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/arm64/kvm/reset.c | 397 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 397 insertions(+) create mode 100644 arch/arm64/kvm/reset.c (limited to 'arch/arm64/kvm/reset.c') diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c new file mode 100644 index 000000000..e0267f672 --- /dev/null +++ b/arch/arm64/kvm/reset.c @@ -0,0 +1,397 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012,2013 - ARM Ltd + * Author: Marc Zyngier + * + * Derived from arch/arm/kvm/reset.c + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Author: Christoffer Dall + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* Maximum phys_shift supported for any VM on this host */ +static u32 kvm_ipa_limit; + +/* + * ARMv8 Reset Values + */ +#define VCPU_RESET_PSTATE_EL1 (PSR_MODE_EL1h | PSR_A_BIT | PSR_I_BIT | \ + PSR_F_BIT | PSR_D_BIT) + +#define VCPU_RESET_PSTATE_SVC (PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | \ + PSR_AA32_I_BIT | PSR_AA32_F_BIT) + +unsigned int kvm_sve_max_vl; + +int kvm_arm_init_sve(void) +{ + if (system_supports_sve()) { + kvm_sve_max_vl = sve_max_virtualisable_vl(); + + /* + * The get_sve_reg()/set_sve_reg() ioctl interface will need + * to be extended with multiple register slice support in + * order to support vector lengths greater than + * VL_ARCH_MAX: + */ + if (WARN_ON(kvm_sve_max_vl > VL_ARCH_MAX)) + kvm_sve_max_vl = VL_ARCH_MAX; + + /* + * Don't even try to make use of vector lengths that + * aren't available on all CPUs, for now: + */ + if (kvm_sve_max_vl < sve_max_vl()) + pr_warn("KVM: SVE vector length for guests limited to %u bytes\n", + kvm_sve_max_vl); + } + + return 0; +} + +static int kvm_vcpu_enable_sve(struct kvm_vcpu *vcpu) +{ + if (!system_supports_sve()) + return -EINVAL; + + vcpu->arch.sve_max_vl = kvm_sve_max_vl; + + /* + * Userspace can still customize the vector lengths by writing + * KVM_REG_ARM64_SVE_VLS. Allocation is deferred until + * kvm_arm_vcpu_finalize(), which freezes the configuration. + */ + vcpu_set_flag(vcpu, GUEST_HAS_SVE); + + return 0; +} + +/* + * Finalize vcpu's maximum SVE vector length, allocating + * vcpu->arch.sve_state as necessary. + */ +static int kvm_vcpu_finalize_sve(struct kvm_vcpu *vcpu) +{ + void *buf; + unsigned int vl; + size_t reg_sz; + int ret; + + vl = vcpu->arch.sve_max_vl; + + /* + * Responsibility for these properties is shared between + * kvm_arm_init_sve(), kvm_vcpu_enable_sve() and + * set_sve_vls(). Double-check here just to be sure: + */ + if (WARN_ON(!sve_vl_valid(vl) || vl > sve_max_virtualisable_vl() || + vl > VL_ARCH_MAX)) + return -EIO; + + reg_sz = vcpu_sve_state_size(vcpu); + buf = kzalloc(reg_sz, GFP_KERNEL_ACCOUNT); + if (!buf) + return -ENOMEM; + + ret = kvm_share_hyp(buf, buf + reg_sz); + if (ret) { + kfree(buf); + return ret; + } + + vcpu->arch.sve_state = buf; + vcpu_set_flag(vcpu, VCPU_SVE_FINALIZED); + return 0; +} + +int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature) +{ + switch (feature) { + case KVM_ARM_VCPU_SVE: + if (!vcpu_has_sve(vcpu)) + return -EINVAL; + + if (kvm_arm_vcpu_sve_finalized(vcpu)) + return -EPERM; + + return kvm_vcpu_finalize_sve(vcpu); + } + + return -EINVAL; +} + +bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu) +{ + if (vcpu_has_sve(vcpu) && !kvm_arm_vcpu_sve_finalized(vcpu)) + return false; + + return true; +} + +void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu) +{ + void *sve_state = vcpu->arch.sve_state; + + kvm_vcpu_unshare_task_fp(vcpu); + kvm_unshare_hyp(vcpu, vcpu + 1); + if (sve_state) + kvm_unshare_hyp(sve_state, sve_state + vcpu_sve_state_size(vcpu)); + kfree(sve_state); +} + +static void kvm_vcpu_reset_sve(struct kvm_vcpu *vcpu) +{ + if (vcpu_has_sve(vcpu)) + memset(vcpu->arch.sve_state, 0, vcpu_sve_state_size(vcpu)); +} + +static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu) +{ + /* + * For now make sure that both address/generic pointer authentication + * features are requested by the userspace together and the system + * supports these capabilities. + */ + if (!test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) || + !test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features) || + !system_has_full_ptr_auth()) + return -EINVAL; + + vcpu_set_flag(vcpu, GUEST_HAS_PTRAUTH); + return 0; +} + +/** + * kvm_set_vm_width() - set the register width for the guest + * @vcpu: Pointer to the vcpu being configured + * + * Set both KVM_ARCH_FLAG_EL1_32BIT and KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED + * in the VM flags based on the vcpu's requested register width, the HW + * capabilities and other options (such as MTE). + * When REG_WIDTH_CONFIGURED is already set, the vcpu settings must be + * consistent with the value of the FLAG_EL1_32BIT bit in the flags. + * + * Return: 0 on success, negative error code on failure. + */ +static int kvm_set_vm_width(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + bool is32bit; + + is32bit = vcpu_has_feature(vcpu, KVM_ARM_VCPU_EL1_32BIT); + + lockdep_assert_held(&kvm->lock); + + if (test_bit(KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED, &kvm->arch.flags)) { + /* + * The guest's register width is already configured. + * Make sure that the vcpu is consistent with it. + */ + if (is32bit == test_bit(KVM_ARCH_FLAG_EL1_32BIT, &kvm->arch.flags)) + return 0; + + return -EINVAL; + } + + if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1) && is32bit) + return -EINVAL; + + /* MTE is incompatible with AArch32 */ + if (kvm_has_mte(kvm) && is32bit) + return -EINVAL; + + if (is32bit) + set_bit(KVM_ARCH_FLAG_EL1_32BIT, &kvm->arch.flags); + + set_bit(KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED, &kvm->arch.flags); + + return 0; +} + +/** + * kvm_reset_vcpu - sets core registers and sys_regs to reset value + * @vcpu: The VCPU pointer + * + * This function sets the registers on the virtual CPU struct to their + * architecturally defined reset values, except for registers whose reset is + * deferred until kvm_arm_vcpu_finalize(). + * + * Note: This function can be called from two paths: The KVM_ARM_VCPU_INIT + * ioctl or as part of handling a request issued by another VCPU in the PSCI + * handling code. In the first case, the VCPU will not be loaded, and in the + * second case the VCPU will be loaded. Because this function operates purely + * on the memory-backed values of system registers, we want to do a full put if + * we were loaded (handling a request) and load the values back at the end of + * the function. Otherwise we leave the state alone. In both cases, we + * disable preemption around the vcpu reset as we would otherwise race with + * preempt notifiers which also call put/load. + */ +int kvm_reset_vcpu(struct kvm_vcpu *vcpu) +{ + struct vcpu_reset_state reset_state; + int ret; + bool loaded; + u32 pstate; + + mutex_lock(&vcpu->kvm->lock); + ret = kvm_set_vm_width(vcpu); + if (!ret) { + reset_state = vcpu->arch.reset_state; + WRITE_ONCE(vcpu->arch.reset_state.reset, false); + } + mutex_unlock(&vcpu->kvm->lock); + + if (ret) + return ret; + + /* Reset PMU outside of the non-preemptible section */ + kvm_pmu_vcpu_reset(vcpu); + + preempt_disable(); + loaded = (vcpu->cpu != -1); + if (loaded) + kvm_arch_vcpu_put(vcpu); + + if (!kvm_arm_vcpu_sve_finalized(vcpu)) { + if (test_bit(KVM_ARM_VCPU_SVE, vcpu->arch.features)) { + ret = kvm_vcpu_enable_sve(vcpu); + if (ret) + goto out; + } + } else { + kvm_vcpu_reset_sve(vcpu); + } + + if (test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) || + test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features)) { + if (kvm_vcpu_enable_ptrauth(vcpu)) { + ret = -EINVAL; + goto out; + } + } + + switch (vcpu->arch.target) { + default: + if (vcpu_el1_is_32bit(vcpu)) { + pstate = VCPU_RESET_PSTATE_SVC; + } else { + pstate = VCPU_RESET_PSTATE_EL1; + } + + if (kvm_vcpu_has_pmu(vcpu) && !kvm_arm_support_pmu_v3()) { + ret = -EINVAL; + goto out; + } + break; + } + + /* Reset core registers */ + memset(vcpu_gp_regs(vcpu), 0, sizeof(*vcpu_gp_regs(vcpu))); + memset(&vcpu->arch.ctxt.fp_regs, 0, sizeof(vcpu->arch.ctxt.fp_regs)); + vcpu->arch.ctxt.spsr_abt = 0; + vcpu->arch.ctxt.spsr_und = 0; + vcpu->arch.ctxt.spsr_irq = 0; + vcpu->arch.ctxt.spsr_fiq = 0; + vcpu_gp_regs(vcpu)->pstate = pstate; + + /* Reset system registers */ + kvm_reset_sys_regs(vcpu); + + /* + * Additional reset state handling that PSCI may have imposed on us. + * Must be done after all the sys_reg reset. + */ + if (reset_state.reset) { + unsigned long target_pc = reset_state.pc; + + /* Gracefully handle Thumb2 entry point */ + if (vcpu_mode_is_32bit(vcpu) && (target_pc & 1)) { + target_pc &= ~1UL; + vcpu_set_thumb(vcpu); + } + + /* Propagate caller endianness */ + if (reset_state.be) + kvm_vcpu_set_be(vcpu); + + *vcpu_pc(vcpu) = target_pc; + vcpu_set_reg(vcpu, 0, reset_state.r0); + } + + /* Reset timer */ + ret = kvm_timer_vcpu_reset(vcpu); +out: + if (loaded) + kvm_arch_vcpu_load(vcpu, smp_processor_id()); + preempt_enable(); + return ret; +} + +u32 get_kvm_ipa_limit(void) +{ + return kvm_ipa_limit; +} + +int kvm_set_ipa_limit(void) +{ + unsigned int parange; + u64 mmfr0; + + mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); + parange = cpuid_feature_extract_unsigned_field(mmfr0, + ID_AA64MMFR0_EL1_PARANGE_SHIFT); + /* + * IPA size beyond 48 bits could not be supported + * on either 4K or 16K page size. Hence let's cap + * it to 48 bits, in case it's reported as larger + * on the system. + */ + if (PAGE_SIZE != SZ_64K) + parange = min(parange, (unsigned int)ID_AA64MMFR0_EL1_PARANGE_48); + + /* + * Check with ARMv8.5-GTG that our PAGE_SIZE is supported at + * Stage-2. If not, things will stop very quickly. + */ + switch (cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_TGRAN_2_SHIFT)) { + case ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_NONE: + kvm_err("PAGE_SIZE not supported at Stage-2, giving up\n"); + return -EINVAL; + case ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_DEFAULT: + kvm_debug("PAGE_SIZE supported at Stage-2 (default)\n"); + break; + case ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_MIN ... ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_MAX: + kvm_debug("PAGE_SIZE supported at Stage-2 (advertised)\n"); + break; + default: + kvm_err("Unsupported value for TGRAN_2, giving up\n"); + return -EINVAL; + } + + kvm_ipa_limit = id_aa64mmfr0_parange_to_phys_shift(parange); + kvm_info("IPA Size Limit: %d bits%s\n", kvm_ipa_limit, + ((kvm_ipa_limit < KVM_PHYS_SHIFT) ? + " (Reduced IPA size, limited VM/VMM compatibility)" : "")); + + return 0; +} -- cgit v1.2.3