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/dccp/ccids/ccid2.c | 793 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 793 insertions(+) create mode 100644 net/dccp/ccids/ccid2.c (limited to 'net/dccp/ccids/ccid2.c') diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c new file mode 100644 index 000000000..4d9823d6d --- /dev/null +++ b/net/dccp/ccids/ccid2.c @@ -0,0 +1,793 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2005, 2006 Andrea Bittau + * + * Changes to meet Linux coding standards, and DCCP infrastructure fixes. + * + * Copyright (c) 2006 Arnaldo Carvalho de Melo + */ + +/* + * This implementation should follow RFC 4341 + */ +#include +#include "../feat.h" +#include "ccid2.h" + + +#ifdef CONFIG_IP_DCCP_CCID2_DEBUG +static bool ccid2_debug; +#define ccid2_pr_debug(format, a...) DCCP_PR_DEBUG(ccid2_debug, format, ##a) +#else +#define ccid2_pr_debug(format, a...) +#endif + +static int ccid2_hc_tx_alloc_seq(struct ccid2_hc_tx_sock *hc) +{ + struct ccid2_seq *seqp; + int i; + + /* check if we have space to preserve the pointer to the buffer */ + if (hc->tx_seqbufc >= (sizeof(hc->tx_seqbuf) / + sizeof(struct ccid2_seq *))) + return -ENOMEM; + + /* allocate buffer and initialize linked list */ + seqp = kmalloc_array(CCID2_SEQBUF_LEN, sizeof(struct ccid2_seq), + gfp_any()); + if (seqp == NULL) + return -ENOMEM; + + for (i = 0; i < (CCID2_SEQBUF_LEN - 1); i++) { + seqp[i].ccid2s_next = &seqp[i + 1]; + seqp[i + 1].ccid2s_prev = &seqp[i]; + } + seqp[CCID2_SEQBUF_LEN - 1].ccid2s_next = seqp; + seqp->ccid2s_prev = &seqp[CCID2_SEQBUF_LEN - 1]; + + /* This is the first allocation. Initiate the head and tail. */ + if (hc->tx_seqbufc == 0) + hc->tx_seqh = hc->tx_seqt = seqp; + else { + /* link the existing list with the one we just created */ + hc->tx_seqh->ccid2s_next = seqp; + seqp->ccid2s_prev = hc->tx_seqh; + + hc->tx_seqt->ccid2s_prev = &seqp[CCID2_SEQBUF_LEN - 1]; + seqp[CCID2_SEQBUF_LEN - 1].ccid2s_next = hc->tx_seqt; + } + + /* store the original pointer to the buffer so we can free it */ + hc->tx_seqbuf[hc->tx_seqbufc] = seqp; + hc->tx_seqbufc++; + + return 0; +} + +static int ccid2_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) +{ + if (ccid2_cwnd_network_limited(ccid2_hc_tx_sk(sk))) + return CCID_PACKET_WILL_DEQUEUE_LATER; + return CCID_PACKET_SEND_AT_ONCE; +} + +static void ccid2_change_l_ack_ratio(struct sock *sk, u32 val) +{ + u32 max_ratio = DIV_ROUND_UP(ccid2_hc_tx_sk(sk)->tx_cwnd, 2); + + /* + * Ensure that Ack Ratio does not exceed ceil(cwnd/2), which is (2) from + * RFC 4341, 6.1.2. We ignore the statement that Ack Ratio 2 is always + * acceptable since this causes starvation/deadlock whenever cwnd < 2. + * The same problem arises when Ack Ratio is 0 (ie. Ack Ratio disabled). + */ + if (val == 0 || val > max_ratio) { + DCCP_WARN("Limiting Ack Ratio (%u) to %u\n", val, max_ratio); + val = max_ratio; + } + dccp_feat_signal_nn_change(sk, DCCPF_ACK_RATIO, + min_t(u32, val, DCCPF_ACK_RATIO_MAX)); +} + +static void ccid2_check_l_ack_ratio(struct sock *sk) +{ + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); + + /* + * After a loss, idle period, application limited period, or RTO we + * need to check that the ack ratio is still less than the congestion + * window. Otherwise, we will send an entire congestion window of + * packets and got no response because we haven't sent ack ratio + * packets yet. + * If the ack ratio does need to be reduced, we reduce it to half of + * the congestion window (or 1 if that's zero) instead of to the + * congestion window. This prevents problems if one ack is lost. + */ + if (dccp_feat_nn_get(sk, DCCPF_ACK_RATIO) > hc->tx_cwnd) + ccid2_change_l_ack_ratio(sk, hc->tx_cwnd/2 ? : 1U); +} + +static void ccid2_change_l_seq_window(struct sock *sk, u64 val) +{ + dccp_feat_signal_nn_change(sk, DCCPF_SEQUENCE_WINDOW, + clamp_val(val, DCCPF_SEQ_WMIN, + DCCPF_SEQ_WMAX)); +} + +static void dccp_tasklet_schedule(struct sock *sk) +{ + struct tasklet_struct *t = &dccp_sk(sk)->dccps_xmitlet; + + if (!test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) { + sock_hold(sk); + __tasklet_schedule(t); + } +} + +static void ccid2_hc_tx_rto_expire(struct timer_list *t) +{ + struct ccid2_hc_tx_sock *hc = from_timer(hc, t, tx_rtotimer); + struct sock *sk = hc->sk; + const bool sender_was_blocked = ccid2_cwnd_network_limited(hc); + + bh_lock_sock(sk); + if (sock_owned_by_user(sk)) { + sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + HZ / 5); + goto out; + } + + ccid2_pr_debug("RTO_EXPIRE\n"); + + if (sk->sk_state == DCCP_CLOSED) + goto out; + + /* back-off timer */ + hc->tx_rto <<= 1; + if (hc->tx_rto > DCCP_RTO_MAX) + hc->tx_rto = DCCP_RTO_MAX; + + /* adjust pipe, cwnd etc */ + hc->tx_ssthresh = hc->tx_cwnd / 2; + if (hc->tx_ssthresh < 2) + hc->tx_ssthresh = 2; + hc->tx_cwnd = 1; + hc->tx_pipe = 0; + + /* clear state about stuff we sent */ + hc->tx_seqt = hc->tx_seqh; + hc->tx_packets_acked = 0; + + /* clear ack ratio state. */ + hc->tx_rpseq = 0; + hc->tx_rpdupack = -1; + ccid2_change_l_ack_ratio(sk, 1); + + /* if we were blocked before, we may now send cwnd=1 packet */ + if (sender_was_blocked) + dccp_tasklet_schedule(sk); + /* restart backed-off timer */ + sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto); +out: + bh_unlock_sock(sk); + sock_put(sk); +} + +/* + * Congestion window validation (RFC 2861). + */ +static bool ccid2_do_cwv = true; +module_param(ccid2_do_cwv, bool, 0644); +MODULE_PARM_DESC(ccid2_do_cwv, "Perform RFC2861 Congestion Window Validation"); + +/** + * ccid2_update_used_window - Track how much of cwnd is actually used + * @hc: socket to update window + * @new_wnd: new window values to add into the filter + * + * This is done in addition to CWV. The sender needs to have an idea of how many + * packets may be in flight, to set the local Sequence Window value accordingly + * (RFC 4340, 7.5.2). The CWV mechanism is exploited to keep track of the + * maximum-used window. We use an EWMA low-pass filter to filter out noise. + */ +static void ccid2_update_used_window(struct ccid2_hc_tx_sock *hc, u32 new_wnd) +{ + hc->tx_expected_wnd = (3 * hc->tx_expected_wnd + new_wnd) / 4; +} + +/* This borrows the code of tcp_cwnd_application_limited() */ +static void ccid2_cwnd_application_limited(struct sock *sk, const u32 now) +{ + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); + /* don't reduce cwnd below the initial window (IW) */ + u32 init_win = rfc3390_bytes_to_packets(dccp_sk(sk)->dccps_mss_cache), + win_used = max(hc->tx_cwnd_used, init_win); + + if (win_used < hc->tx_cwnd) { + hc->tx_ssthresh = max(hc->tx_ssthresh, + (hc->tx_cwnd >> 1) + (hc->tx_cwnd >> 2)); + hc->tx_cwnd = (hc->tx_cwnd + win_used) >> 1; + } + hc->tx_cwnd_used = 0; + hc->tx_cwnd_stamp = now; + + ccid2_check_l_ack_ratio(sk); +} + +/* This borrows the code of tcp_cwnd_restart() */ +static void ccid2_cwnd_restart(struct sock *sk, const u32 now) +{ + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); + u32 cwnd = hc->tx_cwnd, restart_cwnd, + iwnd = rfc3390_bytes_to_packets(dccp_sk(sk)->dccps_mss_cache); + s32 delta = now - hc->tx_lsndtime; + + hc->tx_ssthresh = max(hc->tx_ssthresh, (cwnd >> 1) + (cwnd >> 2)); + + /* don't reduce cwnd below the initial window (IW) */ + restart_cwnd = min(cwnd, iwnd); + + while ((delta -= hc->tx_rto) >= 0 && cwnd > restart_cwnd) + cwnd >>= 1; + hc->tx_cwnd = max(cwnd, restart_cwnd); + hc->tx_cwnd_stamp = now; + hc->tx_cwnd_used = 0; + + ccid2_check_l_ack_ratio(sk); +} + +static void ccid2_hc_tx_packet_sent(struct sock *sk, unsigned int len) +{ + struct dccp_sock *dp = dccp_sk(sk); + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); + const u32 now = ccid2_jiffies32; + struct ccid2_seq *next; + + /* slow-start after idle periods (RFC 2581, RFC 2861) */ + if (ccid2_do_cwv && !hc->tx_pipe && + (s32)(now - hc->tx_lsndtime) >= hc->tx_rto) + ccid2_cwnd_restart(sk, now); + + hc->tx_lsndtime = now; + hc->tx_pipe += 1; + + /* see whether cwnd was fully used (RFC 2861), update expected window */ + if (ccid2_cwnd_network_limited(hc)) { + ccid2_update_used_window(hc, hc->tx_cwnd); + hc->tx_cwnd_used = 0; + hc->tx_cwnd_stamp = now; + } else { + if (hc->tx_pipe > hc->tx_cwnd_used) + hc->tx_cwnd_used = hc->tx_pipe; + + ccid2_update_used_window(hc, hc->tx_cwnd_used); + + if (ccid2_do_cwv && (s32)(now - hc->tx_cwnd_stamp) >= hc->tx_rto) + ccid2_cwnd_application_limited(sk, now); + } + + hc->tx_seqh->ccid2s_seq = dp->dccps_gss; + hc->tx_seqh->ccid2s_acked = 0; + hc->tx_seqh->ccid2s_sent = now; + + next = hc->tx_seqh->ccid2s_next; + /* check if we need to alloc more space */ + if (next == hc->tx_seqt) { + if (ccid2_hc_tx_alloc_seq(hc)) { + DCCP_CRIT("packet history - out of memory!"); + /* FIXME: find a more graceful way to bail out */ + return; + } + next = hc->tx_seqh->ccid2s_next; + BUG_ON(next == hc->tx_seqt); + } + hc->tx_seqh = next; + + ccid2_pr_debug("cwnd=%d pipe=%d\n", hc->tx_cwnd, hc->tx_pipe); + + /* + * FIXME: The code below is broken and the variables have been removed + * from the socket struct. The `ackloss' variable was always set to 0, + * and with arsent there are several problems: + * (i) it doesn't just count the number of Acks, but all sent packets; + * (ii) it is expressed in # of packets, not # of windows, so the + * comparison below uses the wrong formula: Appendix A of RFC 4341 + * comes up with the number K = cwnd / (R^2 - R) of consecutive windows + * of data with no lost or marked Ack packets. If arsent were the # of + * consecutive Acks received without loss, then Ack Ratio needs to be + * decreased by 1 when + * arsent >= K * cwnd / R = cwnd^2 / (R^3 - R^2) + * where cwnd / R is the number of Acks received per window of data + * (cf. RFC 4341, App. A). The problems are that + * - arsent counts other packets as well; + * - the comparison uses a formula different from RFC 4341; + * - computing a cubic/quadratic equation each time is too complicated. + * Hence a different algorithm is needed. + */ +#if 0 + /* Ack Ratio. Need to maintain a concept of how many windows we sent */ + hc->tx_arsent++; + /* We had an ack loss in this window... */ + if (hc->tx_ackloss) { + if (hc->tx_arsent >= hc->tx_cwnd) { + hc->tx_arsent = 0; + hc->tx_ackloss = 0; + } + } else { + /* No acks lost up to now... */ + /* decrease ack ratio if enough packets were sent */ + if (dp->dccps_l_ack_ratio > 1) { + /* XXX don't calculate denominator each time */ + int denom = dp->dccps_l_ack_ratio * dp->dccps_l_ack_ratio - + dp->dccps_l_ack_ratio; + + denom = hc->tx_cwnd * hc->tx_cwnd / denom; + + if (hc->tx_arsent >= denom) { + ccid2_change_l_ack_ratio(sk, dp->dccps_l_ack_ratio - 1); + hc->tx_arsent = 0; + } + } else { + /* we can't increase ack ratio further [1] */ + hc->tx_arsent = 0; /* or maybe set it to cwnd*/ + } + } +#endif + + sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto); + +#ifdef CONFIG_IP_DCCP_CCID2_DEBUG + do { + struct ccid2_seq *seqp = hc->tx_seqt; + + while (seqp != hc->tx_seqh) { + ccid2_pr_debug("out seq=%llu acked=%d time=%u\n", + (unsigned long long)seqp->ccid2s_seq, + seqp->ccid2s_acked, seqp->ccid2s_sent); + seqp = seqp->ccid2s_next; + } + } while (0); + ccid2_pr_debug("=========\n"); +#endif +} + +/** + * ccid2_rtt_estimator - Sample RTT and compute RTO using RFC2988 algorithm + * @sk: socket to perform estimator on + * + * This code is almost identical with TCP's tcp_rtt_estimator(), since + * - it has a higher sampling frequency (recommended by RFC 1323), + * - the RTO does not collapse into RTT due to RTTVAR going towards zero, + * - it is simple (cf. more complex proposals such as Eifel timer or research + * which suggests that the gain should be set according to window size), + * - in tests it was found to work well with CCID2 [gerrit]. + */ +static void ccid2_rtt_estimator(struct sock *sk, const long mrtt) +{ + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); + long m = mrtt ? : 1; + + if (hc->tx_srtt == 0) { + /* First measurement m */ + hc->tx_srtt = m << 3; + hc->tx_mdev = m << 1; + + hc->tx_mdev_max = max(hc->tx_mdev, tcp_rto_min(sk)); + hc->tx_rttvar = hc->tx_mdev_max; + + hc->tx_rtt_seq = dccp_sk(sk)->dccps_gss; + } else { + /* Update scaled SRTT as SRTT += 1/8 * (m - SRTT) */ + m -= (hc->tx_srtt >> 3); + hc->tx_srtt += m; + + /* Similarly, update scaled mdev with regard to |m| */ + if (m < 0) { + m = -m; + m -= (hc->tx_mdev >> 2); + /* + * This neutralises RTO increase when RTT < SRTT - mdev + * (see P. Sarolahti, A. Kuznetsov,"Congestion Control + * in Linux TCP", USENIX 2002, pp. 49-62). + */ + if (m > 0) + m >>= 3; + } else { + m -= (hc->tx_mdev >> 2); + } + hc->tx_mdev += m; + + if (hc->tx_mdev > hc->tx_mdev_max) { + hc->tx_mdev_max = hc->tx_mdev; + if (hc->tx_mdev_max > hc->tx_rttvar) + hc->tx_rttvar = hc->tx_mdev_max; + } + + /* + * Decay RTTVAR at most once per flight, exploiting that + * 1) pipe <= cwnd <= Sequence_Window = W (RFC 4340, 7.5.2) + * 2) AWL = GSS-W+1 <= GAR <= GSS (RFC 4340, 7.5.1) + * GAR is a useful bound for FlightSize = pipe. + * AWL is probably too low here, as it over-estimates pipe. + */ + if (after48(dccp_sk(sk)->dccps_gar, hc->tx_rtt_seq)) { + if (hc->tx_mdev_max < hc->tx_rttvar) + hc->tx_rttvar -= (hc->tx_rttvar - + hc->tx_mdev_max) >> 2; + hc->tx_rtt_seq = dccp_sk(sk)->dccps_gss; + hc->tx_mdev_max = tcp_rto_min(sk); + } + } + + /* + * Set RTO from SRTT and RTTVAR + * As in TCP, 4 * RTTVAR >= TCP_RTO_MIN, giving a minimum RTO of 200 ms. + * This agrees with RFC 4341, 5: + * "Because DCCP does not retransmit data, DCCP does not require + * TCP's recommended minimum timeout of one second". + */ + hc->tx_rto = (hc->tx_srtt >> 3) + hc->tx_rttvar; + + if (hc->tx_rto > DCCP_RTO_MAX) + hc->tx_rto = DCCP_RTO_MAX; +} + +static void ccid2_new_ack(struct sock *sk, struct ccid2_seq *seqp, + unsigned int *maxincr) +{ + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); + struct dccp_sock *dp = dccp_sk(sk); + int r_seq_used = hc->tx_cwnd / dp->dccps_l_ack_ratio; + + if (hc->tx_cwnd < dp->dccps_l_seq_win && + r_seq_used < dp->dccps_r_seq_win) { + if (hc->tx_cwnd < hc->tx_ssthresh) { + if (*maxincr > 0 && ++hc->tx_packets_acked >= 2) { + hc->tx_cwnd += 1; + *maxincr -= 1; + hc->tx_packets_acked = 0; + } + } else if (++hc->tx_packets_acked >= hc->tx_cwnd) { + hc->tx_cwnd += 1; + hc->tx_packets_acked = 0; + } + } + + /* + * Adjust the local sequence window and the ack ratio to allow about + * 5 times the number of packets in the network (RFC 4340 7.5.2) + */ + if (r_seq_used * CCID2_WIN_CHANGE_FACTOR >= dp->dccps_r_seq_win) + ccid2_change_l_ack_ratio(sk, dp->dccps_l_ack_ratio * 2); + else if (r_seq_used * CCID2_WIN_CHANGE_FACTOR < dp->dccps_r_seq_win/2) + ccid2_change_l_ack_ratio(sk, dp->dccps_l_ack_ratio / 2 ? : 1U); + + if (hc->tx_cwnd * CCID2_WIN_CHANGE_FACTOR >= dp->dccps_l_seq_win) + ccid2_change_l_seq_window(sk, dp->dccps_l_seq_win * 2); + else if (hc->tx_cwnd * CCID2_WIN_CHANGE_FACTOR < dp->dccps_l_seq_win/2) + ccid2_change_l_seq_window(sk, dp->dccps_l_seq_win / 2); + + /* + * FIXME: RTT is sampled several times per acknowledgment (for each + * entry in the Ack Vector), instead of once per Ack (as in TCP SACK). + * This causes the RTT to be over-estimated, since the older entries + * in the Ack Vector have earlier sending times. + * The cleanest solution is to not use the ccid2s_sent field at all + * and instead use DCCP timestamps: requires changes in other places. + */ + ccid2_rtt_estimator(sk, ccid2_jiffies32 - seqp->ccid2s_sent); +} + +static void ccid2_congestion_event(struct sock *sk, struct ccid2_seq *seqp) +{ + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); + + if ((s32)(seqp->ccid2s_sent - hc->tx_last_cong) < 0) { + ccid2_pr_debug("Multiple losses in an RTT---treating as one\n"); + return; + } + + hc->tx_last_cong = ccid2_jiffies32; + + hc->tx_cwnd = hc->tx_cwnd / 2 ? : 1U; + hc->tx_ssthresh = max(hc->tx_cwnd, 2U); + + ccid2_check_l_ack_ratio(sk); +} + +static int ccid2_hc_tx_parse_options(struct sock *sk, u8 packet_type, + u8 option, u8 *optval, u8 optlen) +{ + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); + + switch (option) { + case DCCPO_ACK_VECTOR_0: + case DCCPO_ACK_VECTOR_1: + return dccp_ackvec_parsed_add(&hc->tx_av_chunks, optval, optlen, + option - DCCPO_ACK_VECTOR_0); + } + return 0; +} + +static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) +{ + struct dccp_sock *dp = dccp_sk(sk); + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); + const bool sender_was_blocked = ccid2_cwnd_network_limited(hc); + struct dccp_ackvec_parsed *avp; + u64 ackno, seqno; + struct ccid2_seq *seqp; + int done = 0; + unsigned int maxincr = 0; + + /* check reverse path congestion */ + seqno = DCCP_SKB_CB(skb)->dccpd_seq; + + /* XXX this whole "algorithm" is broken. Need to fix it to keep track + * of the seqnos of the dupacks so that rpseq and rpdupack are correct + * -sorbo. + */ + /* need to bootstrap */ + if (hc->tx_rpdupack == -1) { + hc->tx_rpdupack = 0; + hc->tx_rpseq = seqno; + } else { + /* check if packet is consecutive */ + if (dccp_delta_seqno(hc->tx_rpseq, seqno) == 1) + hc->tx_rpseq = seqno; + /* it's a later packet */ + else if (after48(seqno, hc->tx_rpseq)) { + hc->tx_rpdupack++; + + /* check if we got enough dupacks */ + if (hc->tx_rpdupack >= NUMDUPACK) { + hc->tx_rpdupack = -1; /* XXX lame */ + hc->tx_rpseq = 0; +#ifdef __CCID2_COPES_GRACEFULLY_WITH_ACK_CONGESTION_CONTROL__ + /* + * FIXME: Ack Congestion Control is broken; in + * the current state instabilities occurred with + * Ack Ratios greater than 1; causing hang-ups + * and long RTO timeouts. This needs to be fixed + * before opening up dynamic changes. -- gerrit + */ + ccid2_change_l_ack_ratio(sk, 2 * dp->dccps_l_ack_ratio); +#endif + } + } + } + + /* check forward path congestion */ + if (dccp_packet_without_ack(skb)) + return; + + /* still didn't send out new data packets */ + if (hc->tx_seqh == hc->tx_seqt) + goto done; + + ackno = DCCP_SKB_CB(skb)->dccpd_ack_seq; + if (after48(ackno, hc->tx_high_ack)) + hc->tx_high_ack = ackno; + + seqp = hc->tx_seqt; + while (before48(seqp->ccid2s_seq, ackno)) { + seqp = seqp->ccid2s_next; + if (seqp == hc->tx_seqh) { + seqp = hc->tx_seqh->ccid2s_prev; + break; + } + } + + /* + * In slow-start, cwnd can increase up to a maximum of Ack Ratio/2 + * packets per acknowledgement. Rounding up avoids that cwnd is not + * advanced when Ack Ratio is 1 and gives a slight edge otherwise. + */ + if (hc->tx_cwnd < hc->tx_ssthresh) + maxincr = DIV_ROUND_UP(dp->dccps_l_ack_ratio, 2); + + /* go through all ack vectors */ + list_for_each_entry(avp, &hc->tx_av_chunks, node) { + /* go through this ack vector */ + for (; avp->len--; avp->vec++) { + u64 ackno_end_rl = SUB48(ackno, + dccp_ackvec_runlen(avp->vec)); + + ccid2_pr_debug("ackvec %llu |%u,%u|\n", + (unsigned long long)ackno, + dccp_ackvec_state(avp->vec) >> 6, + dccp_ackvec_runlen(avp->vec)); + /* if the seqno we are analyzing is larger than the + * current ackno, then move towards the tail of our + * seqnos. + */ + while (after48(seqp->ccid2s_seq, ackno)) { + if (seqp == hc->tx_seqt) { + done = 1; + break; + } + seqp = seqp->ccid2s_prev; + } + if (done) + break; + + /* check all seqnos in the range of the vector + * run length + */ + while (between48(seqp->ccid2s_seq,ackno_end_rl,ackno)) { + const u8 state = dccp_ackvec_state(avp->vec); + + /* new packet received or marked */ + if (state != DCCPAV_NOT_RECEIVED && + !seqp->ccid2s_acked) { + if (state == DCCPAV_ECN_MARKED) + ccid2_congestion_event(sk, + seqp); + else + ccid2_new_ack(sk, seqp, + &maxincr); + + seqp->ccid2s_acked = 1; + ccid2_pr_debug("Got ack for %llu\n", + (unsigned long long)seqp->ccid2s_seq); + hc->tx_pipe--; + } + if (seqp == hc->tx_seqt) { + done = 1; + break; + } + seqp = seqp->ccid2s_prev; + } + if (done) + break; + + ackno = SUB48(ackno_end_rl, 1); + } + if (done) + break; + } + + /* The state about what is acked should be correct now + * Check for NUMDUPACK + */ + seqp = hc->tx_seqt; + while (before48(seqp->ccid2s_seq, hc->tx_high_ack)) { + seqp = seqp->ccid2s_next; + if (seqp == hc->tx_seqh) { + seqp = hc->tx_seqh->ccid2s_prev; + break; + } + } + done = 0; + while (1) { + if (seqp->ccid2s_acked) { + done++; + if (done == NUMDUPACK) + break; + } + if (seqp == hc->tx_seqt) + break; + seqp = seqp->ccid2s_prev; + } + + /* If there are at least 3 acknowledgements, anything unacknowledged + * below the last sequence number is considered lost + */ + if (done == NUMDUPACK) { + struct ccid2_seq *last_acked = seqp; + + /* check for lost packets */ + while (1) { + if (!seqp->ccid2s_acked) { + ccid2_pr_debug("Packet lost: %llu\n", + (unsigned long long)seqp->ccid2s_seq); + /* XXX need to traverse from tail -> head in + * order to detect multiple congestion events in + * one ack vector. + */ + ccid2_congestion_event(sk, seqp); + hc->tx_pipe--; + } + if (seqp == hc->tx_seqt) + break; + seqp = seqp->ccid2s_prev; + } + + hc->tx_seqt = last_acked; + } + + /* trim acked packets in tail */ + while (hc->tx_seqt != hc->tx_seqh) { + if (!hc->tx_seqt->ccid2s_acked) + break; + + hc->tx_seqt = hc->tx_seqt->ccid2s_next; + } + + /* restart RTO timer if not all outstanding data has been acked */ + if (hc->tx_pipe == 0) + sk_stop_timer(sk, &hc->tx_rtotimer); + else + sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto); +done: + /* check if incoming Acks allow pending packets to be sent */ + if (sender_was_blocked && !ccid2_cwnd_network_limited(hc)) + dccp_tasklet_schedule(sk); + dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks); +} + +static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk) +{ + struct ccid2_hc_tx_sock *hc = ccid_priv(ccid); + struct dccp_sock *dp = dccp_sk(sk); + u32 max_ratio; + + /* RFC 4341, 5: initialise ssthresh to arbitrarily high (max) value */ + hc->tx_ssthresh = ~0U; + + /* Use larger initial windows (RFC 4341, section 5). */ + hc->tx_cwnd = rfc3390_bytes_to_packets(dp->dccps_mss_cache); + hc->tx_expected_wnd = hc->tx_cwnd; + + /* Make sure that Ack Ratio is enabled and within bounds. */ + max_ratio = DIV_ROUND_UP(hc->tx_cwnd, 2); + if (dp->dccps_l_ack_ratio == 0 || dp->dccps_l_ack_ratio > max_ratio) + dp->dccps_l_ack_ratio = max_ratio; + + /* XXX init ~ to window size... */ + if (ccid2_hc_tx_alloc_seq(hc)) + return -ENOMEM; + + hc->tx_rto = DCCP_TIMEOUT_INIT; + hc->tx_rpdupack = -1; + hc->tx_last_cong = hc->tx_lsndtime = hc->tx_cwnd_stamp = ccid2_jiffies32; + hc->tx_cwnd_used = 0; + hc->sk = sk; + timer_setup(&hc->tx_rtotimer, ccid2_hc_tx_rto_expire, 0); + INIT_LIST_HEAD(&hc->tx_av_chunks); + return 0; +} + +static void ccid2_hc_tx_exit(struct sock *sk) +{ + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); + int i; + + sk_stop_timer(sk, &hc->tx_rtotimer); + + for (i = 0; i < hc->tx_seqbufc; i++) + kfree(hc->tx_seqbuf[i]); + hc->tx_seqbufc = 0; + dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks); +} + +static void ccid2_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb) +{ + struct ccid2_hc_rx_sock *hc = ccid2_hc_rx_sk(sk); + + if (!dccp_data_packet(skb)) + return; + + if (++hc->rx_num_data_pkts >= dccp_sk(sk)->dccps_r_ack_ratio) { + dccp_send_ack(sk); + hc->rx_num_data_pkts = 0; + } +} + +struct ccid_operations ccid2_ops = { + .ccid_id = DCCPC_CCID2, + .ccid_name = "TCP-like", + .ccid_hc_tx_obj_size = sizeof(struct ccid2_hc_tx_sock), + .ccid_hc_tx_init = ccid2_hc_tx_init, + .ccid_hc_tx_exit = ccid2_hc_tx_exit, + .ccid_hc_tx_send_packet = ccid2_hc_tx_send_packet, + .ccid_hc_tx_packet_sent = ccid2_hc_tx_packet_sent, + .ccid_hc_tx_parse_options = ccid2_hc_tx_parse_options, + .ccid_hc_tx_packet_recv = ccid2_hc_tx_packet_recv, + .ccid_hc_rx_obj_size = sizeof(struct ccid2_hc_rx_sock), + .ccid_hc_rx_packet_recv = ccid2_hc_rx_packet_recv, +}; + +#ifdef CONFIG_IP_DCCP_CCID2_DEBUG +module_param(ccid2_debug, bool, 0644); +MODULE_PARM_DESC(ccid2_debug, "Enable CCID-2 debug messages"); +#endif -- cgit v1.2.3