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/x86/kernel/apic/apic_numachip.c | 334 +++++++++++++++++++++++++++++++++++ 1 file changed, 334 insertions(+) create mode 100644 arch/x86/kernel/apic/apic_numachip.c (limited to 'arch/x86/kernel/apic/apic_numachip.c') diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c new file mode 100644 index 000000000..a54d817eb --- /dev/null +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -0,0 +1,334 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Numascale NumaConnect-Specific APIC Code + * + * Copyright (C) 2011 Numascale AS. All rights reserved. + * + * Send feedback to + * + */ +#include +#include +#include + +#include +#include + + +#include "local.h" + +u8 numachip_system __read_mostly; +static const struct apic apic_numachip1; +static const struct apic apic_numachip2; +static void (*numachip_apic_icr_write)(int apicid, unsigned int val) __read_mostly; + +static unsigned int numachip1_get_apic_id(unsigned long x) +{ + unsigned long value; + unsigned int id = (x >> 24) & 0xff; + + if (static_cpu_has(X86_FEATURE_NODEID_MSR)) { + rdmsrl(MSR_FAM10H_NODE_ID, value); + id |= (value << 2) & 0xff00; + } + + return id; +} + +static u32 numachip1_set_apic_id(unsigned int id) +{ + return (id & 0xff) << 24; +} + +static unsigned int numachip2_get_apic_id(unsigned long x) +{ + u64 mcfg; + + rdmsrl(MSR_FAM10H_MMIO_CONF_BASE, mcfg); + return ((mcfg >> (28 - 8)) & 0xfff00) | (x >> 24); +} + +static u32 numachip2_set_apic_id(unsigned int id) +{ + return id << 24; +} + +static int numachip_apic_id_valid(u32 apicid) +{ + /* Trust what bootloader passes in MADT */ + return 1; +} + +static int numachip_apic_id_registered(void) +{ + return 1; +} + +static int numachip_phys_pkg_id(int initial_apic_id, int index_msb) +{ + return initial_apic_id >> index_msb; +} + +static void numachip1_apic_icr_write(int apicid, unsigned int val) +{ + write_lcsr(CSR_G3_EXT_IRQ_GEN, (apicid << 16) | val); +} + +static void numachip2_apic_icr_write(int apicid, unsigned int val) +{ + numachip2_write32_lcsr(NUMACHIP2_APIC_ICR, (apicid << 12) | val); +} + +static int numachip_wakeup_secondary(int phys_apicid, unsigned long start_rip) +{ + numachip_apic_icr_write(phys_apicid, APIC_DM_INIT); + numachip_apic_icr_write(phys_apicid, APIC_DM_STARTUP | + (start_rip >> 12)); + + return 0; +} + +static void numachip_send_IPI_one(int cpu, int vector) +{ + int local_apicid, apicid = per_cpu(x86_cpu_to_apicid, cpu); + unsigned int dmode; + + preempt_disable(); + local_apicid = __this_cpu_read(x86_cpu_to_apicid); + + /* Send via local APIC where non-local part matches */ + if (!((apicid ^ local_apicid) >> NUMACHIP_LAPIC_BITS)) { + unsigned long flags; + + local_irq_save(flags); + __default_send_IPI_dest_field(apicid, vector, + APIC_DEST_PHYSICAL); + local_irq_restore(flags); + preempt_enable(); + return; + } + preempt_enable(); + + dmode = (vector == NMI_VECTOR) ? APIC_DM_NMI : APIC_DM_FIXED; + numachip_apic_icr_write(apicid, dmode | vector); +} + +static void numachip_send_IPI_mask(const struct cpumask *mask, int vector) +{ + unsigned int cpu; + + for_each_cpu(cpu, mask) + numachip_send_IPI_one(cpu, vector); +} + +static void numachip_send_IPI_mask_allbutself(const struct cpumask *mask, + int vector) +{ + unsigned int this_cpu = smp_processor_id(); + unsigned int cpu; + + for_each_cpu(cpu, mask) { + if (cpu != this_cpu) + numachip_send_IPI_one(cpu, vector); + } +} + +static void numachip_send_IPI_allbutself(int vector) +{ + unsigned int this_cpu = smp_processor_id(); + unsigned int cpu; + + for_each_online_cpu(cpu) { + if (cpu != this_cpu) + numachip_send_IPI_one(cpu, vector); + } +} + +static void numachip_send_IPI_all(int vector) +{ + numachip_send_IPI_mask(cpu_online_mask, vector); +} + +static void numachip_send_IPI_self(int vector) +{ + apic_write(APIC_SELF_IPI, vector); +} + +static int __init numachip1_probe(void) +{ + return apic == &apic_numachip1; +} + +static int __init numachip2_probe(void) +{ + return apic == &apic_numachip2; +} + +static void fixup_cpu_id(struct cpuinfo_x86 *c, int node) +{ + u64 val; + u32 nodes = 1; + + this_cpu_write(cpu_llc_id, node); + + /* Account for nodes per socket in multi-core-module processors */ + if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) { + rdmsrl(MSR_FAM10H_NODE_ID, val); + nodes = ((val >> 3) & 7) + 1; + } + + c->phys_proc_id = node / nodes; +} + +static int __init numachip_system_init(void) +{ + /* Map the LCSR area and set up the apic_icr_write function */ + switch (numachip_system) { + case 1: + init_extra_mapping_uc(NUMACHIP_LCSR_BASE, NUMACHIP_LCSR_SIZE); + numachip_apic_icr_write = numachip1_apic_icr_write; + break; + case 2: + init_extra_mapping_uc(NUMACHIP2_LCSR_BASE, NUMACHIP2_LCSR_SIZE); + numachip_apic_icr_write = numachip2_apic_icr_write; + break; + default: + return 0; + } + + x86_cpuinit.fixup_cpu_id = fixup_cpu_id; + x86_init.pci.arch_init = pci_numachip_init; + + return 0; +} +early_initcall(numachip_system_init); + +static int numachip1_acpi_madt_oem_check(char *oem_id, char *oem_table_id) +{ + if ((strncmp(oem_id, "NUMASC", 6) != 0) || + (strncmp(oem_table_id, "NCONNECT", 8) != 0)) + return 0; + + numachip_system = 1; + + return 1; +} + +static int numachip2_acpi_madt_oem_check(char *oem_id, char *oem_table_id) +{ + if ((strncmp(oem_id, "NUMASC", 6) != 0) || + (strncmp(oem_table_id, "NCONECT2", 8) != 0)) + return 0; + + numachip_system = 2; + + return 1; +} + +/* APIC IPIs are queued */ +static void numachip_apic_wait_icr_idle(void) +{ +} + +/* APIC NMI IPIs are queued */ +static u32 numachip_safe_apic_wait_icr_idle(void) +{ + return 0; +} + +static const struct apic apic_numachip1 __refconst = { + .name = "NumaConnect system", + .probe = numachip1_probe, + .acpi_madt_oem_check = numachip1_acpi_madt_oem_check, + .apic_id_valid = numachip_apic_id_valid, + .apic_id_registered = numachip_apic_id_registered, + + .delivery_mode = APIC_DELIVERY_MODE_FIXED, + .dest_mode_logical = false, + + .disable_esr = 0, + + .check_apicid_used = NULL, + .init_apic_ldr = flat_init_apic_ldr, + .ioapic_phys_id_map = NULL, + .setup_apic_routing = NULL, + .cpu_present_to_apicid = default_cpu_present_to_apicid, + .apicid_to_cpu_present = NULL, + .check_phys_apicid_present = default_check_phys_apicid_present, + .phys_pkg_id = numachip_phys_pkg_id, + + .get_apic_id = numachip1_get_apic_id, + .set_apic_id = numachip1_set_apic_id, + + .calc_dest_apicid = apic_default_calc_apicid, + + .send_IPI = numachip_send_IPI_one, + .send_IPI_mask = numachip_send_IPI_mask, + .send_IPI_mask_allbutself = numachip_send_IPI_mask_allbutself, + .send_IPI_allbutself = numachip_send_IPI_allbutself, + .send_IPI_all = numachip_send_IPI_all, + .send_IPI_self = numachip_send_IPI_self, + + .wakeup_secondary_cpu = numachip_wakeup_secondary, + .inquire_remote_apic = NULL, /* REMRD not supported */ + + .read = native_apic_mem_read, + .write = native_apic_mem_write, + .eoi_write = native_apic_mem_write, + .icr_read = native_apic_icr_read, + .icr_write = native_apic_icr_write, + .wait_icr_idle = numachip_apic_wait_icr_idle, + .safe_wait_icr_idle = numachip_safe_apic_wait_icr_idle, +}; + +apic_driver(apic_numachip1); + +static const struct apic apic_numachip2 __refconst = { + .name = "NumaConnect2 system", + .probe = numachip2_probe, + .acpi_madt_oem_check = numachip2_acpi_madt_oem_check, + .apic_id_valid = numachip_apic_id_valid, + .apic_id_registered = numachip_apic_id_registered, + + .delivery_mode = APIC_DELIVERY_MODE_FIXED, + .dest_mode_logical = false, + + .disable_esr = 0, + + .check_apicid_used = NULL, + .init_apic_ldr = flat_init_apic_ldr, + .ioapic_phys_id_map = NULL, + .setup_apic_routing = NULL, + .cpu_present_to_apicid = default_cpu_present_to_apicid, + .apicid_to_cpu_present = NULL, + .check_phys_apicid_present = default_check_phys_apicid_present, + .phys_pkg_id = numachip_phys_pkg_id, + + .get_apic_id = numachip2_get_apic_id, + .set_apic_id = numachip2_set_apic_id, + + .calc_dest_apicid = apic_default_calc_apicid, + + .send_IPI = numachip_send_IPI_one, + .send_IPI_mask = numachip_send_IPI_mask, + .send_IPI_mask_allbutself = numachip_send_IPI_mask_allbutself, + .send_IPI_allbutself = numachip_send_IPI_allbutself, + .send_IPI_all = numachip_send_IPI_all, + .send_IPI_self = numachip_send_IPI_self, + + .wakeup_secondary_cpu = numachip_wakeup_secondary, + .inquire_remote_apic = NULL, /* REMRD not supported */ + + .read = native_apic_mem_read, + .write = native_apic_mem_write, + .eoi_write = native_apic_mem_write, + .icr_read = native_apic_icr_read, + .icr_write = native_apic_icr_write, + .wait_icr_idle = numachip_apic_wait_icr_idle, + .safe_wait_icr_idle = numachip_safe_apic_wait_icr_idle, +}; + +apic_driver(apic_numachip2); -- cgit v1.2.3