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(). ... --- drivers/net/ifb.c | 458 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 458 insertions(+) create mode 100644 drivers/net/ifb.c (limited to 'drivers/net/ifb.c') diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c new file mode 100644 index 000000000..78253ad57 --- /dev/null +++ b/drivers/net/ifb.c @@ -0,0 +1,458 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* drivers/net/ifb.c: + + The purpose of this driver is to provide a device that allows + for sharing of resources: + + 1) qdiscs/policies that are per device as opposed to system wide. + ifb allows for a device which can be redirected to thus providing + an impression of sharing. + + 2) Allows for queueing incoming traffic for shaping instead of + dropping. + + The original concept is based on what is known as the IMQ + driver initially written by Martin Devera, later rewritten + by Patrick McHardy and then maintained by Andre Correa. + + You need the tc action mirror or redirect to feed this device + packets. + + + Authors: Jamal Hadi Salim (2005) + +*/ + + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define TX_Q_LIMIT 32 + +struct ifb_q_stats { + u64 packets; + u64 bytes; + struct u64_stats_sync sync; +}; + +struct ifb_q_private { + struct net_device *dev; + struct tasklet_struct ifb_tasklet; + int tasklet_pending; + int txqnum; + struct sk_buff_head rq; + struct sk_buff_head tq; + struct ifb_q_stats rx_stats; + struct ifb_q_stats tx_stats; +} ____cacheline_aligned_in_smp; + +struct ifb_dev_private { + struct ifb_q_private *tx_private; +}; + +/* For ethtools stats. */ +struct ifb_q_stats_desc { + char desc[ETH_GSTRING_LEN]; + size_t offset; +}; + +#define IFB_Q_STAT(m) offsetof(struct ifb_q_stats, m) + +static const struct ifb_q_stats_desc ifb_q_stats_desc[] = { + { "packets", IFB_Q_STAT(packets) }, + { "bytes", IFB_Q_STAT(bytes) }, +}; + +#define IFB_Q_STATS_LEN ARRAY_SIZE(ifb_q_stats_desc) + +static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev); +static int ifb_open(struct net_device *dev); +static int ifb_close(struct net_device *dev); + +static void ifb_update_q_stats(struct ifb_q_stats *stats, int len) +{ + u64_stats_update_begin(&stats->sync); + stats->packets++; + stats->bytes += len; + u64_stats_update_end(&stats->sync); +} + +static void ifb_ri_tasklet(struct tasklet_struct *t) +{ + struct ifb_q_private *txp = from_tasklet(txp, t, ifb_tasklet); + struct netdev_queue *txq; + struct sk_buff *skb; + + txq = netdev_get_tx_queue(txp->dev, txp->txqnum); + skb = skb_peek(&txp->tq); + if (!skb) { + if (!__netif_tx_trylock(txq)) + goto resched; + skb_queue_splice_tail_init(&txp->rq, &txp->tq); + __netif_tx_unlock(txq); + } + + while ((skb = __skb_dequeue(&txp->tq)) != NULL) { + /* Skip tc and netfilter to prevent redirection loop. */ + skb->redirected = 0; +#ifdef CONFIG_NET_CLS_ACT + skb->tc_skip_classify = 1; +#endif + nf_skip_egress(skb, true); + + ifb_update_q_stats(&txp->tx_stats, skb->len); + + rcu_read_lock(); + skb->dev = dev_get_by_index_rcu(dev_net(txp->dev), skb->skb_iif); + if (!skb->dev) { + rcu_read_unlock(); + dev_kfree_skb(skb); + txp->dev->stats.tx_dropped++; + if (skb_queue_len(&txp->tq) != 0) + goto resched; + break; + } + rcu_read_unlock(); + skb->skb_iif = txp->dev->ifindex; + + if (!skb->from_ingress) { + dev_queue_xmit(skb); + } else { + skb_pull_rcsum(skb, skb->mac_len); + netif_receive_skb(skb); + } + } + + if (__netif_tx_trylock(txq)) { + skb = skb_peek(&txp->rq); + if (!skb) { + txp->tasklet_pending = 0; + if (netif_tx_queue_stopped(txq)) + netif_tx_wake_queue(txq); + } else { + __netif_tx_unlock(txq); + goto resched; + } + __netif_tx_unlock(txq); + } else { +resched: + txp->tasklet_pending = 1; + tasklet_schedule(&txp->ifb_tasklet); + } + +} + +static void ifb_stats64(struct net_device *dev, + struct rtnl_link_stats64 *stats) +{ + struct ifb_dev_private *dp = netdev_priv(dev); + struct ifb_q_private *txp = dp->tx_private; + unsigned int start; + u64 packets, bytes; + int i; + + for (i = 0; i < dev->num_tx_queues; i++,txp++) { + do { + start = u64_stats_fetch_begin(&txp->rx_stats.sync); + packets = txp->rx_stats.packets; + bytes = txp->rx_stats.bytes; + } while (u64_stats_fetch_retry(&txp->rx_stats.sync, start)); + stats->rx_packets += packets; + stats->rx_bytes += bytes; + + do { + start = u64_stats_fetch_begin(&txp->tx_stats.sync); + packets = txp->tx_stats.packets; + bytes = txp->tx_stats.bytes; + } while (u64_stats_fetch_retry(&txp->tx_stats.sync, start)); + stats->tx_packets += packets; + stats->tx_bytes += bytes; + } + stats->rx_dropped = dev->stats.rx_dropped; + stats->tx_dropped = dev->stats.tx_dropped; +} + +static int ifb_dev_init(struct net_device *dev) +{ + struct ifb_dev_private *dp = netdev_priv(dev); + struct ifb_q_private *txp; + int i; + + txp = kcalloc(dev->num_tx_queues, sizeof(*txp), GFP_KERNEL); + if (!txp) + return -ENOMEM; + dp->tx_private = txp; + for (i = 0; i < dev->num_tx_queues; i++,txp++) { + txp->txqnum = i; + txp->dev = dev; + __skb_queue_head_init(&txp->rq); + __skb_queue_head_init(&txp->tq); + u64_stats_init(&txp->rx_stats.sync); + u64_stats_init(&txp->tx_stats.sync); + tasklet_setup(&txp->ifb_tasklet, ifb_ri_tasklet); + netif_tx_start_queue(netdev_get_tx_queue(dev, i)); + } + return 0; +} + +static void ifb_get_strings(struct net_device *dev, u32 stringset, u8 *buf) +{ + u8 *p = buf; + int i, j; + + switch (stringset) { + case ETH_SS_STATS: + for (i = 0; i < dev->real_num_rx_queues; i++) + for (j = 0; j < IFB_Q_STATS_LEN; j++) + ethtool_sprintf(&p, "rx_queue_%u_%.18s", + i, ifb_q_stats_desc[j].desc); + + for (i = 0; i < dev->real_num_tx_queues; i++) + for (j = 0; j < IFB_Q_STATS_LEN; j++) + ethtool_sprintf(&p, "tx_queue_%u_%.18s", + i, ifb_q_stats_desc[j].desc); + + break; + } +} + +static int ifb_get_sset_count(struct net_device *dev, int sset) +{ + switch (sset) { + case ETH_SS_STATS: + return IFB_Q_STATS_LEN * (dev->real_num_rx_queues + + dev->real_num_tx_queues); + default: + return -EOPNOTSUPP; + } +} + +static void ifb_fill_stats_data(u64 **data, + struct ifb_q_stats *q_stats) +{ + void *stats_base = (void *)q_stats; + unsigned int start; + size_t offset; + int j; + + do { + start = u64_stats_fetch_begin(&q_stats->sync); + for (j = 0; j < IFB_Q_STATS_LEN; j++) { + offset = ifb_q_stats_desc[j].offset; + (*data)[j] = *(u64 *)(stats_base + offset); + } + } while (u64_stats_fetch_retry(&q_stats->sync, start)); + + *data += IFB_Q_STATS_LEN; +} + +static void ifb_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, u64 *data) +{ + struct ifb_dev_private *dp = netdev_priv(dev); + struct ifb_q_private *txp; + int i; + + for (i = 0; i < dev->real_num_rx_queues; i++) { + txp = dp->tx_private + i; + ifb_fill_stats_data(&data, &txp->rx_stats); + } + + for (i = 0; i < dev->real_num_tx_queues; i++) { + txp = dp->tx_private + i; + ifb_fill_stats_data(&data, &txp->tx_stats); + } +} + +static const struct net_device_ops ifb_netdev_ops = { + .ndo_open = ifb_open, + .ndo_stop = ifb_close, + .ndo_get_stats64 = ifb_stats64, + .ndo_start_xmit = ifb_xmit, + .ndo_validate_addr = eth_validate_addr, + .ndo_init = ifb_dev_init, +}; + +static const struct ethtool_ops ifb_ethtool_ops = { + .get_strings = ifb_get_strings, + .get_sset_count = ifb_get_sset_count, + .get_ethtool_stats = ifb_get_ethtool_stats, +}; + +#define IFB_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | NETIF_F_FRAGLIST | \ + NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL | \ + NETIF_F_HIGHDMA | NETIF_F_HW_VLAN_CTAG_TX | \ + NETIF_F_HW_VLAN_STAG_TX) + +static void ifb_dev_free(struct net_device *dev) +{ + struct ifb_dev_private *dp = netdev_priv(dev); + struct ifb_q_private *txp = dp->tx_private; + int i; + + for (i = 0; i < dev->num_tx_queues; i++,txp++) { + tasklet_kill(&txp->ifb_tasklet); + __skb_queue_purge(&txp->rq); + __skb_queue_purge(&txp->tq); + } + kfree(dp->tx_private); +} + +static void ifb_setup(struct net_device *dev) +{ + /* Initialize the device structure. */ + dev->netdev_ops = &ifb_netdev_ops; + dev->ethtool_ops = &ifb_ethtool_ops; + + /* Fill in device structure with ethernet-generic values. */ + ether_setup(dev); + dev->tx_queue_len = TX_Q_LIMIT; + + dev->features |= IFB_FEATURES; + dev->hw_features |= dev->features; + dev->hw_enc_features |= dev->features; + dev->vlan_features |= IFB_FEATURES & ~(NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX); + + dev->flags |= IFF_NOARP; + dev->flags &= ~IFF_MULTICAST; + dev->priv_flags &= ~IFF_TX_SKB_SHARING; + netif_keep_dst(dev); + eth_hw_addr_random(dev); + dev->needs_free_netdev = true; + dev->priv_destructor = ifb_dev_free; + + dev->min_mtu = 0; + dev->max_mtu = 0; +} + +static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct ifb_dev_private *dp = netdev_priv(dev); + struct ifb_q_private *txp = dp->tx_private + skb_get_queue_mapping(skb); + + ifb_update_q_stats(&txp->rx_stats, skb->len); + + if (!skb->redirected || !skb->skb_iif) { + dev_kfree_skb(skb); + dev->stats.rx_dropped++; + return NETDEV_TX_OK; + } + + if (skb_queue_len(&txp->rq) >= dev->tx_queue_len) + netif_tx_stop_queue(netdev_get_tx_queue(dev, txp->txqnum)); + + __skb_queue_tail(&txp->rq, skb); + if (!txp->tasklet_pending) { + txp->tasklet_pending = 1; + tasklet_schedule(&txp->ifb_tasklet); + } + + return NETDEV_TX_OK; +} + +static int ifb_close(struct net_device *dev) +{ + netif_tx_stop_all_queues(dev); + return 0; +} + +static int ifb_open(struct net_device *dev) +{ + netif_tx_start_all_queues(dev); + return 0; +} + +static int ifb_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + if (tb[IFLA_ADDRESS]) { + if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) + return -EINVAL; + if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) + return -EADDRNOTAVAIL; + } + return 0; +} + +static struct rtnl_link_ops ifb_link_ops __read_mostly = { + .kind = "ifb", + .priv_size = sizeof(struct ifb_dev_private), + .setup = ifb_setup, + .validate = ifb_validate, +}; + +/* Number of ifb devices to be set up by this module. + * Note that these legacy devices have one queue. + * Prefer something like : ip link add ifb10 numtxqueues 8 type ifb + */ +static int numifbs = 2; +module_param(numifbs, int, 0); +MODULE_PARM_DESC(numifbs, "Number of ifb devices"); + +static int __init ifb_init_one(int index) +{ + struct net_device *dev_ifb; + int err; + + dev_ifb = alloc_netdev(sizeof(struct ifb_dev_private), "ifb%d", + NET_NAME_UNKNOWN, ifb_setup); + + if (!dev_ifb) + return -ENOMEM; + + dev_ifb->rtnl_link_ops = &ifb_link_ops; + err = register_netdevice(dev_ifb); + if (err < 0) + goto err; + + return 0; + +err: + free_netdev(dev_ifb); + return err; +} + +static int __init ifb_init_module(void) +{ + int i, err; + + down_write(&pernet_ops_rwsem); + rtnl_lock(); + err = __rtnl_link_register(&ifb_link_ops); + if (err < 0) + goto out; + + for (i = 0; i < numifbs && !err; i++) { + err = ifb_init_one(i); + cond_resched(); + } + if (err) + __rtnl_link_unregister(&ifb_link_ops); + +out: + rtnl_unlock(); + up_write(&pernet_ops_rwsem); + + return err; +} + +static void __exit ifb_cleanup_module(void) +{ + rtnl_link_unregister(&ifb_link_ops); +} + +module_init(ifb_init_module); +module_exit(ifb_cleanup_module); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Jamal Hadi Salim"); +MODULE_ALIAS_RTNL_LINK("ifb"); -- cgit v1.2.3