Bjørn Mork [Fri, 22 May 2015 11:15:22 +0000 (13:15 +0200)]
cdc_ncm: Fix tx_bytes statistics
The tx_curr_frame_payload field is u32. When we try to calculate a
small negative delta based on it, we end up with a positive integer
close to 2^32 instead. So the tx_bytes pointer increases by about
2^32 for every transmitted frame.
Fix by calculating the delta as a signed long.
Cc: Ben Hutchings <ben.hutchings@codethink.co.uk> Reported-by: Florian Bruhin <me@the-compiler.org> Fixes: 7a1e890e2168 ("usbnet: Fix tx_bytes statistic running backward in cdc_ncm") Signed-off-by: Bjørn Mork <bjorn@mork.no> Signed-off-by: David S. Miller <davem@davemloft.net>
The following patchset contain Netfilter fixes for your net tree, they are:
1) Fix a race in nfnetlink_log and nfnetlink_queue that can lead to a crash.
This problem is due to wrong order in the per-net registration and netlink
socket events. Patch from Francesco Ruggeri.
2) Make sure that counters that userspace pass us are higher than 0 in all the
x_tables frontends. Discovered via Trinity, patch from Dave Jones.
3) Revert a patch for br_netfilter to rely on the conntrack status bits. This
breaks stateless IPv6 NAT transformations. Patch from Florian Westphal.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
ip_error does not check if in_dev is NULL before dereferencing it.
IThe following sequence of calls is possible:
CPU A CPU B
ip_rcv_finish
ip_route_input_noref()
ip_route_input_slow()
inetdev_destroy()
dst_input()
With the result that a network device can be destroyed while processing
an input packet.
A crash was triggered with only unicast packets in flight, and
forwarding enabled on the only network device. The error condition
was created by the removal of the network device.
As such it is likely the that error code was -EHOSTUNREACH, and the
action taken by ip_error (if in_dev had been accessible) would have
been to not increment any counters and to have tried and likely failed
to send an icmp error as the network device is going away.
Therefore handle this weird case by just dropping the packet if
!in_dev. It will result in dropping the packet sooner, and will not
result in an actual change of behavior.
Fixes: 251da4130115b ("ipv4: Cache ip_error() routes even when not forwarding.") Reported-by: Vittorio Gambaletta <linuxbugs@vittgam.net> Tested-by: Vittorio Gambaletta <linuxbugs@vittgam.net> Signed-off-by: Vittorio Gambaletta <linuxbugs@vittgam.net> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Fri, 22 May 2015 04:51:19 +0000 (21:51 -0700)]
tcp: fix a potential deadlock in tcp_get_info()
Taking socket spinlock in tcp_get_info() can deadlock, as
inet_diag_dump_icsk() holds the &hashinfo->ehash_locks[i],
while packet processing can use the reverse locking order.
We could avoid this locking for TCP_LISTEN states, but lockdep would
certainly get confused as all TCP sockets share same lockdep classes.
[ 523.722504] ======================================================
[ 523.728706] [ INFO: possible circular locking dependency detected ]
[ 523.734990] 4.1.0-dbg-DEV #1676 Not tainted
[ 523.739202] -------------------------------------------------------
[ 523.745474] ss/18032 is trying to acquire lock:
[ 523.750002] (slock-AF_INET){+.-...}, at: [<ffffffff81669d44>] tcp_get_info+0x2c4/0x360
[ 523.758129]
[ 523.758129] but task is already holding lock:
[ 523.763968] (&(&hashinfo->ehash_locks[i])->rlock){+.-...}, at: [<ffffffff816bcb75>] inet_diag_dump_icsk+0x1d5/0x6c0
[ 523.774661]
[ 523.774661] which lock already depends on the new lock.
[ 523.774661]
[ 523.782850]
[ 523.782850] the existing dependency chain (in reverse order) is:
[ 523.790326]
-> #1 (&(&hashinfo->ehash_locks[i])->rlock){+.-...}:
[ 523.796599] [<ffffffff811126bb>] lock_acquire+0xbb/0x270
[ 523.802565] [<ffffffff816f5868>] _raw_spin_lock+0x38/0x50
[ 523.808628] [<ffffffff81665af8>] __inet_hash_nolisten+0x78/0x110
[ 523.815273] [<ffffffff816819db>] tcp_v4_syn_recv_sock+0x24b/0x350
[ 523.822067] [<ffffffff81684d41>] tcp_check_req+0x3c1/0x500
[ 523.828199] [<ffffffff81682d09>] tcp_v4_do_rcv+0x239/0x3d0
[ 523.834331] [<ffffffff816842fe>] tcp_v4_rcv+0xa8e/0xc10
[ 523.840202] [<ffffffff81658fa3>] ip_local_deliver_finish+0x133/0x3e0
[ 523.847214] [<ffffffff81659a9a>] ip_local_deliver+0xaa/0xc0
[ 523.853440] [<ffffffff816593b8>] ip_rcv_finish+0x168/0x5c0
[ 523.859624] [<ffffffff81659db7>] ip_rcv+0x307/0x420
Lets use u64_sync infrastructure instead. As a bonus, 64bit
arches get optimized, as these are nop for them.
Fixes: 0df48c26d841 ("tcp: add tcpi_bytes_acked to tcp_info") Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Daniel Borkmann [Wed, 20 May 2015 15:13:33 +0000 (17:13 +0200)]
net: sched: fix call_rcu() race on classifier module unloads
Vijay reported that a loop as simple as ...
while true; do
tc qdisc add dev foo root handle 1: prio
tc filter add dev foo parent 1: u32 match u32 0 0 flowid 1
tc qdisc del dev foo root
rmmod cls_u32
done
... will panic the kernel. Moreover, he bisected the change
apparently introducing it to 78fd1d0ab072 ("netlink: Re-add
locking to netlink_lookup() and seq walker").
The removal of synchronize_net() from the netlink socket
triggering the qdisc to be removed, seems to have uncovered
an RCU resp. module reference count race from the tc API.
Given that RCU conversion was done after e341694e3eb5 ("netlink:
Convert netlink_lookup() to use RCU protected hash table")
which added the synchronize_net() originally, occasion of
hitting the bug was less likely (not impossible though):
When qdiscs that i) support attaching classifiers and,
ii) have at least one of them attached, get deleted, they
invoke tcf_destroy_chain(), and thus call into ->destroy()
handler from a classifier module.
After RCU conversion, all classifier that have an internal
prio list, unlink them and initiate freeing via call_rcu()
deferral.
Meanhile, tcf_destroy() releases already reference to the
tp->ops->owner module before the queued RCU callback handler
has been invoked.
Subsequent rmmod on the classifier module is then not prevented
since all module references are already dropped.
By the time, the kernel invokes the RCU callback handler from
the module, that function address is then invalid.
One way to fix it would be to add an rcu_barrier() to
unregister_tcf_proto_ops() to wait for all pending call_rcu()s
to complete.
synchronize_rcu() is not appropriate as under heavy RCU
callback load, registered call_rcu()s could be deferred
longer than a grace period. In case we don't have any pending
call_rcu()s, the barrier is allowed to return immediately.
Since we came here via unregister_tcf_proto_ops(), there
are no users of a given classifier anymore. Further nested
call_rcu()s pointing into the module space are not being
done anywhere.
Only cls_bpf_delete_prog() may schedule a work item, to
unlock pages eventually, but that is not in the range/context
of cls_bpf anymore.
Fixes: 25d8c0d55f24 ("net: rcu-ify tcf_proto") Fixes: 9888faefe132 ("net: sched: cls_basic use RCU") Reported-by: Vijay Subramanian <subramanian.vijay@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Cc: John Fastabend <john.r.fastabend@intel.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Thomas Graf <tgraf@suug.ch> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Alexei Starovoitov <ast@plumgrid.com> Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com> Acked-by: Alexei Starovoitov <ast@plumgrid.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Tim Beale [Mon, 18 May 2015 03:38:38 +0000 (15:38 +1200)]
net: phy: Make sure phy_start() always re-enables the phy interrupts
This is an alternative way of fixing:
commit db9683fb412d ("net: phy: Make sure PHY_RESUMING state change
is always processed")
When the PHY state transitions from PHY_HALTED to PHY_RESUMING, there are
two things we need to do:
1). Re-enable interrupts (and power up the physical link, if powered down)
2). Update the PHY state and net-device based on the link status.
There's no strict reason why #1 has to be done from within the main
phy_state_machine() function. There is a risk that other changes to the
PHY (e.g. setting speed/duplex, which calls phy_start_aneg()) could cause
a subsequent state transition before phy_state_machine() has processed
the PHY_RESUMING state change. This would leave the PHY with interrupts
disabled and/or still in the BMCR_PDOWN/low-power mode.
Moving enabling the interrupts and phy_resume() into phy_start() will
guarantee this work always gets done. As the PHY is already in the HALTED
state and interrupts are disabled, it shouldn't conflict with any work
being done in phy_state_machine(). The downside of this change is that if
the PHY_RESUMING state is ever entered from anywhere else, it'll also have
to repeat this work.
Signed-off-by: Tim Beale <tim.beale@alliedtelesis.co.nz> Signed-off-by: David S. Miller <davem@davemloft.net>
(1) When adding a nexthop of a multipath route fails (e.g. because of a
conflict with an existing route), we are supposed to delete nexthops
already added. However, currently we try to also delete all nexthops we
haven't even tried to add yet so that a "ip route add" command can
actually remove pre-existing routes if it fails.
(2) Attempt to replace a multipath route results in a broken siblings
linked list. Following commands (like "ip route del") can then either
follow a link into freed memory or end in an infinite loop (if the slab
object has been reused).
v2: fix an omission in first patch
v3: change the semantics of replace operation to better match IPv4
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Michal Kubeček [Mon, 18 May 2015 18:54:00 +0000 (20:54 +0200)]
ipv6: fix ECMP route replacement
When replacing an IPv6 multipath route with "ip route replace", i.e.
NLM_F_CREATE | NLM_F_REPLACE, fib6_add_rt2node() replaces only first
matching route without fixing its siblings, resulting in corrupted
siblings linked list; removing one of the siblings can then end in an
infinite loop.
IPv6 ECMP implementation is a bit different from IPv4 so that route
replacement cannot work in exactly the same way. This should be a
reasonable approximation:
1. If the new route is ECMP-able and there is a matching ECMP-able one
already, replace it and all its siblings (if any).
2. If the new route is ECMP-able and no matching ECMP-able route exists,
replace first matching non-ECMP-able (if any) or just add the new one.
3. If the new route is not ECMP-able, replace first matching
non-ECMP-able route (if any) or add the new route.
We also need to remove the NLM_F_REPLACE flag after replacing old
route(s) by first nexthop of an ECMP route so that each subsequent
nexthop does not replace previous one.
Fixes: 51ebd3181572 ("ipv6: add support of equal cost multipath (ECMP)") Signed-off-by: Michal Kubecek <mkubecek@suse.cz> Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Michal Kubeček [Mon, 18 May 2015 18:53:55 +0000 (20:53 +0200)]
ipv6: do not delete previously existing ECMP routes if add fails
If adding a nexthop of an IPv6 multipath route fails, comment in
ip6_route_multipath() says we are going to delete all nexthops already
added. However, current implementation deletes even the routes it
hasn't even tried to add yet. For example, running
ip route add 1234:5678::/64 \
nexthop via fe80::aa dev dummy1 \
nexthop via fe80::bb dev dummy1 \
nexthop via fe80::cc dev dummy1
twice results in removing all routes first command added.
Limit the second (delete) run to nexthops that succeeded in the first
(add) run.
Fixes: 51ebd3181572 ("ipv6: add support of equal cost multipath (ECMP)") Signed-off-by: Michal Kubecek <mkubecek@suse.cz> Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com> Signed-off-by: David S. Miller <davem@davemloft.net>
netfilter: nfnetlink_{log,queue}: Register pernet in first place
nfnetlink_{log,queue}_init() register the netlink callback nf*_rcv_nl_event
before registering the pernet_subsys, but the callback relies on data
structures allocated by pernet init functions.
When nfnetlink_{log,queue} is loaded, if a netlink message is received after
the netlink callback is registered but before the pernet_subsys is registered,
the kernel will panic in the sequence
nfulnl_rcv_nl_event
nfnl_log_pernet
net_generic
BUG_ON(id == 0) where id is nfnl_log_net_id.
The panic can be easily reproduced in 4.0.3 by:
while true ;do modprobe nfnetlink_log ; rmmod nfnetlink_log ; done &
while true ;do ip netns add dummy ; ip netns del dummy ; done &
This patch moves register_pernet_subsys to earlier in nfnetlink_log_init.
Notice that the BUG_ON hit in 4.0.3 was recently removed in 2591ffd308
["netns: remove BUG_ONs from net_generic()"].
Signed-off-by: Francesco Ruggeri <fruggeri@arista.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Yuchung Cheng [Mon, 18 May 2015 19:31:45 +0000 (12:31 -0700)]
tcp: don't over-send F-RTO probes
After sending the new data packets to probe (step 2), F-RTO may
incorrectly send more probes if the next ACK advances SND_UNA and
does not sack new packet. However F-RTO RFC 5682 probes at most
once. This bug may cause sender to always send new data instead of
repairing holes, inducing longer HoL blocking on the receiver for
the application.
Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Yuchung Cheng [Mon, 18 May 2015 19:31:44 +0000 (12:31 -0700)]
tcp: only undo on partial ACKs in CA_Loss
Undo based on TCP timestamps should only happen on ACKs that advance
SND_UNA, according to the Eifel algorithm in RFC 3522:
Section 3.2:
(4) If the value of the Timestamp Echo Reply field of the
acceptable ACK's Timestamps option is smaller than the
value of RetransmitTS, then proceed to step (5),
Section Terminology:
We use the term 'acceptable ACK' as defined in [RFC793]. That is an
ACK that acknowledges previously unacknowledged data.
This is because upon receiving an out-of-order packet, the receiver
returns the last timestamp that advances RCV_NXT, not the current
timestamp of the packet in the DUPACK. Without checking the flag,
the DUPACK will cause tcp_packet_delayed() to return true and
tcp_try_undo_loss() will revert cwnd reduction.
Note that we check the condition in CA_Recovery already by only
calling tcp_try_undo_partial() if FLAG_SND_UNA_ADVANCED is set or
tcp_try_undo_recovery() if snd_una crosses high_seq.
Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Commit <5cf3d46192fc> ("udp: Simplify__udp*_lib_mcast_deliver")
simplified the filter for incoming IPv6 multicast but removed
the check of the local socket address and the UDP destination
address.
This patch restores the filter to prevent sockets bound to a IPv6
multicast IP to receive other UDP traffic link unicast.
Signed-off-by: Henning Rogge <hrogge@gmail.com> Fixes: 5cf3d46192fc ("udp: Simplify__udp*_lib_mcast_deliver") Cc: "David S. Miller" <davem@davemloft.net> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Tue, 19 May 2015 00:06:14 +0000 (17:06 -0700)]
inet: properly align icsk_ca_priv
tcp_illinois and upcoming tcp_cdg require 64bit alignment of
icsk_ca_priv
x86 does not care, but other architectures might.
Fixes: 05cbc0db03e82 ("ipv4: Create probe timer for tcp PMTU as per RFC4821") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Fan Du <fan.du@intel.com> Acked-by: Fan Du <fan.du@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
John W. Linville [Mon, 18 May 2015 17:51:24 +0000 (13:51 -0400)]
vxlan: correct typo in call to unregister_netdevice_queue
By inspection, this appears to be a typo. The gating comparison
involves vxlan->dev rather than dev. In fact, dev is the iterator in
the preceding loop above but it is actually constant in the 2nd loop.
Use of dev seems to be a bad cut-n-paste from the prior call to
unregister_netdevice_queue. Change dev to vxlan->dev, since that is
what is actually being checked.
Signed-off-by: John W. Linville <linville@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Florent Fourcot [Fri, 15 May 2015 22:24:59 +0000 (00:24 +0200)]
tcp/ipv6: fix flow label setting in TIME_WAIT state
commit 1d13a96c74fc ("ipv6: tcp: fix flowlabel value in ACK messages
send from TIME_WAIT") added the flow label in the last TCP packets.
Unfortunately, it was not casted properly.
This patch replace the buggy shift with be32_to_cpu/cpu_to_be32.
Fixes: 1d13a96c74fc ("ipv6: tcp: fix flowlabel value in ACK messages") Reported-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Florent Fourcot <florent.fourcot@enst-bretagne.fr> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Nicolas Dichtel [Wed, 13 May 2015 12:19:42 +0000 (14:19 +0200)]
rtnl/bond: don't send rtnl msg for unregistered iface
Before the patch, the command 'ip link add bond2 type bond mode 802.3ad'
causes the kernel to send a rtnl message for the bond2 interface, with an
ifindex 0.
'ip monitor' shows:
0: bond2: <BROADCAST,MULTICAST,MASTER> mtu 1500 state DOWN group default
link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff
9: bond2@NONE: <BROADCAST,MULTICAST,MASTER> mtu 1500 qdisc noop state DOWN group default
link/ether ea:3e:1f:53:92:7b brd ff:ff:ff:ff:ff:ff
[snip]
The patch fixes the spotted bug by checking in bond driver if the interface
is registered before calling the notifier chain.
It also adds a check in rtmsg_ifinfo() to prevent this kind of bug in the
future.
Fixes: d4261e565000 ("bonding: create netlink event when bonding option is changed") CC: Jiri Pirko <jiri@resnulli.us> Reported-by: Julien Meunier <julien.meunier@6wind.com> Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Herbert Xu [Fri, 15 May 2015 03:30:47 +0000 (11:30 +0800)]
rhashtable: Add cap on number of elements in hash table
We currently have no limit on the number of elements in a hash table.
This is a problem because some users (tipc) set a ceiling on the
maximum table size and when that is reached the hash table may
degenerate. Others may encounter OOM when growing and if we allow
insertions when that happens the hash table perofrmance may also
suffer.
This patch adds a new paramater insecure_max_entries which becomes
the cap on the table. If unset it defaults to max_size * 2. If
it is also zero it means that there is no cap on the number of
elements in the table. However, the table will grow whenever the
utilisation hits 100% and if that growth fails, you will get ENOMEM
on insertion.
As allowing oversubscription is potentially dangerous, the name
contains the word insecure.
Note that the cap is not a hard limit. This is done for performance
reasons as enforcing a hard limit will result in use of atomic ops
that are heavier than the ones we currently use.
The reasoning is that we're only guarding against a gross over-
subscription of the table, rather than a small breach of the limit.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
Tim Beale [Wed, 13 May 2015 01:55:04 +0000 (13:55 +1200)]
net: phy: Make sure PHY_RESUMING state change is always processed
If phy_start_aneg() was called while the phydev is in the PHY_RESUMING
state, then its state would immediately transition to PHY_AN (or
PHY_FORCING). This meant the phy_state_machine() never processed the
PHY_RESUMING state change, which meant interrupts weren't enabled for the
PHY. If the PHY used low-power mode (i.e. using BMCR_PDOWN), then the
physical link wouldn't get powered up again.
There seems no point for phy_start_aneg() to make the PHY_RESUMING -->
PHY_AN transition, as the state machine will do this anyway. I'm not sure
about the case where autoneg is disabled, as my patch will change
behaviour so that the PHY goes to PHY_NOLINK instead of PHY_FORCING. An
alternative solution would be to move the phy_config_interrupt() and
phy_resume() work out of the state machine and into phy_start().
The background behind this: we're running linux v3.16.7 and from user-space
we want to enable the eth port (i.e. do a SIOCSIFFLAGS ioctl with the
IFF_UP flag) and immediately afterward set the interface's speed/duplex.
Enabling the interface calls .ndo_open() then phy_start() and the PHY
transitions PHY_HALTED --> PHY_RESUMING. Setting the speed/duplex ends up
calling phy_ethtool_sset(), which calls phy_start_aneg() (meanwhile the
phy_state_machine() hasn't processed the PHY_RESUMING state change yet).
Signed-off-by: Tim Beale <tim.beale@alliedtelesis.co.nz> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Herbert Xu [Sat, 16 May 2015 13:50:28 +0000 (21:50 +0800)]
netlink: Reset portid after netlink_insert failure
The commit c5adde9468b0714a051eac7f9666f23eb10b61f7 ("netlink:
eliminate nl_sk_hash_lock") breaks the autobind retry mechanism
because it doesn't reset portid after a failed netlink_insert.
This means that should autobind fail the first time around, then
the socket will be stuck in limbo as it can never be bound again
since it already has a non-zero portid.
Fixes: c5adde9468b0 ("netlink: eliminate nl_sk_hash_lock") Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
Florian Fainelli [Fri, 15 May 2015 23:30:41 +0000 (16:30 -0700)]
net: phy: Allow EEE for all RGMII variants
RGMII interfaces come in multiple flavors: RGMII with transmit or
receive internal delay, no delays at all, or delays in both direction.
This change extends the initial check for PHY_INTERFACE_MODE_RGMII to
cover all of these variants since EEE should be allowed for any of these
modes, since it is a property of the RGMII, hence Gigabit PHY capability
more than the RGMII electrical interface and its delays.
Fixes: a59a4d192166 ("phy: add the EEE support and the way to access to the MMD registers") Signed-off-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Ying Xue [Fri, 15 May 2015 04:53:21 +0000 (12:53 +0800)]
rocker: fix a neigh entry leak issue
Once we get a neighbour through looking up arp cache or creating a
new one in rocker_port_ipv4_resolve(), the neighbour's refcount is
already taken. But as we don't put the refcount again after it's
used, this makes the neighbour entry leaked.
Suggested-by: Eric Dumazet <edumazet@google.com> Acked-by: Jiri Pirko <jiri@resnulli.us> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Ying Xue <ying.xue@windriver.com> Acked-by: Jiri Pirko <jiri@resnulli.us> Signed-off-by: David S. Miller <davem@davemloft.net>
In compliance with RFC5961, the network stack send challenge ACK in
response to spurious SYN packets, since commit 0c228e833c88 ("tcp:
Restore RFC5961-compliant behavior for SYN packets").
This pose a problem for netfilter conntrack in state LAST_ACK, because
this challenge ACK is (falsely) seen as ACKing last FIN, causing a
false state transition (into TIME_WAIT).
The challenge ACK is hard to distinguish from real last ACK. Thus,
solution introduce a flag that tracks the potential for seeing a
challenge ACK, in case a SYN packet is let through and current state
is LAST_ACK.
When conntrack transition LAST_ACK to TIME_WAIT happens, this flag is
used for determining if we are expecting a challenge ACK.
Scapy based reproducer script avail here:
https://github.com/netoptimizer/network-testing/blob/master/scapy/tcp_hacks_3WHS_LAST_ACK.py
Fixes: 0c228e833c88 ("tcp: Restore RFC5961-compliant behavior for SYN packets") Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Acked-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Nathan Sullivan [Wed, 13 May 2015 22:01:36 +0000 (17:01 -0500)]
net: macb: Add better comment for RXUBR handling
Describe the handler for RXUBR better with a new comment.
Signed-off-by: Nathan Sullivan <nathan.sullivan@ni.com> Reviewied-by: Josh Cartwright <joshc@ni.com> Reviewied-by: Ben Shelton <ben.shelton@ni.com> Acked-by: Nicolas Ferre <nicolas.ferre@atmel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Bjorn Helgaas [Thu, 14 May 2015 23:17:08 +0000 (18:17 -0500)]
net/mlx4: Avoid 'may be used uninitialized' warnings
With a cross-compiler based on gcc-4.9, I see warnings like the following:
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c: In function 'mlx4_SW2HW_CQ_wrapper':
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c:3048:10: error: 'cq' may be used uninitialized in this function [-Werror=maybe-uninitialized]
cq->mtt = mtt;
I think the warning is spurious because we only use cq when
cq_res_start_move_to() returns zero, and it always initializes *cq in that
case. The srq case is similar. But maybe gcc isn't smart enough to figure
that out.
Initialize cq and srq explicitly to avoid the warnings.
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Vlad Yasevich [Fri, 15 May 2015 00:34:08 +0000 (20:34 -0400)]
ipv6: Fix udp checksums with raw sockets
It was reported that trancerout6 would cause
a kernel to crash when trying to compute checksums
on raw UDP packets. The cause was the check in
__ip6_append_data that would attempt to use
partial checksums on the packet. However,
raw sockets do not initialize partial checksum
fields so partial checksums can't be used.
Solve this the same way IPv4 does it. raw sockets
pass transhdrlen value of 0 to ip_append_data which
causes the checksum to be computed in software. Use
the same check in ip6_append_data (check transhdrlen).
Reported-by: Wolfgang Walter <linux@stwm.de> CC: Wolfgang Walter <linux@stwm.de> CC: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Vladislav Yasevich <vyasevic@redhat.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Wesley Kuo [Wed, 13 May 2015 02:33:15 +0000 (10:33 +0800)]
Bluetooth: Fix remote name event return directly.
This patch fixes hci_remote_name_evt dose not resolve name during
discovery status is RESOLVING. Before simultaneous dual mode scan enabled,
hci_check_pending_name will set discovery status to STOPPED eventually.
Signed-off-by: Wesley Kuo <wesley.kuo@intel.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Vlad Yasevich [Wed, 13 May 2015 00:53:14 +0000 (20:53 -0400)]
vlan: Correctly propagate promisc|allmulti flags in notifier.
Currently vlan notifier handler will try to update all vlans
for a device when that device comes up. A problem occurs,
however, when the vlan device was set to promiscuous, but not
by the user (ex: a bridge). In that case, dev->gflags are
not updated. What results is that the lower device ends
up with an extra promiscuity count. Here are the
backtraces that prove this:
[62852.052179] [<ffffffff814fe248>] __dev_set_promiscuity+0x38/0x1e0
[62852.052186] [<ffffffff8160bcbb>] ? _raw_spin_unlock_bh+0x1b/0x40
[62852.052188] [<ffffffff814fe4be>] ? dev_set_rx_mode+0x2e/0x40
[62852.052190] [<ffffffff814fe694>] dev_set_promiscuity+0x24/0x50
[62852.052194] [<ffffffffa0324795>] vlan_dev_open+0xd5/0x1f0 [8021q]
[62852.052196] [<ffffffff814fe58f>] __dev_open+0xbf/0x140
[62852.052198] [<ffffffff814fe88d>] __dev_change_flags+0x9d/0x170
[62852.052200] [<ffffffff814fe989>] dev_change_flags+0x29/0x60
The above comes from the setting the vlan device to IFF_UP state.
And this one comes from the notification code. What we end
up with is a vlan with promiscuity count of 1 and and a physical
device with a promiscuity count of 2. They should both have
a count 1.
To resolve this issue, vlan code can use dev_get_flags() api
which correctly masks promiscuity and allmulti flags.
Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
1) Handle max TX power properly wrt VIFs and the MAC in iwlwifi, from
Avri Altman.
2) Use the correct FW API for scan completions in iwlwifi, from Avraham
Stern.
3) FW monitor in iwlwifi accidently uses unmapped memory, fix from Liad
Kaufman.
4) rhashtable conversion of mac80211 station table was buggy, the
virtual interface was not taken into account. Fix from Johannes
Berg.
5) Fix deadlock in rtlwifi by not using a zero timeout for
usb_control_msg(), from Larry Finger.
6) Update reordering state before calculating loss detection, from
Yuchung Cheng.
7) Fix off by one in bluetooth firmward parsing, from Dan Carpenter.
8) Fix extended frame handling in xiling_can driver, from Jeppe
Ledet-Pedersen.
9) Fix CODEL packet scheduler behavior in the presence of TSO packets,
from Eric Dumazet.
10) Fix NAPI budget testing in fm10k driver, from Alexander Duyck.
11) macvlan needs to propagate promisc settings down the the lower
device, from Vlad Yasevich.
12) igb driver can oops when changing number of rings, from Toshiaki
Makita.
13) Source specific default routes not handled properly in ipv6, from
Markus Stenberg.
14) Use after free in tc_ctl_tfilter(), from WANG Cong.
15) Use softirq spinlocking in netxen driver, from Tony Camuso.
16) Two ARM bpf JIT fixes from Nicolas Schichan.
17) Handle MSG_DONTWAIT properly in ring based AF_PACKET sends, from
Mathias Kretschmer.
18) Fix x86 bpf JIT implementation of FROM_{BE16,LE16,LE32}, from Alexei
Starovoitov.
19) ll_temac driver DMA maps TX packet header with incorrect length, fix
from Michal Simek.
20) We removed pm_qos bits from netdevice.h, but some indirect
references remained. Kill them. From David Ahern.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (90 commits)
net: Remove remaining remnants of pm_qos from netdevice.h
e1000e: Add pm_qos header
net: phy: micrel: Fix regression in kszphy_probe
net: ll_temac: Fix DMA map size bug
x86: bpf_jit: fix FROM_BE16 and FROM_LE16/32 instructions
netns: return RTM_NEWNSID instead of RTM_GETNSID on a get
Update be2net maintainers' email addresses
net_sched: gred: use correct backlog value in WRED mode
pppoe: drop pppoe device in pppoe_unbind_sock_work
net: qca_spi: Fix possible race during probe
net: mdio-gpio: Allow for unspecified bus id
af_packet / TX_RING not fully non-blocking (w/ MSG_DONTWAIT).
bnx2x: limit fw delay in kdump to 5s after boot
ARM: net: delegate filter to kernel interpreter when imm_offset() return value can't fit into 12bits.
ARM: net fix emit_udiv() for BPF_ALU | BPF_DIV | BPF_K intruction.
mpls: Change reserved label names to be consistent with netbsd
usbnet: avoid integer overflow in start_xmit
netxen_nic: use spin_[un]lock_bh around tx_clean_lock (2)
net: xgene_enet: Set hardware dependency
net: amd-xgbe: Add hardware dependency
...
David Ahern [Tue, 12 May 2015 15:36:59 +0000 (09:36 -0600)]
e1000e: Add pm_qos header
Commit e2c6544829f moved pm_qos_req to e1000_adapter. Add the header file
that defines the struct.
Signed-off-by: David Ahern <dsahern@gmail.com> Cc: Thomas Graf <tgraf@suug.ch> Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
x86: bpf_jit: fix FROM_BE16 and FROM_LE16/32 instructions
FROM_BE16:
'ror %reg, 8' doesn't clear upper bits of the register,
so use additional 'movzwl' insn to zero extend 16 bits into 64
FROM_LE16:
should zero extend lower 16 bits into 64 bit
FROM_LE32:
should zero extend lower 32 bits into 64 bit
Fixes: 89aa075832b0 ("net: sock: allow eBPF programs to be attached to sockets") Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Linus Torvalds [Tue, 12 May 2015 23:02:06 +0000 (16:02 -0700)]
Merge branch 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus
Pull MIPS fixes from Ralf Baechle:
"One build fix for build breakage of all MIPS SMP kernels caused by
Rusty's fix of obsolete use of cpu mask helpers, another to fix the FP
ABI selection when loading an ELF binary"
* 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus:
MIPS: fix FP mode selection in lieu of .MIPS.abiflags data
MIPS: SMP: Fix build error.
Linus Torvalds [Tue, 12 May 2015 22:54:54 +0000 (15:54 -0700)]
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma
Pull rdma fixes from Doug Ledford:
- update MAINTAINERS git repo pointer
- printk garbage fix
- fix for qib and iw_cxgb4 bugs introduced in 4.1 window
- fix for an older iWARP netlink bug
- fix a memcpy issue in ehca driver
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma:
infiniband: Remove duplicated KERN_<LEVEL> from pr_<level> uses
IB/qib: fix test of unsigned variable
RDMA/core: Fix for parsing netlink string attribute
MAINTAINERS: update the official rdma git repo
iw_cxgb4: use wildcard mapping for getting remote addr info
IB/ehca: use correct destination for memcpy
Nicolas Dichtel [Mon, 11 May 2015 13:57:31 +0000 (15:57 +0200)]
netns: return RTM_NEWNSID instead of RTM_GETNSID on a get
Usually, RTM_NEWxxx is returned on a get (same as a dump).
Fixes: 0c7aecd4bde4 ("netns: add rtnl cmd to add and get peer netns ids") Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Linus Torvalds [Tue, 12 May 2015 22:49:29 +0000 (15:49 -0700)]
Merge tag 'for-v4.1-rc' of git://git.infradead.org/battery-2.6
Pull power supply and reset fixes from Sebastian Reichel:
"misc fixes"
* tag 'for-v4.1-rc' of git://git.infradead.org/battery-2.6:
power: bq27x00_battery: Add missing MODULE_ALIAS
power: reset: Add MFD_SYSCON depends for brcmstb
power: reset: ltc2952: Remove bogus hrtimer_start() return value checks
power_supply: fix oops in collie_battery driver
power/reset: at91: fix return value check in at91_reset_platform_probe()
MAINTAINERS: Add me as maintainer of Nokia N900 power supply drivers
axp288_fuel_gauge: Add original author details
Mike Marciniszyn [Tue, 12 May 2015 17:42:42 +0000 (13:42 -0400)]
IB/qib: fix test of unsigned variable
Commit d4988623cc60 ("IB/qib: use arch_phys_wc_add()")
adjusted mtrr inititialization to use the new interface.
Unfortunately, the new interface returns a signed
value and the patch tested the unsigned wc_cookie.
Fix the issue by changing the type of wc_cookie to int. For
the success case the ret left at zero to avoid
a warning from the caller. For failure wc_cookie
is used as the ret.
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
RDMA/core: Fix for parsing netlink string attribute
The string iwpm_ulib_name is recorded in a nlmsg as a netlink attribute.
Without this fix parsing of the nlmsg by the userspace port mapper service fails
because of unknown attribute length, causing the port mapper service not to
register the client, which has sent the nlmsg.
Paul Burton [Wed, 6 May 2015 10:52:32 +0000 (11:52 +0100)]
MIPS: fix FP mode selection in lieu of .MIPS.abiflags data
Commit 46490b572544 ("MIPS: kernel: elf: Improve the overall ABI and FPU
mode checks") reworked the ELF FP ABI mode selection logic, but when
CONFIG_MIPS_O32_FP64_SUPPORT is enabled it breaks the use of binaries
which have no PT_MIPS_ABIFLAGS program header & associated
.MIPS.abiflags section.
A default mode is selected based upon whether the ELF contains MIPS32 or
MIPS64 code, but that selection is made in arch_elf_pt_proc.
arch_elf_pt_proc only executes when a PT_MIPS_ABIFLAGS program header is
found. If one is not found then arch_elf_pt_proc is never called, and no
default overall_fp_mode value is selected. When arch_check_elf is
called, both abi0 & abi1 are MIPS_ABI_FP_UNKNOWN which leads to both
prog_req & interp_req being set to none_req. none_req matches none of
the conditions for mode selection at the end of arch_check_elf, so
overall_fp_mode is left untouched. Finally once mips_set_personality_fp
is called the BUG() in the default case is then hit & the kernel likely
panics.
Fix this by moving the selection of a default overall mode to the start
of arch_check_elf, which runs once per ELF executed regardless of
whether it has a PT_MIPS_ABIFLAGS program header.
Sathya Perla [Tue, 12 May 2015 06:13:50 +0000 (02:13 -0400)]
Update be2net maintainers' email addresses
Emulex developers' email addresses are now "@avagotech" instead of
"@emulex". I'm also replacing Subbu with Padmanabh and Sriharsha in the
maintainers list. The driver's heading was outdated and did not include
some of the chip types (BE3, Lancer and Skyhawk) that the driver has
been supporting for a longtime. I've updated this too.
Signed-off-by: Sathya Perla <sathya.perla@avagotech.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Ralf Baechle [Tue, 12 May 2015 04:43:04 +0000 (06:43 +0200)]
MIPS: SMP: Fix build error.
CC arch/mips/kernel/smp.o
arch/mips/kernel/smp.c: In function ‘start_secondary’:
arch/mips/kernel/smp.c:149:2: error: passing argument 2 of ‘cpumask_set_cpu’ discards ‘volatile’ qualifier from pointer target type [-Werror]
cpumask_set_cpu(cpu, &cpu_callin_map);
^
In file included from ./arch/mips/include/asm/processor.h:14:0,
from ./arch/mips/include/asm/thread_info.h:15,
from include/linux/thread_info.h:54,
from include/asm-generic/preempt.h:4,
from arch/mips/include/generated/asm/preempt.h:1,
from include/linux/preempt.h:18,
from include/linux/interrupt.h:8,
from arch/mips/kernel/smp.c:24:
include/linux/cpumask.h:272:91: note: expected ‘struct cpumask *’ but argument is of type ‘volatile struct cpumask_t *’
static inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
^
arch/mips/kernel/smp.c: In function ‘smp_prepare_boot_cpu’:
arch/mips/kernel/smp.c:211:2: error: passing argument 2 of ‘cpumask_set_cpu’ discards ‘volatile’ qualifier from pointer target type [-Werror]
cpumask_set_cpu(0, &cpu_callin_map);
^
In file included from ./arch/mips/include/asm/processor.h:14:0,
from ./arch/mips/include/asm/thread_info.h:15,
from include/linux/thread_info.h:54,
from include/asm-generic/preempt.h:4,
from arch/mips/include/generated/asm/preempt.h:1,
from include/linux/preempt.h:18,
from include/linux/interrupt.h:8,
from arch/mips/kernel/smp.c:24:
include/linux/cpumask.h:272:91: note: expected ‘struct cpumask *’ but argument is of type ‘volatile struct cpumask_t *’
static inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
^
arch/mips/kernel/smp.c: In function ‘__cpu_up’:
arch/mips/kernel/smp.c:221:10: error: passing argument 2 of ‘cpumask_test_cpu’ discards ‘volatile’ qualifier from pointer target type [-Werror]
while (!cpumask_test_cpu(cpu, &cpu_callin_map))
^
In file included from ./arch/mips/include/asm/processor.h:14:0,
from ./arch/mips/include/asm/thread_info.h:15,
from include/linux/thread_info.h:54,
from include/asm-generic/preempt.h:4,
from arch/mips/include/generated/asm/preempt.h:1,
from include/linux/preempt.h:18,
from include/linux/interrupt.h:8,
from arch/mips/kernel/smp.c:24:
include/linux/cpumask.h:294:90: note: expected ‘const struct cpumask *’ but argument is of type ‘volatile struct cpumask_t *’
static inline int cpumask_test_cpu(int cpu, const struct cpumask *cpumask)
^
cc1: all warnings being treated as errors
make[2]: *** [arch/mips/kernel/smp.o] Error 1
make[1]: *** [arch/mips/kernel] Error 2
make: *** [arch/mips] Error 2
Linus Torvalds [Mon, 11 May 2015 21:42:52 +0000 (14:42 -0700)]
Merge branch 'for-4.1' of git://linux-nfs.org/~bfields/linux
Pull nfsd bugfixes from Bruce Fields:
"Mainly pnfs fixes (and for problems with generic callback code made
more obvious by pnfs)"
* 'for-4.1' of git://linux-nfs.org/~bfields/linux:
nfsd: skip CB_NULL probes for 4.1 or later
nfsd: fix callback restarts
nfsd: split transport vs operation errors for callbacks
svcrpc: fix potential GSSX_ACCEPT_SEC_CONTEXT decoding failures
nfsd: fix pNFS return on close semantics
nfsd: fix the check for confirmed openowner in nfs4_preprocess_stateid_op
nfsd/blocklayout: pretend we can send deviceid notifications
Steve Wise [Thu, 7 May 2015 21:34:23 +0000 (16:34 -0500)]
iw_cxgb4: use wildcard mapping for getting remote addr info
For listening endpoints bound to the wildcard address, we need to pass
the wildcard address mapping to iwpm_get_remote_info() instead of the
mapped address of the new child connection.
Without this fix, and with iwarp port mapping enabled, each iw_cxgb4
connection that is spawned from a listening endpoint bound to the wildcard
address, will generate an annoying dmesg entry about failing to find
the remote address mapping info, and the connection state displayed in
debugfs under /sys/kernel/debug/iw_cxgb4/<pci-slot-no>/eps will not have
the peer's address/port mapping info. The connection still works though.
Fixes: 5b6b8fe ("RDMA/cxgb4: Report the actual address of the remote connecting peer") Signed-off-by: Steve Wise <swise@opengridcomputing.com> Reviewed-by: Tatyana Nikolova <Tatyana.E.Nikolova@intel.com> Reviewed-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
Using an element of a struct as the address for the memcpy of the whole
struct may introduce a buffer overflow and does not help readability either
simply pass the real thing as first argument to memcpy.
Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Nicholas Mc Guire <hofrat@osadl.org> Signed-off-by: Doug Ledford <dledford@redhat.com>
Linus Torvalds [Mon, 11 May 2015 20:57:47 +0000 (13:57 -0700)]
Merge tag 'spi-fix-v4.1-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/spi
Pull spi fixes from Mark Brown:
"A number of driver specific fixes (including several missing
dependencies for randconfig type cases) plus two core fixes.
One makes the setup_transfer() callback optional which unbreaks some
drivers which had been merged with it omitted due to local versions of
this patch and another ensures that we don't corrupt data by leaking
internal dummy buffers to callers, causing the callers to think they
allocated those buffers"
* tag 'spi-fix-v4.1-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/spi:
spi: fsl-espi: fix behaviour for full-duplex xfers
spi: fsl-spi: fix devm_ioremap_resource() error case
spi: Kconfig: Add SOC_LS1021A to SPI_FSL_DSPI dependence
spi/omap2-mcpsi: Always call spi_finalize_current_message()
spi: fsl-spi: use devm_ioremap_resource() to map parameter ram on CPM1
spi: bitbang: Make setup_transfer() callback optional
spi: check tx_buf and rx_buf in spi_unmap_msg
spi: bcm2835: change timeout of polling driver to 1s
spi: bcm2835: Add GPIOLIB dependency
Linus Torvalds [Mon, 11 May 2015 18:09:54 +0000 (11:09 -0700)]
Merge tag 'iommu-fixes-v4.1-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu
Pull iommu fixes from Joerg Roedel:
"Three fixes have queued up:
- reference count fix in the AMD IOMMUv2 driver
- sign extension fix in the ARM-SMMU driver
- build fix for rockchip driver with device tree"
* tag 'iommu-fixes-v4.1-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu:
iommu/arm-smmu: Fix sign-extension of upstream bus addresses at stage 1
iommu/rockchip: Fix build without CONFIG_OF
iommu/amd: Fix bug in put_pasid_state_wait
Linus Torvalds [Mon, 11 May 2015 17:54:20 +0000 (10:54 -0700)]
Merge branch 'for-4.1-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata
Pull libata fixes from Tejun Heo:
"Rather big for fixes pull.
- SCC controllers never lived to see the light of the day. Both
libata and ide drivers removed.
- In some configurations, link power management policy changes
sometimes cause delayed spurious PHY events which can develop into
noticeable failures. This has been reported several times over the
years. Gabriele's patches suppress PHY events for a while after
LPM policy changes which should help most of these failures without
causing too much problem for hotplug use cases.
- A few controller specific fixes"
[ Hmm. I don't think removing SSC support is really a "fix", but hey, it
removes a lot of lines of code. Which I like. So ... good riddance ]
* 'for-4.1-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata:
ahci: avoton port-disable reset-quirk
ata: select DW_DMAC in case of SATA_DWC
libata: Blacklist queued TRIM on all Samsung 800-series
libata: Ignore spurious PHY event on LPM policy change
libata: Add helper to determine when PHY events should be ignored
ata: ahci_st: fixup layering violations / drvdata errors
Remove celleb-only SCC PATA drivers
Linus Torvalds [Mon, 11 May 2015 17:33:31 +0000 (10:33 -0700)]
Merge tag 'md/4.1-rc3-fixes' of git://neil.brown.name/md
Pull md bugfixes from Neil Brown:
"A few fixes for md.
Most of these are related to the new "batched stripe writeout", but
there are a few others"
* tag 'md/4.1-rc3-fixes' of git://neil.brown.name/md:
md/raid5: fix handling of degraded stripes in batches.
md/raid5: fix allocation of 'scribble' array.
md/raid5: don't record new size if resize_stripes fails.
md/raid5: avoid reading parity blocks for full-stripe write to degraded array
md/raid5: more incorrect BUG_ON in handle_stripe_fill.
md/raid5: new alloc_stripe() to allocate an initialize a stripe.
md-raid0: conditional mddev->queue access to suit dm-raid
David Ward [Sun, 10 May 2015 02:01:47 +0000 (22:01 -0400)]
net_sched: gred: use correct backlog value in WRED mode
In WRED mode, the backlog for a single virtual queue (VQ) should not be
used to determine queue behavior; instead the backlog is summed across
all VQs. This sum is currently used when calculating the average queue
lengths. It also needs to be used when determining if the queue's hard
limit has been reached, or when reporting each VQ's backlog via netlink.
q->backlog will only be used if the queue switches out of WRED mode.
Signed-off-by: David Ward <david.ward@ll.mit.edu> Signed-off-by: David S. Miller <davem@davemloft.net>
Felix Fietkau [Sat, 9 May 2015 21:08:38 +0000 (23:08 +0200)]
pppoe: drop pppoe device in pppoe_unbind_sock_work
After receiving a PADT and the socket is closed, user space will no
longer drop the reference to the pppoe device.
This leads to errors like this:
[ 488.570000] unregister_netdevice: waiting for eth0.2 to become free. Usage count = 2
Fixes: 287f3a943fe ("pppoe: Use workqueue to die properly when a PADT is received") Signed-off-by: Felix Fietkau <nbd@openwrt.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Will Deacon [Fri, 8 May 2015 16:44:22 +0000 (17:44 +0100)]
iommu/arm-smmu: Fix sign-extension of upstream bus addresses at stage 1
Stage 1 translation is controlled by two sets of page tables (TTBR0 and
TTBR1) which grow up and down from zero respectively in the ARMv8
translation regime. For the SMMU, we only care about TTBR0 and, in the
case of a 48-bit virtual space, we expect to map virtual addresses 0x0
through to 0xffff_ffff_ffff.
Given that some masters may be incapable of emitting virtual addresses
targetting TTBR1 (e.g. because they sit on a 48-bit bus), the SMMU
architecture allows bit 47 to be sign-extended, halving the virtual
range of TTBR0 but allowing TTBR1 to be used. This is controlled by the
SEP field in TTBCR2.
The SMMU driver incorrectly enables this sign-extension feature, which
causes problems when userspace addresses are programmed into a master
device with the SMMU expecting to map the incoming transactions via
TTBR0; if the top bit of address is set, we will instead get a
translation fault since TTBR1 walks are disabled in the TTBCR.
This patch fixes the issue by disabling sign-extension of a fixed
virtual address bit and instead basing the behaviour on the upstream bus
size: the incoming address is zero extended unless the upstream bus is
only 49 bits wide, in which case bit 48 is used as the sign bit and is
replicated to the upper bits.
Mark Brown [Mon, 11 May 2015 16:29:46 +0000 (17:29 +0100)]
Merge tag 'spi-v4.1-rc1' into spi-linus
spi: Fixes for v4.1
A few driver fixes plus two changes for the core, one to make the
setup_transfer() callback optional which fixes crashes in some drivers
which were updated to use new interfaces without apparent testing and
one to ensure we don't expose the data buffers we use for dummy
transfers to drivers which avoids potential issues with multiple
accesses to them or reuse.
# gpg: Signature made Sat 25 Apr 2015 10:59:47 BST using RSA key ID 5D5487D0
# gpg: key CD7BEEBC: no public key for trusted key - skipped
# gpg: key CD7BEEBC marked as ultimately trusted
# gpg: key AF88CD16: no public key for trusted key - skipped
# gpg: key AF88CD16 marked as ultimately trusted
# gpg: key 16005C11: no public key for trusted key - skipped
# gpg: key 16005C11 marked as ultimately trusted
# gpg: key 5621E907: no public key for trusted key - skipped
# gpg: key 5621E907 marked as ultimately trusted
# gpg: key 5C6153AD: no public key for trusted key - skipped
# gpg: key 5C6153AD marked as ultimately trusted
# gpg: Good signature from "Mark Brown <broonie@sirena.org.uk>"
# gpg: aka "Mark Brown <broonie@debian.org>"
# gpg: aka "Mark Brown <broonie@kernel.org>"
# gpg: aka "Mark Brown <broonie@tardis.ed.ac.uk>"
# gpg: aka "Mark Brown <broonie@linaro.org>"
# gpg: aka "Mark Brown <Mark.Brown@linaro.org>"
Stefan Wahren [Sat, 9 May 2015 07:58:09 +0000 (07:58 +0000)]
net: qca_spi: Fix possible race during probe
Registering the netdev before setting the priv data is unsafe.
So fix this possible race by setting the priv data first.
Signed-off-by: Stefan Wahren <stefan.wahren@i2se.com> Cc: <stable@vger.kernel.org> # v3.18+ Fixes: 291ab06e (net: qualcomm: new Ethernet over SPI driver for QCA7000) Signed-off-by: David S. Miller <davem@davemloft.net>
Bert Vermeulen [Fri, 8 May 2015 14:18:49 +0000 (16:18 +0200)]
net: mdio-gpio: Allow for unspecified bus id
When the bus id was supplied via a struct platform_device, the driver wasn't
handling -1 to mean an unspecified id of the only instance of this driver,
as the platform spec requires.
Signed-off-by: Bert Vermeulen <bert@biot.com> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
af_packet / TX_RING not fully non-blocking (w/ MSG_DONTWAIT).
This patch fixes an issue where the send(MSG_DONTWAIT) call
on a TX_RING is not fully non-blocking in cases where the device's sndBuf is
full. We pass nonblock=true to sock_alloc_send_skb() and return any possibly
occuring error code (most likely EGAIN) to the caller. As the fast-path stays
as it is, we keep the unlikely() around skb == NULL.
Signed-off-by: Mathias Kretschmer <mathias.kretschmer@fokus.fraunhofer.de> Signed-off-by: David S. Miller <davem@davemloft.net>
Michal Schmidt [Thu, 7 May 2015 18:37:10 +0000 (20:37 +0200)]
bnx2x: limit fw delay in kdump to 5s after boot
Commit 12a8541d5c82 "bnx2x: Delay during kdump load" added a 5 seconds
delay to bnx2x's probe function in the kdump case to let the firmware
realize the old driver is gone.
The problem with the delay is that it is per-device, so if you have
several bnx2x NICs in NPAR mode, the delays can accumulate to minutes.
Fix it by adjusting the delay so that we do not wait more than
necessary, i.e. no more delaying after 5 seconds of kernel boot time.
Signed-off-by: Michal Schmidt <mschmidt@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
ARM: net: delegate filter to kernel interpreter when imm_offset() return value can't fit into 12bits.
The ARM JIT code emits "ldr rX, [pc, #offset]" to access the literal
pool. #offset maximum value is 4095 and if the generated code is too
large, the #offset value can overflow and not point to the expected
slot in the literal pool. Additionally, when overflow occurs, bits of
the overflow can end up changing the destination register of the ldr
instruction.
Fix that by detecting the overflow in imm_offset() and setting a flag
that is checked for each BPF instructions converted in
build_body(). As of now it can only be detected in the second pass. As
a result the second build_body() call can now fail, so add the
corresponding cleanup code in that case.
Using multiple literal pools in the JITed code is going to require
lots of intrusive changes to the JIT code (which would better be done
as a feature instead of fix), just delegating to the kernel BPF
interpreter in that case is a more straight forward, minimal fix and
easy to backport.
Fixes: ddecdfcea0ae ("ARM: 7259/3: net: JIT compiler for packet filters") Signed-off-by: Nicolas Schichan <nschichan@freebox.fr> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
ARM: net fix emit_udiv() for BPF_ALU | BPF_DIV | BPF_K intruction.
In that case, emit_udiv() will be called with rn == ARM_R0 (r_scratch)
and loading rm first into ARM_R0 will result in jit_udiv() function
being called the same dividend and divisor. Fix that by loading rn
first into ARM_R1 and then rm into ARM_R0.
Signed-off-by: Nicolas Schichan <nschichan@freebox.fr> Cc: <stable@vger.kernel.org> # v3.13+ Fixes: aee636c4809f (bpf: do not use reciprocal divide) Acked-by: Mircea Gherzan <mgherzan@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Linus Torvalds [Sun, 10 May 2015 21:58:53 +0000 (14:58 -0700)]
Merge branch 'drm-fixes' of git://people.freedesktop.org/~airlied/linux
Pull drm fixes from Dave Airlie:
"I really need to get back to sending these on my Friday, instead of my
Monday morning, but nothing too amazing in here: a few amdkfd fixes, a
few radeon fixes, i915 fixes, one tegra fix and one core fix"
* 'drm-fixes' of git://people.freedesktop.org/~airlied/linux:
drm: Zero out invalid vblank timestamp in drm_update_vblank_count.
drm/tegra: Don't use vblank_disable_immediate on incapable driver.
drm/radeon: stop trying to suspend UVD sessions
drm/radeon: more strictly validate the UVD codec
drm/radeon: make UVD handle checking more strict
drm/radeon: make VCE handle check more strict
drm/radeon: fix userptr lockup
drm/radeon: fix userptr BO unpin bug v3
drm/amdkfd: Initialize sdma vm when creating sdma queue
drm/amdkfd: Don't report local memory size
drm/amdkfd: allow unregister process with queues
drm/i915: Drop PIPE-A quirk for 945GSE HP Mini
drm/i915: Sink rate read should be saved in deca-kHz
drm/i915/dp: there is no audio on port A
drm/i915: Add missing MacBook Pro models with dual channel LVDS
drm/i915: Assume dual channel LVDS if pixel clock necessitates it
drm/radeon: don't setup audio on asics that don't support it
drm/radeon: disable semaphores for UVD V1 (v2)
Dave Airlie [Sun, 10 May 2015 20:06:22 +0000 (06:06 +1000)]
Merge tag 'drm-intel-fixes-2015-05-08' of git://anongit.freedesktop.org/drm-intel into drm-fixes
misc i915 fixes.
* tag 'drm-intel-fixes-2015-05-08' of git://anongit.freedesktop.org/drm-intel:
drm/i915: Drop PIPE-A quirk for 945GSE HP Mini
drm/i915: Sink rate read should be saved in deca-kHz
drm/i915/dp: there is no audio on port A
drm/i915: Add missing MacBook Pro models with dual channel LVDS
drm/i915: Assume dual channel LVDS if pixel clock necessitates it
Mario Kleiner [Tue, 7 Apr 2015 04:31:09 +0000 (06:31 +0200)]
drm: Zero out invalid vblank timestamp in drm_update_vblank_count.
Since commit 844b03f27739135fe1fed2fef06da0ffc4c7a081 we make
sure that after vblank irq off, we return the last valid
(vblank count, vblank timestamp) pair to clients, e.g., during
modesets, which is good.
An overlooked side effect of that commit for kms drivers without
support for precise vblank timestamping is that at vblank irq
enable, when we update the vblank counter from the hw counter, we
can't update the corresponding vblank timestamp, so now we have a
totally mismatched timestamp for the new count to confuse clients.
Restore old client visible behaviour from before Linux 3.17, but
zero out the timestamp at vblank counter update (instead of disable
as in original implementation) if we can't generate a meaningful
timestamp immediately for the new vblank counter. This will fix
this regression, so callers know they need to retry again later
if they need a valid timestamp, but at the same time preserves
the improvements made in the commit mentioned above.
Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com> Cc: <stable@vger.kernel.org> #v3.17+ Cc: Ville Syrjälä <ville.syrjala@linux.intel.com> Cc: Daniel Vetter <daniel@ffwll.ch> Signed-off-by: Dave Airlie <airlied@redhat.com>
Linus Torvalds [Sun, 10 May 2015 18:13:19 +0000 (11:13 -0700)]
Merge tag 'samsung-fixes-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kgene/linux-samsung
Pull samsung fixes from Kukjin Kim:
"Here is Samsung fixes for v4.1. Since I've missed to send this via
arm-soc tree before v4.1-rc3, so I'm sending this to you directly
- fix commit ea08de16eb1b ("ARM: dts: Add DISP1 power domain for
exynos5420") which causes 'unhandled fault: imprecise external
abort' error when PD turned off. ("make DP a consumer of DISP1
power domain")
- fix 's3c-rtc' probe failure on Odriod-X2/U2/U3 boards ("add
'rtc_src' clock to rtc node for source clock of rtc")
- fix typo for 'cpu-crit-0' trip point on exynos5420/5440
- fix S2R failure on exynos5250-snow due to card power of Marvell
WiFi driver (suspend/resume) ("add keep-power-in-susped to WiFi
SDIO node")"
* tag 'samsung-fixes-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kgene/linux-samsung:
ARM: dts: Add keep-power-in-suspend to WiFi SDIO node for exynos5250-snow
ARM: dts: Fix typo in trip point temperature for exynos5420/5440
ARM: dts: add 'rtc_src' clock to rtc node for exynos4412-odroid boards
ARM: dts: Make DP a consumer of DISP1 power domain on Exynos5420
Dan Williams [Fri, 8 May 2015 19:23:55 +0000 (15:23 -0400)]
ahci: avoton port-disable reset-quirk
Avoton AHCI occasionally sees drive probe timeouts at driver load time.
When this happens SCR_STATUS indicates device detected, but no D2H FIS
reception. Reset the internal link state machines by bouncing
port-enable in the PCS register when this occurs.
Cc: <stable@vger.kernel.org> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Tejun Heo <tj@kernel.org>
David S. Miller [Sun, 10 May 2015 02:23:59 +0000 (22:23 -0400)]
Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-queue
Jeff Kirsher says:
====================
Intel Wired LAN Driver Updates 2015-05-07
This series contains updates to igb only.
Toshiaki provides two fixes for igb, first fixes an issue when changing
the number of rings by ethtool which causes oops because of uninitialized
pointers. The second fix resolves a typo where tx_ring was used instead
of the desired rx_ring.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Linus Torvalds [Sat, 9 May 2015 23:13:38 +0000 (16:13 -0700)]
Merge tag 'fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc
Pull ARM SoC fixes from Arnd Bergmann:
"A few patches have come up since the merge window. The largest one is
a rewrite of the PXA lubbock/mainstone IRQ handling. This was already
broken in 2011 by a change to the GPIO code and only noticed now.
The other changes contained here are:
MAINTAINERS file updates:
- Ray Jui and Scott Branden are now co-maintainers for some of the
mach-bcm chips, while Christian Daudt and Marc Carino have stepped
down.
- Andrew Victor is no longer maintaining at91. Instead, Alexandre
Belloni now becomes an official maintainer, after having done a
bulk of the work for a while.
- Baruch Siach, who added the mach-digicolor platform in 4.1 is now
listed as maintainer
- The git URL for mach-socfpga has changed
Bug fixes:
- Three bug fixes for new rockchip rk3288 code
- A regression fix to make SD card support work on certain ux500
boards
- multiple smaller dts fixes for imx, omap, mvebu, and shmobile
- a regression fiix for omap3 power consumption
- a fix for regression in the ARM CCI bus driver
Configuration changes:
- more imx platforms are now enabled in multi_v7_defconfig"
* tag 'fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc: (39 commits)
MAINTAINERS: add Conexant Digicolor machines entry
MAINTAINERS: socfpga: update the git repo for SoCFPGA
ARM: multi_v7_defconfig: Select more FSL SoCs
MAINTAINERS: replace an AT91 maintainer
drivers: CCI: fix used_mask init in validate_group()
bus: omap_l3_noc: Fix master id address decoding for OMAP5
bus: omap_l3_noc: Fix offset for DRA7 CLK1_HOST_CLK1_2 instance
ARM: dts: dra7: Fix efuse register size for ABB
ARM: dts: am57xx-beagle-x15: Switch GPIO fan number
ARM: dts: am57xx-beagle-x15: Switch UART mux pins
ARM: dts: am437x-sk: reduce col-scan-delay-us
ARM: dts: am437x-sk: fix for new newhaven display module revision
ARM: dts: am57xx-beagle-x15: Fix RTC aliases
ARM: dts: am57xx-beagle-x15: Fix IRQ type for mcp7941x
ARM: dts: omap3: Add #iommu-cells to isp and iva iommu
ARM: omap2plus_defconfig: Enable EXTCON_USB_GPIO
ARM: dts: OMAP3-N900: Add microphone bias voltages
ARM: OMAP2+: Fix omap off idle power consumption creeping up
MAINTAINERS: Update brcmstb entry
MAINTAINERS: Remove Christian Daudt for mach-bcm
...
Linus Torvalds [Sat, 9 May 2015 23:07:14 +0000 (16:07 -0700)]
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace
Pull user-namespace fix from Eric Biederman:
"Eric Windish recently reported a really bug that allows mounting fresh
copies of proc and sysfs when it really should not be allowed. The
code attempted to verify that proc and sysfs were fully visible but
there is a test missing to ensure that the root of the filesystem is
visible. Doh!
The following patch fixes that.
This fixes a containment issue that the docker folks are seeing"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
mnt: Fix fs_fully_visible to verify the root directory is visible
Linus Torvalds [Sat, 9 May 2015 21:59:05 +0000 (14:59 -0700)]
Merge branch 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull irq updates from Thomas Gleixner:
"Two patches from the irq departement:
- a simple fix to make dummy_irq_chip usable for wakeup scenarios
- removal of the gic arch_extn hackery. Now that all users are
converted we really want to get rid of the interface so people wont
come up with new use cases"
* 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
irqchip: gic: Drop support for gic_arch_extn
genirq: Set IRQCHIP_SKIP_SET_WAKE flag for dummy_irq_chip
transfer_buffer_length is of type u32. It's therefore wrong to assign it
to a signed integer. This patch avoids the overflow.
It's worth noting that entry->length here is a long; perhaps it would be
beneficial at somepoint to change this to be unsigned as well, if
nothing else relies on its signedness for error conditions or the like.
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Tony Camuso [Wed, 6 May 2015 13:09:18 +0000 (09:09 -0400)]
netxen_nic: use spin_[un]lock_bh around tx_clean_lock (2)
This patch should have been part of the previous patch having the
same summary. See http://marc.info/?l=linux-kernel&m=143039470103795&w=2
Unfortunately, I didn't check to see where else this lock was used before
submitting that patch. This should take care of it for netxen_nic, as I
did a thorough search this time.
To recap from the original patch; although testing this driver with
DEBUG_LOCKDEP and DEBUG_SPINLOCK enabled did not produce any traces,
it would be more prudent in the case of tx_clean_lock to use _bh
versions of spin_[un]lock, since this lock is manipulated in both
the process and softirq contexts.
This patch was tested for functionality and regressions with netperf
and DEBUG_LOCKDEP and DEBUG_SPINLOCK enabled.
Signed-off-by: Tony Camuso <tcamuso@redhat.com> Acked-By: Neil Horman <nhorman@tuxdriver.com> Acked-By: Manish Chopra <manish.chopra@qlogic.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jean Delvare [Wed, 6 May 2015 07:14:34 +0000 (09:14 +0200)]
net: xgene_enet: Set hardware dependency
The xgene_enet driver is only useful on X-Gene SoC.
Signed-off-by: Jean Delvare <jdelvare@suse.de> Cc: Iyappan Subramanian <isubramanian@apm.com> Cc: Keyur Chudgar <kchudgar@apm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jean Delvare [Wed, 6 May 2015 07:04:40 +0000 (09:04 +0200)]
net: amd-xgbe: Add hardware dependency
The amd-xgbe driver currently only works with the Seattle SoC, which
is ARM64 architecture, so there is no point in building this driver on
other architectures except for build testing purpose. The dependency
list can be updated later if the driver ever supports other
architectures.
Signed-off-by: Jean Delvare <jdelvare@suse.de> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
WANG Cong [Tue, 5 May 2015 22:22:02 +0000 (15:22 -0700)]
net_sched: fix a use-after-free in tc_ctl_tfilter()
When tcf_destroy() returns true, tp could be already destroyed,
we should not use tp->next after that.
For long term, we probably should move tp list to list_head.
Fixes: 1e052be69d04 ("net_sched: destroy proto tp when all filters are gone") Cc: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Nathan Sullivan [Tue, 5 May 2015 20:00:25 +0000 (15:00 -0500)]
net: macb: Handle the RXUBR interrupt on all devices
The same hardware issue the at91 must work around applies to at least the
Zynq ethernet, and possibly more devices. The driver also needs to handle
the RXUBR interrupt since it turns it on with MACB_RX_INT_FLAGS anyway.
Signed-off-by: Nathan Sullivan <nathan.sullivan@ni.com> Signed-off-by: David S. Miller <davem@davemloft.net>
This patch-set contains bug fixes for state-recovery at the RDS
layer when the underlying transport is TCP and the TCP state at one
of the endpoints is reset
V2 changes: DaveM comments to reduce memory footprint, follow
NFS/RPC model where possible. Added test-case #3
Without the changes in this set, when one of the endpoints is reset,
the existing code does not correctly clean up RDS socket state for stale
connections, resulting in some unstable, timing-dependant behavior on
the wire, including an infinite exchange of 3WHs back-and-forth, and a
resulting potential to never converge RDS state.
Test cases used to verify the changes in this set are:
1. Start rds client/server applications on two participating nodes,
node1 and node2. After at least one packet has been sent (to establish
the TCP connection), restart the rds_tcp module on the client, and
now resend packets. Tcpdump should show server sending a FIN for the
"old" client port, and clean connection establishment/exchange for
the new client port.
2. At the end of step 1, restart rds srever on node2, and start client on
node1, make sure using tcpdump, 'netstat -an|grep 16385' that
packets flow correctly.
3. start RDS client/server application on two participating nodes, and
repeat steps 1 and 2, but this time, simulate node failure by doing
"ifconfig <intf> down", so no FIN is sent.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
net/rds: RDS-TCP: only initiate reconnect attempt on outgoing TCP socket.
When the peer of an RDS-TCP connection restarts, a reconnect
attempt should only be made from the active side of the TCP
connection, i.e. the side that has a transient TCP port
number. Do not add the passive side of the TCP connection
to the c_hash_node and thus avoid triggering rds_queue_reconnect()
for passive rds connections.
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
net/rds: RDS-TCP: Always create a new rds_sock for an incoming connection.
When running RDS over TCP, the active (client) side connects to the
listening ("passive") side at the RDS_TCP_PORT. After the connection
is established, if the client side reboots (potentially without even
sending a FIN) the server still has a TCP socket in the esablished
state. If the server-side now gets a new SYN comes from the client
with a different client port, TCP will create a new socket-pair, but
the RDS layer will incorrectly pull up the old rds_connection (which
is still associated with the stale t_sock and RDS socket state).
This patch corrects this behavior by having rds_tcp_accept_one()
always create a new connection for an incoming TCP SYN.
The rds and tcp state associated with the old socket-pair is cleaned
up via the rds_tcp_state_change() callback which would typically be
invoked in most cases when the client-TCP sends a FIN on TCP restart,
triggering a transition to CLOSE_WAIT state. In the rarer event of client
death without a FIN, TCP_KEEPALIVE probes on the socket will detect
the stale socket, and the TCP transition to CLOSE state will trigger
the RDS state cleanup.
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
projects / mirror_ubuntu-kernels.git / log