summaryrefslogtreecommitdiff
path: root/arch/powerpc/kvm/book3s_hv.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/kvm/book3s_hv.c')
-rw-r--r--arch/powerpc/kvm/book3s_hv.c252
1 files changed, 210 insertions, 42 deletions
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 0b921704da45..86bff159c51e 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -400,7 +400,10 @@ static inline unsigned long map_pcr_to_cap(unsigned long pcr)
cap = H_GUEST_CAP_POWER9;
break;
case PCR_ARCH_31:
- cap = H_GUEST_CAP_POWER10;
+ if (cpu_has_feature(CPU_FTR_P11_PVR))
+ cap = H_GUEST_CAP_POWER11;
+ else
+ cap = H_GUEST_CAP_POWER10;
break;
default:
break;
@@ -415,7 +418,7 @@ static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
struct kvmppc_vcore *vc = vcpu->arch.vcore;
/* We can (emulate) our own architecture version and anything older */
- if (cpu_has_feature(CPU_FTR_ARCH_31))
+ if (cpu_has_feature(CPU_FTR_P11_PVR) || cpu_has_feature(CPU_FTR_ARCH_31))
host_pcr_bit = PCR_ARCH_31;
else if (cpu_has_feature(CPU_FTR_ARCH_300))
host_pcr_bit = PCR_ARCH_300;
@@ -444,6 +447,7 @@ static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
guest_pcr_bit = PCR_ARCH_300;
break;
case PVR_ARCH_31:
+ case PVR_ARCH_31_P11:
guest_pcr_bit = PCR_ARCH_31;
break;
default:
@@ -1921,14 +1925,22 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
r = EMULATE_FAIL;
if (cpu_has_feature(CPU_FTR_ARCH_300)) {
- if (cause == FSCR_MSGP_LG)
+ switch (cause) {
+ case FSCR_MSGP_LG:
r = kvmppc_emulate_doorbell_instr(vcpu);
- if (cause == FSCR_PM_LG)
+ break;
+ case FSCR_PM_LG:
r = kvmppc_pmu_unavailable(vcpu);
- if (cause == FSCR_EBB_LG)
+ break;
+ case FSCR_EBB_LG:
r = kvmppc_ebb_unavailable(vcpu);
- if (cause == FSCR_TM_LG)
+ break;
+ case FSCR_TM_LG:
r = kvmppc_tm_unavailable(vcpu);
+ break;
+ default:
+ break;
+ }
}
if (r == EMULATE_FAIL) {
kvmppc_core_queue_program(vcpu, SRR1_PROGILL |
@@ -2051,36 +2063,9 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
fallthrough; /* go to facility unavailable handler */
#endif
- case BOOK3S_INTERRUPT_H_FAC_UNAVAIL: {
- u64 cause = vcpu->arch.hfscr >> 56;
-
- /*
- * Only pass HFU interrupts to the L1 if the facility is
- * permitted but disabled by the L1's HFSCR, otherwise
- * the interrupt does not make sense to the L1 so turn
- * it into a HEAI.
- */
- if (!(vcpu->arch.hfscr_permitted & (1UL << cause)) ||
- (vcpu->arch.nested_hfscr & (1UL << cause))) {
- ppc_inst_t pinst;
- vcpu->arch.trap = BOOK3S_INTERRUPT_H_EMUL_ASSIST;
-
- /*
- * If the fetch failed, return to guest and
- * try executing it again.
- */
- r = kvmppc_get_last_inst(vcpu, INST_GENERIC, &pinst);
- vcpu->arch.emul_inst = ppc_inst_val(pinst);
- if (r != EMULATE_DONE)
- r = RESUME_GUEST;
- else
- r = RESUME_HOST;
- } else {
- r = RESUME_HOST;
- }
-
+ case BOOK3S_INTERRUPT_H_FAC_UNAVAIL:
+ r = RESUME_HOST;
break;
- }
case BOOK3S_INTERRUPT_HV_RM_HARD:
vcpu->arch.trap = 0;
@@ -2304,7 +2289,7 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
*val = get_reg_val(id, kvmppc_get_siar_hv(vcpu));
break;
case KVM_REG_PPC_SDAR:
- *val = get_reg_val(id, kvmppc_get_siar_hv(vcpu));
+ *val = get_reg_val(id, kvmppc_get_sdar_hv(vcpu));
break;
case KVM_REG_PPC_SIER:
*val = get_reg_val(id, kvmppc_get_sier_hv(vcpu, 0));
@@ -2348,6 +2333,15 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
case KVM_REG_PPC_DAWRX1:
*val = get_reg_val(id, kvmppc_get_dawrx1_hv(vcpu));
break;
+ case KVM_REG_PPC_DEXCR:
+ *val = get_reg_val(id, kvmppc_get_dexcr_hv(vcpu));
+ break;
+ case KVM_REG_PPC_HASHKEYR:
+ *val = get_reg_val(id, kvmppc_get_hashkeyr_hv(vcpu));
+ break;
+ case KVM_REG_PPC_HASHPKEYR:
+ *val = get_reg_val(id, kvmppc_get_hashpkeyr_hv(vcpu));
+ break;
case KVM_REG_PPC_CIABR:
*val = get_reg_val(id, kvmppc_get_ciabr_hv(vcpu));
break;
@@ -2539,7 +2533,7 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
vcpu->arch.mmcrs = set_reg_val(id, *val);
break;
case KVM_REG_PPC_MMCR3:
- *val = get_reg_val(id, vcpu->arch.mmcr[3]);
+ kvmppc_set_mmcr_hv(vcpu, 3, set_reg_val(id, *val));
break;
case KVM_REG_PPC_PMC1 ... KVM_REG_PPC_PMC8:
i = id - KVM_REG_PPC_PMC1;
@@ -2591,6 +2585,15 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
case KVM_REG_PPC_DAWRX1:
kvmppc_set_dawrx1_hv(vcpu, set_reg_val(id, *val) & ~DAWRX_HYP);
break;
+ case KVM_REG_PPC_DEXCR:
+ kvmppc_set_dexcr_hv(vcpu, set_reg_val(id, *val));
+ break;
+ case KVM_REG_PPC_HASHKEYR:
+ kvmppc_set_hashkeyr_hv(vcpu, set_reg_val(id, *val));
+ break;
+ case KVM_REG_PPC_HASHPKEYR:
+ kvmppc_set_hashpkeyr_hv(vcpu, set_reg_val(id, *val));
+ break;
case KVM_REG_PPC_CIABR:
kvmppc_set_ciabr_hv(vcpu, set_reg_val(id, *val));
/* Don't allow setting breakpoints in hypervisor code */
@@ -4030,7 +4033,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
/* Return to whole-core mode if we split the core earlier */
if (cmd_bit) {
unsigned long hid0 = mfspr(SPRN_HID0);
- unsigned long loops = 0;
hid0 &= ~HID0_POWER8_DYNLPARDIS;
stat_bit = HID0_POWER8_2LPARMODE | HID0_POWER8_4LPARMODE;
@@ -4042,7 +4044,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
if (!(hid0 & stat_bit))
break;
cpu_relax();
- ++loops;
}
split_info.do_nap = 0;
}
@@ -4107,6 +4108,144 @@ static void vcpu_vpa_increment_dispatch(struct kvm_vcpu *vcpu)
}
}
+/* Helper functions for reading L2's stats from L1's VPA */
+#ifdef CONFIG_PPC_PSERIES
+static DEFINE_PER_CPU(u64, l1_to_l2_cs);
+static DEFINE_PER_CPU(u64, l2_to_l1_cs);
+static DEFINE_PER_CPU(u64, l2_runtime_agg);
+
+int kvmhv_get_l2_counters_status(void)
+{
+ return firmware_has_feature(FW_FEATURE_LPAR) &&
+ get_lppaca()->l2_counters_enable;
+}
+
+void kvmhv_set_l2_counters_status(int cpu, bool status)
+{
+ if (!firmware_has_feature(FW_FEATURE_LPAR))
+ return;
+ if (status)
+ lppaca_of(cpu).l2_counters_enable = 1;
+ else
+ lppaca_of(cpu).l2_counters_enable = 0;
+}
+EXPORT_SYMBOL(kvmhv_set_l2_counters_status);
+
+int kvmhv_counters_tracepoint_regfunc(void)
+{
+ int cpu;
+
+ for_each_present_cpu(cpu) {
+ kvmhv_set_l2_counters_status(cpu, true);
+ }
+ return 0;
+}
+
+void kvmhv_counters_tracepoint_unregfunc(void)
+{
+ int cpu;
+
+ for_each_present_cpu(cpu) {
+ kvmhv_set_l2_counters_status(cpu, false);
+ }
+}
+
+static void do_trace_nested_cs_time(struct kvm_vcpu *vcpu)
+{
+ struct lppaca *lp = get_lppaca();
+ u64 l1_to_l2_ns, l2_to_l1_ns, l2_runtime_ns;
+ u64 *l1_to_l2_cs_ptr = this_cpu_ptr(&l1_to_l2_cs);
+ u64 *l2_to_l1_cs_ptr = this_cpu_ptr(&l2_to_l1_cs);
+ u64 *l2_runtime_agg_ptr = this_cpu_ptr(&l2_runtime_agg);
+
+ l1_to_l2_ns = tb_to_ns(be64_to_cpu(lp->l1_to_l2_cs_tb));
+ l2_to_l1_ns = tb_to_ns(be64_to_cpu(lp->l2_to_l1_cs_tb));
+ l2_runtime_ns = tb_to_ns(be64_to_cpu(lp->l2_runtime_tb));
+ trace_kvmppc_vcpu_stats(vcpu, l1_to_l2_ns - *l1_to_l2_cs_ptr,
+ l2_to_l1_ns - *l2_to_l1_cs_ptr,
+ l2_runtime_ns - *l2_runtime_agg_ptr);
+ *l1_to_l2_cs_ptr = l1_to_l2_ns;
+ *l2_to_l1_cs_ptr = l2_to_l1_ns;
+ *l2_runtime_agg_ptr = l2_runtime_ns;
+ vcpu->arch.l1_to_l2_cs = l1_to_l2_ns;
+ vcpu->arch.l2_to_l1_cs = l2_to_l1_ns;
+ vcpu->arch.l2_runtime_agg = l2_runtime_ns;
+}
+
+u64 kvmhv_get_l1_to_l2_cs_time(void)
+{
+ return tb_to_ns(be64_to_cpu(get_lppaca()->l1_to_l2_cs_tb));
+}
+EXPORT_SYMBOL(kvmhv_get_l1_to_l2_cs_time);
+
+u64 kvmhv_get_l2_to_l1_cs_time(void)
+{
+ return tb_to_ns(be64_to_cpu(get_lppaca()->l2_to_l1_cs_tb));
+}
+EXPORT_SYMBOL(kvmhv_get_l2_to_l1_cs_time);
+
+u64 kvmhv_get_l2_runtime_agg(void)
+{
+ return tb_to_ns(be64_to_cpu(get_lppaca()->l2_runtime_tb));
+}
+EXPORT_SYMBOL(kvmhv_get_l2_runtime_agg);
+
+u64 kvmhv_get_l1_to_l2_cs_time_vcpu(void)
+{
+ struct kvm_vcpu *vcpu;
+ struct kvm_vcpu_arch *arch;
+
+ vcpu = local_paca->kvm_hstate.kvm_vcpu;
+ if (vcpu) {
+ arch = &vcpu->arch;
+ return arch->l1_to_l2_cs;
+ } else {
+ return 0;
+ }
+}
+EXPORT_SYMBOL(kvmhv_get_l1_to_l2_cs_time_vcpu);
+
+u64 kvmhv_get_l2_to_l1_cs_time_vcpu(void)
+{
+ struct kvm_vcpu *vcpu;
+ struct kvm_vcpu_arch *arch;
+
+ vcpu = local_paca->kvm_hstate.kvm_vcpu;
+ if (vcpu) {
+ arch = &vcpu->arch;
+ return arch->l2_to_l1_cs;
+ } else {
+ return 0;
+ }
+}
+EXPORT_SYMBOL(kvmhv_get_l2_to_l1_cs_time_vcpu);
+
+u64 kvmhv_get_l2_runtime_agg_vcpu(void)
+{
+ struct kvm_vcpu *vcpu;
+ struct kvm_vcpu_arch *arch;
+
+ vcpu = local_paca->kvm_hstate.kvm_vcpu;
+ if (vcpu) {
+ arch = &vcpu->arch;
+ return arch->l2_runtime_agg;
+ } else {
+ return 0;
+ }
+}
+EXPORT_SYMBOL(kvmhv_get_l2_runtime_agg_vcpu);
+
+#else
+int kvmhv_get_l2_counters_status(void)
+{
+ return 0;
+}
+
+static void do_trace_nested_cs_time(struct kvm_vcpu *vcpu)
+{
+}
+#endif
+
static int kvmhv_vcpu_entry_nestedv2(struct kvm_vcpu *vcpu, u64 time_limit,
unsigned long lpcr, u64 *tb)
{
@@ -4115,6 +4254,11 @@ static int kvmhv_vcpu_entry_nestedv2(struct kvm_vcpu *vcpu, u64 time_limit,
int trap;
long rc;
+ if (vcpu->arch.doorbell_request) {
+ vcpu->arch.doorbell_request = 0;
+ kvmppc_set_dpdes(vcpu, 1);
+ }
+
io = &vcpu->arch.nestedv2_io;
msr = mfmsr();
@@ -4155,6 +4299,10 @@ static int kvmhv_vcpu_entry_nestedv2(struct kvm_vcpu *vcpu, u64 time_limit,
timer_rearm_host_dec(*tb);
+ /* Record context switch and guest_run_time data */
+ if (kvmhv_get_l2_counters_status())
+ do_trace_nested_cs_time(vcpu);
+
return trap;
}
@@ -4205,6 +4353,15 @@ static int kvmhv_vcpu_entry_p9_nested(struct kvm_vcpu *vcpu, u64 time_limit, uns
hvregs.hdec_expiry = time_limit;
/*
+ * hvregs has the doorbell status, so zero it here which
+ * enables us to receive doorbells when H_ENTER_NESTED is
+ * in progress for this vCPU
+ */
+
+ if (vcpu->arch.doorbell_request)
+ vcpu->arch.doorbell_request = 0;
+
+ /*
* When setting DEC, we must always deal with irq_work_raise
* via NMI vs setting DEC. The problem occurs right as we
* switch into guest mode if a NMI hits and sets pending work
@@ -4793,9 +4950,20 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
BOOK3S_INTERRUPT_EXTERNAL, 0);
else
lpcr |= LPCR_MER;
+ } else {
+ /*
+ * L1's copy of L2's LPCR (vcpu->arch.vcore->lpcr) can get its MER bit
+ * unexpectedly set - for e.g. during NMI handling when all register
+ * states are synchronized from L0 to L1. L1 needs to inform L0 about
+ * MER=1 only when there are pending external interrupts.
+ * In the above if check, MER bit is set if there are pending
+ * external interrupts. Hence, explicitly mask off MER bit
+ * here as otherwise it may generate spurious interrupts in L2 KVM
+ * causing an endless loop, which results in L2 guest getting hung.
+ */
+ lpcr &= ~LPCR_MER;
}
} else if (vcpu->arch.pending_exceptions ||
- vcpu->arch.doorbell_request ||
xive_interrupt_pending(vcpu)) {
vcpu->arch.ret = RESUME_HOST;
goto out;
@@ -4856,7 +5024,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
* entering a nested guest in which case the decrementer is now owned
* by L2 and the L1 decrementer is provided in hdec_expires
*/
- if (!kvmhv_is_nestedv2() && kvmppc_core_pending_dec(vcpu) &&
+ if (kvmppc_core_pending_dec(vcpu) &&
((tb < kvmppc_dec_expires_host_tb(vcpu)) ||
(trap == BOOK3S_INTERRUPT_SYSCALL &&
kvmppc_get_gpr(vcpu, 3) == H_ENTER_NESTED)))
@@ -6363,7 +6531,6 @@ static struct kvmppc_ops kvm_ops_hv = {
.unmap_gfn_range = kvm_unmap_gfn_range_hv,
.age_gfn = kvm_age_gfn_hv,
.test_age_gfn = kvm_test_age_gfn_hv,
- .set_spte_gfn = kvm_set_spte_gfn_hv,
.free_memslot = kvmppc_core_free_memslot_hv,
.init_vm = kvmppc_core_init_vm_hv,
.destroy_vm = kvmppc_core_destroy_vm_hv,
@@ -6519,6 +6686,7 @@ static void kvmppc_book3s_exit_hv(void)
module_init(kvmppc_book3s_init_hv);
module_exit(kvmppc_book3s_exit_hv);
+MODULE_DESCRIPTION("KVM on Book3S (POWER8 and later) in hypervisor mode");
MODULE_LICENSE("GPL");
MODULE_ALIAS_MISCDEV(KVM_MINOR);
MODULE_ALIAS("devname:kvm");
generated by cgit (git 2.34.1) at 2025-07-23 09:43:12 +0000