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/char/ipmi/ipmi_powernv.c | 316 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 316 insertions(+) create mode 100644 drivers/char/ipmi/ipmi_powernv.c (limited to 'drivers/char/ipmi/ipmi_powernv.c') diff --git a/drivers/char/ipmi/ipmi_powernv.c b/drivers/char/ipmi/ipmi_powernv.c new file mode 100644 index 000000000..da22a8cbe --- /dev/null +++ b/drivers/char/ipmi/ipmi_powernv.c @@ -0,0 +1,316 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * PowerNV OPAL IPMI driver + * + * Copyright 2014 IBM Corp. + */ + +#define pr_fmt(fmt) "ipmi-powernv: " fmt + +#include +#include +#include +#include +#include +#include + +#include + + +struct ipmi_smi_powernv { + u64 interface_id; + struct ipmi_smi *intf; + unsigned int irq; + + /** + * We assume that there can only be one outstanding request, so + * keep the pending message in cur_msg. We protect this from concurrent + * updates through send & recv calls, (and consequently opal_msg, which + * is in-use when cur_msg is set) with msg_lock + */ + spinlock_t msg_lock; + struct ipmi_smi_msg *cur_msg; + struct opal_ipmi_msg *opal_msg; +}; + +static int ipmi_powernv_start_processing(void *send_info, struct ipmi_smi *intf) +{ + struct ipmi_smi_powernv *smi = send_info; + + smi->intf = intf; + return 0; +} + +static void send_error_reply(struct ipmi_smi_powernv *smi, + struct ipmi_smi_msg *msg, u8 completion_code) +{ + msg->rsp[0] = msg->data[0] | 0x4; + msg->rsp[1] = msg->data[1]; + msg->rsp[2] = completion_code; + msg->rsp_size = 3; + ipmi_smi_msg_received(smi->intf, msg); +} + +static void ipmi_powernv_send(void *send_info, struct ipmi_smi_msg *msg) +{ + struct ipmi_smi_powernv *smi = send_info; + struct opal_ipmi_msg *opal_msg; + unsigned long flags; + int comp, rc; + size_t size; + + /* ensure data_len will fit in the opal_ipmi_msg buffer... */ + if (msg->data_size > IPMI_MAX_MSG_LENGTH) { + comp = IPMI_REQ_LEN_EXCEEDED_ERR; + goto err; + } + + /* ... and that we at least have netfn and cmd bytes */ + if (msg->data_size < 2) { + comp = IPMI_REQ_LEN_INVALID_ERR; + goto err; + } + + spin_lock_irqsave(&smi->msg_lock, flags); + + if (smi->cur_msg) { + comp = IPMI_NODE_BUSY_ERR; + goto err_unlock; + } + + /* format our data for the OPAL API */ + opal_msg = smi->opal_msg; + opal_msg->version = OPAL_IPMI_MSG_FORMAT_VERSION_1; + opal_msg->netfn = msg->data[0]; + opal_msg->cmd = msg->data[1]; + if (msg->data_size > 2) + memcpy(opal_msg->data, msg->data + 2, msg->data_size - 2); + + /* data_size already includes the netfn and cmd bytes */ + size = sizeof(*opal_msg) + msg->data_size - 2; + + pr_devel("%s: opal_ipmi_send(0x%llx, %p, %ld)\n", __func__, + smi->interface_id, opal_msg, size); + rc = opal_ipmi_send(smi->interface_id, opal_msg, size); + pr_devel("%s: -> %d\n", __func__, rc); + + if (!rc) { + smi->cur_msg = msg; + spin_unlock_irqrestore(&smi->msg_lock, flags); + return; + } + + comp = IPMI_ERR_UNSPECIFIED; +err_unlock: + spin_unlock_irqrestore(&smi->msg_lock, flags); +err: + send_error_reply(smi, msg, comp); +} + +static int ipmi_powernv_recv(struct ipmi_smi_powernv *smi) +{ + struct opal_ipmi_msg *opal_msg; + struct ipmi_smi_msg *msg; + unsigned long flags; + uint64_t size; + int rc; + + pr_devel("%s: opal_ipmi_recv(%llx, msg, sz)\n", __func__, + smi->interface_id); + + spin_lock_irqsave(&smi->msg_lock, flags); + + if (!smi->cur_msg) { + spin_unlock_irqrestore(&smi->msg_lock, flags); + pr_warn("no current message?\n"); + return 0; + } + + msg = smi->cur_msg; + opal_msg = smi->opal_msg; + + size = cpu_to_be64(sizeof(*opal_msg) + IPMI_MAX_MSG_LENGTH); + + rc = opal_ipmi_recv(smi->interface_id, + opal_msg, + &size); + size = be64_to_cpu(size); + pr_devel("%s: -> %d (size %lld)\n", __func__, + rc, rc == 0 ? size : 0); + if (rc) { + /* If came via the poll, and response was not yet ready */ + if (rc == OPAL_EMPTY) { + spin_unlock_irqrestore(&smi->msg_lock, flags); + return 0; + } + + smi->cur_msg = NULL; + spin_unlock_irqrestore(&smi->msg_lock, flags); + send_error_reply(smi, msg, IPMI_ERR_UNSPECIFIED); + return 0; + } + + if (size < sizeof(*opal_msg)) { + spin_unlock_irqrestore(&smi->msg_lock, flags); + pr_warn("unexpected IPMI message size %lld\n", size); + return 0; + } + + if (opal_msg->version != OPAL_IPMI_MSG_FORMAT_VERSION_1) { + spin_unlock_irqrestore(&smi->msg_lock, flags); + pr_warn("unexpected IPMI message format (version %d)\n", + opal_msg->version); + return 0; + } + + msg->rsp[0] = opal_msg->netfn; + msg->rsp[1] = opal_msg->cmd; + if (size > sizeof(*opal_msg)) + memcpy(&msg->rsp[2], opal_msg->data, size - sizeof(*opal_msg)); + msg->rsp_size = 2 + size - sizeof(*opal_msg); + + smi->cur_msg = NULL; + spin_unlock_irqrestore(&smi->msg_lock, flags); + ipmi_smi_msg_received(smi->intf, msg); + return 0; +} + +static void ipmi_powernv_request_events(void *send_info) +{ +} + +static void ipmi_powernv_set_run_to_completion(void *send_info, + bool run_to_completion) +{ +} + +static void ipmi_powernv_poll(void *send_info) +{ + struct ipmi_smi_powernv *smi = send_info; + + ipmi_powernv_recv(smi); +} + +static const struct ipmi_smi_handlers ipmi_powernv_smi_handlers = { + .owner = THIS_MODULE, + .start_processing = ipmi_powernv_start_processing, + .sender = ipmi_powernv_send, + .request_events = ipmi_powernv_request_events, + .set_run_to_completion = ipmi_powernv_set_run_to_completion, + .poll = ipmi_powernv_poll, +}; + +static irqreturn_t ipmi_opal_event(int irq, void *data) +{ + struct ipmi_smi_powernv *smi = data; + + ipmi_powernv_recv(smi); + return IRQ_HANDLED; +} + +static int ipmi_powernv_probe(struct platform_device *pdev) +{ + struct ipmi_smi_powernv *ipmi; + struct device *dev; + u32 prop; + int rc; + + if (!pdev || !pdev->dev.of_node) + return -ENODEV; + + dev = &pdev->dev; + + ipmi = devm_kzalloc(dev, sizeof(*ipmi), GFP_KERNEL); + if (!ipmi) + return -ENOMEM; + + spin_lock_init(&ipmi->msg_lock); + + rc = of_property_read_u32(dev->of_node, "ibm,ipmi-interface-id", + &prop); + if (rc) { + dev_warn(dev, "No interface ID property\n"); + goto err_free; + } + ipmi->interface_id = prop; + + rc = of_property_read_u32(dev->of_node, "interrupts", &prop); + if (rc) { + dev_warn(dev, "No interrupts property\n"); + goto err_free; + } + + ipmi->irq = irq_of_parse_and_map(dev->of_node, 0); + if (!ipmi->irq) { + dev_info(dev, "Unable to map irq from device tree\n"); + ipmi->irq = opal_event_request(prop); + } + + rc = request_irq(ipmi->irq, ipmi_opal_event, IRQ_TYPE_LEVEL_HIGH, + "opal-ipmi", ipmi); + if (rc) { + dev_warn(dev, "Unable to request irq\n"); + goto err_dispose; + } + + ipmi->opal_msg = devm_kmalloc(dev, + sizeof(*ipmi->opal_msg) + IPMI_MAX_MSG_LENGTH, + GFP_KERNEL); + if (!ipmi->opal_msg) { + rc = -ENOMEM; + goto err_unregister; + } + + rc = ipmi_register_smi(&ipmi_powernv_smi_handlers, ipmi, dev, 0); + if (rc) { + dev_warn(dev, "IPMI SMI registration failed (%d)\n", rc); + goto err_free_msg; + } + + dev_set_drvdata(dev, ipmi); + return 0; + +err_free_msg: + devm_kfree(dev, ipmi->opal_msg); +err_unregister: + free_irq(ipmi->irq, ipmi); +err_dispose: + irq_dispose_mapping(ipmi->irq); +err_free: + devm_kfree(dev, ipmi); + return rc; +} + +static int ipmi_powernv_remove(struct platform_device *pdev) +{ + struct ipmi_smi_powernv *smi = dev_get_drvdata(&pdev->dev); + + ipmi_unregister_smi(smi->intf); + free_irq(smi->irq, smi); + irq_dispose_mapping(smi->irq); + + return 0; +} + +static const struct of_device_id ipmi_powernv_match[] = { + { .compatible = "ibm,opal-ipmi" }, + { }, +}; + + +static struct platform_driver powernv_ipmi_driver = { + .driver = { + .name = "ipmi-powernv", + .of_match_table = ipmi_powernv_match, + }, + .probe = ipmi_powernv_probe, + .remove = ipmi_powernv_remove, +}; + + +module_platform_driver(powernv_ipmi_driver); + +MODULE_DEVICE_TABLE(of, ipmi_powernv_match); +MODULE_DESCRIPTION("powernv IPMI driver"); +MODULE_AUTHOR("Jeremy Kerr "); +MODULE_LICENSE("GPL"); -- cgit v1.2.3