@@ -819,6 +819,28 @@ static void kvmppc_restart_interrupt(struct kvm_vcpu *vcpu,
}
}
+static int kvmppc_resume_inst_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
+ enum emulation_result emulated, u32 last_inst)
+{
+ switch (emulated) {
+ case EMULATE_AGAIN:
+ return RESUME_GUEST;
+
+ case EMULATE_FAIL:
+ pr_debug("%s: load instruction from guest address %lx failed\n",
+ __func__, vcpu->arch.pc);
+ /* For debugging, encode the failing instruction and
+ * report it to userspace. */
+ run->hw.hardware_exit_reason = ~0ULL << 32;
+ run->hw.hardware_exit_reason |= last_inst;
+ kvmppc_core_queue_program(vcpu, ESR_PIL);
+ return RESUME_HOST;
+
+ default:
+ BUG();
+ }
+}
+
/**
* kvmppc_handle_exit
*
@@ -830,6 +852,8 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
int r = RESUME_HOST;
int s;
int idx;
+ u32 last_inst = KVM_INST_FETCH_FAILED;
+ enum emulation_result emulated = EMULATE_DONE;
/* update before a new last_exit_type is rewritten */
kvmppc_update_timing_stats(vcpu);
@@ -837,6 +861,20 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
/* restart interrupts if they were meant for the host */
kvmppc_restart_interrupt(vcpu, exit_nr);
+ /*
+ * get last instruction before beeing preempted
+ * TODO: for e6500 check also BOOKE_INTERRUPT_LRAT_ERROR & ESR_DATA
+ */
+ switch (exit_nr) {
+ case BOOKE_INTERRUPT_DATA_STORAGE:
+ case BOOKE_INTERRUPT_DTLB_MISS:
+ case BOOKE_INTERRUPT_HV_PRIV:
+ emulated = kvmppc_get_last_inst(vcpu, false, &last_inst);
+ break;
+ default:
+ break;
+ }
+
local_irq_enable();
trace_kvm_exit(exit_nr, vcpu);
@@ -845,6 +883,11 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
run->exit_reason = KVM_EXIT_UNKNOWN;
run->ready_for_interrupt_injection = 1;
+ if (emulated != EMULATE_DONE) {
+ r = kvmppc_resume_inst_load(run, vcpu, emulated, last_inst);
+ goto out;
+ }
+
switch (exit_nr) {
case BOOKE_INTERRUPT_MACHINE_CHECK:
printk("MACHINE CHECK: %lx\n", mfspr(SPRN_MCSR));
@@ -1134,6 +1177,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
BUG();
}
+out:
/*
* To avoid clobbering exit_reason, only check for signals if we
* aren't already exiting to userspace for some other reason.
@@ -121,38 +121,14 @@
1:
.if \flags & NEED_EMU
- /*
- * This assumes you have external PID support.
- * To support a bookehv CPU without external PID, you'll
- * need to look up the TLB entry and create a temporary mapping.
- *
- * FIXME: we don't currently handle if the lwepx faults. PR-mode
- * booke doesn't handle it either. Since Linux doesn't use
- * broadcast tlbivax anymore, the only way this should happen is
- * if the guest maps its memory execute-but-not-read, or if we
- * somehow take a TLB miss in the middle of this entry code and
- * evict the relevant entry. On e500mc, all kernel lowmem is
- * bolted into TLB1 large page mappings, and we don't use
- * broadcast invalidates, so we should not take a TLB miss here.
- *
- * Later we'll need to deal with faults here. Disallowing guest
- * mappings that are execute-but-not-read could be an option on
- * e500mc, but not on chips with an LRAT if it is used.
- */
-
- mfspr r3, SPRN_EPLC /* will already have correct ELPID and EGS */
PPC_STL r15, VCPU_GPR(R15)(r4)
PPC_STL r16, VCPU_GPR(R16)(r4)
PPC_STL r17, VCPU_GPR(R17)(r4)
PPC_STL r18, VCPU_GPR(R18)(r4)
PPC_STL r19, VCPU_GPR(R19)(r4)
- mr r8, r3
PPC_STL r20, VCPU_GPR(R20)(r4)
- rlwimi r8, r6, EPC_EAS_SHIFT - MSR_IR_LG, EPC_EAS
PPC_STL r21, VCPU_GPR(R21)(r4)
- rlwimi r8, r6, EPC_EPR_SHIFT - MSR_PR_LG, EPC_EPR
PPC_STL r22, VCPU_GPR(R22)(r4)
- rlwimi r8, r10, EPC_EPID_SHIFT, EPC_EPID
PPC_STL r23, VCPU_GPR(R23)(r4)
PPC_STL r24, VCPU_GPR(R24)(r4)
PPC_STL r25, VCPU_GPR(R25)(r4)
@@ -162,10 +138,15 @@
PPC_STL r29, VCPU_GPR(R29)(r4)
PPC_STL r30, VCPU_GPR(R30)(r4)
PPC_STL r31, VCPU_GPR(R31)(r4)
- mtspr SPRN_EPLC, r8
- isync
- lwepx r9, 0, r5
- mtspr SPRN_EPLC, r3
+
+ /*
+ * We don't use external PID support. lwepx faults would need to be
+ * handled by KVM and this implies aditional code in DO_KVM (for
+ * DTB_MISS, DSI and LRAT) to check ESR[EPID] and EPLC[EGS] which
+ * is too intrusive for the host. Get last instuction in
+ * kvmppc_get_last_inst().
+ */
+ li r9, KVM_INST_FETCH_FAILED
stw r9, VCPU_LAST_INST(r4)
.endif
@@ -610,11 +610,103 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
}
}
+#ifdef CONFIG_KVM_BOOKE_HV
+int kvmppc_load_last_inst(struct kvm_vcpu *vcpu, enum instruction_type type,
+ u32 *instr)
+{
+ gva_t geaddr;
+ hpa_t addr;
+ hfn_t pfn;
+ hva_t eaddr;
+ u32 mas1, mas2, mas3;
+ u64 mas7_mas3;
+ struct page *page;
+ unsigned int addr_space, psize_shift;
+ bool pr;
+ unsigned long flags;
+
+ /* Search TLB for guest pc to get the real address */
+ geaddr = kvmppc_get_pc(vcpu);
+
+ addr_space = (vcpu->arch.shared->msr & MSR_IS) >> MSR_IR_LG;
+
+ local_irq_save(flags);
+ mtspr(SPRN_MAS6, (vcpu->arch.pid << MAS6_SPID_SHIFT) | addr_space);
+ mtspr(SPRN_MAS5, MAS5_SGS | vcpu->kvm->arch.lpid);
+ asm volatile("tlbsx 0, %[geaddr]\n" : :
+ [geaddr] "r" (geaddr));
+ mtspr(SPRN_MAS5, 0);
+ mtspr(SPRN_MAS8, 0);
+ mas1 = mfspr(SPRN_MAS1);
+ mas2 = mfspr(SPRN_MAS2);
+ mas3 = mfspr(SPRN_MAS3);
+#ifdef CONFIG_64BIT
+ mas7_mas3 = mfspr(SPRN_MAS7_MAS3);
+#else
+ mas7_mas3 = ((u64)mfspr(SPRN_MAS7) << 32) | mas3;
+#endif
+ local_irq_restore(flags);
+
+ /*
+ * If the TLB entry for guest pc was evicted, return to the guest.
+ * There are high chances to find a valid TLB entry next time.
+ */
+ if (!(mas1 & MAS1_VALID))
+ return EMULATE_AGAIN;
+
+ /*
+ * Another thread may rewrite the TLB entry in parallel, don't
+ * execute from the address if the execute permission is not set
+ */
+ pr = vcpu->arch.shared->msr & MSR_PR;
+ if (unlikely((pr && !(mas3 & MAS3_UX)) ||
+ (!pr && !(mas3 & MAS3_SX)))) {
+ pr_err_ratelimited(
+ "%s: Instuction emulation from guest addres %08lx without execute permission\n",
+ __func__, geaddr);
+ return EMULATE_AGAIN;
+ }
+
+ /*
+ * The real address will be mapped by a cacheable, memory coherent,
+ * write-back page. Check for mismatches when LRAT is used.
+ */
+ if (has_feature(vcpu, VCPU_FTR_MMU_V2) &&
+ unlikely((mas2 & MAS2_I) || (mas2 & MAS2_W) || !(mas2 & MAS2_M))) {
+ pr_err_ratelimited(
+ "%s: Instuction emulation from guest addres %08lx mismatches storage attributes\n",
+ __func__, geaddr);
+ return EMULATE_AGAIN;
+ }
+
+ /* Get pfn */
+ psize_shift = MAS1_GET_TSIZE(mas1) + 10;
+ addr = (mas7_mas3 & (~0ULL << psize_shift)) |
+ (geaddr & ((1ULL << psize_shift) - 1ULL));
+ pfn = addr >> PAGE_SHIFT;
+
+ /* Guard against emulation from devices area */
+ if (unlikely(!page_is_ram(pfn))) {
+ pr_err_ratelimited("%s: Instruction emulation from non-RAM host addres %08llx is not supported\n",
+ __func__, addr);
+ return EMULATE_AGAIN;
+ }
+
+ /* Map a page and get guest's instruction */
+ page = pfn_to_page(pfn);
+ eaddr = (unsigned long)kmap_atomic(page);
+ *instr = *(u32 *)(eaddr | (unsigned long)(addr & ~PAGE_MASK));
+ kunmap_atomic((u32 *)eaddr);
+
+ return EMULATE_DONE;
+}
+#else
int kvmppc_load_last_inst(struct kvm_vcpu *vcpu, enum instruction_type type,
u32 *instr)
{
return EMULATE_AGAIN;
}
+#endif
/************* MMU Notifiers *************/