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/connector/cn_proc.c | 403 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 403 insertions(+) create mode 100644 drivers/connector/cn_proc.c (limited to 'drivers/connector/cn_proc.c') diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c new file mode 100644 index 000000000..ccac1c453 --- /dev/null +++ b/drivers/connector/cn_proc.c @@ -0,0 +1,403 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * cn_proc.c - process events connector + * + * Copyright (C) Matt Helsley, IBM Corp. 2005 + * Based on cn_fork.c by Guillaume Thouvenin + * Original copyright notice follows: + * Copyright (C) 2005 BULL SA. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +/* + * Size of a cn_msg followed by a proc_event structure. Since the + * sizeof struct cn_msg is a multiple of 4 bytes, but not 8 bytes, we + * add one 4-byte word to the size here, and then start the actual + * cn_msg structure 4 bytes into the stack buffer. The result is that + * the immediately following proc_event structure is aligned to 8 bytes. + */ +#define CN_PROC_MSG_SIZE (sizeof(struct cn_msg) + sizeof(struct proc_event) + 4) + +/* See comment above; we test our assumption about sizeof struct cn_msg here. */ +static inline struct cn_msg *buffer_to_cn_msg(__u8 *buffer) +{ + BUILD_BUG_ON(sizeof(struct cn_msg) != 20); + return (struct cn_msg *)(buffer + 4); +} + +static atomic_t proc_event_num_listeners = ATOMIC_INIT(0); +static struct cb_id cn_proc_event_id = { CN_IDX_PROC, CN_VAL_PROC }; + +/* local_event.count is used as the sequence number of the netlink message */ +struct local_event { + local_lock_t lock; + __u32 count; +}; +static DEFINE_PER_CPU(struct local_event, local_event) = { + .lock = INIT_LOCAL_LOCK(lock), +}; + +static inline void send_msg(struct cn_msg *msg) +{ + local_lock(&local_event.lock); + + msg->seq = __this_cpu_inc_return(local_event.count) - 1; + ((struct proc_event *)msg->data)->cpu = smp_processor_id(); + + /* + * local_lock() disables preemption during send to ensure the messages + * are ordered according to their sequence numbers. + * + * If cn_netlink_send() fails, the data is not sent. + */ + cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_NOWAIT); + + local_unlock(&local_event.lock); +} + +void proc_fork_connector(struct task_struct *task) +{ + struct cn_msg *msg; + struct proc_event *ev; + __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); + struct task_struct *parent; + + if (atomic_read(&proc_event_num_listeners) < 1) + return; + + msg = buffer_to_cn_msg(buffer); + ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); + ev->timestamp_ns = ktime_get_ns(); + ev->what = PROC_EVENT_FORK; + rcu_read_lock(); + parent = rcu_dereference(task->real_parent); + ev->event_data.fork.parent_pid = parent->pid; + ev->event_data.fork.parent_tgid = parent->tgid; + rcu_read_unlock(); + ev->event_data.fork.child_pid = task->pid; + ev->event_data.fork.child_tgid = task->tgid; + + memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); + msg->ack = 0; /* not used */ + msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ + send_msg(msg); +} + +void proc_exec_connector(struct task_struct *task) +{ + struct cn_msg *msg; + struct proc_event *ev; + __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); + + if (atomic_read(&proc_event_num_listeners) < 1) + return; + + msg = buffer_to_cn_msg(buffer); + ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); + ev->timestamp_ns = ktime_get_ns(); + ev->what = PROC_EVENT_EXEC; + ev->event_data.exec.process_pid = task->pid; + ev->event_data.exec.process_tgid = task->tgid; + + memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); + msg->ack = 0; /* not used */ + msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ + send_msg(msg); +} + +void proc_id_connector(struct task_struct *task, int which_id) +{ + struct cn_msg *msg; + struct proc_event *ev; + __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); + const struct cred *cred; + + if (atomic_read(&proc_event_num_listeners) < 1) + return; + + msg = buffer_to_cn_msg(buffer); + ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); + ev->what = which_id; + ev->event_data.id.process_pid = task->pid; + ev->event_data.id.process_tgid = task->tgid; + rcu_read_lock(); + cred = __task_cred(task); + if (which_id == PROC_EVENT_UID) { + ev->event_data.id.r.ruid = from_kuid_munged(&init_user_ns, cred->uid); + ev->event_data.id.e.euid = from_kuid_munged(&init_user_ns, cred->euid); + } else if (which_id == PROC_EVENT_GID) { + ev->event_data.id.r.rgid = from_kgid_munged(&init_user_ns, cred->gid); + ev->event_data.id.e.egid = from_kgid_munged(&init_user_ns, cred->egid); + } else { + rcu_read_unlock(); + return; + } + rcu_read_unlock(); + ev->timestamp_ns = ktime_get_ns(); + + memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); + msg->ack = 0; /* not used */ + msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ + send_msg(msg); +} + +void proc_sid_connector(struct task_struct *task) +{ + struct cn_msg *msg; + struct proc_event *ev; + __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); + + if (atomic_read(&proc_event_num_listeners) < 1) + return; + + msg = buffer_to_cn_msg(buffer); + ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); + ev->timestamp_ns = ktime_get_ns(); + ev->what = PROC_EVENT_SID; + ev->event_data.sid.process_pid = task->pid; + ev->event_data.sid.process_tgid = task->tgid; + + memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); + msg->ack = 0; /* not used */ + msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ + send_msg(msg); +} + +void proc_ptrace_connector(struct task_struct *task, int ptrace_id) +{ + struct cn_msg *msg; + struct proc_event *ev; + __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); + + if (atomic_read(&proc_event_num_listeners) < 1) + return; + + msg = buffer_to_cn_msg(buffer); + ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); + ev->timestamp_ns = ktime_get_ns(); + ev->what = PROC_EVENT_PTRACE; + ev->event_data.ptrace.process_pid = task->pid; + ev->event_data.ptrace.process_tgid = task->tgid; + if (ptrace_id == PTRACE_ATTACH) { + ev->event_data.ptrace.tracer_pid = current->pid; + ev->event_data.ptrace.tracer_tgid = current->tgid; + } else if (ptrace_id == PTRACE_DETACH) { + ev->event_data.ptrace.tracer_pid = 0; + ev->event_data.ptrace.tracer_tgid = 0; + } else + return; + + memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); + msg->ack = 0; /* not used */ + msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ + send_msg(msg); +} + +void proc_comm_connector(struct task_struct *task) +{ + struct cn_msg *msg; + struct proc_event *ev; + __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); + + if (atomic_read(&proc_event_num_listeners) < 1) + return; + + msg = buffer_to_cn_msg(buffer); + ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); + ev->timestamp_ns = ktime_get_ns(); + ev->what = PROC_EVENT_COMM; + ev->event_data.comm.process_pid = task->pid; + ev->event_data.comm.process_tgid = task->tgid; + get_task_comm(ev->event_data.comm.comm, task); + + memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); + msg->ack = 0; /* not used */ + msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ + send_msg(msg); +} + +void proc_coredump_connector(struct task_struct *task) +{ + struct cn_msg *msg; + struct proc_event *ev; + struct task_struct *parent; + __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); + + if (atomic_read(&proc_event_num_listeners) < 1) + return; + + msg = buffer_to_cn_msg(buffer); + ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); + ev->timestamp_ns = ktime_get_ns(); + ev->what = PROC_EVENT_COREDUMP; + ev->event_data.coredump.process_pid = task->pid; + ev->event_data.coredump.process_tgid = task->tgid; + + rcu_read_lock(); + if (pid_alive(task)) { + parent = rcu_dereference(task->real_parent); + ev->event_data.coredump.parent_pid = parent->pid; + ev->event_data.coredump.parent_tgid = parent->tgid; + } + rcu_read_unlock(); + + memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); + msg->ack = 0; /* not used */ + msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ + send_msg(msg); +} + +void proc_exit_connector(struct task_struct *task) +{ + struct cn_msg *msg; + struct proc_event *ev; + struct task_struct *parent; + __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); + + if (atomic_read(&proc_event_num_listeners) < 1) + return; + + msg = buffer_to_cn_msg(buffer); + ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); + ev->timestamp_ns = ktime_get_ns(); + ev->what = PROC_EVENT_EXIT; + ev->event_data.exit.process_pid = task->pid; + ev->event_data.exit.process_tgid = task->tgid; + ev->event_data.exit.exit_code = task->exit_code; + ev->event_data.exit.exit_signal = task->exit_signal; + + rcu_read_lock(); + if (pid_alive(task)) { + parent = rcu_dereference(task->real_parent); + ev->event_data.exit.parent_pid = parent->pid; + ev->event_data.exit.parent_tgid = parent->tgid; + } + rcu_read_unlock(); + + memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); + msg->ack = 0; /* not used */ + msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ + send_msg(msg); +} + +/* + * Send an acknowledgement message to userspace + * + * Use 0 for success, EFOO otherwise. + * Note: this is the negative of conventional kernel error + * values because it's not being returned via syscall return + * mechanisms. + */ +static void cn_proc_ack(int err, int rcvd_seq, int rcvd_ack) +{ + struct cn_msg *msg; + struct proc_event *ev; + __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); + + if (atomic_read(&proc_event_num_listeners) < 1) + return; + + msg = buffer_to_cn_msg(buffer); + ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); + msg->seq = rcvd_seq; + ev->timestamp_ns = ktime_get_ns(); + ev->cpu = -1; + ev->what = PROC_EVENT_NONE; + ev->event_data.ack.err = err; + memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); + msg->ack = rcvd_ack + 1; + msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ + send_msg(msg); +} + +/** + * cn_proc_mcast_ctl + * @data: message sent from userspace via the connector + */ +static void cn_proc_mcast_ctl(struct cn_msg *msg, + struct netlink_skb_parms *nsp) +{ + enum proc_cn_mcast_op *mc_op = NULL; + int err = 0; + + if (msg->len != sizeof(*mc_op)) + return; + + /* + * Events are reported with respect to the initial pid + * and user namespaces so ignore requestors from + * other namespaces. + */ + if ((current_user_ns() != &init_user_ns) || + !task_is_in_init_pid_ns(current)) + return; + + /* Can only change if privileged. */ + if (!__netlink_ns_capable(nsp, &init_user_ns, CAP_NET_ADMIN)) { + err = EPERM; + goto out; + } + + mc_op = (enum proc_cn_mcast_op *)msg->data; + switch (*mc_op) { + case PROC_CN_MCAST_LISTEN: + atomic_inc(&proc_event_num_listeners); + break; + case PROC_CN_MCAST_IGNORE: + atomic_dec(&proc_event_num_listeners); + break; + default: + err = EINVAL; + break; + } + +out: + cn_proc_ack(err, msg->seq, msg->ack); +} + +/* + * cn_proc_init - initialization entry point + * + * Adds the connector callback to the connector driver. + */ +static int __init cn_proc_init(void) +{ + int err = cn_add_callback(&cn_proc_event_id, + "cn_proc", + &cn_proc_mcast_ctl); + if (err) { + pr_warn("cn_proc failed to register\n"); + return err; + } + return 0; +} +device_initcall(cn_proc_init); -- cgit v1.2.3