Recruiting fewer crypt workers and going inline for slow peers (change 17 and 18) cost one TCP stream in the QEMU lab (4 vCPUs) a third of its throughput, 11.5 to 7-8 Gbps. EC2 didn't show it, as both data planes were at its per-flow limit there. The sender, held to a few GSO packets in flight by TCP Small Queues, never had recruit_factor's worth waiting, so it got one encrypt worker. Now the first recruit_free (default 2) draining workers are recruited at the old backlog, and only past that does recruit_factor apply. And tswg_tx_slow reset its count every 10ms window, so the first tx_inline_mbps' worth of every window was encrypted inline however fast the peer was sending. Now, as on receive, a peer that went over the rate counts as fast for 100ms. Also start the per-peer until-jiffies at the peer's creation rather than 0, which is in the future for the first 5 minutes after boot. One stream in the lab: 7.1 to 11.3 Gbps, 1.23x wireguard-go's, at 0.66x / 0.80x its sender / receiver CPU per GB. Updates #426 Signed-off-by: Brad Fitzpatrick <[email protected]> Change-Id: I59c20b2d005ff3125cd4055fc1d607db3ca18ab1
99 KiB
tswg: Tailscale-flavored kernel WireGuard
This is a living design document. It records requirements, decisions (with their reasons), and the TODO list. Update it whenever something is decided or changes.
Tracking issue: https://github.com/tailscale/tailscale/issues/426
Goal
Move the Tailscale data plane on Linux into the kernel. Packets between Tailscale peers should be encrypted, decrypted and forwarded by a kernel module without crossing into userspace on the direct (UDP) path. tailscaled keeps doing everything else: control plane, disco, NAT traversal (STUN, hole punching), port mapping (UPnP, NAT-PMP, PCP), DERP, and programming the kernel module.
Performance is the primary motivation for this work (stated 2026-11-06). Everything else is in service of getting the data plane out of userspace, so every change should be judged by its effect on performance, and performance must be measured, not assumed.
What we expect to win, compared to wireguard-go with TUN GSO/GRO and UDP GSO/GRO:
- CPU cost per byte and per packet.
- Latency and small-packet rate.
- Forwarding performance for subnet routers and exit nodes.
- Throughput, especially on small or many-core machines, once outer UDP GSO/GRO is in place (see "Performance" below).
Performance
Results at a glance
The current numbers, kept up to date as results come in (details, setups and history in the sections below). "CPU-s/GB" is CPU seconds per GB delivered or forwarded on the measured machine (lower is better); ratios are tswg over wireguard-go. MTU 1280 (Tailscale's) unless noted.
Subnet router on EC2 (TestLeanSubnetRouter): clients, each a peer of
the router, with many TCP flows each to a backend on the router's LAN,
which the router forwards to, masquerading. Updated 2026-11-07.
| router | clients x flows | tswg | wireguard-go | kernel WG | tswg/wggo throughput | CPU-s/GB tswg / wggo / kernel WG | tswg/wggo CPU per GB |
|---|---|---|---|---|---|---|---|
| c7i.16xlarge, 4 CPUs online | 20 x 8 | 13.9 Gbps | 6.3 | 10.2 | 2.2x | 2.38 / 3.87 / 3.35 | 0.61x |
| c7i.16xlarge, 8 CPUs online | 20 x 8 | 23.0 Gbps | 6.4 | 16.9 | 3.6x | 2.62 / 4.56 / 3.98 | 0.57x |
| c7i.48xlarge, 192 CPUs | 8 x 16 | 31.5 Gbps | 7.2 | 12.3 | 4.3x | 3.90 / 3.87 / 94.7 | 1.01x |
| c7i.48xlarge, 192 CPUs | 24 x 8 | 40.0 Gbps | 7.1 | 13.5 | 5.6x | 4.49 / 4.60 / 95.4 | 0.98x |
| c6in.32xlarge, 128 CPUs | 20 x 8 | 57.6 Gbps | 5.8 | 8.1 | 9.9x | 5.26 / 4.72 / 130 | 1.11x |
| c6in.32xlarge, 128 CPUs | 40 x 8 | 72.1 Gbps | 6.14 / - / - | ||||
| c6in.32xlarge, 128 CPUs | 60 x 4 | 74.3 Gbps | 6.2 | 8.1 | 12.0x | 6.25 / 5.57 / 130 | 1.12x |
| c7i.48xlarge, MTU 8920 (data point only) | 8 x 16 | 49.6 Gbps (line rate) | 17.5 | 49.2 | 2.8x | 2.18 / 1.86 / 15.0 | 1.17x |
| c6in.32xlarge, 128 CPUs, idle-residency CPU accounting | 37 x 4 | 70.9 Gbps | 6.2 | 8.5 | 11.5x | 6.50 / 8.57 / 124.6 | 0.76x |
| real tailscaled, kernel vs. TUN mode (c6in.32xlarge) | 37 x 4 | 69.2 Gbps | 6.9 (TUN) | 10.0x | 6.47 / 8.80 / - | 0.74x |
The last row runs real tailscaled (2026-11-08; tskernel and tstun
in TestLeanSubnetRouter): the router advertises the backend's address
with SNAT, the clients (kernel mode) accept it, and a self-contained
control plane (tstest/tswgbench/benchcontrol) runs on the backend.
Kernel mode matches the bare tswg tunnel (70.9 Gbps), so tailscaled adds
no cost on the data path; plain routing on the same clients: 89.5 Gbps.
The same 37 clients through the same router with no tunnel, the clients' routes clamped to MTU 1280 (so the same size packets as through the tunnels): 88.9 Gbps at 1.27 CPU-s/GB, so tswg gets 0.80x of plain routing. Unclamped (jumbo frames), plain routing reaches 165 Gbps; at normal MTUs, the platform's per-packet costs limit it too.
The other direction, as HTTP (2026-11-08; TSWG_SUBNET_LOAD=fetch):
the 37 clients each make requests of 500 bytes over 16 keep-alive
connections to the backend, one at a time on each, which it answers with
1 MiB, so the router encrypts the big responses (forwarding what GRO
merged from the backend) rather than decrypting uploads. c6in.32xlarge
router, MTU 1280, runs interleaved:
| router's data plane | Gbps (runs) | router CPU | CPU-s/GB |
|---|---|---|---|
| tswg before change 11 (encryption straight from GSO packets) | 14.7-17.4 (5 runs) | 60-75% | 37-55 |
| tswg with change 11 | 35.6-37.9 (8 of 14 runs), 17.7-19.2 (6) | 94% / 64-73% | 27-28 / 39-44 |
| tswg with change 12 (run to completion) | 68.4-69.3 (4 runs) | 24% | 3.7-3.8 |
| tswg with change 12, and RPS on the router's NIC | 77.2-78.2 (4 runs) | 45-47% | 6.3-6.6 |
| wireguard-go | 6.1-6.2 (2 runs) | 4% | 7.4-7.6 |
Uploads (the earlier load) with change 12: 67.5-68.1 Gbps at 3.05-3.08 CPU-s/GB (before: 64-66 at 6.7-6.8); with RPS, 65 at 5.2. So run to completion is 11x wireguard-go in both directions, at under half its CPU per GB, and fetches at 0.87x plain routing with RPS.
Change 11 alone more than doubled it in 8 of 14 runs, and added 10-20%
in the rest. Without change 12, the router is bound by one lock, and the
bimodality is unexplained: in both modes, 75-83% of the router's CPU is
spinning on the encrypt ring's consumer lock (ptr_ring_consume_bh in
wg_packet_encrypt_worker), with encryption itself 7%. Each entry is
one forwarded GRO packet, of a few segments (hundreds of interleaved
flows merge poorly), about a million a second, which one ring shared by
all CPUs' workers, as upstream has, can't take on two sockets. Uploads
don't have it (the decrypt ring gets fewer, bigger entries): 64 Gbps
before and after. Tried, and not kept (patches in the TODO list's
item): a ring per worker, as RPS does (no contention, but 3x slower:
entries for a newly recruited worker wait for its CPU to wake, and
uniformly so; also locally, 10.3 -> 7.2 Gbps); recruiting workers only
when the backlog exceeds one per active worker (no change: contention
slows consumption, which grows the backlog, which recruits more);
consuming up to 8 entries per lock (no change). Change 12 removes the
ring from the router's path instead.
With change 12, the router's 32 CPUs that take the NIC's interrupts (its
ENA has 32 queues) are at 100% and the other 96 idle, in both
directions, which caps it near 68 Gbps. RPS
(/sys/class/net/*/queues/rx-*/rps_cpus set to all CPUs) spreads the
work past the NIC's CPUs, by flow hash, so without reordering: fetches
gain 13%, uploads nothing (their limit is elsewhere), at more CPU per GB
for the extra handoff. tailscaled could set it on subnet routers; see
the TODO list. (Those numbers predate change 15, steering, which does
the same for received packets when a CPU is too busy; with it, RPS on a
host receiving tunneled traffic hurts: 81 -> 69 Gbps crawling.)
A big host on the tailnet (2026-11-08; TSWG_SUBNET_LOAD=serve and
crawl): the same c6in.32xlarge (128 CPUs, 32 NIC queues) as an
endpoint, with the 37 clients as its peers, 16 connections each, MTU
1280. Serving, the clients make HTTP-like requests of it (500 bytes, 1
MiB responses); crawling, it makes them of all the clients at once.
"Plain" is the same without a tunnel, its paths clamped to MTU 1280
(TSWG_SUBNET_PLAIN_MTU), so the network's limit with the same packet
sizes:
| big host | serve Gbps | CPU-s/GB | crawl Gbps | CPU-s/GB |
|---|---|---|---|---|
| plain (no tunnel) | 152 | 1.95 | 128 | 4.28 |
| tswg at change 12 | 84-98 | 4.2-4.5 | 41-51 | 6.3-6.5 |
| tswg with changes 13-15 | 133-137 | 3.9 | 80-83 | 5.8 |
| wireguard-go | 5.5-6.7 | 6.5-8.9 | 8.5 | 10.5 |
Serving reaches 0.88x plain, 0.93x counting WireGuard's 60 bytes of
overhead per packet, with no lock contention, the host's CPU 48% busy,
and none of EC2's allowances (ethtool -S's *_allowance_exceeded)
exceeded: the network's limit, near enough. Crawling is limited by the
NIC's queues: the 37 peers' UDP flows hash onto 23 of its 32 queues,
two or three to some, and those run at 660-680k packets per second each,
ENA's limit per queue, while 9 queues carry nothing; plain TCP spreads
592 flows evenly. More peers would even it out; fewer, faster ones, the
same NIC would cap. The NIC's CPUs do only the driver's work, with each
peer's crypto and TCP steered to its own CPU (change 15).
CPU accounting: rows before the last measured CPU from /proc/stat,
which on Ubuntu's AWS kernels (no CONFIG_IRQ_TIME_ACCOUNTING) counts
interrupt and softirq work done on otherwise idle CPUs as idle: it showed
plain routing at 9M packets per second as 1% busy, against 10.5% from
the CPUs' idle-state residencies, which netbench uses since 2026-11-07.
So earlier CPU-s/GB figures understate softirq-heavy work: plain routing
and kernel WireGuard most, tswg somewhat (its crypto runs in kworkers,
which /proc/stat counts), wireguard-go least (mostly user time).
- Limits: wireguard-go about 6-7 Gbps however many peers or CPUs (a
serial stage). tswg: on small routers, its CPUs; on the c7i.48xlarge,
EC2's packet rate allowance (about 12M packets per second through the
router at 40 Gbps); on the c6in.32xlarge (200 Gbps, and no EC2
allowance exceeded), about 75 Gbps, where the NIC's interrupt CPUs
saturate: ENA allocates a fresh page per received packet, and pages
allocated on one CPU and freed on another (transmit completions) contend
for the page allocator's zone lock, 14-20% of those CPUs, plus zeroing
(
init_on_alloc). Tried there, no better: RPS, bigger per-CPU page lists (vm.percpu_pagelist_high_fraction=8), capping wg0's GRO size (for hardware TSO on forwarding), and zero-copy receive (module parameterrx_zerocopy, off by default), which took tswg's own page allocations out (page zeroing 4.7% to 1.1%, zone lock time 9-11% to 7%) but cost more in scatterlist decryption: with 24 clients, 62.5-63.3 Gbps and 6.05 CPU-s/GB against 63.4-64.7 and 5.47 copying. So tswg's allocations weren't what binds; ENA's page per received packet is. More clients helped until about 40 (20: 56 Gbps, 40: 72, 60: 74). - On the big routers, tswg isn't CPU-bound (45% of 128 CPUs at 74 Gbps), so its CPU per byte is about even with wireguard-go's; where CPU is the limit, tswg uses about 0.6x wireguard-go's. Kernel WireGuard's per-packet round-robin worker kicks keep all of a big machine's CPUs busy (98% of 128 for 8 Gbps).
- Clients on c6in were c6in.2xlarge and c6in.large; none was busy (5-27% CPU), nor the backend (13%).
Point to point (TestLeanBenchmark, scripts/leanbench.sh): one tunnel
between two machines, 4 vCPUs each. Updated 2026-11-07; the QEMU lab's
TCP rows 2026-11-09, after change 20 below (TestLeanCompare, medians of
4 runs; kernel WG from before).
| testbed | metric | tswg | wireguard-go | kernel WG | tswg/wggo |
|---|---|---|---|---|---|
| QEMU lab (nested) | TCP 1 stream | 11.3 Gbps | 9.2 | 3.6 | 1.23x |
| QEMU lab (nested) | TCP 4 streams | 12.2 Gbps | 10.3 | 4.2 | 1.18x |
| QEMU lab (nested) | sender / receiver CPU-s/GB, 1 stream | 1.33 / 2.02 | 2.03 / 2.53 | 2.95 / 5.20 | 0.66x / 0.80x |
| QEMU lab (nested) | sender / receiver CPU-s/GB, 4 streams | 1.46 / 1.99 | 1.87 / 2.41 | 0.78x / 0.83x | |
| QEMU lab (nested) | UDP 64B received (loss) | 263k pps (0%) | 242k (79%) | 166k (16%) | 1.08x |
| QEMU lab (nested) | RTT idle / under load p50 | 0.51 / 1.50 ms | 0.60 / 1.79 | 1.07 / 1.07 | 0.85x / 0.84x |
| QEMU lab (nested) | RTT idle / under load p99 | 1.27 / 12.3 ms | 1.28 / 3.78 | 0.99x / 3.3x | |
| EC2 c7i.xlarge | TCP 1 or 4 streams | 7.25 Gbps | 7.25 | 5.3 | 1.0x (EC2's per-flow limit) |
| EC2 c7i.xlarge | sender / receiver CPU-s/GB, 1 stream | 2.48 / 2.47 | 2.59 / 2.97 | 2.68 / 3.80 | 0.96x / 0.83x |
| EC2 c7i.xlarge | UDP 64B received (loss) | 536k pps (0.06%) | 328k (58%) | 430k (1.7%) | 1.6x |
| EC2 c7i.xlarge | RTT idle / under load p50, before inline crypto | 0.92 / 0.82 ms | 0.47 / 3.57 | 0.85 / 1.28 | 1.96x / 0.23x |
| EC2 c6in.32xlarge | RTT idle / under load p50 | 0.75 / 1.61 ms | 0.97 / 3.92 | 0.77x / 0.41x | |
| EC2 c6in.32xlarge | RTT idle / under load p99 | 0.96 / 6.04 ms | 1.24 / 6.42 | 0.77x / 0.94x |
RTT rows are UDP ping-pong (TSWG_COMPARE_LOAD=rtt, medians of 4
runs), idle and under one TCP stream; updated 2026-11-08 with inline
crypto (item 9 below) and softirq NAPI. The kernel WG column is from
before.
wireguard-go at its best (2026-11-08)
So as not to misrepresent wireguard-go, its scaling with flow count, on
EC2, unmodified (Tailscale's fork as the harness runs it: tun.CreateTUN
with TUN offloads, conn.NewStdNetBind with UDP GSO and GRO), on the
c6in.32xlarge big host or router, against the 37 clients (which run
tswg, so as not to be the limit), 16 flows each unless noted. Gbps, with
the host's CPU-s/GB:
| scenario | 1 client | 4 | 16 | 37 | 37, 1 flow each | 37, 4 | 37, 64 |
|---|---|---|---|---|---|---|---|
| subnet router, upload | 6.3 (5.2) | 5.9 | 5.8 | 5.7 (7.6) | 7.5 (5.9) | 6.4 | 6.6 (8.3) |
| subnet router, fetch | 7.2 (4.8) | 8.0 | 7.2 | 7.7 (6.1) | 7.6 (5.4) | 7.4 | 6.6 (8.0) |
| big host, serve | 7.2 (3.6) | 8.2 | 7.9 | 7.1 (5.5) | 8.9 (4.2) | 7.4 | 6.1 (7.2) |
| big host, crawl | 7.2 (6.2) | 11.1 | 9.5 | 9.9 (7.2) | 11.2 (4.7) | 9.8 | 8.8 (8.1) |
- It's flat from one client: 6-11 Gbps whatever the number of peers or flows, best with fewer flows (more cost it CPU per GB and a little throughput), using 3-6% of the host's 128 CPUs, so it isn't CPU-bound but serialized: its TUN device's one queue, read and written by one goroutine each, and its UDP socket's one receive loop. Best seen: 11.2 Gbps (crawling, one flow per client).
- Go runtime settings don't change it (
TSWG_AGENT_ENV, checked to reach the agent): GOGC 400 or off, GOMAXPROCS 8, 16 or 32 are all within 5% of the defaults, in throughput and CPU per GB. - Serving and crawling run the load generator in the same Go process as wireguard-go (the agent), which could cost it; but as a router, where the load runs elsewhere, it does the same 6-8 Gbps.
- Point to point (hosts 0 and 1, both c6in.32xlarge, 1-128 TCP streams,
bulk and fetches), both data planes are held at 7.2-7.6 Gbps by EC2's
limit for one flow (the tunnel is one UDP flow), wireguard-go a little
ahead at 64-128 streams (7.6 against 7.4). But there tswg uses more
CPU per GB than wireguard-go, more so with more streams: bulk,
sender 4.4 -> 7.7 CPU-s/GB from 1 to 128 streams (wireguard-go
3.7-4.4), receiver 4.2 -> 10.7 (4.9-5.6); fetches, sender 7.1 at 128
(4.1). And one fetch stream gets 2.7 Gbps to wireguard-go's 3.5. On a
128-CPU host, tswg's parallel paths (crypt workers, a fast peer's
receive) spread one tunnel's work over far more CPUs than 7 Gbps
needs. Fixed by changes 17-18 (same day, same pair, interleaved
runs, Gbps and CPU-s/GB, sender / receiver):
load tswg wireguard-go tswg/wggo CPU bulk, 1 stream 7.2; 2.1 / 2.6 7.1; 4.1 / 4.9 0.52x / 0.52x bulk, 16 7.3; 3.1 / 4.2 7.1; 4.2 / 5.3 0.74x / 0.79x bulk, 128 7.4; 4.1 / 5.9 7.4; 4.4 / 5.8 0.94x / 1.02x fetch, 1 stream 3.0; 3.4 3.3; 5.5 0.63x (0.91x the throughput) fetch, 16 7.3; 3.0 7.2; 3.7 0.80x fetch, 128 7.2; 3.9 6.9; 4.3 0.91x
tswg in the same sweep (after a reboot, before change 16 below, so on the unlucky NIC queue spread described there) reached 7.3, 29, 71 and 95 Gbps where wireguard-go did 6-8: at 16 clients and up, 4-14x wireguard-go's throughput at 0.6-0.95x its CPU per GB, but with one client, the same throughput (EC2's flow limit) at up to 1.4x its CPU.
The NIC's queue spread is luck: Linux picks the RSS hash key at random
each boot, and with only 37 peers' UDP flows, one boot spread them over
23 of the router's 32 queues, the next over 11. That changed tswg's
results more than any of the work after change 12 (uploads 68 -> 28
Gbps, serving 133 -> 99, crawling 81 -> 42), and doesn't affect
wireguard-go's, which don't reach the NIC's limits. Benchmarks with few
peers should check the spread (ethtool -S's queue_N_rx_cnt); change
19 rebalances it.
After changes 17-19 (another boot; TSWG_SUBNET_RSS_BALANCE had
rebalanced the router's NIC): upload 74, fetch 70, serve 131 and crawl
97 Gbps, at 4.8, 4.3, 3.3 and 6.7 CPU-s/GB. Squeezing the router's RSS
table onto 11 queues (ethtool -X equal 11, like the unlucky boot),
upload fell to 64 and crawl to 72; balancing brought them back to 72
and 78.
What we inherit from upstream WireGuard
- Inner GSO on send: the device advertises GSO (
WG_NETDEV_FEATURESindevice.c), so the stack hands it large TCP super-packets, whichwg_xmitsegments (skb_gso_segment) before encrypting each segment. - Inner GRO on receive: decrypted packets go up through each peer's NAPI
context with
napi_gro_receive(receive.c), so the stack sees coalesced inner packets. - Parallel encryption and decryption across CPUs (per-device crypt workqueue), with per-peer ordering.
What upstream lacks: outer UDP GSO and GRO. Every encrypted packet took its own trip through the UDP/IP stack and the NIC in both directions. These are the kernel analogues of what makes wireguard-go fast, and were the biggest levers; see the next section.
What tswg changes (2026-11-07)
Profiled with the lean harness's sampling profiler (below), then fixed in this order. Each step's throughput is bulk TCP, 1 stream, IPv4, 4 vCPUs.
- Crypt worker kicks (3.6 -> 5.0 Gbps). Upstream queues the next CPU's
crypt worker for every packet, round robin, which usually means an
IPI (a VM exit in a VM); on receive, that was half of the softirq
CPU. Now a packet needs no kick while some worker is draining the
ring (
tswg_busy, paired with the ring under full barriers), and we recruit another CPU's worker only when the backlog shows the busy ones falling behind (tswg_crypt_kick). Workers polling the ring for 20us before going idle, to save more IPIs, didn't help and isn't used. - Outer UDP GSO on send (-> 5.8). First by chaining encrypted packets as
a GSO
frag_list, which needed the packets orphaned (segmenting a frag_list of TCP-owned packets underflowedtcp_wfree's refcount), and whose segmentation copied each packet again. Replaced by: - Encryption into page frags (
tswg_encrypt_list, same throughput, sender CPU 65% -> 43%). Rather than linearize each packet (skb_cow_data, a copy) and encrypt in place, the encrypt worker copies it into pages of its own (computing the inner checksum on the way, asskb_checksum_helpwould), encrypts it there, and gathers each run of equal-size messages into oneSKB_GSO_UDP_L4packet whose payload is those pages. Segmenting that needs only page references, and a NIC with UDP segmentation offload (virtio with USO, here) takes it whole. - Peer queue length. The in-order per-peer queue (
prev_queue) overflowed at upstream's 1024 packets whenever a decrypt worker was held up, silently, and TCP took the drops as congestion. Its limit now counts packets, not entries (a GRO entry is up to 64), at 2048, and drops are counted inrx_droppedandrx_fifo_errors. - Outer UDP GRO on receive (-> 9.6). Our sockets have
gro_receiveandgro_complete, as UDP tunnels do. They merge consecutive data messages of a flow that use the same key and are all the same size but perhaps the last; UDP then hands the merged packet (SKB_GSO_UDP_TUNNEL) toencap_rcvwhole (without the tunnel type, UDP would segment it first, with software checksums). It goes through the decrypt ring and the peer's queue as one entry, and one worker decrypts each message into a new packet (tswg_decrypt_gso).skb_gro_receiveisn't exported, so socket.c has a copy (tswg_gro_merge). - Freeing on the tx worker (-> 10.4). Freeing the original packets in the encrypt workers ran TCP's small queues handlers on all of them at once, contending for the socket lock.
- Backpressure (TSQ). Upstream encrypts in place, so a packet stays
charged to its socket until the NIC has sent it, and TCP is held to
the NIC's pace. Our encrypted packets are new, so without care TCP
could fill the NIC's qdisc as fast as we encrypt, which on a slow
uplink with a FIFO qdisc would be massive bufferbloat. So the
encrypted packet takes over the socket's ownership and charge
(
tswg_move_owner, only for destructors that just unchargetruesize:sock_wfreeand TCP's), with the charge settled to its real size (tswg_settle_charge; segments'truesizeis about twice their length). That cost throughput, since TCP's small queues allow only about 1ms of data in flight, so we set TCP sockets'sk_pacing_shiftto 9 (about 2ms) as Wi-Fi drivers do (8) for their aggregation. - Where the tx worker runs. Upstream pins a peer's tx worker to one CPU by peer ID. When that's the CPU taking the NIC's interrupts, softirq work starved it, and encrypted packets waited up to 20ms to be sent. It's now queued on the CPU that finished encrypting.
- Inline crypto for lone packets (idle RTT p50 in the lab 0.92 ->
0.51ms, wireguard-go 0.60; on EC2 0.75ms against 0.97). Every
handoff to a worker on another CPU can wake a halted vCPU, a VM exit
and a trip through the host's scheduler. So a packet that isn't part
of a batch (not GSO) is encrypted or decrypted where it is when the
workers look idle (
tswg_crypt_idle: empty ring, last-kicked worker not busy), after going on the peer's in-order queue as usual. Under load, workers drain TCP ACKs fast enough that the ring often looks empty, and inlining them moved that work onto the CPUs taking the NIC's interrupts: 8% off a subnet router. Two limits fixed that: at most 8 inline packets per CPU per jiffy (tswg_inline_ok), and no inline encryption from softirq (forwarding, and replies sent from softirq), which alone left 6% behind. Module parameterinline_cryptoturns it off. - NAPI in softirq, not threads. Upstream has each peer's NAPI run in
a kthread (
netif_threaded_enable), one more wakeup per received packet. Threads give a CPU-bound subnet router 4-5% more throughput, but cost idle latency, so it's softirq unless module parameternapi_threadedis set (or per device,/sys/class/net/*/threaded). - Encryption straight from GSO packets (2026-11-08; lab, 1 stream:
10.5 -> 12.2 Gbps, sender CPU 1.82 -> 1.21 CPU-s/GB).
wg_xmitsegmented GSO packets withskb_gso_segment(skb, 0), as upstream does, which with no features also copies and checksums each segment's payload into a new linear packet, after which we copied it again to encrypt it. Now TCP and UDP GSO packets (from local sockets, or made by GRO and being forwarded) stay whole (tswg_gso_whole_ok), get a block of nonces, andtswg_encrypt_listwrites each segment's plaintext straight into our pages: the headers, fixed up as TCP's, UDP's, IPv4's and IPv6's segmentation would (tswg_copy_segment), and its slice of the payload, checksummed while copied. The socket's ownership goes to every packet a GSO packet is encrypted into, as segmentation would. Others (untrusted, tunnels, frag lists, timestamps) are still segmented, but withNETIF_F_SG | NETIF_F_HW_CSUM, so that segments share pages and we checksum them while copying (that alone was 10.5 -> 11.7 Gbps). Forwarding (a LAN host behind the sender, whose packets GRO merges): 5.3 -> 5.8 Gbps. Module parametergso_wholeturns it off;verify_gso(tests) checks every segment againstskb_gso_segment's, whichTestLeanGSOVerify(TCP and UDP GSO, IPv4 and IPv6) andTestLeanGSOVerifyForwardeddo, finding them byte-identical (millions of segments, on the debug kernel too). - Run to completion (2026-11-08; EC2 subnet router fetches, 37 -> 69
Gbps, 27 -> 3.7 CPU-s/GB; uploads 6.8 -> 3.1 CPU-s/GB). The life of a
forwarded packet through upstream's design: on the NIC's CPU, the
peer's staged queue (a spinlock), a nonce and keypair reference
(atomics), the peer's in-order queue (an
xchg), the device's encrypt ring (its producer lock, shared by all CPUs) and a kick of a worker on another CPU (often an IPI); on that CPU, the ring's consumer lock (shared by all workers: the 80% hotspot), encryption, and a kick of the peer's tx worker; on a third CPU, the send. All of that is to encrypt one flow's packets on many CPUs and put them back in order, which forwarded packets don't need: RSS already spreads flows over CPUs and keeps each in order on one. So:
- Transmit:
tswg_xmit_nowencrypts and sends packets with no socket (forwarded) right inwg_xmit, on the CPU they arrived on, as IPsec does: no queues, no locks but the peer's endpoint rwlock, no other CPUs. (Not the earlier softirq starvation, which came from handing work to a worker on a CPU busy with softirq work; this is that work.) Local sockets' packets still go to the workers, to encrypt one flow on several CPUs: "in softirq" alone isn't "forwarded", since much of a TCP sender's sending happens in softirq, as ACKs arrive, and inlining those cost one stream half its throughput. Module parametertx_inline(0 never, 1 forwarded, 2 always). - Receive:
tswg_receive_nowdecrypts a peer's packets inencap_rcv, on the CPU its UDP flow arrives on, and delivers them through the device's per-CPU GRO cells (as VXLAN does), rather than through the decrypt ring, a worker, the peer's in-order queue and its NAPI on yet another CPU. That's one CPU per peer, which a fast peer outruns (one TCP stream: 12.2 -> 6.4 Gbps in the lab), so a peer receiving more thanrx_inline_mbps(default 4000) over 10ms goes the parallel way for at least 100ms, and comes back once that way has delivered all it had, so switching doesn't reorder (but for packets still in the peer NAPI's GRO list as its queue empties). Over a jiffy, GRO's bursts pushed a router's 2 Gbps peers over the threshold, halving uploads. Tried and not kept: a share of each CPU's time for inline transmit, handing off the rest (it reorders flows at every switch); in the lab, inline transmit's per-send virtio notifications (each a VM exit) make forwarding from one veth slower, which EC2's ENA doesn't.
- Sending by combining (2026-11-08). A peer's encrypted packets were
sent in order by its tx worker, one work item, which ran on one CPU at
a time; on a device without UDP segmentation offload (ENA), the
sending CPU also segments what we send, so serving 37 peers, the CPUs
their tx workers landed on ran at 90% and more. Now the encrypt
worker that makes an entry ready sends what's ready in order itself,
if no other CPU is sending the peer's (
tswg_tx_lock, a trylock), and otherwise leaves it to the one that is (tswg_tx_more): still one CPU at a time per peer, so in order, but moving among the CPUs encrypting for it, with no workqueue hop (tswg_tx_kick). - Local sockets' lone packets (TCP's ACKs, small requests) are
encrypted and sent inline too (
tswg_xmit_now), when nothing of the peer's is on its way through the workers, so as not to overtake it: a crawling host spent 7% of its CPU on the encrypt ring's lock for its ACKs. Bulk (GSO) sends still go to the workers. - Steering (
tswg_steer). With more peers than NIC queues, RSS puts several peers' UDP flows on some CPUs and none on others, and receiving inline (change 12) left a crawling host's NIC CPUs at 100% and the rest idle. So when a CPU is too busy (overrx_steer_busy, default 90%, of its last 10ms, fromget_cpu_idle_time_us, or its softirq work out of budget or time,softnet_data.time_squeeze, which alone triggered too rarely), the packets of the peers arriving on it go, for at least a second, to each peer's home CPU: one not itself receiving from a NIC or overloaded, from a point the peer's ID hashes to (tswg_peer_home), through a lockless per-CPU list, an IPI per batch, and that CPU's NAPI, which receives them astswg_receive_nowdoes. It's RPS, per peer and for our packets only, and only when needed. A peer changes between inline, steered and the parallel way only when nothing is on its way the way it was going, so its packets don't reorder (tswg_rx_path). Crawling: 63 -> 81 Gbps. Homes hashed over all CPUs, without avoiding the NIC's, did nothing; RPS (all packets, all the time) got 91 before steering, at 7.0 CPU-s/GB to steering's 5.8. - Picking steering homes by load (2026-11-08). Homes were the first
CPU from a hashed point that wasn't receiving from the NIC or known
to be overloaded, but a CPU knew its own load only when it received
from the NIC itself, which homes don't, so busy homes looked idle and
peers piled onto a few. Now any CPU's load comes from its idle time
(
tswg_cpu_busy, which readsget_cpu_idle_time_usfor any CPU), and a peer's home is the least loaded of 8 spread from its hash, kept while underrx_steer_busy. On the unlucky boot's 11 queues: uploads 28 -> 44 Gbps, crawling 42 -> 51, serving 99 -> 101. - Fewer crypt workers for a tunnel (2026-11-08). One 7 Gbps tunnel on
a 128-CPU host had its crypt work on 33 CPUs, each about 15% busy,
mostly waking up and going back to sleep, with twice wireguard-go's
context switches: up to 1.6x its CPU per GB. A worker was recruited
whenever more than a batch's worth (one GRO packet) waited, which
GRO's bursts always did. Now another is recruited only when more
than
recruit_factor(default 16) times that waits for each worker draining (but never more than a quarter of the ring), and from a compact set of CPUs after the caller's, twice as many as were draining at once in the last 10ms (tswg_crypt_recruit_cpu), rather than round robin over all CPUs. Bulk, 16 streams: sender 4.4 -> 2.9 CPU-s/GB, receiver 7.1 -> 4.2, at the same throughput. Tried and not kept: crypt workers polling for 20-100us before sleeping (more CPU); sorting a peer's decrypted packets by flow before GRO (GRO already merged better than wireguard-go's: 38 TCP segments per MB to its 50); running the peer's NAPI straight from the decrypt worker. - Inline sends and receives for slow peers. A local socket's bulk
(GSO) sends to a peer sending under
tx_inline_mbps(default 2000) over 10ms are encrypted and sent inline, as forwarded packets are (change 12), rather than handed to a worker: for request/response traffic, that handoff is on every response's critical path. Andrx_inline_mbpsis now 1000 (from 4000), so a peer receiving over that goes the parallel way sooner. One HTTP-like stream between big hosts: 2.5 -> 3.0 Gbps (wireguard-go 3.3); crawling 37 peers, 76 -> 89 (at 5.9 -> 7.1 CPU-s/GB); routers and servers unchanged. Not TCP small queues: withouttswg_move_owner, the stream was no faster. - Balancing the NIC's RSS table (tailscale.com
wgengine/tswg/rss). With few peers, the RSS hash key decides how many queues their flows get (change 16's boots: 11 or 23 of 32), and the busiest queues, at ENA's per-queue packet rate limit (about 700k/s), cap the host. ENA's hash couldn't be reproduced from the key and table it reports (no variant of Toeplitz on the 2- or 4-tuple matched), sorss.Balancemeasures: per-queue packet rates from the driver's counters, then each busy queue's table entries' loads by pointing them at idle queues for 300ms, then a bin-packing of the entries onto the queues. Entries carry several flows (37 flows used 19 of 128 entries), so first it tries 8 random hash keys with an even table, keeping the one whose busiest queue is lightest. Each move can reorder a few of a flow's packets. The bench agent's/rss-balanceruns it; tailscaled doesn't yet (see the TODO list). - Fixing changes 17 and 18 for small hosts (2026-11-09). They cost one TCP stream in the QEMU lab (4 vCPUs) a third of its throughput, 11.5 -> 7-8 Gbps, unseen on EC2, where both data planes were at its per-flow limit. Two causes, each needed for the fix:
- The sender, held to a few GSO packets in flight by TCP Small
Queues, never had
recruit_factor's worth waiting, so its stream got one encrypt worker. Now the firstrecruit_free(default 2) draining workers are recruited at the old backlog; past that, change 17's applies, so a big host still can't spread one tunnel wide. tswg_tx_slowreset its count every 10ms window, so the firsttx_inline_mbps' worth of every window was encrypted inline, however fast the peer was sending: at 11 Gbps, 18% of the stream on the sending CPU. Now, as on receive, a peer that went over the rate in any window counts as fast for 100ms.
And the until-jiffies (tswg_tx_fast_until, tswg_rx_parallel_until,
tswg_rx_steer_until) start at the peer's creation, not 0, which
jiffies, starting 5 minutes short of wrapping, are before until
then: so in freshly booted VMs, the lab's included, every peer had
received the parallel way and steered for the first 5 minutes. (That
didn't change the lab's idle RTT, which is noisy, 0.27-0.60ms either
way.) One stream: 7.1 -> 11.3 Gbps (wireguard-go 9.2), at 1.33 / 2.02
sender / receiver CPU-s/GB (1.58 / 2.13). Round-robin recruitment
instead of change 17's compact set made no difference. Big hosts'
CPU per GB with this (the reason for change 17) is to be rechecked
on EC2.
The lean harness's VMs have guest USO off (decided 2026-11-07): with it,
the host hands VM-to-VM UDP GSO packets to the receiving guest still
coalesced, which no physical network does and which flatters UDP data
planes (wireguard-go got 10.5 Gbps with it, 10.0 without).
TSWG_LAB_GUEST_USO=1 turns it back on.
Measuring
Two harnesses:
- natlab (
TestTSWGBenchmark, run withscripts/bench.sh): full tailscaled in TUN mode (wireguard-go) versus tailscaled in kernel mode, on the same pair of gokrazy VMs on one natlab LAN. tta's/tswg/bench/endpoints provide the tools (gokrazy has none): a TCP sink, TCP senders (1 and 4 streams), a 64-byte UDP flood, UDP ping-pong for RTT (idle and under a TCP load), and/proc/statCPU snapshots (busy time excluding idle, iowait and steal). Results are printed as a table and written as JSON. natlab's vnet is a userspace switch in the test process, which costs a lot on the host (the test process ran at 120-150% CPU and each QEMU at 200-260% during TCP runs) and caps throughput, so this harness is for full-stack comparisons and the CPU cost inside the VMs, not absolute numbers. - A lean harness without natlab (decided 2026-11-07; natlab "was never
meant to be fast"), in tailscale.com's
tstest/tswgbench, run withscripts/leanbench.sh(-smokefor the quick correctness test). See "Lean benchmark harness" below.
First natlab results, 2026-11-07 (2 vCPUs per VM, 10-second runs, three runs; the numbers below are from run 2, and runs 1 and 3 agreed within a few percent):
| metric | wireguard-go | tswg | tswg/wg |
|---|---|---|---|
| TCP 1 stream, Mbps | 2455 | 2392 | 0.97x |
| TCP 1 stream, sender / receiver CPU-s per GB | 4.06 / 4.83 | 3.93 / 4.67 | 0.97x / 0.97x |
| TCP 4 streams, Mbps | 2966 | 2856 | 0.96x |
| TCP 4 streams, sender / receiver CPU-s per GB | 3.54 / 4.59 | 3.58 / 4.40 | 1.01x / 0.96x |
| UDP 64B received, pps | 93k | 156k | 1.68x |
| UDP 64B receiver CPU per packet, us | 12.3 | 8.6 | 0.70x |
| RTT idle p50 / p99, ms | 1.29 / 2.61 | 1.30 / 2.20 | 1.01x / 0.84x |
| RTT under TCP load p50 / p99, ms | 2.92 / 7.86 | 1.53 / 4.68 | 0.53x / 0.60x |
Takeaways from natlab (but see the lean harness results below, which overturn the first one):
- Bulk TCP: neither VM was CPU-saturated (50-80% of 2 vCPUs), so throughput is capped by natlab, and the CPU cost per byte is about the same.
- Small packets: the kernel delivers about 1.7x the packets per second at about 30% less CPU per packet.
- Latency under load: the kernel roughly halves RTT p50 and p99 while a TCP stream runs; idle RTT is about the same.
Lean benchmark harness
tstest/tswgbench in tailscale.com (2026-11-07):
- Two QEMU VMs (q35, KVM,
-cpu host, N vCPUs and N virtio-net queues) on a host bridge (tswgb-br, 10.77.0.0/24 and fd77::/64) with multiqueue taps and vhost-net. Creating the bridge and taps needs passwordless sudo; the taps are owned by the user so QEMU isn't root. Everything is removed afterwards. - The VMs boot the natlab gokrazy kernel with a tiny gzipped cpio
initramfs:
/initis a static Go agent (tstest/tswgbench/agent), plus/tswg.ko. Booting takes about a second. - The agent brings up eth0 from the kernel command line and serves an
HTTP API: set up
wg0with one of the data planes, tear it down, show the device, and the sharednetbenchendpoints (the same benchmark code tta serves for natlab, now intstest/tswgbench/netbench). - Data planes:
plain(no tunnel, the ceiling),kernelwg(the kernel's own WireGuard, driven by the tswg Go client with family "wireguard"),tswg, andwggo(Tailscale's wireguard-go fork with a TUN device and its standard bind, so TUN offloads and UDP GSO/GRO, as tailscaled uses, but without magicsock). All tunnels use MTU 1280, as Tailscale does. TestLeanSmoke(about 25 seconds) checks every data plane over IPv4 and IPv6 underlays, which natlab can't (it's IPv4-only here).TestLeanBenchmarkruns the suite for each.
First results, 2026-11-07, IPv4 underlay, 4 vCPUs per VM, 10-second runs (IPv6 is within a few percent; tswg and kernel WireGuard are the same within noise everywhere, so the fork costs nothing):
| metric | wireguard-go | tswg | kernel WG | plaintext |
|---|---|---|---|---|
| TCP 1 stream, Mbps | 10498 | 3645 | 3647 | 16449 |
| TCP 1 stream, sender / receiver CPU (% of VM) | 58 / 62 | 29 / 55 | 29 / 56 | 21 / 15 |
| TCP 1 stream, sender / receiver CPU-s per GB | 1.96 / 2.06 | 3.00 / 5.20 | 2.95 / 5.22 | 0.45 / 0.31 |
| TCP 4 streams, Mbps | 12577 | 4376 | 4380 | 47158 |
| UDP 64B received, pps | 234k | 174k | 170k | 874k |
| UDP 64B receiver CPU per packet, us | 6.7 | 9.2 | 9.3 | 1.3 |
| RTT idle p50 / p99, ms | 0.57 / 1.33 | 0.63 / 2.13 | 0.70 / 1.78 | 0.24 / 0.92 |
| RTT under TCP load p50 / p99, ms | 1.43 / 2.85 | 1.20 / 5.29 | 0.99 / 5.33 | 0.20 / 0.74 |
Takeaways:
- Kernel WireGuard, as upstream designed it, is far behind Tailscale's wireguard-go for bulk traffic: about a third of the throughput, at 1.5x (sender) to 2.5x (receiver) the CPU per byte. It isn't CPU-bound either (29% and 55% of 4 vCPUs), so something serializes it. The natlab results only looked like parity because natlab capped both.
- Likely causes, to verify by profiling: every 1280-byte packet takes its own trip through the UDP/IP stack and the NIC in both directions (no outer UDP GSO on send, no UDP GRO on receive), while wireguard-go batches with UDP GSO/GRO and TUN offloads; the single WireGuard UDP flow lands on one NIC RX queue and so one CPU; and each peer's decrypted packets go through one NAPI context.
- So outer UDP GSO/GRO, and finding where the kernel serializes, are the critical performance work, ahead of everything else. tswg's reason to exist is to beat wireguard-go, and today it doesn't on bulk throughput.
- Small packets are closer: the kernel receives 0.75x the packets of wireguard-go, but at much lower loss (wireguard-go accepts far more from the sender than it can deliver), and at 1.4x the CPU per packet.
- Latency: the kernel is a little worse idle, better at p50 under load, and worse at p99 under load.
Results after the work in "What tswg changes", 2026-11-07 (same setup,
but guest USO off; one 10-second run of each, so expect a few percent of
noise; scripts/leancompare.sh gives medians of interleaved runs, which
put TCP 1 stream at 10.1 vs. 9.7 Gbps and 4 streams at 12.3 vs. 10.8):
| metric (IPv4; IPv6 in parentheses) | wireguard-go | tswg | tswg/wg |
|---|---|---|---|
| TCP 1 stream, Mbps | 10158 (9929) | 10220 (9474) | 1.01x (0.95x) |
| TCP 1 stream, sender / receiver CPU-s per GB | 1.93 / 2.37 | 1.81 / 2.12 | 0.94x / 0.90x |
| TCP 4 streams, Mbps | 11133 (11146) | 11707 (11621) | 1.05x (1.04x) |
| TCP 4 streams, sender / receiver CPU-s per GB | 1.84 / 2.31 | 1.87 / 2.14 | 1.01x / 0.93x |
| UDP 64B received, pps (loss) | 242k (79%) | 263k (0%) | 1.08x |
| UDP 64B receiver CPU per packet, us | 7.3 | 5.2 | 0.72x |
| RTT idle p50 / p99, ms | 0.61 / 1.27 | 0.92 / 1.95 | 1.50x / 1.53x |
| RTT under TCP load p50 / p99, ms | 1.57 / 3.16 | 1.49 / 11.68 | 0.95x / 3.69x |
Takeaways:
- Bulk TCP: tswg went from 0.35x to parity or a little better with one stream, and ahead with four, at 6-10% less CPU per byte, so it should pull further ahead where CPU is the limit. From 3.6 Gbps to 10.2, mostly from outer GSO and GRO.
- Small packets: tswg delivers everything it's sent, at 0.6-0.7x wireguard-go's CPU per packet. (It sends fewer because the sender's socket now waits for the NIC, as it should.)
- Idle latency was worse (since fixed by inline crypto; see "Results at
a glance"), and it's the VM: with the guests booted with
idle=poll(TSWG_LAB_CMDLINE=idle=poll), so that waking a vCPU costs nothing, tswg's idle RTT p50 is 0.08ms, against 0.14 for wireguard-go and 0.06 without a tunnel, and under load 0.71 / 1.70ms (p50 / p99) against 1.07 / 2.36. Each of tswg's handoffs (to an encrypt worker, the tx worker, a decrypt worker, the peer's NAPI thread) can wake a halted vCPU, which costs a VM exit and the host scheduling the vCPU's thread, while wireguard-go's goroutines mostly find their Ps spinning. Cloud VMs pay this too, so it's worth fixing; see the TODO list. - p99 under load is worse, and isn't explained yet: instrumenting the queues showed that at full load the receiving VM's crypt workers and tx worker sometimes didn't run for 10-40ms, with entries waiting in the decrypt ring and the tx queue. The host here is itself a VM, with 16 CPUs for 8 vCPUs and 8 busy vhost threads; check on bare metal and with fewer queues before redesigning around it.
On EC2 (2026-11-07), with the lean harness in remote mode (below): two c7i.xlarge instances (4 vCPUs, Nitro, ENA, Ubuntu 24.04's 7.0.0-1014-aws kernel) in a cluster placement group in us-west-2, one level of virtualization instead of the lab's two:
| metric (IPv4; IPv6 in parentheses) | wireguard-go | tswg | kernel WG |
|---|---|---|---|
| TCP 1 stream, Mbps | 7244 (7027) | 7253 (7033) | 5349 (6605) |
| TCP 1 stream, sender / receiver CPU-s per GB | 2.59 / 2.97 | 2.48 / 2.47 | 2.68 / 3.80 |
| TCP 4 streams, Mbps | 7265 | 7266 | 5646 |
| TCP 4 streams, sender / receiver CPU-s per GB | 2.53 / 2.95 | 2.59 / 2.94 | 2.70 / 3.80 |
| UDP 64B received, pps (loss) | 328k (58%) | 536k (0.06%) | 430k (1.7%) |
| UDP 64B receiver CPU per packet, us | 3.5 | 2.4 | 4.9 |
| RTT idle p50 / p99, ms | 0.47 / 0.71 | 0.92 / 1.18 | 0.85 / 1.23 |
| RTT under TCP load p50 / p99, ms | 3.57 / 5.12 | 0.82 / 5.01 | 1.28 / 3.13 |
- Both tunnels hit the same cap of about 7.25 Gbps (inner), with 1 or 4 streams: EC2's limit for the one outer UDP flow (or its packet rate), not either data plane. So on EC2, CPU per byte is what tells them apart: tswg's receiver uses up to 17% less, and the sender up to 7%. Smaller instances (c7i.large), where CPU is the limit, are next.
- Small packets: 1.6x wireguard-go's packets delivered, at 0.7x the CPU.
- Latency under load: p50 is a quarter of wireguard-go's (TCP backpressure keeps tswg's queues short), p99 the same (IPv6: 2.3x).
- Idle latency was about twice wireguard-go's, as in the lab, so the vCPU-wakeup cost of tswg's handoffs (see above) is real on Nitro too. Inline crypto fixed it (2026-11-08): on a c6in.32xlarge pair, idle p50 / p99 is 0.75 / 0.96ms against wireguard-go's 0.97 / 1.24.
Subnet router (2026-11-07)
Tailscale's most important server role for customers: clients on the
tailnet reach a private LAN (10.0.0.0/24, say) through a subnet router,
which forwards between its tunnel and the LAN, masquerading the clients
(the default, --snat-subnet-routes); the LAN's machines aren't on
Tailscale. wireguard-go is known to fall over with many clients and
flows. TestLeanSubnetRouter (scripts/subnetbench.sh [ROUTER_CPUS...])
sets this up on EC2: a router (c7i.16xlarge, 25 Gbps, with CPUs taken
offline to make CPU the limit), a backend on the same VPC subnet (also
c7i.16xlarge), and 4 clients (c7i.4xlarge) running tswg, each a peer of
the router, each with 16 TCP flows to the backend at once. plain
routes the clients through the router without a tunnel: the ceiling.
| router CPUs | tswg | wireguard-go | kernel WG | plain | tswg/wg |
|---|---|---|---|---|---|
| 4 | 13976 Mbps (96% CPU) | 6627 (68%) | 9756 (91%) | 24890 | 2.1x |
| 8 | 21868 (86%) | 6808 (39%) | 10009 (70%) | 24897 | 3.2x |
| 16 | 22654 (49%) | 8217 (19%) | 11489 (65%) | 24898 | 2.8x |
| 8, 64 flows per client | 21088 (91%) | 6490 (41%) | 9665 (74%) | 3.2x |
Router CPU seconds per GB forwarded: tswg 2.3-2.9, wireguard-go 2.9-4.2, kernel WireGuard 3.2-7.3, plain 0.2-0.4. Medians of 3 interleaved runs.
- tswg scales with the router's CPUs until the network is the limit (at 16 CPUs, 22.7 Gbps of inner traffic is about the 25 Gbps link with WireGuard's overhead), at the lowest CPU cost per byte.
- wireguard-go uses about 3 CPUs however many it has (2.7 of 4, 3.1 of 8, 3.0 of 16), with the rest idle: each peer is capped at about 1.6 Gbps by a serial stage (its profile is mostly idle CPUs and context switches; most likely each peer's receive goroutine, which writes to TUN), so it only scales with more peers. Every tswg client got at least 4.6 Gbps.
- Upstream kernel WireGuard does better than wireguard-go but well below tswg, and least fairly (clients from 0.8 to 2.8 Gbps).
With many more peers (20 clients: the 4 above plus 16 c7i.large, 8 flows each, 160 flows; after the optimizations below):
| router CPUs | tswg | wireguard-go | kernel WG | plain | tswg/wg |
|---|---|---|---|---|---|
| 4 | 13893 Mbps (2.38 CPU-s/GB) | 6268 (3.87) | 10155 (3.35) | 24908 | 2.2x |
| 8 | 23031 (2.62) | 6444 (4.56) | 16935 (3.98) | 24940 | 3.6x |
wireguard-go doesn't scale with peers either (6.4 Gbps with 4 or 20, at 45% of 8 CPUs), so its limit is global rather than per peer: most likely its one goroutine reading the UDP socket. Upstream kernel WireGuard scales with peers (each has its own tx worker and NAPI), from 10.0 to 16.9 Gbps at 8 CPUs.
At 50 Gbps (2026-11-07): router and backend c7i.48xlarge (192 vCPUs, 50 Gbps), 8 clients c7i.8xlarge (12.5 Gbps sustained), 16 flows each, all 192 router CPUs:
| tunnel MTU | tswg | wireguard-go | kernel WG | plain |
|---|---|---|---|---|
| 1280 | 31504 Mbps (3.90 CPU-s/GB) | 7247 (3.87) | 12335 (94.7) | 49911 |
| 8920 | 49611 (2.18) | 17475 (1.86) | 49156 (15.0) | 49900 |
- Jumbo MTUs are rare among Tailscale's customers (decided 2026-11-07: the target is MTU 1280; jumbo results are only a data point). With them (the VPC's MTU is 9001), tswg forwards at line rate, 2.8x wireguard-go, using about 13 of the 192 CPUs. Kernel WireGuard gets there too but with 7x the CPU per byte: its per-packet round-robin worker kicks reach all 192 CPUs (at MTU 1280, 137 of them busy for 12 Gbps), which tswg's on-demand kicks avoid.
- At Tailscale's MTU, 1280, EC2 limits each NIC receive queue to about 715k packets per second (the router's ENA has 16), about 7.3 Gbps of tunnel packets, and a peer's tunnel is one UDP flow, so one queue: a single tunnel tops out there (tswg and wireguard-go alike, between any c7i sizes), and with 8 peers, flows collide on queues (4 clients on 3 queues: the two sharing got half each). More peers spread better; a larger MTU needs 7x fewer packets. The router's CPUs weren't the limit.
- With more peers at MTU 1280 (24 clients: the 8 above plus 16
c7i.2xlarge, 8 flows each, 192 flows), traffic spreads over all the
queues: tswg 39996 Mbps (4.49 CPU-s/GB, about 22 of the 192 CPUs busy),
wireguard-go 7107 (5.6x less), kernel WireGuard 13463 (78% of 192
CPUs). There the limit is EC2's packet rate allowance for the
instance (ENA's
pps_allowance_exceededrises during tswg's runs): at MTU 1280 everything the router handles is small (tunnel packets in, 1280-byte TCP segments out to the backend, ACKs both ways), about 12M packets per second at 40 Gbps. (The plain baseline isn't comparable here: without a tunnel, the clients' TCP uses the VPC's 9001-byte MTU.) - For more: instances with higher packet rate allowances, such as c6in (network optimized, up to 200 Gbps), which the IAM policy doesn't allow yet.
Profile of the tswg router at 4 CPUs (CPU-bound), before the
optimizations: ChaCha20-Poly1305 about 23% (of which 5.5% was a scalar
ChaCha20 block per message for its Poly1305 key), the ENA driver about
20%, packet allocation and freeing about 15%, copying decrypted messages
out 8%, zeroing new pages 5% (Ubuntu enables init_on_alloc).
- Kept: decrypting straight from the received packet when a message is
contiguous there (
tswg_contig), and our own ChaCha20-Poly1305 (tswg_aead.h), which gets the Poly1305 key in the same SIMD pass as the message by running ChaCha20 from block 0 over the 64 bytes before it too and XORing them back out. With 4 clients: 14.1 to 14.9 Gbps, 2.30 to 2.18 CPU-s/GB. - Tried, not kept: zero-copy receive (decrypting in place in the received
pages, handing out packets that reference them), 7% worse:
scatterlist decryption costs more than linear decryption of an L1-hot
copy, and page-fragment packets cost more downstream (header pulls for
NAT, more transmit descriptors). A page pool per decrypt worker for
decrypted packets, to avoid allocating and zeroing pages: they didn't
come back in time, so it still allocated, and was no better. Capping
wg0's
gro_max_sizeat 17 segments (so forwarded GRO packets have no frag_list and the NIC does TSO in hardware): worse, since bigger GRO packets save more in forwarding than software segmentation costs.
EC2 tooling: scripts/ec2.sh (up, start, stop, down, ssh,
status) manages instances in the sandbox account (profile
tswg-sandbox, us-west-2: the org's SCP allows only some regions, and
requires IMDSv2). Everything it creates is named bradfitz-tswg... and
tagged owner=claude-tswg, the only instances the IAM user may manage.
scripts/ec2-idle-stop.sh install sets up a systemd user timer on the
(always-on) dev host that stops the instances once
~/.cache/tslinux/ec2/last-used is 30 minutes old; ec2.sh and the
harness's remote mode touch it while in use. Remote mode
(TSWG_REMOTE=~/.cache/tslinux/ec2/hosts.json, which ec2.sh writes)
copies the agent and the module sources to the instances, builds tswg.ko
on each against its own kernel (with the compiler in /proc/version),
and runs the agent there under systemd; every lean test and script
(leanbench.sh, leancompare.sh) then runs unchanged.
Tools in the lean harness, for this kind of work:
TestLeanProfile(TSWG_LEAN_PROFILE=tswg,wggo): a sampling profiler in the agent (perf_event_open, since the VMs have no perf), per CPU, kernel and Go symbols;TSWG_PROFILE_FOCUS=symreports the call stacks of one symbol.TestLeanCompare(scripts/leancompare.sh): interleaved repeated runs, reporting medians, for A/B checks;TSWG_COMPARE_LOAD=rttfor latency.TestLeanDebug: counters (/proc/net/snmp,/proc/net/dev), the kernel log and the device after a short run.TSWG_DEBUG_KERNEL=1: boots a KASAN, lockdep, DEBUG_VM and DEBUG_NET build of the same kernel (scripts/gokrazy-debug-kernel.sh). Every lean test fails if a VM's kernel reports a bug.
Non-goals
- Upstreaming. tswg is an out-of-tree module, installed via DKMS or similar. We do not depend on upstream WireGuard accepting changes.
- Rust. Decided 2026-11-06: the in-tree Rust networking abstractions are too thin (no sk_buff, net_device, UDP tunnel, or lib/crypto bindings) and out-of-tree Rust modules need a kernel built with CONFIG_RUST and a matching rustc, which most distro kernels can't provide. Revisit later.
- Changing the WireGuard wire protocol. tswg must interoperate with every existing Tailscale peer running wireguard-go, including its hybrid post-quantum handshakes (see "Hybrid post-quantum handshakes").
- Multipath or "spray" sending in the kernel. When disco hasn't yet trusted a direct path, tailscaled sprays from userspace (see "DERP and spray").
Architecture
tailscaled (userspace)
control, disco, STUN, portmapper, DERP client
| genetlink "tswg" | owns the UDP socket(s)
v v
+---------------------------------------------+
| tswg.ko (fork of drivers/net/wireguard) |
| tailscale0 netdev, noise, allowedips, ... |
| encap_rcv on tailscaled's UDP socket: |
| WG messages -> kernel |
| everything else -> socket receive queue |
+---------------------------------------------+
Fork, not patches
tswg is a fork of the in-tree WireGuard driver, kept as close to upstream as possible so upstream security fixes merge cleanly.
- The fork's base is Linux 7.4-rc1's
drivers/net/wireguard(commit 6628e7d4c6b2).diff -r $LINUX/drivers/net/wireguard src, against a Linux tree at that commit, is the fork's delta (plus build files and compat headers); upstream changes since then are merged by hand. - Internal symbols keep their
wg_names. Unexported symbols in two modules don't conflict, so tswg.ko and the in-tree wireguard.ko (built-in or modular) can be loaded at the same time. Renaming them would make every upstream merge painful. - User-visible identifiers are renamed: module
tswg, rtnl link kindtswg(fromKBUILD_MODNAME), genetlink familytswg. - The uapi stays attribute-compatible with upstream WireGuard. New
attributes are only ever appended. That way wgctrl-go and a lightly
patched
wg(8)keep working by changing only the family name. - The uapi header is
src/include/uapi/linux/tswg.h. Upstream generates it, andsrc/generated/netlink.[ch], fromDocumentation/netlink/specs/wireguard.yamlwith YNL. For now we hand-edit the generated files; once we add attributes, keep a forked spec and regenerate with a kernel tree'stools/net/ynl/ynl-regen.sh(TODO).
Kernel compatibility
The fork's base is the newest upstream (currently 7.4-rc1). Older kernels
are supported through compat shims in src/compat/.
- Feature probes, not
LINUX_VERSION_CODEchecks (decided 2026-11-06; RHEL kernels carry years of backports, so version numbers lie).scripts/probe.shcompiles eachsrc/compat/probes/HAVE_*.cagainst the target kernel's build directory, in parallel (about one second in total), and writessrc/compat/generated/autoconf.h. The top-level Makefile runs it before every build. src/compat/compat.his force-included into every file and shims whatever is missing, mostly as macros or static inlines named like the new API, so upstream code stays untouched. The few spots that can't be shimmed from a header get small#ifdef HAVE_...blocks markedTSWG_COMPATin the.cfiles (currently onlydevice.c).- To add a shim: add a probe file, use its
HAVE_macro in compat.h, and build against both an old and a new kernel. - Use the kernel's lib/crypto (chacha20poly1305, blake2s, curve25519). Every distro kernel that ships WireGuard builds those libraries. Do not vendor crypto.
- Builds today: Ubuntu 6.8.0-106-generic (the natlab guest) and 7.0.0-1009-aws (the dev host). The 7.4 path itself (all probes succeeding) isn't verified yet, since that needs a configured and built 7.4 tree.
- Minimum kernel: TBD.
Userspace (Go) side
Decided 2026-11-06: the Go code lives in tailscale.com, because tailscaled is what will program the module.
tailscale.com/wgengine/tswg: netlink client for thetswggenetlink family (configure and dump devices).tailscale.com/cmd/tswgctl: a wg(8)-like debugging tool built on it.- The module itself is in the same repository, under
kernel/linux.
Kernel interface
Everything userspace can see of the module, in one place. The sections
after this one explain the reasons; this is the reference. The source of
truth is src/include/uapi/linux/tswg.h (and the policies in
src/generated/netlink.c); keep this in step with it.
Devices. A tswg device is an rtnetlink link of kind tswg
(ip link add tailscale0 type tswg), configured like any netdev
(addresses, routes, MTU, up and down) over rtnetlink. tailscaled names it
tailscale0. Per device in sysfs, /sys/class/net/DEV/threaded sets
whether its peers' NAPI runs in kthreads (see the napi_threaded module
parameter).
Genetlink family. tswg (WG_GENL_NAME), version 1
(WG_GENL_VERSION). It has upstream WireGuard's two commands and
attributes unchanged, so wgctrl-go and wg(8) work with only the family
name changed:
WG_CMD_GET_DEVICE(dump) andWG_CMD_SET_DEVICE(do), both needing CAP_NET_ADMIN in the device's user namespace (GENL_UNS_ADMIN_PERM). The family isnetnsok: commands act on devices in the caller's network namespace.- Our additions are only ever in one nested attribute per object, numbered
64, far above upstream's, so that upstream can keep appending its own:
WGDEVICE_A_TSWGin a device,WGPEER_A_TSWGin a peer. Unknown nested attributes, and unknown flag bits, are rejected by the policies (strict parsing,NLA_POLICY_MASK), so a newer tailscaled setting an attribute an older module doesn't know gets an error rather than being silently ignored.
Device attributes (in WGDEVICE_A_TSWG):
| attribute | type | direction | meaning |
|---|---|---|---|
TSWGDEVICE_A_SOCK_FD4 |
s32 | set | fd, in the caller's process, of a bound IPv4 UDP socket for the device to use instead of its own; -1 detaches it. See "Shared UDP socket". |
TSWGDEVICE_A_SOCK_FD6 |
s32 | set | the same for IPv6; the socket must be IPV6_V6ONLY. |
TSWGDEVICE_A_FLAGS |
u32 | get | TSWGDEVICE_F_USER_SOCK4 (1), TSWGDEVICE_F_USER_SOCK6 (2): which user sockets are attached. |
Rules: setting WGDEVICE_A_LISTEN_PORT to another port while a user
socket is attached fails with EBUSY. A user socket stays attached until
userspace detaches it or closes its last fd (then the device has no
socket for that family until it gets a new one).
Peer attributes (in WGPEER_A_TSWG):
| attribute | type | direction | meaning |
|---|---|---|---|
TSWGPEER_A_FLAGS |
u32 | set and get | the peer's tswg flags; setting replaces them all. |
TSWGPEER_A_CLEAR_SESSION |
flag | set | forget the peer's keypairs and any handshake in progress, and reset the handshake rate limit, so the next packet starts a handshake at once. See "Peer restarts". |
Peer flags:
| flag | value | meaning |
|---|---|---|
TSWGPEER_F_NO_ROAM |
1 | don't learn the peer's endpoint from incoming packets once it has one; only userspace sets it. See "Endpoints and roaming". |
TSWGPEER_F_HYBRID |
2 | do hybrid post-quantum handshakes with the peer, and only those; both sides must agree, and a change applies from the next handshake. See "Hybrid post-quantum handshakes". |
Within a WG_CMD_SET_DEVICE peer, WGPEER_A_TSWG is applied before
WGPEER_A_ENDPOINT, so that setting no-roam and the endpoint is one
step.
Events. The device multicasts TSWG_CMD_PEER_EVENT (64) messages to
the family's events group (TSWG_MCGRP_EVENTS), in its network
namespace, only built when someone is subscribed. Attributes:
TSWGEVENT_A_IFINDEX (u32), TSWGEVENT_A_PUBLIC_KEY (the peer's, 32
bytes) and TSWGEVENT_A_FLAGS (u32):
| flag | value | meaning |
|---|---|---|
TSWGEVENT_F_SESSION |
1 | a new session (keypair) was derived with the peer |
TSWGEVENT_F_TX |
2 | sent to the peer; at most one per peer per 2 seconds |
TSWGEVENT_F_RX |
4 | received from the peer; likewise rate limited |
Events can be lost if the subscriber's socket overruns; they're hints,
and activity recurs. See "No polling". Subscribing needs no privilege
(the group has no GENL_MCAST_CAP_NET_ADMIN), so any process in the
namespace can see peers' public keys and when they're active; a TODO.
The shared UDP socket. Once attached, the socket's owner keeps using it: WireGuard messages (a first byte of 1-4, then three zero bytes, or for hybrid handshake retries, 0x80 as the fourth) are consumed by the device, and everything else is left in the socket's receive queue. The owner may send its own datagrams on it. See "Shared UDP socket".
Module parameters (/sys/module/tswg/parameters/, all writable at
run time but the counters). These are tuning and debugging knobs, not a
stable interface: tailscaled shouldn't set them, and they may change.
| parameter | default | meaning |
|---|---|---|
inline_crypto |
1 | encrypt and decrypt lone packets inline while the crypt workers are idle (change 9) |
napi_threaded |
0 | run new devices' peer NAPI in kthreads rather than softirq (change 10) |
gso_whole |
1 | encrypt GSO packets a segment at a time rather than segmenting them first (change 11) |
tx_inline |
1 | encrypt and send where packets arrive: 0 never, 1 forwarded ones and lone ones, 2 always (changes 12, 14) |
rx_inline_mbps |
4000 | receive a peer's packets on the CPU they arrive on while it's below this rate; 0 never (change 12) |
rx_steer_busy |
90 | percent busy a CPU must be for its peers' received packets to be steered to other CPUs; 0 never (changes 15, 16) |
rx_zerocopy |
0 | decrypt received messages in place rather than copying them out |
verify_gso |
0 | tests: check every segment built from a GSO packet against skb_gso_segment (slow) |
gso_verified, gso_verify_errors |
read-only counters for verify_gso |
Versioning. The module reports its version at load (pr_info) and
in modinfo (TSWG_VERSION, now 0.0.1). There's no feature negotiation
yet. Userspace detects the module by the genetlink family resolving, and
an attribute it needs that the module lacks fails the request (see
above). Before release, decide how tailscaled tells which features a
loaded module has (bumping WG_GENL_VERSION, or a features attribute in
WG_CMD_GET_DEVICE), so it can fall back to wireguard-go cleanly; see
"DKMS and fallback".
Not part of the interface. tailscaled also uses ordinary kernel
interfaces on the device: raw sockets for TSMP (IP protocol 99) on
tailscale0, and in kernel mode a separate ordinary TUN device,
tailscale0-svc, for the routes to the Tailscale service IPs. Neither
involves the module; see "TSMP and other packets tailscaled sends to
peers" and "Known gaps in kernel mode".
Shared UDP socket
Tailscale needs disco, STUN and WireGuard to share one UDP 4-tuple so NAT
mappings discovered by disco are the ones WireGuard uses. Implemented
2026-11-06 (src/socket.c, "TSWG: user-supplied sockets"), modeled on
L2TP's user-supplied tunnel sockets and ESP-in-UDP:
- tailscaled creates and binds the UDP socket(s) and sets its socket options (SO_MARK, buffer sizes, and so on).
- tailscaled passes the fds to tswg in
WG_CMD_SET_DEVICE, asTSWGDEVICE_A_SOCK_FD4/TSWGDEVICE_A_SOCK_FD6(NLA_S32) nested inWGDEVICE_A_TSWG. The netlink request is processed in the caller's context, sosockfd_lookupsees the caller's fd table. - tswg validates the socket (UDP, the right family, bound, IPv6 sockets
must be
IPV6_V6ONLY, not already used by a tunnel), callssetup_udp_tunnel_sock()with itsencap_rcvandencap_destroy, and keeps a reference to thestruct sock(not the file). encap_rcvconsumes WireGuard messages (a first byte of 1-4 followed by three zero bytes) and returns 1 for everything else, which lands in the socket's normal receive queue for tailscaled. Nothing else Tailscale sends matches: disco starts with "TS", STUN with 0x00, or 0x01 followed by a nonzero byte, and Geneve (peer relay) with 0x00.- tailscaled sends disco and STUN with plain
sendmsgon the same socket.
Details and decisions:
- uapi numbering: all tswg device attributes live in one nested attribute,
WGDEVICE_A_TSWG= 64, far above upstream's (8 today), so upstream can keep appending its own without colliding. Peer attributes will get the same treatment (WGPEER_A_TSWG= 64). Dumps reportTSWGDEVICE_A_FLAGS(TSWGDEVICE_F_USER_SOCK4/6). - Socket lifetime is the lifetime of tailscaled's fd (decided
2026-11-06). When the process closes the socket (or exits), UDP calls
our
encap_destroyand the device drops it, leaving the device with no socket for that family until tailscaled passes a new one. No explicit detach op is needed for restarts. A restart that keeps the data plane up needs the fd to survive it, via systemd's fd store (FileDescriptorStoreMax=); that's a tailscaled-side TODO. - Passing -1 detaches the socket, and the device goes back to creating its own on its listen port (which fails with EADDRINUSE if tailscaled still holds that port).
- The user sockets are kept per device (
tswg_user_sock4/6) across ifdown/ifup; while the device is up they're also its activesock4/sock6. WireGuard messages arriving while the device is down are dropped; everything else still reaches userspace. - Setting
WGDEVICE_A_LISTEN_PORTto a different port while a user socket is attached fails with EBUSY. - Detaching restores the socket to plain UDP (
encap_rcv,encap_type,sk_user_data, checksum conversion). It leaves multicast loopback disabled, since we don't know its previous value, and leaves the encap static key reference for UDP to drop when the socket is destroyed. - A global mutex,
tswg_user_sock_lock, serializes attach and detach, including detach fromencap_destroy, which runs from the user'sclose()without any of our locks held. Lock order:device_update_lock, thentswg_user_sock_lock, thensocket_update_lock. - Attaching also installs our
gro_receive/gro_complete(see "Outer UDP GSO and GRO"), which take precedence over the socket's ownUDP_GROsetting, so whether tailscaled enablesUDP_GROdoesn't matter. Detaching removes them, first undoing the static call thatsetup_udp_tunnel_sockmay have made ofgro_receive(7.x), which must not outlive the module. - We set
sk_allocation = GFP_ATOMICon the user socket, as WireGuard and L2TP do for their sockets, since we send from atomic context.
Endpoints and roaming
Upstream WireGuard roams a peer's endpoint to the source of the latest authenticated packet. That fights disco's path selection: a packet that arrives via DERP would steal the endpoint from a good direct path. Implemented 2026-11-06:
- A per-peer flag,
TSWGPEER_F_NO_ROAM, inTSWGPEER_A_FLAGSnested inWGPEER_A_TSWG(= 64, like the device attribute). SettingTSWGPEER_A_FLAGSreplaces all of the peer's tswg flags. Dumps report it. Go:tswg.PeerConfig.NoRoamandtswg.Peer.NoRoam. - Upstream learns endpoints in three places: on a valid handshake
initiation and a valid handshake response (via
wg_socket_set_peer_endpoint_from_skb) and on each authenticated data packet (wg_packet_consume_data_donecallswg_socket_set_peer_endpointdirectly).tswg_peer_may_roam()(inpeer.h) gates the learned updates, notwg_socket_set_peer_endpointitself, which netlink also uses for explicit updates. - With the flag set, the first authenticated packet still sets the endpoint if the peer doesn't have one yet; after that only userspace changes it. That keeps a peer reachable if it contacts us before tailscaled has given it an endpoint.
- The flag is applied before
WGPEER_A_ENDPOINTin the same request, so pinning and setting an endpoint are one step. - Per-peer rather than device-wide, for now. tailscaled will set it on every peer; a device-wide default is easy to add if per-peer turns out to be a hassle.
- Pinning also stops learning the local source address that upstream records alongside the endpoint (for replying from the same local IP on multihomed hosts); the kernel picks the source address by routing, as in userspace Tailscale.
Changing a peer's endpoint does not re-key or reset the noise session in upstream WireGuard either; that is already fine.
DERP, peer relays and spray: the loopback bridge
Implemented 2026-11-07 in tailscaled (wgengine/kerneldp_linux.go); it
needed no kernel changes. The rule: the kernel handles direct UDP paths
by itself; everything else (DERP, peer relays, and the untrusted-path
spray) goes through tailscaled's loopback bridge.
- The bridge is one UDP socket bound to
0.0.0.0:PwithSO_BINDTODEVICE lo(so only local traffic reaches it) andIP_PKTINFO. - Each peer gets its own address in 127.0.0.0/8 (127.0.0.2 upwards; the
mapping lives for the process's lifetime). When the kernel shouldn't
send to a peer directly, the peer's kernel endpoint is set to that
address and port P. The bridge reads what the kernel sends there, maps
the destination (from
IP_PKTINFO) back to the peer, and hands the ciphertext to magicsock'sendpoint.send, which sends it the way it would a packet from wireguard-go: DERP, a peer relay, or both DERP and the candidate UDP path while that isn't trusted yet (the spray). - In kernel mode, magicsock passes every WireGuard packet it would have
handed to wireguard-go (from DERP, or Geneve-wrapped from a peer relay)
to the bridge instead (
magicsock.Options.KernelWGRecv), which injects it into the kernel by sending it to127.0.0.1:<kernel listen port>from the peer's 127.x.y.z:P (ipi_spec_dst). The kernel finds the peer by receiver index (or, for handshake initiations, by decrypting the static key), so the source only matters for handshake rate limiting and cookie replies, which stay per-peer because each peer has its own address. Packets from unknown peers are injected from 127.0.0.1. - Each peer's kernel endpoint is magicsock's best address if it's direct
and trusted (
magicsock.Conn.KernelPeerPath), else the peer's bridge address; see "No polling" for how changes reach the kernel.
tailscaled integration
Implemented 2026-11-07 on the tailscale.com bradfitz/tswg branch. Opt
in with TS_DEBUG_TSWG=1 on Linux; the code is behind the tswg feature
tag (ts_omit_tswg drops it, and the minimal builds don't include it).
-
Startup: if the module is loaded, tailscaled creates a tswg device named tailscale0 (replacing any stale one) with the usual TUN MTU, and gives the engine and router a fake
tun.Devicethat only reports that name (tswg.NewTailscaleDevice), so the router configures addresses and routes on the tswg device. If the module isn't loaded, tailscaled logs why and falls back to TUN and wireguard-go. tailscaled doesn't load the module itself. -
The engine (
wgengine.Config.KernelWG) keeps wireguard-go running with no peers, since its receive loops are what drive magicsock's socket reads (disco, STUN). The kernel data plane:- sets the device fwmark to Tailscale's bypass mark
(
tsconst.LinuxBypassMarkNum), so the kernel's encrypted packets don't route into tailscale0 (for example via an exit node's default route), as magicsock's sockets do; - shares magicsock's first UDP socket per family with the kernel, again
after every rebind (
magicsock.Conn.SetKernelSocketHook); - reconciles the kernel's peers with magicsock's peers and the live
per-peer config (
SetPeerConfigFunc, whose peer set is otherwise lazy): allowed IPs, preshared key, endpoint, and no-roam on all of them, in netlink messages of at most 32 peers; - feeds direct-path activity, from the kernel's peer events, to
magicsock (
NoteKernelActivity), so it keeps heartbeating active sessions and the direct path stays trusted, and reports per-peer status (bytes, last handshake) in the engine status, from a dump when asked.
- sets the device fwmark to Tailscale's bypass mark
(
-
Tests:
TestTSWGTailscaledDirect(two gokrazy VMs behind easy NATs; the kernel ends up sending directly to the peer's NAT-traversed public address) andTestTSWGTailscaledDERP(hard NATs on both sides; the kernel peer stays on its bridge address and everything flows over DERP). Both start tailscaled before the module is loaded, so they also cover the TUN fallback, then load the module and restart tailscaled. -
wireguard-go must never get peers in kernel mode: if it did (from its lazy peer lookup on an outbound packet or an incoming handshake), it would handshake over magicsock with our keys and fight the kernel's sessions. So in kernel mode the engine doesn't install wireguard-go's
PeerLookupFuncorPeerByIPPacketFunc(decided 2026-11-07).
TSMP and other packets tailscaled sends to peers
Implemented 2026-11-07 (wgengine/kerneldp_tsmp_linux.go). With
wireguard-go, TSMP (IP protocol 99) and the other packets tailscaled
itself exchanges with peers pass through the tstun.Wrapper between the
TUN device and wireguard-go. In kernel mode:
- Outbound: tstun gets an outbound inject hook
(
tstun.Wrapper.SetOutboundInjectHook). In kernel mode, everything tailscaled injects towards peers (TSMP pings, pongs and disco key advertisements, ICMP echo replies, netstack output) goes to it instead of wireguard-go's queue, and the kernel data plane writes it, header and all, to a rawIPPROTO_RAWsocket bound to tailscale0 (IPv4 and IPv6), so the kernel routes it into the tswg device, which encrypts it. - Inbound: raw
IPPROTO_TSMPsockets bound to tailscale0 receive the TSMP packets peers send, and the data plane feeds them totstun.Wrapper.Writeas wireguard-go would, which handles them as usual (answering pings, delivering pongs, learning disco keys). IPv6 raw sockets don't return the IP header, so it's rebuilt from the source address and theIPV6_PKTINFOandIPV6_HOPLIMITcontrol messages. With such a raw socket open, the kernel doesn't answer TSMP with ICMP protocol unreachable. - wireguard-go sends a "priority message" (a TSMP disco key advertisement) whenever it establishes a session. The kernel data plane does the same on the kernel's session event for the peer (see "No polling").
- Tested by
TestTSWGTailscaledTSMP: TSMP pings both ways, and each side receives the other's disco key advertisement (magicsock_tsmp_disco_key_advertisement_received).
No polling
Done 2026-11-07 (at first the data plane polled every second). Nothing in the kernel data plane runs on a timer now; everything is driven by events:
- Peer set and config:
SyncDevicePeer,SetPeerConfigFuncand private key changes request a full sync. - Paths: magicsock calls a hook (
Conn.SetKernelPathHook) whenever a peer's kernel path flips between direct-and-trusted and not. All changes tobestAddrgo throughsetBestAddrLockedand all changes totrustBestAddrUntilthroughsetTrustBestAddrUntilLocked, which check for a flip. Trust lapsing is an event with no packet attached, so while a peer's kernel path is direct, magicsock keeps a timer armed fortrustBestAddrUntil(re-armed if trust was extended meanwhile). The data plane then updates just that peer's endpoint. - While a session is active, the fallback when a direct path dies comes
from magicsock's heartbeat ping timing out after trust lapsed
(
discoPingTimeoutclears the best address). The trust timer is what covers idle sessions: once magicsock stops heartbeating (45 seconds without traffic), trust lapses silently, and the kernel must stop sending directly so that the next packets go through magicsock (DERP plus the candidate path) until the path is trusted again, as with wireguard-go. - Kernel to tailscaled: the module multicasts peer events
(
TSWG_CMD_PEER_EVENTon the "events" genetlink group): a new session (TSWGEVENT_F_SESSION, fromwg_timers_session_derived), and TX and RX activity (TSWGEVENT_F_TX,TSWGEVENT_F_RX), each rate limited to one per peer every 2 seconds (TSWG_ACTIVITY_EVENT_INTERVAL) with a single comparison on the packet path. Messages are only built when someone listens. tailscaled sends the disco key advertisement on session events and feeds direct-path activity to magicsock. If the event socket overruns, events are lost but harmlessly: activity recurs, and the advertisement is an optimization. - All changes to the kernel's peers are applied by one goroutine: hooks only record what to do (full sync, dirty paths, session clears) and kick it, so a sync that read paths a moment ago can't overwrite a newer endpoint, and callers holding LocalBackend locks never wait on a sync that needs them.
- Tests:
TestTSWGTailscaledPathFallback(a direct path dies mid-session; the kernel falls back to the bridge and DERP about 8 seconds later) andTestTSWGTailscaledIdleTrustExpiry(a session goes idle; the kernel moves to the bridge once trust lapses, and back to direct when traffic resumes; fails without the trust timer).
Peer restarts
Implemented 2026-11-07. When a peer's disco key changes in a way that
means it restarted (and so lost its WireGuard keys), ipnlocal calls
Engine.MarkDevicePeerForHandshake. wireguard-go then handshakes after
the next outbound packet. In kernel mode, the data plane instead clears
the kernel's session with the peer (TSWGPEER_A_CLEAR_SESSION: forget
the keypairs and any handshake in progress, as on suspend, and reset the
handshake rate limit), so the next packet is staged and starts a new
handshake right away. In the same request it updates the peer's endpoint
from magicsock's current path, since a restarted peer usually has a new
port, and the handshake should go there rather than wait for the next
reconcile.
Without this, the kernel keeps sending with dead keys until WireGuard's
own timers start a new handshake about 15 seconds later.
TestTSWGTailscaledPeerRestart checks that the first pings after a peer
restart get through (and fails without the session clearing).
Known gaps in kernel mode
Deliberately deferred (2026-11-07: "easy later, not a priority yet"):
- No packet filter: the engine's filter runs on packets passing through userspace, which kernel-mode packets don't. Peers can reach anything on the node. Must be done (nftables, or in the module) before anyone uses this for real.
MagicDNS and the other services at the Tailscale service IPs
(100.100.100.100 and fd7a:115c:a1e0::53) work (2026-11-08), without the
kernel knowing about them: in kernel mode, the tun.Device tailscaled's
TUN wrapper wraps is a real TUN device, tailscale0-svc, rather than a
fake, and the Linux router sends just the routes to the service IPs
there (serviceTUN in wgengine/router/osrouter), so netstack answers
them as in TUN mode, and its replies go back to the OS through it.
Nothing else is routed to it. TestTSWGTailscaledMagicDNS checks UDP
and TCP queries to both service IPs.
Other TODOs:
- Only magicsock's first socket per family is shared;
UDPSockets> 1 isn't supported. - Full syncs walk every peer, but now happen only at startup, on a new private key, and when the config source is (re)installed; each peer change is synced alone (see "Lazy peer configuration").
Hybrid post-quantum handshakes
Tailscale's wireguard-go has a hybrid post-quantum handshake,
Noise_IKhfs+psk2_25519+MLKEM768_ChaChaPoly_BLAKE2s
(wgcfg.PeerConfig.Hybrid, wired up in tailscale.com 2026-10-29, with
a control "disable hybrid" capability for the rollout). Both peers must
agree to use it, with no fallback to the classic handshake, so a
kernel-mode node that couldn't do it would be cut off from any peer that
asked for it. tswg does it (2026-11-08):
- Wire format, as wireguard-go: the initiation carries an ephemeral
ML-KEM-768 encapsulation key, sealed with the key from
es, before the static key (which then uses nonce 1); the response carries a KEM ciphertext, sealed with a key fromee, and the KEM's shared secret is mixed into the chaining key beforese. Messages grow from 148 and 92 bytes to 1348 and 1196. Hybrid messages that are retries have bit 31 of the type set (TSWG_MESSAGE_RETRY, a hint for routing them over more reliable paths); tswg accepts it, sets it on its own retries, and echoes it in responses, as wireguard-go does. - ML-KEM-768 is ours (
src/mlkem.c, FIPS 203, with its own Keccak): Linux has none, and its SHA-3 is too new for the kernels we build for.tests/mlkemchecks it against Go'scrypto/mlkem, which wireguard-go uses: the same keys from the same seeds, decapsulation of each other's ciphertexts, and the same implicit rejection of corrupted ones. noise.ckeeps the classic message structs, with the sealed KEM field passed separately; send.c and receive.c convert to and from the hybrid layouts. The handshake's KEM key (our decapsulation key as initiator, the peer's encapsulation key as responder) is on the heap, only while a handshake is in progress.- Per peer, set by
TSWGPEER_F_HYBRID, which tailscaled sets fromwgcfg.PeerConfig.Hybrid. Like wireguard-go, a peer's handshakes are all hybrid or all classic, and a change applies from the next one. - Tested in natlab, with
TS_DEBUG_FORCE_HYBRID_HANDSHAKES=1(nothing else turns hybrid handshakes on yet):TestTSWGTailscaledHybridTUN(kernel mode against wireguard-go, each initiating, with wireguard-go's hybrid handshake metrics as proof) andTestTSWGTailscaledHybridKernel(kernel mode on both sides).
What doesn't need kernel work
- ACLs: nftables (tailscaled already has nftables and iptables code; conntrack handles return traffic).
- peerapi, Tailscale SSH, Taildrop: kernel sockets on the tailscale0 address. MagicDNS: a route to a TUN device in userspace (see "Known gaps in kernel mode").
- TSMP: raw socket on IP protocol 99.
- Subnet routers and exit nodes: kernel forwarding.
Lazy peer configuration
tailscaled only programs recently active peers into wireguard-go, mostly
because of per-peer cost in wireguard-go. Kernel peers are cheap and
hashed, so the kernel data plane programs every peer, which holds up to
50,000 (2026-11-09; TestLeanScale, in a lab VM, adding 50,000 peers
with an endpoint and two allowed IPs each, 5,000 at a time):
| 500 peers | 5,000 | 50,000 | |
|---|---|---|---|
| kernel memory per peer | 2.2 KB slab | 2.1 KB slab, no per-CPU (106 MB total) | |
| add, per peer in bulk | 48 us | 35 us | 37 us |
| add one / remove one | 48 / 58 us | 59 / 54 us | 39 / 65 us |
| update one's endpoint / replace its allowed IPs | 10 / 13 us | 6 / 15 us | 26 / 80 us |
| rename one (key rotation) | 73 us | 83 us | |
| dump the device | 4 ms | 17 ms | 0.5-0.7 s |
| delete the device | 38 ms | 32 ms | 0.1-0.2 s |
The single-peer operations' growth from 5,000 to 50,000 is cache misses
in bigger tables and tries, not O(N) work: at 20,000 and 50,000, at 16
vCPUs, they're the same (22 and 23 us to update an endpoint, 64 and 79
to replace allowed IPs). Fixed for it: deleting a device
removed its peers one at a time, each waiting for an RCU grace period
(netif_napi_del) and three workqueue flushes, 6ms a peer, so 5 minutes
for 50,000; now all of them wait together (peer_remove_dead_batch),
1000x faster. Each peer's route cache (dst_cache) was per CPU, 40
bytes on each, so 5KB a peer on a 128-CPU host, 250MB for 50,000; it's
now allocated on the peer's first send. And the pubkey and index hash
tables have 2^16 and 2^17 buckets (1.5MB a device), where upstream's
2^11 and 2^13 had chains of 25 at 50,000 peers.
In tailscaled (tailscale.com wgengine/kerneldp_linux.go), each changed
peer (Engine.SyncDevicePeer, called for each peer a netmap delta
changes) used to trigger a full sync, walking every peer through
magicsock and the config source: O(N) per change, so O(N^2) for a
netmap of N changes. Now syncPeer syncs just that peer, O(1): its
magicsock path and config decide whether to add, update or remove it.
magicsock's kernel path hook now also fires when it adds or removes a
peer, so a peer magicsock learns of after its SyncDevicePeer is still
synced.
Key rotation is atomic: a peer that rotates its node key comes to
tailscaled as the removal of the old key and the addition of the new,
in either order, perhaps in different syncs, or as a full netmap. Done
as such, the peer's allowed IPs and traffic would be gone in between.
So tailscaled matches the two by the peer's Tailscale IP (peerAddr;
by its own map of pushed peers' addresses, and LocalBackend's peer by IP
lookup for the other order) and tells the kernel to rename the peer
(TSWGPEER_A_NEW_PUBLIC_KEY, tswg_peer_rename): in one step, under
device_update_lock, the peer moves in the pubkey table to its new key,
with its precomputed static-static and cookie keys recomputed and its
sessions cleared, keeping its allowed IPs, endpoint and queues; O(1).
TestTSWGTailscaledKeyRotation rotates a peer's key (tailscale up --force-reauth) and checks that the other node's kernel always had
exactly one peer, that it renamed it, and that the tunnel works.
Not done: the device dump is O(N) by nature (0.5-0.7s at 50,000), and
tailscaled does one after each full sync (refreshListenPort); the
kernel's peer events, rate limited to one per peer per 2 seconds each
way, could be 50,000 a second with every peer busy; magicsock and
LocalBackend at 50,000 peers are as in TUN mode. If programming every
peer stops scaling, the fallback is an unknown-peer upcall from
wg_noise_handshake_consume_initiation, with a short stash of the
initiation for replay (to avoid a 5s REKEY_TIMEOUT stall).
DKMS and fallback
Out-of-tree modules on Secure Boot systems need signing and MOK enrollment. tailscaled must always fall back to wireguard-go when tswg is missing, fails to load, or reports an incompatible version (the genetlink family version or a feature attribute).
Testbed
Integration tests run as natlab vmtests in tailscale.com
(tstest/natlab/vmtest), which boot QEMU VMs connected by vnet, a
simulated network with NATs, DERP and a test control server. The tests
live in the tailscale.com worktree, in tstest/natlab/vmtest/tswg_test.go.
Run them with scripts/vmtest.sh [TEST_REGEXP]; it sets TSWG_DIR to this
tree, and the tests skip if the tree is missing.
Primary guest: gokrazy
Decided 2026-11-06: the natlab gokrazy image is the primary test guest.
- It boots a recent upstream kernel (7.2.8 today), from the
github.com/gokrazy/kernel.amd64package pinned in tailscale.com's go.mod. A gokrazy bot bumps that package to new kernel releases, and a tailscale.com cron bot bumps the go.mod dependency, so the test guest follows upstream kernels without anyone doing anything. That keeps the fork honest against new kernel APIs, which is where the fork's base is anyway. - Consequence: a gokrazy vmtest failure after a dependency bump most likely means kernel API churn that needs a new compat probe and shim (or an upstream WireGuard change worth importing), not a test flake.
- gokrazy has no userspace tools (no modprobe, iproute2 or shell), just
like the end state, where tailscaled drives the kernel entirely. So
everything is done from Go:
tswg.LoadModulecalls init_module(2) on the tswg.ko image, and links and addresses are set up over rtnetlink. - gokrazy kernels are kernel.org releases plus the patches in
_build/series, with an embedded config (CONFIG_IKCONFIG) and without MODVERSIONS or module signing.scripts/gokrazy-kdir.shrecreates a matching module build tree (download, patch, embedded config,modules_prepare; about 20 seconds, cached). We build with the host's gcc 13 while gokrazy uses Debian 12's gcc 12; the only resulting config differences are toolchain capability bits. If that ever matters, build in a Debian 12 container instead. - Such a tree has no
Module.symvers, so modpost can't check the kernel's exports (we setKBUILD_MODPOST_WARN=1); a missing symbol shows up as a load failure instead. - The test agent (
cmd/tta) has/tswg/load(POST tswg.ko),/tswg/up(create, configure and bring up a one-peer device),/tswg/show(device JSON) and/tswg/dmesg(kernel log lines mentioning tswg, read from /dev/kmsg). TestTSWGGokrazyManualTunnel: two gokrazy VMs on one LAN, tunnel set up through tta, ping across it, and check handshake and byte counters.
Secondary guest: Ubuntu 24.04
Kept for distro and DKMS-style coverage, since that's how real users will install the module.
- The natlab Ubuntu 24.04 cloud image, stock kernel
6.8.0-106-generic. The host is also Ubuntu 24.04 with the same gcc (13.3), soscripts/build-for-ubuntu.shbuilds tswg.ko against that kernel's headers, fetched withapt-get downloadand unpacked into a cache directory (never installed). - The test asks the guest for
uname -r, builds tswg.ko andtswgctl, registers both with the vnet file server, and has the guest curl them fromhttp://52.52.0.6/tswg/<kver>/, thendepmodandmodprobe tswg. Commands run as root over the debug SSH NIC. TestTSWGManualTunnel: the same tunnel check, configured withip linkandtswgctl.
Later
- A custom debug kernel (KASAN, lockdep) built from a Linux tree, which would also cover the 7.4 compat path.
- More distro images (Debian, Fedora) for compat coverage.
Repo layout
Under kernel/linux in tailscale.com:
DESIGN.md: this file.LICENSE: GPL-2.0, as for Linux's WireGuard, which tswg is derived from (the rest of the repository is BSD-3-Clause).src/: the tswg module sources, Kbuild and compat headers.tests/mlkem/: checkssrc/mlkem.cagainst Go'scrypto/mlkem(go testthere).scripts/:probe.sh(compat probes),build.sh(build tswg.ko against a KDIR in a private copy ofsrc/),ubuntu-headers.shandbuild-for-ubuntu.sh(Ubuntu kernels),gokrazy-kdir.shandbuild-for-gokrazy.sh(gokrazy kernels),gokrazy-debug-kernel.sh(a KASAN/lockdep build of a gokrazy kernel),extract-ikconfig(vendored from Linux),vmtest.sh(run the natlab vmtests),bench.sh(natlab benchmark),leanbench.sh(lean benchmark and smoke test),leancompare.sh(quick A/B medians),ec2.shandec2-idle-stop.sh(EC2 instances for the harness's remote mode), andsubnetbench.sh(the subnet router benchmark).
TODO
Performance (the primary motivation; see "Performance"):
- natlab benchmark harness: tailscaled kernel mode vs. TUN mode on the
same VMs (
TestTSWGBenchmark,scripts/bench.sh). - Lean benchmark harness without natlab (tap + vhost-net, gokrazy
kernel, initramfs agent): plaintext, kernel WireGuard, tswg and
wireguard-go, over IPv4 and IPv6 (
TestLeanBenchmark,scripts/leanbench.sh). - Profile the bulk path in the lean harness (an in-agent sampling
profiler,
TestLeanProfile). - Crypt worker kicks on demand, not per packet.
- Outer UDP GSO on send: encrypt into page frags, as
SKB_GSO_UDP_L4packets. - Outer UDP GRO on receive (
gro_receive/gro_complete), decrypting merged packets whole. - TCP backpressure (TSQ) through the NIC, and the tx worker on a CPU that isn't starved.
- Debug kernel (KASAN, lockdep) for the lean harness.
- Beat wireguard-go on bulk TCP and CPU per byte (2026-11-07; at parity to 1.05x on throughput, 0.90-0.94x CPU per byte; see "Performance").
- p99 RTT under load: at parity with wireguard-go on EC2 (0.94x on c6in.32xlarge, 0.98x on c7i.xlarge; see "Performance"). It's only 3.3-3.7x in the nested QEMU lab, where crypt and tx workers on a loaded receiver sometimes don't run for 10-40ms; that wasn't root-caused, and nested virtualization isn't a target.
- Idle latency in VMs (2026-11-08): inline crypto for lone packets when the workers are idle, and softirq NAPI; 0.77-0.85x wireguard-go's idle RTT p50, with subnet router throughput unchanged. Sending from the encrypt worker (skipping the tx worker) wasn't needed.
- Zero-copy receive: tried, 7% worse on a CPU-bound subnet router,
and no better on a 200 Gbps one where page allocation is the limit
(see "Results at a glance"); kept behind
rx_zerocopy, off. - TSO from the inner GSO packet: encrypt straight from it, building
each segment's headers, instead of
skb_gso_segmentinwg_xmit(2026-11-08; change 11 in "What tswg changes"). - Device-coalesced input: UDP packets that arrive already GSO from
the NIC (VM-to-VM with guest USO) skip GRO, so UDP segments them,
with software checksums, before
encap_rcv. - Benchmark a subnet router with many clients and flows
(
TestLeanSubnetRouter): 2.1-3.2x wireguard-go. - Subnet router with many more peers than client machines (several tunnels per client machine, in network namespaces), and an exit node benchmark.
- tailscaled: loading tswg.ko from an image (rather than modprobe, as
DKMS would) must load its dependencies first on distro kernels
(udp_tunnel, ip6_udp_tunnel, libcurve25519 are modules on Ubuntu);
the harness agent does (
loadModuleDeps). - Benchmarks on cloud VMs (EC2, harness remote mode,
scripts/ec2.sh). - Subnet router beyond 40 Gbps at MTU 1280: c6in.32xlarge, 74 Gbps with 60 clients (12x wireguard-go).
- The encrypt ring's consumer lock: on a 128-CPU subnet router sending big responses, 75-83% of the router's CPU contended for it. Change 12 (run to completion) takes forwarded packets off the ring.
- The crypt rings still serve local sockets and fast peers, and so would contend the same way on a big host with many busy local flows (a server, rather than a router): rings per group of CPUs with work stealing, or per-flow steering, as RPS does.
- Forwarded packets' transmit could steer like received ones (change 15) when the NIC's CPUs are busy, instead of RPS: fetches through a 128-CPU router with 32 NIC queues gained 13% from RPS.
- One tunnel on a big host: tswg used up to 2x wireguard-go's CPU per GB, and one fetch stream got 0.77x its throughput; now 0.52-1.02x, and 0.91x (changes 17-18).
- Few peers on a NIC with RSS: the random hash key decided how many
queues they got;
rss.Balance(change 19) rebalances. - tailscaled: run
rss.Balancewhen the kernel data plane is busy and its NIC's queues are uneven (needs CAP_NET_ADMIN, which it has), at most every minute or so, since each pass moves flows. - Recheck one tunnel's CPU per GB between big hosts on EC2 after change 20, which lets two crypt workers come at the old backlog.
- One request/response stream is still 0.91x wireguard-go's.
- Page zeroing (
init_on_alloc, on in Ubuntu's kernels) is 5-13% of a big host's CPU, for pages we fill entirely: a page pool for the encrypted and decrypted packets' pages would recycle them unzeroed. - Subnet router past 75 Gbps at MTU 1280: the ENA interrupt CPUs' page allocator contention, from ENA allocating a page per received packet (zero-copy receive, taking tswg's own allocations out, didn't help). Ideas: ENA with a page pool (upstream driver work); NICs outside EC2 (mlx5 has a page pool); EC2 metal uses ENA too.
- EC2: c7i.large (2 vCPUs, CPU-bound), and the QEMU lab on a c7i.metal-24xl (to see what nesting cost the lab's numbers).
- vmtest: shared socket with
UDP_GROenabled still works. - Profile the encrypt/decrypt path under many-flow and many-peer loads.
- Measure scaling with many peers; unknown-peer upcall only if needed.
Everything else:
- Create repo; import pristine upstream WireGuard (Linux 7.4-rc1).
- Write DESIGN.md.
- Fork into
src/: rename module, link kind and genetlink family totswg; out-of-tree Kbuild/Makefile. - Feature-probe compat framework.
- Build against the host's 7.0 headers.
- Script: fetch and unpack Ubuntu kernel headers for a given version; build tswg.ko against them.
- Compat shims so it builds on Ubuntu 24.04 (6.8).
- Go netlink client (
tailscale.com/wgengine/tswg) andtswgctl. - vmtest: two Ubuntu VMs, load tswg.ko, configure a tswg tunnel by
hand, ping through it (
TestTSWGManualTunnel, passes in about 80s). - Same on gokrazy, with no userspace tools
(
TestTSWGGokrazyManualTunnel, passes in about 23s). - Generate a Module.symvers for gokrazy build trees (for example from the kernel's exported-symbol list) so missing exports fail at build time rather than load time.
- Verify the 7.4 path (all probes succeed) against a built 7.4 tree. (Partly covered: gokrazy's 7.2.8 has every probed API except udp_get_len_short.)
- Forked YNL spec plus regen script. (We now have hand-written
additions in
src/generated/netlink.[ch], marked TSWG.) - Look at the allowedips.c frame-size warning (1048 > 1024 bytes), present in upstream code too.
- Split large peer lists across several netlink messages in the Go client.
- Socket fd passing plus
encap_rcvclassifier (WG vs. disco/STUN). - vmtest: disco/STUN still reach userspace on the shared socket, from
the same 4-tuple; no WireGuard leaks to userspace; closing the fd
detaches; a new fd reattaches (
TestTSWG{Gokrazy,Ubuntu}SharedSocket). - tailscaled: keep the shared sockets in systemd's fd store across restarts.
- Per-peer no-auto-roam flag (
TestTSWG{Gokrazy,Ubuntu}NoRoam). - Loopback DERP endpoints; vmtest with DERP-only path
(
TestTSWGTailscaledDERP). - tailscaled integration on the tailscale.com
bradfitz/tswgbranch (TestTSWGTailscaledDirect). - Kernel mode: packet filter (security; required before real use; deferred).
- Kernel mode: hybrid PQ handshakes (2026-11-08; implemented in
tswg,
TestTSWGTailscaledHybridTUN). - Kernel mode: TSMP (
TestTSWGTailscaledTSMP). - Kernel mode: MagicDNS and the other services at the service IPs,
via a TUN device for just their routes
(
TestTSWGTailscaledMagicDNS). - Kernel mode: clear the session on MarkDevicePeerForHandshake
(
TestTSWGTailscaledPeerRestart). - Kernel mode: event-driven everything, no polling
(
TestTSWGTailscaledPathFallback,TestTSWGTailscaledIdleTrustExpiry). - IPv6 underlay tests for tswg (
TestLeanSmoke). - Kernel mode (tailscaled) over IPv6: exercised on EC2 (some of the subnet router benchmark's clients took direct IPv6 paths).
- Kernel mode bugs found by the EC2 tailscaled benchmark: a reconcile race that left a node's kernel device without its private key (more likely with many peers), and the engine never closing the kernel data plane, leaving tailscale0 behind for a later TUN-mode tailscaled to trip over.
- natlab tests for switching between kernel and TUN mode, on both
nodes at once or one after the other
(
TestTSWGTailscaledModeSwitch{,Rolling}), and for restarting both at once (TestTSWGTailscaledBothRestart). - Flake: in 1 of 4 natlab benchmark runs (2026-11-07), after both nodes restarted tailscaled into kernel mode, the tunnel didn't carry traffic for over 10 seconds, with the kernel endpoints looking direct. Not seen since the kernel mode private key race was fixed (2026-11-08; it left a new kernel device without its key until a later reconcile), in 29 rounds of the tests above, each with the tunnel working on the first ping both ways.
- Scale to a 50,000-node tailnet (2026-11-09; see "Lazy peer configuration"): 2.1 KB of kernel memory per peer, whatever the CPU count; O(1) adds, removals, edits and atomic key rotations, in the module and in tailscaled.
- tailscaled: skip the full device dump after each full sync, and measure the kernel data plane's own memory per peer at 50,000.
- Fallback to wireguard-go when tswg is unavailable (module not loaded).
- Fallback on version or feature mismatch between tailscaled and the loaded module.
- Decide minimum supported kernel.
- dkms.conf and packaging.
- Custom debug kernel (KASAN, lockdep) in the testbed.