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

[Daniel Kiper <dkiper@net-space.pl>]

On Thu, Oct 18, 2018 at 07:55:39PM +0200, Goffredo Baroncelli wrote:
> From: Goffredo Baroncelli <kreijack@inwind.it>
>
> Add support for recovery for a RAID 5 btrfs profile. In addition
> it is added some code as preparatory work for RAID 6 recovery code.
>
> Signed-off-by: Goffredo Baroncelli <kreijack@inwind.it>
> ---
>  grub-core/fs/btrfs.c | 161 +++++++++++++++++++++++++++++++++++++++++--
>  1 file changed, 156 insertions(+), 5 deletions(-)
>
> diff --git a/grub-core/fs/btrfs.c b/grub-core/fs/btrfs.c
> index ea97f0502..b277f2904 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+");
>
> @@ -665,6 +666,140 @@ 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;
> +  int first;
> +
> +  for(i = 0; 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);
> +
> +  for (i = 0, first = 1; i < nstripes; i++)
> +    {
> +      if (!buffers[i].data_is_valid)
> +	continue;
> +
> +      if (first) {
> +	grub_memcpy(dest, buffers[i].buf, csize);
> +	first = 0;
> +      } else
> +	grub_crypto_xor (dest, dest, buffers[i].buf, csize);
> +    }
> +}
> +
> +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)
> +{
> +  struct raid56_buffer *buffers;
> +  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_OUT_OF_MEMORY;
> +  grub_uint64_t i, failed_devices;
> +
> +  buffers = grub_zalloc (sizeof(*buffers) * nstripes);
> +  if (!buffers)
> +    goto cleanup;
> +
> +  for (i = 0; i < nstripes; i++)
> +    {
> +      buffers[i].buf = grub_zalloc (csize);
> +      if (!buffers[i].buf)
> +	goto cleanup;
> +    }
> +
> +  for (failed_devices = 0, i = 0; i < nstripes; i++)
> +    {
> +      struct grub_btrfs_chunk_stripe *stripe;
> +      grub_disk_addr_t paddr;
> +      grub_device_t dev;
> +      grub_err_t err;
> +
> +      /* The struct grub_btrfs_chunk_stripe array lives behind struct
> +	 grub_btrfs_chunk_item. */
> +      stripe = (struct grub_btrfs_chunk_stripe *) (chunk + 1) + 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;

You do not need this and...

> +	  grub_dprintf ("btrfs", "stripe %" PRIuGRUB_UINT64_T " FAILED (dev ID %"
> +			PRIxGRUB_UINT64_T ")\n", i, stripe->device_id);
> +	  failed_devices++;
> +	  continue;
> +	}
> +
> +      err = grub_disk_read (dev->disk, paddr >> GRUB_DISK_SECTOR_BITS,
> +			    paddr & (GRUB_DISK_SECTOR_SIZE - 1),
> +			    csize, buffers[i].buf);
> +      if (err == 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;

...this. grub_zalloc() above did work for you.

> +	  grub_dprintf ("btrfs", "stripe %" PRIuGRUB_UINT64_T
> +			" FAILED (dev ID %" PRIxGRUB_UINT64_T ")\n", i,

s/FAILED/READ FAILED/

Otherwise Reviewed-by: Daniel Kiper <daniel.kiper@oracle.com>

Daniel