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(). ... --- arch/um/os-Linux/drivers/ethertap_user.c | 248 +++++++++++++++++++++++++++++++ 1 file changed, 248 insertions(+) create mode 100644 arch/um/os-Linux/drivers/ethertap_user.c (limited to 'arch/um/os-Linux/drivers/ethertap_user.c') diff --git a/arch/um/os-Linux/drivers/ethertap_user.c b/arch/um/os-Linux/drivers/ethertap_user.c new file mode 100644 index 000000000..9483021d8 --- /dev/null +++ b/arch/um/os-Linux/drivers/ethertap_user.c @@ -0,0 +1,248 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) + * Copyright (C) 2001 Lennert Buytenhek (buytenh@gnu.org) and + * James Leu (jleu@mindspring.net). + * Copyright (C) 2001 by various other people who didn't put their name here. + */ + +#include +#include +#include +#include +#include +#include +#include "etap.h" +#include +#include +#include + +#define MAX_PACKET ETH_MAX_PACKET + +static int etap_user_init(void *data, void *dev) +{ + struct ethertap_data *pri = data; + + pri->dev = dev; + return 0; +} + +struct addr_change { + enum { ADD_ADDR, DEL_ADDR } what; + unsigned char addr[4]; + unsigned char netmask[4]; +}; + +static void etap_change(int op, unsigned char *addr, unsigned char *netmask, + int fd) +{ + struct addr_change change; + char *output; + int n; + + change.what = op; + memcpy(change.addr, addr, sizeof(change.addr)); + memcpy(change.netmask, netmask, sizeof(change.netmask)); + CATCH_EINTR(n = write(fd, &change, sizeof(change))); + if (n != sizeof(change)) { + printk(UM_KERN_ERR "etap_change - request failed, err = %d\n", + errno); + return; + } + + output = uml_kmalloc(UM_KERN_PAGE_SIZE, UM_GFP_KERNEL); + if (output == NULL) + printk(UM_KERN_ERR "etap_change : Failed to allocate output " + "buffer\n"); + read_output(fd, output, UM_KERN_PAGE_SIZE); + if (output != NULL) { + printk("%s", output); + kfree(output); + } +} + +static void etap_open_addr(unsigned char *addr, unsigned char *netmask, + void *arg) +{ + etap_change(ADD_ADDR, addr, netmask, *((int *) arg)); +} + +static void etap_close_addr(unsigned char *addr, unsigned char *netmask, + void *arg) +{ + etap_change(DEL_ADDR, addr, netmask, *((int *) arg)); +} + +struct etap_pre_exec_data { + int control_remote; + int control_me; + int data_me; +}; + +static void etap_pre_exec(void *arg) +{ + struct etap_pre_exec_data *data = arg; + + dup2(data->control_remote, 1); + close(data->data_me); + close(data->control_me); +} + +static int etap_tramp(char *dev, char *gate, int control_me, + int control_remote, int data_me, int data_remote) +{ + struct etap_pre_exec_data pe_data; + int pid, err, n; + char version_buf[sizeof("nnnnn\0")]; + char data_fd_buf[sizeof("nnnnnn\0")]; + char gate_buf[sizeof("nnn.nnn.nnn.nnn\0")]; + char *setup_args[] = { "uml_net", version_buf, "ethertap", dev, + data_fd_buf, gate_buf, NULL }; + char *nosetup_args[] = { "uml_net", version_buf, "ethertap", + dev, data_fd_buf, NULL }; + char **args, c; + + sprintf(data_fd_buf, "%d", data_remote); + sprintf(version_buf, "%d", UML_NET_VERSION); + if (gate != NULL) { + strncpy(gate_buf, gate, 15); + args = setup_args; + } + else args = nosetup_args; + + err = 0; + pe_data.control_remote = control_remote; + pe_data.control_me = control_me; + pe_data.data_me = data_me; + pid = run_helper(etap_pre_exec, &pe_data, args); + + if (pid < 0) + err = pid; + close(data_remote); + close(control_remote); + CATCH_EINTR(n = read(control_me, &c, sizeof(c))); + if (n != sizeof(c)) { + err = -errno; + printk(UM_KERN_ERR "etap_tramp : read of status failed, " + "err = %d\n", -err); + return err; + } + if (c != 1) { + printk(UM_KERN_ERR "etap_tramp : uml_net failed\n"); + err = helper_wait(pid); + } + return err; +} + +static int etap_open(void *data) +{ + struct ethertap_data *pri = data; + char *output; + int data_fds[2], control_fds[2], err, output_len; + + err = tap_open_common(pri->dev, pri->gate_addr); + if (err) + return err; + + err = socketpair(AF_UNIX, SOCK_DGRAM, 0, data_fds); + if (err) { + err = -errno; + printk(UM_KERN_ERR "etap_open - data socketpair failed - " + "err = %d\n", errno); + return err; + } + + err = socketpair(AF_UNIX, SOCK_STREAM, 0, control_fds); + if (err) { + err = -errno; + printk(UM_KERN_ERR "etap_open - control socketpair failed - " + "err = %d\n", errno); + goto out_close_data; + } + + err = etap_tramp(pri->dev_name, pri->gate_addr, control_fds[0], + control_fds[1], data_fds[0], data_fds[1]); + output_len = UM_KERN_PAGE_SIZE; + output = uml_kmalloc(output_len, UM_GFP_KERNEL); + read_output(control_fds[0], output, output_len); + + if (output == NULL) + printk(UM_KERN_ERR "etap_open : failed to allocate output " + "buffer\n"); + else { + printk("%s", output); + kfree(output); + } + + if (err < 0) { + printk(UM_KERN_ERR "etap_tramp failed - err = %d\n", -err); + goto out_close_control; + } + + pri->data_fd = data_fds[0]; + pri->control_fd = control_fds[0]; + iter_addresses(pri->dev, etap_open_addr, &pri->control_fd); + return data_fds[0]; + +out_close_control: + close(control_fds[0]); + close(control_fds[1]); +out_close_data: + close(data_fds[0]); + close(data_fds[1]); + return err; +} + +static void etap_close(int fd, void *data) +{ + struct ethertap_data *pri = data; + + iter_addresses(pri->dev, etap_close_addr, &pri->control_fd); + close(fd); + + if (shutdown(pri->data_fd, SHUT_RDWR) < 0) + printk(UM_KERN_ERR "etap_close - shutdown data socket failed, " + "errno = %d\n", errno); + + if (shutdown(pri->control_fd, SHUT_RDWR) < 0) + printk(UM_KERN_ERR "etap_close - shutdown control socket " + "failed, errno = %d\n", errno); + + close(pri->data_fd); + pri->data_fd = -1; + close(pri->control_fd); + pri->control_fd = -1; +} + +static void etap_add_addr(unsigned char *addr, unsigned char *netmask, + void *data) +{ + struct ethertap_data *pri = data; + + tap_check_ips(pri->gate_addr, addr); + if (pri->control_fd == -1) + return; + etap_open_addr(addr, netmask, &pri->control_fd); +} + +static void etap_del_addr(unsigned char *addr, unsigned char *netmask, + void *data) +{ + struct ethertap_data *pri = data; + + if (pri->control_fd == -1) + return; + + etap_close_addr(addr, netmask, &pri->control_fd); +} + +const struct net_user_info ethertap_user_info = { + .init = etap_user_init, + .open = etap_open, + .close = etap_close, + .remove = NULL, + .add_address = etap_add_addr, + .delete_address = etap_del_addr, + .mtu = ETH_MAX_PACKET, + .max_packet = ETH_MAX_PACKET + ETH_HEADER_ETHERTAP, +}; -- cgit v1.2.3