernel version: linux-next 2c3b09aac00d7835023bbc4473ee06696be64fa8
kernel config: syzkaller.appspot.com/text?tag=KernelConfig&x=176d2dcbf8ba7017
<http://syzkaller.appspot.com/text?tag=KernelConfig&x=176d2dcbf8ba7017>
with KASAN enabled
compiler: Debian clang version 15.0.6, GNU ld (GNU Binutils for Debian) 2.40
Likewise, this bug has more than one title, in my environment， these
titles are also relevant to this bug:
KASAN: slab-use-after-free Read in cma_netevent_callback
KASAN: slab-use-after-free Read in _destroy_id
KASAN: slab-use-after-free in cma_add_id_to_tree
KASAN: slab-use-after-free in compare_netdev_and_ip
root@syzkaller:~# ./925-7
[ 364.962016][ T8201] infiniband syz1: set active
[ 364.963857][ T8201] infiniband syz1: added syz_tun
[ 365.004959][ T8201] RDS/IB: syz1: added
[ 365.006131][ T8201] smc: adding ib device syz1 with port count 1
[ 365.007313][ T8201] smc: ib device syz1 port 1 has pnetid
[ 365.170043][ T8210] syz1: rxe_newlink: already configured on syz_tun
[ 365.190827][ T8211] syz1: rxe_newlink: already configured on syz_tun
[ 365.213461][ T8212] syz1: rxe_newlink: already configured on syz_tun
[ 365.232342][ T8213] syz1: rxe_newlink: already configured on syz_tun
[ 365.243876][ T8214] syz1: rxe_newlink: already configured on syz_tun
[ 365.258450][ T8215] syz1: rxe_newlink: already configured on syz_tun
[ 365.287755][ T8216] syz1: rxe_newlink: already configured on syz_tun
[ 365.307337][ T8217] syz1: rxe_newlink: already configured on syz_tun
[ 365.325342][ T8218] syz1: rxe_newlink: already configured on syz_tun
[ 365.337734][ T8219] syz1: rxe_newlink: already configured on syz_tun
[ 366.230237][ T8278]
==================================================================
[ 366.231886][ T8278] BUG: KASAN: slab-use-after-free in
rdma_resolve_route+0x2524/0x32a0
[ 366.234250][ T8278] Read of size 4 at addr ffff88801ff02184 by task
925-7/8278
[ 366.235595][ T8278]
[ 366.236068][ T8278] CPU: 0 PID: 8278 Comm: 925-7 Not tainted
6.8.0-rc4-next-20240214 #1
[ 366.237492][ T8278] Hardware name: QEMU Standard PC (i440FX + PIIX,
1996), BIOS 1.16.2-debian-1.16.2-1 04/01/2014
[ 366.239327][ T8278] Call Trace:
[ 366.239941][ T8278] <TASK>
[ 366.240469][ T8278] dump_stack_lvl+0x250/0x380
[ 366.242198][ T8278] ? __pfx_dump_stack_lvl+0x10/0x10
[ 366.243109][ T8278] ? __pfx__printk+0x10/0x10
[ 366.243934][ T8278] ? _printk+0xda/0x120
[ 366.244679][ T8278] ? __virt_addr_valid+0x19b/0x580
[ 366.245583][ T8278] ? __virt_addr_valid+0x19b/0x580
[ 366.246482][ T8278] print_report+0x169/0x550
[ 366.247290][ T8278] ? __virt_addr_valid+0x19b/0x580
[ 366.248202][ T8278] ? __virt_addr_valid+0x19b/0x580
[ 366.249100][ T8278] ? __virt_addr_valid+0x4a8/0x580
[ 366.250003][ T8278] ? __phys_addr+0xc3/0x180
[ 366.250822][ T8278] ? rdma_resolve_route+0x2524/0x32a0
[ 366.251840][ T8278] kasan_report+0x143/0x180
[ 366.252635][ T8278] ? _raw_spin_lock_irqsave+0xe1/0x120
[ 366.253586][ T8278] ? rdma_resolve_route+0x2524/0x32a0
[ 366.254542][ T8278] rdma_resolve_route+0x2524/0x32a0
[ 366.255476][ T8278] ? __mutex_lock+0x2ef/0xd70
[ 366.256304][ T8278] ? __pfx_rdma_resolve_route+0x10/0x10
[ 366.257284][ T8278] ? __pfx___mutex_lock+0x10/0x10
[ 366.258168][ T8278] ? ucma_get_ctx+0x29f/0x3b0
[ 366.259002][ T8278] ? __pfx_ucma_get_ctx+0x10/0x10
[ 366.259901][ T8278] ? __might_fault+0xcf/0x130
[ 366.260718][ T8278] ucma_resolve_route+0x1c3/0x330
[ 366.261581][ T8278] ? __pfx_ucma_resolve_route+0x10/0x10
[ 366.262524][ T8278] ? __might_fault+0xcf/0x130
[ 366.263324][ T8278] ? __pfx_ucma_resolve_route+0x10/0x10
[ 366.264273][ T8278] ucma_write+0x2f0/0x440
[ 366.264998][ T8278] ? __pfx_ucma_write+0x10/0x10
[ 366.265802][ T8278] ? bpf_lsm_file_permission+0xe/0x20
[ 366.266701][ T8278] ? rw_verify_area+0x1e7/0x5b0
[ 366.267543][ T8278] ? __pfx_ucma_write+0x10/0x10
[ 366.268341][ T8278] vfs_write+0x2b3/0xcf0
[ 366.269044][ T8278] ? kasan_quarantine_put+0xdc/0x230
[ 366.269917][ T8278] ? lockdep_hardirqs_on+0x99/0x150
[ 366.270784][ T8278] ? __pfx_vfs_write+0x10/0x10
[ 366.271587][ T8278] ? do_sys_openat2+0x160/0x1c0
[ 366.272398][ T8278] ? __pfx_do_sys_openat2+0x10/0x10
[ 366.273264][ T8278] ? __fdget_pos+0x1ab/0x340
[ 366.274037][ T8278] ksys_write+0x18e/0x2d0
[ 366.274764][ T8278] ? __pfx_ksys_write+0x10/0x10
[ 366.275579][ T8278] ? do_syscall_64+0x10a/0x240
[ 366.276380][ T8278] ? do_syscall_64+0xb6/0x240
[ 366.277163][ T8278] do_syscall_64+0xfb/0x240
[ 366.277941][ T8278] entry_SYSCALL_64_after_hwframe+0x6d/0x75
[ 366.278936][ T8278] RIP: 0033:0x437e19
[ 366.279595][ T8278] Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 d1 19
00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8
[ 366.282676][ T8278] RSP: 002b:00007fffdedc7398 EFLAGS: 00000207
ORIG_RAX: 0000000000000001
[ 366.284047][ T8278] RAX: ffffffffffffffda RBX: 00000000200001f8
RCX: 0000000000437e19
[ 366.285331][ T8278] RDX: 0000000000000010 RSI: 0000000020000440
RDI: 0000000000000004
[ 366.286615][ T8278] RBP: 00007fffdedc73c0 R08: 0000000000000000
R09: 0000000000000000
[ 366.287918][ T8278] R10: 0000000000000000 R11: 0000000000000207
R12: 0000000000000001
[ 366.289206][ T8278] R13: 00007fffdedc75e8 R14: 0000000000000001
R15: 0000000000000001
[ 366.290513][ T8278] </TASK>
=* repro.c =*
#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 <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/wait.h>
#include <time.h>
#include <unistd.h>
#include <linux/capability.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 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 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 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 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 void netlink_add_neigh(struct nlmsg* nlmsg,
int sock,
const char* name,
const void* addr,
int addrsize,
const void* mac,
int macsize) {
struct ndmsg hdr;
memset(&hdr, 0, sizeof(hdr));
hdr.ndm_family = addrsize == 4 ? AF_INET : AF_INET6;
hdr.ndm_ifindex = if_nametoindex(name);
hdr.ndm_state = NUD_PERMANENT;
netlink_init(nlmsg, RTM_NEWNEIGH, NLM_F_EXCL | NLM_F_CREATE, &hdr,
sizeof(hdr));
netlink_attr(nlmsg, NDA_DST, addr, addrsize);
netlink_attr(nlmsg, NDA_LLADDR, mac, macsize);
int err = netlink_send(nlmsg, sock);
if (err < 0) {
}
}
static struct nlmsg nlmsg;
static int tunfd = -1;
#define TUN_IFACE "syz_tun"
#define LOCAL_MAC 0xaaaaaaaaaaaa
#define REMOTE_MAC 0xaaaaaaaaaabb
#define LOCAL_IPV4 "172.20.20.170"
#define REMOTE_IPV4 "172.20.20.187"
#define LOCAL_IPV6 "fe80::aa"
#define REMOTE_IPV6 "fe80::bb"
#define IFF_NAPI 0x0010
static void initialize_tun(void) {
tunfd = open("/dev/net/tun", O_RDWR | O_NONBLOCK);
if (tunfd == -1) {
printf("tun: can't open /dev/net/tun: please enable CONFIG_TUN=y\n");
printf("otherwise fuzzing or reproducing might not work as intended\n");
return;
}
const int kTunFd = 200;
if (dup2(tunfd, kTunFd) < 0)
exit(1);
close(tunfd);
tunfd = kTunFd;
struct ifreq ifr;
memset(&ifr, 0, sizeof(ifr));
strncpy(ifr.ifr_name, TUN_IFACE, IFNAMSIZ);
ifr.ifr_flags = IFF_TAP | IFF_NO_PI;
if (ioctl(tunfd, TUNSETIFF, (void*)&ifr) < 0) {
exit(1);
}
char sysctl[64];
sprintf(sysctl, "/proc/sys/net/ipv6/conf/%s/accept_dad", TUN_IFACE);
write_file(sysctl, "0");
sprintf(sysctl, "/proc/sys/net/ipv6/conf/%s/router_solicitations", TUN_IFACE);
write_file(sysctl, "0");
int sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
if (sock == -1)
exit(1);
netlink_add_addr4(&nlmsg, sock, TUN_IFACE, LOCAL_IPV4);
netlink_add_addr6(&nlmsg, sock, TUN_IFACE, LOCAL_IPV6);
uint64_t macaddr = REMOTE_MAC;
struct in_addr in_addr;
inet_pton(AF_INET, REMOTE_IPV4, &in_addr);
netlink_add_neigh(&nlmsg, sock, TUN_IFACE, &in_addr, sizeof(in_addr),
&macaddr, ETH_ALEN);
struct in6_addr in6_addr;
inet_pton(AF_INET6, REMOTE_IPV6, &in6_addr);
netlink_add_neigh(&nlmsg, sock, TUN_IFACE, &in6_addr, sizeof(in6_addr),
&macaddr, ETH_ALEN);
macaddr = LOCAL_MAC;
netlink_device_change(&nlmsg, sock, TUN_IFACE, true, 0, &macaddr, ETH_ALEN,
NULL);
close(sock);
}
static int read_tun(char* data, int size) {
if (tunfd < 0)
return -1;
int rv = read(tunfd, data, size);
if (rv < 0) {
if (errno == EAGAIN || errno == EBADFD)
return -1;
exit(1);
}
return rv;
}
static void flush_tun() {
char data[1000];
while (read_tun(&data[0], sizeof(data)) != -1) {
}
}
#define MAX_FDS 30
static void setup_common() {
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);
setsid();
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);
setup_common();
sandbox_common();
drop_caps();
if (unshare(CLONE_NEWNET)) {
}
write_file("/proc/sys/net/ipv4/ping_group_range", "0 65535");
initialize_tun();
setup_binderfs();
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");
flush_tun();
}
static void close_fds() {
for (int fd = 3; fd < MAX_FDS; fd++)
close(fd);
}
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();
close_fds();
exit(0);
}
int status = 0;
uint64_t start = current_time_ms();
for (;;) {
if (waitpid(-1, &status, WNOHANG | WAIT_FLAGS) == pid)
break;
sleep_ms(1);
if (current_time_ms() - start < 5000)
continue;
kill_and_wait(pid, &status);
break;
}
}
}
uint64_t r[3] = {0xffffffffffffffff, 0xffffffffffffffff, 0xffffffffffffffff};
void execute_one(void) {
intptr_t res = 0;
res = syscall(__NR_socket, /*domain=*/0x10ul, /*type=*/3ul, /*proto=*/0x14);
if (res != -1)
r[0] = res;
*(uint64_t*)0x20000180 = 0;
*(uint32_t*)0x20000188 = 0;
*(uint64_t*)0x20000190 = 0x20000140;
*(uint64_t*)0x20000140 = 0x20000080;
*(uint32_t*)0x20000080 = 0x38;
*(uint16_t*)0x20000084 = 0x1403;
*(uint16_t*)0x20000086 = 1;
*(uint32_t*)0x20000088 = 0;
*(uint32_t*)0x2000008c = 0;
*(uint16_t*)0x20000090 = 9;
*(uint16_t*)0x20000092 = 2;
memcpy((void*)0x20000094, "syz1\000", 5);
*(uint16_t*)0x2000009c = 8;
*(uint16_t*)0x2000009e = 0x41;
memcpy((void*)0x200000a0, "rxe\000", 4);
*(uint16_t*)0x200000a4 = 0x14;
*(uint16_t*)0x200000a6 = 0x33;
memcpy((void*)0x200000a8, "syz_tun\000\000\000\000\000\000\000\000\000", 16);
*(uint64_t*)0x20000148 = 0x38;
*(uint64_t*)0x20000198 = 1;
*(uint64_t*)0x200001a0 = 0;
*(uint64_t*)0x200001a8 = 0;
*(uint32_t*)0x200001b0 = 0;
syscall(__NR_sendmsg, /*fd=*/r[0], /*msg=*/0x20000180ul, /*f=*/0ul);
memcpy((void*)0x20000100, "/dev/infiniband/rdma_cm\000", 24);
res = syscall(__NR_openat, /*fd=*/0xffffffffffffff9cul, /*file=*/0x20000100ul,
/*flags=*/2ul, /*mode=*/0ul);
if (res != -1)
r[1] = res;
*(uint32_t*)0x20000080 = 0;
*(uint16_t*)0x20000084 = 0x18;
*(uint16_t*)0x20000086 = 0xfa00;
*(uint64_t*)0x20000088 = 0;
*(uint64_t*)0x20000090 = 0x200000c0;
*(uint16_t*)0x20000098 = 0x106;
*(uint8_t*)0x2000009a = 0;
memset((void*)0x2000009b, 0, 5);
res = syscall(__NR_write, /*fd=*/r[1], /*data=*/0x20000080ul, /*len=*/0x20ul);
if (res != -1)
r[2] = *(uint32_t*)0x200000c0;
*(uint32_t*)0x200003c0 = 3;
*(uint16_t*)0x200003c4 = 0x40;
*(uint16_t*)0x200003c6 = 0xfa00;
*(uint16_t*)0x200003c8 = 0xa;
*(uint16_t*)0x200003ca = htobe16(0x4e24);
*(uint32_t*)0x200003cc = htobe32(1);
*(uint8_t*)0x200003d0 = -1;
*(uint8_t*)0x200003d1 = 2;
memset((void*)0x200003d2, 0, 13);
*(uint8_t*)0x200003df = 1;
*(uint32_t*)0x200003e0 = 9;
*(uint16_t*)0x200003e4 = 0xa;
*(uint16_t*)0x200003e6 = htobe16(0);
*(uint32_t*)0x200003e8 = htobe32(6);
*(uint8_t*)0x200003ec = 0xfe;
*(uint8_t*)0x200003ed = 0x80;
memset((void*)0x200003ee, 0, 13);
*(uint8_t*)0x200003fb = 0xbb;
*(uint32_t*)0x200003fc = 0xfffff000;
*(uint32_t*)0x20000400 = r[2];
*(uint32_t*)0x20000404 = 2;
syscall(__NR_write, /*fd=*/r[1], /*data=*/0x200003c0ul, /*len=*/0x48ul);
*(uint32_t*)0x20000140 = 0x15;
*(uint16_t*)0x20000144 = 0x110;
*(uint16_t*)0x20000146 = 0xfa00;
*(uint32_t*)0x20000148 = r[2];
*(uint32_t*)0x2000014c = 0;
*(uint16_t*)0x20000150 = 0;
*(uint16_t*)0x20000152 = 0x30;
*(uint32_t*)0x20000154 = 0;
*(uint16_t*)0x20000158 = 0x1b;
*(uint16_t*)0x2000015a = htobe16(0);
*(uint32_t*)0x2000015c = htobe32(0);
memset((void*)0x20000160, 0, 16);
*(uint32_t*)0x20000170 = 0;
*(uint16_t*)0x200001d8 = 0x1b;
*(uint16_t*)0x200001da = htobe16(0);
*(uint32_t*)0x200001dc = htobe32(0);
memset((void*)0x200001e0, 0, 16);
*(uint64_t*)0x200001f0 = htobe64(0);
*(uint64_t*)0x200001f8 = htobe64(0);
*(uint64_t*)0x20000200 = 0;
syscall(__NR_write, /*fd=*/r[1], /*data=*/0x20000140ul, /*len=*/0x118ul);
*(uint32_t*)0x20000440 = 4;
*(uint16_t*)0x20000444 = 8;
*(uint16_t*)0x20000446 = 0xfa00;
*(uint32_t*)0x20000448 = r[2];
*(uint32_t*)0x2000044c = 0xffff741a;
syscall(__NR_write, /*fd=*/r[1], /*data=*/0x20000440ul, /*len=*/0x10ul);
}
int main(void) {
syscall(__NR_mmap, /*addr=*/0x1ffff000ul, /*len=*/0x1000ul, /*prot=*/0ul,
/*flags=MAP_FIXED|MAP_ANONYMOUS|MAP_PRIVATE*/ 0x32ul, /*fd=*/-1,
/*offset=*/0ul);
syscall(__NR_mmap, /*addr=*/0x20000000ul, /*len=*/0x1000000ul,
/*prot=PROT_WRITE|PROT_READ|PROT_EXEC*/ 7ul,
/*flags=MAP_FIXED|MAP_ANONYMOUS|MAP_PRIVATE*/ 0x32ul, /*fd=*/-1,
/*offset=*/0ul);
syscall(__NR_mmap, /*addr=*/0x21000000ul, /*len=*/0x1000ul, /*prot=*/0ul,
/*flags=MAP_FIXED|MAP_ANONYMOUS|MAP_PRIVATE*/ 0x32ul, /*fd=*/-1,
/*offset=*/0ul);
do_sandbox_none();
return 0;
}
and also https://gist.github.com/xrivendell7/080e44fad03c27df3152ff3bcc8a8385
I hope it helps.
Best regards.
xingwei Lee
在 2024/3/4 5:43, xingwei lee 写道:
> Hello, Yanjun I reproduced this bug and comfired, it may help your to
> test your patch.
> As always, I uploaded it here.
Got it. I will make tests with it.
Thanks a lot.
Zhu Yanjun
>
> If you fix this issue, please add the following tag to the reporter or
> reproducer:
> Reported-by: xingwei lee <[email protected]>
> Reported-by: sam sun <[email protected]>
>
> I use the same configuation with syzbot dashboard.
> kernel version: linux-next 2c3b09aac00d7835023bbc4473ee06696be64fa8
> kernel config: syzkaller.appspot.com/text?tag=KernelConfig&x=176d2dcbf8ba7017
> <http://syzkaller.appspot.com/text?tag=KernelConfig&x=176d2dcbf8ba7017>
> with KASAN enabled
> compiler: Debian clang version 15.0.6, GNU ld (GNU Binutils for Debian) 2.40
>
> Likewise, this bug has more than one title, in my environment， these
> titles are also relevant to this bug:
> KASAN: slab-use-after-free Read in cma_netevent_callback
> KASAN: slab-use-after-free Read in _destroy_id
> KASAN: slab-use-after-free in cma_add_id_to_tree
> KASAN: slab-use-after-free in compare_netdev_and_ip
>
> root@syzkaller:~# ./925-7
> [ 364.962016][ T8201] infiniband syz1: set active
> [ 364.963857][ T8201] infiniband syz1: added syz_tun
> [ 365.004959][ T8201] RDS/IB: syz1: added
> [ 365.006131][ T8201] smc: adding ib device syz1 with port count 1
> [ 365.007313][ T8201] smc: ib device syz1 port 1 has pnetid
> [ 365.170043][ T8210] syz1: rxe_newlink: already configured on syz_tun
> [ 365.190827][ T8211] syz1: rxe_newlink: already configured on syz_tun
> [ 365.213461][ T8212] syz1: rxe_newlink: already configured on syz_tun
> [ 365.232342][ T8213] syz1: rxe_newlink: already configured on syz_tun
> [ 365.243876][ T8214] syz1: rxe_newlink: already configured on syz_tun
> [ 365.258450][ T8215] syz1: rxe_newlink: already configured on syz_tun
> [ 365.287755][ T8216] syz1: rxe_newlink: already configured on syz_tun
> [ 365.307337][ T8217] syz1: rxe_newlink: already configured on syz_tun
> [ 365.325342][ T8218] syz1: rxe_newlink: already configured on syz_tun
> [ 365.337734][ T8219] syz1: rxe_newlink: already configured on syz_tun
> [ 366.230237][ T8278]
> ==================================================================
> [ 366.231886][ T8278] BUG: KASAN: slab-use-after-free in
> rdma_resolve_route+0x2524/0x32a0
> [ 366.234250][ T8278] Read of size 4 at addr ffff88801ff02184 by task
> 925-7/8278
> [ 366.235595][ T8278]
> [ 366.236068][ T8278] CPU: 0 PID: 8278 Comm: 925-7 Not tainted
> 6.8.0-rc4-next-20240214 #1
> [ 366.237492][ T8278] Hardware name: QEMU Standard PC (i440FX + PIIX,
> 1996), BIOS 1.16.2-debian-1.16.2-1 04/01/2014
> [ 366.239327][ T8278] Call Trace:
> [ 366.239941][ T8278] <TASK>
> [ 366.240469][ T8278] dump_stack_lvl+0x250/0x380
> [ 366.242198][ T8278] ? __pfx_dump_stack_lvl+0x10/0x10
> [ 366.243109][ T8278] ? __pfx__printk+0x10/0x10
> [ 366.243934][ T8278] ? _printk+0xda/0x120
> [ 366.244679][ T8278] ? __virt_addr_valid+0x19b/0x580
> [ 366.245583][ T8278] ? __virt_addr_valid+0x19b/0x580
> [ 366.246482][ T8278] print_report+0x169/0x550
> [ 366.247290][ T8278] ? __virt_addr_valid+0x19b/0x580
> [ 366.248202][ T8278] ? __virt_addr_valid+0x19b/0x580
> [ 366.249100][ T8278] ? __virt_addr_valid+0x4a8/0x580
> [ 366.250003][ T8278] ? __phys_addr+0xc3/0x180
> [ 366.250822][ T8278] ? rdma_resolve_route+0x2524/0x32a0
> [ 366.251840][ T8278] kasan_report+0x143/0x180
> [ 366.252635][ T8278] ? _raw_spin_lock_irqsave+0xe1/0x120
> [ 366.253586][ T8278] ? rdma_resolve_route+0x2524/0x32a0
> [ 366.254542][ T8278] rdma_resolve_route+0x2524/0x32a0
> [ 366.255476][ T8278] ? __mutex_lock+0x2ef/0xd70
> [ 366.256304][ T8278] ? __pfx_rdma_resolve_route+0x10/0x10
> [ 366.257284][ T8278] ? __pfx___mutex_lock+0x10/0x10
> [ 366.258168][ T8278] ? ucma_get_ctx+0x29f/0x3b0
> [ 366.259002][ T8278] ? __pfx_ucma_get_ctx+0x10/0x10
> [ 366.259901][ T8278] ? __might_fault+0xcf/0x130
> [ 366.260718][ T8278] ucma_resolve_route+0x1c3/0x330
> [ 366.261581][ T8278] ? __pfx_ucma_resolve_route+0x10/0x10
> [ 366.262524][ T8278] ? __might_fault+0xcf/0x130
> [ 366.263324][ T8278] ? __pfx_ucma_resolve_route+0x10/0x10
> [ 366.264273][ T8278] ucma_write+0x2f0/0x440
> [ 366.264998][ T8278] ? __pfx_ucma_write+0x10/0x10
> [ 366.265802][ T8278] ? bpf_lsm_file_permission+0xe/0x20
> [ 366.266701][ T8278] ? rw_verify_area+0x1e7/0x5b0
> [ 366.267543][ T8278] ? __pfx_ucma_write+0x10/0x10
> [ 366.268341][ T8278] vfs_write+0x2b3/0xcf0
> [ 366.269044][ T8278] ? kasan_quarantine_put+0xdc/0x230
> [ 366.269917][ T8278] ? lockdep_hardirqs_on+0x99/0x150
> [ 366.270784][ T8278] ? __pfx_vfs_write+0x10/0x10
> [ 366.271587][ T8278] ? do_sys_openat2+0x160/0x1c0
> [ 366.272398][ T8278] ? __pfx_do_sys_openat2+0x10/0x10
> [ 366.273264][ T8278] ? __fdget_pos+0x1ab/0x340
> [ 366.274037][ T8278] ksys_write+0x18e/0x2d0
> [ 366.274764][ T8278] ? __pfx_ksys_write+0x10/0x10
> [ 366.275579][ T8278] ? do_syscall_64+0x10a/0x240
> [ 366.276380][ T8278] ? do_syscall_64+0xb6/0x240
> [ 366.277163][ T8278] do_syscall_64+0xfb/0x240
> [ 366.277941][ T8278] entry_SYSCALL_64_after_hwframe+0x6d/0x75
> [ 366.278936][ T8278] RIP: 0033:0x437e19
> [ 366.279595][ T8278] Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 d1 19
> 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8
> [ 366.282676][ T8278] RSP: 002b:00007fffdedc7398 EFLAGS: 00000207
> ORIG_RAX: 0000000000000001
> [ 366.284047][ T8278] RAX: ffffffffffffffda RBX: 00000000200001f8
> RCX: 0000000000437e19
> [ 366.285331][ T8278] RDX: 0000000000000010 RSI: 0000000020000440
> RDI: 0000000000000004
> [ 366.286615][ T8278] RBP: 00007fffdedc73c0 R08: 0000000000000000
> R09: 0000000000000000
> [ 366.287918][ T8278] R10: 0000000000000000 R11: 0000000000000207
> R12: 0000000000000001
> [ 366.289206][ T8278] R13: 00007fffdedc75e8 R14: 0000000000000001
> R15: 0000000000000001
> [ 366.290513][ T8278] </TASK>
>
>
> =* repro.c =*
> #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 <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/wait.h>
> #include <time.h>
> #include <unistd.h>
>
> #include <linux/capability.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 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 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 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 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 void netlink_add_neigh(struct nlmsg* nlmsg,
> int sock,
> const char* name,
> const void* addr,
> int addrsize,
> const void* mac,
> int macsize) {
> struct ndmsg hdr;
> memset(&hdr, 0, sizeof(hdr));
> hdr.ndm_family = addrsize == 4 ? AF_INET : AF_INET6;
> hdr.ndm_ifindex = if_nametoindex(name);
> hdr.ndm_state = NUD_PERMANENT;
> netlink_init(nlmsg, RTM_NEWNEIGH, NLM_F_EXCL | NLM_F_CREATE, &hdr,
> sizeof(hdr));
> netlink_attr(nlmsg, NDA_DST, addr, addrsize);
> netlink_attr(nlmsg, NDA_LLADDR, mac, macsize);
> int err = netlink_send(nlmsg, sock);
> if (err < 0) {
> }
> }
>
> static struct nlmsg nlmsg;
>
> static int tunfd = -1;
>
> #define TUN_IFACE "syz_tun"
> #define LOCAL_MAC 0xaaaaaaaaaaaa
> #define REMOTE_MAC 0xaaaaaaaaaabb
> #define LOCAL_IPV4 "172.20.20.170"
> #define REMOTE_IPV4 "172.20.20.187"
> #define LOCAL_IPV6 "fe80::aa"
> #define REMOTE_IPV6 "fe80::bb"
>
> #define IFF_NAPI 0x0010
>
> static void initialize_tun(void) {
> tunfd = open("/dev/net/tun", O_RDWR | O_NONBLOCK);
> if (tunfd == -1) {
> printf("tun: can't open /dev/net/tun: please enable CONFIG_TUN=y\n");
> printf("otherwise fuzzing or reproducing might not work as intended\n");
> return;
> }
> const int kTunFd = 200;
> if (dup2(tunfd, kTunFd) < 0)
> exit(1);
> close(tunfd);
> tunfd = kTunFd;
> struct ifreq ifr;
> memset(&ifr, 0, sizeof(ifr));
> strncpy(ifr.ifr_name, TUN_IFACE, IFNAMSIZ);
> ifr.ifr_flags = IFF_TAP | IFF_NO_PI;
> if (ioctl(tunfd, TUNSETIFF, (void*)&ifr) < 0) {
> exit(1);
> }
> char sysctl[64];
> sprintf(sysctl, "/proc/sys/net/ipv6/conf/%s/accept_dad", TUN_IFACE);
> write_file(sysctl, "0");
> sprintf(sysctl, "/proc/sys/net/ipv6/conf/%s/router_solicitations", TUN_IFACE);
> write_file(sysctl, "0");
> int sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
> if (sock == -1)
> exit(1);
> netlink_add_addr4(&nlmsg, sock, TUN_IFACE, LOCAL_IPV4);
> netlink_add_addr6(&nlmsg, sock, TUN_IFACE, LOCAL_IPV6);
> uint64_t macaddr = REMOTE_MAC;
> struct in_addr in_addr;
> inet_pton(AF_INET, REMOTE_IPV4, &in_addr);
> netlink_add_neigh(&nlmsg, sock, TUN_IFACE, &in_addr, sizeof(in_addr),
> &macaddr, ETH_ALEN);
> struct in6_addr in6_addr;
> inet_pton(AF_INET6, REMOTE_IPV6, &in6_addr);
> netlink_add_neigh(&nlmsg, sock, TUN_IFACE, &in6_addr, sizeof(in6_addr),
> &macaddr, ETH_ALEN);
> macaddr = LOCAL_MAC;
> netlink_device_change(&nlmsg, sock, TUN_IFACE, true, 0, &macaddr, ETH_ALEN,
> NULL);
> close(sock);
> }
>
> static int read_tun(char* data, int size) {
> if (tunfd < 0)
> return -1;
> int rv = read(tunfd, data, size);
> if (rv < 0) {
> if (errno == EAGAIN || errno == EBADFD)
> return -1;
> exit(1);
> }
> return rv;
> }
>
> static void flush_tun() {
> char data[1000];
> while (read_tun(&data[0], sizeof(data)) != -1) {
> }
> }
>
> #define MAX_FDS 30
>
> static void setup_common() {
> 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);
> setsid();
> 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);
> setup_common();
> sandbox_common();
> drop_caps();
> if (unshare(CLONE_NEWNET)) {
> }
> write_file("/proc/sys/net/ipv4/ping_group_range", "0 65535");
> initialize_tun();
> setup_binderfs();
> 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");
> flush_tun();
> }
>
> static void close_fds() {
> for (int fd = 3; fd < MAX_FDS; fd++)
> close(fd);
> }
>
> 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();
> close_fds();
> exit(0);
> }
> int status = 0;
> uint64_t start = current_time_ms();
> for (;;) {
> if (waitpid(-1, &status, WNOHANG | WAIT_FLAGS) == pid)
> break;
> sleep_ms(1);
> if (current_time_ms() - start < 5000)
> continue;
> kill_and_wait(pid, &status);
> break;
> }
> }
> }
>
> uint64_t r[3] = {0xffffffffffffffff, 0xffffffffffffffff, 0xffffffffffffffff};
>
> void execute_one(void) {
> intptr_t res = 0;
> res = syscall(__NR_socket, /*domain=*/0x10ul, /*type=*/3ul, /*proto=*/0x14);
> if (res != -1)
> r[0] = res;
> *(uint64_t*)0x20000180 = 0;
> *(uint32_t*)0x20000188 = 0;
> *(uint64_t*)0x20000190 = 0x20000140;
> *(uint64_t*)0x20000140 = 0x20000080;
> *(uint32_t*)0x20000080 = 0x38;
> *(uint16_t*)0x20000084 = 0x1403;
> *(uint16_t*)0x20000086 = 1;
> *(uint32_t*)0x20000088 = 0;
> *(uint32_t*)0x2000008c = 0;
> *(uint16_t*)0x20000090 = 9;
> *(uint16_t*)0x20000092 = 2;
> memcpy((void*)0x20000094, "syz1\000", 5);
> *(uint16_t*)0x2000009c = 8;
> *(uint16_t*)0x2000009e = 0x41;
> memcpy((void*)0x200000a0, "rxe\000", 4);
> *(uint16_t*)0x200000a4 = 0x14;
> *(uint16_t*)0x200000a6 = 0x33;
> memcpy((void*)0x200000a8, "syz_tun\000\000\000\000\000\000\000\000\000", 16);
> *(uint64_t*)0x20000148 = 0x38;
> *(uint64_t*)0x20000198 = 1;
> *(uint64_t*)0x200001a0 = 0;
> *(uint64_t*)0x200001a8 = 0;
> *(uint32_t*)0x200001b0 = 0;
> syscall(__NR_sendmsg, /*fd=*/r[0], /*msg=*/0x20000180ul, /*f=*/0ul);
> memcpy((void*)0x20000100, "/dev/infiniband/rdma_cm\000", 24);
> res = syscall(__NR_openat, /*fd=*/0xffffffffffffff9cul, /*file=*/0x20000100ul,
> /*flags=*/2ul, /*mode=*/0ul);
> if (res != -1)
> r[1] = res;
> *(uint32_t*)0x20000080 = 0;
> *(uint16_t*)0x20000084 = 0x18;
> *(uint16_t*)0x20000086 = 0xfa00;
> *(uint64_t*)0x20000088 = 0;
> *(uint64_t*)0x20000090 = 0x200000c0;
> *(uint16_t*)0x20000098 = 0x106;
> *(uint8_t*)0x2000009a = 0;
> memset((void*)0x2000009b, 0, 5);
> res = syscall(__NR_write, /*fd=*/r[1], /*data=*/0x20000080ul, /*len=*/0x20ul);
> if (res != -1)
> r[2] = *(uint32_t*)0x200000c0;
> *(uint32_t*)0x200003c0 = 3;
> *(uint16_t*)0x200003c4 = 0x40;
> *(uint16_t*)0x200003c6 = 0xfa00;
> *(uint16_t*)0x200003c8 = 0xa;
> *(uint16_t*)0x200003ca = htobe16(0x4e24);
> *(uint32_t*)0x200003cc = htobe32(1);
> *(uint8_t*)0x200003d0 = -1;
> *(uint8_t*)0x200003d1 = 2;
> memset((void*)0x200003d2, 0, 13);
> *(uint8_t*)0x200003df = 1;
> *(uint32_t*)0x200003e0 = 9;
> *(uint16_t*)0x200003e4 = 0xa;
> *(uint16_t*)0x200003e6 = htobe16(0);
> *(uint32_t*)0x200003e8 = htobe32(6);
> *(uint8_t*)0x200003ec = 0xfe;
> *(uint8_t*)0x200003ed = 0x80;
> memset((void*)0x200003ee, 0, 13);
> *(uint8_t*)0x200003fb = 0xbb;
> *(uint32_t*)0x200003fc = 0xfffff000;
> *(uint32_t*)0x20000400 = r[2];
> *(uint32_t*)0x20000404 = 2;
> syscall(__NR_write, /*fd=*/r[1], /*data=*/0x200003c0ul, /*len=*/0x48ul);
> *(uint32_t*)0x20000140 = 0x15;
> *(uint16_t*)0x20000144 = 0x110;
> *(uint16_t*)0x20000146 = 0xfa00;
> *(uint32_t*)0x20000148 = r[2];
> *(uint32_t*)0x2000014c = 0;
> *(uint16_t*)0x20000150 = 0;
> *(uint16_t*)0x20000152 = 0x30;
> *(uint32_t*)0x20000154 = 0;
> *(uint16_t*)0x20000158 = 0x1b;
> *(uint16_t*)0x2000015a = htobe16(0);
> *(uint32_t*)0x2000015c = htobe32(0);
> memset((void*)0x20000160, 0, 16);
> *(uint32_t*)0x20000170 = 0;
> *(uint16_t*)0x200001d8 = 0x1b;
> *(uint16_t*)0x200001da = htobe16(0);
> *(uint32_t*)0x200001dc = htobe32(0);
> memset((void*)0x200001e0, 0, 16);
> *(uint64_t*)0x200001f0 = htobe64(0);
> *(uint64_t*)0x200001f8 = htobe64(0);
> *(uint64_t*)0x20000200 = 0;
> syscall(__NR_write, /*fd=*/r[1], /*data=*/0x20000140ul, /*len=*/0x118ul);
> *(uint32_t*)0x20000440 = 4;
> *(uint16_t*)0x20000444 = 8;
> *(uint16_t*)0x20000446 = 0xfa00;
> *(uint32_t*)0x20000448 = r[2];
> *(uint32_t*)0x2000044c = 0xffff741a;
> syscall(__NR_write, /*fd=*/r[1], /*data=*/0x20000440ul, /*len=*/0x10ul);
> }
> int main(void) {
> syscall(__NR_mmap, /*addr=*/0x1ffff000ul, /*len=*/0x1000ul, /*prot=*/0ul,
> /*flags=MAP_FIXED|MAP_ANONYMOUS|MAP_PRIVATE*/ 0x32ul, /*fd=*/-1,
> /*offset=*/0ul);
> syscall(__NR_mmap, /*addr=*/0x20000000ul, /*len=*/0x1000000ul,
> /*prot=PROT_WRITE|PROT_READ|PROT_EXEC*/ 7ul,
> /*flags=MAP_FIXED|MAP_ANONYMOUS|MAP_PRIVATE*/ 0x32ul, /*fd=*/-1,
> /*offset=*/0ul);
> syscall(__NR_mmap, /*addr=*/0x21000000ul, /*len=*/0x1000ul, /*prot=*/0ul,
> /*flags=MAP_FIXED|MAP_ANONYMOUS|MAP_PRIVATE*/ 0x32ul, /*fd=*/-1,
> /*offset=*/0ul);
> do_sandbox_none();
> return 0;
> }
>
> and also https://gist.github.com/xrivendell7/080e44fad03c27df3152ff3bcc8a8385
>
> I hope it helps.
> Best regards.
> xingwei Lee