/* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive * for more details. * * KVM/MIPS: MIPS specific KVM APIs * * Copyright (C) 2012 MIPS Technologies, Inc. All rights reserved. * Authors: Sanjay Lal <sanjayl@kymasys.com>
*/
/* * XXXKYMA: We are simulatoring a processor that has the WII bit set in * Config7, so we are "runnable" if interrupts are pending
*/ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{ return !!(vcpu->arch.pending_exceptions);
}
staticvoid kvm_mips_free_gpa_pt(struct kvm *kvm)
{ /* It should always be safe to remove after flushing the whole range */
WARN_ON(!kvm_mips_flush_gpa_pt(kvm, 0, ~0));
pgd_free(NULL, kvm->arch.gpa_mm.pgd);
}
void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot)
{ /* * The slot has been made invalid (ready for moving or deletion), so we * need to ensure that it can no longer be accessed by any guest VCPUs.
*/
/* * If dirty page logging is enabled, write protect all pages in the slot * ready for dirty logging. * * There is no need to do this in any of the following cases: * CREATE: No dirty mappings will already exist. * MOVE/DELETE: The old mappings will already have been cleaned up by * kvm_arch_flush_shadow_memslot()
*/ if (change == KVM_MR_FLAGS_ONLY &&
(!(old->flags & KVM_MEM_LOG_DIRTY_PAGES) &&
new->flags & KVM_MEM_LOG_DIRTY_PAGES)) {
spin_lock(&kvm->mmu_lock); /* Write protect GPA page table entries */
needs_flush = kvm_mips_mkclean_gpa_pt(kvm, new->base_gfn,
new->base_gfn + new->npages - 1); if (needs_flush)
kvm_flush_remote_tlbs_memslot(kvm, new);
spin_unlock(&kvm->mmu_lock);
}
}
/* * Check new ebase actually fits in CP0_EBase. The lack of a write gate * limits us to the low 512MB of physical address space. If the memory * we allocate is out of range, just give up now.
*/ if (!cpu_has_ebase_wg && virt_to_phys(gebase) >= 0x20000000) {
kvm_err("CP0_EBase.WG required for guest exception base %p\n",
gebase);
err = -ENOMEM; goto out_free_gebase;
}
/* Save new ebase */
vcpu->arch.guest_ebase = gebase;
/* * Actually run the vCPU, entering an RCU extended quiescent state (EQS) while * the vCPU is running. * * This must be noinstr as instrumentation may make use of RCU, and this is not * safe during the EQS.
*/ staticint noinstr kvm_mips_vcpu_enter_exit(struct kvm_vcpu *vcpu)
{ int ret;
guest_state_enter_irqoff();
ret = kvm_mips_callbacks->vcpu_run(vcpu);
guest_state_exit_irqoff();
return ret;
}
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
{ int r = -EINTR;
vcpu_load(vcpu);
kvm_sigset_activate(vcpu);
if (vcpu->mmio_needed) { if (!vcpu->mmio_is_write)
kvm_mips_complete_mmio_load(vcpu);
vcpu->mmio_needed = 0;
}
/* * Make sure the read of VCPU requests in vcpu_run() callback is not * reordered ahead of the write to vcpu->mode, or we could miss a TLB * flush request while the requester sees the VCPU as outside of guest * mode and not needing an IPI.
*/
smp_store_mb(vcpu->mode, IN_GUEST_MODE);
r = kvm_mips_vcpu_enter_exit(vcpu);
/* * We must ensure that any pending interrupts are taken before * we exit guest timing so that timer ticks are accounted as * guest time. Transiently unmask interrupts so that any * pending interrupts are taken. * * TODO: is there a barrier which ensures that pending interrupts are * recognised? Currently this just hopes that the CPU takes any pending * interrupts between the enable and disable.
*/
local_irq_enable();
local_irq_disable();
ret = ARRAY_SIZE(kvm_mips_get_one_regs); if (kvm_mips_guest_can_have_fpu(&vcpu->arch)) {
ret += ARRAY_SIZE(kvm_mips_get_one_regs_fpu) + 48; /* odd doubles */ if (boot_cpu_data.fpu_id & MIPS_FPIR_F64)
ret += 16;
} if (kvm_mips_guest_can_have_msa(&vcpu->arch))
ret += ARRAY_SIZE(kvm_mips_get_one_regs_msa) + 32;
ret += kvm_mips_callbacks->num_regs(vcpu);
if (copy_to_user(indices, kvm_mips_get_one_regs, sizeof(kvm_mips_get_one_regs))) return -EFAULT;
indices += ARRAY_SIZE(kvm_mips_get_one_regs);
if (kvm_mips_guest_can_have_fpu(&vcpu->arch)) { if (copy_to_user(indices, kvm_mips_get_one_regs_fpu, sizeof(kvm_mips_get_one_regs_fpu))) return -EFAULT;
indices += ARRAY_SIZE(kvm_mips_get_one_regs_fpu);
for (i = 0; i < 32; ++i) {
index = KVM_REG_MIPS_FPR_32(i); if (copy_to_user(indices, &index, sizeof(index))) return -EFAULT;
++indices;
/* skip odd doubles if no F64 */ if (i & 1 && !(boot_cpu_data.fpu_id & MIPS_FPIR_F64)) continue;
index = KVM_REG_MIPS_FPR_64(i); if (copy_to_user(indices, &index, sizeof(index))) return -EFAULT;
++indices;
}
}
if (kvm_mips_guest_can_have_msa(&vcpu->arch)) { if (copy_to_user(indices, kvm_mips_get_one_regs_msa, sizeof(kvm_mips_get_one_regs_msa))) return -EFAULT;
indices += ARRAY_SIZE(kvm_mips_get_one_regs_msa);
for (i = 0; i < 32; ++i) {
index = KVM_REG_MIPS_VEC_128(i); if (copy_to_user(indices, &index, sizeof(index))) return -EFAULT;
++indices;
}
}
switch (reg->id) { /* General purpose registers */ case KVM_REG_MIPS_R0 ... KVM_REG_MIPS_R31:
v = (long)vcpu->arch.gprs[reg->id - KVM_REG_MIPS_R0]; break; #ifndef CONFIG_CPU_MIPSR6 case KVM_REG_MIPS_HI:
v = (long)vcpu->arch.hi; break; case KVM_REG_MIPS_LO:
v = (long)vcpu->arch.lo; break; #endif case KVM_REG_MIPS_PC:
v = (long)vcpu->arch.pc; break;
/* Floating point registers */ case KVM_REG_MIPS_FPR_32(0) ... KVM_REG_MIPS_FPR_32(31): if (!kvm_mips_guest_has_fpu(&vcpu->arch)) return -EINVAL;
idx = reg->id - KVM_REG_MIPS_FPR_32(0); /* Odd singles in top of even double when FR=0 */ if (kvm_read_c0_guest_status(cop0) & ST0_FR)
v = get_fpr32(&fpu->fpr[idx], 0); else
v = get_fpr32(&fpu->fpr[idx & ~1], idx & 1); break; case KVM_REG_MIPS_FPR_64(0) ... KVM_REG_MIPS_FPR_64(31): if (!kvm_mips_guest_has_fpu(&vcpu->arch)) return -EINVAL;
idx = reg->id - KVM_REG_MIPS_FPR_64(0); /* Can't access odd doubles in FR=0 mode */ if (idx & 1 && !(kvm_read_c0_guest_status(cop0) & ST0_FR)) return -EINVAL;
v = get_fpr64(&fpu->fpr[idx], 0); break; case KVM_REG_MIPS_FCR_IR: if (!kvm_mips_guest_has_fpu(&vcpu->arch)) return -EINVAL;
v = boot_cpu_data.fpu_id; break; case KVM_REG_MIPS_FCR_CSR: if (!kvm_mips_guest_has_fpu(&vcpu->arch)) return -EINVAL;
v = fpu->fcr31; break;
/* MIPS SIMD Architecture (MSA) registers */ case KVM_REG_MIPS_VEC_128(0) ... KVM_REG_MIPS_VEC_128(31): if (!kvm_mips_guest_has_msa(&vcpu->arch)) return -EINVAL; /* Can't access MSA registers in FR=0 mode */ if (!(kvm_read_c0_guest_status(cop0) & ST0_FR)) return -EINVAL;
idx = reg->id - KVM_REG_MIPS_VEC_128(0); #ifdef CONFIG_CPU_LITTLE_ENDIAN /* least significant byte first */
vs[0] = get_fpr64(&fpu->fpr[idx], 0);
vs[1] = get_fpr64(&fpu->fpr[idx], 1); #else /* most significant byte first */
vs[0] = get_fpr64(&fpu->fpr[idx], 1);
vs[1] = get_fpr64(&fpu->fpr[idx], 0); #endif break; case KVM_REG_MIPS_MSA_IR: if (!kvm_mips_guest_has_msa(&vcpu->arch)) return -EINVAL;
v = boot_cpu_data.msa_id; break; case KVM_REG_MIPS_MSA_CSR: if (!kvm_mips_guest_has_msa(&vcpu->arch)) return -EINVAL;
v = fpu->msacsr; break;
/* registers to be handled specially */ default:
ret = kvm_mips_callbacks->get_one_reg(vcpu, reg, &v); if (ret) return ret; break;
} if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U64) {
u64 __user *uaddr64 = (u64 __user *)(long)reg->addr;
switch (ioctl) { case KVM_SET_ONE_REG: case KVM_GET_ONE_REG: { struct kvm_one_reg reg;
r = -EFAULT; if (copy_from_user(®, argp, sizeof(reg))) break; if (ioctl == KVM_SET_ONE_REG)
r = kvm_mips_set_reg(vcpu, ®); else
r = kvm_mips_get_reg(vcpu, ®); break;
} case KVM_GET_REG_LIST: { struct kvm_reg_list __user *user_list = argp; struct kvm_reg_list reg_list; unsigned n;
r = -EFAULT; if (copy_from_user(®_list, user_list, sizeof(reg_list))) break;
n = reg_list.n;
reg_list.n = kvm_mips_num_regs(vcpu); if (copy_to_user(user_list, ®_list, sizeof(reg_list))) break;
r = -E2BIG; if (n < reg_list.n) break;
r = kvm_mips_copy_reg_indices(vcpu, user_list->reg); break;
} case KVM_ENABLE_CAP: { struct kvm_enable_cap cap;
r = -EFAULT; if (copy_from_user(&cap, argp, sizeof(cap))) break;
r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap); break;
} default:
r = -ENOIOCTLCMD;
}
int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
{ int r;
switch (ext) { case KVM_CAP_ONE_REG: case KVM_CAP_ENABLE_CAP: case KVM_CAP_READONLY_MEM: case KVM_CAP_SYNC_MMU: case KVM_CAP_IMMEDIATE_EXIT:
r = 1; break; case KVM_CAP_NR_VCPUS:
r = min_t(unsignedint, num_online_cpus(), KVM_MAX_VCPUS); break; case KVM_CAP_MAX_VCPUS:
r = KVM_MAX_VCPUS; break; case KVM_CAP_MAX_VCPU_ID:
r = KVM_MAX_VCPU_IDS; break; case KVM_CAP_MIPS_FPU: /* We don't handle systems with inconsistent cpu_has_fpu */
r = !!raw_cpu_has_fpu; break; case KVM_CAP_MIPS_MSA: /* * We don't support MSA vector partitioning yet: * 1) It would require explicit support which can't be tested * yet due to lack of support in current hardware. * 2) It extends the state that would need to be saved/restored * by e.g. QEMU for migration. * * When vector partitioning hardware becomes available, support * could be added by requiring a flag when enabling * KVM_CAP_MIPS_MSA capability to indicate that userland knows * to save/restore the appropriate extra state.
*/
r = cpu_has_msa && !(boot_cpu_data.msa_id & MSA_IR_WRPF); break; default:
r = kvm_mips_callbacks->check_extension(kvm, ext); break;
} return r;
}
int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{ int i;
vcpu_load(vcpu);
for (i = 1; i < ARRAY_SIZE(vcpu->arch.gprs); i++)
vcpu->arch.gprs[i] = regs->gpr[i];
vcpu->arch.gprs[0] = 0; /* zero is special, and cannot be set. */
vcpu->arch.hi = regs->hi;
vcpu->arch.lo = regs->lo;
vcpu->arch.pc = regs->pc;
vcpu_put(vcpu); return 0;
}
int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{ int i;
vcpu_load(vcpu);
for (i = 0; i < ARRAY_SIZE(vcpu->arch.gprs); i++)
regs->gpr[i] = vcpu->arch.gprs[i];
switch (exccode) { case EXCCODE_INT:
kvm_debug("[%d]EXCCODE_INT @ %p\n", vcpu->vcpu_id, opc);
++vcpu->stat.int_exits;
if (need_resched())
cond_resched();
ret = RESUME_GUEST; break;
case EXCCODE_CPU:
kvm_debug("EXCCODE_CPU: @ PC: %p\n", opc);
++vcpu->stat.cop_unusable_exits;
ret = kvm_mips_callbacks->handle_cop_unusable(vcpu); /* XXXKYMA: Might need to return to user space */ if (run->exit_reason == KVM_EXIT_IRQ_WINDOW_OPEN)
ret = RESUME_HOST; break;
case EXCCODE_MOD:
++vcpu->stat.tlbmod_exits;
ret = kvm_mips_callbacks->handle_tlb_mod(vcpu); break;
case EXCCODE_TLBS:
kvm_debug("TLB ST fault: cause %#x, status %#x, PC: %p, BadVaddr: %#lx\n",
cause, kvm_read_c0_guest_status(&vcpu->arch.cop0), opc,
badvaddr);
++vcpu->stat.tlbmiss_st_exits;
ret = kvm_mips_callbacks->handle_tlb_st_miss(vcpu); break;
case EXCCODE_TLBL:
kvm_debug("TLB LD fault: cause %#x, PC: %p, BadVaddr: %#lx\n",
cause, opc, badvaddr);
++vcpu->stat.tlbmiss_ld_exits;
ret = kvm_mips_callbacks->handle_tlb_ld_miss(vcpu); break;
case EXCCODE_ADES:
++vcpu->stat.addrerr_st_exits;
ret = kvm_mips_callbacks->handle_addr_err_st(vcpu); break;
case EXCCODE_ADEL:
++vcpu->stat.addrerr_ld_exits;
ret = kvm_mips_callbacks->handle_addr_err_ld(vcpu); break;
case EXCCODE_SYS:
++vcpu->stat.syscall_exits;
ret = kvm_mips_callbacks->handle_syscall(vcpu); break;
case EXCCODE_RI:
++vcpu->stat.resvd_inst_exits;
ret = kvm_mips_callbacks->handle_res_inst(vcpu); break;
case EXCCODE_BP:
++vcpu->stat.break_inst_exits;
ret = kvm_mips_callbacks->handle_break(vcpu); break;
case EXCCODE_TR:
++vcpu->stat.trap_inst_exits;
ret = kvm_mips_callbacks->handle_trap(vcpu); break;
case EXCCODE_MSAFPE:
++vcpu->stat.msa_fpe_exits;
ret = kvm_mips_callbacks->handle_msa_fpe(vcpu); break;
case EXCCODE_FPE:
++vcpu->stat.fpe_exits;
ret = kvm_mips_callbacks->handle_fpe(vcpu); break;
case EXCCODE_MSADIS:
++vcpu->stat.msa_disabled_exits;
ret = kvm_mips_callbacks->handle_msa_disabled(vcpu); break;
case EXCCODE_GE: /* defer exit accounting to handler */
ret = kvm_mips_callbacks->handle_guest_exit(vcpu); break;
if (ret == RESUME_GUEST)
kvm_vz_acquire_htimer(vcpu);
if (er == EMULATE_DONE && !(ret & RESUME_HOST))
kvm_mips_deliver_interrupts(vcpu, cause);
if (!(ret & RESUME_HOST)) { /* Only check for signals if not already exiting to userspace */ if (signal_pending(current)) {
run->exit_reason = KVM_EXIT_INTR;
ret = (-EINTR << 2) | RESUME_HOST;
++vcpu->stat.signal_exits;
trace_kvm_exit(vcpu, KVM_TRACE_EXIT_SIGNAL);
}
}
if (ret == RESUME_GUEST) {
trace_kvm_reenter(vcpu);
/* * Make sure the read of VCPU requests in vcpu_reenter() * callback is not reordered ahead of the write to vcpu->mode, * or we could miss a TLB flush request while the requester sees * the VCPU as outside of guest mode and not needing an IPI.
*/
smp_store_mb(vcpu->mode, IN_GUEST_MODE);
kvm_mips_callbacks->vcpu_reenter(vcpu);
/* * If FPU / MSA are enabled (i.e. the guest's FPU / MSA context * is live), restore FCR31 / MSACSR. * * This should be before returning to the guest exception * vector, as it may well cause an [MSA] FP exception if there * are pending exception bits unmasked. (see * kvm_mips_csr_die_notifier() for how that is handled).
*/ if (kvm_mips_guest_has_fpu(&vcpu->arch) &&
read_c0_status() & ST0_CU1)
__kvm_restore_fcsr(&vcpu->arch);
/* * If MSA state is already live, it is undefined how it interacts with * FR=0 FPU state, and we don't want to hit reserved instruction * exceptions trying to save the MSA state later when CU=1 && FR=1, so * play it safe and save it first.
*/ if (cpu_has_msa && sr & ST0_CU1 && !(sr & ST0_FR) &&
vcpu->arch.aux_inuse & KVM_MIPS_AUX_MSA)
kvm_lose_fpu(vcpu);
/* * Enable FPU for guest * We set FR and FRE according to guest context
*/
change_c0_status(ST0_CU1 | ST0_FR, sr); if (cpu_has_fre) {
cfg5 = kvm_read_c0_guest_config5(cop0);
change_c0_config5(MIPS_CONF5_FRE, cfg5);
}
enable_fpu_hazard();
/* If guest FPU state not active, restore it now */ if (!(vcpu->arch.aux_inuse & KVM_MIPS_AUX_FPU)) {
__kvm_restore_fpu(&vcpu->arch);
vcpu->arch.aux_inuse |= KVM_MIPS_AUX_FPU;
trace_kvm_aux(vcpu, KVM_TRACE_AUX_RESTORE, KVM_TRACE_AUX_FPU);
} else {
trace_kvm_aux(vcpu, KVM_TRACE_AUX_ENABLE, KVM_TRACE_AUX_FPU);
}
/* * Enable FPU if enabled in guest, since we're restoring FPU context * anyway. We set FR and FRE according to guest context.
*/ if (kvm_mips_guest_has_fpu(&vcpu->arch)) {
sr = kvm_read_c0_guest_status(cop0);
/* * If FR=0 FPU state is already live, it is undefined how it * interacts with MSA state, so play it safe and save it first.
*/ if (!(sr & ST0_FR) &&
(vcpu->arch.aux_inuse & (KVM_MIPS_AUX_FPU |
KVM_MIPS_AUX_MSA)) == KVM_MIPS_AUX_FPU)
kvm_lose_fpu(vcpu);
/* Enable MSA for guest */
set_c0_config5(MIPS_CONF5_MSAEN);
enable_fpu_hazard();
switch (vcpu->arch.aux_inuse & (KVM_MIPS_AUX_FPU | KVM_MIPS_AUX_MSA)) { case KVM_MIPS_AUX_FPU: /* * Guest FPU state already loaded, only restore upper MSA state
*/
__kvm_restore_msa_upper(&vcpu->arch);
vcpu->arch.aux_inuse |= KVM_MIPS_AUX_MSA;
trace_kvm_aux(vcpu, KVM_TRACE_AUX_RESTORE, KVM_TRACE_AUX_MSA); break; case 0: /* Neither FPU or MSA already active, restore full MSA state */
__kvm_restore_msa(&vcpu->arch);
vcpu->arch.aux_inuse |= KVM_MIPS_AUX_MSA; if (kvm_mips_guest_has_fpu(&vcpu->arch))
vcpu->arch.aux_inuse |= KVM_MIPS_AUX_FPU;
trace_kvm_aux(vcpu, KVM_TRACE_AUX_RESTORE,
KVM_TRACE_AUX_FPU_MSA); break; default:
trace_kvm_aux(vcpu, KVM_TRACE_AUX_ENABLE, KVM_TRACE_AUX_MSA); break;
}
preempt_enable();
} #endif
/* Drop FPU & MSA without saving it */ void kvm_drop_fpu(struct kvm_vcpu *vcpu)
{
preempt_disable(); if (cpu_has_msa && vcpu->arch.aux_inuse & KVM_MIPS_AUX_MSA) {
disable_msa();
trace_kvm_aux(vcpu, KVM_TRACE_AUX_DISCARD, KVM_TRACE_AUX_MSA);
vcpu->arch.aux_inuse &= ~KVM_MIPS_AUX_MSA;
} if (vcpu->arch.aux_inuse & KVM_MIPS_AUX_FPU) {
clear_c0_status(ST0_CU1 | ST0_FR);
trace_kvm_aux(vcpu, KVM_TRACE_AUX_DISCARD, KVM_TRACE_AUX_FPU);
vcpu->arch.aux_inuse &= ~KVM_MIPS_AUX_FPU;
}
preempt_enable();
}
/* Save and disable FPU & MSA */ void kvm_lose_fpu(struct kvm_vcpu *vcpu)
{ /* * With T&E, FPU & MSA get disabled in root context (hardware) when it * is disabled in guest context (software), but the register state in * the hardware may still be in use. * This is why we explicitly re-enable the hardware before saving.
*/
/* * Step over a specific ctc1 to FCSR and a specific ctcmsa to MSACSR which are * used to restore guest FCSR/MSACSR state and may trigger a "harmless" FP/MSAFP * exception if cause bits are set in the value being written.
*/ staticint kvm_mips_csr_die_notify(struct notifier_block *self, unsignedlong cmd, void *ptr)
{ struct die_args *args = (struct die_args *)ptr; struct pt_regs *regs = args->regs; unsignedlong pc;
/* Only interested in FPE and MSAFPE */ if (cmd != DIE_FP && cmd != DIE_MSAFP) return NOTIFY_DONE;
/* Return immediately if guest context isn't active */ if (!(current->flags & PF_VCPU)) return NOTIFY_DONE;
/* Should never get here from user mode */
BUG_ON(user_mode(regs));
pc = instruction_pointer(regs); switch (cmd) { case DIE_FP: /* match 2nd instruction in __kvm_restore_fcsr */ if (pc != (unsignedlong)&__kvm_restore_fcsr + 4) return NOTIFY_DONE; break; case DIE_MSAFP: /* match 2nd/3rd instruction in __kvm_restore_msacsr */ if (!cpu_has_msa ||
pc < (unsignedlong)&__kvm_restore_msacsr + 4 ||
pc > (unsignedlong)&__kvm_restore_msacsr + 8) return NOTIFY_DONE; break;
}
/* Move PC forward a little and continue executing */
instruction_pointer(regs) += 4;
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.