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/xen/xenbus/xenbus_comms.c | 484 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 484 insertions(+) create mode 100644 drivers/xen/xenbus/xenbus_comms.c (limited to 'drivers/xen/xenbus/xenbus_comms.c') diff --git a/drivers/xen/xenbus/xenbus_comms.c b/drivers/xen/xenbus/xenbus_comms.c new file mode 100644 index 000000000..e5fda0256 --- /dev/null +++ b/drivers/xen/xenbus/xenbus_comms.c @@ -0,0 +1,484 @@ +/****************************************************************************** + * xenbus_comms.c + * + * Low level code to talks to Xen Store: ringbuffer and event channel. + * + * Copyright (C) 2005 Rusty Russell, IBM Corporation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation; or, when distributed + * separately from the Linux kernel or incorporated into other + * software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "xenbus.h" + +/* A list of replies. Currently only one will ever be outstanding. */ +LIST_HEAD(xs_reply_list); + +/* A list of write requests. */ +LIST_HEAD(xb_write_list); +DECLARE_WAIT_QUEUE_HEAD(xb_waitq); +DEFINE_MUTEX(xb_write_mutex); + +/* Protect xenbus reader thread against save/restore. */ +DEFINE_MUTEX(xs_response_mutex); + +static int xenbus_irq; +static struct task_struct *xenbus_task; + +static irqreturn_t wake_waiting(int irq, void *unused) +{ + wake_up(&xb_waitq); + return IRQ_HANDLED; +} + +static int check_indexes(XENSTORE_RING_IDX cons, XENSTORE_RING_IDX prod) +{ + return ((prod - cons) <= XENSTORE_RING_SIZE); +} + +static void *get_output_chunk(XENSTORE_RING_IDX cons, + XENSTORE_RING_IDX prod, + char *buf, uint32_t *len) +{ + *len = XENSTORE_RING_SIZE - MASK_XENSTORE_IDX(prod); + if ((XENSTORE_RING_SIZE - (prod - cons)) < *len) + *len = XENSTORE_RING_SIZE - (prod - cons); + return buf + MASK_XENSTORE_IDX(prod); +} + +static const void *get_input_chunk(XENSTORE_RING_IDX cons, + XENSTORE_RING_IDX prod, + const char *buf, uint32_t *len) +{ + *len = XENSTORE_RING_SIZE - MASK_XENSTORE_IDX(cons); + if ((prod - cons) < *len) + *len = prod - cons; + return buf + MASK_XENSTORE_IDX(cons); +} + +static int xb_data_to_write(void) +{ + struct xenstore_domain_interface *intf = xen_store_interface; + + return (intf->req_prod - intf->req_cons) != XENSTORE_RING_SIZE && + !list_empty(&xb_write_list); +} + +/** + * xb_write - low level write + * @data: buffer to send + * @len: length of buffer + * + * Returns number of bytes written or -err. + */ +static int xb_write(const void *data, unsigned int len) +{ + struct xenstore_domain_interface *intf = xen_store_interface; + XENSTORE_RING_IDX cons, prod; + unsigned int bytes = 0; + + while (len != 0) { + void *dst; + unsigned int avail; + + /* Read indexes, then verify. */ + cons = intf->req_cons; + prod = intf->req_prod; + if (!check_indexes(cons, prod)) { + intf->req_cons = intf->req_prod = 0; + return -EIO; + } + if (!xb_data_to_write()) + return bytes; + + /* Must write data /after/ reading the consumer index. */ + virt_mb(); + + dst = get_output_chunk(cons, prod, intf->req, &avail); + if (avail == 0) + continue; + if (avail > len) + avail = len; + + memcpy(dst, data, avail); + data += avail; + len -= avail; + bytes += avail; + + /* Other side must not see new producer until data is there. */ + virt_wmb(); + intf->req_prod += avail; + + /* Implies mb(): other side will see the updated producer. */ + if (prod <= intf->req_cons) + notify_remote_via_evtchn(xen_store_evtchn); + } + + return bytes; +} + +static int xb_data_to_read(void) +{ + struct xenstore_domain_interface *intf = xen_store_interface; + return (intf->rsp_cons != intf->rsp_prod); +} + +static int xb_read(void *data, unsigned int len) +{ + struct xenstore_domain_interface *intf = xen_store_interface; + XENSTORE_RING_IDX cons, prod; + unsigned int bytes = 0; + + while (len != 0) { + unsigned int avail; + const char *src; + + /* Read indexes, then verify. */ + cons = intf->rsp_cons; + prod = intf->rsp_prod; + if (cons == prod) + return bytes; + + if (!check_indexes(cons, prod)) { + intf->rsp_cons = intf->rsp_prod = 0; + return -EIO; + } + + src = get_input_chunk(cons, prod, intf->rsp, &avail); + if (avail == 0) + continue; + if (avail > len) + avail = len; + + /* Must read data /after/ reading the producer index. */ + virt_rmb(); + + memcpy(data, src, avail); + data += avail; + len -= avail; + bytes += avail; + + /* Other side must not see free space until we've copied out */ + virt_mb(); + intf->rsp_cons += avail; + + /* Implies mb(): other side will see the updated consumer. */ + if (intf->rsp_prod - cons >= XENSTORE_RING_SIZE) + notify_remote_via_evtchn(xen_store_evtchn); + } + + return bytes; +} + +static int process_msg(void) +{ + static struct { + struct xsd_sockmsg msg; + char *body; + union { + void *alloc; + struct xs_watch_event *watch; + }; + bool in_msg; + bool in_hdr; + unsigned int read; + } state; + struct xb_req_data *req; + int err; + unsigned int len; + + if (!state.in_msg) { + state.in_msg = true; + state.in_hdr = true; + state.read = 0; + + /* + * We must disallow save/restore while reading a message. + * A partial read across s/r leaves us out of sync with + * xenstored. + * xs_response_mutex is locked as long as we are processing one + * message. state.in_msg will be true as long as we are holding + * the lock here. + */ + mutex_lock(&xs_response_mutex); + + if (!xb_data_to_read()) { + /* We raced with save/restore: pending data 'gone'. */ + mutex_unlock(&xs_response_mutex); + state.in_msg = false; + return 0; + } + } + + if (state.in_hdr) { + if (state.read != sizeof(state.msg)) { + err = xb_read((void *)&state.msg + state.read, + sizeof(state.msg) - state.read); + if (err < 0) + goto out; + state.read += err; + if (state.read != sizeof(state.msg)) + return 0; + if (state.msg.len > XENSTORE_PAYLOAD_MAX) { + err = -EINVAL; + goto out; + } + } + + len = state.msg.len + 1; + if (state.msg.type == XS_WATCH_EVENT) + len += sizeof(*state.watch); + + state.alloc = kmalloc(len, GFP_NOIO | __GFP_HIGH); + if (!state.alloc) + return -ENOMEM; + + if (state.msg.type == XS_WATCH_EVENT) + state.body = state.watch->body; + else + state.body = state.alloc; + state.in_hdr = false; + state.read = 0; + } + + err = xb_read(state.body + state.read, state.msg.len - state.read); + if (err < 0) + goto out; + + state.read += err; + if (state.read != state.msg.len) + return 0; + + state.body[state.msg.len] = '\0'; + + if (state.msg.type == XS_WATCH_EVENT) { + state.watch->len = state.msg.len; + err = xs_watch_msg(state.watch); + } else { + err = -ENOENT; + mutex_lock(&xb_write_mutex); + list_for_each_entry(req, &xs_reply_list, list) { + if (req->msg.req_id == state.msg.req_id) { + list_del(&req->list); + err = 0; + break; + } + } + mutex_unlock(&xb_write_mutex); + if (err) + goto out; + + if (req->state == xb_req_state_wait_reply) { + req->msg.req_id = req->caller_req_id; + req->msg.type = state.msg.type; + req->msg.len = state.msg.len; + req->body = state.body; + /* write body, then update state */ + virt_wmb(); + req->state = xb_req_state_got_reply; + req->cb(req); + } else + kfree(req); + } + + mutex_unlock(&xs_response_mutex); + + state.in_msg = false; + state.alloc = NULL; + return err; + + out: + mutex_unlock(&xs_response_mutex); + state.in_msg = false; + kfree(state.alloc); + state.alloc = NULL; + return err; +} + +static int process_writes(void) +{ + static struct { + struct xb_req_data *req; + int idx; + unsigned int written; + } state; + void *base; + unsigned int len; + int err = 0; + + if (!xb_data_to_write()) + return 0; + + mutex_lock(&xb_write_mutex); + + if (!state.req) { + state.req = list_first_entry(&xb_write_list, + struct xb_req_data, list); + state.idx = -1; + state.written = 0; + } + + if (state.req->state == xb_req_state_aborted) + goto out_err; + + while (state.idx < state.req->num_vecs) { + if (state.idx < 0) { + base = &state.req->msg; + len = sizeof(state.req->msg); + } else { + base = state.req->vec[state.idx].iov_base; + len = state.req->vec[state.idx].iov_len; + } + err = xb_write(base + state.written, len - state.written); + if (err < 0) + goto out_err; + state.written += err; + if (state.written != len) + goto out; + + state.idx++; + state.written = 0; + } + + list_del(&state.req->list); + state.req->state = xb_req_state_wait_reply; + list_add_tail(&state.req->list, &xs_reply_list); + state.req = NULL; + + out: + mutex_unlock(&xb_write_mutex); + + return 0; + + out_err: + state.req->msg.type = XS_ERROR; + state.req->err = err; + list_del(&state.req->list); + if (state.req->state == xb_req_state_aborted) + kfree(state.req); + else { + /* write err, then update state */ + virt_wmb(); + state.req->state = xb_req_state_got_reply; + wake_up(&state.req->wq); + } + + mutex_unlock(&xb_write_mutex); + + state.req = NULL; + + return err; +} + +static int xb_thread_work(void) +{ + return xb_data_to_read() || xb_data_to_write(); +} + +static int xenbus_thread(void *unused) +{ + int err; + + while (!kthread_should_stop()) { + if (wait_event_interruptible(xb_waitq, xb_thread_work())) + continue; + + err = process_msg(); + if (err == -ENOMEM) + schedule(); + else if (err) + pr_warn_ratelimited("error %d while reading message\n", + err); + + err = process_writes(); + if (err) + pr_warn_ratelimited("error %d while writing message\n", + err); + } + + xenbus_task = NULL; + return 0; +} + +/** + * xb_init_comms - Set up interrupt handler off store event channel. + */ +int xb_init_comms(void) +{ + struct xenstore_domain_interface *intf = xen_store_interface; + + if (intf->req_prod != intf->req_cons) + pr_err("request ring is not quiescent (%08x:%08x)!\n", + intf->req_cons, intf->req_prod); + + if (intf->rsp_prod != intf->rsp_cons) { + pr_warn("response ring is not quiescent (%08x:%08x): fixing up\n", + intf->rsp_cons, intf->rsp_prod); + /* breaks kdump */ + if (!reset_devices) + intf->rsp_cons = intf->rsp_prod; + } + + if (xenbus_irq) { + /* Already have an irq; assume we're resuming */ + rebind_evtchn_irq(xen_store_evtchn, xenbus_irq); + } else { + int err; + + err = bind_evtchn_to_irqhandler(xen_store_evtchn, wake_waiting, + 0, "xenbus", &xb_waitq); + if (err < 0) { + pr_err("request irq failed %i\n", err); + return err; + } + + xenbus_irq = err; + + if (!xenbus_task) { + xenbus_task = kthread_run(xenbus_thread, NULL, + "xenbus"); + if (IS_ERR(xenbus_task)) + return PTR_ERR(xenbus_task); + } + } + + return 0; +} + +void xb_deinit_comms(void) +{ + unbind_from_irqhandler(xenbus_irq, &xb_waitq); + xenbus_irq = 0; +} -- cgit v1.2.3