[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <1e5e679b-a380-48c9-9fcb-a1b6a2d84cd2@amd.com>
Date: Fri, 3 Oct 2025 15:12:16 -0500
From: "Cheatham, Benjamin" <benjamin.cheatham@....com>
To: Terry Bowman <terry.bowman@....com>
CC: <linux-kernel@...r.kernel.org>, <linux-pci@...r.kernel.org>,
<dave@...olabs.net>, <jonathan.cameron@...wei.com>, <dave.jiang@...el.com>,
<alison.schofield@...el.com>, <dan.j.williams@...el.com>,
<bhelgaas@...gle.com>, <shiju.jose@...wei.com>, <ming.li@...omail.com>,
<Smita.KoralahalliChannabasappa@....com>, <rrichter@....com>,
<dan.carpenter@...aro.org>, <PradeepVineshReddy.Kodamati@....com>,
<lukas@...ner.de>, <sathyanarayanan.kuppuswamy@...ux.intel.com>,
<linux-cxl@...r.kernel.org>, <alucerop@....com>, <ira.weiny@...el.com>
Subject: Re: [PATCH v12 23/25] CXL/PCI: Introduce CXL uncorrectable protocol
error recovery
On 9/25/2025 5:34 PM, Terry Bowman wrote:
> Populate the cxl_do_recovery() function with uncorrectable protocol error (UCE)
> handling. Follow similar design as found in PCIe error driver,
> pcie_do_recovery(). One difference is cxl_do_recovery() will treat all UCEs
> as fatal with a kernel panic. This is to prevent corruption on CXL memory.
>
> Introduce cxl_walk_port(). Make this analogous to pci_walk_bridge() but walking
> CXL ports instead. This will iterate through the CXL topology from the
> erroring device through the downstream CXL Ports and Endpoints.
>
> Export pci_aer_clear_fatal_status() for CXL to use if a UCE is not found.
>
> Signed-off-by: Terry Bowman <terry.bowman@....com>
>
> ---
>
> Changes in v11->v12:
> - Cleaned up port discovery in cxl_do_recovery() (Dave)
> - Added PCI_EXP_TYPE_RC_END to type check in cxl_report_error_detected()
>
> Changes in v10->v11:
> - pci_ers_merge_results() - Move to earlier patch
> ---
> drivers/cxl/core/ras.c | 111 +++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 111 insertions(+)
>
> diff --git a/drivers/cxl/core/ras.c b/drivers/cxl/core/ras.c
> index 7e8d63c32d72..45f92defca64 100644
> --- a/drivers/cxl/core/ras.c
> +++ b/drivers/cxl/core/ras.c
> @@ -443,8 +443,119 @@ void cxl_endpoint_port_init_ras(struct cxl_port *ep)
> }
> EXPORT_SYMBOL_NS_GPL(cxl_endpoint_port_init_ras, "CXL");
>
> +static int cxl_report_error_detected(struct device *dev, void *data)
> +{
> + struct pci_dev *pdev = to_pci_dev(dev);
Should probably check if dev_is_pci() first. I don't think it's an issue since
only ports under the root dport are being iterated, but I don't know if this would
trip up cxl_test.
> + pci_ers_result_t vote, *result = data;
> +
> + guard(device)(dev);
> +
> + if ((pci_pcie_type(pdev) == PCI_EXP_TYPE_ENDPOINT) ||
> + (pci_pcie_type(pdev) == PCI_EXP_TYPE_RC_END)) {
> + if (!cxl_pci_drv_bound(pdev))
> + return 0;
> +
> + vote = cxl_error_detected(dev);
> + } else {
> + vote = cxl_port_error_detected(dev);
> + }
> +
> + *result = pci_ers_merge_result(*result, vote);
> +
> + return 0;
> +}
> +
> +static int match_port_by_parent_dport(struct device *dev, const void *dport_dev)
> +{
> + struct cxl_port *port;
> +
> + if (!is_cxl_port(dev))
> + return 0;
> +
> + port = to_cxl_port(dev);
> +
> + return port->parent_dport->dport_dev == dport_dev;
> +}
> +
> +static void cxl_walk_port(struct device *port_dev,
> + int (*cb)(struct device *, void *),
> + void *userdata)
This should just take a struct cxl_port * instead of device *. You always have the
struct cxl_port below and then pass in the &port->dev, only to just cast it back
to a struct cxl_port and never use the device pointer.
> +{
> + struct cxl_dport *dport = NULL;
> + struct cxl_port *port;
> + unsigned long index;
> +
> + if (!port_dev)
> + return;
> +
> + port = to_cxl_port(port_dev);
> + if (port->uport_dev && dev_is_pci(port->uport_dev))
> + cb(port->uport_dev, userdata);
> +
> + xa_for_each(&port->dports, index, dport)
> + {
> + struct device *child_port_dev __free(put_device) =
> + bus_find_device(&cxl_bus_type, &port->dev, dport->dport_dev,
> + match_port_by_parent_dport);
> +
> + cb(dport->dport_dev, userdata);
> +
> + cxl_walk_port(child_port_dev, cxl_report_error_detected, userdata);
> + }
> +
> + if (is_cxl_endpoint(port))
> + cb(port->uport_dev->parent, userdata);
> +}
> +
> static void cxl_do_recovery(struct device *dev)
> {
> + pci_ers_result_t status = PCI_ERS_RESULT_CAN_RECOVER;
> + struct pci_dev *pdev = to_pci_dev(dev);
> + struct cxl_port *port = NULL;
> +
> + if ((pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT) ||
> + (pci_pcie_type(pdev) == PCI_EXP_TYPE_DOWNSTREAM)) {
> + struct cxl_dport *dport;
> + struct cxl_port *rp_port __free(put_cxl_port) = find_cxl_port(&pdev->dev, &dport);
> +
> + port = rp_port;
> +
> + } else if (pci_pcie_type(pdev) == PCI_EXP_TYPE_UPSTREAM) {
> + struct cxl_port *us_port __free(put_cxl_port) = find_cxl_port_by_uport(&pdev->dev);
> +
> + port = us_port;
> +
> + } else if ((pci_pcie_type(pdev) == PCI_EXP_TYPE_ENDPOINT) ||
> + (pci_pcie_type(pdev) == PCI_EXP_TYPE_RC_END)) {
> + struct cxl_dev_state *cxlds;
> +
> + if (!cxl_pci_drv_bound(pdev))
> + return;
> +
> + cxlds = pci_get_drvdata(pdev);
> + port = cxlds->cxlmd->endpoint;
> + }
> +
> + if (!port) {
> + dev_err(dev, "Failed to find the CXL device\n");
> + return;
> + }
> +
> + cxl_walk_port(&port->dev, cxl_report_error_detected, &status);
> + if (status == PCI_ERS_RESULT_PANIC)
> + panic("CXL cachemem error.");
> +
> + /*
> + * If we have native control of AER, clear error status in the device
> + * that detected the error. If the platform retained control of AER,
> + * it is responsible for clearing this status. In that case, the
> + * signaling device may not even be visible to the OS.
> + */
> + if (cxl_error_is_native(pdev)) {
> + pcie_clear_device_status(pdev);
> + pci_aer_clear_nonfatal_status(pdev);
> + pci_aer_clear_fatal_status(pdev);
> + }
> }
>
> static void cxl_handle_cor_ras(struct device *dev, u64 serial, void __iomem *ras_base)
Powered by blists - more mailing lists