linux/arch/arm64/kvm/reset.c
Linus Torvalds 79e06c4c49 RISCV:
- Use common KVM implementation of MMU memory caches
 
 - SBI v0.2 support for Guest
 
 - Initial KVM selftests support
 
 - Fix to avoid spurious virtual interrupts after clearing hideleg CSR
 
 - Update email address for Anup and Atish
 
 ARM:
 - Simplification of the 'vcpu first run' by integrating it into
   KVM's 'pid change' flow
 
 - Refactoring of the FP and SVE state tracking, also leading to
   a simpler state and less shared data between EL1 and EL2 in
   the nVHE case
 
 - Tidy up the header file usage for the nvhe hyp object
 
 - New HYP unsharing mechanism, finally allowing pages to be
   unmapped from the Stage-1 EL2 page-tables
 
 - Various pKVM cleanups around refcounting and sharing
 
 - A couple of vgic fixes for bugs that would trigger once
   the vcpu xarray rework is merged, but not sooner
 
 - Add minimal support for ARMv8.7's PMU extension
 
 - Rework kvm_pgtable initialisation ahead of the NV work
 
 - New selftest for IRQ injection
 
 - Teach selftests about the lack of default IPA space and
   page sizes
 
 - Expand sysreg selftest to deal with Pointer Authentication
 
 - The usual bunch of cleanups and doc update
 
 s390:
 - fix sigp sense/start/stop/inconsistency
 
 - cleanups
 
 x86:
 - Clean up some function prototypes more
 
 - improved gfn_to_pfn_cache with proper invalidation, used by Xen emulation
 
 - add KVM_IRQ_ROUTING_XEN_EVTCHN and event channel delivery
 
 - completely remove potential TOC/TOU races in nested SVM consistency checks
 
 - update some PMCs on emulated instructions
 
 - Intel AMX support (joint work between Thomas and Intel)
 
 - large MMU cleanups
 
 - module parameter to disable PMU virtualization
 
 - cleanup register cache
 
 - first part of halt handling cleanups
 
 - Hyper-V enlightened MSR bitmap support for nested hypervisors
 
 Generic:
 - clean up Makefiles
 
 - introduce CONFIG_HAVE_KVM_DIRTY_RING
 
 - optimize memslot lookup using a tree
 
 - optimize vCPU array usage by converting to xarray
 -----BEGIN PGP SIGNATURE-----
 
 iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmHhxvsUHHBib256aW5p
 QHJlZGhhdC5jb20ACgkQv/vSX3jHroPZkAf+Nz92UL/5nNGcdHtE4m7AToMmitE9
 bYkesf9BMQvAe5wjkABLuoHGi6ay4jabo4fiGzbdkiK7lO5YgfsWiMB3/MT5fl4E
 jRPzaVQabp3YZLM8UYCBmfUVuRj524S967SfSRe0AvYjDEH8y7klPf4+7sCsFT0/
 Px9Vf2KGuOlf0eM78yKg4rGaF0jS22eLgXm6FfNMY8/e29ZAo/jyUmqBY+Z2xxZG
 aWhceDtSheW1jwLHLj3nOlQJvHTn8LVGXBE/R8Gda3ZjrBV2rKaDi4Fh+HD+dz86
 2zVXwzQ7uck2CMW73GMoXMTWoKSHMyvlBOs1BdvBm4UsnGcXR+q8IFCeuQ==
 =s73m
 -----END PGP SIGNATURE-----

Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "RISCV:

   - Use common KVM implementation of MMU memory caches

   - SBI v0.2 support for Guest

   - Initial KVM selftests support

   - Fix to avoid spurious virtual interrupts after clearing hideleg CSR

   - Update email address for Anup and Atish

  ARM:

   - Simplification of the 'vcpu first run' by integrating it into KVM's
     'pid change' flow

   - Refactoring of the FP and SVE state tracking, also leading to a
     simpler state and less shared data between EL1 and EL2 in the nVHE
     case

   - Tidy up the header file usage for the nvhe hyp object

   - New HYP unsharing mechanism, finally allowing pages to be unmapped
     from the Stage-1 EL2 page-tables

   - Various pKVM cleanups around refcounting and sharing

   - A couple of vgic fixes for bugs that would trigger once the vcpu
     xarray rework is merged, but not sooner

   - Add minimal support for ARMv8.7's PMU extension

   - Rework kvm_pgtable initialisation ahead of the NV work

   - New selftest for IRQ injection

   - Teach selftests about the lack of default IPA space and page sizes

   - Expand sysreg selftest to deal with Pointer Authentication

   - The usual bunch of cleanups and doc update

  s390:

   - fix sigp sense/start/stop/inconsistency

   - cleanups

  x86:

   - Clean up some function prototypes more

   - improved gfn_to_pfn_cache with proper invalidation, used by Xen
     emulation

   - add KVM_IRQ_ROUTING_XEN_EVTCHN and event channel delivery

   - completely remove potential TOC/TOU races in nested SVM consistency
     checks

   - update some PMCs on emulated instructions

   - Intel AMX support (joint work between Thomas and Intel)

   - large MMU cleanups

   - module parameter to disable PMU virtualization

   - cleanup register cache

   - first part of halt handling cleanups

   - Hyper-V enlightened MSR bitmap support for nested hypervisors

  Generic:

   - clean up Makefiles

   - introduce CONFIG_HAVE_KVM_DIRTY_RING

   - optimize memslot lookup using a tree

   - optimize vCPU array usage by converting to xarray"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (268 commits)
  x86/fpu: Fix inline prefix warnings
  selftest: kvm: Add amx selftest
  selftest: kvm: Move struct kvm_x86_state to header
  selftest: kvm: Reorder vcpu_load_state steps for AMX
  kvm: x86: Disable interception for IA32_XFD on demand
  x86/fpu: Provide fpu_sync_guest_vmexit_xfd_state()
  kvm: selftests: Add support for KVM_CAP_XSAVE2
  kvm: x86: Add support for getting/setting expanded xstate buffer
  x86/fpu: Add uabi_size to guest_fpu
  kvm: x86: Add CPUID support for Intel AMX
  kvm: x86: Add XCR0 support for Intel AMX
  kvm: x86: Disable RDMSR interception of IA32_XFD_ERR
  kvm: x86: Emulate IA32_XFD_ERR for guest
  kvm: x86: Intercept #NM for saving IA32_XFD_ERR
  x86/fpu: Prepare xfd_err in struct fpu_guest
  kvm: x86: Add emulation for IA32_XFD
  x86/fpu: Provide fpu_update_guest_xfd() for IA32_XFD emulation
  kvm: x86: Enable dynamic xfeatures at KVM_SET_CPUID2
  x86/fpu: Provide fpu_enable_guest_xfd_features() for KVM
  x86/fpu: Add guest support to xfd_enable_feature()
  ...
2022-01-16 16:15:14 +02:00

402 lines
10 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2012,2013 - ARM Ltd
* Author: Marc Zyngier <marc.zyngier@arm.com>
*
* Derived from arch/arm/kvm/reset.c
* Copyright (C) 2012 - Virtual Open Systems and Columbia University
* Author: Christoffer Dall <c.dall@virtualopensystems.com>
*/
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/kvm_host.h>
#include <linux/kvm.h>
#include <linux/hw_breakpoint.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/types.h>
#include <kvm/arm_arch_timer.h>
#include <asm/cpufeature.h>
#include <asm/cputype.h>
#include <asm/fpsimd.h>
#include <asm/ptrace.h>
#include <asm/kvm_arm.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_mmu.h>
#include <asm/virt.h>
/* Maximum phys_shift supported for any VM on this host */
static u32 kvm_ipa_limit;
/*
* ARMv8 Reset Values
*/
#define VCPU_RESET_PSTATE_EL1 (PSR_MODE_EL1h | PSR_A_BIT | PSR_I_BIT | \
PSR_F_BIT | PSR_D_BIT)
#define VCPU_RESET_PSTATE_SVC (PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | \
PSR_AA32_I_BIT | PSR_AA32_F_BIT)
unsigned int kvm_sve_max_vl;
int kvm_arm_init_sve(void)
{
if (system_supports_sve()) {
kvm_sve_max_vl = sve_max_virtualisable_vl();
/*
* The get_sve_reg()/set_sve_reg() ioctl interface will need
* to be extended with multiple register slice support in
* order to support vector lengths greater than
* VL_ARCH_MAX:
*/
if (WARN_ON(kvm_sve_max_vl > VL_ARCH_MAX))
kvm_sve_max_vl = VL_ARCH_MAX;
/*
* Don't even try to make use of vector lengths that
* aren't available on all CPUs, for now:
*/
if (kvm_sve_max_vl < sve_max_vl())
pr_warn("KVM: SVE vector length for guests limited to %u bytes\n",
kvm_sve_max_vl);
}
return 0;
}
static int kvm_vcpu_enable_sve(struct kvm_vcpu *vcpu)
{
if (!system_supports_sve())
return -EINVAL;
vcpu->arch.sve_max_vl = kvm_sve_max_vl;
/*
* Userspace can still customize the vector lengths by writing
* KVM_REG_ARM64_SVE_VLS. Allocation is deferred until
* kvm_arm_vcpu_finalize(), which freezes the configuration.
*/
vcpu->arch.flags |= KVM_ARM64_GUEST_HAS_SVE;
return 0;
}
/*
* Finalize vcpu's maximum SVE vector length, allocating
* vcpu->arch.sve_state as necessary.
*/
static int kvm_vcpu_finalize_sve(struct kvm_vcpu *vcpu)
{
void *buf;
unsigned int vl;
size_t reg_sz;
int ret;
vl = vcpu->arch.sve_max_vl;
/*
* Responsibility for these properties is shared between
* kvm_arm_init_sve(), kvm_vcpu_enable_sve() and
* set_sve_vls(). Double-check here just to be sure:
*/
if (WARN_ON(!sve_vl_valid(vl) || vl > sve_max_virtualisable_vl() ||
vl > VL_ARCH_MAX))
return -EIO;
reg_sz = vcpu_sve_state_size(vcpu);
buf = kzalloc(reg_sz, GFP_KERNEL_ACCOUNT);
if (!buf)
return -ENOMEM;
ret = kvm_share_hyp(buf, buf + reg_sz);
if (ret) {
kfree(buf);
return ret;
}
vcpu->arch.sve_state = buf;
vcpu->arch.flags |= KVM_ARM64_VCPU_SVE_FINALIZED;
return 0;
}
int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature)
{
switch (feature) {
case KVM_ARM_VCPU_SVE:
if (!vcpu_has_sve(vcpu))
return -EINVAL;
if (kvm_arm_vcpu_sve_finalized(vcpu))
return -EPERM;
return kvm_vcpu_finalize_sve(vcpu);
}
return -EINVAL;
}
bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu)
{
if (vcpu_has_sve(vcpu) && !kvm_arm_vcpu_sve_finalized(vcpu))
return false;
return true;
}
void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu)
{
void *sve_state = vcpu->arch.sve_state;
kvm_vcpu_unshare_task_fp(vcpu);
kvm_unshare_hyp(vcpu, vcpu + 1);
if (sve_state)
kvm_unshare_hyp(sve_state, sve_state + vcpu_sve_state_size(vcpu));
kfree(sve_state);
}
static void kvm_vcpu_reset_sve(struct kvm_vcpu *vcpu)
{
if (vcpu_has_sve(vcpu))
memset(vcpu->arch.sve_state, 0, vcpu_sve_state_size(vcpu));
}
static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
{
/*
* For now make sure that both address/generic pointer authentication
* features are requested by the userspace together and the system
* supports these capabilities.
*/
if (!test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) ||
!test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features) ||
!system_has_full_ptr_auth())
return -EINVAL;
vcpu->arch.flags |= KVM_ARM64_GUEST_HAS_PTRAUTH;
return 0;
}
static bool vcpu_allowed_register_width(struct kvm_vcpu *vcpu)
{
struct kvm_vcpu *tmp;
bool is32bit;
unsigned long i;
is32bit = vcpu_has_feature(vcpu, KVM_ARM_VCPU_EL1_32BIT);
if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1) && is32bit)
return false;
/* MTE is incompatible with AArch32 */
if (kvm_has_mte(vcpu->kvm) && is32bit)
return false;
/* Check that the vcpus are either all 32bit or all 64bit */
kvm_for_each_vcpu(i, tmp, vcpu->kvm) {
if (vcpu_has_feature(tmp, KVM_ARM_VCPU_EL1_32BIT) != is32bit)
return false;
}
return true;
}
/**
* kvm_reset_vcpu - sets core registers and sys_regs to reset value
* @vcpu: The VCPU pointer
*
* This function sets the registers on the virtual CPU struct to their
* architecturally defined reset values, except for registers whose reset is
* deferred until kvm_arm_vcpu_finalize().
*
* Note: This function can be called from two paths: The KVM_ARM_VCPU_INIT
* ioctl or as part of handling a request issued by another VCPU in the PSCI
* handling code. In the first case, the VCPU will not be loaded, and in the
* second case the VCPU will be loaded. Because this function operates purely
* on the memory-backed values of system registers, we want to do a full put if
* we were loaded (handling a request) and load the values back at the end of
* the function. Otherwise we leave the state alone. In both cases, we
* disable preemption around the vcpu reset as we would otherwise race with
* preempt notifiers which also call put/load.
*/
int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
{
struct vcpu_reset_state reset_state;
int ret;
bool loaded;
u32 pstate;
mutex_lock(&vcpu->kvm->lock);
reset_state = vcpu->arch.reset_state;
WRITE_ONCE(vcpu->arch.reset_state.reset, false);
mutex_unlock(&vcpu->kvm->lock);
/* Reset PMU outside of the non-preemptible section */
kvm_pmu_vcpu_reset(vcpu);
preempt_disable();
loaded = (vcpu->cpu != -1);
if (loaded)
kvm_arch_vcpu_put(vcpu);
if (!kvm_arm_vcpu_sve_finalized(vcpu)) {
if (test_bit(KVM_ARM_VCPU_SVE, vcpu->arch.features)) {
ret = kvm_vcpu_enable_sve(vcpu);
if (ret)
goto out;
}
} else {
kvm_vcpu_reset_sve(vcpu);
}
if (test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) ||
test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features)) {
if (kvm_vcpu_enable_ptrauth(vcpu)) {
ret = -EINVAL;
goto out;
}
}
if (!vcpu_allowed_register_width(vcpu)) {
ret = -EINVAL;
goto out;
}
switch (vcpu->arch.target) {
default:
if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) {
pstate = VCPU_RESET_PSTATE_SVC;
} else {
pstate = VCPU_RESET_PSTATE_EL1;
}
if (kvm_vcpu_has_pmu(vcpu) && !kvm_arm_support_pmu_v3()) {
ret = -EINVAL;
goto out;
}
break;
}
/* Reset core registers */
memset(vcpu_gp_regs(vcpu), 0, sizeof(*vcpu_gp_regs(vcpu)));
memset(&vcpu->arch.ctxt.fp_regs, 0, sizeof(vcpu->arch.ctxt.fp_regs));
vcpu->arch.ctxt.spsr_abt = 0;
vcpu->arch.ctxt.spsr_und = 0;
vcpu->arch.ctxt.spsr_irq = 0;
vcpu->arch.ctxt.spsr_fiq = 0;
vcpu_gp_regs(vcpu)->pstate = pstate;
/* Reset system registers */
kvm_reset_sys_regs(vcpu);
/*
* Additional reset state handling that PSCI may have imposed on us.
* Must be done after all the sys_reg reset.
*/
if (reset_state.reset) {
unsigned long target_pc = reset_state.pc;
/* Gracefully handle Thumb2 entry point */
if (vcpu_mode_is_32bit(vcpu) && (target_pc & 1)) {
target_pc &= ~1UL;
vcpu_set_thumb(vcpu);
}
/* Propagate caller endianness */
if (reset_state.be)
kvm_vcpu_set_be(vcpu);
*vcpu_pc(vcpu) = target_pc;
vcpu_set_reg(vcpu, 0, reset_state.r0);
}
/* Reset timer */
ret = kvm_timer_vcpu_reset(vcpu);
out:
if (loaded)
kvm_arch_vcpu_load(vcpu, smp_processor_id());
preempt_enable();
return ret;
}
u32 get_kvm_ipa_limit(void)
{
return kvm_ipa_limit;
}
int kvm_set_ipa_limit(void)
{
unsigned int parange;
u64 mmfr0;
mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
parange = cpuid_feature_extract_unsigned_field(mmfr0,
ID_AA64MMFR0_PARANGE_SHIFT);
/*
* IPA size beyond 48 bits could not be supported
* on either 4K or 16K page size. Hence let's cap
* it to 48 bits, in case it's reported as larger
* on the system.
*/
if (PAGE_SIZE != SZ_64K)
parange = min(parange, (unsigned int)ID_AA64MMFR0_PARANGE_48);
/*
* Check with ARMv8.5-GTG that our PAGE_SIZE is supported at
* Stage-2. If not, things will stop very quickly.
*/
switch (cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_TGRAN_2_SHIFT)) {
case ID_AA64MMFR0_TGRAN_2_SUPPORTED_NONE:
kvm_err("PAGE_SIZE not supported at Stage-2, giving up\n");
return -EINVAL;
case ID_AA64MMFR0_TGRAN_2_SUPPORTED_DEFAULT:
kvm_debug("PAGE_SIZE supported at Stage-2 (default)\n");
break;
case ID_AA64MMFR0_TGRAN_2_SUPPORTED_MIN ... ID_AA64MMFR0_TGRAN_2_SUPPORTED_MAX:
kvm_debug("PAGE_SIZE supported at Stage-2 (advertised)\n");
break;
default:
kvm_err("Unsupported value for TGRAN_2, giving up\n");
return -EINVAL;
}
kvm_ipa_limit = id_aa64mmfr0_parange_to_phys_shift(parange);
kvm_info("IPA Size Limit: %d bits%s\n", kvm_ipa_limit,
((kvm_ipa_limit < KVM_PHYS_SHIFT) ?
" (Reduced IPA size, limited VM/VMM compatibility)" : ""));
return 0;
}
int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type)
{
u64 mmfr0, mmfr1;
u32 phys_shift;
if (type & ~KVM_VM_TYPE_ARM_IPA_SIZE_MASK)
return -EINVAL;
phys_shift = KVM_VM_TYPE_ARM_IPA_SIZE(type);
if (phys_shift) {
if (phys_shift > kvm_ipa_limit ||
phys_shift < ARM64_MIN_PARANGE_BITS)
return -EINVAL;
} else {
phys_shift = KVM_PHYS_SHIFT;
if (phys_shift > kvm_ipa_limit) {
pr_warn_once("%s using unsupported default IPA limit, upgrade your VMM\n",
current->comm);
return -EINVAL;
}
}
mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
kvm->arch.vtcr = kvm_get_vtcr(mmfr0, mmfr1, phys_shift);
return 0;
}