linux-stable.git/net, branch v4.19.166

lwt: Disable BH too in run_lwt_bpf()

2020-12-30T10:26:06+00:00

[ Upstream commit d9054a1ff585ba01029584ab730efc794603d68f ]

The per-cpu bpf_redirect_info is shared among all skb_do_redirect()
and BPF redirect helpers. Callers on RX path are all in BH context,
disabling preemption is not sufficient to prevent BH interruption.

In production, we observed strange packet drops because of the race
condition between LWT xmit and TC ingress, and we verified this issue
is fixed after we disable BH.

Although this bug was technically introduced from the beginning, that
is commit 3a0af8fd61f9 ("bpf: BPF for lightweight tunnel infrastructure"),
at that time call_rcu() had to be call_rcu_bh() to match the RCU context.
So this patch may not work well before RCU flavor consolidation has been
completed around v5.0.

Update the comments above the code too, as call_rcu() is now BH friendly.

Signed-off-by: Dongdong Wang 
Signed-off-by: Alexei Starovoitov 
Reviewed-by: Cong Wang 
Link: https://lore.kernel.org/bpf/20201205075946.497763-1-xiyou.wangcong@gmail.com
Signed-off-by: Sasha Levin

cfg80211: initialize rekey_data

2020-12-30T10:26:06+00:00

[ Upstream commit f495acd8851d7b345e5f0e521b2645b1e1f928a0 ]

In case we have old supplicant, the akm field is uninitialized.

Signed-off-by: Sara Sharon 
Signed-off-by: Luca Coelho 
Link: https://lore.kernel.org/r/iwlwifi.20201129172929.930f0ab7ebee.Ic546e384efab3f4a89f318eafddc3eb7d556aecb@changeid
Signed-off-by: Johannes Berg 
Signed-off-by: Sasha Levin

mac80211: don't set set TDLS STA bandwidth wider than possible

2020-12-30T10:26:03+00:00

[ Upstream commit f65607cdbc6b0da356ef5a22552ddd9313cf87a0 ]

When we set up a TDLS station, we set sta->sta.bandwidth solely based
on the capabilities, because the "what's the current bandwidth" check
is bypassed and only applied for other types of stations.

This leads to the unfortunate scenario that the sta->sta.bandwidth is
160 MHz if both stations support it, but we never actually configure
this bandwidth unless the AP is already using 160 MHz; even for wider
bandwidth support we only go up to 80 MHz (at least right now.)

For iwlwifi, this can also lead to firmware asserts, telling us that
we've configured the TX rates for a higher bandwidth than is actually
available due to the PHY configuration.

For non-TDLS, we check against the interface's requested bandwidth,
but we explicitly skip this check for TDLS to cope with the wider BW
case. Change this to
 (a) still limit to the TDLS peer's own chandef, which gets factored
     into the overall PHY configuration we request from the driver,
     and
 (b) limit it to when the TDLS peer is authorized, because it's only
     factored into the channel context in this case.

Fixes: 504871e602d9 ("mac80211: fix bandwidth computation for TDLS peers")
Signed-off-by: Johannes Berg 
Signed-off-by: Luca Coelho 
Link: https://lore.kernel.org/r/iwlwifi.20201206145305.fcc7d29c4590.I11f77e9e25ddf871a3c8d5604650c763e2c5887a@changeid
Signed-off-by: Johannes Berg 
Signed-off-by: Sasha Levin

SUNRPC: xprt_load_transport() needs to support the netid "rdma6"

2020-12-30T10:25:59+00:00

[ Upstream commit d5aa6b22e2258f05317313ecc02efbb988ed6d38 ]

According to RFC5666, the correct netid for an IPv6 addressed RDMA
transport is "rdma6", which we've supported as a mount option since
Linux-4.7. The problem is when we try to load the module "xprtrdma6",
that will fail, since there is no modulealias of that name.

Fixes: 181342c5ebe8 ("xprtrdma: Add rdma6 option to support NFS/RDMA IPv6")
Signed-off-by: Trond Myklebust 
Signed-off-by: Sasha Levin

Bluetooth: Fix null pointer dereference in hci_event_packet()

2020-12-30T10:25:52+00:00

[ Upstream commit 6dfccd13db2ff2b709ef60a50163925d477549aa ]

AMP_MGR is getting derefernced in hci_phy_link_complete_evt(), when called
from hci_event_packet() and there is a possibility, that hcon->amp_mgr may
not be found when accessing after initialization of hcon.

- net/bluetooth/hci_event.c:4945
The bug seems to get triggered in this line:

bredr_hcon = hcon->amp_mgr->l2cap_conn->hcon;

Fix it by adding a NULL check for the hcon->amp_mgr before checking the ev-status.

Fixes: d5e911928bd8 ("Bluetooth: AMP: Process Physical Link Complete evt")
Reported-and-tested-by: syzbot+0bef568258653cff272f@syzkaller.appspotmail.com
Link: https://syzkaller.appspot.com/bug?extid=0bef568258653cff272f
Signed-off-by: Anmol Karn 
Signed-off-by: Marcel Holtmann 
Signed-off-by: Sasha Levin

Bluetooth: Fix slab-out-of-bounds read in hci_le_direct_adv_report_evt()

2020-12-30T10:25:48+00:00

commit f7e0e8b2f1b0a09b527885babda3e912ba820798 upstream.

`num_reports` is not being properly checked. A malformed event packet with
a large `num_reports` number makes hci_le_direct_adv_report_evt() read out
of bounds. Fix it.

Cc: stable@vger.kernel.org
Fixes: 2f010b55884e ("Bluetooth: Add support for handling LE Direct Advertising Report events")
Reported-and-tested-by: syzbot+24ebd650e20bd263ca01@syzkaller.appspotmail.com
Link: https://syzkaller.appspot.com/bug?extid=24ebd650e20bd263ca01
Signed-off-by: Peilin Ye 
Signed-off-by: Marcel Holtmann 
Signed-off-by: Greg Kroah-Hartman

netfilter: x_tables: Switch synchronization to RCU

2020-12-30T10:25:45+00:00

[ Upstream commit cc00bcaa589914096edef7fb87ca5cee4a166b5c ]

When running concurrent iptables rules replacement with data, the per CPU
sequence count is checked after the assignment of the new information.
The sequence count is used to synchronize with the packet path without the
use of any explicit locking. If there are any packets in the packet path using
the table information, the sequence count is incremented to an odd value and
is incremented to an even after the packet process completion.

The new table value assignment is followed by a write memory barrier so every
CPU should see the latest value. If the packet path has started with the old
table information, the sequence counter will be odd and the iptables
replacement will wait till the sequence count is even prior to freeing the
old table info.

However, this assumes that the new table information assignment and the memory
barrier is actually executed prior to the counter check in the replacement
thread. If CPU decides to execute the assignment later as there is no user of
the table information prior to the sequence check, the packet path in another
CPU may use the old table information. The replacement thread would then free
the table information under it leading to a use after free in the packet
processing context-

Unable to handle kernel NULL pointer dereference at virtual
address 000000000000008e
pc : ip6t_do_table+0x5d0/0x89c
lr : ip6t_do_table+0x5b8/0x89c
ip6t_do_table+0x5d0/0x89c
ip6table_filter_hook+0x24/0x30
nf_hook_slow+0x84/0x120
ip6_input+0x74/0xe0
ip6_rcv_finish+0x7c/0x128
ipv6_rcv+0xac/0xe4
__netif_receive_skb+0x84/0x17c
process_backlog+0x15c/0x1b8
napi_poll+0x88/0x284
net_rx_action+0xbc/0x23c
__do_softirq+0x20c/0x48c

This could be fixed by forcing instruction order after the new table
information assignment or by switching to RCU for the synchronization.

Fixes: 80055dab5de0 ("netfilter: x_tables: make xt_replace_table wait until old rules are not used anymore")
Reported-by: Sean Tranchetti 
Reported-by: kernel test robot 
Suggested-by: Florian Westphal 
Signed-off-by: Subash Abhinov Kasiviswanathan 
Signed-off-by: Pablo Neira Ayuso 
Signed-off-by: Sasha Levin

xsk: Fix xsk_poll()'s return type

2020-12-30T10:25:44+00:00

[ Upstream commit 5d946c5abbaf68083fa6a41824dd79e1f06286d8 ]

xsk_poll() is defined as returning 'unsigned int' but the
.poll method is declared as returning '__poll_t', a bitwise type.

Fix this by using the proper return type and using the EPOLL
constants instead of the POLL ones, as required for __poll_t.

Signed-off-by: Luc Van Oostenryck 
Signed-off-by: Daniel Borkmann 
Acked-by: Björn Töpel 
Link: https://lore.kernel.org/bpf/20191120001042.30830-1-luc.vanoostenryck@gmail.com
Signed-off-by: Sasha Levin

net: bridge: vlan: fix error return code in __vlan_add()

2020-12-30T10:25:41+00:00

[ Upstream commit ee4f52a8de2c6f78b01f10b4c330867d88c1653a ]

Fix to return a negative error code from the error handling
case instead of 0, as done elsewhere in this function.

Fixes: f8ed289fab84 ("bridge: vlan: use br_vlan_(get|put)_master to deal with refcounts")
Reported-by: Hulk Robot 
Signed-off-by: Zhang Changzhong 
Acked-by: Nikolay Aleksandrov 
Link: https://lore.kernel.org/r/1607071737-33875-1-git-send-email-zhangchangzhong@huawei.com
Signed-off-by: Jakub Kicinski 
Signed-off-by: Greg Kroah-Hartman

tcp: fix cwnd-limited bug for TSO deferral where we send nothing

2020-12-30T10:25:41+00:00

[ Upstream commit 299bcb55ecd1412f6df606e9dc0912d55610029e ]

When cwnd is not a multiple of the TSO skb size of N*MSS, we can get
into persistent scenarios where we have the following sequence:

(1) ACK for full-sized skb of N*MSS arrives
  -> tcp_write_xmit() transmit full-sized skb with N*MSS
  -> move pacing release time forward
  -> exit tcp_write_xmit() because pacing time is in the future

(2) TSQ callback or TCP internal pacing timer fires
  -> try to transmit next skb, but TSO deferral finds remainder of
     available cwnd is not big enough to trigger an immediate send
     now, so we defer sending until the next ACK.

(3) repeat...

So we can get into a case where we never mark ourselves as
cwnd-limited for many seconds at a time, even with
bulk/infinite-backlog senders, because:

o In case (1) above, every time in tcp_write_xmit() we have enough
cwnd to send a full-sized skb, we are not fully using the cwnd
(because cwnd is not a multiple of the TSO skb size). So every time we
send data, we are not cwnd limited, and so in the cwnd-limited
tracking code in tcp_cwnd_validate() we mark ourselves as not
cwnd-limited.

o In case (2) above, every time in tcp_write_xmit() that we try to
transmit the "remainder" of the cwnd but defer, we set the local
variable is_cwnd_limited to true, but we do not send any packets, so
sent_pkts is zero, so we don't call the cwnd-limited logic to update
tp->is_cwnd_limited.

Fixes: ca8a22634381 ("tcp: make cwnd-limited checks measurement-based, and gentler")
Reported-by: Ingemar Johansson 
Signed-off-by: Neal Cardwell 
Signed-off-by: Yuchung Cheng 
Acked-by: Soheil Hassas Yeganeh 
Signed-off-by: Eric Dumazet 
Link: https://lore.kernel.org/r/20201209035759.1225145-1-ncardwell.kernel@gmail.com
Signed-off-by: Jakub Kicinski 
Signed-off-by: Greg Kroah-Hartman