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/kvm/lapic.h | 277 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 277 insertions(+) create mode 100644 arch/x86/kvm/lapic.h (limited to 'arch/x86/kvm/lapic.h') diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h new file mode 100644 index 000000000..58c3242fc --- /dev/null +++ b/arch/x86/kvm/lapic.h @@ -0,0 +1,277 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __KVM_X86_LAPIC_H +#define __KVM_X86_LAPIC_H + +#include + +#include + +#include "hyperv.h" +#include "smm.h" + +#define KVM_APIC_INIT 0 +#define KVM_APIC_SIPI 1 + +#define APIC_SHORT_MASK 0xc0000 +#define APIC_DEST_NOSHORT 0x0 +#define APIC_DEST_MASK 0x800 + +#define APIC_BUS_CYCLE_NS 1 +#define APIC_BUS_FREQUENCY (1000000000ULL / APIC_BUS_CYCLE_NS) + +#define APIC_BROADCAST 0xFF +#define X2APIC_BROADCAST 0xFFFFFFFFul + +enum lapic_mode { + LAPIC_MODE_DISABLED = 0, + LAPIC_MODE_INVALID = X2APIC_ENABLE, + LAPIC_MODE_XAPIC = MSR_IA32_APICBASE_ENABLE, + LAPIC_MODE_X2APIC = MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE, +}; + +enum lapic_lvt_entry { + LVT_TIMER, + LVT_THERMAL_MONITOR, + LVT_PERFORMANCE_COUNTER, + LVT_LINT0, + LVT_LINT1, + LVT_ERROR, + LVT_CMCI, + + KVM_APIC_MAX_NR_LVT_ENTRIES, +}; + +#define APIC_LVTx(x) ((x) == LVT_CMCI ? APIC_LVTCMCI : APIC_LVTT + 0x10 * (x)) + +struct kvm_timer { + struct hrtimer timer; + s64 period; /* unit: ns */ + ktime_t target_expiration; + u32 timer_mode; + u32 timer_mode_mask; + u64 tscdeadline; + u64 expired_tscdeadline; + u32 timer_advance_ns; + atomic_t pending; /* accumulated triggered timers */ + bool hv_timer_in_use; +}; + +struct kvm_lapic { + unsigned long base_address; + struct kvm_io_device dev; + struct kvm_timer lapic_timer; + u32 divide_count; + struct kvm_vcpu *vcpu; + bool apicv_active; + bool sw_enabled; + bool irr_pending; + bool lvt0_in_nmi_mode; + /* Number of bits set in ISR. */ + s16 isr_count; + /* The highest vector set in ISR; if -1 - invalid, must scan ISR. */ + int highest_isr_cache; + /** + * APIC register page. The layout matches the register layout seen by + * the guest 1:1, because it is accessed by the vmx microcode. + * Note: Only one register, the TPR, is used by the microcode. + */ + void *regs; + gpa_t vapic_addr; + struct gfn_to_hva_cache vapic_cache; + unsigned long pending_events; + unsigned int sipi_vector; + int nr_lvt_entries; +}; + +struct dest_map; + +int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns); +void kvm_free_lapic(struct kvm_vcpu *vcpu); + +int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu); +int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu); +int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu); +int kvm_apic_accept_events(struct kvm_vcpu *vcpu); +void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event); +u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu); +void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8); +void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu); +void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value); +u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu); +void kvm_recalculate_apic_map(struct kvm *kvm); +void kvm_apic_set_version(struct kvm_vcpu *vcpu); +void kvm_apic_after_set_mcg_cap(struct kvm_vcpu *vcpu); +bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, + int shorthand, unsigned int dest, int dest_mode); +int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2); +void kvm_apic_clear_irr(struct kvm_vcpu *vcpu, int vec); +bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr); +bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir, int *max_irr); +void kvm_apic_update_ppr(struct kvm_vcpu *vcpu); +int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, + struct dest_map *dest_map); +int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type); +void kvm_apic_update_apicv(struct kvm_vcpu *vcpu); + +bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, + struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map); +void kvm_apic_send_ipi(struct kvm_lapic *apic, u32 icr_low, u32 icr_high); + +u64 kvm_get_apic_base(struct kvm_vcpu *vcpu); +int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info); +int kvm_apic_get_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s); +int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s); +enum lapic_mode kvm_get_apic_mode(struct kvm_vcpu *vcpu); +int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu); + +u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu); +void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data); + +void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset); +void kvm_apic_set_eoi_accelerated(struct kvm_vcpu *vcpu, int vector); + +int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr); +void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu); +void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu); + +int kvm_x2apic_icr_write(struct kvm_lapic *apic, u64 data); +int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data); +int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data); + +int kvm_hv_vapic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data); +int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data); + +int kvm_lapic_set_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len); +void kvm_lapic_exit(void); + +#define VEC_POS(v) ((v) & (32 - 1)) +#define REG_POS(v) (((v) >> 5) << 4) + +static inline void kvm_lapic_clear_vector(int vec, void *bitmap) +{ + clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); +} + +static inline void kvm_lapic_set_vector(int vec, void *bitmap) +{ + set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); +} + +static inline void kvm_lapic_set_irr(int vec, struct kvm_lapic *apic) +{ + kvm_lapic_set_vector(vec, apic->regs + APIC_IRR); + /* + * irr_pending must be true if any interrupt is pending; set it after + * APIC_IRR to avoid race with apic_clear_irr + */ + apic->irr_pending = true; +} + +static inline u32 __kvm_lapic_get_reg(char *regs, int reg_off) +{ + return *((u32 *) (regs + reg_off)); +} + +static inline u32 kvm_lapic_get_reg(struct kvm_lapic *apic, int reg_off) +{ + return __kvm_lapic_get_reg(apic->regs, reg_off); +} + +DECLARE_STATIC_KEY_FALSE(kvm_has_noapic_vcpu); + +static inline bool lapic_in_kernel(struct kvm_vcpu *vcpu) +{ + if (static_branch_unlikely(&kvm_has_noapic_vcpu)) + return vcpu->arch.apic; + return true; +} + +extern struct static_key_false_deferred apic_hw_disabled; + +static inline bool kvm_apic_hw_enabled(struct kvm_lapic *apic) +{ + if (static_branch_unlikely(&apic_hw_disabled.key)) + return apic->vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE; + return true; +} + +extern struct static_key_false_deferred apic_sw_disabled; + +static inline bool kvm_apic_sw_enabled(struct kvm_lapic *apic) +{ + if (static_branch_unlikely(&apic_sw_disabled.key)) + return apic->sw_enabled; + return true; +} + +static inline bool kvm_apic_present(struct kvm_vcpu *vcpu) +{ + return lapic_in_kernel(vcpu) && kvm_apic_hw_enabled(vcpu->arch.apic); +} + +static inline int kvm_lapic_enabled(struct kvm_vcpu *vcpu) +{ + return kvm_apic_present(vcpu) && kvm_apic_sw_enabled(vcpu->arch.apic); +} + +static inline int apic_x2apic_mode(struct kvm_lapic *apic) +{ + return apic->vcpu->arch.apic_base & X2APIC_ENABLE; +} + +static inline bool kvm_vcpu_apicv_active(struct kvm_vcpu *vcpu) +{ + return lapic_in_kernel(vcpu) && vcpu->arch.apic->apicv_active; +} + +static inline bool kvm_apic_has_pending_init_or_sipi(struct kvm_vcpu *vcpu) +{ + return lapic_in_kernel(vcpu) && vcpu->arch.apic->pending_events; +} + +static inline bool kvm_apic_init_sipi_allowed(struct kvm_vcpu *vcpu) +{ + return !is_smm(vcpu) && + !static_call(kvm_x86_apic_init_signal_blocked)(vcpu); +} + +static inline bool kvm_lowest_prio_delivery(struct kvm_lapic_irq *irq) +{ + return (irq->delivery_mode == APIC_DM_LOWEST || + irq->msi_redir_hint); +} + +static inline int kvm_lapic_latched_init(struct kvm_vcpu *vcpu) +{ + return lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); +} + +bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector); + +void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu); + +void kvm_bitmap_or_dest_vcpus(struct kvm *kvm, struct kvm_lapic_irq *irq, + unsigned long *vcpu_bitmap); + +bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq, + struct kvm_vcpu **dest_vcpu); +int kvm_vector_to_index(u32 vector, u32 dest_vcpus, + const unsigned long *bitmap, u32 bitmap_size); +void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu); +void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu); +void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu); +bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu); +void kvm_lapic_restart_hv_timer(struct kvm_vcpu *vcpu); +bool kvm_can_use_hv_timer(struct kvm_vcpu *vcpu); + +static inline enum lapic_mode kvm_apic_mode(u64 apic_base) +{ + return apic_base & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE); +} + +static inline u8 kvm_xapic_id(struct kvm_lapic *apic) +{ + return kvm_lapic_get_reg(apic, APIC_ID) >> 24; +} + +#endif -- cgit v1.2.3