| Message ID | 20220728080048.21336-1-wenbin.mei@mediatek.com |
|---|---|
| State | New |
| Headers | show |
| Series | mmc: mtk-sd: Clear interrupts when cqe off/disable | expand |
On Thu, 28 Jul 2022 at 10:01, Wenbin Mei <wenbin.mei@mediatek.com> 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@mediatek.com> Applied for fixes and by adding the below tags, thanks! Fixes: 88bd652b3c74 ("mmc: mediatek: command queue support") Cc: stable@vger.kernel.org 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 >
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); } /*
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@mediatek.com> --- drivers/mmc/host/mtk-sd.c | 6 ++++++ 1 file changed, 6 insertions(+)