From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next 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(). ... --- net/ipv4/tcp_cong.c | 488 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 488 insertions(+) create mode 100644 net/ipv4/tcp_cong.c (limited to 'net/ipv4/tcp_cong.c') diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c new file mode 100644 index 000000000..db8b4b488 --- /dev/null +++ b/net/ipv4/tcp_cong.c @@ -0,0 +1,488 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Pluggable TCP congestion control support and newReno + * congestion control. + * Based on ideas from I/O scheduler support and Web100. + * + * Copyright (C) 2005 Stephen Hemminger + */ + +#define pr_fmt(fmt) "TCP: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include + +static DEFINE_SPINLOCK(tcp_cong_list_lock); +static LIST_HEAD(tcp_cong_list); + +/* Simple linear search, don't expect many entries! */ +struct tcp_congestion_ops *tcp_ca_find(const char *name) +{ + struct tcp_congestion_ops *e; + + list_for_each_entry_rcu(e, &tcp_cong_list, list) { + if (strcmp(e->name, name) == 0) + return e; + } + + return NULL; +} + +void tcp_set_ca_state(struct sock *sk, const u8 ca_state) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + trace_tcp_cong_state_set(sk, ca_state); + + if (icsk->icsk_ca_ops->set_state) + icsk->icsk_ca_ops->set_state(sk, ca_state); + icsk->icsk_ca_state = ca_state; +} + +/* Must be called with rcu lock held */ +static struct tcp_congestion_ops *tcp_ca_find_autoload(struct net *net, + const char *name) +{ + struct tcp_congestion_ops *ca = tcp_ca_find(name); + +#ifdef CONFIG_MODULES + if (!ca && capable(CAP_NET_ADMIN)) { + rcu_read_unlock(); + request_module("tcp_%s", name); + rcu_read_lock(); + ca = tcp_ca_find(name); + } +#endif + return ca; +} + +/* Simple linear search, not much in here. */ +struct tcp_congestion_ops *tcp_ca_find_key(u32 key) +{ + struct tcp_congestion_ops *e; + + list_for_each_entry_rcu(e, &tcp_cong_list, list) { + if (e->key == key) + return e; + } + + return NULL; +} + +/* + * Attach new congestion control algorithm to the list + * of available options. + */ +int tcp_register_congestion_control(struct tcp_congestion_ops *ca) +{ + int ret = 0; + + /* all algorithms must implement these */ + if (!ca->ssthresh || !ca->undo_cwnd || + !(ca->cong_avoid || ca->cong_control)) { + pr_err("%s does not implement required ops\n", ca->name); + return -EINVAL; + } + + ca->key = jhash(ca->name, sizeof(ca->name), strlen(ca->name)); + + spin_lock(&tcp_cong_list_lock); + if (ca->key == TCP_CA_UNSPEC || tcp_ca_find_key(ca->key)) { + pr_notice("%s already registered or non-unique key\n", + ca->name); + ret = -EEXIST; + } else { + list_add_tail_rcu(&ca->list, &tcp_cong_list); + pr_debug("%s registered\n", ca->name); + } + spin_unlock(&tcp_cong_list_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(tcp_register_congestion_control); + +/* + * Remove congestion control algorithm, called from + * the module's remove function. Module ref counts are used + * to ensure that this can't be done till all sockets using + * that method are closed. + */ +void tcp_unregister_congestion_control(struct tcp_congestion_ops *ca) +{ + spin_lock(&tcp_cong_list_lock); + list_del_rcu(&ca->list); + spin_unlock(&tcp_cong_list_lock); + + /* Wait for outstanding readers to complete before the + * module gets removed entirely. + * + * A try_module_get() should fail by now as our module is + * in "going" state since no refs are held anymore and + * module_exit() handler being called. + */ + synchronize_rcu(); +} +EXPORT_SYMBOL_GPL(tcp_unregister_congestion_control); + +u32 tcp_ca_get_key_by_name(struct net *net, const char *name, bool *ecn_ca) +{ + const struct tcp_congestion_ops *ca; + u32 key = TCP_CA_UNSPEC; + + might_sleep(); + + rcu_read_lock(); + ca = tcp_ca_find_autoload(net, name); + if (ca) { + key = ca->key; + *ecn_ca = ca->flags & TCP_CONG_NEEDS_ECN; + } + rcu_read_unlock(); + + return key; +} + +char *tcp_ca_get_name_by_key(u32 key, char *buffer) +{ + const struct tcp_congestion_ops *ca; + char *ret = NULL; + + rcu_read_lock(); + ca = tcp_ca_find_key(key); + if (ca) + ret = strncpy(buffer, ca->name, + TCP_CA_NAME_MAX); + rcu_read_unlock(); + + return ret; +} + +/* Assign choice of congestion control. */ +void tcp_assign_congestion_control(struct sock *sk) +{ + struct net *net = sock_net(sk); + struct inet_connection_sock *icsk = inet_csk(sk); + const struct tcp_congestion_ops *ca; + + rcu_read_lock(); + ca = rcu_dereference(net->ipv4.tcp_congestion_control); + if (unlikely(!bpf_try_module_get(ca, ca->owner))) + ca = &tcp_reno; + icsk->icsk_ca_ops = ca; + rcu_read_unlock(); + + memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); + if (ca->flags & TCP_CONG_NEEDS_ECN) + INET_ECN_xmit(sk); + else + INET_ECN_dontxmit(sk); +} + +void tcp_init_congestion_control(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + tcp_sk(sk)->prior_ssthresh = 0; + if (icsk->icsk_ca_ops->init) + icsk->icsk_ca_ops->init(sk); + if (tcp_ca_needs_ecn(sk)) + INET_ECN_xmit(sk); + else + INET_ECN_dontxmit(sk); + icsk->icsk_ca_initialized = 1; +} + +static void tcp_reinit_congestion_control(struct sock *sk, + const struct tcp_congestion_ops *ca) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + tcp_cleanup_congestion_control(sk); + icsk->icsk_ca_ops = ca; + icsk->icsk_ca_setsockopt = 1; + memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); + + if (ca->flags & TCP_CONG_NEEDS_ECN) + INET_ECN_xmit(sk); + else + INET_ECN_dontxmit(sk); + + if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) + tcp_init_congestion_control(sk); +} + +/* Manage refcounts on socket close. */ +void tcp_cleanup_congestion_control(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + if (icsk->icsk_ca_ops->release) + icsk->icsk_ca_ops->release(sk); + bpf_module_put(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner); +} + +/* Used by sysctl to change default congestion control */ +int tcp_set_default_congestion_control(struct net *net, const char *name) +{ + struct tcp_congestion_ops *ca; + const struct tcp_congestion_ops *prev; + int ret; + + rcu_read_lock(); + ca = tcp_ca_find_autoload(net, name); + if (!ca) { + ret = -ENOENT; + } else if (!bpf_try_module_get(ca, ca->owner)) { + ret = -EBUSY; + } else if (!net_eq(net, &init_net) && + !(ca->flags & TCP_CONG_NON_RESTRICTED)) { + /* Only init netns can set default to a restricted algorithm */ + ret = -EPERM; + } else { + prev = xchg(&net->ipv4.tcp_congestion_control, ca); + if (prev) + bpf_module_put(prev, prev->owner); + + ca->flags |= TCP_CONG_NON_RESTRICTED; + ret = 0; + } + rcu_read_unlock(); + + return ret; +} + +/* Set default value from kernel configuration at bootup */ +static int __init tcp_congestion_default(void) +{ + return tcp_set_default_congestion_control(&init_net, + CONFIG_DEFAULT_TCP_CONG); +} +late_initcall(tcp_congestion_default); + +/* Build string with list of available congestion control values */ +void tcp_get_available_congestion_control(char *buf, size_t maxlen) +{ + struct tcp_congestion_ops *ca; + size_t offs = 0; + + rcu_read_lock(); + list_for_each_entry_rcu(ca, &tcp_cong_list, list) { + offs += snprintf(buf + offs, maxlen - offs, + "%s%s", + offs == 0 ? "" : " ", ca->name); + + if (WARN_ON_ONCE(offs >= maxlen)) + break; + } + rcu_read_unlock(); +} + +/* Get current default congestion control */ +void tcp_get_default_congestion_control(struct net *net, char *name) +{ + const struct tcp_congestion_ops *ca; + + rcu_read_lock(); + ca = rcu_dereference(net->ipv4.tcp_congestion_control); + strncpy(name, ca->name, TCP_CA_NAME_MAX); + rcu_read_unlock(); +} + +/* Built list of non-restricted congestion control values */ +void tcp_get_allowed_congestion_control(char *buf, size_t maxlen) +{ + struct tcp_congestion_ops *ca; + size_t offs = 0; + + *buf = '\0'; + rcu_read_lock(); + list_for_each_entry_rcu(ca, &tcp_cong_list, list) { + if (!(ca->flags & TCP_CONG_NON_RESTRICTED)) + continue; + offs += snprintf(buf + offs, maxlen - offs, + "%s%s", + offs == 0 ? "" : " ", ca->name); + + if (WARN_ON_ONCE(offs >= maxlen)) + break; + } + rcu_read_unlock(); +} + +/* Change list of non-restricted congestion control */ +int tcp_set_allowed_congestion_control(char *val) +{ + struct tcp_congestion_ops *ca; + char *saved_clone, *clone, *name; + int ret = 0; + + saved_clone = clone = kstrdup(val, GFP_USER); + if (!clone) + return -ENOMEM; + + spin_lock(&tcp_cong_list_lock); + /* pass 1 check for bad entries */ + while ((name = strsep(&clone, " ")) && *name) { + ca = tcp_ca_find(name); + if (!ca) { + ret = -ENOENT; + goto out; + } + } + + /* pass 2 clear old values */ + list_for_each_entry_rcu(ca, &tcp_cong_list, list) + ca->flags &= ~TCP_CONG_NON_RESTRICTED; + + /* pass 3 mark as allowed */ + while ((name = strsep(&val, " ")) && *name) { + ca = tcp_ca_find(name); + WARN_ON(!ca); + if (ca) + ca->flags |= TCP_CONG_NON_RESTRICTED; + } +out: + spin_unlock(&tcp_cong_list_lock); + kfree(saved_clone); + + return ret; +} + +/* Change congestion control for socket. If load is false, then it is the + * responsibility of the caller to call tcp_init_congestion_control or + * tcp_reinit_congestion_control (if the current congestion control was + * already initialized. + */ +int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, + bool cap_net_admin) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + const struct tcp_congestion_ops *ca; + int err = 0; + + if (icsk->icsk_ca_dst_locked) + return -EPERM; + + rcu_read_lock(); + if (!load) + ca = tcp_ca_find(name); + else + ca = tcp_ca_find_autoload(sock_net(sk), name); + + /* No change asking for existing value */ + if (ca == icsk->icsk_ca_ops) { + icsk->icsk_ca_setsockopt = 1; + goto out; + } + + if (!ca) + err = -ENOENT; + else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || cap_net_admin)) + err = -EPERM; + else if (!bpf_try_module_get(ca, ca->owner)) + err = -EBUSY; + else + tcp_reinit_congestion_control(sk, ca); + out: + rcu_read_unlock(); + return err; +} + +/* Slow start is used when congestion window is no greater than the slow start + * threshold. We base on RFC2581 and also handle stretch ACKs properly. + * We do not implement RFC3465 Appropriate Byte Counting (ABC) per se but + * something better;) a packet is only considered (s)acked in its entirety to + * defend the ACK attacks described in the RFC. Slow start processes a stretch + * ACK of degree N as if N acks of degree 1 are received back to back except + * ABC caps N to 2. Slow start exits when cwnd grows over ssthresh and + * returns the leftover acks to adjust cwnd in congestion avoidance mode. + */ +__bpf_kfunc u32 tcp_slow_start(struct tcp_sock *tp, u32 acked) +{ + u32 cwnd = min(tcp_snd_cwnd(tp) + acked, tp->snd_ssthresh); + + acked -= cwnd - tcp_snd_cwnd(tp); + tcp_snd_cwnd_set(tp, min(cwnd, tp->snd_cwnd_clamp)); + + return acked; +} +EXPORT_SYMBOL_GPL(tcp_slow_start); + +/* In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd (or alternative w), + * for every packet that was ACKed. + */ +__bpf_kfunc void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked) +{ + /* If credits accumulated at a higher w, apply them gently now. */ + if (tp->snd_cwnd_cnt >= w) { + tp->snd_cwnd_cnt = 0; + tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) + 1); + } + + tp->snd_cwnd_cnt += acked; + if (tp->snd_cwnd_cnt >= w) { + u32 delta = tp->snd_cwnd_cnt / w; + + tp->snd_cwnd_cnt -= delta * w; + tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) + delta); + } + tcp_snd_cwnd_set(tp, min(tcp_snd_cwnd(tp), tp->snd_cwnd_clamp)); +} +EXPORT_SYMBOL_GPL(tcp_cong_avoid_ai); + +/* + * TCP Reno congestion control + * This is special case used for fallback as well. + */ +/* This is Jacobson's slow start and congestion avoidance. + * SIGCOMM '88, p. 328. + */ +__bpf_kfunc void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (!tcp_is_cwnd_limited(sk)) + return; + + /* In "safe" area, increase. */ + if (tcp_in_slow_start(tp)) { + acked = tcp_slow_start(tp, acked); + if (!acked) + return; + } + /* In dangerous area, increase slowly. */ + tcp_cong_avoid_ai(tp, tcp_snd_cwnd(tp), acked); +} +EXPORT_SYMBOL_GPL(tcp_reno_cong_avoid); + +/* Slow start threshold is half the congestion window (min 2) */ +__bpf_kfunc u32 tcp_reno_ssthresh(struct sock *sk) +{ + const struct tcp_sock *tp = tcp_sk(sk); + + return max(tcp_snd_cwnd(tp) >> 1U, 2U); +} +EXPORT_SYMBOL_GPL(tcp_reno_ssthresh); + +__bpf_kfunc u32 tcp_reno_undo_cwnd(struct sock *sk) +{ + const struct tcp_sock *tp = tcp_sk(sk); + + return max(tcp_snd_cwnd(tp), tp->prior_cwnd); +} +EXPORT_SYMBOL_GPL(tcp_reno_undo_cwnd); + +struct tcp_congestion_ops tcp_reno = { + .flags = TCP_CONG_NON_RESTRICTED, + .name = "reno", + .owner = THIS_MODULE, + .ssthresh = tcp_reno_ssthresh, + .cong_avoid = tcp_reno_cong_avoid, + .undo_cwnd = tcp_reno_undo_cwnd, +}; -- cgit v1.2.3