Files
tailscale/kernel/linux
Brad Fitzpatrick c306c02b44 kernel/linux/src: do lone packets' crypto inline, and run NAPI in softirq
Handing a packet to a crypt worker, the tx worker or a NAPI kthread on
another CPU can wake a halted vCPU, which in a VM is a VM exit and a
trip through the host's scheduler. tswg's idle round trip time was
1.5-2x wireguard-go's in VMs because of it.

So when the crypt workers look idle, a packet that isn't part of a
batch is encrypted or decrypted where it is, after going on the peer's
in-order queue as before. To keep TCP ACKs under load from moving
crypto onto the CPUs taking the NIC's interrupts (8% off a subnet
router), it's limited to 8 packets per CPU per jiffy, and never done
for encryption from softirq (forwarding). And peers' NAPI runs in
softirq again, not kthreads, unless napi_threaded is set.

Idle RTT p50 is now 0.51ms in the lab (wireguard-go 0.60) and 0.75ms
on EC2 (0.97), with subnet router throughput unchanged at the same
NAPI setting. Threaded NAPI is still 4-5% faster for a CPU-bound
router.

Updates #426

Signed-off-by: Brad Fitzpatrick <[email protected]>
Change-Id: Ib5ebd1edcda1a515dac0ae4e55540bcfe52d1d7f
2026-11-08 00:43:31 +00:00
..