[v3,2/2] cxl/pci: Process CPER events

Commit Message

Ira Weiny April 26, 2024, 8:03 p.m. UTC

If the firmware has configured CXL event support to be firmware first
the OS will receive those events through CPER records.  The CXL layer has
unique DPA to HPA knowledge and existing event trace parsing in
place.[0]

Add a CXL CPER work item and register it with the GHES code to process
CPER events.

[0]
Link: https://lore.kernel.org/all/[e-mail]/

Signed-off-by: Ira Weiny <[e-mail]>

---
Changes:
[djbw: declare work struct here]
---
 drivers/cxl/pci.c | 71 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 70 insertions(+), 1 deletion(-)

Comments

Dan Williams April 26, 2024, 11:52 p.m. UTC | #1

Ira Weiny wrote:
> If the firmware has configured CXL event support to be firmware first
> the OS will receive those events through CPER records.  The CXL layer has
> unique DPA to HPA knowledge and existing event trace parsing in
> place.[0]
> 
> Add a CXL CPER work item and register it with the GHES code to process
> CPER events.
> 
> [0]
> Link: https://lore.kernel.org/all/[e-mail]/

Link: http://lore.kernel.org/r/[e-mail] [0]

Otherwise, looks good,

Reviewed-by: Dan Williams <[e-mail]>

Patch

diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
index 2ff361e756d6..74876c9835e8 100644
--- a/drivers/cxl/pci.c
+++ b/drivers/cxl/pci.c
@@ -974,6 +974,75 @@  static struct pci_driver cxl_pci_driver = {
 	},
 };
 
-module_pci_driver(cxl_pci_driver);
+#define CXL_EVENT_HDR_FLAGS_REC_SEVERITY GENMASK(1, 0)
+static void cxl_handle_cper_event(enum cxl_event_type ev_type,
+				  struct cxl_cper_event_rec *rec)
+{
+	struct cper_cxl_event_devid *device_id = &rec->hdr.device_id;
+	struct pci_dev *pdev __free(pci_dev_put) = NULL;
+	enum cxl_event_log_type log_type;
+	struct cxl_dev_state *cxlds;
+	unsigned int devfn;
+	u32 hdr_flags;
+
+	pr_debug("CPER event %d for device %u:%u:%u.%u\n", ev_type,
+		 device_id->segment_num, device_id->bus_num,
+		 device_id->device_num, device_id->func_num);
+
+	devfn = PCI_DEVFN(device_id->device_num, device_id->func_num);
+	pdev = pci_get_domain_bus_and_slot(device_id->segment_num,
+					   device_id->bus_num, devfn);
+	if (!pdev)
+		return;
+
+	guard(device)(&pdev->dev);
+	if (pdev->driver != &cxl_pci_driver)
+		return;
+
+	cxlds = pci_get_drvdata(pdev);
+	if (!cxlds)
+		return;
+
+	/* Fabricate a log type */
+	hdr_flags = get_unaligned_le24(rec->event.generic.hdr.flags);
+	log_type = FIELD_GET(CXL_EVENT_HDR_FLAGS_REC_SEVERITY, hdr_flags);
+
+	cxl_event_trace_record(cxlds->cxlmd, log_type, ev_type,
+			       &uuid_null, &rec->event);
+}
+
+static void cxl_cper_work_fn(struct work_struct *work)
+{
+	struct cxl_cper_work_data wd;
+
+	while (cxl_cper_kfifo_get(&wd))
+		cxl_handle_cper_event(wd.event_type, &wd.rec);
+}
+static DECLARE_WORK(cxl_cper_work, cxl_cper_work_fn);
+
+static int __init cxl_pci_driver_init(void)
+{
+	int rc;
+
+	rc = pci_register_driver(&cxl_pci_driver);
+	if (rc)
+		return rc;
+
+	rc = cxl_cper_register_work(&cxl_cper_work);
+	if (rc)
+		pci_unregister_driver(&cxl_pci_driver);
+
+	return rc;
+}
+
+static void __exit cxl_pci_driver_exit(void)
+{
+	cxl_cper_unregister_work(&cxl_cper_work);
+	cancel_work_sync(&cxl_cper_work);
+	pci_unregister_driver(&cxl_pci_driver);
+}
+
+module_init(cxl_pci_driver_init);
+module_exit(cxl_pci_driver_exit);
 MODULE_LICENSE("GPL v2");
 MODULE_IMPORT_NS(CXL);