[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20181017163026.GF22535@zn.tnic>
Date: Wed, 17 Oct 2018 18:30:26 +0200
From: Borislav Petkov <bp@...en8.de>
To: Manish Narani <manish.narani@...inx.com>
Cc: robh+dt@...nel.org, mark.rutland@....com, michal.simek@...inx.com,
mchehab@...nel.org, amit.kucheria@...aro.org, sudeep.holla@....com,
olof@...om.net, devicetree@...r.kernel.org,
linux-kernel@...r.kernel.org, linux-arm-kernel@...ts.infradead.org,
linux-edac@...r.kernel.org
Subject: Re: [PATCH v9 4/6] edac: synopsys: Add EDAC ECC support for ZynqMP
DDRC
On Mon, Oct 15, 2018 at 10:59:46AM +0530, Manish Narani wrote:
> Add EDAC ECC support for ZynqMP DDRC IP. The IP supports interrupts for
> corrected and uncorrected errors. Add interrupt handlers for the same.
>
> Signed-off-by: Manish Narani <manish.narani@...inx.com>
> ---
> drivers/edac/Kconfig | 2 +-
> drivers/edac/synopsys_edac.c | 324 ++++++++++++++++++++++++++++++++++++++++---
> 2 files changed, 308 insertions(+), 18 deletions(-)
>
> diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
> index 57304b2..7c40eb2 100644
> --- a/drivers/edac/Kconfig
> +++ b/drivers/edac/Kconfig
> @@ -441,7 +441,7 @@ config EDAC_ALTERA_SDMMC
>
> config EDAC_SYNOPSYS
> tristate "Synopsys DDR Memory Controller"
> - depends on ARCH_ZYNQ
> + depends on ARCH_ZYNQ || ARCH_ZYNQMP
> help
> Support for error detection and correction on the Synopsys DDR
> memory controller.
> diff --git a/drivers/edac/synopsys_edac.c b/drivers/edac/synopsys_edac.c
> index d1999e0..603c4bd 100644
> --- a/drivers/edac/synopsys_edac.c
> +++ b/drivers/edac/synopsys_edac.c
> @@ -22,6 +22,7 @@
> #include <linux/edac.h>
> #include <linux/module.h>
> #include <linux/platform_device.h>
> +#include <linux/interrupt.h>
> #include <linux/of.h>
> #include <linux/of_device.h>
>
> @@ -272,6 +273,8 @@
> * @bank: Bank number.
> * @bitpos: Bit position.
> * @data: Data causing the error.
> + * @bankgrpnr: Bank group number.
> + * @blknr: Block number.
> */
> struct ecc_error_info {
> u32 row;
> @@ -279,6 +282,8 @@ struct ecc_error_info {
> u32 bank;
> u32 bitpos;
> u32 data;
> + u32 bankgrpnr;
> + u32 blknr;
> };
>
> /**
> @@ -385,6 +390,66 @@ static int zynq_get_error_info(struct synps_edac_priv *priv)
> }
>
> /**
> + * zynqmp_get_error_info - Get the current ECC error info.
> + * @priv: DDR memory controller private instance data.
> + *
> + * Return: one if there is no error otherwise returns zero.
> + */
> +static int zynqmp_get_error_info(struct synps_edac_priv *priv)
> +{
> + struct synps_ecc_status *p;
> + u32 regval, clearval = 0;
> + void __iomem *base;
> +
> + base = priv->baseaddr;
> + p = &priv->stat;
> +
> + regval = readl(base + ECC_STAT_OFST);
> + if (!regval)
> + return 1;
> +
> + p->ce_cnt = (regval & ECC_STAT_CECNT_MASK) >> ECC_STAT_CECNT_SHIFT;
> + p->ue_cnt = (regval & ECC_STAT_UECNT_MASK) >> ECC_STAT_UECNT_SHIFT;
> + p->ceinfo.bitpos = (regval & ECC_STAT_BITNUM_MASK);
> +
> + regval = readl(base + ECC_CEADDR0_OFST);
> + if (!p->ce_cnt)
> + goto ue_err;
This check should happen right under the p->ce_cnt assignment a couple
of lines above it. Otherwise the readl() is useless if you jump to the
ue_err label.
IOW, those two readl()'s should happen *after* the ce/ue_cnt checks.
> +
> + p->ceinfo.row = (regval & ECC_CEADDR0_RW_MASK);
> + regval = readl(base + ECC_CEADDR1_OFST);
> + p->ceinfo.bank = (regval & ECC_CEADDR1_BNKNR_MASK) >>
> + ECC_CEADDR1_BNKNR_SHIFT;
> + p->ceinfo.bankgrpnr = (regval & ECC_CEADDR1_BNKGRP_MASK) >>
> + ECC_CEADDR1_BNKGRP_SHIFT;
> + p->ceinfo.blknr = (regval & ECC_CEADDR1_BLKNR_MASK);
> + p->ceinfo.data = readl(base + ECC_CSYND0_OFST);
> + edac_dbg(2, "ECCCSYN0: 0x%08X ECCCSYN1: 0x%08X ECCCSYN2: 0x%08X\n",
> + readl(base + ECC_CSYND0_OFST), readl(base + ECC_CSYND1_OFST),
> + readl(base + ECC_CSYND2_OFST));
> +ue_err:
> + regval = readl(base + ECC_UEADDR0_OFST);
> + if (!p->ue_cnt)
> + goto out;
> +
> + p->ueinfo.row = (regval & ECC_CEADDR0_RW_MASK);
> + regval = readl(base + ECC_UEADDR1_OFST);
> + p->ueinfo.bankgrpnr = (regval & ECC_CEADDR1_BNKGRP_MASK) >>
> + ECC_CEADDR1_BNKGRP_SHIFT;
> + p->ueinfo.bank = (regval & ECC_CEADDR1_BNKNR_MASK) >>
> + ECC_CEADDR1_BNKNR_SHIFT;
> + p->ueinfo.blknr = (regval & ECC_CEADDR1_BLKNR_MASK);
> + p->ueinfo.data = readl(base + ECC_UESYND0_OFST);
> +out:
> + clearval = ECC_CTRL_CLR_CE_ERR | ECC_CTRL_CLR_CE_ERRCNT;
> + clearval |= ECC_CTRL_CLR_UE_ERR | ECC_CTRL_CLR_UE_ERRCNT;
> + writel(clearval, base + ECC_CLR_OFST);
> + writel(0x0, base + ECC_CLR_OFST);
> +
> + return 0;
> +}
> +
...
> +static int setup_irq(struct mem_ctl_info *mci,
> + struct platform_device *pdev)
Align arguments on the opening brace.
> +{
> + struct synps_edac_priv *priv = mci->pvt_info;
> + int ret, irq;
> +
> + irq = platform_get_irq(pdev, 0);
> + if (irq < 0) {
> + edac_printk(KERN_ERR, EDAC_MC,
> + "No IRQ %d in DT\n", irq);
> + return irq;
> + }
> +
> + ret = devm_request_irq(&pdev->dev, irq, intr_handler,
> + 0, dev_name(&pdev->dev), mci);
> + if (ret < 0) {
> + edac_printk(KERN_ERR, EDAC_MC, "Failed to request IRQ\n");
> + return ret;
> + }
> +
> + enable_intr(priv);
> +
> + return 0;
> +}
> +
> static const struct synps_platform_data zynq_edac_def = {
> .get_error_info = zynq_get_error_info,
> .get_mtype = zynq_get_mtype,
> @@ -613,9 +872,26 @@ static const struct synps_platform_data zynq_edac_def = {
> .quirks = 0,
> };
>
> +static const struct synps_platform_data zynqmp_edac_def = {
> + .get_error_info = zynqmp_get_error_info,
> + .get_mtype = zynqmp_get_mtype,
> + .get_dtype = zynqmp_get_dtype,
> + .get_ecc_state = zynqmp_get_ecc_state,
> + .quirks = DDR_ECC_INTR_SUPPORT,
> +};
> +
> static const struct of_device_id synps_edac_match[] = {
> - { .compatible = "xlnx,zynq-ddrc-a05", .data = (void *)&zynq_edac_def },
> - { /* end of table */ }
> + {
> + .compatible = "xlnx,zynq-ddrc-a05",
> + .data = (void *)&zynq_edac_def
> + },
> + {
> + .compatible = "xlnx,zynqmp-ddrc-2.40a",
> + .data = (void *)&zynqmp_edac_def
> + },
> + {
> + /* end of table */
> + }
> };
>
> MODULE_DEVICE_TABLE(of, synps_edac_match);
> @@ -674,6 +950,12 @@ static int mc_probe(struct platform_device *pdev)
>
> mc_init(mci, pdev);
>
> + if (priv->p_data->quirks & DDR_ECC_INTR_SUPPORT) {
> + rc = setup_irq(mci, pdev);
> + if (rc)
> + goto free_edac_mc;
> + }
> +
> rc = edac_mc_add_mc(mci);
> if (rc) {
> edac_printk(KERN_ERR, EDAC_MC,
> @@ -685,7 +967,9 @@ static int mc_probe(struct platform_device *pdev)
> * Start capturing the correctable and uncorrectable errors. A write of
> * 0 starts the counters.
> */
> - writel(0x0, baseaddr + ECC_CTRL_OFST);
> + if (!(priv->p_data->quirks & DDR_ECC_INTR_SUPPORT))
> + writel(0x0, baseaddr + ECC_CTRL_OFST);
> +
> return rc;
>
> free_edac_mc:
> @@ -703,6 +987,12 @@ static int mc_probe(struct platform_device *pdev)
> static int mc_remove(struct platform_device *pdev)
> {
> struct mem_ctl_info *mci = platform_get_drvdata(pdev);
> + struct synps_edac_priv *priv;
> +
> + priv = mci->pvt_info;
Or simply:
struct synps_edac_priv *priv = mci->pvt_info;
> + if (priv->p_data->quirks & DDR_ECC_INTR_SUPPORT)
> + disable_intr(priv);
>
> edac_mc_del_mc(&pdev->dev);
> edac_mc_free(mci);
> --
> 2.1.1
>
--
Regards/Gruss,
Boris.
Good mailing practices for 400: avoid top-posting and trim the reply.
Powered by blists - more mailing lists