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/powerpc/kvm/e500_emulate.c | 452 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 452 insertions(+) create mode 100644 arch/powerpc/kvm/e500_emulate.c (limited to 'arch/powerpc/kvm/e500_emulate.c') diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c new file mode 100644 index 000000000..051102d50 --- /dev/null +++ b/arch/powerpc/kvm/e500_emulate.c @@ -0,0 +1,452 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2008-2011 Freescale Semiconductor, Inc. All rights reserved. + * + * Author: Yu Liu, + * + * Description: + * This file is derived from arch/powerpc/kvm/44x_emulate.c, + * by Hollis Blanchard . + */ + +#include +#include +#include +#include + +#include "booke.h" +#include "e500.h" + +#define XOP_DCBTLS 166 +#define XOP_MSGSND 206 +#define XOP_MSGCLR 238 +#define XOP_MFTMR 366 +#define XOP_TLBIVAX 786 +#define XOP_TLBSX 914 +#define XOP_TLBRE 946 +#define XOP_TLBWE 978 +#define XOP_TLBILX 18 +#define XOP_EHPRIV 270 + +#ifdef CONFIG_KVM_E500MC +static int dbell2prio(ulong param) +{ + int msg = param & PPC_DBELL_TYPE_MASK; + int prio = -1; + + switch (msg) { + case PPC_DBELL_TYPE(PPC_DBELL): + prio = BOOKE_IRQPRIO_DBELL; + break; + case PPC_DBELL_TYPE(PPC_DBELL_CRIT): + prio = BOOKE_IRQPRIO_DBELL_CRIT; + break; + default: + break; + } + + return prio; +} + +static int kvmppc_e500_emul_msgclr(struct kvm_vcpu *vcpu, int rb) +{ + ulong param = vcpu->arch.regs.gpr[rb]; + int prio = dbell2prio(param); + + if (prio < 0) + return EMULATE_FAIL; + + clear_bit(prio, &vcpu->arch.pending_exceptions); + return EMULATE_DONE; +} + +static int kvmppc_e500_emul_msgsnd(struct kvm_vcpu *vcpu, int rb) +{ + ulong param = vcpu->arch.regs.gpr[rb]; + int prio = dbell2prio(rb); + int pir = param & PPC_DBELL_PIR_MASK; + unsigned long i; + struct kvm_vcpu *cvcpu; + + if (prio < 0) + return EMULATE_FAIL; + + kvm_for_each_vcpu(i, cvcpu, vcpu->kvm) { + int cpir = cvcpu->arch.shared->pir; + if ((param & PPC_DBELL_MSG_BRDCAST) || (cpir == pir)) { + set_bit(prio, &cvcpu->arch.pending_exceptions); + kvm_vcpu_kick(cvcpu); + } + } + + return EMULATE_DONE; +} +#endif + +static int kvmppc_e500_emul_ehpriv(struct kvm_vcpu *vcpu, + unsigned int inst, int *advance) +{ + int emulated = EMULATE_DONE; + + switch (get_oc(inst)) { + case EHPRIV_OC_DEBUG: + vcpu->run->exit_reason = KVM_EXIT_DEBUG; + vcpu->run->debug.arch.address = vcpu->arch.regs.nip; + vcpu->run->debug.arch.status = 0; + kvmppc_account_exit(vcpu, DEBUG_EXITS); + emulated = EMULATE_EXIT_USER; + *advance = 0; + break; + default: + emulated = EMULATE_FAIL; + } + return emulated; +} + +static int kvmppc_e500_emul_dcbtls(struct kvm_vcpu *vcpu) +{ + struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); + + /* Always fail to lock the cache */ + vcpu_e500->l1csr0 |= L1CSR0_CUL; + return EMULATE_DONE; +} + +static int kvmppc_e500_emul_mftmr(struct kvm_vcpu *vcpu, unsigned int inst, + int rt) +{ + /* Expose one thread per vcpu */ + if (get_tmrn(inst) == TMRN_TMCFG0) { + kvmppc_set_gpr(vcpu, rt, + 1 | (1 << TMRN_TMCFG0_NATHRD_SHIFT)); + return EMULATE_DONE; + } + + return EMULATE_FAIL; +} + +int kvmppc_core_emulate_op_e500(struct kvm_vcpu *vcpu, + unsigned int inst, int *advance) +{ + int emulated = EMULATE_DONE; + int ra = get_ra(inst); + int rb = get_rb(inst); + int rt = get_rt(inst); + gva_t ea; + + switch (get_op(inst)) { + case 31: + switch (get_xop(inst)) { + + case XOP_DCBTLS: + emulated = kvmppc_e500_emul_dcbtls(vcpu); + break; + +#ifdef CONFIG_KVM_E500MC + case XOP_MSGSND: + emulated = kvmppc_e500_emul_msgsnd(vcpu, rb); + break; + + case XOP_MSGCLR: + emulated = kvmppc_e500_emul_msgclr(vcpu, rb); + break; +#endif + + case XOP_TLBRE: + emulated = kvmppc_e500_emul_tlbre(vcpu); + break; + + case XOP_TLBWE: + emulated = kvmppc_e500_emul_tlbwe(vcpu); + break; + + case XOP_TLBSX: + ea = kvmppc_get_ea_indexed(vcpu, ra, rb); + emulated = kvmppc_e500_emul_tlbsx(vcpu, ea); + break; + + case XOP_TLBILX: { + int type = rt & 0x3; + ea = kvmppc_get_ea_indexed(vcpu, ra, rb); + emulated = kvmppc_e500_emul_tlbilx(vcpu, type, ea); + break; + } + + case XOP_TLBIVAX: + ea = kvmppc_get_ea_indexed(vcpu, ra, rb); + emulated = kvmppc_e500_emul_tlbivax(vcpu, ea); + break; + + case XOP_MFTMR: + emulated = kvmppc_e500_emul_mftmr(vcpu, inst, rt); + break; + + case XOP_EHPRIV: + emulated = kvmppc_e500_emul_ehpriv(vcpu, inst, advance); + break; + + default: + emulated = EMULATE_FAIL; + } + + break; + + default: + emulated = EMULATE_FAIL; + } + + if (emulated == EMULATE_FAIL) + emulated = kvmppc_booke_emulate_op(vcpu, inst, advance); + + return emulated; +} + +int kvmppc_core_emulate_mtspr_e500(struct kvm_vcpu *vcpu, int sprn, ulong spr_val) +{ + struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); + int emulated = EMULATE_DONE; + + switch (sprn) { +#ifndef CONFIG_KVM_BOOKE_HV + case SPRN_PID: + kvmppc_set_pid(vcpu, spr_val); + break; + case SPRN_PID1: + if (spr_val != 0) + return EMULATE_FAIL; + vcpu_e500->pid[1] = spr_val; + break; + case SPRN_PID2: + if (spr_val != 0) + return EMULATE_FAIL; + vcpu_e500->pid[2] = spr_val; + break; + case SPRN_MAS0: + vcpu->arch.shared->mas0 = spr_val; + break; + case SPRN_MAS1: + vcpu->arch.shared->mas1 = spr_val; + break; + case SPRN_MAS2: + vcpu->arch.shared->mas2 = spr_val; + break; + case SPRN_MAS3: + vcpu->arch.shared->mas7_3 &= ~(u64)0xffffffff; + vcpu->arch.shared->mas7_3 |= spr_val; + break; + case SPRN_MAS4: + vcpu->arch.shared->mas4 = spr_val; + break; + case SPRN_MAS6: + vcpu->arch.shared->mas6 = spr_val; + break; + case SPRN_MAS7: + vcpu->arch.shared->mas7_3 &= (u64)0xffffffff; + vcpu->arch.shared->mas7_3 |= (u64)spr_val << 32; + break; +#endif + case SPRN_L1CSR0: + vcpu_e500->l1csr0 = spr_val; + vcpu_e500->l1csr0 &= ~(L1CSR0_DCFI | L1CSR0_CLFC); + break; + case SPRN_L1CSR1: + vcpu_e500->l1csr1 = spr_val; + vcpu_e500->l1csr1 &= ~(L1CSR1_ICFI | L1CSR1_ICLFR); + break; + case SPRN_HID0: + vcpu_e500->hid0 = spr_val; + break; + case SPRN_HID1: + vcpu_e500->hid1 = spr_val; + break; + + case SPRN_MMUCSR0: + emulated = kvmppc_e500_emul_mt_mmucsr0(vcpu_e500, + spr_val); + break; + + case SPRN_PWRMGTCR0: + /* + * Guest relies on host power management configurations + * Treat the request as a general store + */ + vcpu->arch.pwrmgtcr0 = spr_val; + break; + + case SPRN_BUCSR: + /* + * If we are here, it means that we have already flushed the + * branch predictor, so just return to guest. + */ + break; + + /* extra exceptions */ +#ifdef CONFIG_SPE_POSSIBLE + case SPRN_IVOR32: + vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL] = spr_val; + break; + case SPRN_IVOR33: + vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA] = spr_val; + break; + case SPRN_IVOR34: + vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND] = spr_val; + break; +#endif +#ifdef CONFIG_ALTIVEC + case SPRN_IVOR32: + vcpu->arch.ivor[BOOKE_IRQPRIO_ALTIVEC_UNAVAIL] = spr_val; + break; + case SPRN_IVOR33: + vcpu->arch.ivor[BOOKE_IRQPRIO_ALTIVEC_ASSIST] = spr_val; + break; +#endif + case SPRN_IVOR35: + vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR] = spr_val; + break; +#ifdef CONFIG_KVM_BOOKE_HV + case SPRN_IVOR36: + vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL] = spr_val; + break; + case SPRN_IVOR37: + vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL_CRIT] = spr_val; + break; +#endif + default: + emulated = kvmppc_booke_emulate_mtspr(vcpu, sprn, spr_val); + } + + return emulated; +} + +int kvmppc_core_emulate_mfspr_e500(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val) +{ + struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); + int emulated = EMULATE_DONE; + + switch (sprn) { +#ifndef CONFIG_KVM_BOOKE_HV + case SPRN_PID: + *spr_val = vcpu_e500->pid[0]; + break; + case SPRN_PID1: + *spr_val = vcpu_e500->pid[1]; + break; + case SPRN_PID2: + *spr_val = vcpu_e500->pid[2]; + break; + case SPRN_MAS0: + *spr_val = vcpu->arch.shared->mas0; + break; + case SPRN_MAS1: + *spr_val = vcpu->arch.shared->mas1; + break; + case SPRN_MAS2: + *spr_val = vcpu->arch.shared->mas2; + break; + case SPRN_MAS3: + *spr_val = (u32)vcpu->arch.shared->mas7_3; + break; + case SPRN_MAS4: + *spr_val = vcpu->arch.shared->mas4; + break; + case SPRN_MAS6: + *spr_val = vcpu->arch.shared->mas6; + break; + case SPRN_MAS7: + *spr_val = vcpu->arch.shared->mas7_3 >> 32; + break; +#endif + case SPRN_DECAR: + *spr_val = vcpu->arch.decar; + break; + case SPRN_TLB0CFG: + *spr_val = vcpu->arch.tlbcfg[0]; + break; + case SPRN_TLB1CFG: + *spr_val = vcpu->arch.tlbcfg[1]; + break; + case SPRN_TLB0PS: + if (!has_feature(vcpu, VCPU_FTR_MMU_V2)) + return EMULATE_FAIL; + *spr_val = vcpu->arch.tlbps[0]; + break; + case SPRN_TLB1PS: + if (!has_feature(vcpu, VCPU_FTR_MMU_V2)) + return EMULATE_FAIL; + *spr_val = vcpu->arch.tlbps[1]; + break; + case SPRN_L1CSR0: + *spr_val = vcpu_e500->l1csr0; + break; + case SPRN_L1CSR1: + *spr_val = vcpu_e500->l1csr1; + break; + case SPRN_HID0: + *spr_val = vcpu_e500->hid0; + break; + case SPRN_HID1: + *spr_val = vcpu_e500->hid1; + break; + case SPRN_SVR: + *spr_val = vcpu_e500->svr; + break; + + case SPRN_MMUCSR0: + *spr_val = 0; + break; + + case SPRN_MMUCFG: + *spr_val = vcpu->arch.mmucfg; + break; + case SPRN_EPTCFG: + if (!has_feature(vcpu, VCPU_FTR_MMU_V2)) + return EMULATE_FAIL; + /* + * Legacy Linux guests access EPTCFG register even if the E.PT + * category is disabled in the VM. Give them a chance to live. + */ + *spr_val = vcpu->arch.eptcfg; + break; + + case SPRN_PWRMGTCR0: + *spr_val = vcpu->arch.pwrmgtcr0; + break; + + /* extra exceptions */ +#ifdef CONFIG_SPE_POSSIBLE + case SPRN_IVOR32: + *spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL]; + break; + case SPRN_IVOR33: + *spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA]; + break; + case SPRN_IVOR34: + *spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND]; + break; +#endif +#ifdef CONFIG_ALTIVEC + case SPRN_IVOR32: + *spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_ALTIVEC_UNAVAIL]; + break; + case SPRN_IVOR33: + *spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_ALTIVEC_ASSIST]; + break; +#endif + case SPRN_IVOR35: + *spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR]; + break; +#ifdef CONFIG_KVM_BOOKE_HV + case SPRN_IVOR36: + *spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL]; + break; + case SPRN_IVOR37: + *spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL_CRIT]; + break; +#endif + default: + emulated = kvmppc_booke_emulate_mfspr(vcpu, sprn, spr_val); + } + + return emulated; +} + -- cgit v1.2.3