• Lin Zhang's avatar
    net: ieee802154: fix net_device reference release too early · a611c58b
    Lin Zhang authored
    This patch fixes the kernel oops when release net_device reference in
    advance. In function raw_sendmsg(i think the dgram_sendmsg has the same
    problem), there is a race condition between dev_put and dev_queue_xmit
    when the device is gong that maybe lead to dev_queue_ximt to see
    an illegal net_device pointer.
    
    My test kernel is 3.13.0-32 and because i am not have a real 802154
    device, so i change lowpan_newlink function to this:
    
            /* find and hold real wpan device */
            real_dev = dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK]));
            if (!real_dev)
                    return -ENODEV;
    //      if (real_dev->type != ARPHRD_IEEE802154) {
    //              dev_put(real_dev);
    //              return -EINVAL;
    //      }
            lowpan_dev_info(dev)->real_dev = real_dev;
            lowpan_dev_info(dev)->fragment_tag = 0;
            mutex_init(&lowpan_dev_info(dev)->dev_list_mtx);
    
    Also, in order to simulate preempt, i change the raw_sendmsg function
    to this:
    
            skb->dev = dev;
            skb->sk  = sk;
            skb->protocol = htons(ETH_P_IEEE802154);
            dev_put(dev);
            //simulate preempt
            schedule_timeout_uninterruptible(30 * HZ);
            err = dev_queue_xmit(skb);
            if (err > 0)
                    err = net_xmit_errno(err);
    
    and this is my userspace test code named test_send_data:
    
    int main(int argc, char **argv)
    {
            char buf[127];
            int sockfd;
            sockfd = socket(AF_IEEE802154, SOCK_RAW, 0);
            if (sockfd < 0) {
                    printf("create sockfd error: %s\n", strerror(errno));
                    return -1;
            }
            send(sockfd, buf, sizeof(buf), 0);
            return 0;
    }
    
    This is my test case:
    
    root@zhanglin-x-computer:~/develop/802154# uname -a
    Linux zhanglin-x-computer 3.13.0-32-generic #57-Ubuntu SMP Tue Jul 15
    03:51:08 UTC 2014 x86_64 x86_64 x86_64 GNU/Linux
    root@zhanglin-x-computer:~/develop/802154# ip link add link eth0 name
    lowpan0 type lowpan
    root@zhanglin-x-computer:~/develop/802154#
    //keep the lowpan0 device down
    root@zhanglin-x-computer:~/develop/802154# ./test_send_data &
    //wait a while
    root@zhanglin-x-computer:~/develop/802154# ip link del link dev lowpan0
    //the device is gone
    //oops
    [381.303307] general protection fault: 0000 [#1]SMP
    [381.303407] Modules linked in: af_802154 6lowpan bnep rfcomm
    bluetooth nls_iso8859_1 snd_hda_codec_hdmi snd_hda_codec_realtek
    rts5139(C) snd_hda_intel
    snd_had_codec snd_hwdep snd_pcm snd_page_alloc snd_seq_midi
    snd_seq_midi_event snd_rawmidi snd_req intel_rapl snd_seq_device
    coretemp i915 kvm_intel
    kvm snd_timer snd crct10dif_pclmul crc32_pclmul ghash_clmulni_intel
    cypted drm_kms_helper drm i2c_algo_bit soundcore video mac_hid
    parport_pc ppdev ip parport hid_generic
    usbhid hid ahci r8169 mii libahdi
    [381.304286] CPU:1 PID: 2524 Commm: 1 Tainted: G C 0 3.13.0-32-generic
    [381.304409] Hardware name: Haier Haier DT Computer/Haier DT Codputer,
    BIOS FIBT19H02_X64 06/09/2014
    [381.304546] tasks: ffff000096965fc0 ti: ffffB0013779c000 task.ti:
    ffffB8013779c000
    [381.304659] RIP: 0010:[<ffffffff01621fe1>] [<ffffffff81621fe1>]
    __dev_queue_ximt+0x61/0x500
    [381.304798] RSP: 0018:ffffB8013779dca0 EFLAGS: 00010202
    [381.304880] RAX: 272b031d57565351 RBX: 0000000000000000 RCX: ffff8800968f1a00
    [381.304987] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff8800968f1a00
    [381.305095] RBP: ffff8e013773dce0 R08: 0000000000000266 R09: 0000000000000004
    [381.305202] R10: 0000000000000004 R11: 0000000000000005 R12: ffff88013902e000
    [381.305310] R13: 000000000000007f R14: 000000000000007f R15: ffff8800968f1a00
    [381.305418] FS:  00007fc57f50f740(0000) GS: ffff88013fc80000(0000)
    knlGS: 0000000000000000
    [381.305540] CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
    [381.305627] CR2: 00007fad0841c000 CR3: 00000001368dd000 CR4: 00000000001007e0
    [361.905734] Stack:
    [381.305768]  00000000002052d0 000000003facb30a ffff88013779dcc0
    ffff880137764000
    [381.305898]  ffff88013779de70 000000000000007f 000000000000007f
    ffff88013902e000
    [381.306026]  ffff88013779dcf0 ffffffff81622490 ffff88013779dd39
    ffffffffa03af9f1
    [381.306155] Call Trace:
    [381.306202]  [<ffffffff81622490>] dev_queue_xmit+0x10/0x20
    [381.306294]  [<ffffffffa03af9f1>] raw_sendmsg+0x1b1/0x270 [af_802154]
    [381.306396]  [<ffffffffa03af054>] ieee802154_sock_sendmsg+0x14/0x20 [af_802154]
    [381.306512]  [<ffffffff816079eb>] sock_sendmsg+0x8b/0xc0
    [381.306600]  [<ffffffff811d52a5>] ? __d_alloc+0x25/0x180
    [381.306687]  [<ffffffff811a1f56>] ? kmem_cache_alloc_trace+0x1c6/0x1f0
    [381.306791]  [<ffffffff81607b91>] SYSC_sendto+0x121/0x1c0
    [381.306878]  [<ffffffff8109ddf4>] ? vtime_account_user+x54/0x60
    [381.306975]  [<ffffffff81020d45>] ? syscall_trace_enter+0x145/0x250
    [381.307073]  [<ffffffff816086ae>] SyS_sendto+0xe/0x10
    [381.307156]  [<ffffffff8172c87f>] tracesys+0xe1/0xe6
    [381.307233] Code: c6 a1 a4 ff 41 8b 57 78 49 8b 47 20 85 d2 48 8b 80
    78 07 00 00 75 21 49 8b 57 18 48 85 d2 74 18 48 85 c0 74 13 8b 92 ac
    01 00 00 <3b> 50 10 73 08 8b 44 90 14 41 89 47 78 41 f6 84 24 d5 00 00
    00
    [381.307801] RIP [<ffffffff81621fe1>] _dev_queue_xmit+0x61/0x500
    [381.307901]  RSP <ffff88013779dca0>
    [381.347512] Kernel panic - not syncing: Fatal exception in interrupt
    [381.347747] drm_kms_helper: panic occurred, switching back to text console
    
    In my opinion, there is always exist a chance that the device is gong
    before call dev_queue_xmit.
    
    I think the latest kernel is have the same problem and that
    dev_put should be behind of the dev_queue_xmit.
    Signed-off-by: default avatarLin Zhang <xiaolou4617@gmail.com>
    Acked-by: default avatarStefan Schmidt <stefan@osg.samsung.com>
    Signed-off-by: default avatarMarcel Holtmann <marcel@holtmann.org>
    a611c58b
socket.c 23.4 KB