Re: [PATCH v8 06/16] CXL/PCI: Introduce CXL uncorrectable protocol error 'recovery'

[Bowman, Terry]

On 4/23/2025 11:35 AM, Jonathan Cameron wrote:
> On Wed, 26 Mar 2025 20:47:07 -0500
> Terry Bowman <terry.bowman@xxxxxxx> wrote:
>
>> Create cxl_do_recovery() to provide uncorrectable protocol error (UCE)
>> handling. Follow similar design as found in PCIe error driver,
>> pcie_do_recovery(). One difference is that cxl_do_recovery() will treat all
>> UCEs as fatal with a kernel panic. This is to prevent corruption on CXL
>> memory.
>>
>> Copy the PCIe error handlers merge_result(). Introduce PCI_ERS_RESULT_PANIC
>> and add support in the merge_result() routine.
>>
>> Copy pci_walk_bridge() to cxl_walk_bridge(). Make a change to walk the
>> first device in all cases.
>>
>> Copy report_error_detected() to cxl_report_error_detected(). Update this
>> function to populate the CXL error information structure, 'struct
>> cxl_prot_error_info', before calling the device error handler.
>>
>> Call panic() to halt the system in the case of uncorrectable errors (UCE)
>> in cxl_do_recovery(). Export pci_aer_clear_fatal_status() for CXL to use
>> if a UCE is not found. In this case the AER status must be cleared and
>> uses pci_aer_clear_fatal_status().
>>
>> Signed-off-by: Terry Bowman <terry.bowman@xxxxxxx>
>> ---
>>  drivers/cxl/core/ras.c | 92 +++++++++++++++++++++++++++++++++++++++++-
>>  drivers/pci/pci.h      |  2 -
>>  include/linux/pci.h    |  5 +++
>>  3 files changed, 96 insertions(+), 3 deletions(-)
>>
>> diff --git a/drivers/cxl/core/ras.c b/drivers/cxl/core/ras.c
>> index eca8f11a05d9..1f94fc08e72b 100644
>> --- a/drivers/cxl/core/ras.c
>> +++ b/drivers/cxl/core/ras.c
>> @@ -141,7 +141,97 @@ int cxl_create_prot_err_info(struct pci_dev *_pdev, int severity,
>>  }
>>  EXPORT_SYMBOL_NS_GPL(cxl_create_prot_err_info, "CXL");
>>  
>> -static void cxl_do_recovery(struct pci_dev *pdev) { }
>> +
>> +static pci_ers_result_t merge_result(enum pci_ers_result orig,
> Rename perhaps to avoid confusion / grep clashed...
Ok. I'll rename to cxl_merge_results().
>> +				     enum pci_ers_result new)
>> +{
>> +	if (new == PCI_ERS_RESULT_PANIC)
>> +		return PCI_ERS_RESULT_PANIC;
>> +
>> +	if (new == PCI_ERS_RESULT_NO_AER_DRIVER)
>> +		return PCI_ERS_RESULT_NO_AER_DRIVER;
>> +
>> +	if (new == PCI_ERS_RESULT_NONE)
>> +		return orig;
>> +
>> +	switch (orig) {
>> +	case PCI_ERS_RESULT_CAN_RECOVER:
>> +	case PCI_ERS_RESULT_RECOVERED:
>> +		orig = new;
>> +		break;
>> +	case PCI_ERS_RESULT_DISCONNECT:
>> +		if (new == PCI_ERS_RESULT_NEED_RESET)
>> +			orig = PCI_ERS_RESULT_NEED_RESET;
>> +		break;
>> +	default:
>> +		break;
>> +	}
>> +
>> +	return orig;
>> +}
>> +
>> +static void cxl_walk_bridge(struct pci_dev *bridge,
>> +			    int (*cb)(struct pci_dev *, void *),
>> +			    void *userdata)
>> +{
>> +	if (cb(bridge, userdata))
>> +		return;
>> +
>> +	if (bridge->subordinate)
>> +		pci_walk_bus(bridge->subordinate, cb, userdata);
>> +}
>> +
> Trivial but seems there are two blank lines where one will do.
Ok

-Terry

>> +
>> +static int cxl_report_error_detected(struct pci_dev *pdev, void *data)
>> +{
>> +	struct cxl_driver *pdrv;
>> +	pci_ers_result_t vote, *result = data;
>> +	struct cxl_prot_error_info err_info = { 0 };
>> +	const struct cxl_error_handlers *cxl_err_handler;
>> +
>> +	if (cxl_create_prot_err_info(pdev, AER_FATAL, &err_info))
>> +		return 0;
>> +
>> +	struct device *dev __free(put_device) = get_device(err_info.dev);
>> +	if (!dev)
>> +		return 0;
>> +
>> +	pdrv = to_cxl_drv(dev->driver);
>> +	if (!pdrv || !pdrv->err_handler ||
>> +	    !pdrv->err_handler->error_detected)
>> +		return 0;
>> +
>> +	cxl_err_handler = pdrv->err_handler;
>> +	vote = cxl_err_handler->error_detected(dev, &err_info);
>> +
>> +	*result = merge_result(*result, vote);
>> +
>> +	return 0;
>> +}
>> +
>> +static void cxl_do_recovery(struct pci_dev *pdev)
>> +{
>> +	struct pci_host_bridge *host = pci_find_host_bridge(pdev->bus);
>> +	pci_ers_result_t status = PCI_ERS_RESULT_CAN_RECOVER;
>> +
>> +	cxl_walk_bridge(pdev, 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 (host->native_aer) {
>> +		pcie_clear_device_status(pdev);
>> +		pci_aer_clear_nonfatal_status(pdev);
>> +		pci_aer_clear_fatal_status(pdev);
>> +	}
>> +
>> +	pci_info(pdev, "CXL uncorrectable error.\n");
>> +}
>>  
>>  static int cxl_rch_handle_error_iter(struct pci_dev *pdev, void *data)
>>  {
>