mtd: spinand: Fix double counting of ECC stats

In the raw NAND world, ECC engines increment ecc_stats and the final
caller is responsible for returning -EBADMSG if the verification
failed.

In the SPI-NAND world it was a bit different until now because there was
only one possible ECC engine: the on-die one. Indeed, the
spinand_mtd_read() call was incrementing the ecc_stats counters
depending on the outcome of spinand_check_ecc_status() directly.

So now let's split the logic like this:
- spinand_check_ecc_status() is specific to the SPI-NAND on-die engine
  and is kept very simple: it just returns the ECC status (bonus point:
  the content of this helper can be overloaded).
- spinand_ondie_ecc_finish_io_req() is the caller of
  spinand_check_ecc_status() and will increment the counters and
  eventually return -EBADMSG.
- spinand_mtd_read() is not tied to the on-die ECC implementation and
  should be able to handle results coming from other ECC engines: it has
  the responsibility of returning the maximum number of bitflips which
  happened during the entire operation as this is the only helper that
  is aware that several pages may be read in a row.

Fixes: 945845b5 ("mtd: spinand: Instantiate a SPI-NAND on-die ECC engine")
Reported-by: YouChing Lin <ycllin@mxic.com.tw>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Tested-by: YouChing Lin <ycllin@mxic.com.tw>
Link: https://lore.kernel.org/linux-mtd/20210527084345.208215-1-miquel.raynal@bootlin.com