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-loongson-eiointc.c | 437 +++++++++++++++++++++++++++++++++ 1 file changed, 437 insertions(+) create mode 100644 drivers/irqchip/irq-loongson-eiointc.c (limited to 'drivers/irqchip/irq-loongson-eiointc.c') diff --git a/drivers/irqchip/irq-loongson-eiointc.c b/drivers/irqchip/irq-loongson-eiointc.c new file mode 100644 index 000000000..d15fd38c1 --- /dev/null +++ b/drivers/irqchip/irq-loongson-eiointc.c @@ -0,0 +1,437 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Loongson Extend I/O Interrupt Controller support + * + * Copyright (C) 2020-2022 Loongson Technology Corporation Limited + */ + +#define pr_fmt(fmt) "eiointc: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define EIOINTC_REG_NODEMAP 0x14a0 +#define EIOINTC_REG_IPMAP 0x14c0 +#define EIOINTC_REG_ENABLE 0x1600 +#define EIOINTC_REG_BOUNCE 0x1680 +#define EIOINTC_REG_ISR 0x1800 +#define EIOINTC_REG_ROUTE 0x1c00 + +#define VEC_REG_COUNT 4 +#define VEC_COUNT_PER_REG 64 +#define VEC_COUNT (VEC_REG_COUNT * VEC_COUNT_PER_REG) +#define VEC_REG_IDX(irq_id) ((irq_id) / VEC_COUNT_PER_REG) +#define VEC_REG_BIT(irq_id) ((irq_id) % VEC_COUNT_PER_REG) +#define EIOINTC_ALL_ENABLE 0xffffffff + +#define MAX_EIO_NODES (NR_CPUS / CORES_PER_EIO_NODE) + +static int nr_pics; + +struct eiointc_priv { + u32 node; + nodemask_t node_map; + cpumask_t cpuspan_map; + struct fwnode_handle *domain_handle; + struct irq_domain *eiointc_domain; +}; + +static struct eiointc_priv *eiointc_priv[MAX_IO_PICS]; + +static void eiointc_enable(void) +{ + uint64_t misc; + + misc = iocsr_read64(LOONGARCH_IOCSR_MISC_FUNC); + misc |= IOCSR_MISC_FUNC_EXT_IOI_EN; + iocsr_write64(misc, LOONGARCH_IOCSR_MISC_FUNC); +} + +static int cpu_to_eio_node(int cpu) +{ + return cpu_logical_map(cpu) / CORES_PER_EIO_NODE; +} + +static void eiointc_set_irq_route(int pos, unsigned int cpu, unsigned int mnode, nodemask_t *node_map) +{ + int i, node, cpu_node, route_node; + unsigned char coremap; + uint32_t pos_off, data, data_byte, data_mask; + + pos_off = pos & ~3; + data_byte = pos & 3; + data_mask = ~BIT_MASK(data_byte) & 0xf; + + /* Calculate node and coremap of target irq */ + cpu_node = cpu_logical_map(cpu) / CORES_PER_EIO_NODE; + coremap = BIT(cpu_logical_map(cpu) % CORES_PER_EIO_NODE); + + for_each_online_cpu(i) { + node = cpu_to_eio_node(i); + if (!node_isset(node, *node_map)) + continue; + + /* EIO node 0 is in charge of inter-node interrupt dispatch */ + route_node = (node == mnode) ? cpu_node : node; + data = ((coremap | (route_node << 4)) << (data_byte * 8)); + csr_any_send(EIOINTC_REG_ROUTE + pos_off, data, data_mask, node * CORES_PER_EIO_NODE); + } +} + +static DEFINE_RAW_SPINLOCK(affinity_lock); + +static int eiointc_set_irq_affinity(struct irq_data *d, const struct cpumask *affinity, bool force) +{ + unsigned int cpu; + unsigned long flags; + uint32_t vector, regaddr; + struct cpumask intersect_affinity; + struct eiointc_priv *priv = d->domain->host_data; + + raw_spin_lock_irqsave(&affinity_lock, flags); + + cpumask_and(&intersect_affinity, affinity, cpu_online_mask); + cpumask_and(&intersect_affinity, &intersect_affinity, &priv->cpuspan_map); + + if (cpumask_empty(&intersect_affinity)) { + raw_spin_unlock_irqrestore(&affinity_lock, flags); + return -EINVAL; + } + cpu = cpumask_first(&intersect_affinity); + + vector = d->hwirq; + regaddr = EIOINTC_REG_ENABLE + ((vector >> 5) << 2); + + /* Mask target vector */ + csr_any_send(regaddr, EIOINTC_ALL_ENABLE & (~BIT(vector & 0x1F)), + 0x0, priv->node * CORES_PER_EIO_NODE); + + /* Set route for target vector */ + eiointc_set_irq_route(vector, cpu, priv->node, &priv->node_map); + + /* Unmask target vector */ + csr_any_send(regaddr, EIOINTC_ALL_ENABLE, + 0x0, priv->node * CORES_PER_EIO_NODE); + + irq_data_update_effective_affinity(d, cpumask_of(cpu)); + + raw_spin_unlock_irqrestore(&affinity_lock, flags); + + return IRQ_SET_MASK_OK; +} + +static int eiointc_index(int node) +{ + int i; + + for (i = 0; i < nr_pics; i++) { + if (node_isset(node, eiointc_priv[i]->node_map)) + return i; + } + + return -1; +} + +static int eiointc_router_init(unsigned int cpu) +{ + int i, bit; + uint32_t data; + uint32_t node = cpu_to_eio_node(cpu); + uint32_t index = eiointc_index(node); + + if (index < 0) { + pr_err("Error: invalid nodemap!\n"); + return -1; + } + + if ((cpu_logical_map(cpu) % CORES_PER_EIO_NODE) == 0) { + eiointc_enable(); + + for (i = 0; i < VEC_COUNT / 32; i++) { + data = (((1 << (i * 2 + 1)) << 16) | (1 << (i * 2))); + iocsr_write32(data, EIOINTC_REG_NODEMAP + i * 4); + } + + for (i = 0; i < VEC_COUNT / 32 / 4; i++) { + bit = BIT(1 + index); /* Route to IP[1 + index] */ + data = bit | (bit << 8) | (bit << 16) | (bit << 24); + iocsr_write32(data, EIOINTC_REG_IPMAP + i * 4); + } + + for (i = 0; i < VEC_COUNT / 4; i++) { + /* Route to Node-0 Core-0 */ + if (index == 0) + bit = BIT(cpu_logical_map(0)); + else + bit = (eiointc_priv[index]->node << 4) | 1; + + data = bit | (bit << 8) | (bit << 16) | (bit << 24); + iocsr_write32(data, EIOINTC_REG_ROUTE + i * 4); + } + + for (i = 0; i < VEC_COUNT / 32; i++) { + data = 0xffffffff; + iocsr_write32(data, EIOINTC_REG_ENABLE + i * 4); + iocsr_write32(data, EIOINTC_REG_BOUNCE + i * 4); + } + } + + return 0; +} + +static void eiointc_irq_dispatch(struct irq_desc *desc) +{ + int i; + u64 pending; + bool handled = false; + struct irq_chip *chip = irq_desc_get_chip(desc); + struct eiointc_priv *priv = irq_desc_get_handler_data(desc); + + chained_irq_enter(chip, desc); + + for (i = 0; i < VEC_REG_COUNT; i++) { + pending = iocsr_read64(EIOINTC_REG_ISR + (i << 3)); + iocsr_write64(pending, EIOINTC_REG_ISR + (i << 3)); + while (pending) { + int bit = __ffs(pending); + int irq = bit + VEC_COUNT_PER_REG * i; + + generic_handle_domain_irq(priv->eiointc_domain, irq); + pending &= ~BIT(bit); + handled = true; + } + } + + if (!handled) + spurious_interrupt(); + + chained_irq_exit(chip, desc); +} + +static void eiointc_ack_irq(struct irq_data *d) +{ +} + +static void eiointc_mask_irq(struct irq_data *d) +{ +} + +static void eiointc_unmask_irq(struct irq_data *d) +{ +} + +static struct irq_chip eiointc_irq_chip = { + .name = "EIOINTC", + .irq_ack = eiointc_ack_irq, + .irq_mask = eiointc_mask_irq, + .irq_unmask = eiointc_unmask_irq, + .irq_set_affinity = eiointc_set_irq_affinity, +}; + +static int eiointc_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) +{ + int ret; + unsigned int i, type; + unsigned long hwirq = 0; + struct eiointc *priv = domain->host_data; + + ret = irq_domain_translate_onecell(domain, arg, &hwirq, &type); + if (ret) + return ret; + + for (i = 0; i < nr_irqs; i++) { + irq_domain_set_info(domain, virq + i, hwirq + i, &eiointc_irq_chip, + priv, handle_edge_irq, NULL, NULL); + } + + return 0; +} + +static void eiointc_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + int i; + + for (i = 0; i < nr_irqs; i++) { + struct irq_data *d = irq_domain_get_irq_data(domain, virq + i); + + irq_set_handler(virq + i, NULL); + irq_domain_reset_irq_data(d); + } +} + +static const struct irq_domain_ops eiointc_domain_ops = { + .translate = irq_domain_translate_onecell, + .alloc = eiointc_domain_alloc, + .free = eiointc_domain_free, +}; + +static void acpi_set_vec_parent(int node, struct irq_domain *parent, struct acpi_vector_group *vec_group) +{ + int i; + + if (cpu_has_flatmode) + node = cpu_to_node(node * CORES_PER_EIO_NODE); + + for (i = 0; i < MAX_IO_PICS; i++) { + if (node == vec_group[i].node) { + vec_group[i].parent = parent; + return; + } + } +} + +static struct irq_domain *acpi_get_vec_parent(int node, struct acpi_vector_group *vec_group) +{ + int i; + + for (i = 0; i < MAX_IO_PICS; i++) { + if (node == vec_group[i].node) + return vec_group[i].parent; + } + return NULL; +} + +static int eiointc_suspend(void) +{ + return 0; +} + +static void eiointc_resume(void) +{ + int i, j; + struct irq_desc *desc; + struct irq_data *irq_data; + + eiointc_router_init(0); + + for (i = 0; i < nr_pics; i++) { + for (j = 0; j < VEC_COUNT; j++) { + desc = irq_resolve_mapping(eiointc_priv[i]->eiointc_domain, j); + if (desc && desc->handle_irq && desc->handle_irq != handle_bad_irq) { + raw_spin_lock(&desc->lock); + irq_data = &desc->irq_data; + eiointc_set_irq_affinity(irq_data, irq_data->common->affinity, 0); + raw_spin_unlock(&desc->lock); + } + } + } +} + +static struct syscore_ops eiointc_syscore_ops = { + .suspend = eiointc_suspend, + .resume = eiointc_resume, +}; + +static int __init pch_pic_parse_madt(union acpi_subtable_headers *header, + const unsigned long end) +{ + struct acpi_madt_bio_pic *pchpic_entry = (struct acpi_madt_bio_pic *)header; + unsigned int node = (pchpic_entry->address >> 44) & 0xf; + struct irq_domain *parent = acpi_get_vec_parent(node, pch_group); + + if (parent) + return pch_pic_acpi_init(parent, pchpic_entry); + + return -EINVAL; +} + +static int __init pch_msi_parse_madt(union acpi_subtable_headers *header, + const unsigned long end) +{ + struct acpi_madt_msi_pic *pchmsi_entry = (struct acpi_madt_msi_pic *)header; + struct irq_domain *parent = acpi_get_vec_parent(eiointc_priv[nr_pics - 1]->node, msi_group); + + if (parent) + return pch_msi_acpi_init(parent, pchmsi_entry); + + return -EINVAL; +} + +static int __init acpi_cascade_irqdomain_init(void) +{ + int r; + + r = acpi_table_parse_madt(ACPI_MADT_TYPE_BIO_PIC, pch_pic_parse_madt, 0); + if (r < 0) + return r; + + r = acpi_table_parse_madt(ACPI_MADT_TYPE_MSI_PIC, pch_msi_parse_madt, 1); + if (r < 0) + return r; + + return 0; +} + +int __init eiointc_acpi_init(struct irq_domain *parent, + struct acpi_madt_eio_pic *acpi_eiointc) +{ + int i, ret, parent_irq; + unsigned long node_map; + struct eiointc_priv *priv; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->domain_handle = irq_domain_alloc_named_id_fwnode("EIOPIC", + acpi_eiointc->node); + if (!priv->domain_handle) { + pr_err("Unable to allocate domain handle\n"); + goto out_free_priv; + } + + priv->node = acpi_eiointc->node; + node_map = acpi_eiointc->node_map ? : -1ULL; + + for_each_possible_cpu(i) { + if (node_map & (1ULL << cpu_to_eio_node(i))) { + node_set(cpu_to_eio_node(i), priv->node_map); + cpumask_or(&priv->cpuspan_map, &priv->cpuspan_map, cpumask_of(i)); + } + } + + /* Setup IRQ domain */ + priv->eiointc_domain = irq_domain_create_linear(priv->domain_handle, VEC_COUNT, + &eiointc_domain_ops, priv); + if (!priv->eiointc_domain) { + pr_err("loongson-eiointc: cannot add IRQ domain\n"); + goto out_free_handle; + } + + eiointc_priv[nr_pics++] = priv; + + eiointc_router_init(0); + + parent_irq = irq_create_mapping(parent, acpi_eiointc->cascade); + irq_set_chained_handler_and_data(parent_irq, eiointc_irq_dispatch, priv); + + register_syscore_ops(&eiointc_syscore_ops); + cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_LOONGARCH_STARTING, + "irqchip/loongarch/intc:starting", + eiointc_router_init, NULL); + + acpi_set_vec_parent(acpi_eiointc->node, priv->eiointc_domain, pch_group); + acpi_set_vec_parent(acpi_eiointc->node, priv->eiointc_domain, msi_group); + ret = acpi_cascade_irqdomain_init(); + + return ret; + +out_free_handle: + irq_domain_free_fwnode(priv->domain_handle); + priv->domain_handle = NULL; +out_free_priv: + kfree(priv); + + return -ENOMEM; +} -- cgit v1.2.3