wireguard: queueing: use saner cpu selection wrapping

Using `% nr_cpumask_bits` is slow and complicated, and not totally
robust toward dynamic changes to CPU topologies. Rather than storing the
next CPU in the round-robin, just store the last one, and also return
that value. This simplifies the loop drastically into a much more common
pattern.

Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
Cc: stable@vger.kernel.org
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Tested-by: Manuel Leiner <manuel.leiner@gmx.de>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

cpumask: fix incorrect cpumask scanning result checks

It turns out that commit 596ff4a09b89 ("cpumask: re-introduce
constant-sized cpumask optimizations") exposed a number of cases of
drivers not checking the result of "cpumask_next()" and friends
correctly.

The documented correct check for "no more cpus in the cpumask" is to
check for the result being equal or larger than the number of possible
CPU ids, exactly _because_ we've always done those constant-sized
cpumask scans using a widened type before. So the return value of a
cpumask scan should be checked with

if (cpu >= nr_cpu_ids)
...

because the cpumask scan did not necessarily stop exactly *at* that
maximum CPU id.

But a few cases ended up instead using checks like

if (cpu == nr_cpumask_bits)
...

which used that internal "widened" number of bits. And that used to
work pretty much by accident (ok, in this case "by accident" is simply
because it matched the historical internal implementation of the cpumask
scanning, so it was more of a "intentionally using implementation
details rather than an accident").

But the extended constant-sized optimizations then did that internal
implementation differently, and now that code that did things wrong but
matched the old implementation no longer worked at all.

Which then causes subsequent odd problems due to using what ends up
being an invalid CPU ID.

Most of these cases require either unusual hardware or special uses to
hit, but the random.c one triggers quite easily.

All you really need is to have a sufficiently small CONFIG_NR_CPUS value
for the bit scanning optimization to be triggered, but not enough CPUs
to then actually fill that widened cpumask. At that point, the cpumask
scanning will return the NR_CPUS constant, which is _not_ the same as
nr_cpumask_bits.

This just does the mindless fix with

sed -i 's/== nr_cpumask_bits/>= nr_cpu_ids/'

to fix the incorrect uses.

The ones in the SCSI lpfc driver in particular could probably be fixed
more cleanly by just removing that repeated pattern entirely, but I am
not emptionally invested enough in that driver to care.

Reported-and-tested-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/lkml/481b19b5-83a0-4793-b4fd-194ad7b978c3@roeck-us.net/
Reported-and-tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/lkml/CAMuHMdUKo_Sf7TjKzcNDa8Ve+6QrK+P8nSQrSQ=6LTRmcBKNww@mail.gmail.com/
Reported-by: Vernon Yang <vernon2gm@gmail.com>
Link: https://lore.kernel.org/lkml/20230306160651.2016767-1-vernon2gm@gmail.com/
Cc: Yury Norov <yury.norov@gmail.com>
Cc: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

skbuff: Switch structure bounds to struct_group()

In preparation for FORTIFY_SOURCE performing compile-time and run-time
field bounds checking for memcpy(), memmove(), and memset(), avoid
intentionally writing across neighboring fields.

Replace the existing empty member position markers "headers_start" and
"headers_end" with a struct_group(). This will allow memcpy() and sizeof()
to more easily reason about sizes, and improve readability.

"pahole" shows no size nor member offset changes to struct sk_buff.
"objdump -d" shows no object code changes (outside of WARNs affected by
source line number changes).

Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Jason A. Donenfeld <Jason@zx2c4.com> # drivers/net/wireguard/*
Link: https://lore.kernel.org/lkml/20210728035006.GD35706@embeddedor
Signed-off-by: David S. Miller <davem@davemloft.net>

wireguard: receive: use ring buffer for incoming handshakes

Apparently the spinlock on incoming_handshake's skb_queue is highly
contended, and a torrent of handshake or cookie packets can bring the
data plane to its knees, simply by virtue of enqueueing the handshake
packets to be processed asynchronously. So, we try switching this to a
ring buffer to hopefully have less lock contention. This alleviates the
problem somewhat, though it still isn't perfect, so future patches will
have to improve this further. However, it at least doesn't completely
diminish the data plane.

Reported-by: Streun Fabio <fstreun@student.ethz.ch>
Reported-by: Joel Wanner <joel.wanner@inf.ethz.ch>
Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

wireguard: queueing: get rid of per-peer ring buffers

Having two ring buffers per-peer means that every peer results in two
massive ring allocations. On an 8-core x86_64 machine, this commit
reduces the per-peer allocation from 18,688 bytes to 1,856 bytes, which
is an 90% reduction. Ninety percent! With some single-machine
deployments approaching 500,000 peers, we're talking about a reduction
from 7 gigs of memory down to 700 megs of memory.

In order to get rid of these per-peer allocations, this commit switches
to using a list-based queueing approach. Currently GSO fragments are
chained together using the skb->next pointer (the skb_list_* singly
linked list approach), so we form the per-peer queue around the unused
skb->prev pointer (which sort of makes sense because the links are
pointing backwards). Use of skb_queue_* is not possible here, because
that is based on doubly linked lists and spinlocks. Multiple cores can
write into the queue at any given time, because its writes occur in the
start_xmit path or in the udp_recv path. But reads happen in a single
workqueue item per-peer, amounting to a multi-producer, single-consumer
paradigm.

The MPSC queue is implemented locklessly and never blocks. However, it
is not linearizable (though it is serializable), with a very tight and
unlikely race on writes, which, when hit (some tiny fraction of the
0.15% of partial adds on a fully loaded 16-core x86_64 system), causes
the queue reader to terminate early. However, because every packet sent
queues up the same workqueue item after it is fully added, the worker
resumes again, and stopping early isn't actually a problem, since at
that point the packet wouldn't have yet been added to the encryption
queue. These properties allow us to avoid disabling interrupts or
spinning. The design is based on Dmitry Vyukov's algorithm [1].

Performance-wise, ordinarily list-based queues aren't preferable to
ringbuffers, because of cache misses when following pointers around.
However, we *already* have to follow the adjacent pointers when working
through fragments, so there shouldn't actually be any change there. A
potential downside is that dequeueing is a bit more complicated, but the
ptr_ring structure used prior had a spinlock when dequeueing, so all and
all the difference appears to be a wash.

Actually, from profiling, the biggest performance hit, by far, of this
commit winds up being atomic_add_unless(count, 1, max) and atomic_
dec(count), which account for the majority of CPU time, according to
perf. In that sense, the previous ring buffer was superior in that it
could check if it was full by head==tail, which the list-based approach
cannot do.

But all and all, this enables us to get massive memory savings, allowing
WireGuard to scale for real world deployments, without taking much of a
performance hit.

[1] http://www.1024cores.net/home/lock-free-algorithms/queues/intrusive-mpsc-node-based-queue

Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

wireguard: queueing: make use of ip_tunnel_parse_protocol

Now that wg_examine_packet_protocol has been added for general
consumption as ip_tunnel_parse_protocol, it's possible to remove
wg_examine_packet_protocol and simply use the new
ip_tunnel_parse_protocol function directly.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

wireguard: queueing: preserve flow hash across packet scrubbing

It's important that we clear most header fields during encapsulation and
decapsulation, because the packet is substantially changed, and we don't
want any info leak or logic bug due to an accidental correlation. But,
for encapsulation, it's wrong to clear skb->hash, since it's used by
fq_codel and flow dissection in general. Without it, classification does
not proceed as usual. This change might make it easier to estimate the
number of innerflows by examining clustering of out of order packets,
but this shouldn't open up anything that can't already be inferred
otherwise (e.g. syn packet size inference), and fq_codel can be disabled
anyway.

Furthermore, it might be the case that the hash isn't used or queried at
all until after wireguard transmits the encrypted UDP packet, which
means skb->hash might still be zero at this point, and thus no hash
taken over the inner packet data. In order to address this situation, we
force a calculation of skb->hash before encrypting packet data.

Of course this means that fq_codel might transmit packets slightly more
out of order than usual. Toke did some testing on beefy machines with
high quantities of parallel flows and found that increasing the
reply-attack counter to 8192 takes care of the most pathological cases
pretty well.

Reported-by: Dave Taht <dave.taht@gmail.com>
Reviewed-and-tested-by: Toke Høiland-Jørgensen <toke@toke.dk>
Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net: Fix CONFIG_NET_CLS_ACT=n and CONFIG_NFT_FWD_NETDEV={y, m} build

net/netfilter/nft_fwd_netdev.c: In function ‘nft_fwd_netdev_eval’:
net/netfilter/nft_fwd_netdev.c:32:10: error: ‘struct sk_buff’ has no member named ‘tc_redirected’
pkt->skb->tc_redirected = 1;
^~
net/netfilter/nft_fwd_netdev.c:33:10: error: ‘struct sk_buff’ has no member named ‘tc_from_ingress’
pkt->skb->tc_from_ingress = 1;
^~

To avoid a direct dependency with tc actions from netfilter, wrap the
redirect bits around CONFIG_NET_REDIRECT and move helpers to
include/linux/skbuff.h. Turn on this toggle from the ifb driver, the
only existing client of these bits in the tree.

This patch adds skb_set_redirected() that sets on the redirected bit
on the skbuff, it specifies if the packet was redirect from ingress
and resets the timestamp (timestamp reset was originally missing in the
netfilter bugfix).

Fixes: bcfabee1afd99484 ("netfilter: nft_fwd_netdev: allow to redirect to ifb via ingress")
Reported-by: noreply@ellerman.id.au
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

wireguard: queueing: account for skb->protocol==0

We carry out checks to the effect of:

if (skb->protocol != wg_examine_packet_protocol(skb))
goto err;

By having wg_skb_examine_untrusted_ip_hdr return 0 on failure, this
means that the check above still passes in the case where skb->protocol
is zero, which is possible to hit with AF_PACKET:

struct sockaddr_pkt saddr = { .spkt_device = "wg0" };
unsigned char buffer[5] = { 0 };
sendto(socket(AF_PACKET, SOCK_PACKET, /* skb->protocol = */ 0),
buffer, sizeof(buffer), 0, (const struct sockaddr *)&saddr, sizeof(saddr));

Additional checks mean that this isn't actually a problem in the code
base, but I could imagine it becoming a problem later if the function is
used more liberally.

I would prefer to fix this by having wg_examine_packet_protocol return a
32-bit ~0 value on failure, which will never match any value of
skb->protocol, which would simply change the generated code from a mov
to a movzx. However, sparse complains, and adding __force casts doesn't
seem like a good idea, so instead we just add a simple helper function
to check for the zero return value. Since wg_examine_packet_protocol
itself gets inlined, this winds up not adding an additional branch to
the generated code, since the 0 return value already happens in a
mergable branch.

Reported-by: Fabian Freyer <fabianfreyer@radicallyopensecurity.com>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

wireguard: queueing: do not account for pfmemalloc when clearing skb header

Before 8b7008620b84 ("net: Don't copy pfmemalloc flag in __copy_skb_
header()"), the pfmemalloc flag used to be between headers_start and
headers_end, which is a region we clear when preparing the packet for
encryption/decryption. This is a parameter we certainly want to
preserve, which is why 8b7008620b84 moved it out of there. The code here
was written in a world before 8b7008620b84, though, where we had to
manually account for it. This commit brings things up to speed.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net: WireGuard secure network tunnel

WireGuard is a layer 3 secure networking tunnel made specifically for
the kernel, that aims to be much simpler and easier to audit than IPsec.
Extensive documentation and description of the protocol and
considerations, along with formal proofs of the cryptography, are
available at:

* https://www.wireguard.com/
* https://www.wireguard.com/papers/wireguard.pdf

This commit implements WireGuard as a simple network device driver,
accessible in the usual RTNL way used by virtual network drivers. It
makes use of the udp_tunnel APIs, GRO, GSO, NAPI, and the usual set of
networking subsystem APIs. It has a somewhat novel multicore queueing
system designed for maximum throughput and minimal latency of encryption
operations, but it is implemented modestly using workqueues and NAPI.
Configuration is done via generic Netlink, and following a review from
the Netlink maintainer a year ago, several high profile userspace tools
have already implemented the API.

This commit also comes with several different tests, both in-kernel
tests and out-of-kernel tests based on network namespaces, taking profit
of the fact that sockets used by WireGuard intentionally stay in the
namespace the WireGuard interface was originally created, exactly like
the semantics of userspace tun devices. See wireguard.com/netns/ for
pictures and examples.

The source code is fairly short, but rather than combining everything
into a single file, WireGuard is developed as cleanly separable files,
making auditing and comprehension easier. Things are laid out as
follows:

* noise.[ch], cookie.[ch], messages.h: These implement the bulk of the
cryptographic aspects of the protocol, and are mostly data-only in
nature, taking in buffers of bytes and spitting out buffers of
bytes. They also handle reference counting for their various shared
pieces of data, like keys and key lists.

* ratelimiter.[ch]: Used as an integral part of cookie.[ch] for
ratelimiting certain types of cryptographic operations in accordance
with particular WireGuard semantics.

* allowedips.[ch], peerlookup.[ch]: The main lookup structures of
WireGuard, the former being trie-like with particular semantics, an
integral part of the design of the protocol, and the latter just
being nice helper functions around the various hashtables we use.

* device.[ch]: Implementation of functions for the netdevice and for
rtnl, responsible for maintaining the life of a given interface and
wiring it up to the rest of WireGuard.

* peer.[ch]: Each interface has a list of peers, with helper functions
available here for creation, destruction, and reference counting.

* socket.[ch]: Implementation of functions related to udp_socket and
the general set of kernel socket APIs, for sending and receiving
ciphertext UDP packets, and taking care of WireGuard-specific sticky
socket routing semantics for the automatic roaming.

* netlink.[ch]: Userspace API entry point for configuring WireGuard
peers and devices. The API has been implemented by several userspace
tools and network management utility, and the WireGuard project
distributes the basic wg(8) tool.

* queueing.[ch]: Shared function on the rx and tx path for handling
the various queues used in the multicore algorithms.

* send.c: Handles encrypting outgoing packets in parallel on
multiple cores, before sending them in order on a single core, via
workqueues and ring buffers. Also handles sending handshake and cookie
messages as part of the protocol, in parallel.

* receive.c: Handles decrypting incoming packets in parallel on
multiple cores, before passing them off in order to be ingested via
the rest of the networking subsystem with GRO via the typical NAPI
poll function. Also handles receiving handshake and cookie messages
as part of the protocol, in parallel.

* timers.[ch]: Uses the timer wheel to implement protocol particular
event timeouts, and gives a set of very simple event-driven entry
point functions for callers.

* main.c, version.h: Initialization and deinitialization of the module.

* selftest/*.h: Runtime unit tests for some of the most security
sensitive functions.

* tools/testing/selftests/wireguard/netns.sh: Aforementioned testing
script using network namespaces.

This commit aims to be as self-contained as possible, implementing
WireGuard as a standalone module not needing much special handling or
coordination from the network subsystem. I expect for future
optimizations to the network stack to positively improve WireGuard, and
vice-versa, but for the time being, this exists as intentionally
standalone.

We introduce a menu option for CONFIG_WIREGUARD, as well as providing a
verbose debug log and self-tests via CONFIG_WIREGUARD_DEBUG.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: David Miller <davem@davemloft.net>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: linux-crypto@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: netdev@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>