acpi/ghes, cxl/pci: Process CXL CPER Protocol Errors

When PCIe AER is in FW-First, OS should process CXL Protocol errors from
CPER records. Introduce support for handling and logging CXL Protocol
errors.

The defined trace events cxl_aer_uncorrectable_error and
cxl_aer_correctable_error trace native CXL AER endpoint errors. Reuse them
to trace FW-First Protocol errors.

Since the CXL code is required to be called from process context and
GHES is in interrupt context, use workqueues for processing.

Similar to CXL CPER event handling, use kfifo to handle errors as it
simplifies queue processing by providing lock free fifo operations.

Add the ability for the CXL sub-system to register a workqueue to
process CXL CPER protocol errors.

[DJ: return cxl_cper_register_prot_err_work() directly in cxl_ras_init()]

Signed-off-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
Reviewed-by: Li Ming <ming.li@zohomail.com>
Reviewed-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Link: https://patch.msgid.link/20250310223839.31342-2-Smita.KoralahalliChannabasappa@amd.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>

1 files changed, 49 insertions, 0 deletions

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 4d725d988c43..289e365f84b2 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -674,6 +674,15 @@ static void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata,
 	schedule_work(&entry->work);
 }
 
+/* Room for 8 entries */
+#define CXL_CPER_PROT_ERR_FIFO_DEPTH 8
+static DEFINE_KFIFO(cxl_cper_prot_err_fifo, struct cxl_cper_prot_err_work_data,
+		    CXL_CPER_PROT_ERR_FIFO_DEPTH);
+
+/* Synchronize schedule_work() with cxl_cper_prot_err_work changes */
+static DEFINE_SPINLOCK(cxl_cper_prot_err_work_lock);
+struct work_struct *cxl_cper_prot_err_work;
+
 static void cxl_cper_post_prot_err(struct cxl_cper_sec_prot_err *prot_err,
 				   int severity)
 {
@@ -700,6 +709,11 @@ static void cxl_cper_post_prot_err(struct cxl_cper_sec_prot_err *prot_err,
 	if (!(prot_err->valid_bits & PROT_ERR_VALID_SERIAL_NUMBER))
 		pr_warn(FW_WARN "CXL CPER no device serial number\n");
 
+	guard(spinlock_irqsave)(&cxl_cper_prot_err_work_lock);
+
+	if (!cxl_cper_prot_err_work)
+		return;
+
 	switch (prot_err->agent_type) {
 	case RCD:
 	case DEVICE:
@@ -721,9 +735,44 @@ static void cxl_cper_post_prot_err(struct cxl_cper_sec_prot_err *prot_err,
 				   prot_err->agent_type);
 		return;
 	}
+
+	if (!kfifo_put(&cxl_cper_prot_err_fifo, wd)) {
+		pr_err_ratelimited("CXL CPER kfifo overflow\n");
+		return;
+	}
+
+	schedule_work(cxl_cper_prot_err_work);
 #endif
 }
 
+int cxl_cper_register_prot_err_work(struct work_struct *work)
+{
+	if (cxl_cper_prot_err_work)
+		return -EINVAL;
+
+	guard(spinlock)(&cxl_cper_prot_err_work_lock);
+	cxl_cper_prot_err_work = work;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_register_prot_err_work, "CXL");
+
+int cxl_cper_unregister_prot_err_work(struct work_struct *work)
+{
+	if (cxl_cper_prot_err_work != work)
+		return -EINVAL;
+
+	guard(spinlock)(&cxl_cper_prot_err_work_lock);
+	cxl_cper_prot_err_work = NULL;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_prot_err_work, "CXL");
+
+int cxl_cper_prot_err_kfifo_get(struct cxl_cper_prot_err_work_data *wd)
+{
+	return kfifo_get(&cxl_cper_prot_err_fifo, wd);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_prot_err_kfifo_get, "CXL");
+
 /* Room for 8 entries for each of the 4 event log queues */
 #define CXL_CPER_FIFO_DEPTH 32
 DEFINE_KFIFO(cxl_cper_fifo, struct cxl_cper_work_data, CXL_CPER_FIFO_DEPTH);