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/irqchip/irq-gic-v3-mbi.c | 334 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 334 insertions(+) create mode 100644 drivers/irqchip/irq-gic-v3-mbi.c (limited to 'drivers/irqchip/irq-gic-v3-mbi.c') diff --git a/drivers/irqchip/irq-gic-v3-mbi.c b/drivers/irqchip/irq-gic-v3-mbi.c new file mode 100644 index 000000000..dbb8b1efd --- /dev/null +++ b/drivers/irqchip/irq-gic-v3-mbi.c @@ -0,0 +1,334 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2018 ARM Limited, All Rights Reserved. + * Author: Marc Zyngier + */ + +#define pr_fmt(fmt) "GICv3: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +struct mbi_range { + u32 spi_start; + u32 nr_spis; + unsigned long *bm; +}; + +static DEFINE_MUTEX(mbi_lock); +static phys_addr_t mbi_phys_base; +static struct mbi_range *mbi_ranges; +static unsigned int mbi_range_nr; + +static struct irq_chip mbi_irq_chip = { + .name = "MBI", + .irq_mask = irq_chip_mask_parent, + .irq_unmask = irq_chip_unmask_parent, + .irq_eoi = irq_chip_eoi_parent, + .irq_set_type = irq_chip_set_type_parent, + .irq_set_affinity = irq_chip_set_affinity_parent, +}; + +static int mbi_irq_gic_domain_alloc(struct irq_domain *domain, + unsigned int virq, + irq_hw_number_t hwirq) +{ + struct irq_fwspec fwspec; + struct irq_data *d; + int err; + + /* + * Using ACPI? There is no MBI support in the spec, you + * shouldn't even be here. + */ + if (!is_of_node(domain->parent->fwnode)) + return -EINVAL; + + /* + * Let's default to edge. This is consistent with traditional + * MSIs, and systems requiring level signaling will just + * enforce the trigger on their own. + */ + fwspec.fwnode = domain->parent->fwnode; + fwspec.param_count = 3; + fwspec.param[0] = 0; + fwspec.param[1] = hwirq - 32; + fwspec.param[2] = IRQ_TYPE_EDGE_RISING; + + err = irq_domain_alloc_irqs_parent(domain, virq, 1, &fwspec); + if (err) + return err; + + d = irq_domain_get_irq_data(domain->parent, virq); + return d->chip->irq_set_type(d, IRQ_TYPE_EDGE_RISING); +} + +static void mbi_free_msi(struct mbi_range *mbi, unsigned int hwirq, + int nr_irqs) +{ + mutex_lock(&mbi_lock); + bitmap_release_region(mbi->bm, hwirq - mbi->spi_start, + get_count_order(nr_irqs)); + mutex_unlock(&mbi_lock); +} + +static int mbi_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *args) +{ + msi_alloc_info_t *info = args; + struct mbi_range *mbi = NULL; + int hwirq, offset, i, err = 0; + + mutex_lock(&mbi_lock); + for (i = 0; i < mbi_range_nr; i++) { + offset = bitmap_find_free_region(mbi_ranges[i].bm, + mbi_ranges[i].nr_spis, + get_count_order(nr_irqs)); + if (offset >= 0) { + mbi = &mbi_ranges[i]; + break; + } + } + mutex_unlock(&mbi_lock); + + if (!mbi) + return -ENOSPC; + + hwirq = mbi->spi_start + offset; + + err = iommu_dma_prepare_msi(info->desc, + mbi_phys_base + GICD_SETSPI_NSR); + if (err) + return err; + + for (i = 0; i < nr_irqs; i++) { + err = mbi_irq_gic_domain_alloc(domain, virq + i, hwirq + i); + if (err) + goto fail; + + irq_domain_set_hwirq_and_chip(domain, virq + i, hwirq + i, + &mbi_irq_chip, mbi); + } + + return 0; + +fail: + irq_domain_free_irqs_parent(domain, virq, nr_irqs); + mbi_free_msi(mbi, hwirq, nr_irqs); + return err; +} + +static void mbi_irq_domain_free(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs) +{ + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + struct mbi_range *mbi = irq_data_get_irq_chip_data(d); + + mbi_free_msi(mbi, d->hwirq, nr_irqs); + irq_domain_free_irqs_parent(domain, virq, nr_irqs); +} + +static const struct irq_domain_ops mbi_domain_ops = { + .alloc = mbi_irq_domain_alloc, + .free = mbi_irq_domain_free, +}; + +static void mbi_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) +{ + msg[0].address_hi = upper_32_bits(mbi_phys_base + GICD_SETSPI_NSR); + msg[0].address_lo = lower_32_bits(mbi_phys_base + GICD_SETSPI_NSR); + msg[0].data = data->parent_data->hwirq; + + iommu_dma_compose_msi_msg(irq_data_get_msi_desc(data), msg); +} + +#ifdef CONFIG_PCI_MSI +/* PCI-specific irqchip */ +static void mbi_mask_msi_irq(struct irq_data *d) +{ + pci_msi_mask_irq(d); + irq_chip_mask_parent(d); +} + +static void mbi_unmask_msi_irq(struct irq_data *d) +{ + pci_msi_unmask_irq(d); + irq_chip_unmask_parent(d); +} + +static struct irq_chip mbi_msi_irq_chip = { + .name = "MSI", + .irq_mask = mbi_mask_msi_irq, + .irq_unmask = mbi_unmask_msi_irq, + .irq_eoi = irq_chip_eoi_parent, + .irq_compose_msi_msg = mbi_compose_msi_msg, +}; + +static struct msi_domain_info mbi_msi_domain_info = { + .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_PCI_MSIX | MSI_FLAG_MULTI_PCI_MSI), + .chip = &mbi_msi_irq_chip, +}; + +static int mbi_allocate_pci_domain(struct irq_domain *nexus_domain, + struct irq_domain **pci_domain) +{ + *pci_domain = pci_msi_create_irq_domain(nexus_domain->parent->fwnode, + &mbi_msi_domain_info, + nexus_domain); + if (!*pci_domain) + return -ENOMEM; + + return 0; +} +#else +static int mbi_allocate_pci_domain(struct irq_domain *nexus_domain, + struct irq_domain **pci_domain) +{ + *pci_domain = NULL; + return 0; +} +#endif + +static void mbi_compose_mbi_msg(struct irq_data *data, struct msi_msg *msg) +{ + mbi_compose_msi_msg(data, msg); + + msg[1].address_hi = upper_32_bits(mbi_phys_base + GICD_CLRSPI_NSR); + msg[1].address_lo = lower_32_bits(mbi_phys_base + GICD_CLRSPI_NSR); + msg[1].data = data->parent_data->hwirq; + + iommu_dma_compose_msi_msg(irq_data_get_msi_desc(data), &msg[1]); +} + +/* Platform-MSI specific irqchip */ +static struct irq_chip mbi_pmsi_irq_chip = { + .name = "pMSI", + .irq_set_type = irq_chip_set_type_parent, + .irq_compose_msi_msg = mbi_compose_mbi_msg, + .flags = IRQCHIP_SUPPORTS_LEVEL_MSI, +}; + +static struct msi_domain_ops mbi_pmsi_ops = { +}; + +static struct msi_domain_info mbi_pmsi_domain_info = { + .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_LEVEL_CAPABLE), + .ops = &mbi_pmsi_ops, + .chip = &mbi_pmsi_irq_chip, +}; + +static int mbi_allocate_domains(struct irq_domain *parent) +{ + struct irq_domain *nexus_domain, *pci_domain, *plat_domain; + int err; + + nexus_domain = irq_domain_create_hierarchy(parent, 0, 0, parent->fwnode, + &mbi_domain_ops, NULL); + if (!nexus_domain) + return -ENOMEM; + + irq_domain_update_bus_token(nexus_domain, DOMAIN_BUS_NEXUS); + + err = mbi_allocate_pci_domain(nexus_domain, &pci_domain); + + plat_domain = platform_msi_create_irq_domain(parent->fwnode, + &mbi_pmsi_domain_info, + nexus_domain); + + if (err || !plat_domain) { + if (plat_domain) + irq_domain_remove(plat_domain); + if (pci_domain) + irq_domain_remove(pci_domain); + irq_domain_remove(nexus_domain); + return -ENOMEM; + } + + return 0; +} + +int __init mbi_init(struct fwnode_handle *fwnode, struct irq_domain *parent) +{ + struct device_node *np; + const __be32 *reg; + int ret, n; + + np = to_of_node(fwnode); + + if (!of_property_read_bool(np, "msi-controller")) + return 0; + + n = of_property_count_elems_of_size(np, "mbi-ranges", sizeof(u32)); + if (n <= 0 || n % 2) + return -EINVAL; + + mbi_range_nr = n / 2; + mbi_ranges = kcalloc(mbi_range_nr, sizeof(*mbi_ranges), GFP_KERNEL); + if (!mbi_ranges) + return -ENOMEM; + + for (n = 0; n < mbi_range_nr; n++) { + ret = of_property_read_u32_index(np, "mbi-ranges", n * 2, + &mbi_ranges[n].spi_start); + if (ret) + goto err_free_mbi; + ret = of_property_read_u32_index(np, "mbi-ranges", n * 2 + 1, + &mbi_ranges[n].nr_spis); + if (ret) + goto err_free_mbi; + + mbi_ranges[n].bm = bitmap_zalloc(mbi_ranges[n].nr_spis, GFP_KERNEL); + if (!mbi_ranges[n].bm) { + ret = -ENOMEM; + goto err_free_mbi; + } + pr_info("MBI range [%d:%d]\n", mbi_ranges[n].spi_start, + mbi_ranges[n].spi_start + mbi_ranges[n].nr_spis - 1); + } + + reg = of_get_property(np, "mbi-alias", NULL); + if (reg) { + mbi_phys_base = of_translate_address(np, reg); + if (mbi_phys_base == (phys_addr_t)OF_BAD_ADDR) { + ret = -ENXIO; + goto err_free_mbi; + } + } else { + struct resource res; + + if (of_address_to_resource(np, 0, &res)) { + ret = -ENXIO; + goto err_free_mbi; + } + + mbi_phys_base = res.start; + } + + pr_info("Using MBI frame %pa\n", &mbi_phys_base); + + ret = mbi_allocate_domains(parent); + if (ret) + goto err_free_mbi; + + return 0; + +err_free_mbi: + if (mbi_ranges) { + for (n = 0; n < mbi_range_nr; n++) + bitmap_free(mbi_ranges[n].bm); + kfree(mbi_ranges); + } + + return ret; +} -- cgit v1.2.3