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/kvmclock.c | 345 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 345 insertions(+) create mode 100644 arch/x86/kernel/kvmclock.c (limited to 'arch/x86/kernel/kvmclock.c') diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c new file mode 100644 index 000000000..0f35d44c5 --- /dev/null +++ b/arch/x86/kernel/kvmclock.c @@ -0,0 +1,345 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* KVM paravirtual clock driver. A clocksource implementation + Copyright (C) 2008 Glauber de Oliveira Costa, Red Hat Inc. +*/ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +static int kvmclock __initdata = 1; +static int kvmclock_vsyscall __initdata = 1; +static int msr_kvm_system_time __ro_after_init = MSR_KVM_SYSTEM_TIME; +static int msr_kvm_wall_clock __ro_after_init = MSR_KVM_WALL_CLOCK; +static u64 kvm_sched_clock_offset __ro_after_init; + +static int __init parse_no_kvmclock(char *arg) +{ + kvmclock = 0; + return 0; +} +early_param("no-kvmclock", parse_no_kvmclock); + +static int __init parse_no_kvmclock_vsyscall(char *arg) +{ + kvmclock_vsyscall = 0; + return 0; +} +early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall); + +/* Aligned to page sizes to match whats mapped via vsyscalls to userspace */ +#define HVC_BOOT_ARRAY_SIZE \ + (PAGE_SIZE / sizeof(struct pvclock_vsyscall_time_info)) + +static struct pvclock_vsyscall_time_info + hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __bss_decrypted __aligned(PAGE_SIZE); +static struct pvclock_wall_clock wall_clock __bss_decrypted; +static struct pvclock_vsyscall_time_info *hvclock_mem; +DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); +EXPORT_PER_CPU_SYMBOL_GPL(hv_clock_per_cpu); + +/* + * The wallclock is the time of day when we booted. Since then, some time may + * have elapsed since the hypervisor wrote the data. So we try to account for + * that with system time + */ +static void kvm_get_wallclock(struct timespec64 *now) +{ + wrmsrl(msr_kvm_wall_clock, slow_virt_to_phys(&wall_clock)); + preempt_disable(); + pvclock_read_wallclock(&wall_clock, this_cpu_pvti(), now); + preempt_enable(); +} + +static int kvm_set_wallclock(const struct timespec64 *now) +{ + return -ENODEV; +} + +static noinstr u64 kvm_clock_read(void) +{ + u64 ret; + + preempt_disable_notrace(); + ret = pvclock_clocksource_read_nowd(this_cpu_pvti()); + preempt_enable_notrace(); + return ret; +} + +static u64 kvm_clock_get_cycles(struct clocksource *cs) +{ + return kvm_clock_read(); +} + +static noinstr u64 kvm_sched_clock_read(void) +{ + return kvm_clock_read() - kvm_sched_clock_offset; +} + +static inline void kvm_sched_clock_init(bool stable) +{ + if (!stable) + clear_sched_clock_stable(); + kvm_sched_clock_offset = kvm_clock_read(); + paravirt_set_sched_clock(kvm_sched_clock_read); + + pr_info("kvm-clock: using sched offset of %llu cycles", + kvm_sched_clock_offset); + + BUILD_BUG_ON(sizeof(kvm_sched_clock_offset) > + sizeof(((struct pvclock_vcpu_time_info *)NULL)->system_time)); +} + +/* + * If we don't do that, there is the possibility that the guest + * will calibrate under heavy load - thus, getting a lower lpj - + * and execute the delays themselves without load. This is wrong, + * because no delay loop can finish beforehand. + * Any heuristics is subject to fail, because ultimately, a large + * poll of guests can be running and trouble each other. So we preset + * lpj here + */ +static unsigned long kvm_get_tsc_khz(void) +{ + setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ); + return pvclock_tsc_khz(this_cpu_pvti()); +} + +static void __init kvm_get_preset_lpj(void) +{ + unsigned long khz; + u64 lpj; + + khz = kvm_get_tsc_khz(); + + lpj = ((u64)khz * 1000); + do_div(lpj, HZ); + preset_lpj = lpj; +} + +bool kvm_check_and_clear_guest_paused(void) +{ + struct pvclock_vsyscall_time_info *src = this_cpu_hvclock(); + bool ret = false; + + if (!src) + return ret; + + if ((src->pvti.flags & PVCLOCK_GUEST_STOPPED) != 0) { + src->pvti.flags &= ~PVCLOCK_GUEST_STOPPED; + pvclock_touch_watchdogs(); + ret = true; + } + return ret; +} + +static int kvm_cs_enable(struct clocksource *cs) +{ + vclocks_set_used(VDSO_CLOCKMODE_PVCLOCK); + return 0; +} + +struct clocksource kvm_clock = { + .name = "kvm-clock", + .read = kvm_clock_get_cycles, + .rating = 400, + .mask = CLOCKSOURCE_MASK(64), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, + .enable = kvm_cs_enable, +}; +EXPORT_SYMBOL_GPL(kvm_clock); + +static void kvm_register_clock(char *txt) +{ + struct pvclock_vsyscall_time_info *src = this_cpu_hvclock(); + u64 pa; + + if (!src) + return; + + pa = slow_virt_to_phys(&src->pvti) | 0x01ULL; + wrmsrl(msr_kvm_system_time, pa); + pr_debug("kvm-clock: cpu %d, msr %llx, %s", smp_processor_id(), pa, txt); +} + +static void kvm_save_sched_clock_state(void) +{ +} + +static void kvm_restore_sched_clock_state(void) +{ + kvm_register_clock("primary cpu clock, resume"); +} + +#ifdef CONFIG_X86_LOCAL_APIC +static void kvm_setup_secondary_clock(void) +{ + kvm_register_clock("secondary cpu clock"); +} +#endif + +void kvmclock_disable(void) +{ + native_write_msr(msr_kvm_system_time, 0, 0); +} + +static void __init kvmclock_init_mem(void) +{ + unsigned long ncpus; + unsigned int order; + struct page *p; + int r; + + if (HVC_BOOT_ARRAY_SIZE >= num_possible_cpus()) + return; + + ncpus = num_possible_cpus() - HVC_BOOT_ARRAY_SIZE; + order = get_order(ncpus * sizeof(*hvclock_mem)); + + p = alloc_pages(GFP_KERNEL, order); + if (!p) { + pr_warn("%s: failed to alloc %d pages", __func__, (1U << order)); + return; + } + + hvclock_mem = page_address(p); + + /* + * hvclock is shared between the guest and the hypervisor, must + * be mapped decrypted. + */ + if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) { + r = set_memory_decrypted((unsigned long) hvclock_mem, + 1UL << order); + if (r) { + __free_pages(p, order); + hvclock_mem = NULL; + pr_warn("kvmclock: set_memory_decrypted() failed. Disabling\n"); + return; + } + } + + memset(hvclock_mem, 0, PAGE_SIZE << order); +} + +static int __init kvm_setup_vsyscall_timeinfo(void) +{ + if (!kvm_para_available() || !kvmclock || nopv) + return 0; + + kvmclock_init_mem(); + +#ifdef CONFIG_X86_64 + if (per_cpu(hv_clock_per_cpu, 0) && kvmclock_vsyscall) { + u8 flags; + + flags = pvclock_read_flags(&hv_clock_boot[0].pvti); + if (!(flags & PVCLOCK_TSC_STABLE_BIT)) + return 0; + + kvm_clock.vdso_clock_mode = VDSO_CLOCKMODE_PVCLOCK; + } +#endif + + return 0; +} +early_initcall(kvm_setup_vsyscall_timeinfo); + +static int kvmclock_setup_percpu(unsigned int cpu) +{ + struct pvclock_vsyscall_time_info *p = per_cpu(hv_clock_per_cpu, cpu); + + /* + * The per cpu area setup replicates CPU0 data to all cpu + * pointers. So carefully check. CPU0 has been set up in init + * already. + */ + if (!cpu || (p && p != per_cpu(hv_clock_per_cpu, 0))) + return 0; + + /* Use the static page for the first CPUs, allocate otherwise */ + if (cpu < HVC_BOOT_ARRAY_SIZE) + p = &hv_clock_boot[cpu]; + else if (hvclock_mem) + p = hvclock_mem + cpu - HVC_BOOT_ARRAY_SIZE; + else + return -ENOMEM; + + per_cpu(hv_clock_per_cpu, cpu) = p; + return p ? 0 : -ENOMEM; +} + +void __init kvmclock_init(void) +{ + u8 flags; + + if (!kvm_para_available() || !kvmclock) + return; + + if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) { + msr_kvm_system_time = MSR_KVM_SYSTEM_TIME_NEW; + msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK_NEW; + } else if (!kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) { + return; + } + + if (cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "kvmclock:setup_percpu", + kvmclock_setup_percpu, NULL) < 0) { + return; + } + + pr_info("kvm-clock: Using msrs %x and %x", + msr_kvm_system_time, msr_kvm_wall_clock); + + this_cpu_write(hv_clock_per_cpu, &hv_clock_boot[0]); + kvm_register_clock("primary cpu clock"); + pvclock_set_pvti_cpu0_va(hv_clock_boot); + + if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) + pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT); + + flags = pvclock_read_flags(&hv_clock_boot[0].pvti); + kvm_sched_clock_init(flags & PVCLOCK_TSC_STABLE_BIT); + + x86_platform.calibrate_tsc = kvm_get_tsc_khz; + x86_platform.calibrate_cpu = kvm_get_tsc_khz; + x86_platform.get_wallclock = kvm_get_wallclock; + x86_platform.set_wallclock = kvm_set_wallclock; +#ifdef CONFIG_X86_LOCAL_APIC + x86_cpuinit.early_percpu_clock_init = kvm_setup_secondary_clock; +#endif + x86_platform.save_sched_clock_state = kvm_save_sched_clock_state; + x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state; + kvm_get_preset_lpj(); + + /* + * X86_FEATURE_NONSTOP_TSC is TSC runs at constant rate + * with P/T states and does not stop in deep C-states. + * + * Invariant TSC exposed by host means kvmclock is not necessary: + * can use TSC as clocksource. + * + */ + if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC) && + boot_cpu_has(X86_FEATURE_NONSTOP_TSC) && + !check_tsc_unstable()) + kvm_clock.rating = 299; + + clocksource_register_hz(&kvm_clock, NSEC_PER_SEC); + pv_info.name = "KVM"; +} -- cgit v1.2.3