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/sh/kernel/smp.c | 471 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 471 insertions(+) create mode 100644 arch/sh/kernel/smp.c (limited to 'arch/sh/kernel/smp.c') diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c new file mode 100644 index 000000000..65924d9ec --- /dev/null +++ b/arch/sh/kernel/smp.c @@ -0,0 +1,471 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * arch/sh/kernel/smp.c + * + * SMP support for the SuperH processors. + * + * Copyright (C) 2002 - 2010 Paul Mundt + * Copyright (C) 2006 - 2007 Akio Idehara + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +int __cpu_number_map[NR_CPUS]; /* Map physical to logical */ +int __cpu_logical_map[NR_CPUS]; /* Map logical to physical */ + +struct plat_smp_ops *mp_ops = NULL; + +/* State of each CPU */ +DEFINE_PER_CPU(int, cpu_state) = { 0 }; + +void register_smp_ops(struct plat_smp_ops *ops) +{ + if (mp_ops) + printk(KERN_WARNING "Overriding previously set SMP ops\n"); + + mp_ops = ops; +} + +static inline void smp_store_cpu_info(unsigned int cpu) +{ + struct sh_cpuinfo *c = cpu_data + cpu; + + memcpy(c, &boot_cpu_data, sizeof(struct sh_cpuinfo)); + + c->loops_per_jiffy = loops_per_jiffy; +} + +void __init smp_prepare_cpus(unsigned int max_cpus) +{ + unsigned int cpu = smp_processor_id(); + + init_new_context(current, &init_mm); + current_thread_info()->cpu = cpu; + mp_ops->prepare_cpus(max_cpus); + +#ifndef CONFIG_HOTPLUG_CPU + init_cpu_present(cpu_possible_mask); +#endif +} + +void __init smp_prepare_boot_cpu(void) +{ + unsigned int cpu = smp_processor_id(); + + __cpu_number_map[0] = cpu; + __cpu_logical_map[0] = cpu; + + set_cpu_online(cpu, true); + set_cpu_possible(cpu, true); + + per_cpu(cpu_state, cpu) = CPU_ONLINE; +} + +#ifdef CONFIG_HOTPLUG_CPU +void native_cpu_die(unsigned int cpu) +{ + unsigned int i; + + for (i = 0; i < 10; i++) { + smp_rmb(); + if (per_cpu(cpu_state, cpu) == CPU_DEAD) { + if (system_state == SYSTEM_RUNNING) + pr_info("CPU %u is now offline\n", cpu); + + return; + } + + msleep(100); + } + + pr_err("CPU %u didn't die...\n", cpu); +} + +int native_cpu_disable(unsigned int cpu) +{ + return cpu == 0 ? -EPERM : 0; +} + +void play_dead_common(void) +{ + idle_task_exit(); + irq_ctx_exit(raw_smp_processor_id()); + mb(); + + __this_cpu_write(cpu_state, CPU_DEAD); + local_irq_disable(); +} + +void native_play_dead(void) +{ + play_dead_common(); +} + +int __cpu_disable(void) +{ + unsigned int cpu = smp_processor_id(); + int ret; + + ret = mp_ops->cpu_disable(cpu); + if (ret) + return ret; + + /* + * Take this CPU offline. Once we clear this, we can't return, + * and we must not schedule until we're ready to give up the cpu. + */ + set_cpu_online(cpu, false); + + /* + * OK - migrate IRQs away from this CPU + */ + migrate_irqs(); + + /* + * Flush user cache and TLB mappings, and then remove this CPU + * from the vm mask set of all processes. + */ + flush_cache_all(); +#ifdef CONFIG_MMU + local_flush_tlb_all(); +#endif + + clear_tasks_mm_cpumask(cpu); + + return 0; +} +#else /* ... !CONFIG_HOTPLUG_CPU */ +int native_cpu_disable(unsigned int cpu) +{ + return -ENOSYS; +} + +void native_cpu_die(unsigned int cpu) +{ + /* We said "no" in __cpu_disable */ + BUG(); +} + +void native_play_dead(void) +{ + BUG(); +} +#endif + +asmlinkage void start_secondary(void) +{ + unsigned int cpu = smp_processor_id(); + struct mm_struct *mm = &init_mm; + + enable_mmu(); + mmgrab(mm); + mmget(mm); + current->active_mm = mm; +#ifdef CONFIG_MMU + enter_lazy_tlb(mm, current); + local_flush_tlb_all(); +#endif + + per_cpu_trap_init(); + + notify_cpu_starting(cpu); + + local_irq_enable(); + + calibrate_delay(); + + smp_store_cpu_info(cpu); + + set_cpu_online(cpu, true); + per_cpu(cpu_state, cpu) = CPU_ONLINE; + + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); +} + +extern struct { + unsigned long sp; + unsigned long bss_start; + unsigned long bss_end; + void *start_kernel_fn; + void *cpu_init_fn; + void *thread_info; +} stack_start; + +int __cpu_up(unsigned int cpu, struct task_struct *tsk) +{ + unsigned long timeout; + + per_cpu(cpu_state, cpu) = CPU_UP_PREPARE; + + /* Fill in data in head.S for secondary cpus */ + stack_start.sp = tsk->thread.sp; + stack_start.thread_info = tsk->stack; + stack_start.bss_start = 0; /* don't clear bss for secondary cpus */ + stack_start.start_kernel_fn = start_secondary; + + flush_icache_range((unsigned long)&stack_start, + (unsigned long)&stack_start + sizeof(stack_start)); + wmb(); + + mp_ops->start_cpu(cpu, (unsigned long)_stext); + + timeout = jiffies + HZ; + while (time_before(jiffies, timeout)) { + if (cpu_online(cpu)) + break; + + udelay(10); + barrier(); + } + + if (cpu_online(cpu)) + return 0; + + return -ENOENT; +} + +void __init smp_cpus_done(unsigned int max_cpus) +{ + unsigned long bogosum = 0; + int cpu; + + for_each_online_cpu(cpu) + bogosum += cpu_data[cpu].loops_per_jiffy; + + printk(KERN_INFO "SMP: Total of %d processors activated " + "(%lu.%02lu BogoMIPS).\n", num_online_cpus(), + bogosum / (500000/HZ), + (bogosum / (5000/HZ)) % 100); +} + +void smp_send_reschedule(int cpu) +{ + mp_ops->send_ipi(cpu, SMP_MSG_RESCHEDULE); +} + +void smp_send_stop(void) +{ + smp_call_function(stop_this_cpu, 0, 0); +} + +void arch_send_call_function_ipi_mask(const struct cpumask *mask) +{ + int cpu; + + for_each_cpu(cpu, mask) + mp_ops->send_ipi(cpu, SMP_MSG_FUNCTION); +} + +void arch_send_call_function_single_ipi(int cpu) +{ + mp_ops->send_ipi(cpu, SMP_MSG_FUNCTION_SINGLE); +} + +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +void tick_broadcast(const struct cpumask *mask) +{ + int cpu; + + for_each_cpu(cpu, mask) + mp_ops->send_ipi(cpu, SMP_MSG_TIMER); +} + +static void ipi_timer(void) +{ + irq_enter(); + tick_receive_broadcast(); + irq_exit(); +} +#endif + +void smp_message_recv(unsigned int msg) +{ + switch (msg) { + case SMP_MSG_FUNCTION: + generic_smp_call_function_interrupt(); + break; + case SMP_MSG_RESCHEDULE: + scheduler_ipi(); + break; + case SMP_MSG_FUNCTION_SINGLE: + generic_smp_call_function_single_interrupt(); + break; +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST + case SMP_MSG_TIMER: + ipi_timer(); + break; +#endif + default: + printk(KERN_WARNING "SMP %d: %s(): unknown IPI %d\n", + smp_processor_id(), __func__, msg); + break; + } +} + +/* Not really SMP stuff ... */ +int setup_profiling_timer(unsigned int multiplier) +{ + return 0; +} + +#ifdef CONFIG_MMU + +static void flush_tlb_all_ipi(void *info) +{ + local_flush_tlb_all(); +} + +void flush_tlb_all(void) +{ + on_each_cpu(flush_tlb_all_ipi, 0, 1); +} + +static void flush_tlb_mm_ipi(void *mm) +{ + local_flush_tlb_mm((struct mm_struct *)mm); +} + +/* + * The following tlb flush calls are invoked when old translations are + * being torn down, or pte attributes are changing. For single threaded + * address spaces, a new context is obtained on the current cpu, and tlb + * context on other cpus are invalidated to force a new context allocation + * at switch_mm time, should the mm ever be used on other cpus. For + * multithreaded address spaces, intercpu interrupts have to be sent. + * Another case where intercpu interrupts are required is when the target + * mm might be active on another cpu (eg debuggers doing the flushes on + * behalf of debugees, kswapd stealing pages from another process etc). + * Kanoj 07/00. + */ +void flush_tlb_mm(struct mm_struct *mm) +{ + preempt_disable(); + + if ((atomic_read(&mm->mm_users) != 1) || (current->mm != mm)) { + smp_call_function(flush_tlb_mm_ipi, (void *)mm, 1); + } else { + int i; + for_each_online_cpu(i) + if (smp_processor_id() != i) + cpu_context(i, mm) = 0; + } + local_flush_tlb_mm(mm); + + preempt_enable(); +} + +struct flush_tlb_data { + struct vm_area_struct *vma; + unsigned long addr1; + unsigned long addr2; +}; + +static void flush_tlb_range_ipi(void *info) +{ + struct flush_tlb_data *fd = (struct flush_tlb_data *)info; + + local_flush_tlb_range(fd->vma, fd->addr1, fd->addr2); +} + +void flush_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + struct mm_struct *mm = vma->vm_mm; + + preempt_disable(); + if ((atomic_read(&mm->mm_users) != 1) || (current->mm != mm)) { + struct flush_tlb_data fd; + + fd.vma = vma; + fd.addr1 = start; + fd.addr2 = end; + smp_call_function(flush_tlb_range_ipi, (void *)&fd, 1); + } else { + int i; + for_each_online_cpu(i) + if (smp_processor_id() != i) + cpu_context(i, mm) = 0; + } + local_flush_tlb_range(vma, start, end); + preempt_enable(); +} + +static void flush_tlb_kernel_range_ipi(void *info) +{ + struct flush_tlb_data *fd = (struct flush_tlb_data *)info; + + local_flush_tlb_kernel_range(fd->addr1, fd->addr2); +} + +void flush_tlb_kernel_range(unsigned long start, unsigned long end) +{ + struct flush_tlb_data fd; + + fd.addr1 = start; + fd.addr2 = end; + on_each_cpu(flush_tlb_kernel_range_ipi, (void *)&fd, 1); +} + +static void flush_tlb_page_ipi(void *info) +{ + struct flush_tlb_data *fd = (struct flush_tlb_data *)info; + + local_flush_tlb_page(fd->vma, fd->addr1); +} + +void flush_tlb_page(struct vm_area_struct *vma, unsigned long page) +{ + preempt_disable(); + if ((atomic_read(&vma->vm_mm->mm_users) != 1) || + (current->mm != vma->vm_mm)) { + struct flush_tlb_data fd; + + fd.vma = vma; + fd.addr1 = page; + smp_call_function(flush_tlb_page_ipi, (void *)&fd, 1); + } else { + int i; + for_each_online_cpu(i) + if (smp_processor_id() != i) + cpu_context(i, vma->vm_mm) = 0; + } + local_flush_tlb_page(vma, page); + preempt_enable(); +} + +static void flush_tlb_one_ipi(void *info) +{ + struct flush_tlb_data *fd = (struct flush_tlb_data *)info; + local_flush_tlb_one(fd->addr1, fd->addr2); +} + +void flush_tlb_one(unsigned long asid, unsigned long vaddr) +{ + struct flush_tlb_data fd; + + fd.addr1 = asid; + fd.addr2 = vaddr; + + smp_call_function(flush_tlb_one_ipi, (void *)&fd, 1); + local_flush_tlb_one(asid, vaddr); +} + +#endif -- cgit v1.2.3