On Thu, 28 Jul 2022 at 10:01, Wenbin Mei <wenbin.mei@xxxxxxxxxxxx> wrote:
>
> Currently we don't clear MSDC interrupts when cqe off/disable, which led
> to the data complete interrupt will be reserved for the next command.
> If the next command with data transfer after cqe off/disable, we process
> the CMD ready interrupt and trigger DMA start for data, but the data
> complete interrupt is already exists, then SW assume that the data transfer
> is complete, SW will trigger DMA stop, but the data may not be transmitted
> yet or is transmitting, so we may encounter the following error:
> mtk-msdc 11230000.mmc: CMD bus busy detected.
>
> Signed-off-by: Wenbin Mei <wenbin.mei@xxxxxxxxxxxx>
Applied for fixes and by adding the below tags, thanks!
Fixes: 88bd652b3c74 ("mmc: mediatek: command queue support")
Cc: stable@xxxxxxxxxxxxxxx
Kind regards
Uffe
> ---
> drivers/mmc/host/mtk-sd.c | 6 ++++++
> 1 file changed, 6 insertions(+)
>
> diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
> index 4ff73d1883de..69d78604d1fc 100644
> --- a/drivers/mmc/host/mtk-sd.c
> +++ b/drivers/mmc/host/mtk-sd.c
> @@ -2446,6 +2446,9 @@ static void msdc_cqe_disable(struct mmc_host *mmc, bool recovery)
> /* disable busy check */
> sdr_clr_bits(host->base + MSDC_PATCH_BIT1, MSDC_PB1_BUSY_CHECK_SEL);
>
> + val = readl(host->base + MSDC_INT);
> + writel(val, host->base + MSDC_INT);
> +
> if (recovery) {
> sdr_set_field(host->base + MSDC_DMA_CTRL,
> MSDC_DMA_CTRL_STOP, 1);
> @@ -2932,11 +2935,14 @@ static int __maybe_unused msdc_suspend(struct device *dev)
> struct mmc_host *mmc = dev_get_drvdata(dev);
> struct msdc_host *host = mmc_priv(mmc);
> int ret;
> + u32 val;
>
> if (mmc->caps2 & MMC_CAP2_CQE) {
> ret = cqhci_suspend(mmc);
> if (ret)
> return ret;
> + val = readl(host->base + MSDC_INT);
> + writel(val, host->base + MSDC_INT);
> }
>
> /*
> --
> 2.25.1
>
