On 6/3/25 10:22 AM, Terry Bowman wrote:
> During CXL device cleanup the CXL PCIe Port device interrupts remain
> enabled. This potentially allows unnecessary interrupt processing on
> behalf of the CXL errors while the device is destroyed.
>
> Disable CXL protocol errors by setting the CXL devices' AER mask register.
>
> Introduce pci_aer_mask_internal_errors() similar to pci_aer_unmask_internal_errors().
>
> Introduce cxl_mask_prot_interrupts() to call pci_aer_mask_internal_errors().
> Add calls to cxl_mask_prot_interrupts() within CXL Port teardown for CXL
> Root Ports, CXL Downstream Switch Ports, CXL Upstream Switch Ports, and CXL
> Endpoints. Follow the same "bottom-up" approach used during CXL Port
> teardown.
>
> Implement cxl_mask_prot_interrupts() in a header file to avoid introducing
> Kconfig ifdefs in cxl/core/port.c.
>
> Signed-off-by: Terry Bowman <terry.bowman@xxxxxxx>
Reviewed-by: Dave Jiang <dave.jiang@xxxxxxxxx>
> ---
> drivers/cxl/core/port.c | 6 ++++++
> drivers/cxl/cxl.h | 8 ++++++++
> drivers/pci/pcie/aer.c | 21 +++++++++++++++++++++
> include/linux/aer.h | 1 +
> 4 files changed, 36 insertions(+)
>
> diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
> index 07b9bb0f601f..6aaaad002a7f 100644
> --- a/drivers/cxl/core/port.c
> +++ b/drivers/cxl/core/port.c
> @@ -1433,6 +1433,9 @@ EXPORT_SYMBOL_NS_GPL(cxl_endpoint_autoremove, "CXL");
> */
> static void delete_switch_port(struct cxl_port *port)
> {
> + cxl_mask_prot_interrupts(port->uport_dev);
> + cxl_mask_prot_interrupts(port->parent_dport->dport_dev);
> +
> devm_release_action(port->dev.parent, cxl_unlink_parent_dport, port);
> devm_release_action(port->dev.parent, cxl_unlink_uport, port);
> devm_release_action(port->dev.parent, unregister_port, port);
> @@ -1446,6 +1449,7 @@ static void reap_dports(struct cxl_port *port)
> device_lock_assert(&port->dev);
>
> xa_for_each(&port->dports, index, dport) {
> + cxl_mask_prot_interrupts(dport->dport_dev);
> devm_release_action(&port->dev, cxl_dport_unlink, dport);
> devm_release_action(&port->dev, cxl_dport_remove, dport);
> devm_kfree(&port->dev, dport);
> @@ -1476,6 +1480,8 @@ static void cxl_detach_ep(void *data)
> {
> struct cxl_memdev *cxlmd = data;
>
> + cxl_mask_prot_interrupts(cxlmd->cxlds->dev);
> +
> for (int i = cxlmd->depth - 1; i >= 1; i--) {
> struct cxl_port *port, *parent_port;
> struct detach_ctx ctx = {
> diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
> index 2c1c00466a25..2753db3d473e 100644
> --- a/drivers/cxl/cxl.h
> +++ b/drivers/cxl/cxl.h
> @@ -12,6 +12,7 @@
> #include <linux/node.h>
> #include <linux/io.h>
> #include <linux/pci.h>
> +#include <linux/aer.h>
>
> extern const struct nvdimm_security_ops *cxl_security_ops;
>
> @@ -771,9 +772,16 @@ struct cxl_dport *devm_cxl_add_rch_dport(struct cxl_port *port,
> #ifdef CONFIG_PCIEAER_CXL
> void cxl_setup_parent_dport(struct device *host, struct cxl_dport *dport);
> void cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device *host);
> +static inline void cxl_mask_prot_interrupts(struct device *dev)
> +{
> + struct pci_dev *pdev __free(pci_dev_put) = pci_dev_get(to_pci_dev(dev));
> +
> + pci_aer_mask_internal_errors(pdev);
> +}
> #else
> static inline void cxl_dport_init_ras_reporting(struct cxl_dport *dport,
> struct device *host) { }
> +static inline void cxl_mask_prot_interrupts(struct device *dev) { }
> #endif
>
> struct cxl_decoder *to_cxl_decoder(struct device *dev);
> diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
> index 2d202ad1453a..69230cf87d79 100644
> --- a/drivers/pci/pcie/aer.c
> +++ b/drivers/pci/pcie/aer.c
> @@ -979,6 +979,27 @@ void pci_aer_unmask_internal_errors(struct pci_dev *dev)
> }
> EXPORT_SYMBOL_NS_GPL(pci_aer_unmask_internal_errors, "CXL");
>
> +/**
> + * pci_aer_mask_internal_errors - mask internal errors
> + * @dev: pointer to the pcie_dev data structure
> + *
> + * Masks internal errors in the Uncorrectable and Correctable Error
> + * Mask registers.
> + *
> + * Note: AER must be enabled and supported by the device which must be
> + * checked in advance, e.g. with pcie_aer_is_native().
> + */
> +void pci_aer_mask_internal_errors(struct pci_dev *dev)
> +{
> + int aer = dev->aer_cap;
> +
> + pci_clear_and_set_config_dword(dev, aer + PCI_ERR_UNCOR_MASK,
> + 0, PCI_ERR_UNC_INTN);
> + pci_clear_and_set_config_dword(dev, aer + PCI_ERR_COR_MASK,
> + 0, PCI_ERR_COR_INTERNAL);
> +}
> +EXPORT_SYMBOL_NS_GPL(pci_aer_mask_internal_errors, "CXL");
> +
> static bool is_cxl_mem_dev(struct pci_dev *dev)
> {
> /*
> diff --git a/include/linux/aer.h b/include/linux/aer.h
> index 74600e75705f..41167ad3797a 100644
> --- a/include/linux/aer.h
> +++ b/include/linux/aer.h
> @@ -108,5 +108,6 @@ int cper_severity_to_aer(int cper_severity);
> void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn,
> int severity, struct aer_capability_regs *aer_regs);
> void pci_aer_unmask_internal_errors(struct pci_dev *dev);
> +void pci_aer_mask_internal_errors(struct pci_dev *dev);
> #endif //_AER_H_
>
