// 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/coproc.c: * Copyright (C) 2012 - Virtual Open Systems and Columbia University * Authors: Rusty Russell <rusty@rustcorp.com.au> * Christoffer Dall <c.dall@virtualopensystems.com>
*/
/* * For AArch32, we only take care of what is being trapped. Anything * that has to do with init and userspace access has to go via the * 64bit interface.
*/
staticenum sr_loc_attr locate_direct_register(conststruct kvm_vcpu *vcpu, enum vcpu_sysreg reg)
{ switch (reg) { case SCTLR_EL1: case CPACR_EL1: case TTBR0_EL1: case TTBR1_EL1: case TCR_EL1: case TCR2_EL1: case PIR_EL1: case PIRE0_EL1: case POR_EL1: case ESR_EL1: case AFSR0_EL1: case AFSR1_EL1: case FAR_EL1: case MAIR_EL1: case VBAR_EL1: case CONTEXTIDR_EL1: case AMAIR_EL1: case CNTKCTL_EL1: case ELR_EL1: case SPSR_EL1: case ZCR_EL1: case SCTLR2_EL1: /* * EL1 registers which have an ELx2 mapping are loaded if * we're not in hypervisor context.
*/ return is_hyp_ctxt(vcpu) ? SR_LOC_MEMORY : SR_LOC_LOADED;
case TPIDR_EL0: case TPIDRRO_EL0: case TPIDR_EL1: case PAR_EL1: case DACR32_EL2: case IFSR32_EL2: case DBGVCR32_EL2: /* These registers are always loaded, no matter what */ return SR_LOC_LOADED;
default: /* Non-mapped EL2 registers are by definition in memory. */ return SR_LOC_MEMORY;
}
}
static u64 read_sr_from_cpu(enum vcpu_sysreg reg)
{
u64 val = 0x8badf00d8badf00d;
switch (reg) { case SCTLR_EL1: val = read_sysreg_s(SYS_SCTLR_EL12); break; case CPACR_EL1: val = read_sysreg_s(SYS_CPACR_EL12); break; case TTBR0_EL1: val = read_sysreg_s(SYS_TTBR0_EL12); break; case TTBR1_EL1: val = read_sysreg_s(SYS_TTBR1_EL12); break; case TCR_EL1: val = read_sysreg_s(SYS_TCR_EL12); break; case TCR2_EL1: val = read_sysreg_s(SYS_TCR2_EL12); break; case PIR_EL1: val = read_sysreg_s(SYS_PIR_EL12); break; case PIRE0_EL1: val = read_sysreg_s(SYS_PIRE0_EL12); break; case POR_EL1: val = read_sysreg_s(SYS_POR_EL12); break; case ESR_EL1: val = read_sysreg_s(SYS_ESR_EL12); break; case AFSR0_EL1: val = read_sysreg_s(SYS_AFSR0_EL12); break; case AFSR1_EL1: val = read_sysreg_s(SYS_AFSR1_EL12); break; case FAR_EL1: val = read_sysreg_s(SYS_FAR_EL12); break; case MAIR_EL1: val = read_sysreg_s(SYS_MAIR_EL12); break; case VBAR_EL1: val = read_sysreg_s(SYS_VBAR_EL12); break; case CONTEXTIDR_EL1: val = read_sysreg_s(SYS_CONTEXTIDR_EL12);break; case AMAIR_EL1: val = read_sysreg_s(SYS_AMAIR_EL12); break; case CNTKCTL_EL1: val = read_sysreg_s(SYS_CNTKCTL_EL12); break; case ELR_EL1: val = read_sysreg_s(SYS_ELR_EL12); break; case SPSR_EL1: val = read_sysreg_s(SYS_SPSR_EL12); break; case ZCR_EL1: val = read_sysreg_s(SYS_ZCR_EL12); break; case SCTLR2_EL1: val = read_sysreg_s(SYS_SCTLR2_EL12); break; case TPIDR_EL0: val = read_sysreg_s(SYS_TPIDR_EL0); break; case TPIDRRO_EL0: val = read_sysreg_s(SYS_TPIDRRO_EL0); break; case TPIDR_EL1: val = read_sysreg_s(SYS_TPIDR_EL1); break; case PAR_EL1: val = read_sysreg_par(); break; case DACR32_EL2: val = read_sysreg_s(SYS_DACR32_EL2); break; case IFSR32_EL2: val = read_sysreg_s(SYS_IFSR32_EL2); break; case DBGVCR32_EL2: val = read_sysreg_s(SYS_DBGVCR32_EL2); break; default: WARN_ON_ONCE(1);
}
return val;
}
staticvoid write_sr_to_cpu(enum vcpu_sysreg reg, u64 val)
{ switch (reg) { case SCTLR_EL1: write_sysreg_s(val, SYS_SCTLR_EL12); break; case CPACR_EL1: write_sysreg_s(val, SYS_CPACR_EL12); break; case TTBR0_EL1: write_sysreg_s(val, SYS_TTBR0_EL12); break; case TTBR1_EL1: write_sysreg_s(val, SYS_TTBR1_EL12); break; case TCR_EL1: write_sysreg_s(val, SYS_TCR_EL12); break; case TCR2_EL1: write_sysreg_s(val, SYS_TCR2_EL12); break; case PIR_EL1: write_sysreg_s(val, SYS_PIR_EL12); break; case PIRE0_EL1: write_sysreg_s(val, SYS_PIRE0_EL12); break; case POR_EL1: write_sysreg_s(val, SYS_POR_EL12); break; case ESR_EL1: write_sysreg_s(val, SYS_ESR_EL12); break; case AFSR0_EL1: write_sysreg_s(val, SYS_AFSR0_EL12); break; case AFSR1_EL1: write_sysreg_s(val, SYS_AFSR1_EL12); break; case FAR_EL1: write_sysreg_s(val, SYS_FAR_EL12); break; case MAIR_EL1: write_sysreg_s(val, SYS_MAIR_EL12); break; case VBAR_EL1: write_sysreg_s(val, SYS_VBAR_EL12); break; case CONTEXTIDR_EL1: write_sysreg_s(val, SYS_CONTEXTIDR_EL12);break; case AMAIR_EL1: write_sysreg_s(val, SYS_AMAIR_EL12); break; case CNTKCTL_EL1: write_sysreg_s(val, SYS_CNTKCTL_EL12); break; case ELR_EL1: write_sysreg_s(val, SYS_ELR_EL12); break; case SPSR_EL1: write_sysreg_s(val, SYS_SPSR_EL12); break; case ZCR_EL1: write_sysreg_s(val, SYS_ZCR_EL12); break; case SCTLR2_EL1: write_sysreg_s(val, SYS_SCTLR2_EL12); break; case TPIDR_EL0: write_sysreg_s(val, SYS_TPIDR_EL0); break; case TPIDRRO_EL0: write_sysreg_s(val, SYS_TPIDRRO_EL0); break; case TPIDR_EL1: write_sysreg_s(val, SYS_TPIDR_EL1); break; case PAR_EL1: write_sysreg_s(val, SYS_PAR_EL1); break; case DACR32_EL2: write_sysreg_s(val, SYS_DACR32_EL2); break; case IFSR32_EL2: write_sysreg_s(val, SYS_IFSR32_EL2); break; case DBGVCR32_EL2: write_sysreg_s(val, SYS_DBGVCR32_EL2); break; default: WARN_ON_ONCE(1);
}
}
/* * CNTHCTL_EL2 requires some special treatment to account * for the bits that can be set via CNTKCTL_EL1 when E2H==1.
*/ switch (reg) { case CNTHCTL_EL2:
val = read_sysreg_el1(SYS_CNTKCTL);
val &= CNTKCTL_VALID_BITS;
val |= __vcpu_sys_reg(vcpu, reg) & ~CNTKCTL_VALID_BITS; return val; default:
WARN_ON_ONCE(1);
}
}
if (loc.loc & SR_LOC_LOADED) { enum vcpu_sysreg map_reg = reg;
if (loc.loc & SR_LOC_MAPPED)
map_reg = loc.map_reg;
if (!(loc.loc & SR_LOC_XLATED)) {
u64 val = read_sr_from_cpu(map_reg);
if (reg >= __SANITISED_REG_START__)
val = kvm_vcpu_apply_reg_masks(vcpu, reg, val);
switch (reg) { case CNTHCTL_EL2: /* * If E2H=1, some of the bits are backed by * CNTKCTL_EL1, while the rest is kept in memory. * Yes, this is fun stuff.
*/
write_sysreg_el1(val, SYS_CNTKCTL); break; default:
WARN_ON_ONCE(1);
}
}
/* * Fabricate a CCSIDR value as the overriding value does not exist. * The real CCSIDR value will not be used as it can vary by the * physical CPU which the vcpu currently resides in. * * The line size is determined with get_min_cache_line_size(), which * should be valid for all CPUs even if they have different cache * configuration. * * The associativity bits are cleared, meaning the geometry of all data * and unified caches (which are guaranteed to be PIPT and thus * non-aliasing) are 1 set and 1 way. * Guests should not be doing cache operations by set/way at all, and * for this reason, we trap them and attempt to infer the intent, so * that we can flush the entire guest's address space at the appropriate * time. The exposed geometry minimizes the number of the traps. * [If guests should attempt to infer aliasing properties from the * geometry (which is not permitted by the architecture), they would * only do so for virtually indexed caches.] * * We don't check if the cache level exists as it is allowed to return * an UNKNOWN value if not.
*/ return SYS_FIELD_PREP(CCSIDR_EL1, LineSize, line_size - 4);
}
/* * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized).
*/ staticbool access_dcsw(struct kvm_vcpu *vcpu, struct sys_reg_params *p, conststruct sys_reg_desc *r)
{ if (!p->is_write) return read_from_write_only(vcpu, p, r);
/* * Only track S/W ops if we don't have FWB. It still indicates * that the guest is a bit broken (S/W operations should only * be done by firmware, knowing that there is only a single * CPU left in the system, and certainly not from non-secure * software).
*/ if (!cpus_have_final_cap(ARM64_HAS_STAGE2_FWB))
kvm_set_way_flush(vcpu);
/* * Generic accessor for VM registers. Only called as long as HCR_TVM * is set. If the guest enables the MMU, we stop trapping the VM * sys_regs and leave it in complete control of the caches.
*/ staticbool access_vm_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *p, conststruct sys_reg_desc *r)
{ bool was_enabled = vcpu_has_cache_enabled(vcpu);
u64 val, mask, shift;
BUG_ON(!p->is_write);
get_access_mask(r, &mask, &shift);
if (~mask) {
val = vcpu_read_sys_reg(vcpu, r->reg);
val &= ~mask;
} else {
val = 0;
}
/* * Trap handler for the GICv3 SGI generation system register. * Forward the request to the VGIC emulation. * The cp15_64 code makes sure this automatically works * for both AArch64 and AArch32 accesses.
*/ staticbool access_gic_sgi(struct kvm_vcpu *vcpu, struct sys_reg_params *p, conststruct sys_reg_desc *r)
{ bool g1;
if (!kvm_has_gicv3(vcpu->kvm)) return undef_access(vcpu, p, r);
if (!p->is_write) return read_from_write_only(vcpu, p, r);
/* * In a system where GICD_CTLR.DS=1, a ICC_SGI0R_EL1 access generates * Group0 SGIs only, while ICC_SGI1R_EL1 can generate either group, * depending on the SGI configuration. ICC_ASGI1R_EL1 is effectively * equivalent to ICC_SGI0R_EL1, as there is no "alternative" secure * group.
*/ if (p->Op0 == 0) { /* AArch32 */ switch (p->Op1) { default: /* Keep GCC quiet */ case 0: /* ICC_SGI1R */
g1 = true; break; case 1: /* ICC_ASGI1R */ case 2: /* ICC_SGI0R */
g1 = false; break;
}
} else { /* AArch64 */ switch (p->Op2) { default: /* Keep GCC quiet */ case 5: /* ICC_SGI1R_EL1 */
g1 = true; break; case 6: /* ICC_ASGI1R_EL1 */ case 7: /* ICC_SGI0R_EL1 */
g1 = false; break;
}
}
/* * ARMv8.1 mandates at least a trivial LORegion implementation, where all the * RW registers are RES0 (which we can implement as RAZ/WI). On an ARMv8.0 * system, these registers should UNDEF. LORID_EL1 being a RO register, we * treat it separately.
*/ staticbool trap_loregion(struct kvm_vcpu *vcpu, struct sys_reg_params *p, conststruct sys_reg_desc *r)
{
u32 sr = reg_to_encoding(r);
if (!kvm_has_feat(vcpu->kvm, ID_AA64MMFR1_EL1, LO, IMP)) return undef_access(vcpu, p, r);
if (p->is_write && sr == SYS_LORID_EL1) return write_to_read_only(vcpu, p, r);
staticint set_oslsr_el1(struct kvm_vcpu *vcpu, conststruct sys_reg_desc *rd,
u64 val)
{ /* * The only modifiable bit is the OSLK bit. Refuse the write if * userspace attempts to change any other bit in the register.
*/ if ((val ^ rd->val) & ~OSLSR_EL1_OSLK) return -EINVAL;
/* * reg_to_dbg/dbg_to_reg * * A 32 bit write to a debug register leave top bits alone * A 32 bit read from a debug register only returns the bottom bits
*/ staticvoid reg_to_dbg(struct kvm_vcpu *vcpu, struct sys_reg_params *p, conststruct sys_reg_desc *rd,
u64 *dbg_reg)
{
u64 mask, shift, val;
get_access_mask(rd, &mask, &shift);
val = *dbg_reg;
val &= ~mask;
val |= (p->regval & (mask >> shift)) << shift;
*dbg_reg = val;
}
/* * Bail early if we couldn't find storage for the register, the * KVM_BUG_ON() in demux_wb_reg() will prevent this VM from ever * being run.
*/ if (!reg) return 0;
/* * Map the vcpu_id into the first three affinity level fields of * the MPIDR. We limit the number of VCPUs in level 0 due to a * limitation to 16 CPUs in that level in the ICC_SGIxR registers * of the GICv3 to be able to address each CPU directly when * sending IPIs.
*/
mpidr = (vcpu->vcpu_id & 0x0f) << MPIDR_LEVEL_SHIFT(0);
mpidr |= ((vcpu->vcpu_id >> 4) & 0xff) << MPIDR_LEVEL_SHIFT(1);
mpidr |= ((vcpu->vcpu_id >> 12) & 0xff) << MPIDR_LEVEL_SHIFT(2);
mpidr |= (1ULL << 31);
vcpu_write_sys_reg(vcpu, mpidr, MPIDR_EL1);
static u64 reset_pmevtyper(struct kvm_vcpu *vcpu, conststruct sys_reg_desc *r)
{ /* This thing will UNDEF, who cares about the reset value? */ if (!kvm_vcpu_has_pmu(vcpu)) return 0;
if (p->is_write) { /* * Only update writeable bits of PMCR (continuing into * kvm_pmu_handle_pmcr() as well)
*/
val = kvm_vcpu_read_pmcr(vcpu);
val &= ~ARMV8_PMU_PMCR_MASK;
val |= p->regval & ARMV8_PMU_PMCR_MASK; if (!kvm_supports_32bit_el0())
val |= ARMV8_PMU_PMCR_LC;
kvm_pmu_handle_pmcr(vcpu, val);
} else { /* PMCR.P & PMCR.C are RAZ */
val = kvm_vcpu_read_pmcr(vcpu)
& ~(ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C);
p->regval = val;
}
/* * The vCPU can't have more counters than the PMU hardware * implements. Ignore this error to maintain compatibility * with the existing KVM behavior.
*/ if (!kvm_vm_has_ran_once(kvm) &&
!vcpu_has_nv(vcpu) &&
new_n <= kvm_arm_pmu_get_max_counters(kvm))
kvm->arch.nr_pmu_counters = new_n;
mutex_unlock(&kvm->arch.config_lock);
/* * Ignore writes to RES0 bits, read only bits that are cleared on * vCPU reset, and writable bits that KVM doesn't support yet. * (i.e. only PMCR.N and bits [7:0] are mutable from userspace) * The LP bit is RES0 when FEAT_PMUv3p5 is not supported on the vCPU. * But, we leave the bit as it is here, as the vCPU's PMUver might * be changed later (NOTE: the bit will be cleared on first vCPU run * if necessary).
*/
val &= ARMV8_PMU_PMCR_MASK;
/* The LC bit is RES1 when AArch32 is not supported */ if (!kvm_supports_32bit_el0())
val |= ARMV8_PMU_PMCR_LC;
/* * If we land here on a PtrAuth access, that is because we didn't * fixup the access on exit by allowing the PtrAuth sysregs. The only * way this happens is when the guest does not have PtrAuth support * enabled.
*/ #define __PTRAUTH_KEY(k) \
{ SYS_DESC(SYS_## k), undef_access, reset_unknown, k, \
.visibility = ptrauth_visibility}
/* Some features have different safe value type in KVM than host features */ switch (id) { case SYS_ID_AA64DFR0_EL1: switch (kvm_ftr.shift) { case ID_AA64DFR0_EL1_PMUVer_SHIFT:
kvm_ftr.type = FTR_LOWER_SAFE; break; case ID_AA64DFR0_EL1_DebugVer_SHIFT:
kvm_ftr.type = FTR_LOWER_SAFE; break;
} break; case SYS_ID_DFR0_EL1: if (kvm_ftr.shift == ID_DFR0_EL1_PerfMon_SHIFT)
kvm_ftr.type = FTR_LOWER_SAFE; break;
}
/* * arm64_check_features() - Check if a feature register value constitutes * a subset of features indicated by the idreg's KVM sanitised limit. * * This function will check if each feature field of @val is the "safe" value * against idreg's KVM sanitised limit return from reset() callback. * If a field value in @val is the same as the one in limit, it is always * considered the safe value regardless For register fields that are not in * writable, only the value in limit is considered the safe value. * * Return: 0 if all the fields are safe. Otherwise, return negative errno.
*/ staticint arm64_check_features(struct kvm_vcpu *vcpu, conststruct sys_reg_desc *rd,
u64 val)
{ conststruct arm64_ftr_reg *ftr_reg; conststruct arm64_ftr_bits *ftrp = NULL;
u32 id = reg_to_encoding(rd);
u64 writable_mask = rd->val;
u64 limit = rd->reset(vcpu, rd);
u64 mask = 0;
/* * Hidden and unallocated ID registers may not have a corresponding * struct arm64_ftr_reg. Of course, if the register is RAZ we know the * only safe value is 0.
*/ if (sysreg_visible_as_raz(vcpu, rd)) return val ? -E2BIG : 0;
ftr_reg = get_arm64_ftr_reg(id); if (!ftr_reg) return -EINVAL;
/* For fields that are not writable, values in limit are the safe values. */ if ((val & ~mask) != (limit & ~mask)) return -E2BIG;
return 0;
}
static u8 pmuver_to_perfmon(u8 pmuver)
{ switch (pmuver) { case ID_AA64DFR0_EL1_PMUVer_IMP: return ID_DFR0_EL1_PerfMon_PMUv3; case ID_AA64DFR0_EL1_PMUVer_IMP_DEF: return ID_DFR0_EL1_PerfMon_IMPDEF; default: /* Anything ARMv8.1+ and NI have the same value. For now. */ return pmuver;
}
}
/* Read a sanitised cpufeature ID register by sys_reg_desc */ static u64 __kvm_read_sanitised_id_reg(conststruct kvm_vcpu *vcpu, conststruct sys_reg_desc *r)
{
u32 id = reg_to_encoding(r);
u64 val;
if (sysreg_visible_as_raz(vcpu, r)) return 0;
val = read_sanitised_ftr_reg(id);
switch (id) { case SYS_ID_AA64DFR0_EL1:
val = sanitise_id_aa64dfr0_el1(vcpu, val); break; case SYS_ID_AA64PFR0_EL1:
val = sanitise_id_aa64pfr0_el1(vcpu, val); break; case SYS_ID_AA64PFR1_EL1:
val = sanitise_id_aa64pfr1_el1(vcpu, val); break; case SYS_ID_AA64PFR2_EL1:
val &= ID_AA64PFR2_EL1_FPMR |
(kvm_has_mte(vcpu->kvm) ?
ID_AA64PFR2_EL1_MTEFAR | ID_AA64PFR2_EL1_MTESTOREONLY :
0); break; case SYS_ID_AA64ISAR1_EL1: if (!vcpu_has_ptrauth(vcpu))
val &= ~(ID_AA64ISAR1_EL1_APA |
ID_AA64ISAR1_EL1_API |
ID_AA64ISAR1_EL1_GPA |
ID_AA64ISAR1_EL1_GPI); break; case SYS_ID_AA64ISAR2_EL1: if (!vcpu_has_ptrauth(vcpu))
val &= ~(ID_AA64ISAR2_EL1_APA3 |
ID_AA64ISAR2_EL1_GPA3); if (!cpus_have_final_cap(ARM64_HAS_WFXT) ||
has_broken_cntvoff())
val &= ~ID_AA64ISAR2_EL1_WFxT; break; case SYS_ID_AA64ISAR3_EL1:
val &= ID_AA64ISAR3_EL1_FPRCVT | ID_AA64ISAR3_EL1_FAMINMAX; break; case SYS_ID_AA64MMFR2_EL1:
val &= ~ID_AA64MMFR2_EL1_CCIDX_MASK;
val &= ~ID_AA64MMFR2_EL1_NV; break; case SYS_ID_AA64MMFR3_EL1:
val &= ID_AA64MMFR3_EL1_TCRX |
ID_AA64MMFR3_EL1_SCTLRX |
ID_AA64MMFR3_EL1_S1POE |
ID_AA64MMFR3_EL1_S1PIE; break; case SYS_ID_MMFR4_EL1:
val &= ~ID_MMFR4_EL1_CCIDX; break;
}
if (vcpu_has_nv(vcpu))
val = limit_nv_id_reg(vcpu->kvm, id, val);
/* * Return true if the register's (Op0, Op1, CRn, CRm, Op2) is * (3, 0, 0, crm, op2), where 1<=crm<8, 0<=op2<8, which is the range of ID * registers KVM maintains on a per-VM basis. * * Additionally, the implementation ID registers and CTR_EL0 are handled as * per-VM registers.
*/ staticinlinebool is_vm_ftr_id_reg(u32 id)
{ switch (id) { case SYS_CTR_EL0: case SYS_MIDR_EL1: case SYS_REVIDR_EL1: case SYS_AIDR_EL1: returntrue; default: return (sys_reg_Op0(id) == 3 && sys_reg_Op1(id) == 0 &&
sys_reg_CRn(id) == 0 && sys_reg_CRm(id) >= 1 &&
sys_reg_CRm(id) < 8);
switch (id) { case SYS_ID_AA64ZFR0_EL1: if (!vcpu_has_sve(vcpu)) return REG_RAZ; break;
}
return 0;
}
staticunsignedint aa32_id_visibility(conststruct kvm_vcpu *vcpu, conststruct sys_reg_desc *r)
{ /* * AArch32 ID registers are UNKNOWN if AArch32 isn't implemented at any * EL. Promote to RAZ/WI in order to guarantee consistency between * systems.
*/ if (!kvm_supports_32bit_el0()) return REG_RAZ | REG_USER_WI;
static u64 sanitise_id_aa64pfr0_el1(conststruct kvm_vcpu *vcpu, u64 val)
{ if (!vcpu_has_sve(vcpu))
val &= ~ID_AA64PFR0_EL1_SVE_MASK;
/* * The default is to expose CSV2 == 1 if the HW isn't affected. * Although this is a per-CPU feature, we make it global because * asymmetric systems are just a nuisance. * * Userspace can override this as long as it doesn't promise * the impossible.
*/ if (arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED) {
val &= ~ID_AA64PFR0_EL1_CSV2_MASK;
val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, CSV2, IMP);
} if (arm64_get_meltdown_state() == SPECTRE_UNAFFECTED) {
val &= ~ID_AA64PFR0_EL1_CSV3_MASK;
val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, CSV3, IMP);
}
if (vgic_is_v3(vcpu->kvm)) {
val &= ~ID_AA64PFR0_EL1_GIC_MASK;
val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, GIC, IMP);
}
val &= ~ID_AA64PFR0_EL1_AMU_MASK;
/* * MPAM is disabled by default as KVM also needs a set of PARTID to * program the MPAMVPMx_EL2 PARTID remapping registers with. But some * older kernels let the guest see the ID bit.
*/
val &= ~ID_AA64PFR0_EL1_MPAM_MASK;
if (!kvm_has_mte(vcpu->kvm)) {
val &= ~ID_AA64PFR1_EL1_MTE;
val &= ~ID_AA64PFR1_EL1_MTE_frac;
}
if (!(cpus_have_final_cap(ARM64_HAS_RASV1P1_EXTN) &&
SYS_FIELD_GET(ID_AA64PFR0_EL1, RAS, pfr0) == ID_AA64PFR0_EL1_RAS_IMP))
val &= ~ID_AA64PFR1_EL1_RAS_frac;
val &= ~ID_AA64PFR1_EL1_SME;
val &= ~ID_AA64PFR1_EL1_RNDR_trap;
val &= ~ID_AA64PFR1_EL1_NMI;
val &= ~ID_AA64PFR1_EL1_GCS;
val &= ~ID_AA64PFR1_EL1_THE;
val &= ~ID_AA64PFR1_EL1_MTEX;
val &= ~ID_AA64PFR1_EL1_PFAR;
val &= ~ID_AA64PFR1_EL1_MPAM_frac;
/* * Only initialize the PMU version if the vCPU was configured with one.
*/
val &= ~ID_AA64DFR0_EL1_PMUVer_MASK; if (kvm_vcpu_has_pmu(vcpu))
val |= SYS_FIELD_PREP(ID_AA64DFR0_EL1, PMUVer,
kvm_arm_pmu_get_pmuver_limit());
/* Hide SPE from guests */
val &= ~ID_AA64DFR0_EL1_PMSVer_MASK;
/* Hide BRBE from guests */
val &= ~ID_AA64DFR0_EL1_BRBE_MASK;
/* * Prior to commit 3d0dba5764b9 ("KVM: arm64: PMU: Move the * ID_AA64DFR0_EL1.PMUver limit to VM creation"), KVM erroneously * exposed an IMP_DEF PMU to userspace and the guest on systems w/ * non-architectural PMUs. Of course, PMUv3 is the only game in town for * PMU virtualization, so the IMP_DEF value was rather user-hostile. * * At minimum, we're on the hook to allow values that were given to * userspace by KVM. Cover our tracks here and replace the IMP_DEF value * with a more sensible NI. The value of an ID register changing under * the nose of the guest is unfortunate, but is certainly no more * surprising than an ill-guided PMU driver poking at impdef system * registers that end in an UNDEF...
*/ if (pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF)
val &= ~ID_AA64DFR0_EL1_PMUVer_MASK;
/* * ID_AA64DFR0_EL1.DebugVer is one of those awkward fields with a * nonzero minimum safe value.
*/ if (debugver < ID_AA64DFR0_EL1_DebugVer_IMP) return -EINVAL;
val &= ~ID_DFR0_EL1_PerfMon_MASK; if (kvm_vcpu_has_pmu(vcpu)) {
perfmon = pmuver_to_perfmon(kvm_arm_pmu_get_pmuver_limit());
val |= SYS_FIELD_PREP(ID_DFR0_EL1, PerfMon, perfmon);
}
val = ID_REG_LIMIT_FIELD_ENUM(val, ID_DFR0_EL1, CopDbg, Debugv8p8);
if (perfmon == ID_DFR0_EL1_PerfMon_IMPDEF) {
val &= ~ID_DFR0_EL1_PerfMon_MASK;
perfmon = 0;
}
/* * Allow DFR0_EL1.PerfMon to be set from userspace as long as * it doesn't promise more than what the HW gives us on the * AArch64 side (as everything is emulated with that), and * that this is a PMUv3.
*/ if (perfmon != 0 && perfmon < ID_DFR0_EL1_PerfMon_PMUv3) return -EINVAL;
if (copdbg < ID_DFR0_EL1_CopDbg_Armv8) return -EINVAL;
/* * Commit 011e5f5bf529f ("arm64/cpufeature: Add remaining feature bits * in ID_AA64PFR0 register") exposed the MPAM field of AA64PFR0_EL1 to * guests, but didn't add trap handling. KVM doesn't support MPAM and * always returns an UNDEF for these registers. The guest must see 0 * for this field. * * But KVM must also accept values from user-space that were provided * by KVM. On CPUs that support MPAM, permit user-space to write * the sanitizied value to ID_AA64PFR0_EL1.MPAM, but ignore this field.
*/ if ((hw_val & mpam_mask) == (user_val & mpam_mask))
user_val &= ~ID_AA64PFR0_EL1_MPAM_MASK;
/* Fail the guest's request to disable the AA64 ISA at EL{0,1,2} */ if (!FIELD_GET(ID_AA64PFR0_EL1_EL0, user_val) ||
!FIELD_GET(ID_AA64PFR0_EL1_EL1, user_val) ||
(vcpu_has_nv(vcpu) && !FIELD_GET(ID_AA64PFR0_EL1_EL2, user_val))) return -EINVAL;
/* * If we are running on a GICv5 host and support FEAT_GCIE_LEGACY, then * we support GICv3. Fail attempts to do anything but set that to IMP.
*/ if (vgic_is_v3_compat(vcpu->kvm) &&
FIELD_GET(ID_AA64PFR0_EL1_GIC_MASK, user_val) != ID_AA64PFR0_EL1_GIC_IMP) return -EINVAL;
/* See set_id_aa64pfr0_el1 for comment about MPAM */ if ((hw_val & mpam_mask) == (user_val & mpam_mask))
user_val &= ~ID_AA64PFR1_EL1_MPAM_frac_MASK;
/* * Previously MTE_frac was hidden from guest. However, if the * hardware supports MTE2 but not MTE_ASYM_FAULT then a value * of 0 for this field indicates that the hardware supports * MTE_ASYNC. Whereas, 0xf indicates MTE_ASYNC is not supported. * * As KVM must accept values from KVM provided by user-space, * when ID_AA64PFR1_EL1.MTE is 2 allow user-space to set * ID_AA64PFR1_EL1.MTE_frac to 0. However, ignore it to avoid * incorrectly claiming hardware support for MTE_ASYNC in the * guest.
*/
/* * We made the mistake to expose the now deprecated NV field, * so allow userspace to write it, but silently ignore it.
*/ if ((hw_val & nv_mask) == (user_val & nv_mask))
user_val &= ~nv_mask;
/* * Both AIVIVT (0b01) and VPIPT (0b00) are documented as reserved. * Hence only allow to set VIPT(0b10) or PIPT(0b11) for L1Ip based * on what hardware reports. * * Using a VIPT software model on PIPT will lead to over invalidation, * but still correct. Hence, we can allow downgrading PIPT to VIPT, * but not the other way around. This is handled via arm64_ftr_safe_value() * as CTR_EL0 ftr_bits has L1Ip field with type FTR_EXACT and safe value * set as VIPT.
*/ switch (user_L1Ip) { case CTR_EL0_L1Ip_RESERVED_VPIPT: case CTR_EL0_L1Ip_RESERVED_AIVIVT: return -EINVAL; case CTR_EL0_L1Ip_VIPT: case CTR_EL0_L1Ip_PIPT: return set_id_reg(vcpu, rd, user_val); default: return -ENOENT;
}
}
/* * cpufeature ID register user accessors * * For now, these registers are immutable for userspace, so no values * are stored, and for set_id_reg() we don't allow the effective value * to be changed.
*/ staticint get_id_reg(struct kvm_vcpu *vcpu, conststruct sys_reg_desc *rd,
u64 *val)
{ /* * Avoid locking if the VM has already started, as the ID registers are * guaranteed to be invariant at that point.
*/ if (kvm_vm_has_ran_once(vcpu->kvm)) {
*val = read_id_reg(vcpu, rd); return 0;
}
staticint set_id_reg(struct kvm_vcpu *vcpu, conststruct sys_reg_desc *rd,
u64 val)
{
u32 id = reg_to_encoding(rd); int ret;
mutex_lock(&vcpu->kvm->arch.config_lock);
/* * Once the VM has started the ID registers are immutable. Reject any * write that does not match the final register value.
*/ if (kvm_vm_has_ran_once(vcpu->kvm)) { if (val != read_id_reg(vcpu, rd))
ret = -EBUSY; else
ret = 0;
ret = arm64_check_features(vcpu, rd, val); if (!ret)
kvm_set_vm_id_reg(vcpu->kvm, id, val);
mutex_unlock(&vcpu->kvm->arch.config_lock);
/* * arm64_check_features() returns -E2BIG to indicate the register's * feature set is a superset of the maximally-allowed register value. * While it would be nice to precisely describe this to userspace, the * existing UAPI for KVM_SET_ONE_REG has it that invalid register * writes return -EINVAL.
*/ if (ret == -E2BIG)
ret = -EINVAL; return ret;
}
/* * Fabricate a CLIDR_EL1 value instead of using the real value, which can vary * by the physical CPU which the vcpu currently resides in.
*/ static u64 reset_clidr(struct kvm_vcpu *vcpu, conststruct sys_reg_desc *r)
{
u64 ctr_el0 = read_sanitised_ftr_reg(SYS_CTR_EL0);
u64 clidr;
u8 loc;
if ((ctr_el0 & CTR_EL0_IDC)) { /* * Data cache clean to the PoU is not required so LoUU and LoUIS * will not be set and a unified cache, which will be marked as * LoC, will be added. * * If not DIC, let the unified cache L2 so that an instruction * cache can be added as L1 later.
*/
loc = (ctr_el0 & CTR_EL0_DIC) ? 1 : 2;
clidr = CACHE_TYPE_UNIFIED << CLIDR_CTYPE_SHIFT(loc);
} else { /* * Data cache clean to the PoU is required so let L1 have a data * cache and mark it as LoUU and LoUIS. As L1 has a data cache, * it can be marked as LoC too.
*/
loc = 1;
clidr = 1 << CLIDR_LOUU_SHIFT;
clidr |= 1 << CLIDR_LOUIS_SHIFT;
clidr |= CACHE_TYPE_DATA << CLIDR_CTYPE_SHIFT(1);
}
/* * Instruction cache invalidation to the PoU is required so let L1 have * an instruction cache. If L1 already has a data cache, it will be * CACHE_TYPE_SEPARATE.
*/ if (!(ctr_el0 & CTR_EL0_DIC))
clidr |= CACHE_TYPE_INST << CLIDR_CTYPE_SHIFT(1);
clidr |= loc << CLIDR_LOC_SHIFT;
/* * Add tag cache unified to data cache. Allocation tags and data are * unified in a cache line so that it looks valid even if there is only * one cache line.
*/ if (kvm_has_mte(vcpu->kvm))
clidr |= 2ULL << CLIDR_TTYPE_SHIFT(loc);
staticbool bad_vncr_trap(struct kvm_vcpu *vcpu, struct sys_reg_params *p, conststruct sys_reg_desc *r)
{ /* * We really shouldn't be here, and this is likely the result * of a misconfigured trap, as this register should target the * VNCR page, and nothing else.
*/ return bad_trap(vcpu, p, r, "trap of VNCR-backed register");
}
staticbool bad_redir_trap(struct kvm_vcpu *vcpu, struct sys_reg_params *p, conststruct sys_reg_desc *r)
{ /* * We really shouldn't be here, and this is likely the result * of a misconfigured trap, as this register should target the * corresponding EL1, and nothing else.
*/ return bad_trap(vcpu, p, r, "trap of EL2 register redirected to EL1");
}
/* * Since reset() callback and field val are not used for idregs, they will be * used for specific purposes for idregs. * The reset() would return KVM sanitised register value. The value would be the * same as the host kernel sanitised value if there is no KVM sanitisation. * The val would be used as a mask indicating writable fields for the idreg. * Only bits with 1 are writable from userspace. This mask might not be * necessary in the future whenever all ID registers are enabled as writable * from userspace.
*/
/* sys_reg_desc initialiser for known cpufeature ID registers */ #define ID_SANITISED(name) { \
ID_DESC(name), \
.val = 0, \
}
/* sys_reg_desc initialiser for writable ID registers */ #define ID_WRITABLE(name, mask) { \
ID_DESC(name), \
.val = mask, \
}
/* * 32bit ID regs are fully writable when the guest is 32bit * capable. Nothing in the KVM code should rely on 32bit features * anyway, only 64bit, so let the VMM do its worse.
*/ #define AA32_ID_WRITABLE(name) { \
ID_DESC(name), \
.visibility = aa32_id_visibility, \
.val = GENMASK(31, 0), \
}
/* sys_reg_desc initialiser for cpufeature ID registers that need filtering */ #define ID_FILTERED(sysreg, name, mask) { \
ID_DESC(sysreg), \
.set_user = set_##name, \
.val = (mask), \
}
/* * sys_reg_desc initialiser for known ID registers that we hide from guests. * For now, these are exposed just like unallocated ID regs: they appear * RAZ for the guest.
*/ #define ID_HIDDEN(name) { \
ID_DESC(name), \
.visibility = raz_visibility, \
.val = 0, \
}
if (!p->is_write) {
p->regval = old; returntrue;
}
val = p->regval;
hpmn = FIELD_GET(MDCR_EL2_HPMN, val);
/* * If HPMN is out of bounds, limit it to what we actually * support. This matches the UNKNOWN definition of the field * in that case, and keeps the emulation simple. Sort of.
*/ if (hpmn > vcpu->kvm->arch.nr_pmu_counters) {
hpmn = vcpu->kvm->arch.nr_pmu_counters;
u64p_replace_bits(&val, hpmn, MDCR_EL2_HPMN);
}
__vcpu_assign_sys_reg(vcpu, MDCR_EL2, val);
/* * Request a reload of the PMU to enable/disable the counters * affected by HPME.
*/ if ((old ^ val) & MDCR_EL2_HPME)
kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
switch(reg_to_encoding(r)) { case SYS_ERXPFGCDN_EL1: case SYS_ERXPFGCTL_EL1: case SYS_ERXPFGF_EL1: case SYS_ERXMISC2_EL1: case SYS_ERXMISC3_EL1: if (!(kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, V1P1) ||
(kvm_has_feat_enum(kvm, ID_AA64PFR0_EL1, RAS, IMP) &&
kvm_has_feat(kvm, ID_AA64PFR1_EL1, RAS_frac, RASv1p1)))) {
kvm_inject_undefined(vcpu); returnfalse;
} break; default: if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, IMP)) {
kvm_inject_undefined(vcpu); returnfalse;
}
}
return trap_raz_wi(vcpu, p, r);
}
/* * For historical (ahem ABI) reasons, KVM treated MIDR_EL1, REVIDR_EL1, and * AIDR_EL1 as "invariant" registers, meaning userspace cannot change them. * The values made visible to userspace were the register values of the boot * CPU. * * At the same time, reads from these registers at EL1 previously were not * trapped, allowing the guest to read the actual hardware value. On big-little * machines, this means the VM can see different values depending on where a * given vCPU got scheduled. * * These registers are now trapped as collateral damage from SME, and what * follows attempts to give a user / guest view consistent with the existing * ABI.
*/ staticbool access_imp_id_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *p, conststruct sys_reg_desc *r)
{ if (p->is_write) return write_to_read_only(vcpu, p, r);
/* * Return the VM-scoped implementation ID register values if userspace * has made them writable.
*/ if (test_bit(KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS, &vcpu->kvm->arch.flags)) return access_id_reg(vcpu, p, r);
/* * Otherwise, fall back to the old behavior of returning the value of * the current CPU.
*/ switch (reg_to_encoding(r)) { case SYS_REVIDR_EL1:
p->regval = read_sysreg(revidr_el1); break; case SYS_AIDR_EL1:
p->regval = read_sysreg(aidr_el1); break; default:
WARN_ON_ONCE(1);
}
expected = read_id_reg(vcpu, r); if (expected == val) return 0;
if (!test_bit(KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS, &kvm->arch.flags)) return -EINVAL;
/* * Once the VM has started the ID registers are immutable. Reject the * write if userspace tries to change it.
*/ if (kvm_vm_has_ran_once(kvm)) return -EBUSY;
/* * Any value is allowed for the implementation ID registers so long as * it is within the writable mask.
*/ if ((val & r->val) != val) return -EINVAL;
/* * Architected system registers. * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2 * * Debug handling: We do trap most, if not all debug related system * registers. The implementation is good enough to ensure that a guest * can use these with minimal performance degradation. The drawback is * that we don't implement any of the external debug architecture. * This should be revisited if we ever encounter a more demanding * guest...
*/ staticconststruct sys_reg_desc sys_reg_descs[] = {
DBG_BCR_BVR_WCR_WVR_EL1(0),
DBG_BCR_BVR_WCR_WVR_EL1(1),
{ SYS_DESC(SYS_MDCCINT_EL1), trap_debug_regs, reset_val, MDCCINT_EL1, 0 },
{ SYS_DESC(SYS_MDSCR_EL1), trap_debug_regs, reset_val, MDSCR_EL1, 0 },
DBG_BCR_BVR_WCR_WVR_EL1(2),
DBG_BCR_BVR_WCR_WVR_EL1(3),
DBG_BCR_BVR_WCR_WVR_EL1(4),
DBG_BCR_BVR_WCR_WVR_EL1(5),
DBG_BCR_BVR_WCR_WVR_EL1(6),
DBG_BCR_BVR_WCR_WVR_EL1(7),
DBG_BCR_BVR_WCR_WVR_EL1(8),
DBG_BCR_BVR_WCR_WVR_EL1(9),
DBG_BCR_BVR_WCR_WVR_EL1(10),
DBG_BCR_BVR_WCR_WVR_EL1(11),
DBG_BCR_BVR_WCR_WVR_EL1(12),
DBG_BCR_BVR_WCR_WVR_EL1(13),
DBG_BCR_BVR_WCR_WVR_EL1(14),
DBG_BCR_BVR_WCR_WVR_EL1(15),
/* CRm=5 */ /* * Prior to FEAT_Debugv8.9, the architecture defines context-aware * breakpoints (CTX_CMPs) as the highest numbered breakpoints (BRPs). * KVM does not trap + emulate the breakpoint registers, and as such * cannot support a layout that misaligns with the underlying hardware. * While it may be possible to describe a subset that aligns with * hardware, just prevent changes to BRPs and CTX_CMPs altogether for * simplicity. * * See DDI0487K.a, section D2.8.3 Breakpoint types and linking * of breakpoints for more details.
*/
ID_FILTERED(ID_AA64DFR0_EL1, id_aa64dfr0_el1,
ID_AA64DFR0_EL1_DoubleLock_MASK |
ID_AA64DFR0_EL1_WRPs_MASK |
ID_AA64DFR0_EL1_PMUVer_MASK |
ID_AA64DFR0_EL1_DebugVer_MASK),
ID_SANITISED(ID_AA64DFR1_EL1),
ID_UNALLOCATED(5,2),
ID_UNALLOCATED(5,3),
ID_HIDDEN(ID_AA64AFR0_EL1),
ID_HIDDEN(ID_AA64AFR1_EL1),
ID_UNALLOCATED(5,6),
ID_UNALLOCATED(5,7),
/* There is no FGT associated with AT S1E2A :-( */ if (op == OP_AT_S1E2A &&
!kvm_has_feat(vcpu->kvm, ID_AA64ISAR2_EL1, ATS1A, IMP)) {
kvm_inject_undefined(vcpu); returnfalse;
}
/* Only defined here as this is an internal "abstraction" */ union tlbi_info { struct {
u64 start;
u64 size;
} range;
struct {
u64 addr;
} ipa;
struct {
u64 addr;
u32 encoding;
} va;
};
staticvoid s2_mmu_unmap_range(struct kvm_s2_mmu *mmu, constunion tlbi_info *info)
{ /* * The unmap operation is allowed to drop the MMU lock and block, which * means that @mmu could be used for a different context than the one * currently being invalidated. * * This behavior is still safe, as: * * 1) The vCPU(s) that recycled the MMU are responsible for invalidating * the entire MMU before reusing it, which still honors the intent * of a TLBI. * * 2) Until the guest TLBI instruction is 'retired' (i.e. increment PC * and ERET to the guest), other vCPUs are allowed to use stale * translations. * * 3) Accidentally unmapping an unrelated MMU context is nonfatal, and * at worst may cause more aborts for shadow stage-2 fills. * * Dropping the MMU lock also implies that shadow stage-2 fills could * happen behind the back of the TLBI. This is still safe, though, as * the L1 needs to put its stage-2 in a consistent state before doing * the TLBI.
*/
kvm_stage2_unmap_range(mmu, info->range.start, info->range.size, true);
}
if (!kvm_supported_tlbi_ipas2_op(vcpu, sys_encoding)) return undef_access(vcpu, p, r);
/* * Because the shadow S2 structure doesn't necessarily reflect that * of the guest's S2 (different base granule size, for example), we * decide to ignore TTL and only use the described range.
*/
base = decode_range_tlbi(p->regval, &range, NULL);
/* * We drop a number of things from the supplied value: * * - NS bit: we're non-secure only. * * - IPA[51:48]: We don't support 52bit IPA just yet... * * And of course, adjust the IPA to be on an actual address.
*/
base_addr = (info->ipa.addr & GENMASK_ULL(35, 0)) << 12;
max_size = compute_tlb_inval_range(mmu, info->ipa.addr);
base_addr &= ~(max_size - 1);
/* * See comment in s2_mmu_unmap_range() for why this is allowed to * reschedule.
*/
kvm_stage2_unmap_range(mmu, base_addr, max_size, true);
}
/* * If we're here, this is because we've trapped on a EL1 TLBI * instruction that affects the EL1 translation regime while * we're running in a context that doesn't allow us to let the * HW do its thing (aka vEL2): * * - HCR_EL2.E2H == 0 : a non-VHE guest * - HCR_EL2.{E2H,TGE} == { 1, 0 } : a VHE guest in guest mode * * Another possibility is that we are invalidating the EL2 context * using EL1 instructions, but that we landed here because we need * additional invalidation for structures that are not held in the * CPU TLBs (such as the VNCR pseudo-TLB and its EL2 mapping). In * that case, we are guaranteed that HCR_EL2.{E2H,TGE} == { 1, 1 } * as we don't allow an NV-capable L1 in a nVHE configuration. * * We don't expect these helpers to ever be called when running * in a vEL1 context.
*/
WARN_ON(!vcpu_is_el2(vcpu));
if (!kvm_supported_tlbi_s1e1_op(vcpu, sys_encoding)) return undef_access(vcpu, p, r);
if (vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu)) {
kvm_handle_s1e2_tlbi(vcpu, sys_encoding, p->regval); returntrue;
}
/* * Trapped cp14 registers. We generally ignore most of the external * debug, on the principle that they don't really make sense to a * guest. Revisit this one day, would this principle change.
*/ staticconststruct sys_reg_desc cp14_regs[] = { /* DBGDIDR */
{ Op1( 0), CRn( 0), CRm( 0), Op2( 0), trap_dbgdidr }, /* DBGDTRRXext */
{ Op1( 0), CRn( 0), CRm( 0), Op2( 2), trap_raz_wi },
/* Check for regs disabled by runtime config */ if (sysreg_hidden(vcpu, r)) {
kvm_inject_undefined(vcpu); return;
}
/* * Not having an accessor means that we have configured a trap * that we don't know how to handle. This certainly qualifies * as a gross bug that should be fixed right away.
*/
BUG_ON(!r->access);
/* Skip instruction if instructed so */ if (likely(r->access(vcpu, params, r)))
kvm_incr_pc(vcpu);
}
/* * emulate_cp -- tries to match a sys_reg access in a handling table, and * call the corresponding trap handler. * * @params: pointer to the descriptor of the access * @table: array of trap descriptors * @num: size of the trap descriptor array * * Return true if the access has been handled, false if not.
*/ staticbool emulate_cp(struct kvm_vcpu *vcpu, struct sys_reg_params *params, conststruct sys_reg_desc *table,
size_t num)
{ conststruct sys_reg_desc *r;
if (!table) returnfalse; /* Not handled */
r = find_reg(params, table, num);
if (r) {
perform_access(vcpu, params, r); returntrue;
}
/* * Make a 64-bit value out of Rt and Rt2. As we use the same trap * backends between AArch32 and AArch64, we get away with it.
*/ if (params.is_write) {
params.regval = vcpu_get_reg(vcpu, Rt) & 0xffffffff;
params.regval |= vcpu_get_reg(vcpu, Rt2) << 32;
}
/* * If the table contains a handler, handle the * potential register operation in the case of a read and return * with success.
*/ if (emulate_cp(vcpu, ¶ms, global, nr_global)) { /* Split up the value between registers for the read side */ if (!params.is_write) {
vcpu_set_reg(vcpu, Rt, lower_32_bits(params.regval));
vcpu_set_reg(vcpu, Rt2, upper_32_bits(params.regval));
}
/* * The CP10 ID registers are architecturally mapped to AArch64 feature * registers. Abuse that fact so we can rely on the AArch64 handler for accesses * from AArch32.
*/ staticbool kvm_esr_cp10_id_to_sys64(u64 esr, struct sys_reg_params *params)
{
u8 reg_id = (esr >> 10) & 0xf; bool valid;
/** * kvm_handle_cp10_id() - Handles a VMRS trap on guest access to a 'Media and * VFP Register' from AArch32. * @vcpu: The vCPU pointer * * MVFR{0-2} are architecturally mapped to the AArch64 MVFR{0-2}_EL1 registers. * Work out the correct AArch64 system register encoding and reroute to the * AArch64 system register emulation.
*/ int kvm_handle_cp10_id(struct kvm_vcpu *vcpu)
{ int Rt = kvm_vcpu_sys_get_rt(vcpu);
u64 esr = kvm_vcpu_get_esr(vcpu); struct sys_reg_params params;
/* UNDEF on any unhandled register access */ if (!kvm_esr_cp10_id_to_sys64(esr, ¶ms)) {
kvm_inject_undefined(vcpu); return 1;
}
if (emulate_sys_reg(vcpu, ¶ms))
vcpu_set_reg(vcpu, Rt, params.regval);
return 1;
}
/** * kvm_emulate_cp15_id_reg() - Handles an MRC trap on a guest CP15 access where * CRn=0, which corresponds to the AArch32 feature * registers. * @vcpu: the vCPU pointer * @params: the system register access parameters. * * Our cp15 system register tables do not enumerate the AArch32 feature * registers. Conveniently, our AArch64 table does, and the AArch32 system * register encoding can be trivially remapped into the AArch64 for the feature * registers: Append op0=3, leaving op1, CRn, CRm, and op2 the same. * * According to DDI0487G.b G7.3.1, paragraph "Behavior of VMSAv8-32 32-bit * System registers with (coproc=0b1111, CRn==c0)", read accesses from this * range are either UNKNOWN or RES0. Rerouting remains architectural as we * treat undefined registers in this range as RAZ.
*/ staticint kvm_emulate_cp15_id_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *params)
{ int Rt = kvm_vcpu_sys_get_rt(vcpu);
/* Treat impossible writes to RO registers as UNDEFINED */ if (params->is_write) {
unhandled_cp_access(vcpu, params); return 1;
}
params->Op0 = 3;
/* * All registers where CRm > 3 are known to be UNKNOWN/RAZ from AArch32. * Avoid conflicting with future expansion of AArch64 feature registers * and simply treat them as RAZ here.
*/ if (params->CRm > 3)
params->regval = 0; elseif (!emulate_sys_reg(vcpu, params)) return 1;
/* * Certain AArch32 ID registers are handled by rerouting to the AArch64 * system register table. Registers in the ID range where CRm=0 are * excluded from this scheme as they do not trivially map into AArch64 * system register encodings, except for AIDR/REVIDR.
*/ if (params.Op1 == 0 && params.CRn == 0 &&
(params.CRm || params.Op2 == 6 /* REVIDR */)) return kvm_emulate_cp15_id_reg(vcpu, ¶ms); if (params.Op1 == 1 && params.CRn == 0 &&
params.CRm == 0 && params.Op2 == 7 /* AIDR */) return kvm_emulate_cp15_id_reg(vcpu, ¶ms);
/** * emulate_sys_reg - Emulate a guest access to an AArch64 system register * @vcpu: The VCPU pointer * @params: Decoded system register parameters * * Return: true if the system register access was successful, false otherwise.
*/ staticbool emulate_sys_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *params)
{ conststruct sys_reg_desc *r;
r = find_reg(params, sys_reg_descs, ARRAY_SIZE(sys_reg_descs)); if (likely(r)) {
perform_access(vcpu, params, r); returntrue;
}
/** * kvm_reset_sys_regs - sets system registers to reset value * @vcpu: The VCPU pointer * * This function finds the right table above and sets the registers on the * virtual CPU struct to their architecturally defined reset values.
*/ void kvm_reset_sys_regs(struct kvm_vcpu *vcpu)
{ struct kvm *kvm = vcpu->kvm; unsignedlong i;
for (i = 0; i < ARRAY_SIZE(sys_reg_descs); i++) { conststruct sys_reg_desc *r = &sys_reg_descs[i];
/* System registers have Op0=={2,3}, as per DDI487 J.a C5.1.2 */ if (params.Op0 == 2 || params.Op0 == 3)
desc = &sys_reg_descs[sr_idx]; else
desc = &sys_insn_descs[sr_idx];
perform_access(vcpu, ¶ms, desc);
/* Read from system register? */ if (!params.is_write &&
(params.Op0 == 2 || params.Op0 == 3))
vcpu_set_reg(vcpu, Rt, params.regval);
return 1;
}
/****************************************************************************** * Userspace API
*****************************************************************************/
/* Fail if we have unknown bits set. */ if (id & ~(KVM_REG_ARCH_MASK|KVM_REG_SIZE_MASK|KVM_REG_ARM_COPROC_MASK
| ((1 << KVM_REG_ARM_COPROC_SHIFT)-1))) return -ENOENT;
switch (id & KVM_REG_ARM_DEMUX_ID_MASK) { case KVM_REG_ARM_DEMUX_ID_CCSIDR: if (KVM_REG_SIZE(id) != 4) return -ENOENT;
val = (id & KVM_REG_ARM_DEMUX_VAL_MASK)
>> KVM_REG_ARM_DEMUX_VAL_SHIFT; if (val >= CSSELR_MAX) return -ENOENT;
/* Fail if we have unknown bits set. */ if (id & ~(KVM_REG_ARCH_MASK|KVM_REG_SIZE_MASK|KVM_REG_ARM_COPROC_MASK
| ((1 << KVM_REG_ARM_COPROC_SHIFT)-1))) return -ENOENT;
switch (id & KVM_REG_ARM_DEMUX_ID_MASK) { case KVM_REG_ARM_DEMUX_ID_CCSIDR: if (KVM_REG_SIZE(id) != 4) return -ENOENT;
val = (id & KVM_REG_ARM_DEMUX_VAL_MASK)
>> KVM_REG_ARM_DEMUX_VAL_SHIFT; if (val >= CSSELR_MAX) return -ENOENT;
if (put_user(sys_reg_to_index(reg), *uind)) returnfalse;
(*uind)++; returntrue;
}
staticint walk_one_sys_reg(conststruct kvm_vcpu *vcpu, conststruct sys_reg_desc *rd,
u64 __user **uind, unsignedint *total)
{ /* * Ignore registers we trap but don't save, * and for which no custom user accessor is provided.
*/ if (!(rd->reg || rd->get_user)) return 0;
if (sysreg_hidden(vcpu, rd)) return 0;
if (!copy_reg_to_user(rd, uind)) return -EFAULT;
(*total)++; return 0;
}
/* Assumed ordered tables, see kvm_sys_reg_table_init. */ staticint walk_sys_regs(struct kvm_vcpu *vcpu, u64 __user *uind)
{ conststruct sys_reg_desc *i2, *end2; unsignedint total = 0; int err;
/* Only feature id range is supported, reserved[13] must be zero. */ if (range->range ||
memcmp(range->reserved, zero_page, sizeof(range->reserved))) return -EINVAL;
/* Wipe the whole thing first */ if (clear_user(masks, KVM_ARM_FEATURE_ID_RANGE_SIZE * sizeof(__u64))) return -EFAULT;
for (int i = 0; i < ARRAY_SIZE(sys_reg_descs); i++) { conststruct sys_reg_desc *reg = &sys_reg_descs[i];
u32 encoding = reg_to_encoding(reg);
u64 val;
if (!is_feature_id_reg(encoding) || !reg->set_user) continue;
if (!reg->val ||
(is_aa32_id_reg(encoding) && !kvm_supports_32bit_el0())) { continue;
}
val = reg->val;
if (put_user(val, (masks + KVM_ARM_FEATURE_ID_RANGE_INDEX(encoding)))) return -EFAULT;
}
if (vcpu_el1_is_32bit(vcpu))
vcpu->arch.hcr_el2 &= ~HCR_RW;
if (kvm_has_mte(vcpu->kvm))
vcpu->arch.hcr_el2 |= HCR_ATA;
/* * In the absence of FGT, we cannot independently trap TLBI * Range instructions. This isn't great, but trapping all * TLBIs would be far worse. Live with it...
*/ if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS))
vcpu->arch.hcr_el2 |= HCR_TTLBOS;
}
/* * Perform last adjustments to the ID registers that are implied by the * configuration outside of the ID regs themselves, as well as any * initialisation that directly depend on these ID registers (such as * RES0/RES1 behaviours). This is not the place to configure traps though. * * Because this can be called once per CPU, changes must be idempotent.
*/ int kvm_finalize_sys_regs(struct kvm_vcpu *vcpu)
{ struct kvm *kvm = vcpu->kvm;
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.
