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/book3s_interrupts.S | 239 +++++++++++++++++++++++++++++++++++ 1 file changed, 239 insertions(+) create mode 100644 arch/powerpc/kvm/book3s_interrupts.S (limited to 'arch/powerpc/kvm/book3s_interrupts.S') diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S new file mode 100644 index 000000000..f4bec2fc5 --- /dev/null +++ b/arch/powerpc/kvm/book3s_interrupts.S @@ -0,0 +1,239 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * + * Copyright SUSE Linux Products GmbH 2009 + * + * Authors: Alexander Graf + */ + +#include +#include +#include +#include +#include +#include +#include + +#if defined(CONFIG_PPC_BOOK3S_64) +#ifdef CONFIG_PPC64_ELF_ABI_V2 +#define FUNC(name) name +#else +#define FUNC(name) GLUE(.,name) +#endif +#define GET_SHADOW_VCPU(reg) addi reg, r13, PACA_SVCPU + +#elif defined(CONFIG_PPC_BOOK3S_32) +#define FUNC(name) name +#define GET_SHADOW_VCPU(reg) lwz reg, (THREAD + THREAD_KVM_SVCPU)(r2) + +#endif /* CONFIG_PPC_BOOK3S_64 */ + +#define VCPU_LOAD_NVGPRS(vcpu) \ + PPC_LL r14, VCPU_GPR(R14)(vcpu); \ + PPC_LL r15, VCPU_GPR(R15)(vcpu); \ + PPC_LL r16, VCPU_GPR(R16)(vcpu); \ + PPC_LL r17, VCPU_GPR(R17)(vcpu); \ + PPC_LL r18, VCPU_GPR(R18)(vcpu); \ + PPC_LL r19, VCPU_GPR(R19)(vcpu); \ + PPC_LL r20, VCPU_GPR(R20)(vcpu); \ + PPC_LL r21, VCPU_GPR(R21)(vcpu); \ + PPC_LL r22, VCPU_GPR(R22)(vcpu); \ + PPC_LL r23, VCPU_GPR(R23)(vcpu); \ + PPC_LL r24, VCPU_GPR(R24)(vcpu); \ + PPC_LL r25, VCPU_GPR(R25)(vcpu); \ + PPC_LL r26, VCPU_GPR(R26)(vcpu); \ + PPC_LL r27, VCPU_GPR(R27)(vcpu); \ + PPC_LL r28, VCPU_GPR(R28)(vcpu); \ + PPC_LL r29, VCPU_GPR(R29)(vcpu); \ + PPC_LL r30, VCPU_GPR(R30)(vcpu); \ + PPC_LL r31, VCPU_GPR(R31)(vcpu); \ + +/***************************************************************************** + * * + * Guest entry / exit code that is in kernel module memory (highmem) * + * * + ****************************************************************************/ + +/* Registers: + * r3: vcpu pointer + */ +_GLOBAL(__kvmppc_vcpu_run) + +kvm_start_entry: + /* Write correct stack frame */ + mflr r0 + PPC_STL r0,PPC_LR_STKOFF(r1) + + /* Save host state to the stack */ + PPC_STLU r1, -SWITCH_FRAME_SIZE(r1) + + /* Save r3 (vcpu) */ + SAVE_GPR(3, r1) + + /* Save non-volatile registers (r14 - r31) */ + SAVE_NVGPRS(r1) + + /* Save CR */ + mfcr r14 + stw r14, _CCR(r1) + + /* Save LR */ + PPC_STL r0, _LINK(r1) + + /* Load non-volatile guest state from the vcpu */ + VCPU_LOAD_NVGPRS(r3) + +kvm_start_lightweight: + /* Copy registers into shadow vcpu so we can access them in real mode */ + bl FUNC(kvmppc_copy_to_svcpu) + nop + REST_GPR(3, r1) + +#ifdef CONFIG_PPC_BOOK3S_64 + /* Get the dcbz32 flag */ + PPC_LL r0, VCPU_HFLAGS(r3) + rldicl r0, r0, 0, 63 /* r3 &= 1 */ + stb r0, HSTATE_RESTORE_HID5(r13) + + /* Load up guest SPRG3 value, since it's user readable */ + lbz r4, VCPU_SHAREDBE(r3) + cmpwi r4, 0 + ld r5, VCPU_SHARED(r3) + beq sprg3_little_endian +sprg3_big_endian: +#ifdef __BIG_ENDIAN__ + ld r4, VCPU_SHARED_SPRG3(r5) +#else + addi r5, r5, VCPU_SHARED_SPRG3 + ldbrx r4, 0, r5 +#endif + b after_sprg3_load +sprg3_little_endian: +#ifdef __LITTLE_ENDIAN__ + ld r4, VCPU_SHARED_SPRG3(r5) +#else + addi r5, r5, VCPU_SHARED_SPRG3 + ldbrx r4, 0, r5 +#endif + +after_sprg3_load: + mtspr SPRN_SPRG3, r4 +#endif /* CONFIG_PPC_BOOK3S_64 */ + + PPC_LL r4, VCPU_SHADOW_MSR(r3) /* get shadow_msr */ + + /* Jump to segment patching handler and into our guest */ + bl FUNC(kvmppc_entry_trampoline) + nop + +/* + * This is the handler in module memory. It gets jumped at from the + * lowmem trampoline code, so it's basically the guest exit code. + * + */ + + /* + * Register usage at this point: + * + * R1 = host R1 + * R2 = host R2 + * R12 = exit handler id + * R13 = PACA + * SVCPU.* = guest * + * MSR.EE = 1 + * + */ + + PPC_LL r3, GPR3(r1) /* vcpu pointer */ + + /* + * kvmppc_copy_from_svcpu can clobber volatile registers, save + * the exit handler id to the vcpu and restore it from there later. + */ + stw r12, VCPU_TRAP(r3) + + /* Transfer reg values from shadow vcpu back to vcpu struct */ + + bl FUNC(kvmppc_copy_from_svcpu) + nop + +#ifdef CONFIG_PPC_BOOK3S_64 + /* + * Reload kernel SPRG3 value. + * No need to save guest value as usermode can't modify SPRG3. + */ + ld r3, PACA_SPRG_VDSO(r13) + mtspr SPRN_SPRG_VDSO_WRITE, r3 +#endif /* CONFIG_PPC_BOOK3S_64 */ + + /* R7 = vcpu */ + PPC_LL r7, GPR3(r1) + + PPC_STL r14, VCPU_GPR(R14)(r7) + PPC_STL r15, VCPU_GPR(R15)(r7) + PPC_STL r16, VCPU_GPR(R16)(r7) + PPC_STL r17, VCPU_GPR(R17)(r7) + PPC_STL r18, VCPU_GPR(R18)(r7) + PPC_STL r19, VCPU_GPR(R19)(r7) + PPC_STL r20, VCPU_GPR(R20)(r7) + PPC_STL r21, VCPU_GPR(R21)(r7) + PPC_STL r22, VCPU_GPR(R22)(r7) + PPC_STL r23, VCPU_GPR(R23)(r7) + PPC_STL r24, VCPU_GPR(R24)(r7) + PPC_STL r25, VCPU_GPR(R25)(r7) + PPC_STL r26, VCPU_GPR(R26)(r7) + PPC_STL r27, VCPU_GPR(R27)(r7) + PPC_STL r28, VCPU_GPR(R28)(r7) + PPC_STL r29, VCPU_GPR(R29)(r7) + PPC_STL r30, VCPU_GPR(R30)(r7) + PPC_STL r31, VCPU_GPR(R31)(r7) + + /* Pass the exit number as 2nd argument to kvmppc_handle_exit */ + lwz r4, VCPU_TRAP(r7) + + /* Restore r3 (vcpu) */ + REST_GPR(3, r1) + bl FUNC(kvmppc_handle_exit_pr) + + /* If RESUME_GUEST, get back in the loop */ + cmpwi r3, RESUME_GUEST + beq kvm_loop_lightweight + + cmpwi r3, RESUME_GUEST_NV + beq kvm_loop_heavyweight + +kvm_exit_loop: + + PPC_LL r4, _LINK(r1) + mtlr r4 + + lwz r14, _CCR(r1) + mtcr r14 + + /* Restore non-volatile host registers (r14 - r31) */ + REST_NVGPRS(r1) + + addi r1, r1, SWITCH_FRAME_SIZE + blr + +kvm_loop_heavyweight: + + PPC_LL r4, _LINK(r1) + PPC_STL r4, (PPC_LR_STKOFF + SWITCH_FRAME_SIZE)(r1) + + /* Load vcpu */ + REST_GPR(3, r1) + + /* Load non-volatile guest state from the vcpu */ + VCPU_LOAD_NVGPRS(r3) + + /* Jump back into the beginning of this function */ + b kvm_start_lightweight + +kvm_loop_lightweight: + + /* We'll need the vcpu pointer */ + REST_GPR(3, r1) + + /* Jump back into the beginning of this function */ + b kvm_start_lightweight -- cgit v1.2.3