Re: [PATCH v9 QEMU 11/15] vfio: Add save state functions to SaveVMHandlers

From: Alex Williamson <alex.williamson@redhat.com>
To: Kirti Wankhede <kwankhede@nvidia.com>
Cc: Zhengxiao.zx@Alibaba-inc.com, kevin.tian@intel.com,
	yi.l.liu@intel.com, cjia@nvidia.com, eskultet@redhat.com,
	ziye.yang@intel.com, qemu-devel@nongnu.org, cohuck@redhat.com,
	shuangtai.tst@alibaba-inc.com, dgilbert@redhat.com,
	zhi.a.wang@intel.com, mlevitsk@redhat.com, pasic@linux.ibm.com,
	aik@ozlabs.ru, eauger@redhat.com, felipe@nutanix.com,
	jonathan.davies@nutanix.com, yan.y.zhao@intel.com,
	changpeng.liu@intel.com, Ken.Xue@amd.com
Subject: Re: [PATCH v9 QEMU 11/15] vfio: Add save state functions to SaveVMHandlers
Date: Wed, 13 Nov 2019 22:04:18 -0700	[thread overview]
Message-ID: <20191113220418.081244d6@x1.home> (raw)
In-Reply-To: <1573578324-8389-12-git-send-email-kwankhede@nvidia.com>

On Tue, 12 Nov 2019 22:35:20 +0530
Kirti Wankhede <kwankhede@nvidia.com> wrote:

> Added .save_live_pending, .save_live_iterate and .save_live_complete_precopy
> functions. These functions handles pre-copy and stop-and-copy phase.
> 
> In _SAVING|_RUNNING device state or pre-copy phase:
> - read pending_bytes. If pending_bytes > 0, go through below steps.
> - read data_offset - indicates kernel driver to write data to staging
>   buffer.
> - read data_size - amount of data in bytes written by vendor driver in
>   migration region.
> - read data_size bytes of data from data_offset in the migration region.
> - Write data packet to file stream as below:
> {VFIO_MIG_FLAG_DEV_DATA_STATE, data_size, actual data,
> VFIO_MIG_FLAG_END_OF_STATE }
> 
> In _SAVING device state or stop-and-copy phase
> a. read config space of device and save to migration file stream. This
>    doesn't need to be from vendor driver. Any other special config state
>    from driver can be saved as data in following iteration.
> b. read pending_bytes. If pending_bytes > 0, go through below steps.
> c. read data_offset - indicates kernel driver to write data to staging
>    buffer.
> d. read data_size - amount of data in bytes written by vendor driver in
>    migration region.
> e. read data_size bytes of data from data_offset in the migration region.
> f. Write data packet as below:
>    {VFIO_MIG_FLAG_DEV_DATA_STATE, data_size, actual data}
> g. iterate through steps b to f while (pending_bytes > 0)
> h. Write {VFIO_MIG_FLAG_END_OF_STATE}
> 
> When data region is mapped, its user's responsibility to read data from

s/mapped/made available/

"mapped" is confusing given the mmap'd features.

> data_offset of data_size before moving to next steps.
>
> Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
> Reviewed-by: Neo Jia <cjia@nvidia.com>
> ---
>  hw/vfio/migration.c  | 245 ++++++++++++++++++++++++++++++++++++++++++++++++++-
>  hw/vfio/trace-events |   6 ++
>  2 files changed, 250 insertions(+), 1 deletion(-)
> 
> diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
> index 48aac6d29876..f890e864e174 100644
> --- a/hw/vfio/migration.c
> +++ b/hw/vfio/migration.c
> @@ -120,6 +120,137 @@ static int vfio_migration_set_state(VFIODevice *vbasedev, uint32_t set_flags,
>      return 0;
>  }
>  
> +static void *find_data_region(VFIORegion *region,
> +                              uint64_t data_offset,
> +                              uint64_t data_size)
> +{
> +    void *ptr = NULL;
> +    int i;
> +
> +    for (i = 0; i < region->nr_mmaps; i++) {
> +        if ((data_offset >= region->mmaps[i].offset) &&
> +            (data_offset < region->mmaps[i].offset + region->mmaps[i].size) &&
> +            (data_size <= region->mmaps[i].size)) {

data_offset is determined to live somewhere within the mmap and
data_size is independently determined to be smaller than the entire
mmaps size.  This is broken.

> +            ptr = region->mmaps[i].mmap + (data_offset -
> +                                           region->mmaps[i].offset);

If the data offset is mmap'd, this gives us a pointer to the start, but
we have no idea if the entire range is accessible via this pointer, nor
does the API require it to be.

> +            break;
> +        }
> +    }
> +    return ptr;
> +}
> +
> +static int vfio_save_buffer(QEMUFile *f, VFIODevice *vbasedev)
> +{
> +    VFIOMigration *migration = vbasedev->migration;
> +    VFIORegion *region = &migration->region;
> +    uint64_t data_offset = 0, data_size = 0;
> +    int ret;
> +
> +    ret = pread(vbasedev->fd, &data_offset, sizeof(data_offset),
> +                region->fd_offset + offsetof(struct vfio_device_migration_info,
> +                                             data_offset));
> +    if (ret != sizeof(data_offset)) {
> +        error_report("%s: Failed to get migration buffer data offset %d",
> +                     vbasedev->name, ret);
> +        return -EINVAL;
> +    }
> +
> +    ret = pread(vbasedev->fd, &data_size, sizeof(data_size),
> +                region->fd_offset + offsetof(struct vfio_device_migration_info,
> +                                             data_size));
> +    if (ret != sizeof(data_size)) {
> +        error_report("%s: Failed to get migration buffer data size %d",
> +                     vbasedev->name, ret);
> +        return -EINVAL;
> +    }
> +
> +    if (data_size > 0) {
> +        void *buf = NULL;
> +        bool buffer_mmaped;
> +
> +        if (region->mmaps) {
> +            buf = find_data_region(region, data_offset, data_size);
> +        }
> +
> +        buffer_mmaped = (buf != NULL) ? true : false;
> +
> +        if (!buffer_mmaped) {
> +            buf = g_try_malloc0(data_size);
> +            if (!buf) {
> +                error_report("%s: Error allocating buffer ", __func__);
> +                return -ENOMEM;
> +            }
> +
> +            ret = pread(vbasedev->fd, buf, data_size,
> +                        region->fd_offset + data_offset);
> +            if (ret != data_size) {
> +                error_report("%s: Failed to get migration data %d",
> +                             vbasedev->name, ret);
> +                g_free(buf);
> +                return -EINVAL;
> +            }

Seems like this needs to be bound and chunked to some "reasonable"
size, the vendor driver could be exposing gigabytes of data at a time.
Do we have a quota for this phase?

> +        }
> +
> +        qemu_put_be64(f, data_size);
> +        qemu_put_buffer(f, buf, data_size);
> +
> +        if (!buffer_mmaped) {
> +            g_free(buf);
> +        }
> +    } else {
> +        qemu_put_be64(f, data_size);

Why would we stuff zero or <0 into the data stream here?

> +    }

There's clearly an assumption here that a chunk of data from the device
is entirely mmap'd or not.  That's not a requirement of the API and I
believe we've discussed cases where a vendor driver could have
partially mapped and partially emulated data chunks.

> +
> +    trace_vfio_save_buffer(vbasedev->name, data_offset, data_size,
> +                           migration->pending_bytes);
> +
> +    ret = qemu_file_get_error(f);
> +    if (ret) {
> +        return ret;
> +    }
> +
> +    return data_size;

AIUI, it's required to read pending_bytes to indicate the data has been
consumed, I don't see that done here.

> +}
> +
> +static int vfio_update_pending(VFIODevice *vbasedev)
> +{
> +    VFIOMigration *migration = vbasedev->migration;
> +    VFIORegion *region = &migration->region;
> +    uint64_t pending_bytes = 0;
> +    int ret;
> +
> +    ret = pread(vbasedev->fd, &pending_bytes, sizeof(pending_bytes),
> +                region->fd_offset + offsetof(struct vfio_device_migration_info,
> +                                             pending_bytes));
> +    if ((ret < 0) || (ret != sizeof(pending_bytes))) {

Two tests for the same thing.

> +        error_report("%s: Failed to get pending bytes %d",
> +                     vbasedev->name, ret);
> +        migration->pending_bytes = 0;
> +        return (ret < 0) ? ret : -EINVAL;

pread returns -1 on error and sets errno, the ret value isn't very
interesting.

> +    }
> +
> +    migration->pending_bytes = pending_bytes;
> +    trace_vfio_update_pending(vbasedev->name, pending_bytes);
> +    return 0;
> +}
> +
> +static int vfio_save_device_config_state(QEMUFile *f, void *opaque)
> +{
> +    VFIODevice *vbasedev = opaque;
> +
> +    qemu_put_be64(f, VFIO_MIG_FLAG_DEV_CONFIG_STATE);
> +
> +    if (vbasedev->ops && vbasedev->ops->vfio_save_config) {

A vbasedev w/o ops doesn't seem possible.

> +        vbasedev->ops->vfio_save_config(vbasedev, f);
> +    }
> +
> +    qemu_put_be64(f, VFIO_MIG_FLAG_END_OF_STATE);

Is it worthwhile to include these markers w/o vfio_save_config?
Couldn't we simply move them into the conditional section?

> +
> +    trace_vfio_save_device_config_state(vbasedev->name);
> +
> +    return qemu_file_get_error(f);
> +}
> +
>  /* ---------------------------------------------------------------------- */
>  
>  static int vfio_save_setup(QEMUFile *f, void *opaque)
> @@ -136,7 +267,7 @@ static int vfio_save_setup(QEMUFile *f, void *opaque)
>          qemu_mutex_unlock_iothread();
>          if (ret) {
>              error_report("%s: Failed to mmap VFIO migration region %d: %s",
> -                         vbasedev->name, migration->region.index,
> +                         vbasedev->name, migration->region.nr,

Fix this in patch that introduced it, looks like this wouldn't even
compile previously.

>                           strerror(-ret));
>              return ret;
>          }
> @@ -170,9 +301,121 @@ static void vfio_save_cleanup(void *opaque)
>      trace_vfio_save_cleanup(vbasedev->name);
>  }
>  
> +static void vfio_save_pending(QEMUFile *f, void *opaque,
> +                              uint64_t threshold_size,
> +                              uint64_t *res_precopy_only,
> +                              uint64_t *res_compatible,
> +                              uint64_t *res_postcopy_only)
> +{
> +    VFIODevice *vbasedev = opaque;
> +    VFIOMigration *migration = vbasedev->migration;
> +    int ret;
> +
> +    ret = vfio_update_pending(vbasedev);
> +    if (ret) {
> +        return;
> +    }
> +
> +    *res_precopy_only += migration->pending_bytes;
> +
> +    trace_vfio_save_pending(vbasedev->name, *res_precopy_only,
> +                            *res_postcopy_only, *res_compatible);
> +}
> +
> +static int vfio_save_iterate(QEMUFile *f, void *opaque)
> +{
> +    VFIODevice *vbasedev = opaque;
> +    int ret, data_size;
> +
> +    qemu_put_be64(f, VFIO_MIG_FLAG_DEV_DATA_STATE);
> +
> +    data_size = vfio_save_buffer(f, vbasedev);
> +
> +    if (data_size < 0) {
> +        error_report("%s: vfio_save_buffer failed %s", vbasedev->name,
> +                     strerror(errno));
> +        return data_size;
> +    }
> +
> +    qemu_put_be64(f, VFIO_MIG_FLAG_END_OF_STATE);
> +
> +    ret = qemu_file_get_error(f);
> +    if (ret) {
> +        return ret;
> +    }
> +
> +    trace_vfio_save_iterate(vbasedev->name, data_size);
> +    if (data_size == 0) {
> +        /* indicates data finished, goto complete phase */
> +        return 1;
> +    }

I don't think this matches our spec, pending_bytes seems to indicate
we've finished, data_size of zero does not have a defined meaning.

> +
> +    return 0;
> +}
> +
> +static int vfio_save_complete_precopy(QEMUFile *f, void *opaque)
> +{
> +    VFIODevice *vbasedev = opaque;
> +    VFIOMigration *migration = vbasedev->migration;
> +    int ret;
> +
> +    ret = vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_SAVING,
> +                                   VFIO_DEVICE_STATE_RUNNING);
> +    if (ret) {
> +        error_report("%s: Failed to set state STOP and SAVING",
> +                     vbasedev->name);
> +        return ret;
> +    }
> +
> +    ret = vfio_save_device_config_state(f, opaque);
> +    if (ret) {
> +        return ret;
> +    }
> +
> +    ret = vfio_update_pending(vbasedev);
> +    if (ret) {
> +        return ret;
> +    }
> +
> +    while (migration->pending_bytes > 0) {
> +        qemu_put_be64(f, VFIO_MIG_FLAG_DEV_DATA_STATE);
> +        ret = vfio_save_buffer(f, vbasedev);
> +        if (ret < 0) {
> +            error_report("%s: Failed to save buffer", vbasedev->name);
> +            return ret;
> +        } else if (ret == 0) {
> +            break;
> +        }
> +
> +        ret = vfio_update_pending(vbasedev);
> +        if (ret) {
> +            return ret;
> +        }
> +    }

Here we use pending_bytes for the stop condition and update
pending_bytes per loop, which is different than the above save iterate
function.

> +
> +    qemu_put_be64(f, VFIO_MIG_FLAG_END_OF_STATE);
> +
> +    ret = qemu_file_get_error(f);
> +    if (ret) {
> +        return ret;
> +    }
> +
> +    ret = vfio_migration_set_state(vbasedev, 0, VFIO_DEVICE_STATE_SAVING);
> +    if (ret) {
> +        error_report("%s: Failed to set state STOPPED", vbasedev->name);
> +        return ret;
> +    }
> +
> +    trace_vfio_save_complete_precopy(vbasedev->name);
> +    return ret;
> +}
> +
>  static SaveVMHandlers savevm_vfio_handlers = {
>      .save_setup = vfio_save_setup,
>      .save_cleanup = vfio_save_cleanup,
> +    .save_live_pending = vfio_save_pending,
> +    .save_live_iterate = vfio_save_iterate,
> +    .save_live_complete_precopy = vfio_save_complete_precopy,
>  };
>  
>  /* ---------------------------------------------------------------------- */
> diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
> index 4bb43f18f315..bdf40ba368c7 100644
> --- a/hw/vfio/trace-events
> +++ b/hw/vfio/trace-events
> @@ -151,3 +151,9 @@ vfio_vmstate_change(char *name, int running, const char *reason, uint32_t dev_st
>  vfio_migration_state_notifier(char *name, int state) " (%s) state %d"
>  vfio_save_setup(char *name) " (%s)"
>  vfio_save_cleanup(char *name) " (%s)"
> +vfio_save_buffer(char *name, uint64_t data_offset, uint64_t data_size, uint64_t pending) " (%s) Offset 0x%"PRIx64" size 0x%"PRIx64" pending 0x%"PRIx64
> +vfio_update_pending(char *name, uint64_t pending) " (%s) pending 0x%"PRIx64
> +vfio_save_device_config_state(char *name) " (%s)"
> +vfio_save_pending(char *name, uint64_t precopy, uint64_t postcopy, uint64_t compatible) " (%s) precopy 0x%"PRIx64" postcopy 0x%"PRIx64" compatible 0x%"PRIx64
> +vfio_save_iterate(char *name, int data_size) " (%s) data_size %d"
> +vfio_save_complete_precopy(char *name) " (%s)"