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/ethernet/sun/ldmvsw.c | 476 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 476 insertions(+) create mode 100644 drivers/net/ethernet/sun/ldmvsw.c (limited to 'drivers/net/ethernet/sun/ldmvsw.c') diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c new file mode 100644 index 000000000..8addee6d0 --- /dev/null +++ b/drivers/net/ethernet/sun/ldmvsw.c @@ -0,0 +1,476 @@ +// SPDX-License-Identifier: GPL-2.0 +/* ldmvsw.c: Sun4v LDOM Virtual Switch Driver. + * + * Copyright (C) 2016-2017 Oracle. All rights reserved. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#if defined(CONFIG_IPV6) +#include +#endif + +#include +#include +#include + +#include +#include + +/* This driver makes use of the common code in sunvnet_common.c */ +#include "sunvnet_common.h" + +/* Length of time before we decide the hardware is hung, + * and dev->tx_timeout() should be called to fix the problem. + */ +#define VSW_TX_TIMEOUT (10 * HZ) + +/* Static HW Addr used for the network interfaces representing vsw ports */ +static u8 vsw_port_hwaddr[ETH_ALEN] = {0xFE, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF}; + +#define DRV_MODULE_NAME "ldmvsw" +#define DRV_MODULE_VERSION "1.2" +#define DRV_MODULE_RELDATE "March 4, 2017" + +static char version[] = + DRV_MODULE_NAME " " DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")"; +MODULE_AUTHOR("Oracle"); +MODULE_DESCRIPTION("Sun4v LDOM Virtual Switch Driver"); +MODULE_LICENSE("GPL"); +MODULE_VERSION(DRV_MODULE_VERSION); + +/* Ordered from largest major to lowest */ +static struct vio_version vsw_versions[] = { + { .major = 1, .minor = 8 }, + { .major = 1, .minor = 7 }, + { .major = 1, .minor = 6 }, + { .major = 1, .minor = 0 }, +}; + +static void vsw_get_drvinfo(struct net_device *dev, + struct ethtool_drvinfo *info) +{ + strscpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver)); + strscpy(info->version, DRV_MODULE_VERSION, sizeof(info->version)); +} + +static u32 vsw_get_msglevel(struct net_device *dev) +{ + struct vnet_port *port = netdev_priv(dev); + + return port->vp->msg_enable; +} + +static void vsw_set_msglevel(struct net_device *dev, u32 value) +{ + struct vnet_port *port = netdev_priv(dev); + + port->vp->msg_enable = value; +} + +static const struct ethtool_ops vsw_ethtool_ops = { + .get_drvinfo = vsw_get_drvinfo, + .get_msglevel = vsw_get_msglevel, + .set_msglevel = vsw_set_msglevel, + .get_link = ethtool_op_get_link, +}; + +static LIST_HEAD(vnet_list); +static DEFINE_MUTEX(vnet_list_mutex); + +/* func arg to vnet_start_xmit_common() to get the proper tx port */ +static struct vnet_port *vsw_tx_port_find(struct sk_buff *skb, + struct net_device *dev) +{ + struct vnet_port *port = netdev_priv(dev); + + return port; +} + +static u16 vsw_select_queue(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev) +{ + struct vnet_port *port = netdev_priv(dev); + + if (!port) + return 0; + + return port->q_index; +} + +/* Wrappers to common functions */ +static netdev_tx_t vsw_start_xmit(struct sk_buff *skb, struct net_device *dev) +{ + return sunvnet_start_xmit_common(skb, dev, vsw_tx_port_find); +} + +static void vsw_set_rx_mode(struct net_device *dev) +{ + struct vnet_port *port = netdev_priv(dev); + + return sunvnet_set_rx_mode_common(dev, port->vp); +} + +int ldmvsw_open(struct net_device *dev) +{ + struct vnet_port *port = netdev_priv(dev); + struct vio_driver_state *vio = &port->vio; + + /* reset the channel */ + vio_link_state_change(vio, LDC_EVENT_RESET); + vnet_port_reset(port); + vio_port_up(vio); + + return 0; +} +EXPORT_SYMBOL_GPL(ldmvsw_open); + +#ifdef CONFIG_NET_POLL_CONTROLLER +static void vsw_poll_controller(struct net_device *dev) +{ + struct vnet_port *port = netdev_priv(dev); + + return sunvnet_poll_controller_common(dev, port->vp); +} +#endif + +static const struct net_device_ops vsw_ops = { + .ndo_open = ldmvsw_open, + .ndo_stop = sunvnet_close_common, + .ndo_set_rx_mode = vsw_set_rx_mode, + .ndo_set_mac_address = sunvnet_set_mac_addr_common, + .ndo_validate_addr = eth_validate_addr, + .ndo_tx_timeout = sunvnet_tx_timeout_common, + .ndo_start_xmit = vsw_start_xmit, + .ndo_select_queue = vsw_select_queue, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = vsw_poll_controller, +#endif +}; + +static const char *local_mac_prop = "local-mac-address"; +static const char *cfg_handle_prop = "cfg-handle"; + +static struct vnet *vsw_get_vnet(struct mdesc_handle *hp, + u64 port_node, + u64 *handle) +{ + struct vnet *vp; + struct vnet *iter; + const u64 *local_mac = NULL; + const u64 *cfghandle = NULL; + u64 a; + + /* Get the parent virtual-network-switch macaddr and cfghandle */ + mdesc_for_each_arc(a, hp, port_node, MDESC_ARC_TYPE_BACK) { + u64 target = mdesc_arc_target(hp, a); + const char *name; + + name = mdesc_get_property(hp, target, "name", NULL); + if (!name || strcmp(name, "virtual-network-switch")) + continue; + + local_mac = mdesc_get_property(hp, target, + local_mac_prop, NULL); + cfghandle = mdesc_get_property(hp, target, + cfg_handle_prop, NULL); + break; + } + if (!local_mac || !cfghandle) + return ERR_PTR(-ENODEV); + + /* find or create associated vnet */ + vp = NULL; + mutex_lock(&vnet_list_mutex); + list_for_each_entry(iter, &vnet_list, list) { + if (iter->local_mac == *local_mac) { + vp = iter; + break; + } + } + + if (!vp) { + vp = kzalloc(sizeof(*vp), GFP_KERNEL); + if (unlikely(!vp)) { + mutex_unlock(&vnet_list_mutex); + return ERR_PTR(-ENOMEM); + } + + spin_lock_init(&vp->lock); + INIT_LIST_HEAD(&vp->port_list); + INIT_LIST_HEAD(&vp->list); + vp->local_mac = *local_mac; + list_add(&vp->list, &vnet_list); + } + + mutex_unlock(&vnet_list_mutex); + + *handle = (u64)*cfghandle; + + return vp; +} + +static struct net_device *vsw_alloc_netdev(u8 hwaddr[], + struct vio_dev *vdev, + u64 handle, + u64 port_id) +{ + struct net_device *dev; + struct vnet_port *port; + + dev = alloc_etherdev_mqs(sizeof(*port), VNET_MAX_TXQS, 1); + if (!dev) + return ERR_PTR(-ENOMEM); + dev->needed_headroom = VNET_PACKET_SKIP + 8; + dev->needed_tailroom = 8; + + eth_hw_addr_set(dev, hwaddr); + ether_addr_copy(dev->perm_addr, dev->dev_addr); + + sprintf(dev->name, "vif%d.%d", (int)handle, (int)port_id); + + dev->netdev_ops = &vsw_ops; + dev->ethtool_ops = &vsw_ethtool_ops; + dev->watchdog_timeo = VSW_TX_TIMEOUT; + + dev->hw_features = NETIF_F_HW_CSUM | NETIF_F_SG; + dev->features = dev->hw_features; + + /* MTU range: 68 - 65535 */ + dev->min_mtu = ETH_MIN_MTU; + dev->max_mtu = VNET_MAX_MTU; + + SET_NETDEV_DEV(dev, &vdev->dev); + + return dev; +} + +static struct ldc_channel_config vsw_ldc_cfg = { + .event = sunvnet_event_common, + .mtu = 64, + .mode = LDC_MODE_UNRELIABLE, +}; + +static struct vio_driver_ops vsw_vio_ops = { + .send_attr = sunvnet_send_attr_common, + .handle_attr = sunvnet_handle_attr_common, + .handshake_complete = sunvnet_handshake_complete_common, +}; + +static const char *remote_macaddr_prop = "remote-mac-address"; +static const char *id_prop = "id"; + +static int vsw_port_probe(struct vio_dev *vdev, const struct vio_device_id *id) +{ + struct mdesc_handle *hp; + struct vnet_port *port; + unsigned long flags; + struct vnet *vp; + struct net_device *dev; + const u64 *rmac; + int len, i, err; + const u64 *port_id; + u64 handle; + + hp = mdesc_grab(); + + rmac = mdesc_get_property(hp, vdev->mp, remote_macaddr_prop, &len); + err = -ENODEV; + if (!rmac) { + pr_err("Port lacks %s property\n", remote_macaddr_prop); + mdesc_release(hp); + return err; + } + + port_id = mdesc_get_property(hp, vdev->mp, id_prop, NULL); + err = -ENODEV; + if (!port_id) { + pr_err("Port lacks %s property\n", id_prop); + mdesc_release(hp); + return err; + } + + /* Get (or create) the vnet associated with this port */ + vp = vsw_get_vnet(hp, vdev->mp, &handle); + if (IS_ERR(vp)) { + err = PTR_ERR(vp); + pr_err("Failed to get vnet for vsw-port\n"); + mdesc_release(hp); + return err; + } + + mdesc_release(hp); + + dev = vsw_alloc_netdev(vsw_port_hwaddr, vdev, handle, *port_id); + if (IS_ERR(dev)) { + err = PTR_ERR(dev); + pr_err("Failed to alloc netdev for vsw-port\n"); + return err; + } + + port = netdev_priv(dev); + + INIT_LIST_HEAD(&port->list); + + for (i = 0; i < ETH_ALEN; i++) + port->raddr[i] = (*rmac >> (5 - i) * 8) & 0xff; + + port->vp = vp; + port->dev = dev; + port->switch_port = 1; + port->tso = false; /* no tso in vsw, misbehaves in bridge */ + port->tsolen = 0; + + /* Mark the port as belonging to ldmvsw which directs the + * common code to use the net_device in the vnet_port + * rather than the net_device in the vnet (which is used + * by sunvnet). This bit is used by the VNET_PORT_TO_NET_DEVICE + * macro. + */ + port->vsw = 1; + + err = vio_driver_init(&port->vio, vdev, VDEV_NETWORK, + vsw_versions, ARRAY_SIZE(vsw_versions), + &vsw_vio_ops, dev->name); + if (err) + goto err_out_free_dev; + + err = vio_ldc_alloc(&port->vio, &vsw_ldc_cfg, port); + if (err) + goto err_out_free_dev; + + dev_set_drvdata(&vdev->dev, port); + + netif_napi_add(dev, &port->napi, sunvnet_poll_common); + + spin_lock_irqsave(&vp->lock, flags); + list_add_rcu(&port->list, &vp->port_list); + spin_unlock_irqrestore(&vp->lock, flags); + + timer_setup(&port->clean_timer, sunvnet_clean_timer_expire_common, 0); + + err = register_netdev(dev); + if (err) { + pr_err("Cannot register net device, aborting\n"); + goto err_out_del_timer; + } + + spin_lock_irqsave(&vp->lock, flags); + sunvnet_port_add_txq_common(port); + spin_unlock_irqrestore(&vp->lock, flags); + + napi_enable(&port->napi); + vio_port_up(&port->vio); + + /* assure no carrier until we receive an LDC_EVENT_UP, + * even if the vsw config script tries to force us up + */ + netif_carrier_off(dev); + + netdev_info(dev, "LDOM vsw-port %pM\n", dev->dev_addr); + + pr_info("%s: PORT ( remote-mac %pM%s )\n", dev->name, + port->raddr, " switch-port"); + + return 0; + +err_out_del_timer: + del_timer_sync(&port->clean_timer); + list_del_rcu(&port->list); + synchronize_rcu(); + netif_napi_del(&port->napi); + dev_set_drvdata(&vdev->dev, NULL); + vio_ldc_free(&port->vio); + +err_out_free_dev: + free_netdev(dev); + return err; +} + +static void vsw_port_remove(struct vio_dev *vdev) +{ + struct vnet_port *port = dev_get_drvdata(&vdev->dev); + unsigned long flags; + + if (port) { + del_timer_sync(&port->vio.timer); + del_timer_sync(&port->clean_timer); + + napi_disable(&port->napi); + unregister_netdev(port->dev); + + list_del_rcu(&port->list); + + synchronize_rcu(); + spin_lock_irqsave(&port->vp->lock, flags); + sunvnet_port_rm_txq_common(port); + spin_unlock_irqrestore(&port->vp->lock, flags); + netif_napi_del(&port->napi); + sunvnet_port_free_tx_bufs_common(port); + vio_ldc_free(&port->vio); + + dev_set_drvdata(&vdev->dev, NULL); + + free_netdev(port->dev); + } +} + +static void vsw_cleanup(void) +{ + struct vnet *vp; + + /* just need to free up the vnet list */ + mutex_lock(&vnet_list_mutex); + while (!list_empty(&vnet_list)) { + vp = list_first_entry(&vnet_list, struct vnet, list); + list_del(&vp->list); + /* vio_unregister_driver() should have cleaned up port_list */ + if (!list_empty(&vp->port_list)) + pr_err("Ports not removed by VIO subsystem!\n"); + kfree(vp); + } + mutex_unlock(&vnet_list_mutex); +} + +static const struct vio_device_id vsw_port_match[] = { + { + .type = "vsw-port", + }, + {}, +}; +MODULE_DEVICE_TABLE(vio, vsw_port_match); + +static struct vio_driver vsw_port_driver = { + .id_table = vsw_port_match, + .probe = vsw_port_probe, + .remove = vsw_port_remove, + .name = "vsw_port", +}; + +static int __init vsw_init(void) +{ + pr_info("%s\n", version); + return vio_register_driver(&vsw_port_driver); +} + +static void __exit vsw_exit(void) +{ + vio_unregister_driver(&vsw_port_driver); + vsw_cleanup(); +} + +module_init(vsw_init); +module_exit(vsw_exit); -- cgit v1.2.3