On Tue, 12 Jun 2018 10:02:12 +0200
Stefan Agner <ste...@agner.ch> wrote:
> >> +static int tegra_nand_read_page_hwecc(struct mtd_info *mtd,
> >> + struct nand_chip *chip,
> >> + uint8_t *buf, int oob_required, int page)
> >> +{
> >> + struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
> >> + struct tegra_nand_chip *nand = to_tegra_chip(chip);
> >> + void *oob_buf = oob_required ? chip->oob_poi : 0;
> >> + u32 dec_stat, max_corr_cnt;
> >> + unsigned long fail_sec_flag;
> >> + int ret;
> >> +
> >> + tegra_nand_hw_ecc(ctrl, chip, true);
> >> + ret = tegra_nand_page_xfer(mtd, chip, buf, oob_buf, nand->tag.length,
> >> + page, true);
> >> + tegra_nand_hw_ecc(ctrl, chip, false);
> >> + if (ret)
> >> + return ret;
> >> +
> >> + /* No correctable or un-correctable errors, page must have 0 bitflips */
> >> + if (!ctrl->last_read_error)
> >> + return 0;
> >> +
> >> + /*
> >> + * Correctable or un-correctable errors occurred. Use DEC_STAT_BUF
> >> + * which contains information for all ECC selections.
> >> + *
> >> + * Note that since we do not use Command Queues DEC_RESULT does not
> >> + * state the number of pages we can read from the DEC_STAT_BUF. But
> >> + * since CORRFAIL_ERR did occur during page read we do have a valid
> >> + * result in DEC_STAT_BUF.
> >> + */
> >> + ctrl->last_read_error = false;
> >> + dec_stat = readl_relaxed(ctrl->regs + DEC_STAT_BUF);
> >> +
> >> + fail_sec_flag = (dec_stat & DEC_STAT_BUF_FAIL_SEC_FLAG_MASK) >>
> >> + DEC_STAT_BUF_FAIL_SEC_FLAG_SHIFT;
> >> +
> >> + max_corr_cnt = (dec_stat & DEC_STAT_BUF_MAX_CORR_CNT_MASK) >>
> >> + DEC_STAT_BUF_MAX_CORR_CNT_SHIFT;
> >> +
> >> + if (fail_sec_flag) {
> >> + int bit, max_bitflips = 0;
> >> +
> >> + /*
> >> + * Check if all sectors in a page failed. If only some failed
> >> + * its definitly not an erased page and we can return error
> >> + * stats right away.
> >> + *
> >> + * E.g. controller might return fail_sec_flag with 0x4, which
> >> + * would mean only the third sector failed to correct.
That works because you have NAND_NO_SUBPAGE_WRITE set (i.e. no partial
page programming), probably something you should state here.
> >> + */
> >> + if (fail_sec_flag ^ GENMASK(chip->ecc.steps - 1, 0)) {
> >> + mtd->ecc_stats.failed += hweight8(fail_sec_flag);
> >> + return max_corr_cnt;
> >> + }
> >> +
> >> + /*
> >> + * All sectors failed to correct, but the ECC isn't smart
> >> + * enough to figure out if a page is really completely erased.
> >> + * We check the read data here to figure out if it's a
> >> + * legitimate ECC error or only an erased page.
> >> + */
> >> + for_each_set_bit(bit, &fail_sec_flag, chip->ecc.steps) {
> >> + u8 *data = buf + (chip->ecc.size * bit);
> >> +
> >> + ret = nand_check_erased_ecc_chunk(data, chip->ecc.size,
> >> + NULL, 0,
You should also check that the ECC bytes are 0xff here, otherwise you
won't detect corruption of pages almost filled 0xff but with a few bits
set to 0.
When you use nand_check_erased_ecc_chunk(), it's important to always
pass the data along with its associated ECC bytes.
> >> + NULL, 0,
If you support writing extra OOB bytes, you should also pass them here.
> >> + chip->ecc.strength);
> >> + if (ret < 0)
> >> + mtd->ecc_stats.failed++;
> >> + else
> >> + max_bitflips = max(ret, max_bitflips);
> >> + }
> >> +
> >> + return max_t(unsigned int, max_corr_cnt, max_bitflips);
> >> + } else {
> >> + int corr_sec_flag;
> >> +
> >> + corr_sec_flag = (dec_stat & DEC_STAT_BUF_CORR_SEC_FLAG_MASK) >>
> >> + DEC_STAT_BUF_CORR_SEC_FLAG_SHIFT;
> >> +
> >> + /*
> >> + * The value returned in the register is the maximum of
> >> + * bitflips encountered in any of the ECC regions. As there is
> >> + * no way to get the number of bitflips in a specific regions
> >> + * we are not able to deliver correct stats but instead
> >> + * overestimate the number of corrected bitflips by assuming
> >> + * that all regions where errors have been corrected
> >> + * encountered the maximum number of bitflips.
> >> + */
> >> + mtd->ecc_stats.corrected += max_corr_cnt *
> >> hweight8(corr_sec_flag);
> >> +
> >> + return max_corr_cnt;
> >> + }
> >> +
