Re: [PATCH v7 10/17] cxl/pci: Add log message and add type check in existing RAS handlers

From: Dave Jiang
Date: Tue Feb 11 2025 - 18:28:19 EST




On 2/11/25 12:24 PM, Terry Bowman wrote:
> The CXL RAS handlers do not currently log if the RAS registers are
> unmapped. This is needed in order to help debug CXL error handling. Update
> the CXL driver to log a warning message if the RAS register block is
> unmapped.
>
> Also, add type check before processing EP or RCH DP.
>
> Signed-off-by: Terry Bowman <terry.bowman@xxxxxxx>
> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@xxxxxxxxxx>
> Reviewed-by: Ira Weiny <ira.weiny@xxxxxxxxx>
> Reviewed-by: Gregory Price <gourry@xxxxxxxxxx>

Reviewed-by: Dave Jiang <dave.jiang@xxxxxxxxx>
> ---
> drivers/cxl/core/pci.c | 20 ++++++++++++++------
> 1 file changed, 14 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
> index 69bb030aa8e1..af809e7cbe3b 100644
> --- a/drivers/cxl/core/pci.c
> +++ b/drivers/cxl/core/pci.c
> @@ -658,15 +658,19 @@ static void __cxl_handle_cor_ras(struct device *dev,
> void __iomem *addr;
> u32 status;
>
> - if (!ras_base)
> + if (!ras_base) {
> + dev_warn_once(dev, "CXL RAS register block is not mapped");
> return;
> + }
>
> addr = ras_base + CXL_RAS_CORRECTABLE_STATUS_OFFSET;
> status = readl(addr);
> - if (status & CXL_RAS_CORRECTABLE_STATUS_MASK) {
> - writel(status & CXL_RAS_CORRECTABLE_STATUS_MASK, addr);
> + if (!(status & CXL_RAS_CORRECTABLE_STATUS_MASK))
> + return;
> + writel(status & CXL_RAS_CORRECTABLE_STATUS_MASK, addr);
> +
> + if (is_cxl_memdev(dev))
> trace_cxl_aer_correctable_error(to_cxl_memdev(dev), status);
> - }
> }
>
> static void cxl_handle_endpoint_cor_ras(struct cxl_dev_state *cxlds)
> @@ -702,8 +706,10 @@ static bool __cxl_handle_ras(struct device *dev, void __iomem *ras_base)
> u32 status;
> u32 fe;
>
> - if (!ras_base)
> + if (!ras_base) {
> + dev_warn_once(dev, "CXL RAS register block is not mapped");
> return false;
> + }
>
> addr = ras_base + CXL_RAS_UNCORRECTABLE_STATUS_OFFSET;
> status = readl(addr);
> @@ -722,7 +728,9 @@ static bool __cxl_handle_ras(struct device *dev, void __iomem *ras_base)
> }
>
> header_log_copy(ras_base, hl);
> - trace_cxl_aer_uncorrectable_error(to_cxl_memdev(dev), status, fe, hl);
> + if (is_cxl_memdev(dev))
> + trace_cxl_aer_uncorrectable_error(to_cxl_memdev(dev), status, fe, hl);
> +
> writel(status & CXL_RAS_UNCORRECTABLE_STATUS_MASK, addr);
>
> return true;