Re: [PATCH v26 08/17] vfio: Add save state functions to SaveVMHandlers

[Kirti Wankhede <kwankhede@nvidia.com>]

On 9/26/2020 2:32 AM, Alex Williamson wrote:
> On Wed, 23 Sep 2020 04:54:10 +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
>> 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           | 273 ++++++++++++++++++++++++++++++++++++++++++
>>   hw/vfio/trace-events          |   6 +
>>   include/hw/vfio/vfio-common.h |   1 +
>>   3 files changed, 280 insertions(+)
>>
>> diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
>> index 8e8adaa25779..4611bb972228 100644
>> --- a/hw/vfio/migration.c
>> +++ b/hw/vfio/migration.c
>> @@ -180,6 +180,154 @@ static int vfio_migration_set_state(VFIODevice *vbasedev, uint32_t mask,
>>       return 0;
>>   }
>>   
>> +static void *get_data_section_size(VFIORegion *region, uint64_t data_offset,
>> +                                   uint64_t data_size, uint64_t *size)
>> +{
>> +    void *ptr = NULL;
>> +    uint64_t limit = 0;
>> +    int i;
>> +
>> +    if (!region->mmaps) {
>> +        if (size) {
>> +            *size = data_size;
>> +        }
>> +        return ptr;
>> +    }
>> +
>> +    for (i = 0; i < region->nr_mmaps; i++) {
>> +        VFIOMmap *map = region->mmaps + i;
>> +
>> +        if ((data_offset >= map->offset) &&
>> +            (data_offset < map->offset + map->size)) {
>> +
>> +            /* check if data_offset is within sparse mmap areas */
>> +            ptr = map->mmap + data_offset - map->offset;
>> +            if (size) {
>> +                *size = MIN(data_size, map->offset + map->size - data_offset);
>> +            }
>> +            break;
>> +        } else if ((data_offset < map->offset) &&
>> +                   (!limit || limit > map->offset)) {
>> +            /*
>> +             * data_offset is not within sparse mmap areas, find size of
>> +             * non-mapped area. Check through all list since region->mmaps list
>> +             * is not sorted.
>> +             */
>> +            limit = map->offset;
>> +        }
>> +    }
>> +
>> +    if (!ptr && size) {
>> +        *size = limit ? limit - data_offset : data_size;
> 
> 'limit - data_offset' doesn't take data_size into account, this should
> be MIN(data_size, limit - data_offset).
> 

Done.

>> +    }
>> +    return ptr;
>> +}
>> +
>> +static int vfio_save_buffer(QEMUFile *f, VFIODevice *vbasedev, uint64_t *size)
>> +{
>> +    VFIOMigration *migration = vbasedev->migration;
>> +    VFIORegion *region = &migration->region;
>> +    uint64_t data_offset = 0, data_size = 0, sz;
>> +    int ret;
>> +
>> +    ret = vfio_mig_read(vbasedev, &data_offset, sizeof(data_offset),
>> +                region->fd_offset + offsetof(struct vfio_device_migration_info,
>> +                                             data_offset));
>> +    if (ret < 0) {
>> +        return ret;
>> +    }
>> +
>> +    ret = vfio_mig_read(vbasedev, &data_size, sizeof(data_size),
>> +                region->fd_offset + offsetof(struct vfio_device_migration_info,
>> +                                             data_size));
>> +    if (ret < 0) {
>> +        return ret;
>> +    }
>> +
>> +    trace_vfio_save_buffer(vbasedev->name, data_offset, data_size,
>> +                           migration->pending_bytes);
>> +
>> +    qemu_put_be64(f, data_size);
>> +    sz = data_size;
>> +
>> +    while (sz) {
>> +        void *buf = NULL;
> 
> Unnecessary initialization.
> 
>> +        uint64_t sec_size;
>> +        bool buf_allocated = false;
>> +
>> +        buf = get_data_section_size(region, data_offset, sz, &sec_size);
>> +
>> +        if (!buf) {
>> +            buf = g_try_malloc(sec_size);
>> +            if (!buf) {
>> +                error_report("%s: Error allocating buffer ", __func__);
>> +                return -ENOMEM;
>> +            }
>> +            buf_allocated = true;
>> +
>> +            ret = vfio_mig_read(vbasedev, buf, sec_size,
>> +                                region->fd_offset + data_offset);
>> +            if (ret < 0) {
>> +                g_free(buf);
>> +                return ret;
>> +            }
>> +        }
>> +
>> +        qemu_put_buffer(f, buf, sec_size);
>> +
>> +        if (buf_allocated) {
>> +            g_free(buf);
>> +        }
>> +        sz -= sec_size;
>> +        data_offset += sec_size;
>> +    }
>> +
>> +    ret = qemu_file_get_error(f);
>> +
>> +    if (!ret && size) {
>> +        *size = data_size;
>> +    }
>> +
>> +    return ret;
>> +}
>> +
>> +static int vfio_update_pending(VFIODevice *vbasedev)
>> +{
>> +    VFIOMigration *migration = vbasedev->migration;
>> +    VFIORegion *region = &migration->region;
>> +    uint64_t pending_bytes = 0;
>> +    int ret;
>> +
>> +    ret = vfio_mig_read(vbasedev, &pending_bytes, sizeof(pending_bytes),
>> +                region->fd_offset + offsetof(struct vfio_device_migration_info,
>> +                                             pending_bytes));
>> +    if (ret < 0) {
>> +        migration->pending_bytes = 0;
>> +        return ret;
>> +    }
>> +
>> +    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) {
>> +        vbasedev->ops->vfio_save_config(vbasedev, f);
>> +    }
>> +
>> +    qemu_put_be64(f, VFIO_MIG_FLAG_END_OF_STATE);
>> +
>> +    trace_vfio_save_device_config_state(vbasedev->name);
>> +
>> +    return qemu_file_get_error(f);
>> +}
>> +
>>   /* ---------------------------------------------------------------------- */
>>   
>>   static int vfio_save_setup(QEMUFile *f, void *opaque)
>> @@ -232,9 +380,134 @@ 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;
>> +    VFIOMigration *migration = vbasedev->migration;
>> +    uint64_t data_size;
>> +    int ret;
>> +
>> +    qemu_put_be64(f, VFIO_MIG_FLAG_DEV_DATA_STATE);
>> +
>> +    if (migration->pending_bytes == 0) {
>> +        ret = vfio_update_pending(vbasedev);
>> +        if (ret) {
>> +            return ret;
>> +        }
>> +
>> +        if (migration->pending_bytes == 0) {
>> +            /* indicates data finished, goto complete phase */
>> +            return 1;
>> +        }
>> +    }
>> +
>> +    ret = vfio_save_buffer(f, vbasedev, &data_size);
>> +
>> +    if (ret) {
>> +        error_report("%s: vfio_save_buffer failed %s", vbasedev->name,
>> +                     strerror(errno));
>> +        return ret;
>> +    }
>> +
>> +    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);
>> +
>> +    return 0;
>> +}
>> +
>> +static int vfio_save_complete_precopy(QEMUFile *f, void *opaque)
>> +{
>> +    VFIODevice *vbasedev = opaque;
>> +    VFIOMigration *migration = vbasedev->migration;
>> +    uint64_t data_size;
>> +    int ret;
>> +
>> +    ret = vfio_migration_set_state(vbasedev, ~VFIO_DEVICE_STATE_RUNNING,
>> +                                   VFIO_DEVICE_STATE_SAVING);
>> +    if (ret) {
>> +        error_report("%s: Failed to set state STOP and SAVING",
>> +                     vbasedev->name);
>> +        return ret;
>> +    }
> 
> This also assumes success implies desired state.
> 
>> +
>> +    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, &data_size);
>> +        if (ret < 0) {
>> +            error_report("%s: Failed to save buffer", vbasedev->name);
>> +            return ret;
>> +        }
>> +
>> +        if (data_size == 0) {
>> +            break;
>> +        }
>> +
>> +        ret = vfio_update_pending(vbasedev);
>> +        if (ret) {
>> +            return ret;
>> +        }
>> +    }
>> +
>> +    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, ~VFIO_DEVICE_STATE_SAVING, 0);
>> +    if (ret) {
>> +        error_report("%s: Failed to set state STOPPED", vbasedev->name);
>> +        return ret;
>> +    }
> 
> And another.  Thanks,
>


Fixing in patch 5.

Thanks,
Kirti


> Alex
> 
>> +
>> +    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 982d8dccb219..118b5547c921 100644
>> --- a/hw/vfio/trace-events
>> +++ b/hw/vfio/trace-events
>> @@ -154,3 +154,9 @@ vfio_vmstate_change(const char *name, int running, const char *reason, uint32_t
>>   vfio_migration_state_notifier(const char *name, const char *state) " (%s) state %s"
>>   vfio_save_setup(const char *name) " (%s)"
>>   vfio_save_cleanup(const char *name) " (%s)"
>> +vfio_save_buffer(const 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(const char *name, uint64_t pending) " (%s) pending 0x%"PRIx64
>> +vfio_save_device_config_state(const char *name) " (%s)"
>> +vfio_save_pending(const char *name, uint64_t precopy, uint64_t postcopy, uint64_t compatible) " (%s) precopy 0x%"PRIx64" postcopy 0x%"PRIx64" compatible 0x%"PRIx64
>> +vfio_save_iterate(const char *name, int data_size) " (%s) data_size %d"
>> +vfio_save_complete_precopy(const char *name) " (%s)"
>> diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
>> index 49c7c7a0e29a..471e444a364c 100644
>> --- a/include/hw/vfio/vfio-common.h
>> +++ b/include/hw/vfio/vfio-common.h
>> @@ -60,6 +60,7 @@ typedef struct VFIORegion {
>>   
>>   typedef struct VFIOMigration {
>>       VFIORegion region;
>> +    uint64_t pending_bytes;
>>   } VFIOMigration;
>>   
>>   typedef struct VFIOAddressSpace {
>