diff options
Diffstat (limited to 'accel/kvm/kvm-all.c')
| -rw-r--r-- | accel/kvm/kvm-all.c | 238 |
1 files changed, 146 insertions, 92 deletions
diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c index fe4cd721d9..905fb844e4 100644 --- a/accel/kvm/kvm-all.c +++ b/accel/kvm/kvm-all.c @@ -2381,6 +2381,109 @@ uint32_t kvm_dirty_ring_size(void) return kvm_state->kvm_dirty_ring_size; } +static int do_kvm_create_vm(MachineState *ms, int type) +{ + KVMState *s; + int ret; + + s = KVM_STATE(ms->accelerator); + + do { + ret = kvm_ioctl(s, KVM_CREATE_VM, type); + } while (ret == -EINTR); + + if (ret < 0) { + error_report("ioctl(KVM_CREATE_VM) failed: %s", strerror(-ret)); + +#ifdef TARGET_S390X + if (ret == -EINVAL) { + error_printf("Host kernel setup problem detected." + " Please verify:\n"); + error_printf("- for kernels supporting the" + " switch_amode or user_mode parameters, whether"); + error_printf(" user space is running in primary address space\n"); + error_printf("- for kernels supporting the vm.allocate_pgste" + " sysctl, whether it is enabled\n"); + } +#elif defined(TARGET_PPC) + if (ret == -EINVAL) { + error_printf("PPC KVM module is not loaded. Try modprobe kvm_%s.\n", + (type == 2) ? "pr" : "hv"); + } +#endif + } + + return ret; +} + +static int find_kvm_machine_type(MachineState *ms) +{ + MachineClass *mc = MACHINE_GET_CLASS(ms); + int type; + + if (object_property_find(OBJECT(current_machine), "kvm-type")) { + g_autofree char *kvm_type; + kvm_type = object_property_get_str(OBJECT(current_machine), + "kvm-type", + &error_abort); + type = mc->kvm_type(ms, kvm_type); + } else if (mc->kvm_type) { + type = mc->kvm_type(ms, NULL); + } else { + type = kvm_arch_get_default_type(ms); + } + return type; +} + +static int kvm_setup_dirty_ring(KVMState *s) +{ + uint64_t dirty_log_manual_caps; + int ret; + + /* + * Enable KVM dirty ring if supported, otherwise fall back to + * dirty logging mode + */ + ret = kvm_dirty_ring_init(s); + if (ret < 0) { + return ret; + } + + /* + * KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is not needed when dirty ring is + * enabled. More importantly, KVM_DIRTY_LOG_INITIALLY_SET will assume no + * page is wr-protected initially, which is against how kvm dirty ring is + * usage - kvm dirty ring requires all pages are wr-protected at the very + * beginning. Enabling this feature for dirty ring causes data corruption. + * + * TODO: Without KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 and kvm clear dirty log, + * we may expect a higher stall time when starting the migration. In the + * future we can enable KVM_CLEAR_DIRTY_LOG to work with dirty ring too: + * instead of clearing dirty bit, it can be a way to explicitly wr-protect + * guest pages. + */ + if (!s->kvm_dirty_ring_size) { + dirty_log_manual_caps = + kvm_check_extension(s, KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); + dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | + KVM_DIRTY_LOG_INITIALLY_SET); + s->manual_dirty_log_protect = dirty_log_manual_caps; + if (dirty_log_manual_caps) { + ret = kvm_vm_enable_cap(s, KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2, 0, + dirty_log_manual_caps); + if (ret) { + warn_report("Trying to enable capability %"PRIu64" of " + "KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 but failed. " + "Falling back to the legacy mode. ", + dirty_log_manual_caps); + s->manual_dirty_log_protect = 0; + } + } + } + + return 0; +} + static int kvm_init(MachineState *ms) { MachineClass *mc = MACHINE_GET_CLASS(ms); @@ -2400,7 +2503,6 @@ static int kvm_init(MachineState *ms) const KVMCapabilityInfo *missing_cap; int ret; int type; - uint64_t dirty_log_manual_caps; qemu_mutex_init(&kml_slots_lock); @@ -2423,7 +2525,7 @@ static int kvm_init(MachineState *ms) QLIST_INIT(&s->kvm_parked_vcpus); s->fd = qemu_open_old(s->device ?: "/dev/kvm", O_RDWR); if (s->fd == -1) { - fprintf(stderr, "Could not access KVM kernel module: %m\n"); + error_report("Could not access KVM kernel module: %m"); ret = -errno; goto err; } @@ -2433,13 +2535,13 @@ static int kvm_init(MachineState *ms) if (ret >= 0) { ret = -EINVAL; } - fprintf(stderr, "kvm version too old\n"); + error_report("kvm version too old"); goto err; } if (ret > KVM_API_VERSION) { ret = -EINVAL; - fprintf(stderr, "kvm version not supported\n"); + error_report("kvm version not supported"); goto err; } @@ -2463,49 +2565,14 @@ static int kvm_init(MachineState *ms) } s->as = g_new0(struct KVMAs, s->nr_as); - if (object_property_find(OBJECT(current_machine), "kvm-type")) { - g_autofree char *kvm_type = object_property_get_str(OBJECT(current_machine), - "kvm-type", - &error_abort); - type = mc->kvm_type(ms, kvm_type); - } else if (mc->kvm_type) { - type = mc->kvm_type(ms, NULL); - } else { - type = kvm_arch_get_default_type(ms); - } - + type = find_kvm_machine_type(ms); if (type < 0) { ret = -EINVAL; goto err; } - do { - ret = kvm_ioctl(s, KVM_CREATE_VM, type); - } while (ret == -EINTR); - + ret = do_kvm_create_vm(ms, type); if (ret < 0) { - fprintf(stderr, "ioctl(KVM_CREATE_VM) failed: %d %s\n", -ret, - strerror(-ret)); - -#ifdef TARGET_S390X - if (ret == -EINVAL) { - fprintf(stderr, - "Host kernel setup problem detected. Please verify:\n"); - fprintf(stderr, "- for kernels supporting the switch_amode or" - " user_mode parameters, whether\n"); - fprintf(stderr, - " user space is running in primary address space\n"); - fprintf(stderr, - "- for kernels supporting the vm.allocate_pgste sysctl, " - "whether it is enabled\n"); - } -#elif defined(TARGET_PPC) - if (ret == -EINVAL) { - fprintf(stderr, - "PPC KVM module is not loaded. Try modprobe kvm_%s.\n", - (type == 2) ? "pr" : "hv"); - } -#endif goto err; } @@ -2522,9 +2589,9 @@ static int kvm_init(MachineState *ms) nc->name, nc->num, soft_vcpus_limit); if (nc->num > hard_vcpus_limit) { - fprintf(stderr, "Number of %s cpus requested (%d) exceeds " - "the maximum cpus supported by KVM (%d)\n", - nc->name, nc->num, hard_vcpus_limit); + error_report("Number of %s cpus requested (%d) exceeds " + "the maximum cpus supported by KVM (%d)", + nc->name, nc->num, hard_vcpus_limit); exit(1); } } @@ -2538,8 +2605,8 @@ static int kvm_init(MachineState *ms) } if (missing_cap) { ret = -EINVAL; - fprintf(stderr, "kvm does not support %s\n%s", - missing_cap->name, upgrade_note); + error_report("kvm does not support %s", missing_cap->name); + error_printf("%s", upgrade_note); goto err; } @@ -2547,47 +2614,11 @@ static int kvm_init(MachineState *ms) s->coalesced_pio = s->coalesced_mmio && kvm_check_extension(s, KVM_CAP_COALESCED_PIO); - /* - * Enable KVM dirty ring if supported, otherwise fall back to - * dirty logging mode - */ - ret = kvm_dirty_ring_init(s); + ret = kvm_setup_dirty_ring(s); if (ret < 0) { goto err; } - /* - * KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is not needed when dirty ring is - * enabled. More importantly, KVM_DIRTY_LOG_INITIALLY_SET will assume no - * page is wr-protected initially, which is against how kvm dirty ring is - * usage - kvm dirty ring requires all pages are wr-protected at the very - * beginning. Enabling this feature for dirty ring causes data corruption. - * - * TODO: Without KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 and kvm clear dirty log, - * we may expect a higher stall time when starting the migration. In the - * future we can enable KVM_CLEAR_DIRTY_LOG to work with dirty ring too: - * instead of clearing dirty bit, it can be a way to explicitly wr-protect - * guest pages. - */ - if (!s->kvm_dirty_ring_size) { - dirty_log_manual_caps = - kvm_check_extension(s, KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); - dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | - KVM_DIRTY_LOG_INITIALLY_SET); - s->manual_dirty_log_protect = dirty_log_manual_caps; - if (dirty_log_manual_caps) { - ret = kvm_vm_enable_cap(s, KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2, 0, - dirty_log_manual_caps); - if (ret) { - warn_report("Trying to enable capability %"PRIu64" of " - "KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 but failed. " - "Falling back to the legacy mode. ", - dirty_log_manual_caps); - s->manual_dirty_log_protect = 0; - } - } - } - #ifdef KVM_CAP_VCPU_EVENTS s->vcpu_events = kvm_check_extension(s, KVM_CAP_VCPU_EVENTS); #endif @@ -2762,9 +2793,15 @@ void kvm_flush_coalesced_mmio_buffer(void) static void do_kvm_cpu_synchronize_state(CPUState *cpu, run_on_cpu_data arg) { if (!cpu->vcpu_dirty && !kvm_state->guest_state_protected) { - int ret = kvm_arch_get_registers(cpu); + Error *err = NULL; + int ret = kvm_arch_get_registers(cpu, &err); if (ret) { - error_report("Failed to get registers: %s", strerror(-ret)); + if (err) { + error_reportf_err(err, "Failed to synchronize CPU state: "); + } else { + error_report("Failed to get registers: %s", strerror(-ret)); + } + cpu_dump_state(cpu, stderr, CPU_DUMP_CODE); vm_stop(RUN_STATE_INTERNAL_ERROR); } @@ -2782,9 +2819,15 @@ void kvm_cpu_synchronize_state(CPUState *cpu) static void do_kvm_cpu_synchronize_post_reset(CPUState *cpu, run_on_cpu_data arg) { - int ret = kvm_arch_put_registers(cpu, KVM_PUT_RESET_STATE); + Error *err = NULL; + int ret = kvm_arch_put_registers(cpu, KVM_PUT_RESET_STATE, &err); if (ret) { - error_report("Failed to put registers after reset: %s", strerror(-ret)); + if (err) { + error_reportf_err(err, "Restoring resisters after reset: "); + } else { + error_report("Failed to put registers after reset: %s", + strerror(-ret)); + } cpu_dump_state(cpu, stderr, CPU_DUMP_CODE); vm_stop(RUN_STATE_INTERNAL_ERROR); } @@ -2799,9 +2842,15 @@ void kvm_cpu_synchronize_post_reset(CPUState *cpu) static void do_kvm_cpu_synchronize_post_init(CPUState *cpu, run_on_cpu_data arg) { - int ret = kvm_arch_put_registers(cpu, KVM_PUT_FULL_STATE); + Error *err = NULL; + int ret = kvm_arch_put_registers(cpu, KVM_PUT_FULL_STATE, &err); if (ret) { - error_report("Failed to put registers after init: %s", strerror(-ret)); + if (err) { + error_reportf_err(err, "Putting registers after init: "); + } else { + error_report("Failed to put registers after init: %s", + strerror(-ret)); + } exit(1); } @@ -2991,10 +3040,15 @@ int kvm_cpu_exec(CPUState *cpu) MemTxAttrs attrs; if (cpu->vcpu_dirty) { - ret = kvm_arch_put_registers(cpu, KVM_PUT_RUNTIME_STATE); + Error *err = NULL; + ret = kvm_arch_put_registers(cpu, KVM_PUT_RUNTIME_STATE, &err); if (ret) { - error_report("Failed to put registers after init: %s", - strerror(-ret)); + if (err) { + error_reportf_err(err, "Putting registers after init: "); + } else { + error_report("Failed to put registers after init: %s", + strerror(-ret)); + } ret = -1; break; } |