Files
linux/arch/arm64/include/asm/el2_setup.h
Linus Torvalds 01f492e181 Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull kvm updates from Paolo Bonzini:
 "Arm:

   - Add support for tracing in the standalone EL2 hypervisor code,
     which should help both debugging and performance analysis. This
     uses the new infrastructure for 'remote' trace buffers that can be
     exposed by non-kernel entities such as firmware, and which came
     through the tracing tree

   - Add support for GICv5 Per Processor Interrupts (PPIs), as the
     starting point for supporting the new GIC architecture in KVM

   - Finally add support for pKVM protected guests, where pages are
     unmapped from the host as they are faulted into the guest and can
     be shared back from the guest using pKVM hypercalls. Protected
     guests are created using a new machine type identifier. As the
     elusive guestmem has not yet delivered on its promises, anonymous
     memory is also supported

     This is only a first step towards full isolation from the host; for
     example, the CPU register state and DMA accesses are not yet
     isolated. Because this does not really yet bring fully what it
     promises, it is hidden behind CONFIG_ARM_PKVM_GUEST +
     'kvm-arm.mode=protected', and also triggers TAINT_USER when a VM is
     created. Caveat emptor

   - Rework the dreaded user_mem_abort() function to make it more
     maintainable, reducing the amount of state being exposed to the
     various helpers and rendering a substantial amount of state
     immutable

   - Expand the Stage-2 page table dumper to support NV shadow page
     tables on a per-VM basis

   - Tidy up the pKVM PSCI proxy code to be slightly less hard to
     follow

   - Fix both SPE and TRBE in non-VHE configurations so that they do not
     generate spurious, out of context table walks that ultimately lead
     to very bad HW lockups

   - A small set of patches fixing the Stage-2 MMU freeing in error
     cases

   - Tighten-up accepted SMC immediate value to be only #0 for host
     SMCCC calls

   - The usual cleanups and other selftest churn

  LoongArch:

   - Use CSR_CRMD_PLV for kvm_arch_vcpu_in_kernel()

   - Add DMSINTC irqchip in kernel support

  RISC-V:

   - Fix steal time shared memory alignment checks

   - Fix vector context allocation leak

   - Fix array out-of-bounds in pmu_ctr_read() and pmu_fw_ctr_read_hi()

   - Fix double-free of sdata in kvm_pmu_clear_snapshot_area()

   - Fix integer overflow in kvm_pmu_validate_counter_mask()

   - Fix shift-out-of-bounds in make_xfence_request()

   - Fix lost write protection on huge pages during dirty logging

   - Split huge pages during fault handling for dirty logging

   - Skip CSR restore if VCPU is reloaded on the same core

   - Implement kvm_arch_has_default_irqchip() for KVM selftests

   - Factored-out ISA checks into separate sources

   - Added hideleg to struct kvm_vcpu_config

   - Factored-out VCPU config into separate sources

   - Support configuration of per-VM HGATP mode from KVM user space

  s390:

   - Support for ESA (31-bit) guests inside nested hypervisors

   - Remove restriction on memslot alignment, which is not needed
     anymore with the new gmap code

   - Fix LPSW/E to update the bear (which of course is the breaking
     event address register)

  x86:

   - Shut up various UBSAN warnings on reading module parameter before
     they were initialized

   - Don't zero-allocate page tables that are used for splitting
     hugepages in the TDP MMU, as KVM is guaranteed to set all SPTEs in
     the page table and thus write all bytes

   - As an optimization, bail early when trying to unsync 4KiB mappings
     if the target gfn can just be mapped with a 2MiB hugepage

  x86 generic:

   - Copy single-chunk MMIO write values into struct kvm_vcpu (more
     precisely struct kvm_mmio_fragment) to fix use-after-free stack
     bugs where KVM would dereference stack pointer after an exit to
     userspace

   - Clean up and comment the emulated MMIO code to try to make it
     easier to maintain (not necessarily "easy", but "easier")

   - Move VMXON+VMXOFF and EFER.SVME toggling out of KVM (not *all* of
     VMX and SVM enabling) as it is needed for trusted I/O

   - Advertise support for AVX512 Bit Matrix Multiply (BMM) instructions

   - Immediately fail the build if a required #define is missing in one
     of KVM's headers that is included multiple times

   - Reject SET_GUEST_DEBUG with -EBUSY if there's an already injected
     exception, mostly to prevent syzkaller from abusing the uAPI to
     trigger WARNs, but also because it can help prevent userspace from
     unintentionally crashing the VM

   - Exempt SMM from CPUID faulting on Intel, as per the spec

   - Misc hardening and cleanup changes

  x86 (AMD):

   - Fix and optimize IRQ window inhibit handling for AVIC; make it
     per-vCPU so that KVM doesn't prematurely re-enable AVIC if multiple
     vCPUs have to-be-injected IRQs

   - Clean up and optimize the OSVW handling, avoiding a bug in which
     KVM would overwrite state when enabling virtualization on multiple
     CPUs in parallel. This should not be a problem because OSVW should
     usually be the same for all CPUs

   - Drop a WARN in KVM_MEMORY_ENCRYPT_REG_REGION where KVM complains
     about a "too large" size based purely on user input

   - Clean up and harden the pinning code for KVM_MEMORY_ENCRYPT_REG_REGION

   - Disallow synchronizing a VMSA of an already-launched/encrypted
     vCPU, as doing so for an SNP guest will crash the host due to an
     RMP violation page fault

   - Overhaul KVM's APIs for detecting SEV+ guests so that VM-scoped
     queries are required to hold kvm->lock, and enforce it by lockdep.
     Fix various bugs where sev_guest() was not ensured to be stable for
     the whole duration of a function or ioctl

   - Convert a pile of kvm->lock SEV code to guard()

   - Play nicer with userspace that does not enable
     KVM_CAP_EXCEPTION_PAYLOAD, for which KVM needs to set CR2 and DR6
     as a response to ioctls such as KVM_GET_VCPU_EVENTS (even if the
     payload would end up in EXITINFO2 rather than CR2, for example).
     Only set CR2 and DR6 when consumption of the payload is imminent,
     but on the other hand force delivery of the payload in all paths
     where userspace retrieves CR2 or DR6

   - Use vcpu->arch.cr2 when updating vmcb12's CR2 on nested #VMEXIT
     instead of vmcb02->save.cr2. The value is out of sync after a
     save/restore or after a #PF is injected into L2

   - Fix a class of nSVM bugs where some fields written by the CPU are
     not synchronized from vmcb02 to cached vmcb12 after VMRUN, and so
     are not up-to-date when saved by KVM_GET_NESTED_STATE

   - Fix a class of bugs where the ordering between KVM_SET_NESTED_STATE
     and KVM_SET_{S}REGS could cause vmcb02 to be incorrectly
     initialized after save+restore

   - Add a variety of missing nSVM consistency checks

   - Fix several bugs where KVM failed to correctly update VMCB fields
     on nested #VMEXIT

   - Fix several bugs where KVM failed to correctly synthesize #UD or
     #GP for SVM-related instructions

   - Add support for save+restore of virtualized LBRs (on SVM)

   - Refactor various helpers and macros to improve clarity and
     (hopefully) make the code easier to maintain

   - Aggressively sanitize fields when copying from vmcb12, to guard
     against unintentionally allowing L1 to utilize yet-to-be-defined
     features

   - Fix several bugs where KVM botched rAX legality checks when
     emulating SVM instructions. There are remaining issues in that KVM
     doesn't handle size prefix overrides for 64-bit guests

   - Fail emulation of VMRUN/VMLOAD/VMSAVE if mapping vmcb12 fails
     instead of somewhat arbitrarily synthesizing #GP (i.e. don't double
     down on AMD's architectural but sketchy behavior of generating #GP
     for "unsupported" addresses)

   - Cache all used vmcb12 fields to further harden against TOCTOU bugs

  x86 (Intel):

   - Drop obsolete branch hint prefixes from the VMX instruction macros

   - Use ASM_INPUT_RM() in __vmcs_writel() to coerce clang into using a
     register input when appropriate

   - Code cleanups

  guest_memfd:

   - Don't mark guest_memfd folios as accessed, as guest_memfd doesn't
     support reclaim, the memory is unevictable, and there is no storage
     to write back to

  LoongArch selftests:

   - Add KVM PMU test cases

  s390 selftests:

   - Enable more memory selftests

  x86 selftests:

   - Add support for Hygon CPUs in KVM selftests

   - Fix a bug in the MSR test where it would get false failures on
     AMD/Hygon CPUs with exactly one of RDPID or RDTSCP

   - Add an MADV_COLLAPSE testcase for guest_memfd as a regression test
     for a bug where the kernel would attempt to collapse guest_memfd
     folios against KVM's will"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (373 commits)
  KVM: x86: use inlines instead of macros for is_sev_*guest
  x86/virt: Treat SVM as unsupported when running as an SEV+ guest
  KVM: SEV: Goto an existing error label if charging misc_cg for an ASID fails
  KVM: SVM: Move lock-protected allocation of SEV ASID into a separate helper
  KVM: SEV: use mutex guard in snp_handle_guest_req()
  KVM: SEV: use mutex guard in sev_mem_enc_unregister_region()
  KVM: SEV: use mutex guard in sev_mem_enc_ioctl()
  KVM: SEV: use mutex guard in snp_launch_update()
  KVM: SEV: Assert that kvm->lock is held when querying SEV+ support
  KVM: SEV: Document that checking for SEV+ guests when reclaiming memory is "safe"
  KVM: SEV: Hide "struct kvm_sev_info" behind CONFIG_KVM_AMD_SEV=y
  KVM: SEV: WARN on unhandled VM type when initializing VM
  KVM: LoongArch: selftests: Add PMU overflow interrupt test
  KVM: LoongArch: selftests: Add basic PMU event counting test
  KVM: LoongArch: selftests: Add cpucfg read/write helpers
  LoongArch: KVM: Add DMSINTC inject msi to vCPU
  LoongArch: KVM: Add DMSINTC device support
  LoongArch: KVM: Make vcpu_is_preempted() as a macro rather than function
  LoongArch: KVM: Move host CSR_GSTAT save and restore in context switch
  LoongArch: KVM: Move host CSR_EENTRY save and restore in context switch
  ...
2026-04-17 07:18:03 -07:00

604 lines
17 KiB
C

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Copyright (C) 2012,2013 - ARM Ltd
* Author: Marc Zyngier <marc.zyngier@arm.com>
*/
#ifndef __ARM_KVM_INIT_H__
#define __ARM_KVM_INIT_H__
#ifndef __ASSEMBLER__
#error Assembly-only header
#endif
#include <asm/kvm_arm.h>
#include <asm/ptrace.h>
#include <asm/sysreg.h>
#include <linux/irqchip/arm-gic-v3.h>
.macro init_el2_hcr val
mov_q x0, \val
/*
* Compliant CPUs advertise their VHE-onlyness with
* ID_AA64MMFR4_EL1.E2H0 < 0. On such CPUs HCR_EL2.E2H is RES1, but it
* can reset into an UNKNOWN state and might not read as 1 until it has
* been initialized explicitly.
* Initialize HCR_EL2.E2H so that later code can rely upon HCR_EL2.E2H
* indicating whether the CPU is running in E2H mode.
*/
mrs_s x1, SYS_ID_AA64MMFR4_EL1
sbfx x1, x1, #ID_AA64MMFR4_EL1_E2H0_SHIFT, #ID_AA64MMFR4_EL1_E2H0_WIDTH
cmp x1, #0
b.lt .LnE2H0_\@
/*
* Unfortunately, HCR_EL2.E2H can be RES1 even if not advertised
* as such via ID_AA64MMFR4_EL1.E2H0:
*
* - Fruity CPUs predate the !FEAT_E2H0 relaxation, and seem to
* have HCR_EL2.E2H implemented as RAO/WI.
*
* - On CPUs that lack FEAT_FGT, a hypervisor can't trap guest
* reads of ID_AA64MMFR4_EL1 to advertise !FEAT_E2H0. NV
* guests on these hosts can write to HCR_EL2.E2H without
* trapping to the hypervisor, but these writes have no
* functional effect.
*
* Handle both cases by checking for an essential VHE property
* (system register remapping) to decide whether we're
* effectively VHE-only or not.
*/
msr_hcr_el2 x0 // Setup HCR_EL2 as nVHE
mov x1, #1 // Write something to FAR_EL1
msr far_el1, x1
isb
mov x1, #2 // Try to overwrite it via FAR_EL2
msr far_el2, x1
isb
mrs x1, far_el1 // If we see the latest write in FAR_EL1,
cmp x1, #2 // we can safely assume we are VHE only.
b.ne .LnVHE_\@ // Otherwise, we know that nVHE works.
.LnE2H0_\@:
orr x0, x0, #HCR_E2H
msr_hcr_el2 x0
.LnVHE_\@:
.endm
.macro __init_el2_sctlr
mov_q x0, INIT_SCTLR_EL2_MMU_OFF
msr sctlr_el2, x0
isb
.endm
.macro __init_el2_hcrx
mrs x0, id_aa64mmfr1_el1
ubfx x0, x0, #ID_AA64MMFR1_EL1_HCX_SHIFT, #4
cbz x0, .Lskip_hcrx_\@
mov_q x0, (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En | HCRX_EL2_EnFPM)
/* Enable GCS if supported */
mrs_s x1, SYS_ID_AA64PFR1_EL1
ubfx x1, x1, #ID_AA64PFR1_EL1_GCS_SHIFT, #4
cbz x1, .Lskip_gcs_hcrx_\@
orr x0, x0, #HCRX_EL2_GCSEn
.Lskip_gcs_hcrx_\@:
/* Enable LS64, LS64_V if supported */
mrs_s x1, SYS_ID_AA64ISAR1_EL1
ubfx x1, x1, #ID_AA64ISAR1_EL1_LS64_SHIFT, #4
cbz x1, .Lset_hcrx_\@
orr x0, x0, #HCRX_EL2_EnALS
cmp x1, #ID_AA64ISAR1_EL1_LS64_LS64_V
b.lt .Lset_hcrx_\@
orr x0, x0, #HCRX_EL2_EnASR
.Lset_hcrx_\@:
msr_s SYS_HCRX_EL2, x0
.Lskip_hcrx_\@:
.endm
/* Check if running in host at EL2 mode, i.e., (h)VHE. Jump to fail if not. */
.macro __check_hvhe fail, tmp
mrs \tmp, hcr_el2
and \tmp, \tmp, #HCR_E2H
cbz \tmp, \fail
.endm
/*
* Allow Non-secure EL1 and EL0 to access physical timer and counter.
* This is not necessary for VHE, since the host kernel runs in EL2,
* and EL0 accesses are configured in the later stage of boot process.
* Note that when HCR_EL2.E2H == 1, CNTHCTL_EL2 has the same bit layout
* as CNTKCTL_EL1, and CNTKCTL_EL1 accessing instructions are redefined
* to access CNTHCTL_EL2. This allows the kernel designed to run at EL1
* to transparently mess with the EL0 bits via CNTKCTL_EL1 access in
* EL2.
*/
.macro __init_el2_timers
mov x0, #3 // Enable EL1 physical timers
__check_hvhe .LnVHE_\@, x1
lsl x0, x0, #10
.LnVHE_\@:
msr cnthctl_el2, x0
msr cntvoff_el2, xzr // Clear virtual offset
.endm
/* Branch to skip_label if SPE version is less than given version */
.macro __spe_vers_imp skip_label, version, tmp
mrs \tmp, id_aa64dfr0_el1
ubfx \tmp, \tmp, #ID_AA64DFR0_EL1_PMSVer_SHIFT, #4
cmp \tmp, \version
b.lt \skip_label
.endm
.macro __init_el2_debug
mrs x1, id_aa64dfr0_el1
ubfx x0, x1, #ID_AA64DFR0_EL1_PMUVer_SHIFT, #4
cmp x0, #ID_AA64DFR0_EL1_PMUVer_NI
ccmp x0, #ID_AA64DFR0_EL1_PMUVer_IMP_DEF, #4, ne
b.eq .Lskip_pmu_\@ // Skip if no PMU present or IMP_DEF
mrs x0, pmcr_el0 // Disable debug access traps
ubfx x0, x0, #11, #5 // to EL2 and allow access to
.Lskip_pmu_\@:
csel x2, xzr, x0, eq // all PMU counters from EL1
/* Statistical profiling */
__spe_vers_imp .Lskip_spe_\@, ID_AA64DFR0_EL1_PMSVer_IMP, x0 // Skip if SPE not present
mrs_s x0, SYS_PMBIDR_EL1 // If SPE available at EL2,
and x0, x0, #(1 << PMBIDR_EL1_P_SHIFT)
cbnz x0, .Lskip_spe_el2_\@ // then permit sampling of physical
mov x0, #(1 << PMSCR_EL2_PCT_SHIFT | \
1 << PMSCR_EL2_PA_SHIFT)
msr_s SYS_PMSCR_EL2, x0 // addresses and physical counter
.Lskip_spe_el2_\@:
mov x0, #MDCR_EL2_E2PB_MASK
orr x2, x2, x0 // If we don't have VHE, then
// use EL1&0 translation.
.Lskip_spe_\@:
/* Trace buffer */
ubfx x0, x1, #ID_AA64DFR0_EL1_TraceBuffer_SHIFT, #4
cbz x0, .Lskip_trace_\@ // Skip if TraceBuffer is not present
mrs_s x0, SYS_TRBIDR_EL1
and x0, x0, TRBIDR_EL1_P
cbnz x0, .Lskip_trace_\@ // If TRBE is available at EL2
mov x0, #MDCR_EL2_E2TB_MASK
orr x2, x2, x0 // allow the EL1&0 translation
// to own it.
.Lskip_trace_\@:
msr mdcr_el2, x2 // Configure debug traps
.endm
/* LORegions */
.macro __init_el2_lor
mrs x1, id_aa64mmfr1_el1
ubfx x0, x1, #ID_AA64MMFR1_EL1_LO_SHIFT, 4
cbz x0, .Lskip_lor_\@
msr_s SYS_LORC_EL1, xzr
.Lskip_lor_\@:
.endm
/* Stage-2 translation */
.macro __init_el2_stage2
msr vttbr_el2, xzr
.endm
/* GICv3 system register access */
.macro __init_el2_gicv3
mrs x0, id_aa64pfr0_el1
ubfx x0, x0, #ID_AA64PFR0_EL1_GIC_SHIFT, #4
cbz x0, .Lskip_gicv3_\@
mrs_s x0, SYS_ICC_SRE_EL2
orr x0, x0, #ICC_SRE_EL2_SRE // Set ICC_SRE_EL2.SRE==1
orr x0, x0, #ICC_SRE_EL2_ENABLE // Set ICC_SRE_EL2.Enable==1
msr_s SYS_ICC_SRE_EL2, x0
isb // Make sure SRE is now set
mrs_s x0, SYS_ICC_SRE_EL2 // Read SRE back,
tbz x0, #0, .Lskip_gicv3_\@ // and check that it sticks
msr_s SYS_ICH_HCR_EL2, xzr // Reset ICH_HCR_EL2 to defaults
.Lskip_gicv3_\@:
.endm
/* GICv5 system register access */
.macro __init_el2_gicv5
mrs_s x0, SYS_ID_AA64PFR2_EL1
ubfx x0, x0, #ID_AA64PFR2_EL1_GCIE_SHIFT, #4
cbz x0, .Lskip_gicv5_\@
mov x0, #(ICH_HFGITR_EL2_GICRCDNMIA | \
ICH_HFGITR_EL2_GICRCDIA | \
ICH_HFGITR_EL2_GICCDDI | \
ICH_HFGITR_EL2_GICCDEOI | \
ICH_HFGITR_EL2_GICCDHM | \
ICH_HFGITR_EL2_GICCDRCFG | \
ICH_HFGITR_EL2_GICCDPEND | \
ICH_HFGITR_EL2_GICCDAFF | \
ICH_HFGITR_EL2_GICCDPRI | \
ICH_HFGITR_EL2_GICCDDIS | \
ICH_HFGITR_EL2_GICCDEN)
msr_s SYS_ICH_HFGITR_EL2, x0 // Disable instruction traps
mov_q x0, (ICH_HFGRTR_EL2_ICC_PPI_ACTIVERn_EL1 | \
ICH_HFGRTR_EL2_ICC_PPI_PRIORITYRn_EL1 | \
ICH_HFGRTR_EL2_ICC_PPI_PENDRn_EL1 | \
ICH_HFGRTR_EL2_ICC_PPI_ENABLERn_EL1 | \
ICH_HFGRTR_EL2_ICC_PPI_HMRn_EL1 | \
ICH_HFGRTR_EL2_ICC_IAFFIDR_EL1 | \
ICH_HFGRTR_EL2_ICC_ICSR_EL1 | \
ICH_HFGRTR_EL2_ICC_PCR_EL1 | \
ICH_HFGRTR_EL2_ICC_HPPIR_EL1 | \
ICH_HFGRTR_EL2_ICC_CR0_EL1 | \
ICH_HFGRTR_EL2_ICC_IDRn_EL1 | \
ICH_HFGRTR_EL2_ICC_APR_EL1)
msr_s SYS_ICH_HFGRTR_EL2, x0 // Disable reg read traps
mov_q x0, (ICH_HFGWTR_EL2_ICC_PPI_ACTIVERn_EL1 | \
ICH_HFGWTR_EL2_ICC_PPI_PRIORITYRn_EL1 | \
ICH_HFGWTR_EL2_ICC_PPI_PENDRn_EL1 | \
ICH_HFGWTR_EL2_ICC_PPI_ENABLERn_EL1 | \
ICH_HFGWTR_EL2_ICC_ICSR_EL1 | \
ICH_HFGWTR_EL2_ICC_PCR_EL1 | \
ICH_HFGWTR_EL2_ICC_CR0_EL1 | \
ICH_HFGWTR_EL2_ICC_APR_EL1)
msr_s SYS_ICH_HFGWTR_EL2, x0 // Disable reg write traps
mov x0, #(ICH_VCTLR_EL2_En)
msr_s SYS_ICH_VCTLR_EL2, x0 // Enable vHPPI selection
.Lskip_gicv5_\@:
.endm
.macro __init_el2_hstr
msr hstr_el2, xzr // Disable CP15 traps to EL2
.endm
/* Virtual CPU ID registers */
.macro __init_el2_nvhe_idregs
mrs x0, midr_el1
mrs x1, mpidr_el1
msr vpidr_el2, x0
msr vmpidr_el2, x1
.endm
/* Coprocessor traps */
.macro __init_el2_cptr
__check_hvhe .LnVHE_\@, x1
mov x0, #CPACR_EL1_FPEN
msr cpacr_el1, x0
b .Lskip_set_cptr_\@
.LnVHE_\@:
mov x0, #0x33ff
msr cptr_el2, x0 // Disable copro. traps to EL2
.Lskip_set_cptr_\@:
.endm
/*
* Configure BRBE to permit recording cycle counts and branch mispredicts.
*
* At any EL, to record cycle counts BRBE requires that both BRBCR_EL2.CC=1 and
* BRBCR_EL1.CC=1.
*
* At any EL, to record branch mispredicts BRBE requires that both
* BRBCR_EL2.MPRED=1 and BRBCR_EL1.MPRED=1.
*
* Set {CC,MPRED} in BRBCR_EL2 in case nVHE mode is used and we are
* executing in EL1.
*/
.macro __init_el2_brbe
mrs x1, id_aa64dfr0_el1
ubfx x1, x1, #ID_AA64DFR0_EL1_BRBE_SHIFT, #4
cbz x1, .Lskip_brbe_\@
mov_q x0, BRBCR_ELx_CC | BRBCR_ELx_MPRED
msr_s SYS_BRBCR_EL2, x0
.Lskip_brbe_\@:
.endm
/* Disable any fine grained traps */
.macro __init_el2_fgt
mrs x1, id_aa64mmfr0_el1
ubfx x1, x1, #ID_AA64MMFR0_EL1_FGT_SHIFT, #4
cbz x1, .Lskip_fgt_\@
mov x0, xzr
mov x2, xzr
/* If SPEv1p2 is implemented, */
__spe_vers_imp .Lskip_spe_fgt_\@, #ID_AA64DFR0_EL1_PMSVer_V1P2, x1
/* Disable PMSNEVFR_EL1 read and write traps */
orr x0, x0, #HDFGRTR_EL2_nPMSNEVFR_EL1_MASK
orr x2, x2, #HDFGWTR_EL2_nPMSNEVFR_EL1_MASK
.Lskip_spe_fgt_\@:
mrs x1, id_aa64dfr0_el1
ubfx x1, x1, #ID_AA64DFR0_EL1_BRBE_SHIFT, #4
cbz x1, .Lskip_brbe_fgt_\@
/*
* Disable read traps for the following registers
*
* [BRBSRC|BRBTGT|RBINF]_EL1
* [BRBSRCINJ|BRBTGTINJ|BRBINFINJ|BRBTS]_EL1
*/
orr x0, x0, #HDFGRTR_EL2_nBRBDATA_MASK
/*
* Disable write traps for the following registers
*
* [BRBSRCINJ|BRBTGTINJ|BRBINFINJ|BRBTS]_EL1
*/
orr x2, x2, #HDFGWTR_EL2_nBRBDATA_MASK
/* Disable read and write traps for [BRBCR|BRBFCR]_EL1 */
orr x0, x0, #HDFGRTR_EL2_nBRBCTL_MASK
orr x2, x2, #HDFGWTR_EL2_nBRBCTL_MASK
/* Disable read traps for BRBIDR_EL1 */
orr x0, x0, #HDFGRTR_EL2_nBRBIDR_MASK
.Lskip_brbe_fgt_\@:
.Lset_debug_fgt_\@:
msr_s SYS_HDFGRTR_EL2, x0
msr_s SYS_HDFGWTR_EL2, x2
mov x0, xzr
mov x2, xzr
mrs x1, id_aa64dfr0_el1
ubfx x1, x1, #ID_AA64DFR0_EL1_BRBE_SHIFT, #4
cbz x1, .Lskip_brbe_insn_fgt_\@
/* Disable traps for BRBIALL instruction */
orr x2, x2, #HFGITR_EL2_nBRBIALL_MASK
/* Disable traps for BRBINJ instruction */
orr x2, x2, #HFGITR_EL2_nBRBINJ_MASK
.Lskip_brbe_insn_fgt_\@:
mrs x1, id_aa64pfr1_el1
ubfx x1, x1, #ID_AA64PFR1_EL1_SME_SHIFT, #4
cbz x1, .Lskip_sme_fgt_\@
/* Disable nVHE traps of TPIDR2 and SMPRI */
orr x0, x0, #HFGRTR_EL2_nSMPRI_EL1_MASK
orr x0, x0, #HFGRTR_EL2_nTPIDR2_EL0_MASK
.Lskip_sme_fgt_\@:
mrs_s x1, SYS_ID_AA64MMFR3_EL1
ubfx x1, x1, #ID_AA64MMFR3_EL1_S1PIE_SHIFT, #4
cbz x1, .Lskip_pie_fgt_\@
/* Disable trapping of PIR_EL1 / PIRE0_EL1 */
orr x0, x0, #HFGRTR_EL2_nPIR_EL1
orr x0, x0, #HFGRTR_EL2_nPIRE0_EL1
.Lskip_pie_fgt_\@:
mrs_s x1, SYS_ID_AA64MMFR3_EL1
ubfx x1, x1, #ID_AA64MMFR3_EL1_S1POE_SHIFT, #4
cbz x1, .Lskip_poe_fgt_\@
/* Disable trapping of POR_EL0 */
orr x0, x0, #HFGRTR_EL2_nPOR_EL0
.Lskip_poe_fgt_\@:
/* GCS depends on PIE so we don't check it if PIE is absent */
mrs_s x1, SYS_ID_AA64PFR1_EL1
ubfx x1, x1, #ID_AA64PFR1_EL1_GCS_SHIFT, #4
cbz x1, .Lskip_gce_fgt_\@
/* Disable traps of access to GCS registers at EL0 and EL1 */
orr x0, x0, #HFGRTR_EL2_nGCS_EL1_MASK
orr x0, x0, #HFGRTR_EL2_nGCS_EL0_MASK
.Lskip_gce_fgt_\@:
.Lset_fgt_\@:
msr_s SYS_HFGRTR_EL2, x0
msr_s SYS_HFGWTR_EL2, x0
msr_s SYS_HFGITR_EL2, x2
mrs x1, id_aa64pfr0_el1 // AMU traps UNDEF without AMU
ubfx x1, x1, #ID_AA64PFR0_EL1_AMU_SHIFT, #4
cbz x1, .Lskip_amu_fgt_\@
msr_s SYS_HAFGRTR_EL2, xzr
.Lskip_amu_fgt_\@:
.Lskip_fgt_\@:
.endm
.macro __init_el2_fgt2
mrs x1, id_aa64mmfr0_el1
ubfx x1, x1, #ID_AA64MMFR0_EL1_FGT_SHIFT, #4
cmp x1, #ID_AA64MMFR0_EL1_FGT_FGT2
b.lt .Lskip_fgt2_\@
mov x0, xzr
mrs x1, id_aa64dfr0_el1
ubfx x1, x1, #ID_AA64DFR0_EL1_PMUVer_SHIFT, #4
cmp x1, #ID_AA64DFR0_EL1_PMUVer_V3P9
b.lt .Lskip_pmuv3p9_\@
orr x0, x0, #HDFGRTR2_EL2_nPMICNTR_EL0
orr x0, x0, #HDFGRTR2_EL2_nPMICFILTR_EL0
orr x0, x0, #HDFGRTR2_EL2_nPMUACR_EL1
.Lskip_pmuv3p9_\@:
/* If SPE is implemented, */
__spe_vers_imp .Lskip_spefds_\@, ID_AA64DFR0_EL1_PMSVer_IMP, x1
/* we can read PMSIDR and */
mrs_s x1, SYS_PMSIDR_EL1
and x1, x1, #PMSIDR_EL1_FDS
/* if FEAT_SPE_FDS is implemented, */
cbz x1, .Lskip_spefds_\@
/* disable traps of PMSDSFR to EL2. */
orr x0, x0, #HDFGRTR2_EL2_nPMSDSFR_EL1
.Lskip_spefds_\@:
msr_s SYS_HDFGRTR2_EL2, x0
msr_s SYS_HDFGWTR2_EL2, x0
msr_s SYS_HFGRTR2_EL2, xzr
msr_s SYS_HFGWTR2_EL2, xzr
msr_s SYS_HFGITR2_EL2, xzr
.Lskip_fgt2_\@:
.endm
/**
* Initialize EL2 registers to sane values. This should be called early on all
* cores that were booted in EL2. Note that everything gets initialised as
* if VHE was not available. The kernel context will be upgraded to VHE
* if possible later on in the boot process
*
* Regs: x0, x1 and x2 are clobbered.
*/
.macro init_el2_state
__init_el2_sctlr
__init_el2_hcrx
__init_el2_timers
__init_el2_debug
__init_el2_brbe
__init_el2_lor
__init_el2_stage2
__init_el2_gicv3
__init_el2_gicv5
__init_el2_hstr
__init_el2_nvhe_idregs
__init_el2_cptr
__init_el2_fgt
__init_el2_fgt2
.endm
#ifndef __KVM_NVHE_HYPERVISOR__
// This will clobber tmp1 and tmp2, and expect tmp1 to contain
// the id register value as read from the HW
.macro __check_override idreg, fld, width, pass, fail, tmp1, tmp2
ubfx \tmp1, \tmp1, #\fld, #\width
cbz \tmp1, \fail
adr_l \tmp1, \idreg\()_override
ldr \tmp2, [\tmp1, FTR_OVR_VAL_OFFSET]
ldr \tmp1, [\tmp1, FTR_OVR_MASK_OFFSET]
ubfx \tmp2, \tmp2, #\fld, #\width
ubfx \tmp1, \tmp1, #\fld, #\width
cmp \tmp1, xzr
and \tmp2, \tmp2, \tmp1
csinv \tmp2, \tmp2, xzr, ne
cbnz \tmp2, \pass
b \fail
.endm
// This will clobber tmp1 and tmp2
.macro check_override idreg, fld, pass, fail, tmp1, tmp2
mrs \tmp1, \idreg\()_el1
__check_override \idreg \fld 4 \pass \fail \tmp1 \tmp2
.endm
#else
// This will clobber tmp
.macro __check_override idreg, fld, width, pass, fail, tmp, ignore
ldr_l \tmp, \idreg\()_el1_sys_val
ubfx \tmp, \tmp, #\fld, #\width
cbnz \tmp, \pass
b \fail
.endm
.macro check_override idreg, fld, pass, fail, tmp, ignore
__check_override \idreg \fld 4 \pass \fail \tmp \ignore
.endm
#endif
.macro finalise_el2_state
check_override id_aa64pfr0, ID_AA64PFR0_EL1_MPAM_SHIFT, .Linit_mpam_\@, .Lskip_mpam_\@, x1, x2
.Linit_mpam_\@:
mov x0, #MPAM2_EL2_EnMPAMSM_MASK
msr_s SYS_MPAM2_EL2, x0 // use the default partition,
// and disable lower traps
mrs_s x0, SYS_MPAMIDR_EL1
tbz x0, #MPAMIDR_EL1_HAS_HCR_SHIFT, .Lskip_mpam_\@ // skip if no MPAMHCR reg
msr_s SYS_MPAMHCR_EL2, xzr // clear TRAP_MPAMIDR_EL1 -> EL2
.Lskip_mpam_\@:
check_override id_aa64pfr1, ID_AA64PFR1_EL1_GCS_SHIFT, .Linit_gcs_\@, .Lskip_gcs_\@, x1, x2
.Linit_gcs_\@:
msr_s SYS_GCSCR_EL1, xzr
msr_s SYS_GCSCRE0_EL1, xzr
.Lskip_gcs_\@:
check_override id_aa64pfr0, ID_AA64PFR0_EL1_SVE_SHIFT, .Linit_sve_\@, .Lskip_sve_\@, x1, x2
.Linit_sve_\@: /* SVE register access */
__check_hvhe .Lcptr_nvhe_\@, x1
// (h)VHE case
mrs x0, cpacr_el1 // Disable SVE traps
orr x0, x0, #CPACR_EL1_ZEN
msr cpacr_el1, x0
b .Lskip_set_cptr_\@
.Lcptr_nvhe_\@: // nVHE case
mrs x0, cptr_el2 // Disable SVE traps
bic x0, x0, #CPTR_EL2_TZ
msr cptr_el2, x0
.Lskip_set_cptr_\@:
isb
mov x1, #ZCR_ELx_LEN_MASK // SVE: Enable full vector
msr_s SYS_ZCR_EL2, x1 // length for EL1.
.Lskip_sve_\@:
check_override id_aa64pfr1, ID_AA64PFR1_EL1_SME_SHIFT, .Linit_sme_\@, .Lskip_sme_\@, x1, x2
.Linit_sme_\@: /* SME register access and priority mapping */
__check_hvhe .Lcptr_nvhe_sme_\@, x1
// (h)VHE case
mrs x0, cpacr_el1 // Disable SME traps
orr x0, x0, #CPACR_EL1_SMEN
msr cpacr_el1, x0
b .Lskip_set_cptr_sme_\@
.Lcptr_nvhe_sme_\@: // nVHE case
mrs x0, cptr_el2 // Disable SME traps
bic x0, x0, #CPTR_EL2_TSM
msr cptr_el2, x0
.Lskip_set_cptr_sme_\@:
isb
mrs x1, sctlr_el2
orr x1, x1, #SCTLR_ELx_ENTP2 // Disable TPIDR2 traps
msr sctlr_el2, x1
isb
mov x0, #0 // SMCR controls
// Full FP in SM?
mrs_s x1, SYS_ID_AA64SMFR0_EL1
__check_override id_aa64smfr0, ID_AA64SMFR0_EL1_FA64_SHIFT, 1, .Linit_sme_fa64_\@, .Lskip_sme_fa64_\@, x1, x2
.Linit_sme_fa64_\@:
orr x0, x0, SMCR_ELx_FA64_MASK
.Lskip_sme_fa64_\@:
// ZT0 available?
mrs_s x1, SYS_ID_AA64SMFR0_EL1
__check_override id_aa64smfr0, ID_AA64SMFR0_EL1_SMEver_SHIFT, 4, .Linit_sme_zt0_\@, .Lskip_sme_zt0_\@, x1, x2
.Linit_sme_zt0_\@:
orr x0, x0, SMCR_ELx_EZT0_MASK
.Lskip_sme_zt0_\@:
orr x0, x0, #SMCR_ELx_LEN_MASK // Enable full SME vector
msr_s SYS_SMCR_EL2, x0 // length for EL1.
mrs_s x1, SYS_SMIDR_EL1 // Priority mapping supported?
ubfx x1, x1, #SMIDR_EL1_SMPS_SHIFT, #1
cbz x1, .Lskip_sme_\@
msr_s SYS_SMPRIMAP_EL2, xzr // Make all priorities equal
.Lskip_sme_\@:
.endm
#endif /* __ARM_KVM_INIT_H__ */