+30
−1
+78
−2
+1
−0
Loading
Merge branch 'bpf-cpumap-type-for-XDP_REDIRECT'
Jesper Dangaard Brouer says: ==================== net: New bpf cpumap type for XDP_REDIRECT Introducing a new way to redirect XDP frames. Notice how no driver changes are necessary given the design of XDP_REDIRECT. This redirect map type is called 'cpumap', as it allows redirection XDP frames to remote CPUs. The remote CPU will do the SKB allocation and start the network stack invocation on that CPU. This is a scalability and isolation mechanism, that allow separating the early driver network XDP layer, from the rest of the netstack, and assigning dedicated CPUs for this stage. The sysadm control/configure the RX-CPU to NIC-RX queue (as usual) via procfs smp_affinity and how many queues are configured via ethtool --set-channels. Benchmarks show that a single CPU can handle approx 11Mpps. Thus, only assigning two NIC RX-queues (and two CPUs) is sufficient for handling 10Gbit/s wirespeed smallest packet 14.88Mpps. Reducing the number of queues have the advantage that more packets being "bulk" available per hard interrupt[1]. [1] https://www.netdevconf.org/2.1/papers/BusyPollingNextGen.pdf Use-cases: 1. End-host based pre-filtering for DDoS mitigation. This is fast enough to allow software to see and filter all packets wirespeed. Thus, no packets getting silently dropped by hardware. 2. Given NIC HW unevenly distributes packets across RX queue, this mechanism can be used for redistribution load across CPUs. This usually happens when HW is unaware of a new protocol. This resembles RPS (Receive Packet Steering), just faster, but with more responsibility placed on the BPF program for correct steering. 3. Auto-scaling or power saving via only activating the appropriate number of remote CPUs for handling the current load. The cpumap tracepoints can function as a feedback loop for this purpose. In V7, a --stress-mode was implemented for the samples program, which between each stats update, adds + removes CPUs from the map concurrently with traffic. I did find and fix some concurrency issues in the tear-down path, details in patch desc. The stress test have now been running for 15 hours without any issues, while being bombarded with 11.6 Mpps via pktgen_sample04_many_flows.sh. See individual patches for patchset-version changes. ==================== Signed-off-by:David S. Miller <davem@davemloft.net>