Re: [PATCH v11 02/27] migration: push Error **errp into vmstate_load_state()

[Fabiano Rosas <farosas@suse.de>]

Arun Menon <armenon@redhat.com> writes:

> Hi Fabiano,
>
> Thanks for the review.
>
> On Fri, Aug 15, 2025 at 12:41:50PM -0300, Fabiano Rosas wrote:
>> Arun Menon <armenon@redhat.com> writes:
>> 
>> > This is an incremental step in converting vmstate loading
>> > code to report error via Error objects instead of directly
>> > printing it to console/monitor.
>> > It is ensured that vmstate_load_state() must report an error
>> > in errp, in case of failure.
>> >
>> > Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
>> > Signed-off-by: Arun Menon <armenon@redhat.com>
>> > ---
>> >  hw/display/virtio-gpu.c     |  2 +-
>> >  hw/pci/pci.c                |  3 ++-
>> >  hw/s390x/virtio-ccw.c       |  2 +-
>> >  hw/scsi/spapr_vscsi.c       |  2 +-
>> >  hw/vfio/pci.c               |  3 ++-
>> >  hw/virtio/virtio-mmio.c     |  3 ++-
>> >  hw/virtio/virtio-pci.c      |  2 +-
>> >  hw/virtio/virtio.c          |  4 +--
>> >  include/migration/vmstate.h |  2 +-
>> >  migration/cpr.c             |  5 ++--
>> >  migration/savevm.c          |  6 +++--
>> >  migration/vmstate-types.c   | 22 ++++++++++++----
>> >  migration/vmstate.c         | 61 ++++++++++++++++++++++++++++++-------------
>> >  tests/unit/test-vmstate.c   | 63 ++++++++++++++++++++++++++++++++++++++-------
>> >  ui/vdagent.c                |  3 ++-
>> >  15 files changed, 136 insertions(+), 47 deletions(-)
>> >
>> > diff --git a/hw/display/virtio-gpu.c b/hw/display/virtio-gpu.c
>> > index 0a1a625b0ea6cf26cb0d799171a57ed3d3ab2442..5dc31bc6bfb0272e29a4364ab10de2595a4bedf7 100644
>> > --- a/hw/display/virtio-gpu.c
>> > +++ b/hw/display/virtio-gpu.c
>> > @@ -1343,7 +1343,7 @@ static int virtio_gpu_load(QEMUFile *f, void *opaque, size_t size,
>> >      }
>> >  
>> >      /* load & apply scanout state */
>> > -    vmstate_load_state(f, &vmstate_virtio_gpu_scanouts, g, 1);
>> > +    vmstate_load_state(f, &vmstate_virtio_gpu_scanouts, g, 1, &error_fatal);
>> >  
>> >      return 0;
>> >  }
>> > diff --git a/hw/pci/pci.c b/hw/pci/pci.c
>> > index c70b5ceebaf1f2b10768bd030526cbb518da2b8d..6be932d3bb67ff0c4808707db2a7b6378a90e82b 100644
>> > --- a/hw/pci/pci.c
>> > +++ b/hw/pci/pci.c
>> > @@ -934,7 +934,8 @@ void pci_device_save(PCIDevice *s, QEMUFile *f)
>> >  int pci_device_load(PCIDevice *s, QEMUFile *f)
>> >  {
>> >      int ret;
>> > -    ret = vmstate_load_state(f, &vmstate_pci_device, s, s->version_id);
>> > +    ret = vmstate_load_state(f, &vmstate_pci_device, s, s->version_id,
>> > +                             &error_fatal);
>> >      /* Restore the interrupt status bit. */
>> >      pci_update_irq_status(s);
>> >      return ret;
>> > diff --git a/hw/s390x/virtio-ccw.c b/hw/s390x/virtio-ccw.c
>> > index d2f85b39f30f7fc82e0c600144c0a958e1269b2c..6a9641a03d5d3a38a4de7ceb9deffc0cc303bcff 100644
>> > --- a/hw/s390x/virtio-ccw.c
>> > +++ b/hw/s390x/virtio-ccw.c
>> > @@ -1136,7 +1136,7 @@ static void virtio_ccw_save_config(DeviceState *d, QEMUFile *f)
>> >  static int virtio_ccw_load_config(DeviceState *d, QEMUFile *f)
>> >  {
>> >      VirtioCcwDevice *dev = VIRTIO_CCW_DEVICE(d);
>> > -    return vmstate_load_state(f, &vmstate_virtio_ccw_dev, dev, 1);
>> > +    return vmstate_load_state(f, &vmstate_virtio_ccw_dev, dev, 1, &error_fatal);
>> >  }
>> >  
>> >  static void virtio_ccw_pre_plugged(DeviceState *d, Error **errp)
>> > diff --git a/hw/scsi/spapr_vscsi.c b/hw/scsi/spapr_vscsi.c
>> > index 20f70fb2729de78b9636a6b8c869695dab4f8902..8c896022d324f51962605288d6d6df1648c83cde 100644
>> > --- a/hw/scsi/spapr_vscsi.c
>> > +++ b/hw/scsi/spapr_vscsi.c
>> > @@ -648,7 +648,7 @@ static void *vscsi_load_request(QEMUFile *f, SCSIRequest *sreq)
>> >      assert(!req->active);
>> >  
>> >      memset(req, 0, sizeof(*req));
>> > -    rc = vmstate_load_state(f, &vmstate_spapr_vscsi_req, req, 1);
>> > +    rc = vmstate_load_state(f, &vmstate_spapr_vscsi_req, req, 1, &error_fatal);
>> >      if (rc) {
>> >          fprintf(stderr, "VSCSI: failed loading request tag#%u\n", sreq->tag);
>> >          return NULL;
>> > diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
>> > index 4fa692c1a32bcfa4e4939e5fcb64f2bf19905b3b..0be54762cdcbdb4780b8228b0bdf7fc6bd74dd57 100644
>> > --- a/hw/vfio/pci.c
>> > +++ b/hw/vfio/pci.c
>> > @@ -2795,7 +2795,8 @@ static int vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f)
>> >          old_addr[bar] = pdev->io_regions[bar].addr;
>> >      }
>> >  
>> > -    ret = vmstate_load_state(f, &vmstate_vfio_pci_config, vdev, 1);
>> > +    ret = vmstate_load_state(f, &vmstate_vfio_pci_config, vdev, 1,
>> > +                             &error_fatal);
>> >      if (ret) {
>> >          return ret;
>> >      }
>> > diff --git a/hw/virtio/virtio-mmio.c b/hw/virtio/virtio-mmio.c
>> > index 532c67107ba1d2978a76cf49f9cdc1de1dea3e11..0a688909fc606a3c9fde933667ae8c309ab527d0 100644
>> > --- a/hw/virtio/virtio-mmio.c
>> > +++ b/hw/virtio/virtio-mmio.c
>> > @@ -34,6 +34,7 @@
>> >  #include "qemu/error-report.h"
>> >  #include "qemu/log.h"
>> >  #include "trace.h"
>> > +#include "qapi/error.h"
>> >  
>> >  static bool virtio_mmio_ioeventfd_enabled(DeviceState *d)
>> >  {
>> > @@ -619,7 +620,7 @@ static int virtio_mmio_load_extra_state(DeviceState *opaque, QEMUFile *f)
>> >  {
>> >      VirtIOMMIOProxy *proxy = VIRTIO_MMIO(opaque);
>> >  
>> > -    return vmstate_load_state(f, &vmstate_virtio_mmio, proxy, 1);
>> > +    return vmstate_load_state(f, &vmstate_virtio_mmio, proxy, 1, &error_fatal);
>> >  }
>> >  
>> >  static bool virtio_mmio_has_extra_state(DeviceState *opaque)
>> > diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
>> > index 767216d795998708f5716a23ae16c79cd90ff489..b04faa1e5c91b5cef40e54ec41d92422d16bfc13 100644
>> > --- a/hw/virtio/virtio-pci.c
>> > +++ b/hw/virtio/virtio-pci.c
>> > @@ -161,7 +161,7 @@ static int virtio_pci_load_extra_state(DeviceState *d, QEMUFile *f)
>> >  {
>> >      VirtIOPCIProxy *proxy = to_virtio_pci_proxy(d);
>> >  
>> > -    return vmstate_load_state(f, &vmstate_virtio_pci, proxy, 1);
>> > +    return vmstate_load_state(f, &vmstate_virtio_pci, proxy, 1, &error_fatal);
>> >  }
>> >  
>> >  static void virtio_pci_save_queue(DeviceState *d, int n, QEMUFile *f)
>> > diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c
>> > index 9a81ad912e013fc254899c4e55cff1f76a6112a4..6bcafb338d1b5becadcacf092ba33a6ae4c3d194 100644
>> > --- a/hw/virtio/virtio.c
>> > +++ b/hw/virtio/virtio.c
>> > @@ -3327,14 +3327,14 @@ virtio_load(VirtIODevice *vdev, QEMUFile *f, int version_id)
>> >      }
>> >  
>> >      if (vdc->vmsd) {
>> > -        ret = vmstate_load_state(f, vdc->vmsd, vdev, version_id);
>> > +        ret = vmstate_load_state(f, vdc->vmsd, vdev, version_id, &error_fatal);
>> >          if (ret) {
>> >              return ret;
>> >          }
>> >      }
>> >  
>> >      /* Subsections */
>> > -    ret = vmstate_load_state(f, &vmstate_virtio, vdev, 1);
>> > +    ret = vmstate_load_state(f, &vmstate_virtio, vdev, 1, &error_fatal);
>> >      if (ret) {
>> >          return ret;
>> >      }
>> > diff --git a/include/migration/vmstate.h b/include/migration/vmstate.h
>> > index 1ff7bd9ac425ba67cd5ca7ad97bcf570f9e19abe..056781b1c21e737583f081594d9f88b32adfd674 100644
>> > --- a/include/migration/vmstate.h
>> > +++ b/include/migration/vmstate.h
>> > @@ -1196,7 +1196,7 @@ extern const VMStateInfo vmstate_info_qlist;
>> >      }
>> >  
>> >  int vmstate_load_state(QEMUFile *f, const VMStateDescription *vmsd,
>> > -                       void *opaque, int version_id);
>> > +                       void *opaque, int version_id, Error **errp);
>> >  int vmstate_save_state(QEMUFile *f, const VMStateDescription *vmsd,
>> >                         void *opaque, JSONWriter *vmdesc);
>> >  int vmstate_save_state_with_err(QEMUFile *f, const VMStateDescription *vmsd,
>> > diff --git a/migration/cpr.c b/migration/cpr.c
>> > index 42ad0b0d500e5de57faf0c6517e216b2d1c0cacf..bdb24736f44e91ba59b6e622a315597c97e7f64d 100644
>> > --- a/migration/cpr.c
>> > +++ b/migration/cpr.c
>> > @@ -202,6 +202,7 @@ int cpr_state_save(MigrationChannel *channel, Error **errp)
>> >  
>> >  int cpr_state_load(MigrationChannel *channel, Error **errp)
>> >  {
>> > +    ERRP_GUARD();
>> >      int ret;
>> >      uint32_t v;
>> >      QEMUFile *f;
>> > @@ -233,9 +234,9 @@ int cpr_state_load(MigrationChannel *channel, Error **errp)
>> >          return -ENOTSUP;
>> >      }
>> >  
>> > -    ret = vmstate_load_state(f, &vmstate_cpr_state, &cpr_state, 1);
>> > +    ret = vmstate_load_state(f, &vmstate_cpr_state, &cpr_state, 1, errp);
>> >      if (ret) {
>> > -        error_setg(errp, "vmstate_load_state error %d", ret);
>> > +        error_prepend(errp, "vmstate_load_state error %d: ", ret);
>> >          qemu_fclose(f);
>> >          return ret;
>> >      }
>> > diff --git a/migration/savevm.c b/migration/savevm.c
>> > index fabbeb296ae987d0c06ba6dafda63720205fecfd..cb64f2855d46aaa7c617b3e4079a2c9e566079b2 100644
>> > --- a/migration/savevm.c
>> > +++ b/migration/savevm.c
>> > @@ -969,7 +969,8 @@ static int vmstate_load(QEMUFile *f, SaveStateEntry *se)
>> >      if (!se->vmsd) {         /* Old style */
>> >          return se->ops->load_state(f, se->opaque, se->load_version_id);
>> >      }
>> > -    return vmstate_load_state(f, se->vmsd, se->opaque, se->load_version_id);
>> > +    return vmstate_load_state(f, se->vmsd, se->opaque, se->load_version_id,
>> > +                              &error_fatal);
>> >  }
>> >  
>> >  static void vmstate_save_old_style(QEMUFile *f, SaveStateEntry *se,
>> > @@ -2839,7 +2840,8 @@ static int qemu_loadvm_state_header(QEMUFile *f)
>> >              error_report("Configuration section missing");
>> >              return -EINVAL;
>> >          }
>> > -        ret = vmstate_load_state(f, &vmstate_configuration, &savevm_state, 0);
>> > +        ret = vmstate_load_state(f, &vmstate_configuration, &savevm_state, 0,
>> > +                                 &error_fatal);
>> >  
>> >          if (ret) {
>> >              return ret;
>> > diff --git a/migration/vmstate-types.c b/migration/vmstate-types.c
>> > index 741a588b7e18c6d37724b08a0101edc8bc74a0a5..f41670cc853c5b41ccc8def354886a8e5c1451fd 100644
>> > --- a/migration/vmstate-types.c
>> > +++ b/migration/vmstate-types.c
>> > @@ -19,6 +19,7 @@
>> >  #include "qemu/error-report.h"
>> >  #include "qemu/queue.h"
>> >  #include "trace.h"
>> > +#include "qapi/error.h"
>> >  
>> >  /* bool */
>> >  
>> > @@ -543,13 +544,17 @@ static int get_tmp(QEMUFile *f, void *pv, size_t size,
>> >                     const VMStateField *field)
>> >  {
>> >      int ret;
>> > +    Error *local_err = NULL;
>> >      const VMStateDescription *vmsd = field->vmsd;
>> >      int version_id = field->version_id;
>> >      void *tmp = g_malloc(size);
>> >  
>> >      /* Writes the parent field which is at the start of the tmp */
>> >      *(void **)tmp = pv;
>> > -    ret = vmstate_load_state(f, vmsd, tmp, version_id);
>> > +    ret = vmstate_load_state(f, vmsd, tmp, version_id, &local_err);
>> > +    if (ret < 0) {
>> > +        warn_report_err(local_err);
>> > +    }
>> >      g_free(tmp);
>> >      return ret;
>> >  }
>> > @@ -626,6 +631,7 @@ static int get_qtailq(QEMUFile *f, void *pv, size_t unused_size,
>> >                        const VMStateField *field)
>> >  {
>> >      int ret = 0;
>> > +    Error *local_err = NULL;
>> >      const VMStateDescription *vmsd = field->vmsd;
>> >      /* size of a QTAILQ element */
>> >      size_t size = field->size;
>> > @@ -649,8 +655,9 @@ static int get_qtailq(QEMUFile *f, void *pv, size_t unused_size,
>> >  
>> >      while (qemu_get_byte(f)) {
>> >          elm = g_malloc(size);
>> > -        ret = vmstate_load_state(f, vmsd, elm, version_id);
>> > +        ret = vmstate_load_state(f, vmsd, elm, version_id, &local_err);
>> >          if (ret) {
>> > +            warn_report_err(local_err);
>> >              return ret;
>> >          }
>> >          QTAILQ_RAW_INSERT_TAIL(pv, elm, entry_offset);
>> > @@ -772,6 +779,7 @@ static int get_gtree(QEMUFile *f, void *pv, size_t unused_size,
>> >      GTree *tree = *pval;
>> >      void *key, *val;
>> >      int ret = 0;
>> > +    Error *local_err = NULL;
>> >  
>> >      /* in case of direct key, the key vmsd can be {}, ie. check fields */
>> >      if (!direct_key && version_id > key_vmsd->version_id) {
>> > @@ -803,18 +811,20 @@ static int get_gtree(QEMUFile *f, void *pv, size_t unused_size,
>> >              key = (void *)(uintptr_t)qemu_get_be64(f);
>> >          } else {
>> >              key = g_malloc0(key_size);
>> > -            ret = vmstate_load_state(f, key_vmsd, key, version_id);
>> > +            ret = vmstate_load_state(f, key_vmsd, key, version_id, &local_err);
>> >              if (ret) {
>> >                  error_report("%s : failed to load %s (%d)",
>> >                               field->name, key_vmsd->name, ret);
>> > +                warn_report_err(local_err);
>> >                  goto key_error;
>> >              }
>> >          }
>> >          val = g_malloc0(val_size);
>> > -        ret = vmstate_load_state(f, val_vmsd, val, version_id);
>> > +        ret = vmstate_load_state(f, val_vmsd, val, version_id, &local_err);
>> >          if (ret) {
>> >              error_report("%s : failed to load %s (%d)",
>> >                           field->name, val_vmsd->name, ret);
>> > +            warn_report_err(local_err);
>> >              goto val_error;
>> >          }
>> >          g_tree_insert(tree, key, val);
>> > @@ -872,6 +882,7 @@ static int get_qlist(QEMUFile *f, void *pv, size_t unused_size,
>> >                       const VMStateField *field)
>> >  {
>> >      int ret = 0;
>> > +    Error *local_err = NULL;
>> >      const VMStateDescription *vmsd = field->vmsd;
>> >      /* size of a QLIST element */
>> >      size_t size = field->size;
>> > @@ -892,10 +903,11 @@ static int get_qlist(QEMUFile *f, void *pv, size_t unused_size,
>> >  
>> >      while (qemu_get_byte(f)) {
>> >          elm = g_malloc(size);
>> > -        ret = vmstate_load_state(f, vmsd, elm, version_id);
>> > +        ret = vmstate_load_state(f, vmsd, elm, version_id, &local_err);
>> >          if (ret) {
>> >              error_report("%s: failed to load %s (%d)", field->name,
>> >                           vmsd->name, ret);
>> > +            warn_report_err(local_err);
>> >              g_free(elm);
>> >              return ret;
>> >          }
>> > diff --git a/migration/vmstate.c b/migration/vmstate.c
>> > index 6108c7fe283a5013ce42ea9987723c489aef26a2..1cd609a1d598995af1e51d1f4d58d68133f1426d 100644
>> > --- a/migration/vmstate.c
>> > +++ b/migration/vmstate.c
>> > @@ -132,29 +132,34 @@ static void vmstate_handle_alloc(void *ptr, const VMStateField *field,
>> >  }
>> >  
>> >  int vmstate_load_state(QEMUFile *f, const VMStateDescription *vmsd,
>> > -                       void *opaque, int version_id)
>> > +                       void *opaque, int version_id, Error **errp)
>> >  {
>> > +    ERRP_GUARD();
>> >      const VMStateField *field = vmsd->fields;
>> >      int ret = 0;
>> >  
>> >      trace_vmstate_load_state(vmsd->name, version_id);
>> >      if (version_id > vmsd->version_id) {
>> > -        error_report("%s: incoming version_id %d is too new "
>> > -                     "for local version_id %d",
>> > -                     vmsd->name, version_id, vmsd->version_id);
>> > +        error_setg(errp, "%s: incoming version_id %d is too new "
>> > +                   "for local version_id %d",
>> > +                   vmsd->name, version_id, vmsd->version_id);
>> >          trace_vmstate_load_state_end(vmsd->name, "too new", -EINVAL);
>> >          return -EINVAL;
>> >      }
>> >      if  (version_id < vmsd->minimum_version_id) {
>> > -        error_report("%s: incoming version_id %d is too old "
>> > -                     "for local minimum version_id  %d",
>> > -                     vmsd->name, version_id, vmsd->minimum_version_id);
>> > +        error_setg(errp, "%s: incoming version_id %d is too old "
>> > +                   "for local minimum version_id %d",
>> > +                   vmsd->name, version_id, vmsd->minimum_version_id);
>> >          trace_vmstate_load_state_end(vmsd->name, "too old", -EINVAL);
>> >          return -EINVAL;
>> >      }
>> >      if (vmsd->pre_load) {
>> >          ret = vmsd->pre_load(opaque);
>> >          if (ret) {
>> > +            error_setg(errp, "VM pre load failed for: '%s', "
>> 
>> "VM" pre load is a little ambiguous. Simply "pre load" or "pre load
>> hook" is better.
> Sure, will do this.
>> 
>> > +                       "version_id: %d, minimum version_id: %d, ret: %d",
>> > +                       vmsd->name, vmsd->version_id, vmsd->minimum_version_id,
>> > +                       ret);
>> >              return ret;
>> >          }
>> >      }
>> > @@ -192,13 +197,20 @@ int vmstate_load_state(QEMUFile *f, const VMStateDescription *vmsd,
>> >  
>> >                  if (inner_field->flags & VMS_STRUCT) {
>> >                      ret = vmstate_load_state(f, inner_field->vmsd, curr_elem,
>> > -                                             inner_field->vmsd->version_id);
>> > +                                             inner_field->vmsd->version_id,
>> > +                                             errp);
>> >                  } else if (inner_field->flags & VMS_VSTRUCT) {
>> >                      ret = vmstate_load_state(f, inner_field->vmsd, curr_elem,
>> > -                                             inner_field->struct_version_id);
>> > +                                             inner_field->struct_version_id,
>> > +                                             errp);
>> >                  } else {
>> >                      ret = inner_field->info->get(f, curr_elem, size,
>> >                                                   inner_field);
>> > +                    if (ret < 0) {
>> > +                        error_setg(errp,
>> > +                                   "Failed to get info for %s: %d",
>> > +                                   inner_field->name, ret);
>> 
>> "get info" is not correct. This is the type-specific getter
>> invocation. Because the migration (for the most part) is a stream, each
>> type provides it's own getter which knows about the size of the field
>> and any particularities such as magic values. So:
>> 
>> error_setg(errp, "Failed to load element of type %s for %s: %d",
>>            info->name, inner_field->name, ret);
> yes, will change the message. Thanks.
>> 
>> > +                    }
>> >                  }
>> >  
>> >                  /* If we used a fake temp field.. free it now */
>> > @@ -208,30 +220,42 @@ int vmstate_load_state(QEMUFile *f, const VMStateDescription *vmsd,
>> >  
>> >                  if (ret >= 0) {
>> >                      ret = qemu_file_get_error(f);
>> > +                    if (ret < 0) {
>> > +                        error_setg(errp, "Failed to load %s state: %d",
>> > +                                   vmsd->name, ret);
>> 
>> We could go a little more specific here, it's useful to know whether the
>> error was on the transport side, rather than something logical with the
>> migrated data. I don't really care about the actual string, but one
>> suggestion is "stream error":
>> 
>> error_setg(errp, "Failed to load %s state: stream error: %d",
>>            vmsd->name, ret);
> yes, will add stream error. Thanks.
>> 
>> > +                    }
>> >                  }
>> >                  if (ret < 0) {
>> >                      qemu_file_set_error(f, ret);
>> > -                    error_report("Failed to load %s:%s", vmsd->name,
>> > -                                 field->name);
>> > +                    error_prepend(errp,
>> > +                                  "Failed to load %s:%s version_id: %d: ",
>> 
>> Usage of : is inconsistent with below /
> Since we used error_prepend here, we need an extra space after the colon ':'
> That way the next error string looks readable.

Right, that's not what I'm talking about. What's inconsistent is: %s:%s
vs. %s/%s

>> 
>> > +                                   vmsd->name, field->name, vmsd->version_id);
>> >                      trace_vmstate_load_field_error(field->name, ret);
>> >                      return ret;
>> >                  }
>> >              }
>> >          } else if (field->flags & VMS_MUST_EXIST) {
>> > -            error_report("Input validation failed: %s/%s",
>> > -                         vmsd->name, field->name);
>> > +            error_setg(errp, "Input validation failed: %s/%s version_id: %d",

here^