aboutsummaryrefslogtreecommitdiff
path: root/samples/bpf/hbm_edt_kern.c
diff options
context:
space:
mode:
authorLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
committerLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /samples/bpf/hbm_edt_kern.c
downloadlinux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz
linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip
Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted
Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ...
Diffstat (limited to '')
-rw-r--r--samples/bpf/hbm_edt_kern.c168
1 files changed, 168 insertions, 0 deletions
diff --git a/samples/bpf/hbm_edt_kern.c b/samples/bpf/hbm_edt_kern.c
new file mode 100644
index 000000000..6294f1d71
--- /dev/null
+++ b/samples/bpf/hbm_edt_kern.c
@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * Sample Host Bandwidth Manager (HBM) BPF program.
+ *
+ * A cgroup skb BPF egress program to limit cgroup output bandwidth.
+ * It uses a modified virtual token bucket queue to limit average
+ * egress bandwidth. The implementation uses credits instead of tokens.
+ * Negative credits imply that queueing would have happened (this is
+ * a virtual queue, so no queueing is done by it. However, queueing may
+ * occur at the actual qdisc (which is not used for rate limiting).
+ *
+ * This implementation uses 3 thresholds, one to start marking packets and
+ * the other two to drop packets:
+ * CREDIT
+ * - <--------------------------|------------------------> +
+ * | | | 0
+ * | Large pkt |
+ * | drop thresh |
+ * Small pkt drop Mark threshold
+ * thresh
+ *
+ * The effect of marking depends on the type of packet:
+ * a) If the packet is ECN enabled and it is a TCP packet, then the packet
+ * is ECN marked.
+ * b) If the packet is a TCP packet, then we probabilistically call tcp_cwr
+ * to reduce the congestion window. The current implementation uses a linear
+ * distribution (0% probability at marking threshold, 100% probability
+ * at drop threshold).
+ * c) If the packet is not a TCP packet, then it is dropped.
+ *
+ * If the credit is below the drop threshold, the packet is dropped. If it
+ * is a TCP packet, then it also calls tcp_cwr since packets dropped by
+ * a cgroup skb BPF program do not automatically trigger a call to
+ * tcp_cwr in the current kernel code.
+ *
+ * This BPF program actually uses 2 drop thresholds, one threshold
+ * for larger packets (>= 120 bytes) and another for smaller packets. This
+ * protects smaller packets such as SYNs, ACKs, etc.
+ *
+ * The default bandwidth limit is set at 1Gbps but this can be changed by
+ * a user program through a shared BPF map. In addition, by default this BPF
+ * program does not limit connections using loopback. This behavior can be
+ * overwritten by the user program. There is also an option to calculate
+ * some statistics, such as percent of packets marked or dropped, which
+ * a user program, such as hbm, can access.
+ */
+
+#include "hbm_kern.h"
+
+SEC("cgroup_skb/egress")
+int _hbm_out_cg(struct __sk_buff *skb)
+{
+ long long delta = 0, delta_send;
+ unsigned long long curtime, sendtime;
+ struct hbm_queue_stats *qsp = NULL;
+ unsigned int queue_index = 0;
+ bool congestion_flag = false;
+ bool ecn_ce_flag = false;
+ struct hbm_pkt_info pkti = {};
+ struct hbm_vqueue *qdp;
+ bool drop_flag = false;
+ bool cwr_flag = false;
+ int len = skb->len;
+ int rv = ALLOW_PKT;
+
+ qsp = bpf_map_lookup_elem(&queue_stats, &queue_index);
+
+ // Check if we should ignore loopback traffic
+ if (qsp != NULL && !qsp->loopback && (skb->ifindex == 1))
+ return ALLOW_PKT;
+
+ hbm_get_pkt_info(skb, &pkti);
+
+ // We may want to account for the length of headers in len
+ // calculation, like ETH header + overhead, specially if it
+ // is a gso packet. But I am not doing it right now.
+
+ qdp = bpf_get_local_storage(&queue_state, 0);
+ if (!qdp)
+ return ALLOW_PKT;
+ if (qdp->lasttime == 0)
+ hbm_init_edt_vqueue(qdp, 1024);
+
+ curtime = bpf_ktime_get_ns();
+
+ // Begin critical section
+ bpf_spin_lock(&qdp->lock);
+ delta = qdp->lasttime - curtime;
+ // bound bursts to 100us
+ if (delta < -BURST_SIZE_NS) {
+ // negative delta is a credit that allows bursts
+ qdp->lasttime = curtime - BURST_SIZE_NS;
+ delta = -BURST_SIZE_NS;
+ }
+ sendtime = qdp->lasttime;
+ delta_send = BYTES_TO_NS(len, qdp->rate);
+ __sync_add_and_fetch(&(qdp->lasttime), delta_send);
+ bpf_spin_unlock(&qdp->lock);
+ // End critical section
+
+ // Set EDT of packet
+ skb->tstamp = sendtime;
+
+ // Check if we should update rate
+ if (qsp != NULL && (qsp->rate * 128) != qdp->rate)
+ qdp->rate = qsp->rate * 128;
+
+ // Set flags (drop, congestion, cwr)
+ // last packet will be sent in the future, bound latency
+ if (delta > DROP_THRESH_NS || (delta > LARGE_PKT_DROP_THRESH_NS &&
+ len > LARGE_PKT_THRESH)) {
+ drop_flag = true;
+ if (pkti.is_tcp && pkti.ecn == 0)
+ cwr_flag = true;
+ } else if (delta > MARK_THRESH_NS) {
+ if (pkti.is_tcp)
+ congestion_flag = true;
+ else
+ drop_flag = true;
+ }
+
+ if (congestion_flag) {
+ if (bpf_skb_ecn_set_ce(skb)) {
+ ecn_ce_flag = true;
+ } else {
+ if (pkti.is_tcp) {
+ unsigned int rand = bpf_get_prandom_u32();
+
+ if (delta >= MARK_THRESH_NS +
+ (rand % MARK_REGION_SIZE_NS)) {
+ // Do congestion control
+ cwr_flag = true;
+ }
+ } else if (len > LARGE_PKT_THRESH) {
+ // Problem if too many small packets?
+ drop_flag = true;
+ congestion_flag = false;
+ }
+ }
+ }
+
+ if (pkti.is_tcp && drop_flag && pkti.packets_out <= 1) {
+ drop_flag = false;
+ cwr_flag = true;
+ congestion_flag = false;
+ }
+
+ if (qsp != NULL && qsp->no_cn)
+ cwr_flag = false;
+
+ hbm_update_stats(qsp, len, curtime, congestion_flag, drop_flag,
+ cwr_flag, ecn_ce_flag, &pkti, (int) delta);
+
+ if (drop_flag) {
+ __sync_add_and_fetch(&(qdp->lasttime), -delta_send);
+ rv = DROP_PKT;
+ }
+
+ if (cwr_flag)
+ rv |= CWR;
+ return rv;
+}
+char _license[] SEC("license") = "GPL";