--- /dev/null
- !kvm_vcpu_dabt_isextabt(vcpu) &&
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#ifndef __ARM64_KVM_HYP_SWITCH_H__
+#define __ARM64_KVM_HYP_SWITCH_H__
+
+#include <linux/arm-smccc.h>
+#include <linux/kvm_host.h>
+#include <linux/types.h>
+#include <linux/jump_label.h>
+#include <uapi/linux/psci.h>
+
+#include <kvm/arm_psci.h>
+
+#include <asm/barrier.h>
+#include <asm/cpufeature.h>
+#include <asm/kprobes.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
+#include <asm/fpsimd.h>
+#include <asm/debug-monitors.h>
+#include <asm/processor.h>
+#include <asm/thread_info.h>
+
+extern const char __hyp_panic_string[];
+
+/* Check whether the FP regs were dirtied while in the host-side run loop: */
+static inline bool update_fp_enabled(struct kvm_vcpu *vcpu)
+{
+ /*
+ * When the system doesn't support FP/SIMD, we cannot rely on
+ * the _TIF_FOREIGN_FPSTATE flag. However, we always inject an
+ * abort on the very first access to FP and thus we should never
+ * see KVM_ARM64_FP_ENABLED. For added safety, make sure we always
+ * trap the accesses.
+ */
+ if (!system_supports_fpsimd() ||
+ vcpu->arch.host_thread_info->flags & _TIF_FOREIGN_FPSTATE)
+ vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED |
+ KVM_ARM64_FP_HOST);
+
+ return !!(vcpu->arch.flags & KVM_ARM64_FP_ENABLED);
+}
+
+/* Save the 32-bit only FPSIMD system register state */
+static inline void __fpsimd_save_fpexc32(struct kvm_vcpu *vcpu)
+{
+ if (!vcpu_el1_is_32bit(vcpu))
+ return;
+
+ __vcpu_sys_reg(vcpu, FPEXC32_EL2) = read_sysreg(fpexc32_el2);
+}
+
+static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
+{
+ /*
+ * We are about to set CPTR_EL2.TFP to trap all floating point
+ * register accesses to EL2, however, the ARM ARM clearly states that
+ * traps are only taken to EL2 if the operation would not otherwise
+ * trap to EL1. Therefore, always make sure that for 32-bit guests,
+ * we set FPEXC.EN to prevent traps to EL1, when setting the TFP bit.
+ * If FP/ASIMD is not implemented, FPEXC is UNDEFINED and any access to
+ * it will cause an exception.
+ */
+ if (vcpu_el1_is_32bit(vcpu) && system_supports_fpsimd()) {
+ write_sysreg(1 << 30, fpexc32_el2);
+ isb();
+ }
+}
+
+static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
+{
+ /* Trap on AArch32 cp15 c15 (impdef sysregs) accesses (EL1 or EL0) */
+ write_sysreg(1 << 15, hstr_el2);
+
+ /*
+ * Make sure we trap PMU access from EL0 to EL2. Also sanitize
+ * PMSELR_EL0 to make sure it never contains the cycle
+ * counter, which could make a PMXEVCNTR_EL0 access UNDEF at
+ * EL1 instead of being trapped to EL2.
+ */
+ write_sysreg(0, pmselr_el0);
+ write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
+ write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
+}
+
+static inline void __deactivate_traps_common(void)
+{
+ write_sysreg(0, hstr_el2);
+ write_sysreg(0, pmuserenr_el0);
+}
+
+static inline void ___activate_traps(struct kvm_vcpu *vcpu)
+{
+ u64 hcr = vcpu->arch.hcr_el2;
+
+ if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM))
+ hcr |= HCR_TVM;
+
+ write_sysreg(hcr, hcr_el2);
+
+ if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE))
+ write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2);
+}
+
+static inline void ___deactivate_traps(struct kvm_vcpu *vcpu)
+{
+ /*
+ * If we pended a virtual abort, preserve it until it gets
+ * cleared. See D1.14.3 (Virtual Interrupts) for details, but
+ * the crucial bit is "On taking a vSError interrupt,
+ * HCR_EL2.VSE is cleared to 0."
+ */
+ if (vcpu->arch.hcr_el2 & HCR_VSE) {
+ vcpu->arch.hcr_el2 &= ~HCR_VSE;
+ vcpu->arch.hcr_el2 |= read_sysreg(hcr_el2) & HCR_VSE;
+ }
+}
+
+static inline void __activate_vm(struct kvm_s2_mmu *mmu)
+{
+ __load_guest_stage2(mmu);
+}
+
+static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar)
+{
+ u64 par, tmp;
+
+ /*
+ * Resolve the IPA the hard way using the guest VA.
+ *
+ * Stage-1 translation already validated the memory access
+ * rights. As such, we can use the EL1 translation regime, and
+ * don't have to distinguish between EL0 and EL1 access.
+ *
+ * We do need to save/restore PAR_EL1 though, as we haven't
+ * saved the guest context yet, and we may return early...
+ */
+ par = read_sysreg(par_el1);
+ asm volatile("at s1e1r, %0" : : "r" (far));
+ isb();
+
+ tmp = read_sysreg(par_el1);
+ write_sysreg(par, par_el1);
+
+ if (unlikely(tmp & SYS_PAR_EL1_F))
+ return false; /* Translation failed, back to guest */
+
+ /* Convert PAR to HPFAR format */
+ *hpfar = PAR_TO_HPFAR(tmp);
+ return true;
+}
+
+static inline bool __populate_fault_info(struct kvm_vcpu *vcpu)
+{
+ u8 ec;
+ u64 esr;
+ u64 hpfar, far;
+
+ esr = vcpu->arch.fault.esr_el2;
+ ec = ESR_ELx_EC(esr);
+
+ if (ec != ESR_ELx_EC_DABT_LOW && ec != ESR_ELx_EC_IABT_LOW)
+ return true;
+
+ far = read_sysreg_el2(SYS_FAR);
+
+ /*
+ * The HPFAR can be invalid if the stage 2 fault did not
+ * happen during a stage 1 page table walk (the ESR_EL2.S1PTW
+ * bit is clear) and one of the two following cases are true:
+ * 1. The fault was due to a permission fault
+ * 2. The processor carries errata 834220
+ *
+ * Therefore, for all non S1PTW faults where we either have a
+ * permission fault or the errata workaround is enabled, we
+ * resolve the IPA using the AT instruction.
+ */
+ if (!(esr & ESR_ELx_S1PTW) &&
+ (cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
+ (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
+ if (!__translate_far_to_hpfar(far, &hpfar))
+ return false;
+ } else {
+ hpfar = read_sysreg(hpfar_el2);
+ }
+
+ vcpu->arch.fault.far_el2 = far;
+ vcpu->arch.fault.hpfar_el2 = hpfar;
+ return true;
+}
+
+/* Check for an FPSIMD/SVE trap and handle as appropriate */
+static inline bool __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
+{
+ bool vhe, sve_guest, sve_host;
+ u8 esr_ec;
+
+ if (!system_supports_fpsimd())
+ return false;
+
+ /*
+ * Currently system_supports_sve() currently implies has_vhe(),
+ * so the check is redundant. However, has_vhe() can be determined
+ * statically and helps the compiler remove dead code.
+ */
+ if (has_vhe() && system_supports_sve()) {
+ sve_guest = vcpu_has_sve(vcpu);
+ sve_host = vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE;
+ vhe = true;
+ } else {
+ sve_guest = false;
+ sve_host = false;
+ vhe = has_vhe();
+ }
+
+ esr_ec = kvm_vcpu_trap_get_class(vcpu);
+ if (esr_ec != ESR_ELx_EC_FP_ASIMD &&
+ esr_ec != ESR_ELx_EC_SVE)
+ return false;
+
+ /* Don't handle SVE traps for non-SVE vcpus here: */
+ if (!sve_guest)
+ if (esr_ec != ESR_ELx_EC_FP_ASIMD)
+ return false;
+
+ /* Valid trap. Switch the context: */
+
+ if (vhe) {
+ u64 reg = read_sysreg(cpacr_el1) | CPACR_EL1_FPEN;
+
+ if (sve_guest)
+ reg |= CPACR_EL1_ZEN;
+
+ write_sysreg(reg, cpacr_el1);
+ } else {
+ write_sysreg(read_sysreg(cptr_el2) & ~(u64)CPTR_EL2_TFP,
+ cptr_el2);
+ }
+
+ isb();
+
+ if (vcpu->arch.flags & KVM_ARM64_FP_HOST) {
+ /*
+ * In the SVE case, VHE is assumed: it is enforced by
+ * Kconfig and kvm_arch_init().
+ */
+ if (sve_host) {
+ struct thread_struct *thread = container_of(
+ vcpu->arch.host_fpsimd_state,
+ struct thread_struct, uw.fpsimd_state);
+
+ sve_save_state(sve_pffr(thread),
+ &vcpu->arch.host_fpsimd_state->fpsr);
+ } else {
+ __fpsimd_save_state(vcpu->arch.host_fpsimd_state);
+ }
+
+ vcpu->arch.flags &= ~KVM_ARM64_FP_HOST;
+ }
+
+ if (sve_guest) {
+ sve_load_state(vcpu_sve_pffr(vcpu),
+ &vcpu->arch.ctxt.fp_regs.fpsr,
+ sve_vq_from_vl(vcpu->arch.sve_max_vl) - 1);
+ write_sysreg_s(__vcpu_sys_reg(vcpu, ZCR_EL1), SYS_ZCR_EL12);
+ } else {
+ __fpsimd_restore_state(&vcpu->arch.ctxt.fp_regs);
+ }
+
+ /* Skip restoring fpexc32 for AArch64 guests */
+ if (!(read_sysreg(hcr_el2) & HCR_RW))
+ write_sysreg(__vcpu_sys_reg(vcpu, FPEXC32_EL2), fpexc32_el2);
+
+ vcpu->arch.flags |= KVM_ARM64_FP_ENABLED;
+
+ return true;
+}
+
+static inline bool handle_tx2_tvm(struct kvm_vcpu *vcpu)
+{
+ u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu));
+ int rt = kvm_vcpu_sys_get_rt(vcpu);
+ u64 val = vcpu_get_reg(vcpu, rt);
+
+ /*
+ * The normal sysreg handling code expects to see the traps,
+ * let's not do anything here.
+ */
+ if (vcpu->arch.hcr_el2 & HCR_TVM)
+ return false;
+
+ switch (sysreg) {
+ case SYS_SCTLR_EL1:
+ write_sysreg_el1(val, SYS_SCTLR);
+ break;
+ case SYS_TTBR0_EL1:
+ write_sysreg_el1(val, SYS_TTBR0);
+ break;
+ case SYS_TTBR1_EL1:
+ write_sysreg_el1(val, SYS_TTBR1);
+ break;
+ case SYS_TCR_EL1:
+ write_sysreg_el1(val, SYS_TCR);
+ break;
+ case SYS_ESR_EL1:
+ write_sysreg_el1(val, SYS_ESR);
+ break;
+ case SYS_FAR_EL1:
+ write_sysreg_el1(val, SYS_FAR);
+ break;
+ case SYS_AFSR0_EL1:
+ write_sysreg_el1(val, SYS_AFSR0);
+ break;
+ case SYS_AFSR1_EL1:
+ write_sysreg_el1(val, SYS_AFSR1);
+ break;
+ case SYS_MAIR_EL1:
+ write_sysreg_el1(val, SYS_MAIR);
+ break;
+ case SYS_AMAIR_EL1:
+ write_sysreg_el1(val, SYS_AMAIR);
+ break;
+ case SYS_CONTEXTIDR_EL1:
+ write_sysreg_el1(val, SYS_CONTEXTIDR);
+ break;
+ default:
+ return false;
+ }
+
+ __kvm_skip_instr(vcpu);
+ return true;
+}
+
+static inline bool esr_is_ptrauth_trap(u32 esr)
+{
+ u32 ec = ESR_ELx_EC(esr);
+
+ if (ec == ESR_ELx_EC_PAC)
+ return true;
+
+ if (ec != ESR_ELx_EC_SYS64)
+ return false;
+
+ switch (esr_sys64_to_sysreg(esr)) {
+ case SYS_APIAKEYLO_EL1:
+ case SYS_APIAKEYHI_EL1:
+ case SYS_APIBKEYLO_EL1:
+ case SYS_APIBKEYHI_EL1:
+ case SYS_APDAKEYLO_EL1:
+ case SYS_APDAKEYHI_EL1:
+ case SYS_APDBKEYLO_EL1:
+ case SYS_APDBKEYHI_EL1:
+ case SYS_APGAKEYLO_EL1:
+ case SYS_APGAKEYHI_EL1:
+ return true;
+ }
+
+ return false;
+}
+
+#define __ptrauth_save_key(ctxt, key) \
+ do { \
+ u64 __val; \
+ __val = read_sysreg_s(SYS_ ## key ## KEYLO_EL1); \
+ ctxt_sys_reg(ctxt, key ## KEYLO_EL1) = __val; \
+ __val = read_sysreg_s(SYS_ ## key ## KEYHI_EL1); \
+ ctxt_sys_reg(ctxt, key ## KEYHI_EL1) = __val; \
+} while(0)
+
+static inline bool __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpu_context *ctxt;
+ u64 val;
+
+ if (!vcpu_has_ptrauth(vcpu) ||
+ !esr_is_ptrauth_trap(kvm_vcpu_get_esr(vcpu)))
+ return false;
+
+ ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
+ __ptrauth_save_key(ctxt, APIA);
+ __ptrauth_save_key(ctxt, APIB);
+ __ptrauth_save_key(ctxt, APDA);
+ __ptrauth_save_key(ctxt, APDB);
+ __ptrauth_save_key(ctxt, APGA);
+
+ vcpu_ptrauth_enable(vcpu);
+
+ val = read_sysreg(hcr_el2);
+ val |= (HCR_API | HCR_APK);
+ write_sysreg(val, hcr_el2);
+
+ return true;
+}
+
+/*
+ * Return true when we were able to fixup the guest exit and should return to
+ * the guest, false when we should restore the host state and return to the
+ * main run loop.
+ */
+static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+ if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ)
+ vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR);
+
+ /*
+ * We're using the raw exception code in order to only process
+ * the trap if no SError is pending. We will come back to the
+ * same PC once the SError has been injected, and replay the
+ * trapping instruction.
+ */
+ if (*exit_code != ARM_EXCEPTION_TRAP)
+ goto exit;
+
+ if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) &&
+ kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 &&
+ handle_tx2_tvm(vcpu))
+ return true;
+
+ /*
+ * We trap the first access to the FP/SIMD to save the host context
+ * and restore the guest context lazily.
+ * If FP/SIMD is not implemented, handle the trap and inject an
+ * undefined instruction exception to the guest.
+ * Similarly for trapped SVE accesses.
+ */
+ if (__hyp_handle_fpsimd(vcpu))
+ return true;
+
+ if (__hyp_handle_ptrauth(vcpu))
+ return true;
+
+ if (!__populate_fault_info(vcpu))
+ return true;
+
+ if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
+ bool valid;
+
+ valid = kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_DABT_LOW &&
+ kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
+ kvm_vcpu_dabt_isvalid(vcpu) &&
++ !kvm_vcpu_abt_issea(vcpu) &&
+ !kvm_vcpu_dabt_iss1tw(vcpu);
+
+ if (valid) {
+ int ret = __vgic_v2_perform_cpuif_access(vcpu);
+
+ if (ret == 1)
+ return true;
+
+ /* Promote an illegal access to an SError.*/
+ if (ret == -1)
+ *exit_code = ARM_EXCEPTION_EL1_SERROR;
+
+ goto exit;
+ }
+ }
+
+ if (static_branch_unlikely(&vgic_v3_cpuif_trap) &&
+ (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 ||
+ kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_CP15_32)) {
+ int ret = __vgic_v3_perform_cpuif_access(vcpu);
+
+ if (ret == 1)
+ return true;
+ }
+
+exit:
+ /* Return to the host kernel and handle the exit */
+ return false;
+}
+
+static inline bool __needs_ssbd_off(struct kvm_vcpu *vcpu)
+{
+ if (!cpus_have_final_cap(ARM64_SSBD))
+ return false;
+
+ return !(vcpu->arch.workaround_flags & VCPU_WORKAROUND_2_FLAG);
+}
+
+static inline void __set_guest_arch_workaround_state(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_ARM64_SSBD
+ /*
+ * The host runs with the workaround always present. If the
+ * guest wants it disabled, so be it...
+ */
+ if (__needs_ssbd_off(vcpu) &&
+ __hyp_this_cpu_read(arm64_ssbd_callback_required))
+ arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 0, NULL);
+#endif
+}
+
+static inline void __set_host_arch_workaround_state(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_ARM64_SSBD
+ /*
+ * If the guest has disabled the workaround, bring it back on.
+ */
+ if (__needs_ssbd_off(vcpu) &&
+ __hyp_this_cpu_read(arm64_ssbd_callback_required))
+ arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 1, NULL);
+#endif
+}
+
+#endif /* __ARM64_KVM_HYP_SWITCH_H__ */
*/
void kvm_flush_remote_tlbs(struct kvm *kvm)
{
- kvm_call_hyp(__kvm_tlb_flush_vmid, kvm);
+ kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu);
}
-static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
+static void kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa,
+ int level)
{
- kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa);
+ kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ipa, level);
}
/*
/**
* stage2_dissolve_pmd() - clear and flush huge PMD entry
- * @kvm: pointer to kvm structure.
+ * @mmu: pointer to mmu structure to operate on
* @addr: IPA
* @pmd: pmd pointer for IPA
*
* Function clears a PMD entry, flushes addr 1st and 2nd stage TLBs.
*/
-static void stage2_dissolve_pmd(struct kvm *kvm, phys_addr_t addr, pmd_t *pmd)
+static void stage2_dissolve_pmd(struct kvm_s2_mmu *mmu, phys_addr_t addr, pmd_t *pmd)
{
if (!pmd_thp_or_huge(*pmd))
return;
pmd_clear(pmd);
- kvm_tlb_flush_vmid_ipa(kvm, addr);
+ kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PMD_LEVEL);
put_page(virt_to_page(pmd));
}
/**
* stage2_dissolve_pud() - clear and flush huge PUD entry
- * @kvm: pointer to kvm structure.
+ * @mmu: pointer to mmu structure to operate on
* @addr: IPA
* @pud: pud pointer for IPA
*
* Function clears a PUD entry, flushes addr 1st and 2nd stage TLBs.
*/
-static void stage2_dissolve_pud(struct kvm *kvm, phys_addr_t addr, pud_t *pudp)
+static void stage2_dissolve_pud(struct kvm_s2_mmu *mmu, phys_addr_t addr, pud_t *pudp)
{
+ struct kvm *kvm = mmu->kvm;
+
if (!stage2_pud_huge(kvm, *pudp))
return;
stage2_pud_clear(kvm, pudp);
- kvm_tlb_flush_vmid_ipa(kvm, addr);
+ kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PUD_LEVEL);
put_page(virt_to_page(pudp));
}
return p;
}
-static void clear_stage2_pgd_entry(struct kvm *kvm, pgd_t *pgd, phys_addr_t addr)
+static void clear_stage2_pgd_entry(struct kvm_s2_mmu *mmu, pgd_t *pgd, phys_addr_t addr)
{
+ struct kvm *kvm = mmu->kvm;
p4d_t *p4d_table __maybe_unused = stage2_p4d_offset(kvm, pgd, 0UL);
stage2_pgd_clear(kvm, pgd);
- kvm_tlb_flush_vmid_ipa(kvm, addr);
+ kvm_tlb_flush_vmid_ipa(mmu, addr, S2_NO_LEVEL_HINT);
stage2_p4d_free(kvm, p4d_table);
put_page(virt_to_page(pgd));
}
-static void clear_stage2_p4d_entry(struct kvm *kvm, p4d_t *p4d, phys_addr_t addr)
+static void clear_stage2_p4d_entry(struct kvm_s2_mmu *mmu, p4d_t *p4d, phys_addr_t addr)
{
+ struct kvm *kvm = mmu->kvm;
pud_t *pud_table __maybe_unused = stage2_pud_offset(kvm, p4d, 0);
stage2_p4d_clear(kvm, p4d);
- kvm_tlb_flush_vmid_ipa(kvm, addr);
+ kvm_tlb_flush_vmid_ipa(mmu, addr, S2_NO_LEVEL_HINT);
stage2_pud_free(kvm, pud_table);
put_page(virt_to_page(p4d));
}
-static void clear_stage2_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr)
+static void clear_stage2_pud_entry(struct kvm_s2_mmu *mmu, pud_t *pud, phys_addr_t addr)
{
+ struct kvm *kvm = mmu->kvm;
pmd_t *pmd_table __maybe_unused = stage2_pmd_offset(kvm, pud, 0);
+
VM_BUG_ON(stage2_pud_huge(kvm, *pud));
stage2_pud_clear(kvm, pud);
- kvm_tlb_flush_vmid_ipa(kvm, addr);
+ kvm_tlb_flush_vmid_ipa(mmu, addr, S2_NO_LEVEL_HINT);
stage2_pmd_free(kvm, pmd_table);
put_page(virt_to_page(pud));
}
-static void clear_stage2_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
+static void clear_stage2_pmd_entry(struct kvm_s2_mmu *mmu, pmd_t *pmd, phys_addr_t addr)
{
pte_t *pte_table = pte_offset_kernel(pmd, 0);
VM_BUG_ON(pmd_thp_or_huge(*pmd));
pmd_clear(pmd);
- kvm_tlb_flush_vmid_ipa(kvm, addr);
+ kvm_tlb_flush_vmid_ipa(mmu, addr, S2_NO_LEVEL_HINT);
free_page((unsigned long)pte_table);
put_page(virt_to_page(pmd));
}
* we then fully enforce cacheability of RAM, no matter what the guest
* does.
*/
-static void unmap_stage2_ptes(struct kvm *kvm, pmd_t *pmd,
+static void unmap_stage2_ptes(struct kvm_s2_mmu *mmu, pmd_t *pmd,
phys_addr_t addr, phys_addr_t end)
{
phys_addr_t start_addr = addr;
pte_t old_pte = *pte;
kvm_set_pte(pte, __pte(0));
- kvm_tlb_flush_vmid_ipa(kvm, addr);
+ kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PTE_LEVEL);
/* No need to invalidate the cache for device mappings */
if (!kvm_is_device_pfn(pte_pfn(old_pte)))
}
} while (pte++, addr += PAGE_SIZE, addr != end);
- if (stage2_pte_table_empty(kvm, start_pte))
- clear_stage2_pmd_entry(kvm, pmd, start_addr);
+ if (stage2_pte_table_empty(mmu->kvm, start_pte))
+ clear_stage2_pmd_entry(mmu, pmd, start_addr);
}
-static void unmap_stage2_pmds(struct kvm *kvm, pud_t *pud,
+static void unmap_stage2_pmds(struct kvm_s2_mmu *mmu, pud_t *pud,
phys_addr_t addr, phys_addr_t end)
{
+ struct kvm *kvm = mmu->kvm;
phys_addr_t next, start_addr = addr;
pmd_t *pmd, *start_pmd;
pmd_t old_pmd = *pmd;
pmd_clear(pmd);
- kvm_tlb_flush_vmid_ipa(kvm, addr);
+ kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PMD_LEVEL);
kvm_flush_dcache_pmd(old_pmd);
put_page(virt_to_page(pmd));
} else {
- unmap_stage2_ptes(kvm, pmd, addr, next);
+ unmap_stage2_ptes(mmu, pmd, addr, next);
}
}
} while (pmd++, addr = next, addr != end);
if (stage2_pmd_table_empty(kvm, start_pmd))
- clear_stage2_pud_entry(kvm, pud, start_addr);
+ clear_stage2_pud_entry(mmu, pud, start_addr);
}
-static void unmap_stage2_puds(struct kvm *kvm, p4d_t *p4d,
+static void unmap_stage2_puds(struct kvm_s2_mmu *mmu, p4d_t *p4d,
phys_addr_t addr, phys_addr_t end)
{
+ struct kvm *kvm = mmu->kvm;
phys_addr_t next, start_addr = addr;
pud_t *pud, *start_pud;
pud_t old_pud = *pud;
stage2_pud_clear(kvm, pud);
- kvm_tlb_flush_vmid_ipa(kvm, addr);
+ kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PUD_LEVEL);
kvm_flush_dcache_pud(old_pud);
put_page(virt_to_page(pud));
} else {
- unmap_stage2_pmds(kvm, pud, addr, next);
+ unmap_stage2_pmds(mmu, pud, addr, next);
}
}
} while (pud++, addr = next, addr != end);
if (stage2_pud_table_empty(kvm, start_pud))
- clear_stage2_p4d_entry(kvm, p4d, start_addr);
+ clear_stage2_p4d_entry(mmu, p4d, start_addr);
}
-static void unmap_stage2_p4ds(struct kvm *kvm, pgd_t *pgd,
+static void unmap_stage2_p4ds(struct kvm_s2_mmu *mmu, pgd_t *pgd,
phys_addr_t addr, phys_addr_t end)
{
+ struct kvm *kvm = mmu->kvm;
phys_addr_t next, start_addr = addr;
p4d_t *p4d, *start_p4d;
do {
next = stage2_p4d_addr_end(kvm, addr, end);
if (!stage2_p4d_none(kvm, *p4d))
- unmap_stage2_puds(kvm, p4d, addr, next);
+ unmap_stage2_puds(mmu, p4d, addr, next);
} while (p4d++, addr = next, addr != end);
if (stage2_p4d_table_empty(kvm, start_p4d))
- clear_stage2_pgd_entry(kvm, pgd, start_addr);
+ clear_stage2_pgd_entry(mmu, pgd, start_addr);
}
/**
* destroying the VM), otherwise another faulting VCPU may come in and mess
* with things behind our backs.
*/
-static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
+static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
{
+ struct kvm *kvm = mmu->kvm;
pgd_t *pgd;
phys_addr_t addr = start, end = start + size;
phys_addr_t next;
assert_spin_locked(&kvm->mmu_lock);
WARN_ON(size & ~PAGE_MASK);
- pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr);
+ pgd = mmu->pgd + stage2_pgd_index(kvm, addr);
do {
/*
* Make sure the page table is still active, as another thread
* could have possibly freed the page table, while we released
* the lock.
*/
- if (!READ_ONCE(kvm->arch.pgd))
+ if (!READ_ONCE(mmu->pgd))
break;
next = stage2_pgd_addr_end(kvm, addr, end);
if (!stage2_pgd_none(kvm, *pgd))
- unmap_stage2_p4ds(kvm, pgd, addr, next);
+ unmap_stage2_p4ds(mmu, pgd, addr, next);
/*
* If the range is too large, release the kvm->mmu_lock
* to prevent starvation and lockup detector warnings.
} while (pgd++, addr = next, addr != end);
}
-static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd,
+static void stage2_flush_ptes(struct kvm_s2_mmu *mmu, pmd_t *pmd,
phys_addr_t addr, phys_addr_t end)
{
pte_t *pte;
} while (pte++, addr += PAGE_SIZE, addr != end);
}
-static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud,
+static void stage2_flush_pmds(struct kvm_s2_mmu *mmu, pud_t *pud,
phys_addr_t addr, phys_addr_t end)
{
+ struct kvm *kvm = mmu->kvm;
pmd_t *pmd;
phys_addr_t next;
if (pmd_thp_or_huge(*pmd))
kvm_flush_dcache_pmd(*pmd);
else
- stage2_flush_ptes(kvm, pmd, addr, next);
+ stage2_flush_ptes(mmu, pmd, addr, next);
}
} while (pmd++, addr = next, addr != end);
}
-static void stage2_flush_puds(struct kvm *kvm, p4d_t *p4d,
+static void stage2_flush_puds(struct kvm_s2_mmu *mmu, p4d_t *p4d,
phys_addr_t addr, phys_addr_t end)
{
+ struct kvm *kvm = mmu->kvm;
pud_t *pud;
phys_addr_t next;
if (stage2_pud_huge(kvm, *pud))
kvm_flush_dcache_pud(*pud);
else
- stage2_flush_pmds(kvm, pud, addr, next);
+ stage2_flush_pmds(mmu, pud, addr, next);
}
} while (pud++, addr = next, addr != end);
}
-static void stage2_flush_p4ds(struct kvm *kvm, pgd_t *pgd,
+static void stage2_flush_p4ds(struct kvm_s2_mmu *mmu, pgd_t *pgd,
phys_addr_t addr, phys_addr_t end)
{
+ struct kvm *kvm = mmu->kvm;
p4d_t *p4d;
phys_addr_t next;
do {
next = stage2_p4d_addr_end(kvm, addr, end);
if (!stage2_p4d_none(kvm, *p4d))
- stage2_flush_puds(kvm, p4d, addr, next);
+ stage2_flush_puds(mmu, p4d, addr, next);
} while (p4d++, addr = next, addr != end);
}
static void stage2_flush_memslot(struct kvm *kvm,
struct kvm_memory_slot *memslot)
{
+ struct kvm_s2_mmu *mmu = &kvm->arch.mmu;
phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
phys_addr_t end = addr + PAGE_SIZE * memslot->npages;
phys_addr_t next;
pgd_t *pgd;
- pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr);
+ pgd = mmu->pgd + stage2_pgd_index(kvm, addr);
do {
next = stage2_pgd_addr_end(kvm, addr, end);
if (!stage2_pgd_none(kvm, *pgd))
- stage2_flush_p4ds(kvm, pgd, addr, next);
+ stage2_flush_p4ds(mmu, pgd, addr, next);
if (next != end)
cond_resched_lock(&kvm->mmu_lock);
}
/**
- * kvm_alloc_stage2_pgd - allocate level-1 table for stage-2 translation.
- * @kvm: The KVM struct pointer for the VM.
+ * kvm_init_stage2_mmu - Initialise a S2 MMU strucrure
+ * @kvm: The pointer to the KVM structure
+ * @mmu: The pointer to the s2 MMU structure
*
* Allocates only the stage-2 HW PGD level table(s) of size defined by
- * stage2_pgd_size(kvm).
+ * stage2_pgd_size(mmu->kvm).
*
* Note we don't need locking here as this is only called when the VM is
* created, which can only be done once.
*/
-int kvm_alloc_stage2_pgd(struct kvm *kvm)
+int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu)
{
phys_addr_t pgd_phys;
pgd_t *pgd;
+ int cpu;
- if (kvm->arch.pgd != NULL) {
+ if (mmu->pgd != NULL) {
kvm_err("kvm_arch already initialized?\n");
return -EINVAL;
}
if (WARN_ON(pgd_phys & ~kvm_vttbr_baddr_mask(kvm)))
return -EINVAL;
- kvm->arch.pgd = pgd;
- kvm->arch.pgd_phys = pgd_phys;
+ mmu->last_vcpu_ran = alloc_percpu(typeof(*mmu->last_vcpu_ran));
+ if (!mmu->last_vcpu_ran) {
+ free_pages_exact(pgd, stage2_pgd_size(kvm));
+ return -ENOMEM;
+ }
+
+ for_each_possible_cpu(cpu)
+ *per_cpu_ptr(mmu->last_vcpu_ran, cpu) = -1;
+
+ mmu->kvm = kvm;
+ mmu->pgd = pgd;
+ mmu->pgd_phys = pgd_phys;
+ mmu->vmid.vmid_gen = 0;
+
return 0;
}
if (!(vma->vm_flags & VM_PFNMAP)) {
gpa_t gpa = addr + (vm_start - memslot->userspace_addr);
- unmap_stage2_range(kvm, gpa, vm_end - vm_start);
+ unmap_stage2_range(&kvm->arch.mmu, gpa, vm_end - vm_start);
}
hva = vm_end;
} while (hva < reg_end);
srcu_read_unlock(&kvm->srcu, idx);
}
-/**
- * kvm_free_stage2_pgd - free all stage-2 tables
- * @kvm: The KVM struct pointer for the VM.
- *
- * Walks the level-1 page table pointed to by kvm->arch.pgd and frees all
- * underlying level-2 and level-3 tables before freeing the actual level-1 table
- * and setting the struct pointer to NULL.
- */
-void kvm_free_stage2_pgd(struct kvm *kvm)
+void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu)
{
+ struct kvm *kvm = mmu->kvm;
void *pgd = NULL;
spin_lock(&kvm->mmu_lock);
- if (kvm->arch.pgd) {
- unmap_stage2_range(kvm, 0, kvm_phys_size(kvm));
- pgd = READ_ONCE(kvm->arch.pgd);
- kvm->arch.pgd = NULL;
- kvm->arch.pgd_phys = 0;
+ if (mmu->pgd) {
+ unmap_stage2_range(mmu, 0, kvm_phys_size(kvm));
+ pgd = READ_ONCE(mmu->pgd);
+ mmu->pgd = NULL;
}
spin_unlock(&kvm->mmu_lock);
/* Free the HW pgd, one page at a time */
- if (pgd)
+ if (pgd) {
free_pages_exact(pgd, stage2_pgd_size(kvm));
+ free_percpu(mmu->last_vcpu_ran);
+ }
}
-static p4d_t *stage2_get_p4d(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+static p4d_t *stage2_get_p4d(struct kvm_s2_mmu *mmu, struct kvm_mmu_memory_cache *cache,
phys_addr_t addr)
{
+ struct kvm *kvm = mmu->kvm;
pgd_t *pgd;
p4d_t *p4d;
- pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr);
+ pgd = mmu->pgd + stage2_pgd_index(kvm, addr);
if (stage2_pgd_none(kvm, *pgd)) {
if (!cache)
return NULL;
return stage2_p4d_offset(kvm, pgd, addr);
}
-static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+static pud_t *stage2_get_pud(struct kvm_s2_mmu *mmu, struct kvm_mmu_memory_cache *cache,
phys_addr_t addr)
{
+ struct kvm *kvm = mmu->kvm;
p4d_t *p4d;
pud_t *pud;
- p4d = stage2_get_p4d(kvm, cache, addr);
+ p4d = stage2_get_p4d(mmu, cache, addr);
if (stage2_p4d_none(kvm, *p4d)) {
if (!cache)
return NULL;
return stage2_pud_offset(kvm, p4d, addr);
}
-static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+static pmd_t *stage2_get_pmd(struct kvm_s2_mmu *mmu, struct kvm_mmu_memory_cache *cache,
phys_addr_t addr)
{
+ struct kvm *kvm = mmu->kvm;
pud_t *pud;
pmd_t *pmd;
- pud = stage2_get_pud(kvm, cache, addr);
+ pud = stage2_get_pud(mmu, cache, addr);
if (!pud || stage2_pud_huge(kvm, *pud))
return NULL;
return stage2_pmd_offset(kvm, pud, addr);
}
-static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
- *cache, phys_addr_t addr, const pmd_t *new_pmd)
+static int stage2_set_pmd_huge(struct kvm_s2_mmu *mmu,
+ struct kvm_mmu_memory_cache *cache,
+ phys_addr_t addr, const pmd_t *new_pmd)
{
pmd_t *pmd, old_pmd;
retry:
- pmd = stage2_get_pmd(kvm, cache, addr);
+ pmd = stage2_get_pmd(mmu, cache, addr);
VM_BUG_ON(!pmd);
old_pmd = *pmd;
* get handled accordingly.
*/
if (!pmd_thp_or_huge(old_pmd)) {
- unmap_stage2_range(kvm, addr & S2_PMD_MASK, S2_PMD_SIZE);
+ unmap_stage2_range(mmu, addr & S2_PMD_MASK, S2_PMD_SIZE);
goto retry;
}
/*
*/
WARN_ON_ONCE(pmd_pfn(old_pmd) != pmd_pfn(*new_pmd));
pmd_clear(pmd);
- kvm_tlb_flush_vmid_ipa(kvm, addr);
+ kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PMD_LEVEL);
} else {
get_page(virt_to_page(pmd));
}
return 0;
}
-static int stage2_set_pud_huge(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+static int stage2_set_pud_huge(struct kvm_s2_mmu *mmu,
+ struct kvm_mmu_memory_cache *cache,
phys_addr_t addr, const pud_t *new_pudp)
{
+ struct kvm *kvm = mmu->kvm;
pud_t *pudp, old_pud;
retry:
- pudp = stage2_get_pud(kvm, cache, addr);
+ pudp = stage2_get_pud(mmu, cache, addr);
VM_BUG_ON(!pudp);
old_pud = *pudp;
* the range for this block and retry.
*/
if (!stage2_pud_huge(kvm, old_pud)) {
- unmap_stage2_range(kvm, addr & S2_PUD_MASK, S2_PUD_SIZE);
+ unmap_stage2_range(mmu, addr & S2_PUD_MASK, S2_PUD_SIZE);
goto retry;
}
WARN_ON_ONCE(kvm_pud_pfn(old_pud) != kvm_pud_pfn(*new_pudp));
stage2_pud_clear(kvm, pudp);
- kvm_tlb_flush_vmid_ipa(kvm, addr);
+ kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PUD_LEVEL);
} else {
get_page(virt_to_page(pudp));
}
* leaf-entry is returned in the appropriate level variable - pudpp,
* pmdpp, ptepp.
*/
-static bool stage2_get_leaf_entry(struct kvm *kvm, phys_addr_t addr,
+static bool stage2_get_leaf_entry(struct kvm_s2_mmu *mmu, phys_addr_t addr,
pud_t **pudpp, pmd_t **pmdpp, pte_t **ptepp)
{
+ struct kvm *kvm = mmu->kvm;
pud_t *pudp;
pmd_t *pmdp;
pte_t *ptep;
*pmdpp = NULL;
*ptepp = NULL;
- pudp = stage2_get_pud(kvm, NULL, addr);
+ pudp = stage2_get_pud(mmu, NULL, addr);
if (!pudp || stage2_pud_none(kvm, *pudp) || !stage2_pud_present(kvm, *pudp))
return false;
return true;
}
-static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr)
+static bool stage2_is_exec(struct kvm_s2_mmu *mmu, phys_addr_t addr)
{
pud_t *pudp;
pmd_t *pmdp;
pte_t *ptep;
bool found;
- found = stage2_get_leaf_entry(kvm, addr, &pudp, &pmdp, &ptep);
+ found = stage2_get_leaf_entry(mmu, addr, &pudp, &pmdp, &ptep);
if (!found)
return false;
return kvm_s2pte_exec(ptep);
}
-static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+static int stage2_set_pte(struct kvm_s2_mmu *mmu,
+ struct kvm_mmu_memory_cache *cache,
phys_addr_t addr, const pte_t *new_pte,
unsigned long flags)
{
+ struct kvm *kvm = mmu->kvm;
pud_t *pud;
pmd_t *pmd;
pte_t *pte, old_pte;
VM_BUG_ON(logging_active && !cache);
/* Create stage-2 page table mapping - Levels 0 and 1 */
- pud = stage2_get_pud(kvm, cache, addr);
+ pud = stage2_get_pud(mmu, cache, addr);
if (!pud) {
/*
* Ignore calls from kvm_set_spte_hva for unallocated
* on to allocate page.
*/
if (logging_active)
- stage2_dissolve_pud(kvm, addr, pud);
+ stage2_dissolve_pud(mmu, addr, pud);
if (stage2_pud_none(kvm, *pud)) {
if (!cache)
* allocate page.
*/
if (logging_active)
- stage2_dissolve_pmd(kvm, addr, pmd);
+ stage2_dissolve_pmd(mmu, addr, pmd);
/* Create stage-2 page mappings - Level 2 */
if (pmd_none(*pmd)) {
return 0;
kvm_set_pte(pte, __pte(0));
- kvm_tlb_flush_vmid_ipa(kvm, addr);
+ kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PTE_LEVEL);
} else {
get_page(virt_to_page(pte));
}
if (ret)
goto out;
spin_lock(&kvm->mmu_lock);
- ret = stage2_set_pte(kvm, &cache, addr, &pte,
- KVM_S2PTE_FLAG_IS_IOMAP);
+ ret = stage2_set_pte(&kvm->arch.mmu, &cache, addr, &pte,
+ KVM_S2PTE_FLAG_IS_IOMAP);
spin_unlock(&kvm->mmu_lock);
if (ret)
goto out;
* @addr: range start address
* @end: range end address
*/
-static void stage2_wp_pmds(struct kvm *kvm, pud_t *pud,
+static void stage2_wp_pmds(struct kvm_s2_mmu *mmu, pud_t *pud,
phys_addr_t addr, phys_addr_t end)
{
+ struct kvm *kvm = mmu->kvm;
pmd_t *pmd;
phys_addr_t next;
/**
* stage2_wp_puds - write protect P4D range
- * @pgd: pointer to pgd entry
+ * @p4d: pointer to p4d entry
* @addr: range start address
* @end: range end address
*/
-static void stage2_wp_puds(struct kvm *kvm, p4d_t *p4d,
+static void stage2_wp_puds(struct kvm_s2_mmu *mmu, p4d_t *p4d,
phys_addr_t addr, phys_addr_t end)
{
+ struct kvm *kvm = mmu->kvm;
pud_t *pud;
phys_addr_t next;
if (!kvm_s2pud_readonly(pud))
kvm_set_s2pud_readonly(pud);
} else {
- stage2_wp_pmds(kvm, pud, addr, next);
+ stage2_wp_pmds(mmu, pud, addr, next);
}
}
} while (pud++, addr = next, addr != end);
* @addr: range start address
* @end: range end address
*/
-static void stage2_wp_p4ds(struct kvm *kvm, pgd_t *pgd,
+static void stage2_wp_p4ds(struct kvm_s2_mmu *mmu, pgd_t *pgd,
phys_addr_t addr, phys_addr_t end)
{
+ struct kvm *kvm = mmu->kvm;
p4d_t *p4d;
phys_addr_t next;
do {
next = stage2_p4d_addr_end(kvm, addr, end);
if (!stage2_p4d_none(kvm, *p4d))
- stage2_wp_puds(kvm, p4d, addr, next);
+ stage2_wp_puds(mmu, p4d, addr, next);
} while (p4d++, addr = next, addr != end);
}
* @addr: Start address of range
* @end: End address of range
*/
-static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
+static void stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
{
+ struct kvm *kvm = mmu->kvm;
pgd_t *pgd;
phys_addr_t next;
- pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr);
+ pgd = mmu->pgd + stage2_pgd_index(kvm, addr);
do {
/*
* Release kvm_mmu_lock periodically if the memory region is
* the lock.
*/
cond_resched_lock(&kvm->mmu_lock);
- if (!READ_ONCE(kvm->arch.pgd))
+ if (!READ_ONCE(mmu->pgd))
break;
next = stage2_pgd_addr_end(kvm, addr, end);
if (stage2_pgd_present(kvm, *pgd))
- stage2_wp_p4ds(kvm, pgd, addr, next);
+ stage2_wp_p4ds(mmu, pgd, addr, next);
} while (pgd++, addr = next, addr != end);
}
end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
spin_lock(&kvm->mmu_lock);
- stage2_wp_range(kvm, start, end);
+ stage2_wp_range(&kvm->arch.mmu, start, end);
spin_unlock(&kvm->mmu_lock);
kvm_flush_remote_tlbs(kvm);
}
phys_addr_t start = (base_gfn + __ffs(mask)) << PAGE_SHIFT;
phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT;
- stage2_wp_range(kvm, start, end);
+ stage2_wp_range(&kvm->arch.mmu, start, end);
}
/*
pgprot_t mem_type = PAGE_S2;
bool logging_active = memslot_is_logging(memslot);
unsigned long vma_pagesize, flags = 0;
+ struct kvm_s2_mmu *mmu = vcpu->arch.hw_mmu;
write_fault = kvm_is_write_fault(vcpu);
exec_fault = kvm_vcpu_trap_is_iabt(vcpu);
* execute permissions, and we preserve whatever we have.
*/
needs_exec = exec_fault ||
- (fault_status == FSC_PERM && stage2_is_exec(kvm, fault_ipa));
+ (fault_status == FSC_PERM && stage2_is_exec(mmu, fault_ipa));
if (vma_pagesize == PUD_SIZE) {
pud_t new_pud = kvm_pfn_pud(pfn, mem_type);
if (needs_exec)
new_pud = kvm_s2pud_mkexec(new_pud);
- ret = stage2_set_pud_huge(kvm, memcache, fault_ipa, &new_pud);
+ ret = stage2_set_pud_huge(mmu, memcache, fault_ipa, &new_pud);
} else if (vma_pagesize == PMD_SIZE) {
pmd_t new_pmd = kvm_pfn_pmd(pfn, mem_type);
if (needs_exec)
new_pmd = kvm_s2pmd_mkexec(new_pmd);
- ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd);
+ ret = stage2_set_pmd_huge(mmu, memcache, fault_ipa, &new_pmd);
} else {
pte_t new_pte = kvm_pfn_pte(pfn, mem_type);
if (needs_exec)
new_pte = kvm_s2pte_mkexec(new_pte);
- ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, flags);
+ ret = stage2_set_pte(mmu, memcache, fault_ipa, &new_pte, flags);
}
out_unlock:
spin_lock(&vcpu->kvm->mmu_lock);
- if (!stage2_get_leaf_entry(vcpu->kvm, fault_ipa, &pud, &pmd, &pte))
+ if (!stage2_get_leaf_entry(vcpu->arch.hw_mmu, fault_ipa, &pud, &pmd, &pte))
goto out;
if (pud) { /* HugeTLB */
is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
/* Synchronous External Abort? */
- if (kvm_vcpu_dabt_isextabt(vcpu)) {
+ if (kvm_vcpu_abt_issea(vcpu)) {
/*
* For RAS the host kernel may handle this abort.
* There is no need to pass the error into the guest.
*/
- if (!kvm_handle_guest_sea(fault_ipa, kvm_vcpu_get_esr(vcpu)))
- return 1;
-
- if (unlikely(!is_iabt)) {
+ if (kvm_handle_guest_sea(fault_ipa, kvm_vcpu_get_esr(vcpu)))
kvm_inject_vabt(vcpu);
- return 1;
- }
+
+ return 1;
}
trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_esr(vcpu),
hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable);
write_fault = kvm_is_write_fault(vcpu);
if (kvm_is_error_hva(hva) || (write_fault && !writable)) {
+ /*
+ * The guest has put either its instructions or its page-tables
+ * somewhere it shouldn't have. Userspace won't be able to do
+ * anything about this (there's no syndrome for a start), so
+ * re-inject the abort back into the guest.
+ */
if (is_iabt) {
- /* Prefetch Abort on I/O address */
ret = -ENOEXEC;
goto out;
}
+ if (kvm_vcpu_dabt_iss1tw(vcpu)) {
+ kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
+ ret = 1;
+ goto out_unlock;
+ }
+
/*
* Check for a cache maintenance operation. Since we
* ended-up here, we know it is outside of any memory
* So let's assume that the guest is just being
* cautious, and skip the instruction.
*/
- if (kvm_vcpu_dabt_is_cm(vcpu)) {
+ if (kvm_is_error_hva(hva) && kvm_vcpu_dabt_is_cm(vcpu)) {
kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
ret = 1;
goto out_unlock;
static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
{
- unmap_stage2_range(kvm, gpa, size);
+ unmap_stage2_range(&kvm->arch.mmu, gpa, size);
return 0;
}
int kvm_unmap_hva_range(struct kvm *kvm,
unsigned long start, unsigned long end)
{
- if (!kvm->arch.pgd)
+ if (!kvm->arch.mmu.pgd)
return 0;
trace_kvm_unmap_hva_range(start, end);
* therefore stage2_set_pte() never needs to clear out a huge PMD
* through this calling path.
*/
- stage2_set_pte(kvm, NULL, gpa, pte, 0);
+ stage2_set_pte(&kvm->arch.mmu, NULL, gpa, pte, 0);
return 0;
}
kvm_pfn_t pfn = pte_pfn(pte);
pte_t stage2_pte;
- if (!kvm->arch.pgd)
+ if (!kvm->arch.mmu.pgd)
return 0;
trace_kvm_set_spte_hva(hva);
pte_t *pte;
WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE);
- if (!stage2_get_leaf_entry(kvm, gpa, &pud, &pmd, &pte))
+ if (!stage2_get_leaf_entry(&kvm->arch.mmu, gpa, &pud, &pmd, &pte))
return 0;
if (pud)
pte_t *pte;
WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE);
- if (!stage2_get_leaf_entry(kvm, gpa, &pud, &pmd, &pte))
+ if (!stage2_get_leaf_entry(&kvm->arch.mmu, gpa, &pud, &pmd, &pte))
return 0;
if (pud)
int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
{
- if (!kvm->arch.pgd)
+ if (!kvm->arch.mmu.pgd)
return 0;
trace_kvm_age_hva(start, end);
return handle_hva_to_gpa(kvm, start, end, kvm_age_hva_handler, NULL);
int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
{
- if (!kvm->arch.pgd)
+ if (!kvm->arch.mmu.pgd)
return 0;
trace_kvm_test_age_hva(hva);
return handle_hva_to_gpa(kvm, hva, hva + PAGE_SIZE,
spin_lock(&kvm->mmu_lock);
if (ret)
- unmap_stage2_range(kvm, mem->guest_phys_addr, mem->memory_size);
+ unmap_stage2_range(&kvm->arch.mmu, mem->guest_phys_addr, mem->memory_size);
else
stage2_flush_memslot(kvm, memslot);
spin_unlock(&kvm->mmu_lock);
void kvm_arch_flush_shadow_all(struct kvm *kvm)
{
- kvm_free_stage2_pgd(kvm);
+ kvm_free_stage2_pgd(&kvm->arch.mmu);
}
void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
phys_addr_t size = slot->npages << PAGE_SHIFT;
spin_lock(&kvm->mmu_lock);
- unmap_stage2_range(kvm, gpa, size);
+ unmap_stage2_range(&kvm->arch.mmu, gpa, size);
spin_unlock(&kvm->mmu_lock);
}