Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

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().
  ...

1 files changed, 350 insertions, 0 deletions

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
new file mode 100644
index 000000000..43c3bc0f9
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -0,0 +1,350 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#ifndef __ARM_KVM_ASM_H__
+#define __ARM_KVM_ASM_H__
+
+#include <asm/hyp_image.h>
+#include <asm/insn.h>
+#include <asm/virt.h>
+
+#define ARM_EXIT_WITH_SERROR_BIT  31
+#define ARM_EXCEPTION_CODE(x)	  ((x) & ~(1U << ARM_EXIT_WITH_SERROR_BIT))
+#define ARM_EXCEPTION_IS_TRAP(x)  (ARM_EXCEPTION_CODE((x)) == ARM_EXCEPTION_TRAP)
+#define ARM_SERROR_PENDING(x)	  !!((x) & (1U << ARM_EXIT_WITH_SERROR_BIT))
+
+#define ARM_EXCEPTION_IRQ	  0
+#define ARM_EXCEPTION_EL1_SERROR  1
+#define ARM_EXCEPTION_TRAP	  2
+#define ARM_EXCEPTION_IL	  3
+/* The hyp-stub will return this for any kvm_call_hyp() call */
+#define ARM_EXCEPTION_HYP_GONE	  HVC_STUB_ERR
+
+#define kvm_arm_exception_type					\
+	{ARM_EXCEPTION_IRQ,		"IRQ"		},	\
+	{ARM_EXCEPTION_EL1_SERROR, 	"SERROR"	},	\
+	{ARM_EXCEPTION_TRAP, 		"TRAP"		},	\
+	{ARM_EXCEPTION_HYP_GONE,	"HYP_GONE"	}
+
+/*
+ * Size of the HYP vectors preamble. kvm_patch_vector_branch() generates code
+ * that jumps over this.
+ */
+#define KVM_VECTOR_PREAMBLE	(2 * AARCH64_INSN_SIZE)
+
+#define KVM_HOST_SMCCC_ID(id)						\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
+			   ARM_SMCCC_SMC_64,				\
+			   ARM_SMCCC_OWNER_VENDOR_HYP,			\
+			   (id))
+
+#define KVM_HOST_SMCCC_FUNC(name) KVM_HOST_SMCCC_ID(__KVM_HOST_SMCCC_FUNC_##name)
+
+#define __KVM_HOST_SMCCC_FUNC___kvm_hyp_init			0
+
+#ifndef __ASSEMBLY__
+
+#include <linux/mm.h>
+
+enum __kvm_host_smccc_func {
+	/* Hypercalls available only prior to pKVM finalisation */
+	/* __KVM_HOST_SMCCC_FUNC___kvm_hyp_init */
+	__KVM_HOST_SMCCC_FUNC___kvm_get_mdcr_el2 = __KVM_HOST_SMCCC_FUNC___kvm_hyp_init + 1,
+	__KVM_HOST_SMCCC_FUNC___pkvm_init,
+	__KVM_HOST_SMCCC_FUNC___pkvm_create_private_mapping,
+	__KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector,
+	__KVM_HOST_SMCCC_FUNC___kvm_enable_ssbs,
+	__KVM_HOST_SMCCC_FUNC___vgic_v3_init_lrs,
+	__KVM_HOST_SMCCC_FUNC___vgic_v3_get_gic_config,
+	__KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize,
+
+	/* Hypercalls available after pKVM finalisation */
+	__KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp,
+	__KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_hyp,
+	__KVM_HOST_SMCCC_FUNC___kvm_adjust_pc,
+	__KVM_HOST_SMCCC_FUNC___kvm_vcpu_run,
+	__KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context,
+	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa,
+	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid,
+	__KVM_HOST_SMCCC_FUNC___kvm_flush_cpu_context,
+	__KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff,
+	__KVM_HOST_SMCCC_FUNC___vgic_v3_read_vmcr,
+	__KVM_HOST_SMCCC_FUNC___vgic_v3_write_vmcr,
+	__KVM_HOST_SMCCC_FUNC___vgic_v3_save_aprs,
+	__KVM_HOST_SMCCC_FUNC___vgic_v3_restore_aprs,
+	__KVM_HOST_SMCCC_FUNC___pkvm_vcpu_init_traps,
+	__KVM_HOST_SMCCC_FUNC___pkvm_init_vm,
+	__KVM_HOST_SMCCC_FUNC___pkvm_init_vcpu,
+	__KVM_HOST_SMCCC_FUNC___pkvm_teardown_vm,
+};
+
+#define DECLARE_KVM_VHE_SYM(sym)	extern char sym[]
+#define DECLARE_KVM_NVHE_SYM(sym)	extern char kvm_nvhe_sym(sym)[]
+
+/*
+ * Define a pair of symbols sharing the same name but one defined in
+ * VHE and the other in nVHE hyp implementations.
+ */
+#define DECLARE_KVM_HYP_SYM(sym)		\
+	DECLARE_KVM_VHE_SYM(sym);		\
+	DECLARE_KVM_NVHE_SYM(sym)
+
+#define DECLARE_KVM_VHE_PER_CPU(type, sym)	\
+	DECLARE_PER_CPU(type, sym)
+#define DECLARE_KVM_NVHE_PER_CPU(type, sym)	\
+	DECLARE_PER_CPU(type, kvm_nvhe_sym(sym))
+
+#define DECLARE_KVM_HYP_PER_CPU(type, sym)	\
+	DECLARE_KVM_VHE_PER_CPU(type, sym);	\
+	DECLARE_KVM_NVHE_PER_CPU(type, sym)
+
+/*
+ * Compute pointer to a symbol defined in nVHE percpu region.
+ * Returns NULL if percpu memory has not been allocated yet.
+ */
+#define this_cpu_ptr_nvhe_sym(sym)	per_cpu_ptr_nvhe_sym(sym, smp_processor_id())
+#define per_cpu_ptr_nvhe_sym(sym, cpu)						\
+	({									\
+		unsigned long base, off;					\
+		base = kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu];		\
+		off = (unsigned long)&CHOOSE_NVHE_SYM(sym) -			\
+		      (unsigned long)&CHOOSE_NVHE_SYM(__per_cpu_start);		\
+		base ? (typeof(CHOOSE_NVHE_SYM(sym))*)(base + off) : NULL;	\
+	})
+
+#if defined(__KVM_NVHE_HYPERVISOR__)
+
+#define CHOOSE_NVHE_SYM(sym)	sym
+#define CHOOSE_HYP_SYM(sym)	CHOOSE_NVHE_SYM(sym)
+
+/* The nVHE hypervisor shouldn't even try to access VHE symbols */
+extern void *__nvhe_undefined_symbol;
+#define CHOOSE_VHE_SYM(sym)		__nvhe_undefined_symbol
+#define this_cpu_ptr_hyp_sym(sym)	(&__nvhe_undefined_symbol)
+#define per_cpu_ptr_hyp_sym(sym, cpu)	(&__nvhe_undefined_symbol)
+
+#elif defined(__KVM_VHE_HYPERVISOR__)
+
+#define CHOOSE_VHE_SYM(sym)	sym
+#define CHOOSE_HYP_SYM(sym)	CHOOSE_VHE_SYM(sym)
+
+/* The VHE hypervisor shouldn't even try to access nVHE symbols */
+extern void *__vhe_undefined_symbol;
+#define CHOOSE_NVHE_SYM(sym)		__vhe_undefined_symbol
+#define this_cpu_ptr_hyp_sym(sym)	(&__vhe_undefined_symbol)
+#define per_cpu_ptr_hyp_sym(sym, cpu)	(&__vhe_undefined_symbol)
+
+#else
+
+/*
+ * BIG FAT WARNINGS:
+ *
+ * - Don't be tempted to change the following is_kernel_in_hyp_mode()
+ *   to has_vhe(). has_vhe() is implemented as a *final* capability,
+ *   while this is used early at boot time, when the capabilities are
+ *   not final yet....
+ *
+ * - Don't let the nVHE hypervisor have access to this, as it will
+ *   pick the *wrong* symbol (yes, it runs at EL2...).
+ */
+#define CHOOSE_HYP_SYM(sym)		(is_kernel_in_hyp_mode()	\
+					   ? CHOOSE_VHE_SYM(sym)	\
+					   : CHOOSE_NVHE_SYM(sym))
+
+#define this_cpu_ptr_hyp_sym(sym)	(is_kernel_in_hyp_mode()	\
+					   ? this_cpu_ptr(&sym)		\
+					   : this_cpu_ptr_nvhe_sym(sym))
+
+#define per_cpu_ptr_hyp_sym(sym, cpu)	(is_kernel_in_hyp_mode()	\
+					   ? per_cpu_ptr(&sym, cpu)	\
+					   : per_cpu_ptr_nvhe_sym(sym, cpu))
+
+#define CHOOSE_VHE_SYM(sym)	sym
+#define CHOOSE_NVHE_SYM(sym)	kvm_nvhe_sym(sym)
+
+#endif
+
+struct kvm_nvhe_init_params {
+	unsigned long mair_el2;
+	unsigned long tcr_el2;
+	unsigned long tpidr_el2;
+	unsigned long stack_hyp_va;
+	unsigned long stack_pa;
+	phys_addr_t pgd_pa;
+	unsigned long hcr_el2;
+	unsigned long vttbr;
+	unsigned long vtcr;
+};
+
+/*
+ * Used by the host in EL1 to dump the nVHE hypervisor backtrace on
+ * hyp_panic() in non-protected mode.
+ *
+ * @stack_base:                 hyp VA of the hyp_stack base.
+ * @overflow_stack_base:        hyp VA of the hyp_overflow_stack base.
+ * @fp:                         hyp FP where the backtrace begins.
+ * @pc:                         hyp PC where the backtrace begins.
+ */
+struct kvm_nvhe_stacktrace_info {
+	unsigned long stack_base;
+	unsigned long overflow_stack_base;
+	unsigned long fp;
+	unsigned long pc;
+};
+
+/* Translate a kernel address @ptr into its equivalent linear mapping */
+#define kvm_ksym_ref(ptr)						\
+	({								\
+		void *val = (ptr);					\
+		if (!is_kernel_in_hyp_mode())				\
+			val = lm_alias((ptr));				\
+		val;							\
+	 })
+#define kvm_ksym_ref_nvhe(sym)	kvm_ksym_ref(kvm_nvhe_sym(sym))
+
+struct kvm;
+struct kvm_vcpu;
+struct kvm_s2_mmu;
+
+DECLARE_KVM_NVHE_SYM(__kvm_hyp_init);
+DECLARE_KVM_HYP_SYM(__kvm_hyp_vector);
+#define __kvm_hyp_init		CHOOSE_NVHE_SYM(__kvm_hyp_init)
+#define __kvm_hyp_vector	CHOOSE_HYP_SYM(__kvm_hyp_vector)
+
+extern unsigned long kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[];
+DECLARE_KVM_NVHE_SYM(__per_cpu_start);
+DECLARE_KVM_NVHE_SYM(__per_cpu_end);
+
+DECLARE_KVM_HYP_SYM(__bp_harden_hyp_vecs);
+#define __bp_harden_hyp_vecs	CHOOSE_HYP_SYM(__bp_harden_hyp_vecs)
+
+extern void __kvm_flush_vm_context(void);
+extern void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu);
+extern void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa,
+				     int level);
+extern void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu);
+
+extern void __kvm_timer_set_cntvoff(u64 cntvoff);
+
+extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
+
+extern void __kvm_adjust_pc(struct kvm_vcpu *vcpu);
+
+extern u64 __vgic_v3_get_gic_config(void);
+extern u64 __vgic_v3_read_vmcr(void);
+extern void __vgic_v3_write_vmcr(u32 vmcr);
+extern void __vgic_v3_init_lrs(void);
+
+extern u64 __kvm_get_mdcr_el2(void);
+
+#define __KVM_EXTABLE(from, to)						\
+	"	.pushsection	__kvm_ex_table, \"a\"\n"		\
+	"	.align		3\n"					\
+	"	.long		(" #from " - .), (" #to " - .)\n"	\
+	"	.popsection\n"
+
+
+#define __kvm_at(at_op, addr)						\
+( { 									\
+	int __kvm_at_err = 0;						\
+	u64 spsr, elr;							\
+	asm volatile(							\
+	"	mrs	%1, spsr_el2\n"					\
+	"	mrs	%2, elr_el2\n"					\
+	"1:	at	"at_op", %3\n"					\
+	"	isb\n"							\
+	"	b	9f\n"						\
+	"2:	msr	spsr_el2, %1\n"					\
+	"	msr	elr_el2, %2\n"					\
+	"	mov	%w0, %4\n"					\
+	"9:\n"								\
+	__KVM_EXTABLE(1b, 2b)						\
+	: "+r" (__kvm_at_err), "=&r" (spsr), "=&r" (elr)		\
+	: "r" (addr), "i" (-EFAULT));					\
+	__kvm_at_err;							\
+} )
+
+
+#else /* __ASSEMBLY__ */
+
+.macro get_host_ctxt reg, tmp
+	adr_this_cpu \reg, kvm_host_data, \tmp
+	add	\reg, \reg, #HOST_DATA_CONTEXT
+.endm
+
+.macro get_vcpu_ptr vcpu, ctxt
+	get_host_ctxt \ctxt, \vcpu
+	ldr	\vcpu, [\ctxt, #HOST_CONTEXT_VCPU]
+.endm
+
+.macro get_loaded_vcpu vcpu, ctxt
+	adr_this_cpu \ctxt, kvm_hyp_ctxt, \vcpu
+	ldr	\vcpu, [\ctxt, #HOST_CONTEXT_VCPU]
+.endm
+
+.macro set_loaded_vcpu vcpu, ctxt, tmp
+	adr_this_cpu \ctxt, kvm_hyp_ctxt, \tmp
+	str	\vcpu, [\ctxt, #HOST_CONTEXT_VCPU]
+.endm
+
+/*
+ * KVM extable for unexpected exceptions.
+ * Create a struct kvm_exception_table_entry output to a section that can be
+ * mapped by EL2. The table is not sorted.
+ *
+ * The caller must ensure:
+ * x18 has the hypervisor value to allow any Shadow-Call-Stack instrumented
+ * code to write to it, and that SPSR_EL2 and ELR_EL2 are restored by the fixup.
+ */
+.macro	_kvm_extable, from, to
+	.pushsection	__kvm_ex_table, "a"
+	.align		3
+	.long		(\from - .), (\to - .)
+	.popsection
+.endm
+
+#define CPU_XREG_OFFSET(x)	(CPU_USER_PT_REGS + 8*x)
+#define CPU_LR_OFFSET		CPU_XREG_OFFSET(30)
+#define CPU_SP_EL0_OFFSET	(CPU_LR_OFFSET + 8)
+
+/*
+ * We treat x18 as callee-saved as the host may use it as a platform
+ * register (e.g. for shadow call stack).
+ */
+.macro save_callee_saved_regs ctxt
+	str	x18,      [\ctxt, #CPU_XREG_OFFSET(18)]
+	stp	x19, x20, [\ctxt, #CPU_XREG_OFFSET(19)]
+	stp	x21, x22, [\ctxt, #CPU_XREG_OFFSET(21)]
+	stp	x23, x24, [\ctxt, #CPU_XREG_OFFSET(23)]
+	stp	x25, x26, [\ctxt, #CPU_XREG_OFFSET(25)]
+	stp	x27, x28, [\ctxt, #CPU_XREG_OFFSET(27)]
+	stp	x29, lr,  [\ctxt, #CPU_XREG_OFFSET(29)]
+.endm
+
+.macro restore_callee_saved_regs ctxt
+	// We require \ctxt is not x18-x28
+	ldr	x18,      [\ctxt, #CPU_XREG_OFFSET(18)]
+	ldp	x19, x20, [\ctxt, #CPU_XREG_OFFSET(19)]
+	ldp	x21, x22, [\ctxt, #CPU_XREG_OFFSET(21)]
+	ldp	x23, x24, [\ctxt, #CPU_XREG_OFFSET(23)]
+	ldp	x25, x26, [\ctxt, #CPU_XREG_OFFSET(25)]
+	ldp	x27, x28, [\ctxt, #CPU_XREG_OFFSET(27)]
+	ldp	x29, lr,  [\ctxt, #CPU_XREG_OFFSET(29)]
+.endm
+
+.macro save_sp_el0 ctxt, tmp
+	mrs	\tmp,	sp_el0
+	str	\tmp,	[\ctxt, #CPU_SP_EL0_OFFSET]
+.endm
+
+.macro restore_sp_el0 ctxt, tmp
+	ldr	\tmp,	  [\ctxt, #CPU_SP_EL0_OFFSET]
+	msr	sp_el0, \tmp
+.endm
+
+#endif
+
+#endif /* __ARM_KVM_ASM_H__ */