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/powerpc/sysdev/ehv_pic.c | 299 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 299 insertions(+) create mode 100644 arch/powerpc/sysdev/ehv_pic.c (limited to 'arch/powerpc/sysdev/ehv_pic.c') diff --git a/arch/powerpc/sysdev/ehv_pic.c b/arch/powerpc/sysdev/ehv_pic.c new file mode 100644 index 000000000..00705258e --- /dev/null +++ b/arch/powerpc/sysdev/ehv_pic.c @@ -0,0 +1,299 @@ +/* + * Driver for ePAPR Embedded Hypervisor PIC + * + * Copyright 2008-2011 Freescale Semiconductor, Inc. + * + * Author: Ashish Kalra + * + * This file is licensed under the terms of the GNU General Public License + * version 2. This program is licensed "as is" without any warranty of any + * kind, whether express or implied. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include + +static struct ehv_pic *global_ehv_pic; +static DEFINE_SPINLOCK(ehv_pic_lock); + +static u32 hwirq_intspec[NR_EHV_PIC_INTS]; +static u32 __iomem *mpic_percpu_base_vaddr; + +#define IRQ_TYPE_MPIC_DIRECT 4 +#define MPIC_EOI 0x00B0 + +/* + * Linux descriptor level callbacks + */ + +void ehv_pic_unmask_irq(struct irq_data *d) +{ + unsigned int src = virq_to_hw(d->irq); + + ev_int_set_mask(src, 0); +} + +void ehv_pic_mask_irq(struct irq_data *d) +{ + unsigned int src = virq_to_hw(d->irq); + + ev_int_set_mask(src, 1); +} + +void ehv_pic_end_irq(struct irq_data *d) +{ + unsigned int src = virq_to_hw(d->irq); + + ev_int_eoi(src); +} + +void ehv_pic_direct_end_irq(struct irq_data *d) +{ + out_be32(mpic_percpu_base_vaddr + MPIC_EOI / 4, 0); +} + +int ehv_pic_set_affinity(struct irq_data *d, const struct cpumask *dest, + bool force) +{ + unsigned int src = virq_to_hw(d->irq); + unsigned int config, prio, cpu_dest; + int cpuid = irq_choose_cpu(dest); + unsigned long flags; + + spin_lock_irqsave(&ehv_pic_lock, flags); + ev_int_get_config(src, &config, &prio, &cpu_dest); + ev_int_set_config(src, config, prio, cpuid); + spin_unlock_irqrestore(&ehv_pic_lock, flags); + + return IRQ_SET_MASK_OK; +} + +static unsigned int ehv_pic_type_to_vecpri(unsigned int type) +{ + /* Now convert sense value */ + + switch (type & IRQ_TYPE_SENSE_MASK) { + case IRQ_TYPE_EDGE_RISING: + return EHV_PIC_INFO(VECPRI_SENSE_EDGE) | + EHV_PIC_INFO(VECPRI_POLARITY_POSITIVE); + + case IRQ_TYPE_EDGE_FALLING: + case IRQ_TYPE_EDGE_BOTH: + return EHV_PIC_INFO(VECPRI_SENSE_EDGE) | + EHV_PIC_INFO(VECPRI_POLARITY_NEGATIVE); + + case IRQ_TYPE_LEVEL_HIGH: + return EHV_PIC_INFO(VECPRI_SENSE_LEVEL) | + EHV_PIC_INFO(VECPRI_POLARITY_POSITIVE); + + case IRQ_TYPE_LEVEL_LOW: + default: + return EHV_PIC_INFO(VECPRI_SENSE_LEVEL) | + EHV_PIC_INFO(VECPRI_POLARITY_NEGATIVE); + } +} + +int ehv_pic_set_irq_type(struct irq_data *d, unsigned int flow_type) +{ + unsigned int src = virq_to_hw(d->irq); + unsigned int vecpri, vold, vnew, prio, cpu_dest; + unsigned long flags; + + if (flow_type == IRQ_TYPE_NONE) + flow_type = IRQ_TYPE_LEVEL_LOW; + + irqd_set_trigger_type(d, flow_type); + + vecpri = ehv_pic_type_to_vecpri(flow_type); + + spin_lock_irqsave(&ehv_pic_lock, flags); + ev_int_get_config(src, &vold, &prio, &cpu_dest); + vnew = vold & ~(EHV_PIC_INFO(VECPRI_POLARITY_MASK) | + EHV_PIC_INFO(VECPRI_SENSE_MASK)); + vnew |= vecpri; + + /* + * TODO : Add specific interface call for platform to set + * individual interrupt priorities. + * platform currently using static/default priority for all ints + */ + + prio = 8; + + ev_int_set_config(src, vecpri, prio, cpu_dest); + + spin_unlock_irqrestore(&ehv_pic_lock, flags); + return IRQ_SET_MASK_OK_NOCOPY; +} + +static struct irq_chip ehv_pic_irq_chip = { + .irq_mask = ehv_pic_mask_irq, + .irq_unmask = ehv_pic_unmask_irq, + .irq_eoi = ehv_pic_end_irq, + .irq_set_type = ehv_pic_set_irq_type, +}; + +static struct irq_chip ehv_pic_direct_eoi_irq_chip = { + .irq_mask = ehv_pic_mask_irq, + .irq_unmask = ehv_pic_unmask_irq, + .irq_eoi = ehv_pic_direct_end_irq, + .irq_set_type = ehv_pic_set_irq_type, +}; + +/* Return an interrupt vector or 0 if no interrupt is pending. */ +unsigned int ehv_pic_get_irq(void) +{ + int irq; + + BUG_ON(global_ehv_pic == NULL); + + if (global_ehv_pic->coreint_flag) + irq = mfspr(SPRN_EPR); /* if core int mode */ + else + ev_int_iack(0, &irq); /* legacy mode */ + + if (irq == 0xFFFF) /* 0xFFFF --> no irq is pending */ + return 0; + + /* + * this will also setup revmap[] in the slow path for the first + * time, next calls will always use fast path by indexing revmap + */ + return irq_linear_revmap(global_ehv_pic->irqhost, irq); +} + +static int ehv_pic_host_match(struct irq_domain *h, struct device_node *node, + enum irq_domain_bus_token bus_token) +{ + /* Exact match, unless ehv_pic node is NULL */ + struct device_node *of_node = irq_domain_get_of_node(h); + return of_node == NULL || of_node == node; +} + +static int ehv_pic_host_map(struct irq_domain *h, unsigned int virq, + irq_hw_number_t hw) +{ + struct ehv_pic *ehv_pic = h->host_data; + struct irq_chip *chip; + + /* Default chip */ + chip = &ehv_pic->hc_irq; + + if (mpic_percpu_base_vaddr) + if (hwirq_intspec[hw] & IRQ_TYPE_MPIC_DIRECT) + chip = &ehv_pic_direct_eoi_irq_chip; + + irq_set_chip_data(virq, chip); + /* + * using handle_fasteoi_irq as our irq handler, this will + * only call the eoi callback and suitable for the MPIC + * controller which set ISR/IPR automatically and clear the + * highest priority active interrupt in ISR/IPR when we do + * a specific eoi + */ + irq_set_chip_and_handler(virq, chip, handle_fasteoi_irq); + + /* Set default irq type */ + irq_set_irq_type(virq, IRQ_TYPE_NONE); + + return 0; +} + +static int ehv_pic_host_xlate(struct irq_domain *h, struct device_node *ct, + const u32 *intspec, unsigned int intsize, + irq_hw_number_t *out_hwirq, unsigned int *out_flags) + +{ + /* + * interrupt sense values coming from the guest device tree + * interrupt specifiers can have four possible sense and + * level encoding information and they need to + * be translated between firmware type & linux type. + */ + + static unsigned char map_of_senses_to_linux_irqtype[4] = { + IRQ_TYPE_EDGE_FALLING, + IRQ_TYPE_EDGE_RISING, + IRQ_TYPE_LEVEL_LOW, + IRQ_TYPE_LEVEL_HIGH, + }; + + *out_hwirq = intspec[0]; + if (intsize > 1) { + hwirq_intspec[intspec[0]] = intspec[1]; + *out_flags = map_of_senses_to_linux_irqtype[intspec[1] & + ~IRQ_TYPE_MPIC_DIRECT]; + } else { + *out_flags = IRQ_TYPE_NONE; + } + + return 0; +} + +static const struct irq_domain_ops ehv_pic_host_ops = { + .match = ehv_pic_host_match, + .map = ehv_pic_host_map, + .xlate = ehv_pic_host_xlate, +}; + +void __init ehv_pic_init(void) +{ + struct device_node *np, *np2; + struct ehv_pic *ehv_pic; + int coreint_flag = 1; + + np = of_find_compatible_node(NULL, NULL, "epapr,hv-pic"); + if (!np) { + pr_err("ehv_pic_init: could not find epapr,hv-pic node\n"); + return; + } + + if (!of_find_property(np, "has-external-proxy", NULL)) + coreint_flag = 0; + + ehv_pic = kzalloc(sizeof(struct ehv_pic), GFP_KERNEL); + if (!ehv_pic) { + of_node_put(np); + return; + } + + ehv_pic->irqhost = irq_domain_add_linear(np, NR_EHV_PIC_INTS, + &ehv_pic_host_ops, ehv_pic); + if (!ehv_pic->irqhost) { + of_node_put(np); + kfree(ehv_pic); + return; + } + + np2 = of_find_compatible_node(NULL, NULL, "fsl,hv-mpic-per-cpu"); + if (np2) { + mpic_percpu_base_vaddr = of_iomap(np2, 0); + if (!mpic_percpu_base_vaddr) + pr_err("ehv_pic_init: of_iomap failed\n"); + + of_node_put(np2); + } + + ehv_pic->hc_irq = ehv_pic_irq_chip; + ehv_pic->hc_irq.irq_set_affinity = ehv_pic_set_affinity; + ehv_pic->coreint_flag = coreint_flag; + + global_ehv_pic = ehv_pic; + irq_set_default_host(global_ehv_pic->irqhost); +} -- cgit v1.2.3