Re: [PATCH 7/9] btrfs: Add support for recovery for a RAID 5 btrfs profiles.

[Daniel Kiper]

On Sun, Jun 03, 2018 at 08:53:46PM +0200, Goffredo Baroncelli wrote:
> Add support for recovery fo a RAID 5 btrfs profile. In addition

s/fo /for /

> it is added some code as preparatory work for RAID 6 recovery code.
>
> Signed-off-by: Goffredo Baroncelli <address@hidden>
> ---
>  grub-core/fs/btrfs.c | 180 +++++++++++++++++++++++++++++++++++++++++--
>  1 file changed, 175 insertions(+), 5 deletions(-)
>
> diff --git a/grub-core/fs/btrfs.c b/grub-core/fs/btrfs.c
> index 9cdbfe792..c8f034641 100644
> --- a/grub-core/fs/btrfs.c
> +++ b/grub-core/fs/btrfs.c
> @@ -29,6 +29,7 @@
>  #include <minilzo.h>
>  #include <grub/i18n.h>
>  #include <grub/btrfs.h>
> +#include <grub/crypto.h>
>
>  GRUB_MOD_LICENSE ("GPLv3+");
>
> @@ -666,6 +667,157 @@ btrfs_read_from_chunk (struct grub_btrfs_data *data,
>      return err;
>  }
>
> +struct raid56_buffer {
> +  void *buf;
> +  int  data_is_valid;
> +};
> +
> +static void
> +rebuild_raid5 (char *dest, struct raid56_buffer *buffers,
> +            grub_uint64_t nstripes, grub_uint64_t csize)
> +{
> +  grub_uint64_t i;

grub_uint64_t i = 0;
int first = 1;

> +  int first;
> +
> +  i = 0;

Then you can drop this assignment.

> +  while (buffers[i].data_is_valid && i < nstripes)
> +    ++i;
> +
> +  if (i == nstripes)
> +    {
> +      grub_dprintf ("btrfs", "called rebuild_raid5(), but all disks are 
> OK\n");
> +      return;
> +    }
> +
> +  grub_dprintf ("btrfs", "rebuilding RAID 5 stripe #%" PRIuGRUB_UINT64_T 
> "\n",
> +             i);

This can be in one line.

> +  first = 1;

And you can drop this assignment too.

> +  for (i = 0; i < nstripes; i++)
> +    {
> +      if (!buffers[i].data_is_valid)
> +     continue;
> +
> +      if (first)
> +     grub_memcpy(dest, buffers[i].buf, csize);
> +      else
> +     grub_crypto_xor (dest, dest, buffers[i].buf, csize);

I am not sure why at first you use grub_memcpy() and
then move to grub_crypto_xor(). Could you explain this?
Why do not use grub_crypto_xor() in all cases?

> +
> +      first = 0;
> +    }
> +}
> +
> +static grub_err_t
> +raid56_read_retry (struct grub_btrfs_data *data,
> +                struct grub_btrfs_chunk_item *chunk,
> +                grub_uint64_t stripe_offset,
> +                grub_uint64_t csize, void *buf)
> +{
> +

Please drop this empty line. I have asked about that earlier.

> +  struct raid56_buffer *buffers = NULL;
> +  grub_uint64_t nstripes = grub_le_to_cpu16 (chunk->nstripes);
> +  grub_uint64_t chunk_type = grub_le_to_cpu64 (chunk->type);
> +  grub_err_t ret = GRUB_ERR_NONE;
> +  grub_uint64_t i, failed_devices;
> +
> +  buffers = grub_zalloc (sizeof(*buffers) * nstripes);

How often this function is called? Maybe you should consider
doing memory allocation for this function only once and free
it at btrfs module unload.

> +  if (!buffers)
> +    {
> +      ret = GRUB_ERR_OUT_OF_MEMORY;
> +      goto cleanup;
> +    }
> +
> +  for (i = 0; i < nstripes; i++)
> +    {
> +      buffers[i].buf = grub_zalloc (csize);

Ditto.

> +      if (!buffers[i].buf)
> +     {
> +       ret = GRUB_ERR_OUT_OF_MEMORY;
> +       goto cleanup;
> +     }
> +    }
> +
> +  for (i = 0; i < nstripes; i++)
> +    {
> +      struct grub_btrfs_chunk_stripe *stripe;
> +      grub_disk_addr_t paddr;
> +      grub_device_t dev;
> +      grub_err_t err2;
> +
> +      stripe = (struct grub_btrfs_chunk_stripe *) (chunk + 1);
> +      stripe += i;
> +
> +      paddr = grub_le_to_cpu64 (stripe->offset) + stripe_offset;
> +      grub_dprintf ("btrfs", "reading paddr %" PRIxGRUB_UINT64_T
> +                    " from stripe ID %" PRIxGRUB_UINT64_T "\n", paddr,
> +                    stripe->device_id);
> +
> +      dev = find_device (data, stripe->device_id);
> +      if (!dev)
> +     {
> +       buffers[i].data_is_valid = 0;
> +       grub_dprintf ("btrfs", "stripe %" PRIuGRUB_UINT64_T " FAILED (dev ID 
> %"
> +                     PRIxGRUB_UINT64_T ")\n", i, stripe->device_id);
> +       continue;
> +     }
> +
> +      err2 = grub_disk_read (dev->disk, paddr >> GRUB_DISK_SECTOR_BITS,
> +                          paddr & (GRUB_DISK_SECTOR_SIZE - 1),
> +                          csize, buffers[i].buf);
> +      if (err2 == GRUB_ERR_NONE)
> +     {
> +       buffers[i].data_is_valid = 1;
> +       grub_dprintf ("btrfs", "stripe %" PRIuGRUB_UINT64_T " Ok (dev ID %"
> +                     PRIxGRUB_UINT64_T ")\n", i, stripe->device_id);
> +     }
> +      else
> +     {
> +       buffers[i].data_is_valid = 0;
> +       grub_dprintf ("btrfs", "stripe %" PRIuGRUB_UINT64_T
> +                     " FAILED (dev ID %" PRIxGRUB_UINT64_T ")\n", i,
> +                     stripe->device_id);
> +     }
> +    }
> +
> +  failed_devices = 0;
> +  for (i = 0; i < nstripes; i++)

for (failed_devices = i = 0; i < nstripes; i++)

> +    if (!buffers[i].data_is_valid)
> +      ++failed_devices;
> +  if (failed_devices > 1 && (chunk_type & GRUB_BTRFS_CHUNK_TYPE_RAID5))
> +    {
> +      grub_dprintf ("btrfs",
> +                 "not enough disks for RAID 5: total %" PRIuGRUB_UINT64_T
> +                 ", missing %" PRIuGRUB_UINT64_T "\n",
> +                 nstripes, failed_devices);
> +      ret = GRUB_ERR_READ_ERROR;
> +      goto cleanup;
> +    }
> +  else
> +    {
> +      grub_dprintf ("btrfs",
> +                    "enough disks for RAID 5 rebuilding: total %"
> +                 PRIuGRUB_UINT64_T ", missing %" PRIuGRUB_UINT64_T "\n",
> +                    nstripes, failed_devices);
> +    }
> +
> +  /* if these are enough, try to rebuild the data */
> +  if (chunk_type & GRUB_BTRFS_CHUNK_TYPE_RAID5)
> +    rebuild_raid5 (buf, buffers, nstripes, csize);
> +  else
> +    grub_dprintf ("btrfs", "called rebuild_raid6(), NOT IMPLEMENTED\n");
> +
> +cleanup:

Space before the label please.
I have asked about earlier.

> +

Please drop this empty line.

Daniel