The new netlink API is no longer "v2" but rather the standard API and
the legacy API is now "nl compat". We split them into separate
start/stop and put them in different files in order to further
distinguish them.
Signed-off-by: NRichard Alpe <richard.alpe@ericsson.com>
Reviewed-by: NErik Hugne <erik.hugne@ericsson.com>
Reviewed-by: NYing Xue <ying.xue@windriver.com>
Reviewed-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Make sure root user does not try something stupid.

Also make sure mask field in struct rps_sock_flow_table
does not share a cache line with the potentially often dirtied
flow table.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Fixes: 567e4b79 ("net: rfs: add hash collision detection")
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Receive Flow Steering is a nice solution but suffers from
hash collisions when a mix of connected and unconnected traffic
is received on the host, when flow hash table is populated.

Also, clearing flow in inet_release() makes RFS not very good
for short lived flows, as many packets can follow close().
(FIN , ACK packets, ...)

This patch extends the information stored into global hash table
to not only include cpu number, but upper part of the hash value.

I use a 32bit value, and dynamically split it in two parts.

For host with less than 64 possible cpus, this gives 6 bits for the
cpu number, and 26 (32-6) bits for the upper part of the hash.

Since hash bucket selection use low order bits of the hash, we have
a full hash match, if /proc/sys/net/core/rps_sock_flow_entries is big
enough.

If the hash found in flow table does not match, we fallback to RPS (if
it is enabled for the rxqueue).

This means that a packet for an non connected flow can avoid the
IPI through a unrelated/victim CPU.

This also means we no longer have to clear the table at socket
close time, and this helps short lived flows performance.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Acked-by: NTom Herbert <therbert@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

encap.sport and encap.dport are __be16, use nla_{get,put}_be16 instead
of nla_{get,put}_u16.

Fixes the sparse warnings:

warning: incorrect type in assignment (different base types)
   expected restricted __be32 [addressable] [usertype] o_key
   got restricted __be16 [addressable] [usertype] i_flags
warning: incorrect type in assignment (different base types)
   expected restricted __be16 [usertype] sport
   got unsigned short
warning: incorrect type in assignment (different base types)
   expected restricted __be16 [usertype] dport
   got unsigned short
warning: incorrect type in argument 3 (different base types)
   expected unsigned short [unsigned] [usertype] value
   got restricted __be16 [usertype] sport
warning: incorrect type in argument 3 (different base types)
   expected unsigned short [unsigned] [usertype] value
   got restricted __be16 [usertype] dport
Signed-off-by: NSabrina Dubroca <sd@queasysnail.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In commit c637c103 ("tipc: resolve race
problem at unicast message reception") we introduced a time limit
for how long the function tipc_sk_eneque() would be allowed to execute
its loop. Unfortunately, the test for when this limit is passed was put
in the wrong place, resulting in a lost message when the test is true.

We fix this by moving the test to before we dequeue the next buffer
from the input queue.
Signed-off-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

rt6_probe allocates a struct __rt6_probe_work and schedules a work handler rt6_probe_deferred.
But rt6_probe_deferred kfree's the struct work_struct instead of struct __rt6_probe_work.
This works, because struct work_struct is the first element of struct __rt6_probe_work.

Change it to kfree struct __rt6_probe_work to not implicitly depend on
struct work_struct being the first element.

This does not affect the generated code.
Signed-off-by: NMichael Buesch <m@bues.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Ensure that in state FIN_WAIT2 or TIME_WAIT, where the connection is
represented by a tcp_timewait_sock, we rate limit dupacks in response
to incoming packets (a) with TCP timestamps that fail PAWS checks, or
(b) with sequence numbers that are out of the acceptable window.

We do not send a dupack in response to out-of-window packets if it has
been less than sysctl_tcp_invalid_ratelimit (default 500ms) since we
last sent a dupack in response to an out-of-window packet.
Reported-by: NAvery Fay <avery@mixpanel.com>
Signed-off-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NYuchung Cheng <ycheng@google.com>
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Ensure that in state ESTABLISHED, where the connection is represented
by a tcp_sock, we rate limit dupacks in response to incoming packets
(a) with TCP timestamps that fail PAWS checks, or (b) with sequence
numbers or ACK numbers that are out of the acceptable window.

We do not send a dupack in response to out-of-window packets if it has
been less than sysctl_tcp_invalid_ratelimit (default 500ms) since we
last sent a dupack in response to an out-of-window packet.

There is already a similar (although global) rate-limiting mechanism
for "challenge ACKs". When deciding whether to send a challence ACK,
we first consult the new per-connection rate limit, and then the
global rate limit.
Reported-by: NAvery Fay <avery@mixpanel.com>
Signed-off-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NYuchung Cheng <ycheng@google.com>
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In the SYN_RECV state, where the TCP connection is represented by
tcp_request_sock, we now rate-limit SYNACKs in response to a client's
retransmitted SYNs: we do not send a SYNACK in response to client SYN
if it has been less than sysctl_tcp_invalid_ratelimit (default 500ms)
since we last sent a SYNACK in response to a client's retransmitted
SYN.

This allows the vast majority of legitimate client connections to
proceed unimpeded, even for the most aggressive platforms, iOS and
MacOS, which actually retransmit SYNs 1-second intervals for several
times in a row. They use SYN RTO timeouts following the progression:
1,1,1,1,1,2,4,8,16,32.
Reported-by: NAvery Fay <avery@mixpanel.com>
Signed-off-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NYuchung Cheng <ycheng@google.com>
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Helpers for mitigating ACK loops by rate-limiting dupacks sent in
response to incoming out-of-window packets.

This patch includes:

- rate-limiting logic
- sysctl to control how often we allow dupacks to out-of-window packets
- SNMP counter for cases where we rate-limited our dupack sending

The rate-limiting logic in this patch decides to not send dupacks in
response to out-of-window segments if (a) they are SYNs or pure ACKs
and (b) the remote endpoint is sending them faster than the configured
rate limit.

We rate-limit our responses rather than blocking them entirely or
resetting the connection, because legitimate connections can rely on
dupacks in response to some out-of-window segments. For example, zero
window probes are typically sent with a sequence number that is below
the current window, and ZWPs thus expect to thus elicit a dupack in
response.

We allow dupacks in response to TCP segments with data, because these
may be spurious retransmissions for which the remote endpoint wants to
receive DSACKs. This is safe because segments with data can't
realistically be part of ACK loops, which by their nature consist of
each side sending pure/data-less ACKs to each other.

The dupack interval is controlled by a new sysctl knob,
tcp_invalid_ratelimit, given in milliseconds, in case an administrator
needs to dial this upward in the face of a high-rate DoS attack. The
name and units are chosen to be analogous to the existing analogous
knob for ICMP, icmp_ratelimit.

The default value for tcp_invalid_ratelimit is 500ms, which allows at
most one such dupack per 500ms. This is chosen to be 2x faster than
the 1-second minimum RTO interval allowed by RFC 6298 (section 2, rule
2.4). We allow the extra 2x factor because network delay variations
can cause packets sent at 1 second intervals to be compressed and
arrive much closer.
Reported-by: NAvery Fay <avery@mixpanel.com>
Signed-off-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NYuchung Cheng <ycheng@google.com>
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Flow alloc needs to initialize unmasked key pointer. Otherwise
it can crash kernel trying to free random unmasked-key pointer.

general protection fault: 0000 [#1] SMP
3.19.0-rc6-net-next+ #457
Hardware name: Supermicro X7DWU/X7DWU, BIOS  1.1 04/30/2008
RIP: 0010:[<ffffffff8111df0e>] [<ffffffff8111df0e>] kfree+0xac/0x196
Call Trace:
 [<ffffffffa060bd87>] flow_free+0x21/0x59 [openvswitch]
 [<ffffffffa060bde0>] ovs_flow_free+0x21/0x23 [openvswitch]
 [<ffffffffa0605b4a>] ovs_packet_cmd_execute+0x2f3/0x35f [openvswitch]
 [<ffffffffa0605995>] ? ovs_packet_cmd_execute+0x13e/0x35f [openvswitch]
 [<ffffffff811fe6fb>] ? nla_parse+0x4f/0xec
 [<ffffffff8139a2fc>] genl_family_rcv_msg+0x26d/0x2c9
 [<ffffffff8107620f>] ? __lock_acquire+0x90e/0x9aa
 [<ffffffff8139a3be>] genl_rcv_msg+0x66/0x89
 [<ffffffff8139a358>] ? genl_family_rcv_msg+0x2c9/0x2c9
 [<ffffffff81399591>] netlink_rcv_skb+0x3e/0x95
 [<ffffffff81399898>] ? genl_rcv+0x18/0x37
 [<ffffffff813998a7>] genl_rcv+0x27/0x37
 [<ffffffff81399033>] netlink_unicast+0x103/0x191
 [<ffffffff81399382>] netlink_sendmsg+0x2c1/0x310
 [<ffffffff811007ad>] ? might_fault+0x50/0xa0
 [<ffffffff8135c773>] do_sock_sendmsg+0x5f/0x7a
 [<ffffffff8135c799>] sock_sendmsg+0xb/0xd
 [<ffffffff8135cacf>] ___sys_sendmsg+0x1a3/0x218
 [<ffffffff8113e54b>] ? get_close_on_exec+0x86/0x86
 [<ffffffff8115a9d0>] ? fsnotify+0x32c/0x348
 [<ffffffff8115a720>] ? fsnotify+0x7c/0x348
 [<ffffffff8113e5f5>] ? __fget+0xaa/0xbf
 [<ffffffff8113e54b>] ? get_close_on_exec+0x86/0x86
 [<ffffffff8135cccd>] __sys_sendmsg+0x3d/0x5e
 [<ffffffff8135cd02>] SyS_sendmsg+0x14/0x16
 [<ffffffff81411852>] system_call_fastpath+0x12/0x17

Fixes: 74ed7ab9("openvswitch: Add support for unique flow IDs.")
CC: Joe Stringer <joestringer@nicira.com>
Reported-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NPravin B Shelar <pshelar@nicira.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch fixes a missing bridge port check caught by smatch.

setlink/dellink of attributes like vlans can come for a bridge device
and there is no need to offload those today. So, this patch adds a bridge
port check. (In these cases however, the BRIDGE_SELF flags will always be set
and we may not hit a problem with the current code).

smatch complaint:

The patch 68e331c7: "bridge: offload bridge port attributes to
switch asic if feature flag set" from Jan 29, 2015, leads to the
following Smatch complaint:

net/bridge/br_netlink.c:552 br_setlink()
	 error: we previously assumed 'p' could be null (see line 518)

net/bridge/br_netlink.c
   517
   518		if (p && protinfo) {
                    ^
Check for NULL.
Reported-By: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NRoopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Commit 083735f4 ("rds: switch rds_message_copy_from_user() to iov_iter")
breaks rds_message_copy_from_user() semantics on success, and causes it
to return nbytes copied, when it should return 0.  This commit fixes that bug.
Signed-off-by: NSowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The macro rdsdebug is defined as

  pr_debug("%s(): " fmt, __func__ , ##args)

Hence it doesn't make sense to include the name of the calling
function explicitly in the format string passed to rdsdebug.
Signed-off-by: NRasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

OVS userspace already probes the openvswitch kernel module for
OVS_ACTION_ATTR_SET_MASKED support.  This patch adds the kernel module
implementation of masked set actions.

The existing set action sets many fields at once.  When only a subset
of the IP header fields, for example, should be modified, all the IP
fields need to be exact matched so that the other field values can be
copied to the set action.  A masked set action allows modification of
an arbitrary subset of the supported header bits without requiring the
rest to be matched.

Masked set action is now supported for all writeable key types, except
for the tunnel key.  The set tunnel action is an exception as any
input tunnel info is cleared before action processing starts, so there
is no tunnel info to mask.

The kernel module converts all (non-tunnel) set actions to masked set
actions.  This makes action processing more uniform, and results in
less branching and duplicating the action processing code.  When
returning actions to userspace, the fully masked set actions are
converted back to normal set actions.  We use a kernel internal action
code to be able to tell the userspace provided and converted masked
set actions apart.
Signed-off-by: NJarno Rajahalme <jrajahalme@nicira.com>
Acked-by: NPravin B Shelar <pshelar@nicira.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In a previous commit in this series we resolved a race problem during
unicast message reception.

Here, we resolve the same problem at multicast reception. We apply the
same technique: an input queue serializing the delivery of arriving
buffers. The main difference is that here we do it in two steps.
First, the broadcast link feeds arriving buffers into the tail of an
arrival queue, which head is consumed at the socket level, and where
destination lookup is performed. Second, if the lookup is successful,
the resulting buffer clones are fed into a second queue, the input
queue. This queue is consumed at reception in the socket just like
in the unicast case. Both queues are protected by the same lock, -the
one of the input queue.
Reviewed-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The structure 'tipc_port_list' is used to collect port numbers
representing multicast destination socket on a receiving node.
The list is not based on a standard linked list, and is in reality
optimized for the uncommon case that there are more than one
multicast destinations per node. This makes the list handling
unecessarily complex, and as a consequence, even the socket
multicast reception becomes more complex.

In this commit, we replace 'tipc_port_list' with a new 'struct
tipc_plist', which is based on a standard list. We give the new
list stack (push/pop) semantics, someting that simplifies
the implementation of the function tipc_sk_mcast_rcv().
Reviewed-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The new input message queue in struct tipc_link can be used for
delivering connection abort messages to subscribing sockets. This
makes it possible to simplify the code for such cases.

This commit removes the temporary list in tipc_node_unlock()
used for transforming abort subscriptions to messages. Instead, the
abort messages are now created at the moment of lost contact, and
then added to the last failed link's generic input queue for delivery
to the sockets concerned.
Reviewed-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

TIPC handles message cardinality and sequencing at the link layer,
before passing messages upwards to the destination sockets. During the
upcall from link to socket no locks are held. It is therefore possible,
and we see it happen occasionally, that messages arriving in different
threads and delivered in sequence still bypass each other before they
reach the destination socket. This must not happen, since it violates
the sequentiality guarantee.

We solve this by adding a new input buffer queue to the link structure.
Arriving messages are added safely to the tail of that queue by the
link, while the head of the queue is consumed, also safely, by the
receiving socket. Sequentiality is secured per socket by only allowing
buffers to be dequeued inside the socket lock. Since there may be multiple
simultaneous readers of the queue, we use a 'filter' parameter to reduce
the risk that they peek the same buffer from the queue, hence also
reducing the risk of contention on the receiving socket locks.

This solves the sequentiality problem, and seems to cause no measurable
performance degradation.

A nice side effect of this change is that lock handling in the functions
tipc_rcv() and tipc_bcast_rcv() now becomes uniform, something that
will enable future simplifications of those functions.
Reviewed-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The list for outgoing traffic buffers from a socket is currently
allocated on the stack. This forces us to initialize the queue for
each sent message, something costing extra CPU cycles in the most
critical data path. Later in this series we will introduce a new
safe input buffer queue, something that would force us to initialize
even the spinlock of the outgoing queue. A closer analysis reveals
that the queue always is filled and emptied within the same lock_sock()
session. It is therefore safe to use a queue aggregated in the socket
itself for this purpose. Since there already exists a queue for this
in struct sock, sk_write_queue, we introduce use of that queue in
this commit.
Reviewed-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The function tipc_msg_eval() is in reality doing two related, but
different tasks. First it tries to find a new destination for named
messages, in case there was no first lookup, or if the first lookup
failed. Second, it does what its name suggests, evaluating the validity
of the message and its destination, and returning an appropriate error
code depending on the result.

This is confusing, and in this commit we choose to break it up into two
functions. A new function, tipc_msg_lookup_dest(), first attempts to find
a new destination, if the message is of the right type. If this lookup
fails, or if the message should not be subject to a second lookup, the
already existing tipc_msg_reverse() is called. This function performs
prepares the message for rejection, if applicable.
Reviewed-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The code for enqueuing arriving buffers in the function tipc_sk_rcv()
contains long code lines and currently goes to two indentation levels.
As a cosmetic preparaton for the next commits, we break it out into
a separate function.
Reviewed-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Despite recent improvements, the handling of error codes and return
values at reception of messages in the socket layer is still confusing.

In this commit, we try to make it more comprehensible. First, we
separate between the return values coming from the functions called
by tipc_sk_rcv(), -those are TIPC specific error codes, and the
return values returned by tipc_sk_rcv() itself. Second, we don't
use the returned TIPC error code as indication for whether a buffer
should be forwarded/rejected or not; instead we use the buffer pointer
passed along with filter_msg(). This separation is necessary because
we sometimes want to forward messages even when there is no error
(i.e., protocol messages and successfully secondary looked up data
messages).
Reviewed-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The most common usage of namespace information is when we fetch the
own node addess from the net structure. This leads to a lot of
passing around of a parameter of type 'struct net *' between
functions just to make them able to obtain this address.

However, in many cases this is unnecessary. The own node address
is readily available as a member of both struct tipc_sock and
tipc_link, and can be fetched from there instead.
The fact that the vast majority of functions in socket.c and link.c
anyway are maintaining a pointer to their respective base structures
makes this option even more compelling.

In this commit, we introduce the inline functions tsk_own_node()
and link_own_node() to make it easy for functions to fetch the node
address from those structs instead of having to pass along and
dereference the namespace struct.

In particular, we make calls to the msg_xx() functions in msg.{h,c}
context independent by directly passing them the own node address
as parameter when needed. Those functions should be regarded as
leaves in the code dependency tree, and it is hence desirable to
keep them namspace unaware.

Apart from a potential positive effect on cache behavior, these
changes make it easier to introduce the changes that will follow
later in this series.
Reviewed-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fixes following sparse warnings :

net/ipv6/sit.c:1509:32: warning: incorrect type in assignment (different base types)
net/ipv6/sit.c:1509:32:    expected restricted __be16 [usertype] sport
net/ipv6/sit.c:1509:32:    got unsigned short
net/ipv6/sit.c:1514:32: warning: incorrect type in assignment (different base types)
net/ipv6/sit.c:1514:32:    expected restricted __be16 [usertype] dport
net/ipv6/sit.c:1514:32:    got unsigned short
net/ipv6/sit.c:1711:38: warning: incorrect type in argument 3 (different base types)
net/ipv6/sit.c:1711:38:    expected unsigned short [unsigned] [usertype] value
net/ipv6/sit.c:1711:38:    got restricted __be16 [usertype] sport
net/ipv6/sit.c:1713:38: warning: incorrect type in argument 3 (different base types)
net/ipv6/sit.c:1713:38:    expected unsigned short [unsigned] [usertype] value
net/ipv6/sit.c:1713:38:    got restricted __be16 [usertype] dport
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

netdev_adjacent_add_links() and netdev_adjacent_del_links()
are static.

queue->qdisc has __rcu annotation, need to use RCU_INIT_POINTER()
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

info is in network byte order, change it back to host byte order
before use. In particular, the current code sets the MTU of the tunnel
to a wrong (too big) value.

Fixes: c12b395a ("gre: Support GRE over IPv6")
Signed-off-by: NSabrina Dubroca <sd@queasysnail.net>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Revert "bridge: Let bridge not age 'externally' learnt FDB entries, they are removed when 'external' entity notifies the aging"

This reverts commit 9a05dde5.

Requested by Scott Feldman.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

FQ has a fast path for skb attached to a socket, as it does not
have to compute a flow hash. But for other packets, FQ being non
stochastic means that hosts exposed to random Internet traffic
can allocate million of flows structure (104 bytes each) pretty
easily. Not only host can OOM, but lookup in RB trees can take
too much cpu and memory resources.

This patch adds a new attribute, orphan_mask, that is adding
possibility of having a stochastic hash for orphaned skb.

Its default value is 1024 slots, to mimic SFQ behavior.

Note: This does not apply to locally generated TCP traffic,
and no locally generated traffic will share a flow structure
with another perfect or stochastic flow.

This patch also handles the specific case of SYNACK messages:

They are attached to the listener socket, and therefore all map
to a single hash bucket. If listener have set SO_MAX_PACING_RATE,
hoping to have new accepted socket inherit this rate, SYNACK
might be paced and even dropped.

This is very similar to an internal patch Google have used more
than one year.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When we added pacing to TCP, we decided to let sch_fq take care
of actual pacing.

All TCP had to do was to compute sk->pacing_rate using simple formula:

sk->pacing_rate = 2 * cwnd * mss / rtt

It works well for senders (bulk flows), but not very well for receivers
or even RPC :

cwnd on the receiver can be less than 10, rtt can be around 100ms, so we
can end up pacing ACK packets, slowing down the sender.

Really, only the sender should pace, according to its own logic.

Instead of adding a new bit in skb, or call yet another flow
dissection, we tweak skb->truesize to a small value (2), and
we instruct sch_fq to use new helper and not pace pure ack.

Note this also helps TCP small queue, as ack packets present
in qdisc/NIC do not prevent sending a data packet (RPC workload)

This helps to reduce tx completion overhead, ack packets can use regular
sock_wfree() instead of tcp_wfree() which is a bit more expensive.

This has no impact in the case packets are sent to loopback interface,
as we do not coalesce ack packets (were we would detect skb->truesize
lie)

In case netem (with a delay) is used, skb_orphan_partial() also sets
skb->truesize to 1.

This patch is a combination of two patches we used for about one year at
Google.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch gets rid of the manual rhashtable walk in nft_hash
which touches rhashtable internals that should not be exposed.
It does so by using the rhashtable iterator primitives.

Note that I'm leaving nft_hash_destroy alone since it's only
invoked on shutdown and it shouldn't be affected by changes
to rhashtable internals (or at least not what I'm planning to
change).
Signed-off-by: NHerbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch gets rid of the manual rhashtable walk in netlink
which touches rhashtable internals that should not be exposed.
It does so by using the rhashtable iterator primitives.

In fact the existing code was very buggy.  Some sockets weren't
shown at all while others were shown more than once.
Signed-off-by: NHerbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In tcf_exts_dump_stats(), ensure that exts->actions is not empty before
accessing the first element of that list and calling tcf_action_copy_stats()
on it.  This fixes some random segvs when adding filters of type "basic" with
no particular action.

This also fixes the dumping of those "no-action" filters, which more often
than not made calls to tcf_action_copy_stats() fail and consequently netlink
attributes added by the caller to be removed by a call to nla_nest_cancel().

Fixes: 33be6271 ("net_sched: act: use standard struct list_head")
Signed-off-by: NIgnacy Gawędzki <ignacy.gawedzki@green-communications.fr>
Acked-by: NCong Wang <cwang@twopensource.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Configuring fq with quantum 0 hangs the system, presumably because of a
non-interruptible infinite loop. Either way quantum 0 does not make sense.

Reproduce with:
sudo tc qdisc add dev lo root fq quantum 0 initial_quantum 0
ping 127.0.0.1
Signed-off-by: NKenneth Klette Jonassen <kennetkl@ifi.uio.no>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add event which provides an indication on a change in the state
of a bonding slave. The event handler should cast the pointer to the
appropriate type (struct netdev_bonding_info) in order to get the
full info about the slave.
Signed-off-by: NMoni Shoua <monis@mellanox.com>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When a new link instance is created, it is trigged to start by
sending it a TIPC_STARTING_EVT, whereafter a regular link
reset is applied to it.

The starting event is codewise treated as a timeout event, and prompts
a link RESET message to be sent to the peer node, carrying a link
session identifier. The later link_reset() call nudges this session
identifier, whereafter all subsequent RESET messages will be sent out
with the new identifier. The latter session number overrides the former,
causing the peer to unconditionally accept it irrespective of its
current working state.

We don't think that this causes any problem, but it is not in accordance
with the protocol spec, and may cause confusion when debugging TIPC
sessions.

To avoid this, we make the starting event distinct from the
subsequent timeout events, by not allowing the former to send
out any RESET message. This eliminates the described problem.
Reviewed-by: NErik Hugne <erik.hugne@ericsson.com>
Reviewed-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Instances of struct node are created in the function tipc_disc_rcv()
under the assumption that there is no race between received discovery
messages arriving from the same node. This assumption is wrong.
When we use more than one bearer, it is possible that discovery
messages from the same node arrive at the same moment, resulting in
creation of two instances of struct tipc_node. This may later cause
confusion during link establishment, and may result in one of the links
never becoming activated.

We fix this by making lookup and potential creation of nodes atomic.
Instead of first looking up the node, and in case of failure, create it,
we now start with looking up the node inside node_link_create(), and
return a reference to that one if found. Otherwise, we go ahead and
create the node as we did before.
Reviewed-by: NErik Hugne <erik.hugne@ericsson.com>
Reviewed-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

During link failover it may happen that the remaining link goes
down while it is still in the process of taking over traffic
from a previously failed link. When this happens, we currently
abort the failover procedure and reset the first failed link to
non-failover mode, so that it will be ready to re-establish
contact with its peer when it comes available.

However, if the first link goes down because its bearer was manually
disabled, it is not enough to reset it; it must also be deleted;
which is supposed to happen when the failover procedure is finished.
Otherwise it will remain a zombie link: attached to the owner node
structure, in mode LINK_STOPPED, and permanently blocking any re-
establishing of the link to the peer via the interface in question.

We fix this by amending the failover abort procedure. Apart from
resetting the link to non-failover state, we test if the link is
also in LINK_STOPPED mode. If so, we delete it, using the conditional
tipc_link_delete() function introduced in the previous commit.
Reviewed-by: NErik Hugne <erik.hugne@ericsson.com>
Reviewed-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When a bearer is disabled, all pertaining links will be reset and
deleted. However, if there is a second active link towards a killed
link's destination, the delete has to be postponed until the failover
is finished. During this interval, we currently put the link in zombie
mode, i.e., we take it out of traffic, delete its timer, but leave it
attached to the owner node structure until all missing packets have
been received.  When this is done, we detach the link from its node
and delete it, assuming that the synchronous timer deletion that was
initiated earlier in a different thread has finished.

This is unsafe, as the failover may finish before del_timer_sync()
has returned in the other thread.

We fix this by adding an atomic reference counter of type kref in
struct tipc_link. The counter keeps track of the references kept
to the link by the owner node and the timer. We then do a conditional
delete, based on the reference counter, both after the failover has
been finished and when the timer expires, if applicable. Whoever
comes last, will actually delete the link. This approach also implies
that we can make the deletion of the timer asynchronous.
Reviewed-by: NErik Hugne <erik.hugne@ericsson.com>
Reviewed-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Max unacked packets/bytes is an int while sizeof(long) was used in the
sysctl table.

This means that when they were getting read we'd also leak kernel memory
to userspace along with the timeout values.
Signed-off-by: NSasha Levin <sasha.levin@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>