Commits · cf28f3bbfca097d956f9021cb710dfad56adcc62 · nexedi / linux

17 Aug, 2020 7 commits

bpf: Use get_file_rcu() instead of get_file() for task_file iterator · cf28f3bb

Yonghong Song authored Aug 17, 2020

With latest `bpftool prog` command, we observed the following kernel
panic.
    BUG: kernel NULL pointer dereference, address: 0000000000000000
    #PF: supervisor instruction fetch in kernel mode
    #PF: error_code(0x0010) - not-present page
    PGD dfe894067 P4D dfe894067 PUD deb663067 PMD 0
    Oops: 0010 [#1] SMP
    CPU: 9 PID: 6023 ...
    RIP: 0010:0x0
    Code: Bad RIP value.
    RSP: 0000:ffffc900002b8f18 EFLAGS: 00010286
    RAX: ffff8883a405f400 RBX: ffff888e46a6bf00 RCX: 000000008020000c
    RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8883a405f400
    RBP: ffff888e46a6bf50 R08: 0000000000000000 R09: ffffffff81129600
    R10: ffff8883a405f300 R11: 0000160000000000 R12: 0000000000002710
    R13: 000000e9494b690c R14: 0000000000000202 R15: 0000000000000009
    FS:  00007fd9187fe700(0000) GS:ffff888e46a40000(0000) knlGS:0000000000000000
    CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
    CR2: ffffffffffffffd6 CR3: 0000000de5d33002 CR4: 0000000000360ee0
    DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
    DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
    Call Trace:
     <IRQ>
     rcu_core+0x1a4/0x440
     __do_softirq+0xd3/0x2c8
     irq_exit+0x9d/0xa0
     smp_apic_timer_interrupt+0x68/0x120
     apic_timer_interrupt+0xf/0x20
     </IRQ>
    RIP: 0033:0x47ce80
    Code: Bad RIP value.
    RSP: 002b:00007fd9187fba40 EFLAGS: 00000206 ORIG_RAX: ffffffffffffff13
    RAX: 0000000000000002 RBX: 00007fd931789160 RCX: 000000000000010c
    RDX: 00007fd9308cdfb4 RSI: 00007fd9308cdfb4 RDI: 00007ffedd1ea0a8
    RBP: 00007fd9187fbab0 R08: 000000000000000e R09: 000000000000002a
    R10: 0000000000480210 R11: 00007fd9187fc570 R12: 00007fd9316cc400
    R13: 0000000000000118 R14: 00007fd9308cdfb4 R15: 00007fd9317a9380

After further analysis, the bug is triggered by
Commit eaaacd23 ("bpf: Add task and task/file iterator targets")
which introduced task_file bpf iterator, which traverses all open file
descriptors for all tasks in the current namespace.
The latest `bpftool prog` calls a task_file bpf program to traverse
all files in the system in order to associate processes with progs/maps, etc.
When traversing files for a given task, rcu read_lock is taken to
access all files in a file_struct. But it used get_file() to grab
a file, which is not right. It is possible file->f_count is 0 and
get_file() will unconditionally increase it.
Later put_file() may cause all kind of issues with the above
as one of sympotoms.

The failure can be reproduced with the following steps in a few seconds:
    $ cat t.c
    #include <stdio.h>
    #include <sys/types.h>
    #include <sys/stat.h>
    #include <fcntl.h>
    #include <unistd.h>

    #define N 10000
    int fd[N];
    int main() {
      int i;

      for (i = 0; i < N; i++) {
        fd[i] = open("./note.txt", 'r');
        if (fd[i] < 0) {
           fprintf(stderr, "failed\n");
           return -1;
        }
      }
      for (i = 0; i < N; i++)
        close(fd[i]);

      return 0;
    }
    $ gcc -O2 t.c
    $ cat run.sh
    #/bin/bash
    for i in {1..100}
    do
      while true; do ./a.out; done &
    done
    $ ./run.sh
    $ while true; do bpftool prog >& /dev/null; done

This patch used get_file_rcu() which only grabs a file if the
file->f_count is not zero. This is to ensure the file pointer
is always valid. The above reproducer did not fail for more
than 30 minutes.

Fixes: eaaacd23 ("bpf: Add task and task/file iterator targets")
Suggested-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Link: https://lore.kernel.org/bpf/20200817174214.252601-1-yhs@fb.com

cf28f3bb

Revert "net: xdp: pull ethernet header off packet after computing skb->protocol" · 7f9bf6e8

David S. Miller authored Aug 17, 2020

This reverts commit f8414a8d.

eth_type_trans() does the necessary pull on the skb.
Signed-off-by: David S. Miller <davem@davemloft.net>

7f9bf6e8

phylink: <linux/phylink.h>: fix function prototype kernel-doc warning · 0b76e642

Randy Dunlap authored Aug 16, 2020

Fix a kernel-doc warning for the pcs_config() function prototype:

../include/linux/phylink.h:406: warning: Excess function parameter 'permit_pause_to_mac' description in 'pcs_config'

Fixes: 7137e18f ("net: phylink: add struct phylink_pcs")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>

0b76e642

mptcp: sendmsg: reset iter on error redux · b3b2854d

Florian Westphal authored Aug 16, 2020

This fix wasn't correct: When this function is invoked from the
retransmission worker, the iterator contains garbage and resetting
it causes a crash.

As the work queue should not be performance critical also zero the
msghdr struct.

Fixes: 35759383 "(mptcp: sendmsg: reset iter on error)"
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>

b3b2854d

net: devlink: Remove overzealous WARN_ON with snapshots · bd71ea60

Andrew Lunn authored Aug 16, 2020

It is possible to trigger this WARN_ON from user space by triggering a
devlink snapshot with an ID which already exists. We don't need both
-EEXISTS being reported and spamming the kernel log.
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Tested-by: Chris Healy <cphealy@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

bd71ea60

tipc: not enable tipc when ipv6 works as a module · c5301899

Xin Long authored Aug 16, 2020

When using ipv6_dev_find() in one module, it requires ipv6 not to
work as a module. Otherwise, this error occurs in build:

  undefined reference to `ipv6_dev_find'.

So fix it by adding "depends on IPV6 || IPV6=n" to tipc/Kconfig,
as it does in sctp/Kconfig.

Fixes: 5a6f6f57 ("tipc: set ub->ifindex for local ipv6 address")
Reported-by: kernel test robot <lkp@intel.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

c5301899

tipc: fix uninit skb->data in tipc_nl_compat_dumpit() · 47733f9d

Cong Wang authored Aug 15, 2020

__tipc_nl_compat_dumpit() has two callers, and it expects them to
pass a valid nlmsghdr via arg->data. This header is artificial and
crafted just for __tipc_nl_compat_dumpit().

tipc_nl_compat_publ_dump() does so by putting a genlmsghdr as well
as some nested attribute, TIPC_NLA_SOCK. But the other caller
tipc_nl_compat_dumpit() does not, this leaves arg->data uninitialized
on this call path.

Fix this by just adding a similar nlmsghdr without any payload in
tipc_nl_compat_dumpit().

This bug exists since day 1, but the recent commit 6ea67769
("net: tipc: prepare attrs in __tipc_nl_compat_dumpit()") makes it
easier to appear.

Reported-and-tested-by: syzbot+0e7181deafa7e0b79923@syzkaller.appspotmail.com
Fixes: d0796d1e ("tipc: convert legacy nl bearer dump to nl compat")
Cc: Jon Maloy <jmaloy@redhat.com>
Cc: Ying Xue <ying.xue@windriver.com>
Cc: Richard Alpe <richard.alpe@ericsson.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

47733f9d

16 Aug, 2020 6 commits

Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf · 8c26544f

David S. Miller authored Aug 16, 2020

Pablo Neira Ayuso says:

====================
Netfilter fixes for net

The following patchset contains Netfilter fixes for net:

1) Endianness issue in IPv4 option support in nft_exthdr,
   from Stephen Suryaputra.

2) Removes the waitcount optimization in nft_compat,
   from Florian Westphal.

3) Remove ipv6 -> nf_defrag_ipv6 module dependency, from
   Florian Westphal.

4) Memleak in chain binding support, also from Florian.

5) Simplify nft_flowtable.sh selftest, from Fabian Frederick.

6) Optional MTU arguments for selftest nft_flowtable.sh,
   also from Fabian.

7) Remove noise error report when killing process in
   selftest nft_flowtable.sh, from Fabian Frederick.

8) Reject bogus getsockopt option length in ebtables,
   from Florian Westphal.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

8c26544f

Merge tag 'linux-can-fixes-for-5.9-20200815' of... · 71a50419

David S. Miller authored Aug 16, 2020

Merge tag 'linux-can-fixes-for-5.9-20200815' of git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can

Marc Kleine-Budde says:

====================
pull-request: can 2020-08-15

this is a pull request of 4 patches for net/master.

All patches are by Zhang Changzhong and fix broadcast related problems in the
j1939 CAN networking stack.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

71a50419

net: Fix potential wrong skb->protocol in skb_vlan_untag() · 55eff0eb

Miaohe Lin authored Aug 15, 2020

We may access the two bytes after vlan_hdr in vlan_set_encap_proto(). So
we should pull VLAN_HLEN + sizeof(unsigned short) in skb_vlan_untag() or
we may access the wrong data.

Fixes: 0d5501c1 ("net: Always untag vlan-tagged traffic on input.")
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

55eff0eb

net: xdp: pull ethernet header off packet after computing skb->protocol · f8414a8d

Jason A. Donenfeld authored Aug 15, 2020

When an XDP program changes the ethernet header protocol field,
eth_type_trans is used to recalculate skb->protocol. In order for
eth_type_trans to work correctly, the ethernet header must actually be
part of the skb data segment, so the code first pushes that onto the
head of the skb. However, it subsequently forgets to pull it back off,
making the behavior of the passed-on packet inconsistent between the
protocol modifying case and the static protocol case. This patch fixes
the issue by simply pulling the ethernet header back off of the skb
head.

Fixes: 29724956 ("net: fix generic XDP to handle if eth header was mangled")
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

f8414a8d

ipvlan: fix device features · d0f5c707

Mahesh Bandewar authored Aug 14, 2020

Processing NETDEV_FEAT_CHANGE causes IPvlan links to lose
NETIF_F_LLTX feature because of the incorrect handling of
features in ipvlan_fix_features().

--before--
lpaa10:~# ethtool -k ipvl0 | grep tx-lockless
tx-lockless: on [fixed]
lpaa10:~# ethtool -K ipvl0 tso off
Cannot change tcp-segmentation-offload
Actual changes:
vlan-challenged: off [fixed]
tx-lockless: off [fixed]
lpaa10:~# ethtool -k ipvl0 | grep tx-lockless
tx-lockless: off [fixed]
lpaa10:~#

--after--
lpaa10:~# ethtool -k ipvl0 | grep tx-lockless
tx-lockless: on [fixed]
lpaa10:~# ethtool -K ipvl0 tso off
Cannot change tcp-segmentation-offload
Could not change any device features
lpaa10:~# ethtool -k ipvl0 | grep tx-lockless
tx-lockless: on [fixed]
lpaa10:~#

Fixes: 2ad7bf36 ("ipvlan: Initial check-in of the IPVLAN driver.")
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

d0f5c707

bonding: fix a potential double-unregister · 83270702

Cong Wang authored Aug 14, 2020

When we tear down a network namespace, we unregister all
the netdevices within it. So we may queue a slave device
and a bonding device together in the same unregister queue.

If the only slave device is non-ethernet, it would
automatically unregister the bonding device as well. Thus,
we may end up unregistering the bonding device twice.

Workaround this special case by checking reg_state.

Fixes: 9b5e383c ("net: Introduce unregister_netdevice_many()")
Reported-by: syzbot+af23e7f3e0a7e10c8b67@syzkaller.appspotmail.com
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

83270702

15 Aug, 2020 19 commits

can: j1939: add rxtimer for multipacket broadcast session · 0ae18a82

Zhang Changzhong authored Aug 05, 2020

According to SAE J1939/21 (Chapter 5.12.3 and APPENDIX C), for transmit side
the required time interval between packets of a multipacket broadcast message
is 50 to 200 ms, the responder shall use a timeout of 250ms (provides margin
allowing for the maximumm spacing of 200ms). For receive side a timeout will
occur when a time of greater than 750 ms elapsed between two message packets
when more packets were expected.

So this patch fix and add rxtimer for multipacket broadcast session.

Fixes: 9d71dd0c ("can: add support of SAE J1939 protocol")
Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com>
Link: https://lore.kernel.org/r/1596599425-5534-5-git-send-email-zhangchangzhong@huawei.comAcked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>

0ae18a82

can: j1939: abort multipacket broadcast session when timeout occurs · 2b8b2e31

Zhang Changzhong authored Aug 05, 2020

If timeout occurs, j1939_tp_rxtimer() first calls hrtimer_start() to restart
rxtimer, and then calls __j1939_session_cancel() to set session->state =
J1939_SESSION_WAITING_ABORT. At next timeout expiration, because of the
J1939_SESSION_WAITING_ABORT session state j1939_tp_rxtimer() will call
j1939_session_deactivate_activate_next() to deactivate current session, and
rxtimer won't be set.

But for multipacket broadcast session, __j1939_session_cancel() don't set
session->state = J1939_SESSION_WAITING_ABORT, thus current session won't be
deactivate and hrtimer_start() is called to start new rxtimer again and again.

So fix it by moving session->state = J1939_SESSION_WAITING_ABORT out of if
(!j1939_cb_is_broadcast(&session->skcb)) statement.

Fixes: 9d71dd0c ("can: add support of SAE J1939 protocol")
Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com>
Link: https://lore.kernel.org/r/1596599425-5534-4-git-send-email-zhangchangzhong@huawei.comAcked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>

2b8b2e31

can: j1939: cancel rxtimer on multipacket broadcast session complete · e8b17653

Zhang Changzhong authored Aug 05, 2020

If j1939_xtp_rx_dat_one() receive last frame of multipacket broadcast message,
j1939_session_timers_cancel() should be called to cancel rxtimer.

Fixes: 9d71dd0c ("can: add support of SAE J1939 protocol")
Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com>
Link: https://lore.kernel.org/r/1596599425-5534-3-git-send-email-zhangchangzhong@huawei.comAcked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>

e8b17653

can: j1939: fix support for multipacket broadcast message · f4fd77fd

Zhang Changzhong authored Aug 05, 2020

Currently j1939_tp_im_involved_anydir() in j1939_tp_recv() check the previously
set flags J1939_ECU_LOCAL_DST and J1939_ECU_LOCAL_SRC of incoming skb, thus
multipacket broadcast message was aborted by receive side because it may come
from remote ECUs and have no exact dst address. Similarly, j1939_tp_cmd_recv()
and j1939_xtp_rx_dat() didn't process broadcast message.

So fix it by checking and process broadcast message in j1939_tp_recv(),
j1939_tp_cmd_recv() and j1939_xtp_rx_dat().

Fixes: 9d71dd0c ("can: add support of SAE J1939 protocol")
Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com>
Link: https://lore.kernel.org/r/1596599425-5534-2-git-send-email-zhangchangzhong@huawei.comAcked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>

f4fd77fd