This is a rewrite of NewReno loss recovery implementation that is
simpler and standalone for readability and better performance by
using less states.

Note that NewReno refers to RFC6582 as a modification to the fast
recovery algorithm. It is used only if the connection does not
support SACK in Linux. It should not to be confused with the Reno
(AIMD) congestion control.
Signed-off-by: NYuchung Cheng <ycheng@google.com>
Signed-off-by: NNeal Cardwell <ncardwell@google.com>
Reviewed-by: NEric Dumazet <edumazet@google.com>
Reviewed-by: NSoheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: NPriyaranjan Jha <priyarjha@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds support for the classic DUPACK threshold rule
(#DupThresh) in RACK.

When the number of packets SACKed is greater or equal to the
threshold, RACK sets the reordering window to zero which would
immediately mark all the unsacked packets below the highest SACKed
sequence lost. Since this approach is known to not work well with
reordering, RACK only uses it if no reordering has been observed.

The DUPACK threshold rule is a particularly useful extension to the
fast recoveries triggered by RACK reordering timer. For example
data-center transfers where the RTT is much smaller than a timer
tick, or high RTT path where the default RTT/4 may take too long.

Note that this patch differs slightly from RFC6675. RFC6675
considers a packet lost when at least #DupThresh higher-sequence
packets are SACKed.

With RACK, for connections that have seen reordering, RACK
continues to use a dynamically-adaptive time-based reordering
window to detect losses. But for connections on which we have not
yet seen reordering, this patch considers a packet lost when at
least one higher sequence packet is SACKed and the total number
of SACKed packets is at least DupThresh. For example, suppose a
connection has not seen reordering, and sends 10 packets, and
packets 3, 5, 7 are SACKed. RFC6675 considers packets 1 and 2
lost. RACK considers packets 1, 2, 4, 6 lost.

There is some small risk of spurious retransmits here due to
reordering. However, this is mostly limited to the first flight of
a connection on which the sender receives SACKs from reordering.
And RFC 6675 and FACK loss detection have a similar risk on the
first flight with reordering (it's just that the risk of spurious
retransmits from reordering was slightly narrower for those older
algorithms due to the margin of 3*MSS).

Also the minimum reordering window is reduced from 1 msec to 0
to recover quicker on short RTT transfers. Therefore RACK is more
aggressive in marking packets lost during recovery to reduce the
reordering window timeouts.
Signed-off-by: NYuchung Cheng <ycheng@google.com>
Signed-off-by: NNeal Cardwell <ncardwell@google.com>
Reviewed-by: NEric Dumazet <edumazet@google.com>
Reviewed-by: NSoheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: NPriyaranjan Jha <priyarjha@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

So that we can use lockdep on it.
The newly introduced sequence lock has the same scope of busylock,
so it shares the same lockdep annotation, but it's only used for
NOLOCK qdiscs.

With this changeset we acquire such lock in the control path around
flushing operation (qdisc reset), to allow more NOLOCK qdisc perf
improvement in the next patch.
Signed-off-by: NPaolo Abeni <pabeni@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently NOLOCK qdiscs pay a measurable overhead to atomically
manipulate the __QDISC_STATE_RUNNING. Such bit is flipped twice per
packet in the uncontended scenario with packet rate below the
line rate: on packed dequeue and on the next, failing dequeue attempt.

This changeset moves the bit manipulation into the qdisc_run_{begin,end}
helpers, so that the bit is now flipped only once per packet, with
measurable performance improvement in the uncontended scenario.

This also allows simplifying the qdisc teardown code path - since
qdisc_is_running() is now effective for each qdisc type - and avoid a
possible race between qdisc_run() and dev_deactivate_many(), as now
the some_qdisc_is_busy() can properly detect NOLOCK qdiscs being busy
dequeuing packets.
Signed-off-by: NPaolo Abeni <pabeni@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The rx load balancing provided by balance-alb is not mutually
exclusive with using hashing for tx selection, and should provide a decent
speed increase because this eliminates spinlocks and cache contention.
Signed-off-by: NDebabrata Banerjee <dbanerje@akamai.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch only refactors the existing sockmap code. This will allow
much of the psock initialization code path and bpf helper codes to
work for both sockmap bpf map types that are backed by an array, the
currently supported type, and the new hash backed bpf map type
sockhash.

Most the fallout comes from three changes,

  - Pushing bpf programs into an independent structure so we
    can use it from the htab struct in the next patch.
  - Generalizing helpers to use void *key instead of the hardcoded
    u32.
  - Instead of passing map/key through the metadata we now do
    the lookup inline. This avoids storing the key in the metadata
    which will be useful when keys can be longer than 4 bytes. We
    rename the sk pointers to sk_redir at this point as well to
    avoid any confusion between the current sk pointer and the
    redirect pointer sk_redir.
Signed-off-by: NJohn Fastabend <john.fastabend@gmail.com>
Acked-by: NDavid S. Miller <davem@davemloft.net>
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>

Currently, when the rule is not to be exclusively executed by the
hardware, extack is not passed along and offloading failures don't
get logged. The idea was that hardware failures are okay because the
rule will get executed in software then and this way it doesn't confuse
unware users.

But this is not helpful in case one needs to understand why a certain
rule failed to get offloaded. Considering it may have been a temporary
failure, like resources exceeded or so, reproducing it later and knowing
that it is triggering the same reason may be challenging.

The ultimate goal is to improve Open vSwitch debuggability when using
flower offloading.

This patch adds a new flag to enable verbose logging. With the flag set,
extack will be passed to the driver, which will be able to log the
error. As the operation itself probably won't fail (not because of this,
at least), current iproute will already log it as a Warning.

The flag is generic, so it can be reused later. No need to restrict it
just for HW offloading. The command line will follow the syntax that
tc-ebpf already uses, tc ... [ verbose ] ... , and extend its meaning.

For example:
# ./tc qdisc add dev p7p1 ingress
# ./tc filter add dev p7p1 parent ffff: protocol ip prio 1 \
	flower verbose \
	src_mac ed:13:db:00:00:00 dst_mac 01:80:c2:00:00:d0 \
	src_ip 56.0.0.0 dst_ip 55.0.0.0 action drop
Warning: TC offload is disabled on net device.
# echo $?
0
# ./tc filter add dev p7p1 parent ffff: protocol ip prio 1 \
	flower \
	src_mac ff:13:db:00:00:00 dst_mac 01:80:c2:00:00:d0 \
	src_ip 56.0.0.0 dst_ip 55.0.0.0 action drop
# echo $?
0
Signed-off-by: NMarcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

linux-4.16 got support for softirq based hrtimers.
TCP can switch its pacing hrtimer to this variant, since this
avoids going through a tasklet and some atomic operations.

pacing timer logic looks like other (jiffies based) tcp timers.

v2: use hrtimer_try_to_cancel() in tcp_clear_xmit_timers()
    to correctly release reference on socket if needed.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add support for PHYLINK within the DSA subsystem in order to support more
complex devices such as pluggable (SFP) and non-pluggable (SFF) modules, 10G
PHYs, and traditional PHYs. Using PHYLINK allows us to drop some amount of
complexity we had while probing fixed and non-fixed PHYs using Device Tree.

Because PHYLINK separates the Ethernet MAC/port configuration into different
stages, we let switch drivers implement those, and for now, we maintain
functionality by calling dsa_slave_adjust_link() during
phylink_mac_link_{up,down} which provides semantically equivalent steps.

Drivers willing to take advantage of PHYLINK should implement the phylink_mac_*
operations that DSA wraps.

We cannot quite remove the adjust_link() callback just yet, because a number of
drivers rely on that for configuring their "CPU" and "DSA" ports, this is done
dsa_port_setup_phy_of() and dsa_port_fixed_link_register_of() still.

Drivers that utilize fixed links for user-facing ports (e.g: bcm_sf2) will need
to implement phylink_mac_ops from now on to preserve functionality, since PHYLINK
*does not* create a phy_device instance for fixed links.
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In preparation for adding support for PHYLINK within DSA, define a number of
operations that we will need and that switch drivers can start implementing.
Proper integration with PHYLINK will follow in subsequent patches.

We start selecting PHYLINK (which implies PHYLIB) in net/dsa/Kconfig
such that drivers can be guaranteed that this dependency is properly
taken care of and can start referencing PHYLINK helper functions without
requiring stubs or anything.
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There was a regression at some point from the intended functionality of
commit f60c3704 ("bonding: Fix alb mode to only use first level
vlans.")

Given the return value vlan_get_encap_level() we need to store the nest
level of the bond device, and then compare the vlan's encap level to
this. Without this, this check always fails and learning packets are
never sent.

In addition, this same commit caused a regression in the behavior of
balance_alb, which requires learning packets be sent for all interfaces
using the slave's mac in order to load balance properly. For vlan's
that have not set a user mac, we can send after checking one bit.
Otherwise we need send the set mac, albeit defeating rx load balancing
for that vlan.
Signed-off-by: NDebabrata Banerjee <dbanerje@akamai.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add stubs to retrieve a handle to an IPv6 FIB table, fib6_get_table,
a stub to do a lookup in a specific table, fib6_table_lookup, and
a stub for a full route lookup.

The stubs are needed for core bpf code to handle the case when the
IPv6 module is not builtin.
Signed-off-by: NDavid Ahern <dsahern@gmail.com>
Acked-by: NDavid S. Miller <davem@davemloft.net>
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>

Add IPv6 equivalent to fib_lookup. Does a fib lookup, including rules,
but returns a FIB entry, fib6_info, rather than a dst based rt6_info.
fib6_lookup is any where from 140% (MULTIPLE_TABLES config disabled)
to 60% faster than any of the dst based lookup methods (without custom
rules) and 25% faster with custom rules (e.g., l3mdev rule).

Since the lookup function has a completely different signature,
fib6_rule_action is split into 2 paths: the existing one is
renamed __fib6_rule_action and a new one for the fib6_info path
is added. fib6_rule_action decides which to call based on the
lookup_ptr. If it is fib6_table_lookup then the new path is taken.

Caller must hold rcu lock as no reference is taken on the returned
fib entry.
Signed-off-by: NDavid Ahern <dsahern@gmail.com>
Acked-by: NDavid S. Miller <davem@davemloft.net>
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>

ip6_pol_route is used for ingress and egress FIB lookups. Refactor it
moving the table lookup into a separate fib6_table_lookup that can be
invoked separately and export the new function.

ip6_pol_route now calls fib6_table_lookup and uses the result to generate
a dst based rt6_info.
Signed-off-by: NDavid Ahern <dsahern@gmail.com>
Acked-by: NDavid S. Miller <davem@davemloft.net>
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>

Rename rt6_multipath_select to fib6_multipath_select and export it.
A later patch wants access to it similar to IPv4's fib_select_path.
Signed-off-by: NDavid Ahern <dsahern@gmail.com>
Acked-by: NDavid S. Miller <davem@davemloft.net>
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>

Rename fib6_lookup to fib6_node_lookup to better reflect what it
returns. The fib6_lookup name will be used in a later patch for
an IPv6 equivalent to IPv4's fib_lookup.
Signed-off-by: NDavid Ahern <dsahern@gmail.com>
Acked-by: NDavid S. Miller <davem@davemloft.net>
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>

This version has some suggestions by Eric Dumazet:

- Use a local variable for the mark in IPv6 instead of ctl_sk to avoid SMP
races.
- Use the more elegant "IP4_REPLY_MARK(net, skb->mark) ?: sk->sk_mark"
statement.
- Factorize code as sk_fullsock() check is not necessary.

Aidan McGurn from Openwave Mobility systems reported the following bug:

"Marked routing is broken on customer deployment. Its effects are large
increase in Uplink retransmissions caused by the client never receiving
the final ACK to their FINACK - this ACK misses the mark and routes out
of the incorrect route."

Currently marks are added to sk_buffs for replies when the "fwmark_reflect"
sysctl is enabled. But not for TW sockets that had sk->sk_mark set via
setsockopt(SO_MARK..).

Fix this in IPv4/v6 by adding tw->tw_mark for TIME_WAIT sockets. Copy the the
original sk->sk_mark in __inet_twsk_hashdance() to the new tw->tw_mark location.
Then progate this so that the skb gets sent with the correct mark. Do the same
for resets. Give the "fwmark_reflect" sysctl precedence over sk->sk_mark so that
netfilter rules are still honored.
Signed-off-by: NJon Maxwell <jmaxwell37@gmail.com>
Reviewed-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

INET_CSK_DEBUG is always set and only is used for 2 pr_debug calls.

EXPORT_SYMBOL(inet_csk_timer_bug_msg) is only used by these 2
pr_debug calls and is also unnecessary as the exported string can
be used directly by these calls.
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

No changes in refcount semantics -- key init is false; replace

static_key_slow_inc|dec   with   static_branch_inc|dec
static_key_false          with   static_branch_unlikely

Added a '_key' suffix to memalloc_socks, for better self
documentation.
Signed-off-by: NDavidlohr Bueso <dbueso@suse.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

No changes in refcount semantics -- key init is false; replace

static_key_slow_inc|dec   with   static_branch_inc|dec
static_key_false          with   static_branch_unlikely
Signed-off-by: NDavidlohr Bueso <dbueso@suse.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch is meant to allow us to avoid having to recompute the checksum
from scratch and have it passed as a parameter.

Instead of taking that approach we can take advantage of the fact that the
length that was used to compute the existing checksum is included in the
UDP header.

Finally to avoid the need to invert the result we can just call csum16_add
and csum16_sub directly. By doing this we can avoid a number of
instructions in the loop that is handling segmentation.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Acked-by: NWillem de Bruijn <willemb@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There is no point in passing MSS as a parameter for for the GSO
segmentation call as it is already available via the shared info for the
skb itself.
Reviewed-by: NEric Dumazet <edumazet@google.com>
Acked-by: NWillem de Bruijn <willemb@google.com>
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This change fixes a couple of type mismatch reported by the sparse
tool, explicitly using the requested type for the offending arguments.
Signed-off-by: NPaolo Abeni <pabeni@redhat.com>
Acked-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When the core networking needs to detect the transport offset in a given
packet and parse it explicitly, a full-blown flow_keys struct is used for
storage.
This patch introduces a smaller keys store, rework the basic flow dissect
helper to use it, and apply this new helper where possible - namely in
skb_probe_transport_header(). The used flow dissector data structures
are renamed to match more closely the new role.

The above gives ~50% performance improvement in micro benchmarking around
skb_probe_transport_header() and ~30% around eth_get_headlen(), mostly due
to the smaller memset. Small, but measurable improvement is measured also
in macro benchmarking.

v1 -> v2: use the new helper in eth_get_headlen() and skb_get_poff(),
  as per DaveM suggestion
Suggested-by: NDavid Miller <davem@davemloft.net>
Signed-off-by: NPaolo Abeni <pabeni@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NWolfram Sang <wsa+renesas@sang-engineering.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fix 88 instances of a kernel-doc warning:
  ../include/net/mac80211.h:2083: warning: bad line:  >
Signed-off-by: NRandy Dunlap <rdunlap@infradead.org>
Cc: linux-wireless@vger.kernel.org
Cc: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>

Signed-off-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>

This slipped through the cracks in the followup set to the fib6_info flip.
Rename rt6_next to fib6_next.
Signed-off-by: NDavid Ahern <dsahern@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Another setsockopt (XDP_TX_QUEUE) is added to let the process allocate
a queue, where the user process can pass frames to be transmitted by
the kernel.

The mmapping of the queue is done using the XDP_PGOFF_TX_QUEUE offset.
Signed-off-by: NMagnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: NAlexei Starovoitov <ast@kernel.org>

The xskmap is yet another BPF map, very much inspired by
dev/cpu/sockmap, and is a holder of AF_XDP sockets. A user application
adds AF_XDP sockets into the map, and by using the bpf_redirect_map
helper, an XDP program can redirect XDP frames to an AF_XDP socket.

Note that a socket that is bound to certain ifindex/queue index will
*only* accept XDP frames from that netdev/queue index. If an XDP
program tries to redirect from a netdev/queue index other than what
the socket is bound to, the frame will not be received on the socket.

A socket can reside in multiple maps.

v3: Fixed race and simplified code.
v2: Removed one indirection in map lookup.
Signed-off-by: NBjörn Töpel <bjorn.topel@intel.com>
Signed-off-by: NAlexei Starovoitov <ast@kernel.org>

Here the actual receive functions of AF_XDP are implemented, that in a
later commit, will be called from the XDP layers.

There's one set of functions for the XDP_DRV side and another for
XDP_SKB (generic).

A new XDP API, xdp_return_buff, is also introduced.

Adding xdp_return_buff, which is analogous to xdp_return_frame, but
acts upon an struct xdp_buff. The API will be used by AF_XDP in future
commits.

Support for the poll syscall is also implemented.

v2: xskq_validate_id did not update cons_tail.
    The entries variable was calculated twice in xskq_nb_avail.
    Squashed xdp_return_buff commit.
Signed-off-by: NBjörn Töpel <bjorn.topel@intel.com>
Signed-off-by: NAlexei Starovoitov <ast@kernel.org>

Here, the bind syscall is added. Binding an AF_XDP socket, means
associating the socket to an umem, a netdev and a queue index. This
can be done in two ways.

The first way, creating a "socket from scratch". Create the umem using
the XDP_UMEM_REG setsockopt and an associated fill queue with
XDP_UMEM_FILL_QUEUE. Create the Rx queue using the XDP_RX_QUEUE
setsockopt. Call bind passing ifindex and queue index ("channel" in
ethtool speak).

The second way to bind a socket, is simply skipping the
umem/netdev/queue index, and passing another already setup AF_XDP
socket. The new socket will then have the same umem/netdev/queue index
as the parent so it will share the same umem. You must also set the
flags field in the socket address to XDP_SHARED_UMEM.

v2: Use PTR_ERR instead of passing error variable explicitly.
Signed-off-by: NMagnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: NAlexei Starovoitov <ast@kernel.org>

Another setsockopt (XDP_RX_QUEUE) is added to let the process allocate
a queue, where the kernel can pass completed Rx frames from the kernel
to user process.

The mmapping of the queue is done using the XDP_PGOFF_RX_QUEUE offset.
Signed-off-by: NBjörn Töpel <bjorn.topel@intel.com>
Signed-off-by: NAlexei Starovoitov <ast@kernel.org>

In this commit the base structure of the AF_XDP address family is set
up. Further, we introduce the abilty register a window of user memory
to the kernel via the XDP_UMEM_REG setsockopt syscall. The memory
window is viewed by an AF_XDP socket as a set of equally large
frames. After a user memory registration all frames are "owned" by the
user application, and not the kernel.

v2: More robust checks on umem creation and unaccount on error.
    Call set_page_dirty_lock on cleanup.
    Simplified xdp_umem_reg.
Co-authored-by: NMagnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: NMagnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: NBjörn Töpel <bjorn.topel@intel.com>
Signed-off-by: NAlexei Starovoitov <ast@kernel.org>

The following patch enables sending notifications also for events on FDB
entries that weren't added by the user. Give the drivers the information
necessary to distinguish between the two origins of FDB entries.

To maintain the current behavior, have switchdev-implementing drivers
bail out on notifications about non-user-added FDB entries. In case of
mlxsw driver, allow a call to mlxsw_sp_span_respin() so that SPAN over
bridge catches up with the changed FDB.
Signed-off-by: NPetr Machata <petrm@mellanox.com>
Reviewed-by: NNikolay Aleksandrov <nikolay@cumulusnetworks.com>
Acked-by: NIvan Vecera <ivecera@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This reverts commit edd7ceb7 ("ipv6: Allow non-gateway ECMP for
IPv6").

Eric reported a division by zero in rt6_multipath_rebalance() which is
caused by above commit that considers identical local routes to be
siblings. The division by zero happens because a nexthop weight is not
set for local routes.

Revert the commit as it does not fix a bug and has side effects.

To reproduce:

# ip -6 address add 2001:db8::1/64 dev dummy0
# ip -6 address add 2001:db8::1/64 dev dummy1

Fixes: edd7ceb7 ("ipv6: Allow non-gateway ECMP for IPv6")
Signed-off-by: NIdo Schimmel <idosch@mellanox.com>
Reported-by: NEric Dumazet <eric.dumazet@gmail.com>
Tested-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It is reported that in some cases, write_space may be called in
do_tcp_sendpages, such that we recursively invoke do_tcp_sendpages again:

[  660.468802]  ? do_tcp_sendpages+0x8d/0x580
[  660.468826]  ? tls_push_sg+0x74/0x130 [tls]
[  660.468852]  ? tls_push_record+0x24a/0x390 [tls]
[  660.468880]  ? tls_write_space+0x6a/0x80 [tls]
...

tls_push_sg already does a loop over all sending sg's, so ignore
any tls_write_space notifications until we are done sending.
We then have to call the previous write_space to wake up
poll() waiters after we are done with the send loop.
Reported-by: NAndre Tomt <andre@tomt.net>
Signed-off-by: NDave Watson <davejwatson@fb.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It is valid to have static routes where the nexthop
is an interface not an address such as tunnels.
For IPv4 it was possible to use ECMP on these routes
but not for IPv6.
Signed-off-by: NThomas Winter <Thomas.Winter@alliedtelesis.co.nz>
Cc: David Ahern <dsahern@gmail.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Acked-by: NDavid Ahern <dsahern@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

And do so if the skb doesn't have enough space for the payload.
This is a preparation for the next patch.
Signed-off-by: NMarcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds a generic infrastructure to offload TLS crypto to a
network device. It enables the kernel TLS socket to skip encryption
and authentication operations on the transmit side of the data path.
Leaving those computationally expensive operations to the NIC.

The NIC offload infrastructure builds TLS records and pushes them to
the TCP layer just like the SW KTLS implementation and using the same
API.
TCP segmentation is mostly unaffected. Currently the only exception is
that we prevent mixed SKBs where only part of the payload requires
offload. In the future we are likely to add a similar restriction
following a change cipher spec record.

The notable differences between SW KTLS and NIC offloaded TLS
implementations are as follows:
1. The offloaded implementation builds "plaintext TLS record", those
records contain plaintext instead of ciphertext and place holder bytes
instead of authentication tags.
2. The offloaded implementation maintains a mapping from TCP sequence
number to TLS records. Thus given a TCP SKB sent from a NIC offloaded
TLS socket, we can use the tls NIC offload infrastructure to obtain
enough context to encrypt the payload of the SKB.
A TLS record is released when the last byte of the record is ack'ed,
this is done through the new icsk_clean_acked callback.

The infrastructure should be extendable to support various NIC offload
implementations.  However it is currently written with the
implementation below in mind:
The NIC assumes that packets from each offloaded stream are sent as
plaintext and in-order. It keeps track of the TLS records in the TCP
stream. When a packet marked for offload is transmitted, the NIC
encrypts the payload in-place and puts authentication tags in the
relevant place holders.

The responsibility for handling out-of-order packets (i.e. TCP
retransmission, qdisc drops) falls on the netdev driver.

The netdev driver keeps track of the expected TCP SN from the NIC's
perspective.  If the next packet to transmit matches the expected TCP
SN, the driver advances the expected TCP SN, and transmits the packet
with TLS offload indication.

If the next packet to transmit does not match the expected TCP SN. The
driver calls the TLS layer to obtain the TLS record that includes the
TCP of the packet for transmission. Using this TLS record, the driver
posts a work entry on the transmit queue to reconstruct the NIC TLS
state required for the offload of the out-of-order packet. It updates
the expected TCP SN accordingly and transmits the now in-order packet.
The same queue is used for packet transmission and TLS context
reconstruction to avoid the need for flushing the transmit queue before
issuing the context reconstruction request.
Signed-off-by: NIlya Lesokhin <ilyal@mellanox.com>
Signed-off-by: NBoris Pismenny <borisp@mellanox.com>
Signed-off-by: NAviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>