Add support for mirroring before the CT action by spliting the pre ct rule.
Mirror outputs are done first on the tc chain,prio table rule (the fwd
rule), which will then forward to a per port fwd table.
On this fwd table, we insert the original pre ct rule that forwards to
ct/ct nat table.
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Maor Dickman <maord@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

Multiple commands can be printed at the same time which can
lead to wrong order of their lines in dmesg output.
As a result, it's hard to match data dumps to the correct command
or which command was fully dumped at some point.

Fix this by displaying the corresponding command index, and also
indicate when a command was fully dumped.
Signed-off-by: Alaa Hleihel <alaa@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

Increasing the size of the indirection_rqt array from 128 to 256 bytes
pushed the stack usage of the mlx5e_hairpin_fill_rqt_rqns() function
over the warning limit when building with clang and CONFIG_KASAN:

drivers/net/ethernet/mellanox/mlx5/core/en_tc.c:970:1: error: stack frame size of 1180 bytes in function 'mlx5e_tc_add_nic_flow' [-Werror,-Wframe-larger-than=]

Using dynamic allocation here is safe because the caller does the
same, and it reduces the stack usage of the function to just a few
bytes.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

Dump the ICOSQ's WQE descriptor when a completion with error is received.
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

Commit e20f0dbf ("net/mlx5e: RX, Add a prefetch command for small
L1_CACHE_BYTES") switched to using net_prefetchw at all places in mlx5e.
In the same time frame, commit 5af75c74 ("net/mlx5e: Enhanced TX
MPWQE for SKBs") added one more usage of prefetchw. When these two
changes were merged, this new occurrence of prefetchw wasn't replaced
with net_prefetchw.

This commit fixes this last occurrence of prefetchw in
mlx5e_tx_mpwqe_session_start, making the same change that was done in
mlx5e_xdp_mpwqe_session_start.
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

Fix the following coccicheck warnings:

drivers/net/ethernet/mellanox/mlx5/core/devlink.c:145:29-66: WARNING
avoid newline at end of message in NL_SET_ERR_MSG_MOD
drivers/net/ethernet/mellanox/mlx5/core/devlink.c:140:29-77: WARNING
avoid newline at end of message in NL_SET_ERR_MSG_MOD
Signed-off-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

Read congestion counters from all ports in any lag mode rather than
only in RoCE lag mode (e.g., VF lag).
Signed-off-by: Mark Zhang <markzhang@nvidia.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

Fix the following coccicheck warnings:

./drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c:495:2-3: Unneeded
semicolon.
Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Signed-off-by: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

It is allocated with kvzalloc(), the corresponding release function
should not be kfree(), use kvfree() instead.

Generated by: scripts/coccinelle/api/kfree_mismatch.cocci
Signed-off-by: Junlin Yang <yangjunlin@yulong.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

The field source_eswitch_owner_vhca_id was not consumed
in the same way as in STEv0. Added the missing set.

Fixes: 10b69418 ("net/mlx5: DR, Add HW STEv1 match logic")
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

Remove the dr_ste_v1_set_rx_decap_l3 function that was
replaced by another function - fixing a rebase error.
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

"reforamt" -> "reformat"
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

"either" is outside the parentheses, so the matching "or" should be too.
Signed-off-by: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>

Eric Dumazet says:

====================
tcp: better deal with delayed TX completions

Jakub and Neil reported an increase of RTO timers whenever
TX completions are delayed a bit more (by increasing
NIC TX coalescing parameters)

While problems have been there forever, second patch might
introduce some regressions so I prefer not backport
them to stable releases before things settle.

Many thanks to FB team for their help and tests.

Few packetdrill tests need to be changed to reflect
the improvements brought by this series.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

TSQ provides a nice way to avoid bufferbloat on individual socket,
including retransmit packets. We can get rid of the old
heuristic:

	/* Do not sent more than we queued. 1/4 is reserved for possible
	 * copying overhead: fragmentation, tunneling, mangling etc.
	 */
	if (refcount_read(&sk->sk_wmem_alloc) >
	    min_t(u32, sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2),
		  sk->sk_sndbuf))
		return -EAGAIN;

This heuristic was giving false positives according to Jakub,
whenever TX completions are delayed above RTT. (Ack packets
are processed by TCP stack before clones are orphaned/freed)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Jakub Kicinski <kuba@kernel.org>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Jakub reported Data included in a Fastopen SYN that had to be
retransmit would have to wait for an RTO if TX completions are slow,
even with prior fix.

This is because tcp_rcv_fastopen_synack() does not use standard
rtx logic, meaning TSQ handler exits early in tcp_tsq_write()
because tp->lost_out == tp->retrans_out

Lets make tcp_rcv_fastopen_synack() use standard rtx logic,
by using tcp_mark_skb_lost() on the skb thats needs to be
sent again.

Not this raised a warning in tcp_fastretrans_alert() during my tests
since we consider the data not being aknowledged
by the receiver does not mean packet was lost on the network.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Jakub Kicinski <kuba@kernel.org>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Jakub and Neil reported an increase of RTO timers whenever
TX completions are delayed a bit more (by increasing
NIC TX coalescing parameters)

Main issue is that TCP stack has a logic preventing a packet
being retransmit if the prior clone has not yet been
orphaned or freed.

This logic came with commit 1f3279ae ("tcp: avoid
retransmits of TCP packets hanging in host queues")

Thankfully, in the case skb_still_in_host_queue() detects
the initial clone is still in flight, it can use TSQ logic
that will eventually retry later, at the moment the clone
is freed or orphaned.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Neil Spring <ntspring@fb.com>
Reported-by: Jakub Kicinski <kuba@kernel.org>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

fix some coding style issues in the isdn header
Signed-off-by: Tong Zhang <ztong0001@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch fixes the following warning from sparse:

net/tipc/monitor.c:263:35: warning: incorrect type in assignment (different base types)
net/tipc/monitor.c:263:35:    expected unsigned int
net/tipc/monitor.c:263:35:    got restricted __be32 [usertype]
[...]
net/tipc/node.c:374:13: warning: context imbalance in 'tipc_node_read_lock' - wrong count at exit
net/tipc/node.c:379:13: warning: context imbalance in 'tipc_node_read_unlock' - unexpected unlock
net/tipc/node.c:384:13: warning: context imbalance in 'tipc_node_write_lock' - wrong count at exit
net/tipc/node.c:389:13: warning: context imbalance in 'tipc_node_write_unlock_fast' - unexpected unlock
net/tipc/node.c:404:17: warning: context imbalance in 'tipc_node_write_unlock' - unexpected unlock
[...]
net/tipc/crypto.c:1201:9: warning: incorrect type in initializer (different address spaces)
net/tipc/crypto.c:1201:9:    expected struct tipc_aead [noderef] __rcu *__tmp
net/tipc/crypto.c:1201:9:    got struct tipc_aead *
[...]
Acked-by: Jon Maloy <jmaloy@redhat.com>
Signed-off-by: Hoang Huu Le <hoang.h.le@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

(struct tipc_link_info)->dest is in network order (__be32), so we must
convert the value to network order before assigning. The problem detected
by sparse:

net/tipc/netlink_compat.c:699:24: warning: incorrect type in assignment (different base types)
net/tipc/netlink_compat.c:699:24:    expected restricted __be32 [usertype] dest
net/tipc/netlink_compat.c:699:24:    got int
Acked-by: Jon Maloy <jmaloy@redhat.com>
Signed-off-by: Hoang Le <hoang.h.le@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

Ido Schimmel says:

====================
mlxsw: Implement sampling using mirroring

So far, sampling was implemented using a dedicated sampling mechanism
that is available on all Spectrum ASICs. Spectrum-2 and later ASICs
support sampling by mirroring packets to the CPU port with probability.
This method has a couple of advantages compared to the legacy method:

* Extra metadata per-packet: Egress port, egress traffic class, traffic
  class occupancy and end-to-end latency
* Ability to sample packets on egress / per-flow as opposed to only
  ingress

This series should not result in any user-visible changes and its aim is
to convert Spectrum-2 and later ASICs to perform sampling by mirroring
to the CPU port with probability. Future submissions will expose the
additional metadata and enable sampling using more triggers (e.g.,
egress).

Series overview:

Patches #1-#3 extend the SPAN (mirroring) module to accept new
parameters required for sampling. See individual commit messages for
detailed explanation.

Patch #4-#5 split sampling support between Spectrum-1 and later ASIC while
still using the legacy method for all ASIC generations.

Patch #6 converts Spectrum-2 and later ASICs to perform sampling by
mirroring to the CPU port with probability.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Spectrum-2 and later ASICs support sampling of packets by mirroring to
the CPU with probability. There are several advantages compared to the
legacy dedicated sampling mechanism:

* Extra metadata per-packet: Egress port, egress traffic class, traffic
  class occupancy and end-to-end latency
* Ability to sample packets on egress / per-flow

Convert Spectrum-2 and later ASICs to perform sampling by mirroring to
the CPU with probability.

Subsequent patches will add support for egress / per-flow sampling and
expose the extra metadata.
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Sampling of ingress packets is supported using a dedicated sampling
mechanism on all Spectrum ASICs. However, Spectrum-2 and later ASICs
support more sophisticated sampling by mirroring packets to the CPU.

As a preparation for more advanced sampling configurations, split the trap
configuration used for sampled packets between Spectrum-1 and later ASICs.

This is needed since packets that are mirrored to the CPU are trapped
via a different trap identifier compared to packets that are sampled
using the dedicated sampling mechanism.
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Sampling of ingress packets is supported using a dedicated sampling
mechanism on all Spectrum ASICs. However, Spectrum-2 and later ASICs
support more sophisticated sampling by mirroring packets to the CPU.

As a preparation for more advanced sampling configurations, split the
sampling operations between Spectrum-1 and later ASICs.
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Currently, every packet that matches a mirroring trigger (e.g., received
packets, buffer dropped packets) is mirrored. Spectrum-2 and later ASICs
support mirroring with probability, where every 1 in N matched packets
is mirrored.

Extend the API that creates the binding between the trigger and the SPAN
agent with a probability rate parameter, which is an attribute of the
trigger. Set it to '1' to maintain existing behavior.

Subsequent patches will use it to perform more sophisticated sampling,
by mirroring packets to the CPU with probability.
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The MPAR and MPAGR registers are used to configure the binding between
the mirroring trigger (e.g., received packet) and the SPAN agent. Add
probability rate field, which will allow us to support sampling by
mirroring to the CPU.
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

When packets are mirrored to the CPU, the trap identifier with which the
packets are trapped is determined according to the session identifier of
the SPAN agent performing the mirroring. Packets that are trapped for
the same logical reason (e.g., buffer drops) should use the same session
identifier.

Currently, a single session is implicitly supported (identifier 0) and
is used for packets that are mirrored to the CPU due to buffer drops
(e.g., early drop).

Subsequent patches are going to mirror packets to the CPU due to
sampling, which will require a different session identifier.

Prepare for that by making the session identifier an attribute of the
SPAN agent.
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Saeed Mahameed says:

====================
This series provides some cleanups to mlx5 driver
For more information please see tag log below.

Please pull and let me know if there is any problem.

mlx5-updates-2021-03-11

Cleanups for mlx5 driver

1) Fix build warnings form Arnd and Vlad
2) Leon improves locking for driver load/unload flows
3) From Roi, Lockdep false dependency warning
4) Other trivial cleanups
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Petr Machata says:

====================
nexthop: Resilient next-hop groups

At this moment, there is only one type of next-hop group: an mpath group.
Mpath groups implement the hash-threshold algorithm, described in RFC
2992[1].

To select a next hop, hash-threshold algorithm first assigns a range of
hashes to each next hop in the group, and then selects the next hop by
comparing the SKB hash with the individual ranges. When a next hop is
removed from the group, the ranges are recomputed, which leads to
reassignment of parts of hash space from one next hop to another. RFC 2992
illustrates it thus:

             +-------+-------+-------+-------+-------+
             |   1   |   2   |   3   |   4   |   5   |
             +-------+-+-----+---+---+-----+-+-------+
             |    1    |    2    |    4    |    5    |
             +---------+---------+---------+---------+

              Before and after deletion of next hop 3
	      under the hash-threshold algorithm.

Note how next hop 2 gave up part of the hash space in favor of next hop 1,
and 4 in favor of 5. While there will usually be some overlap between the
previous and the new distribution, some traffic flows change the next hop
that they resolve to.

If a multipath group is used for load-balancing between multiple servers,
this hash space reassignment causes an issue that packets from a single
flow suddenly end up arriving at a server that does not expect them, which
may lead to TCP reset.

If a multipath group is used for load-balancing among available paths to
the same server, the issue is that different latencies and reordering along
the way causes the packets to arrive in the wrong order.

Resilient hashing is a technique to address the above problem. Resilient
next-hop group has another layer of indirection between the group itself
and its constituent next hops: a hash table. The selection algorithm uses a
straightforward modulo operation on the SKB hash to choose a hash table
bucket, then reads the next hop that this bucket contains, and forwards
traffic there.

This indirection brings an important feature. In the hash-threshold
algorithm, the range of hashes associated with a next hop must be
continuous. With a hash table, mapping between the hash table buckets and
the individual next hops is arbitrary. Therefore when a next hop is deleted
the buckets that held it are simply reassigned to other next hops:

             +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
             |1|1|1|1|2|2|2|2|3|3|3|3|4|4|4|4|5|5|5|5|
             +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
	                      v v v v
             +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
             |1|1|1|1|2|2|2|2|1|2|4|5|4|4|4|4|5|5|5|5|
             +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

              Before and after deletion of next hop 3
	      under the resilient hashing algorithm.

When weights of next hops in a group are altered, it may be possible to
choose a subset of buckets that are currently not used for forwarding
traffic, and use those to satisfy the new next-hop distribution demands,
keeping the "busy" buckets intact. This way, established flows are ideally
kept being forwarded to the same endpoints through the same paths as before
the next-hop group change.

This patch set adds the implementation of resilient next-hop groups.

In a nutshell, the algorithm works as follows. Each next hop has a number
of buckets that it wants to have, according to its weight and the number of
buckets in the hash table. In case of an event that might cause bucket
allocation change, the numbers for individual next hops are updated,
similarly to how ranges are updated for mpath group next hops. Following
that, a new "upkeep" algorithm runs, and for idle buckets that belong to a
next hop that is currently occupying more buckets than it wants (it is
"overweight"), it migrates the buckets to one of the next hops that has
fewer buckets than it wants (it is "underweight"). If, after this, there
are still underweight next hops, another upkeep run is scheduled to a
future time.

Chances are there are not enough "idle" buckets to satisfy the new demands.
The algorithm has knobs to select both what it means for a bucket to be
idle, and for whether and when to forcefully migrate buckets if there keeps
being an insufficient number of idle ones.

To illustrate the usage, consider the following commands:

 # ip nexthop add id 1 via 192.0.2.2 dev dummy1
 # ip nexthop add id 2 via 192.0.2.3 dev dummy1
 # ip nexthop add id 10 group 1/2 type resilient \
	buckets 8 idle_timer 60 unbalanced_timer 300

The last command creates a resilient next-hop group. It will have 8
buckets, each bucket will be considered idle when no traffic hits it for at
least 60 seconds, and if the table remains out of balance for 300 seconds,
it will be forcefully brought into balance.

If not present in netlink message, the idle timer defaults to 120 seconds,
and there is no unbalanced timer, meaning the group may remain unbalanced
indefinitely. The value of 120 is the default in Cumulus implementation of
resilient next-hop groups. To a degree the default is arbitrary, the only
value that certainly does not make sense is 0. Therefore going with an
existing deployed implementation is reasonable.

Unbalanced time, i.e. how long since the last time that all nexthops had as
many buckets as they should according to their weights, is reported when
the group is dumped:

 # ip nexthop show id 10
 id 10 group 1/2 type resilient buckets 8 idle_timer 60 unbalanced_timer 300 unbalanced_time 0

When replacing next hops or changing weights, if one does not specify some
parameters, their value is left as it was:

 # ip nexthop replace id 10 group 1,2/2 type resilient
 # ip nexthop show id 10
 id 10 group 1,2/2 type resilient buckets 8 idle_timer 60 unbalanced_timer 300 unbalanced_time 0

It is also possible to do a dump of individual buckets (and now you know
why there were only 8 of them in the example above):

 # ip nexthop bucket show id 10
 id 10 index 0 idle_time 5.59 nhid 1
 id 10 index 1 idle_time 5.59 nhid 1
 id 10 index 2 idle_time 8.74 nhid 2
 id 10 index 3 idle_time 8.74 nhid 2
 id 10 index 4 idle_time 8.74 nhid 1
 id 10 index 5 idle_time 8.74 nhid 1
 id 10 index 6 idle_time 8.74 nhid 1
 id 10 index 7 idle_time 8.74 nhid 1

Note the two buckets that have a shorter idle time. Those are the ones that
were migrated after the nexthop replace command to satisfy the new demand
that nexthop 1 be given 6 buckets instead of 4.

The patchset proceeds as follows:

- Patches #1 and #2 are small refactoring patches.

- Patch #3 adds a new flag to struct nh_group, is_multipath. This flag is
  meant to be set for all nexthop groups that in general have several
  nexthops from which they choose, and avoids a more expensive dispatch
  based on reading several flags, one for each nexthop group type.

- Patch #4 contains defines of new UAPI attributes and the new next-hop
  group type. At this point, the nexthop code is made to bounce the new
  type. As the resilient hashing code is gradually added in the following
  patch sets, it will remain dead. The last patch will make it accessible.

  This patch also adds a suite of new messages related to next hop buckets.
  This approach was taken instead of overloading the information on the
  existing RTM_{NEW,DEL,GET}NEXTHOP messages for the following reasons.

  First, a next-hop group can contain a large number of next-hop buckets
  (4k is not unheard of). This imposes limits on the amount of information
  that can be encoded for each next-hop bucket given a netlink message is
  limited to 64k bytes.

  Second, while RTM_NEWNEXTHOPBUCKET is only used for notifications at this
  point, in the future it can be extended to provide user space with
  control over next-hop buckets configuration.

- Patch #5 contains the meat of the resilient next-hop group support.

- Patches #6 and #7 implement support for notifications towards the
  drivers.

- Patch #8 adds an interface for the drivers to report resilient hash
  table bucket activity. Drivers will be able to report through this
  interface whether traffic is hitting a given bucket.

- Patch #9 adds an interface for the drivers to report whether a given
  hash table bucket is offloaded or trapping traffic.

- In patches #10, #11, #12 and #13, UAPI is implemented. This includes all
  the code necessary for creation of resilient groups, bucket dumping and
  getting, and bucket migration notifications.

- In patch #14 the next-hop groups are finally made available.

The overall plan is to contribute approximately the following patchsets:

1) Nexthop policy refactoring (already pushed)
2) Preparations for resilient next-hop groups (already pushed)
3) Implementation of resilient next-hop groups (this patchset)
4) Netdevsim offload plus a suite of selftests
5) Preparations for mlxsw offload of resilient next-hop groups
6) mlxsw offload including selftests

Interested parties can look at the current state of the code at [2] and
[3].

[1] https://tools.ietf.org/html/rfc2992
[2] https://github.com/idosch/linux/commits/submit/res_integ_v1
[3] https://github.com/idosch/iproute2/commits/submit/res_v1
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Now that all the code is in place, stop rejecting requests to create
resilient next-hop groups.
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Nexthop replacements et.al. are notified through netlink, but if a delayed
work migrates buckets on the background, userspace will stay oblivious.
Notify these as RTM_NEWNEXTHOPBUCKET events.
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Allow getting (but not setting) individual buckets to inspect the next hop
mapped therein, idle time, and flags.
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Add a dump handler for resilient next hop buckets. When next-hop group ID
is given, it walks buckets of that group, otherwise it walks buckets of all
groups. It then dumps the buckets whose next hops match the given filtering
criteria.
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Implement the netlink messages that allow creation and dumping of resilient
nexthop groups.
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

The kernel periodically checks the idle time of nexthop buckets to
determine if they are idle and can be re-populated with a new nexthop.

When the resilient nexthop group is offloaded to hardware, the kernel
will not see activity on nexthop buckets unless it is reported from
hardware.

Add a function that can be periodically called by device drivers to
report activity on nexthop buckets after querying it from the underlying
device.
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Add a function that can be called by device drivers to set "offload" or
"trap" indication on nexthop buckets following nexthop notifications and
other changes such as a neighbour becoming invalid.
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Implement the following notifications towards drivers:

- NEXTHOP_EVENT_REPLACE, when a resilient nexthop group is created.

- NEXTHOP_EVENT_BUCKET_REPLACE any time there is a change in assignment of
  next hops to hash table buckets. That includes replacements, deletions,
  and delayed upkeep cycles. Some bucket notifications can be vetoed by the
  driver, to make it possible to propagate bucket busy-ness flags from the
  HW back to the algorithm. Some are however forced, e.g. if a next hop is
  deleted, all buckets that use this next hop simply must be migrated,
  whether the HW wishes so or not.

- NEXTHOP_EVENT_RES_TABLE_PRE_REPLACE, before a resilient nexthop group is
  replaced. Usually the driver will get the bucket notifications as well,
  and could veto those. But in some cases, a bucket may not be migrated
  immediately, but during delayed upkeep, and that is too late to roll the
  transaction back. This notification allows the driver to take a look and
  veto the new proposed group up front, before anything is committed.
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Add data structures that will be used for in-kernel notifications about
addition / deletion of a resilient nexthop group and about changes to a
hash bucket within a resilient group.
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

At this moment, there is only one type of next-hop group: an mpath group,
which implements the hash-threshold algorithm.

To select a next hop, hash-threshold algorithm first assigns a range of
hashes to each next hop in the group, and then selects the next hop by
comparing the SKB hash with the individual ranges. When a next hop is
removed from the group, the ranges are recomputed, which leads to
reassignment of parts of hash space from one next hop to another. While
there will usually be some overlap between the previous and the new
distribution, some traffic flows change the next hop that they resolve to.
That causes problems e.g. as established TCP connections are reset, because
the traffic is forwarded to a server that is not familiar with the
connection.

Resilient hashing is a technique to address the above problem. Resilient
next-hop group has another layer of indirection between the group itself
and its constituent next hops: a hash table. The selection algorithm uses a
straightforward modulo operation to choose a hash bucket, and then reads
the next hop that this bucket contains, and forwards traffic there.

This indirection brings an important feature. In the hash-threshold
algorithm, the range of hashes associated with a next hop must be
continuous. With a hash table, mapping between the hash table buckets and
the individual next hops is arbitrary. Therefore when a next hop is deleted
the buckets that held it are simply reassigned to other next hops. When
weights of next hops in a group are altered, it may be possible to choose a
subset of buckets that are currently not used for forwarding traffic, and
use those to satisfy the new next-hop distribution demands, keeping the
"busy" buckets intact. This way, established flows are ideally kept being
forwarded to the same endpoints through the same paths as before the
next-hop group change.

In a nutshell, the algorithm works as follows. Each next hop has a number
of buckets that it wants to have, according to its weight and the number of
buckets in the hash table. In case of an event that might cause bucket
allocation change, the numbers for individual next hops are updated,
similarly to how ranges are updated for mpath group next hops. Following
that, a new "upkeep" algorithm runs, and for idle buckets that belong to a
next hop that is currently occupying more buckets than it wants (it is
"overweight"), it migrates the buckets to one of the next hops that has
fewer buckets than it wants (it is "underweight"). If, after this, there
are still underweight next hops, another upkeep run is scheduled to a
future time.

Chances are there are not enough "idle" buckets to satisfy the new demands.
The algorithm has knobs to select both what it means for a bucket to be
idle, and for whether and when to forcefully migrate buckets if there keeps
being an insufficient number of idle buckets.

There are three users of the resilient data structures.

- The forwarding code accesses them under RCU, and does not modify them
  except for updating the time a selected bucket was last used.

- Netlink code, running under RTNL, which may modify the data.

- The delayed upkeep code, which may modify the data. This runs unlocked,
  and mutual exclusion between the RTNL code and the delayed upkeep is
  maintained by canceling the delayed work synchronously before the RTNL
  code touches anything. Later it restarts the delayed work if necessary.

The RTNL code has to implement next-hop group replacement, next hop
removal, etc. For removal, the mpath code uses a neat trick of having a
backup next hop group structure, doing the necessary changes offline, and
then RCU-swapping them in. However, the hash tables for resilient hashing
are about an order of magnitude larger than the groups themselves (the size
might be e.g. 4K entries), and it was felt that keeping two of them is an
overkill. Both the primary next-hop group and the spare therefore use the
same resilient table, and writers are careful to keep all references valid
for the forwarding code. The hash table references next-hop group entries
from the next-hop group that is currently in the primary role (i.e. not
spare). During the transition from primary to spare, the table references a
mix of both the primary group and the spare. When a next hop is deleted,
the corresponding buckets are not set to NULL, but instead marked as empty,
so that the pointer is valid and can be used by the forwarding code. The
buckets are then migrated to a new next-hop group entry during upkeep. The
only times that the hash table is invalid is the very beginning and very
end of its lifetime. Between those points, it is always kept valid.

This patch introduces the core support code itself. It does not handle
notifications towards drivers, which are kept as if the group were an mpath
one. It does not handle netlink either. The only bit currently exposed to
user space is the new next-hop group type, and that is currently bounced.
There is therefore no way to actually access this code.
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

- RTM_NEWNEXTHOP et.al. that handle resilient groups will have a new nested
  attribute, NHA_RES_GROUP, whose elements are attributes NHA_RES_GROUP_*.

- RTM_NEWNEXTHOPBUCKET et.al. is a suite of new messages that will
  currently serve only for dumping of individual buckets of resilient next
  hop groups. For nexthop group buckets, these messages will carry a nested
  attribute NHA_RES_BUCKET, whose elements are attributes NHA_RES_BUCKET_*.

  There are several reasons why a new suite of messages is created for
  nexthop buckets instead of overloading the information on the existing
  RTM_{NEW,DEL,GET}NEXTHOP messages.

  First, a nexthop group can contain a large number of nexthop buckets (4k
  is not unheard of). This imposes limits on the amount of information that
  can be encoded for each nexthop bucket given a netlink message is limited
  to 64k bytes.

  Second, while RTM_NEWNEXTHOPBUCKET is only used for notifications at
  this point, in the future it can be extended to provide user space with
  control over nexthop buckets configuration.

- The new group type is NEXTHOP_GRP_TYPE_RES. Note that nexthop code is
  adjusted to bounce groups with that type for now.
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>