Re: [Qemu-devel] [RFC v2 05/33] migration: better error handling with QEMUFile

[Dr. David Alan Gilbert]

* Peter Xu (address@hidden) wrote:
> If the postcopy down due to some reason, we can always see this on dst:
> 
>   qemu-system-x86_64: RP: Received invalid message 0x0000 length 0x0000
> 
> However in most cases that's not the real issue. The problem is that
> qemu_get_be16() has no way to show whether the returned data is valid or
> not, and we are _always_ assuming it is valid. That's possibly not wise.
> 
> The best approach to solve this would be: refactoring QEMUFile interface
> to allow the APIs to return error if there is. However it needs quite a
> bit of work and testing. For now, let's explicitly check the validity
> first before using the data in all places for qemu_get_*().
> 
> This patch tries to fix most of the cases I can see. Only if we are with
> this, can we make sure we are processing the valid data, and also can we
> make sure we can capture the channel down events correctly.
> 
> Signed-off-by: Peter Xu <address@hidden>
> ---
>  migration/migration.c |  5 +++++
>  migration/ram.c       | 22 ++++++++++++++++++----
>  migration/savevm.c    | 41 +++++++++++++++++++++++++++++++++++++++--
>  3 files changed, 62 insertions(+), 6 deletions(-)
> 
> diff --git a/migration/migration.c b/migration/migration.c
> index c818412..92bf9b8 100644
> --- a/migration/migration.c
> +++ b/migration/migration.c
> @@ -1543,6 +1543,11 @@ static void *source_return_path_thread(void *opaque)
>          header_type = qemu_get_be16(rp);
>          header_len = qemu_get_be16(rp);
>  
> +        if (qemu_file_get_error(rp)) {
> +            mark_source_rp_bad(ms);
> +            goto out;
> +        }
> +
>          if (header_type >= MIG_RP_MSG_MAX ||
>              header_type == MIG_RP_MSG_INVALID) {
>              error_report("RP: Received invalid message 0x%04x length 0x%04x",
> diff --git a/migration/ram.c b/migration/ram.c
> index affb20c..7e20097 100644
> --- a/migration/ram.c
> +++ b/migration/ram.c
> @@ -2417,7 +2417,7 @@ static int ram_load_postcopy(QEMUFile *f)
>      void *last_host = NULL;
>      bool all_zero = false;
>  
> -    while (!ret && !(flags & RAM_SAVE_FLAG_EOS)) {
> +    while (!(flags & RAM_SAVE_FLAG_EOS)) {

With this change, I don't see what's checking the result of:
   ret = postcopy_place_page(...)
at the bottom of the loop.

>          ram_addr_t addr;
>          void *host = NULL;
>          void *page_buffer = NULL;
> @@ -2426,6 +2426,16 @@ static int ram_load_postcopy(QEMUFile *f)
>          uint8_t ch;
>  
>          addr = qemu_get_be64(f);
> +
> +        /*
> +         * If qemu file error, we should stop here, and then "addr"
> +         * may be invalid
> +         */
> +        ret = qemu_file_get_error(f);
> +        if (ret) {
> +            break;
> +        }
> +
>          flags = addr & ~TARGET_PAGE_MASK;
>          addr &= TARGET_PAGE_MASK;
>  
> @@ -2506,6 +2516,13 @@ static int ram_load_postcopy(QEMUFile *f)
>              error_report("Unknown combination of migration flags: %#x"
>                           " (postcopy mode)", flags);
>              ret = -EINVAL;
> +            break;
> +        }
> +
> +        /* Detect for any possible file errors */
> +        if (qemu_file_get_error(f)) {
> +            ret = qemu_file_get_error(f);
> +            break;
>          }
>  
>          if (place_needed) {
> @@ -2520,9 +2537,6 @@ static int ram_load_postcopy(QEMUFile *f)
>                                            place_source, block);
>              }
>          }
> -        if (!ret) {
> -            ret = qemu_file_get_error(f);
> -        }
>      }
>  
>      return ret;
> diff --git a/migration/savevm.c b/migration/savevm.c
> index fdd15fa..7172f14 100644
> --- a/migration/savevm.c
> +++ b/migration/savevm.c
> @@ -1720,6 +1720,11 @@ static int loadvm_process_command(QEMUFile *f)
>      cmd = qemu_get_be16(f);
>      len = qemu_get_be16(f);
>  
> +    /* Check validity before continue processing of cmds */
> +    if (qemu_file_get_error(f)) {
> +        return qemu_file_get_error(f);
> +    }
> +
>      trace_loadvm_process_command(cmd, len);
>      if (cmd >= MIG_CMD_MAX || cmd == MIG_CMD_INVALID) {
>          error_report("MIG_CMD 0x%x unknown (len 0x%x)", cmd, len);
> @@ -1785,6 +1790,7 @@ static int loadvm_process_command(QEMUFile *f)
>   */
>  static bool check_section_footer(QEMUFile *f, SaveStateEntry *se)
>  {
> +    int ret;
>      uint8_t read_mark;
>      uint32_t read_section_id;
>  
> @@ -1795,6 +1801,13 @@ static bool check_section_footer(QEMUFile *f, 
> SaveStateEntry *se)
>  
>      read_mark = qemu_get_byte(f);
>  
> +    ret = qemu_file_get_error(f);
> +    if (ret) {
> +        error_report("%s: Read section footer failed: %d",
> +                     __func__, ret);
> +        return false;
> +    }
> +
>      if (read_mark != QEMU_VM_SECTION_FOOTER) {
>          error_report("Missing section footer for %s", se->idstr);
>          return false;
> @@ -1830,6 +1843,13 @@ qemu_loadvm_section_start_full(QEMUFile *f, 
> MigrationIncomingState *mis)
>      instance_id = qemu_get_be32(f);
>      version_id = qemu_get_be32(f);
>  
> +    ret = qemu_file_get_error(f);
> +    if (ret) {
> +        error_report("%s: Failed to read instance/version ID: %d",
> +                     __func__, ret);
> +        return ret;
> +    }
> +
>      trace_qemu_loadvm_state_section_startfull(section_id, idstr,
>              instance_id, version_id);
>      /* Find savevm section */
> @@ -1877,6 +1897,13 @@ qemu_loadvm_section_part_end(QEMUFile *f, 
> MigrationIncomingState *mis)
>  
>      section_id = qemu_get_be32(f);
>  
> +    ret = qemu_file_get_error(f);
> +    if (ret) {
> +        error_report("%s: Failed to read section ID: %d",
> +                     __func__, ret);
> +        return ret;
> +    }
> +
>      trace_qemu_loadvm_state_section_partend(section_id);
>      QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
>          if (se->load_section_id == section_id) {
> @@ -1944,8 +1971,14 @@ static int qemu_loadvm_state_main(QEMUFile *f, 
> MigrationIncomingState *mis)
>      uint8_t section_type;
>      int ret = 0;
>  
> -    while ((section_type = qemu_get_byte(f)) != QEMU_VM_EOF) {
> -        ret = 0;
> +    while (true) {
> +        section_type = qemu_get_byte(f);
> +
> +        if (qemu_file_get_error(f)) {
> +            ret = qemu_file_get_error(f);
> +            break;
> +        }
> +
>          trace_qemu_loadvm_state_section(section_type);
>          switch (section_type) {
>          case QEMU_VM_SECTION_START:
> @@ -1969,6 +2002,10 @@ static int qemu_loadvm_state_main(QEMUFile *f, 
> MigrationIncomingState *mis)
>                  goto out;
>              }
>              break;
> +        case QEMU_VM_EOF:
> +            /* This is the end of migration */
> +            goto out;
> +            break;

You don't need the goto and the break (although it does no harm).

Dave

>          default:
>              error_report("Unknown savevm section type %d", section_type);
>              ret = -EINVAL;
> -- 
> 2.7.4
> 
> 
--
Dr. David Alan Gilbert / address@hidden / Manchester, UK