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/netdevsim/bus.c | 354 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 354 insertions(+) create mode 100644 drivers/net/netdevsim/bus.c (limited to 'drivers/net/netdevsim/bus.c') diff --git a/drivers/net/netdevsim/bus.c b/drivers/net/netdevsim/bus.c new file mode 100644 index 000000000..0052968e8 --- /dev/null +++ b/drivers/net/netdevsim/bus.c @@ -0,0 +1,354 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2017 Netronome Systems, Inc. + * Copyright (C) 2019 Mellanox Technologies. All rights reserved + */ + +#include +#include +#include +#include +#include +#include +#include + +#include "netdevsim.h" + +static DEFINE_IDA(nsim_bus_dev_ids); +static LIST_HEAD(nsim_bus_dev_list); +static DEFINE_MUTEX(nsim_bus_dev_list_lock); +static bool nsim_bus_enable; + +static struct nsim_bus_dev *to_nsim_bus_dev(struct device *dev) +{ + return container_of(dev, struct nsim_bus_dev, dev); +} + +static ssize_t +nsim_bus_dev_numvfs_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev); + unsigned int num_vfs; + int ret; + + ret = kstrtouint(buf, 0, &num_vfs); + if (ret) + return ret; + + device_lock(dev); + ret = -ENOENT; + if (dev_get_drvdata(dev)) + ret = nsim_drv_configure_vfs(nsim_bus_dev, num_vfs); + device_unlock(dev); + + return ret ? ret : count; +} + +static ssize_t +nsim_bus_dev_numvfs_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev); + + return sprintf(buf, "%u\n", nsim_bus_dev->num_vfs); +} + +static struct device_attribute nsim_bus_dev_numvfs_attr = + __ATTR(sriov_numvfs, 0664, nsim_bus_dev_numvfs_show, + nsim_bus_dev_numvfs_store); + +static ssize_t +new_port_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev); + unsigned int port_index; + int ret; + + /* Prevent to use nsim_bus_dev before initialization. */ + if (!smp_load_acquire(&nsim_bus_dev->init)) + return -EBUSY; + ret = kstrtouint(buf, 0, &port_index); + if (ret) + return ret; + + ret = nsim_drv_port_add(nsim_bus_dev, NSIM_DEV_PORT_TYPE_PF, port_index); + return ret ? ret : count; +} + +static struct device_attribute nsim_bus_dev_new_port_attr = __ATTR_WO(new_port); + +static ssize_t +del_port_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev); + unsigned int port_index; + int ret; + + /* Prevent to use nsim_bus_dev before initialization. */ + if (!smp_load_acquire(&nsim_bus_dev->init)) + return -EBUSY; + ret = kstrtouint(buf, 0, &port_index); + if (ret) + return ret; + + ret = nsim_drv_port_del(nsim_bus_dev, NSIM_DEV_PORT_TYPE_PF, port_index); + return ret ? ret : count; +} + +static struct device_attribute nsim_bus_dev_del_port_attr = __ATTR_WO(del_port); + +static struct attribute *nsim_bus_dev_attrs[] = { + &nsim_bus_dev_numvfs_attr.attr, + &nsim_bus_dev_new_port_attr.attr, + &nsim_bus_dev_del_port_attr.attr, + NULL, +}; + +static const struct attribute_group nsim_bus_dev_attr_group = { + .attrs = nsim_bus_dev_attrs, +}; + +static const struct attribute_group *nsim_bus_dev_attr_groups[] = { + &nsim_bus_dev_attr_group, + NULL, +}; + +static void nsim_bus_dev_release(struct device *dev) +{ + struct nsim_bus_dev *nsim_bus_dev; + + nsim_bus_dev = container_of(dev, struct nsim_bus_dev, dev); + kfree(nsim_bus_dev); +} + +static struct device_type nsim_bus_dev_type = { + .groups = nsim_bus_dev_attr_groups, + .release = nsim_bus_dev_release, +}; + +static struct nsim_bus_dev * +nsim_bus_dev_new(unsigned int id, unsigned int port_count, unsigned int num_queues); + +static ssize_t +new_device_store(struct bus_type *bus, const char *buf, size_t count) +{ + unsigned int id, port_count, num_queues; + struct nsim_bus_dev *nsim_bus_dev; + int err; + + err = sscanf(buf, "%u %u %u", &id, &port_count, &num_queues); + switch (err) { + case 1: + port_count = 1; + fallthrough; + case 2: + num_queues = 1; + fallthrough; + case 3: + if (id > INT_MAX) { + pr_err("Value of \"id\" is too big.\n"); + return -EINVAL; + } + break; + default: + pr_err("Format for adding new device is \"id port_count num_queues\" (uint uint unit).\n"); + return -EINVAL; + } + + mutex_lock(&nsim_bus_dev_list_lock); + /* Prevent to use resource before initialization. */ + if (!smp_load_acquire(&nsim_bus_enable)) { + err = -EBUSY; + goto err; + } + + nsim_bus_dev = nsim_bus_dev_new(id, port_count, num_queues); + if (IS_ERR(nsim_bus_dev)) { + err = PTR_ERR(nsim_bus_dev); + goto err; + } + + /* Allow using nsim_bus_dev */ + smp_store_release(&nsim_bus_dev->init, true); + + list_add_tail(&nsim_bus_dev->list, &nsim_bus_dev_list); + mutex_unlock(&nsim_bus_dev_list_lock); + + return count; +err: + mutex_unlock(&nsim_bus_dev_list_lock); + return err; +} +static BUS_ATTR_WO(new_device); + +static void nsim_bus_dev_del(struct nsim_bus_dev *nsim_bus_dev); + +static ssize_t +del_device_store(struct bus_type *bus, const char *buf, size_t count) +{ + struct nsim_bus_dev *nsim_bus_dev, *tmp; + unsigned int id; + int err; + + err = sscanf(buf, "%u", &id); + switch (err) { + case 1: + if (id > INT_MAX) { + pr_err("Value of \"id\" is too big.\n"); + return -EINVAL; + } + break; + default: + pr_err("Format for deleting device is \"id\" (uint).\n"); + return -EINVAL; + } + + err = -ENOENT; + mutex_lock(&nsim_bus_dev_list_lock); + /* Prevent to use resource before initialization. */ + if (!smp_load_acquire(&nsim_bus_enable)) { + mutex_unlock(&nsim_bus_dev_list_lock); + return -EBUSY; + } + list_for_each_entry_safe(nsim_bus_dev, tmp, &nsim_bus_dev_list, list) { + if (nsim_bus_dev->dev.id != id) + continue; + list_del(&nsim_bus_dev->list); + nsim_bus_dev_del(nsim_bus_dev); + err = 0; + break; + } + mutex_unlock(&nsim_bus_dev_list_lock); + return !err ? count : err; +} +static BUS_ATTR_WO(del_device); + +static struct attribute *nsim_bus_attrs[] = { + &bus_attr_new_device.attr, + &bus_attr_del_device.attr, + NULL +}; +ATTRIBUTE_GROUPS(nsim_bus); + +static int nsim_bus_probe(struct device *dev) +{ + struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev); + + return nsim_drv_probe(nsim_bus_dev); +} + +static void nsim_bus_remove(struct device *dev) +{ + struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev); + + nsim_drv_remove(nsim_bus_dev); +} + +static int nsim_num_vf(struct device *dev) +{ + struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev); + + return nsim_bus_dev->num_vfs; +} + +static struct bus_type nsim_bus = { + .name = DRV_NAME, + .dev_name = DRV_NAME, + .bus_groups = nsim_bus_groups, + .probe = nsim_bus_probe, + .remove = nsim_bus_remove, + .num_vf = nsim_num_vf, +}; + +#define NSIM_BUS_DEV_MAX_VFS 4 + +static struct nsim_bus_dev * +nsim_bus_dev_new(unsigned int id, unsigned int port_count, unsigned int num_queues) +{ + struct nsim_bus_dev *nsim_bus_dev; + int err; + + nsim_bus_dev = kzalloc(sizeof(*nsim_bus_dev), GFP_KERNEL); + if (!nsim_bus_dev) + return ERR_PTR(-ENOMEM); + + err = ida_alloc_range(&nsim_bus_dev_ids, id, id, GFP_KERNEL); + if (err < 0) + goto err_nsim_bus_dev_free; + nsim_bus_dev->dev.id = err; + nsim_bus_dev->dev.bus = &nsim_bus; + nsim_bus_dev->dev.type = &nsim_bus_dev_type; + nsim_bus_dev->port_count = port_count; + nsim_bus_dev->num_queues = num_queues; + nsim_bus_dev->initial_net = current->nsproxy->net_ns; + nsim_bus_dev->max_vfs = NSIM_BUS_DEV_MAX_VFS; + /* Disallow using nsim_bus_dev */ + smp_store_release(&nsim_bus_dev->init, false); + + err = device_register(&nsim_bus_dev->dev); + if (err) + goto err_nsim_bus_dev_id_free; + + return nsim_bus_dev; + +err_nsim_bus_dev_id_free: + ida_free(&nsim_bus_dev_ids, nsim_bus_dev->dev.id); + put_device(&nsim_bus_dev->dev); + nsim_bus_dev = NULL; +err_nsim_bus_dev_free: + kfree(nsim_bus_dev); + return ERR_PTR(err); +} + +static void nsim_bus_dev_del(struct nsim_bus_dev *nsim_bus_dev) +{ + /* Disallow using nsim_bus_dev */ + smp_store_release(&nsim_bus_dev->init, false); + ida_free(&nsim_bus_dev_ids, nsim_bus_dev->dev.id); + device_unregister(&nsim_bus_dev->dev); +} + +static struct device_driver nsim_driver = { + .name = DRV_NAME, + .bus = &nsim_bus, + .owner = THIS_MODULE, +}; + +int nsim_bus_init(void) +{ + int err; + + err = bus_register(&nsim_bus); + if (err) + return err; + err = driver_register(&nsim_driver); + if (err) + goto err_bus_unregister; + /* Allow using resources */ + smp_store_release(&nsim_bus_enable, true); + return 0; + +err_bus_unregister: + bus_unregister(&nsim_bus); + return err; +} + +void nsim_bus_exit(void) +{ + struct nsim_bus_dev *nsim_bus_dev, *tmp; + + /* Disallow using resources */ + smp_store_release(&nsim_bus_enable, false); + + mutex_lock(&nsim_bus_dev_list_lock); + list_for_each_entry_safe(nsim_bus_dev, tmp, &nsim_bus_dev_list, list) { + list_del(&nsim_bus_dev->list); + nsim_bus_dev_del(nsim_bus_dev); + } + mutex_unlock(&nsim_bus_dev_list_lock); + + driver_unregister(&nsim_driver); + bus_unregister(&nsim_bus); +} -- cgit v1.2.3