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/xen/smp_pv.c | 460 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 460 insertions(+) create mode 100644 arch/x86/xen/smp_pv.c (limited to 'arch/x86/xen/smp_pv.c') diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c new file mode 100644 index 000000000..a9cf8c8fa --- /dev/null +++ b/arch/x86/xen/smp_pv.c @@ -0,0 +1,460 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Xen SMP support + * + * This file implements the Xen versions of smp_ops. SMP under Xen is + * very straightforward. Bringing a CPU up is simply a matter of + * loading its initial context and setting it running. + * + * IPIs are handled through the Xen event mechanism. + * + * Because virtual CPUs can be scheduled onto any real CPU, there's no + * useful topology information for the kernel to make use of. As a + * result, all CPUs are treated as if they're single-core and + * single-threaded. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +#include +#include +#include + +#include +#include +#include + +#include +#include +#include + +#include +#include "xen-ops.h" +#include "mmu.h" +#include "smp.h" +#include "pmu.h" + +cpumask_var_t xen_cpu_initialized_map; + +static DEFINE_PER_CPU(struct xen_common_irq, xen_irq_work) = { .irq = -1 }; +static DEFINE_PER_CPU(struct xen_common_irq, xen_pmu_irq) = { .irq = -1 }; + +static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id); +void asm_cpu_bringup_and_idle(void); + +static void cpu_bringup(void) +{ + int cpu; + + cr4_init(); + cpu_init(); + touch_softlockup_watchdog(); + + /* PVH runs in ring 0 and allows us to do native syscalls. Yay! */ + if (!xen_feature(XENFEAT_supervisor_mode_kernel)) { + xen_enable_sysenter(); + xen_enable_syscall(); + } + cpu = smp_processor_id(); + smp_store_cpu_info(cpu); + cpu_data(cpu).x86_max_cores = 1; + set_cpu_sibling_map(cpu); + + speculative_store_bypass_ht_init(); + + xen_setup_cpu_clockevents(); + + notify_cpu_starting(cpu); + + set_cpu_online(cpu, true); + + cpu_set_state_online(cpu); /* Implies full memory barrier. */ + + /* We can take interrupts now: we're officially "up". */ + local_irq_enable(); +} + +asmlinkage __visible void cpu_bringup_and_idle(void) +{ + cpu_bringup(); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); +} + +void xen_smp_intr_free_pv(unsigned int cpu) +{ + kfree(per_cpu(xen_irq_work, cpu).name); + per_cpu(xen_irq_work, cpu).name = NULL; + if (per_cpu(xen_irq_work, cpu).irq >= 0) { + unbind_from_irqhandler(per_cpu(xen_irq_work, cpu).irq, NULL); + per_cpu(xen_irq_work, cpu).irq = -1; + } + + kfree(per_cpu(xen_pmu_irq, cpu).name); + per_cpu(xen_pmu_irq, cpu).name = NULL; + if (per_cpu(xen_pmu_irq, cpu).irq >= 0) { + unbind_from_irqhandler(per_cpu(xen_pmu_irq, cpu).irq, NULL); + per_cpu(xen_pmu_irq, cpu).irq = -1; + } +} + +int xen_smp_intr_init_pv(unsigned int cpu) +{ + int rc; + char *callfunc_name, *pmu_name; + + callfunc_name = kasprintf(GFP_KERNEL, "irqwork%d", cpu); + per_cpu(xen_irq_work, cpu).name = callfunc_name; + rc = bind_ipi_to_irqhandler(XEN_IRQ_WORK_VECTOR, + cpu, + xen_irq_work_interrupt, + IRQF_PERCPU|IRQF_NOBALANCING, + callfunc_name, + NULL); + if (rc < 0) + goto fail; + per_cpu(xen_irq_work, cpu).irq = rc; + + if (is_xen_pmu) { + pmu_name = kasprintf(GFP_KERNEL, "pmu%d", cpu); + per_cpu(xen_pmu_irq, cpu).name = pmu_name; + rc = bind_virq_to_irqhandler(VIRQ_XENPMU, cpu, + xen_pmu_irq_handler, + IRQF_PERCPU|IRQF_NOBALANCING, + pmu_name, NULL); + if (rc < 0) + goto fail; + per_cpu(xen_pmu_irq, cpu).irq = rc; + } + + return 0; + + fail: + xen_smp_intr_free_pv(cpu); + return rc; +} + +static void __init _get_smp_config(unsigned int early) +{ + int i, rc; + unsigned int subtract = 0; + + if (early) + return; + + num_processors = 0; + disabled_cpus = 0; + for (i = 0; i < nr_cpu_ids; i++) { + rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL); + if (rc >= 0) { + num_processors++; + set_cpu_possible(i, true); + } else { + set_cpu_possible(i, false); + set_cpu_present(i, false); + subtract++; + } + } +#ifdef CONFIG_HOTPLUG_CPU + /* This is akin to using 'nr_cpus' on the Linux command line. + * Which is OK as when we use 'dom0_max_vcpus=X' we can only + * have up to X, while nr_cpu_ids is greater than X. This + * normally is not a problem, except when CPU hotplugging + * is involved and then there might be more than X CPUs + * in the guest - which will not work as there is no + * hypercall to expand the max number of VCPUs an already + * running guest has. So cap it up to X. */ + if (subtract) + set_nr_cpu_ids(nr_cpu_ids - subtract); +#endif + +} + +static void __init xen_pv_smp_prepare_boot_cpu(void) +{ + BUG_ON(smp_processor_id() != 0); + native_smp_prepare_boot_cpu(); + + if (!xen_feature(XENFEAT_writable_page_tables)) + /* We've switched to the "real" per-cpu gdt, so make + * sure the old memory can be recycled. */ + make_lowmem_page_readwrite(xen_initial_gdt); + + xen_setup_vcpu_info_placement(); + + /* + * The alternative logic (which patches the unlock/lock) runs before + * the smp bootup up code is activated. Hence we need to set this up + * the core kernel is being patched. Otherwise we will have only + * modules patched but not core code. + */ + xen_init_spinlocks(); +} + +static void __init xen_pv_smp_prepare_cpus(unsigned int max_cpus) +{ + unsigned cpu; + + if (skip_ioapic_setup) { + char *m = (max_cpus == 0) ? + "The nosmp parameter is incompatible with Xen; " \ + "use Xen dom0_max_vcpus=1 parameter" : + "The noapic parameter is incompatible with Xen"; + + xen_raw_printk(m); + panic(m); + } + xen_init_lock_cpu(0); + + smp_prepare_cpus_common(); + + cpu_data(0).x86_max_cores = 1; + + speculative_store_bypass_ht_init(); + + xen_pmu_init(0); + + if (xen_smp_intr_init(0) || xen_smp_intr_init_pv(0)) + BUG(); + + if (!alloc_cpumask_var(&xen_cpu_initialized_map, GFP_KERNEL)) + panic("could not allocate xen_cpu_initialized_map\n"); + + cpumask_copy(xen_cpu_initialized_map, cpumask_of(0)); + + /* Restrict the possible_map according to max_cpus. */ + while ((num_possible_cpus() > 1) && (num_possible_cpus() > max_cpus)) { + for (cpu = nr_cpu_ids - 1; !cpu_possible(cpu); cpu--) + continue; + set_cpu_possible(cpu, false); + } + + for_each_possible_cpu(cpu) + set_cpu_present(cpu, true); +} + +static int +cpu_initialize_context(unsigned int cpu, struct task_struct *idle) +{ + struct vcpu_guest_context *ctxt; + struct desc_struct *gdt; + unsigned long gdt_mfn; + + /* used to tell cpu_init() that it can proceed with initialization */ + cpumask_set_cpu(cpu, cpu_callout_mask); + if (cpumask_test_and_set_cpu(cpu, xen_cpu_initialized_map)) + return 0; + + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (ctxt == NULL) { + cpumask_clear_cpu(cpu, xen_cpu_initialized_map); + cpumask_clear_cpu(cpu, cpu_callout_mask); + return -ENOMEM; + } + + gdt = get_cpu_gdt_rw(cpu); + + /* + * Bring up the CPU in cpu_bringup_and_idle() with the stack + * pointing just below where pt_regs would be if it were a normal + * kernel entry. + */ + ctxt->user_regs.eip = (unsigned long)asm_cpu_bringup_and_idle; + ctxt->flags = VGCF_IN_KERNEL; + ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */ + ctxt->user_regs.ds = __USER_DS; + ctxt->user_regs.es = __USER_DS; + ctxt->user_regs.ss = __KERNEL_DS; + ctxt->user_regs.cs = __KERNEL_CS; + ctxt->user_regs.esp = (unsigned long)task_pt_regs(idle); + + xen_copy_trap_info(ctxt->trap_ctxt); + + BUG_ON((unsigned long)gdt & ~PAGE_MASK); + + gdt_mfn = arbitrary_virt_to_mfn(gdt); + make_lowmem_page_readonly(gdt); + make_lowmem_page_readonly(mfn_to_virt(gdt_mfn)); + + ctxt->gdt_frames[0] = gdt_mfn; + ctxt->gdt_ents = GDT_ENTRIES; + + /* + * Set SS:SP that Xen will use when entering guest kernel mode + * from guest user mode. Subsequent calls to load_sp0() can + * change this value. + */ + ctxt->kernel_ss = __KERNEL_DS; + ctxt->kernel_sp = task_top_of_stack(idle); + + ctxt->gs_base_kernel = per_cpu_offset(cpu); + ctxt->event_callback_eip = + (unsigned long)xen_asm_exc_xen_hypervisor_callback; + ctxt->failsafe_callback_eip = + (unsigned long)xen_failsafe_callback; + per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir); + + ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_gfn(swapper_pg_dir)); + if (HYPERVISOR_vcpu_op(VCPUOP_initialise, xen_vcpu_nr(cpu), ctxt)) + BUG(); + + kfree(ctxt); + return 0; +} + +static int xen_pv_cpu_up(unsigned int cpu, struct task_struct *idle) +{ + int rc; + + rc = common_cpu_up(cpu, idle); + if (rc) + return rc; + + xen_setup_runstate_info(cpu); + + /* + * PV VCPUs are always successfully taken down (see 'while' loop + * in xen_cpu_die()), so -EBUSY is an error. + */ + rc = cpu_check_up_prepare(cpu); + if (rc) + return rc; + + /* make sure interrupts start blocked */ + per_cpu(xen_vcpu, cpu)->evtchn_upcall_mask = 1; + + rc = cpu_initialize_context(cpu, idle); + if (rc) + return rc; + + xen_pmu_init(cpu); + + rc = HYPERVISOR_vcpu_op(VCPUOP_up, xen_vcpu_nr(cpu), NULL); + BUG_ON(rc); + + while (cpu_report_state(cpu) != CPU_ONLINE) + HYPERVISOR_sched_op(SCHEDOP_yield, NULL); + + return 0; +} + +#ifdef CONFIG_HOTPLUG_CPU +static int xen_pv_cpu_disable(void) +{ + unsigned int cpu = smp_processor_id(); + if (cpu == 0) + return -EBUSY; + + cpu_disable_common(); + + load_cr3(swapper_pg_dir); + return 0; +} + +static void xen_pv_cpu_die(unsigned int cpu) +{ + while (HYPERVISOR_vcpu_op(VCPUOP_is_up, + xen_vcpu_nr(cpu), NULL)) { + __set_current_state(TASK_UNINTERRUPTIBLE); + schedule_timeout(HZ/10); + } + + if (common_cpu_die(cpu) == 0) { + xen_smp_intr_free(cpu); + xen_uninit_lock_cpu(cpu); + xen_teardown_timer(cpu); + xen_pmu_finish(cpu); + } +} + +static void __noreturn xen_pv_play_dead(void) /* used only with HOTPLUG_CPU */ +{ + play_dead_common(); + HYPERVISOR_vcpu_op(VCPUOP_down, xen_vcpu_nr(smp_processor_id()), NULL); + xen_cpu_bringup_again((unsigned long)task_pt_regs(current)); + BUG(); +} + +#else /* !CONFIG_HOTPLUG_CPU */ +static int xen_pv_cpu_disable(void) +{ + return -ENOSYS; +} + +static void xen_pv_cpu_die(unsigned int cpu) +{ + BUG(); +} + +static void __noreturn xen_pv_play_dead(void) +{ + BUG(); +} + +#endif +static void stop_self(void *v) +{ + int cpu = smp_processor_id(); + + /* make sure we're not pinning something down */ + load_cr3(swapper_pg_dir); + /* should set up a minimal gdt */ + + set_cpu_online(cpu, false); + + HYPERVISOR_vcpu_op(VCPUOP_down, xen_vcpu_nr(cpu), NULL); + BUG(); +} + +static void xen_pv_stop_other_cpus(int wait) +{ + smp_call_function(stop_self, NULL, wait); +} + +static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id) +{ + irq_work_run(); + inc_irq_stat(apic_irq_work_irqs); + + return IRQ_HANDLED; +} + +static const struct smp_ops xen_smp_ops __initconst = { + .smp_prepare_boot_cpu = xen_pv_smp_prepare_boot_cpu, + .smp_prepare_cpus = xen_pv_smp_prepare_cpus, + .smp_cpus_done = xen_smp_cpus_done, + + .cpu_up = xen_pv_cpu_up, + .cpu_die = xen_pv_cpu_die, + .cpu_disable = xen_pv_cpu_disable, + .play_dead = xen_pv_play_dead, + + .stop_other_cpus = xen_pv_stop_other_cpus, + .smp_send_reschedule = xen_smp_send_reschedule, + + .send_call_func_ipi = xen_smp_send_call_function_ipi, + .send_call_func_single_ipi = xen_smp_send_call_function_single_ipi, +}; + +void __init xen_smp_init(void) +{ + smp_ops = xen_smp_ops; + + /* Avoid searching for BIOS MP tables */ + x86_init.mpparse.find_smp_config = x86_init_noop; + x86_init.mpparse.get_smp_config = _get_smp_config; +} -- cgit v1.2.3