[PATCH v3 06/10] ACPI: extlog: Defer CXL protocol error handling to avoid lock inversion

[Dave Jiang <dave.jiang@intel.com>]

sashiko-bot flagged an AB-BA deadlock between the PCI device_lock and
the MCE decoder chain rwsem.

extlog_print() calls cxl_cper_handle_prot_err() synchronously while the
MCE notifier chain rwsem is held, and that path takes the PCI device_lock
via guard(device)(). The probe path takes the locks in the opposite
order (device_lock held while mce_register_decode_chain() takes the
rwsem), so the two form an AB-BA deadlock.

ghes.c already avoids this by posting protocol errors to a kfifo and
handling them from a workqueue via cxl_cper_post_prot_err(). Export that
function and use it from acpi_extlog.c instead of calling
cxl_cper_handle_prot_err() directly.

Reported-by: sashiko-bot@kernel.org
Link: https://lore.kernel.org/linux-cxl/20260709165457.8BA181F000E9@smtp.kernel.org/
Assisted-by: Claude:claude-sonnet-4-6
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/acpi/acpi_extlog.c | 23 +++--------------------
 drivers/acpi/apei/ghes.c   |  5 +++--
 include/acpi/ghes.h        |  4 ++++
 3 files changed, 10 insertions(+), 22 deletions(-)

diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c
index 0c440d75d9a7..ae79d090de33 100644
--- a/drivers/acpi/acpi_extlog.c
+++ b/drivers/acpi/acpi_extlog.c
@@ -172,23 +172,6 @@ static void extlog_print_pcie(struct cper_sec_pcie *pcie_err,
 #endif
 }
 
-static void
-extlog_cxl_cper_handle_prot_err(struct cxl_cper_sec_prot_err *prot_err,
-				int severity, u32 len)
-{
-#ifdef ACPI_APEI_PCIEAER
-	struct cxl_cper_prot_err_work_data wd;
-
-	if (cxl_cper_sec_prot_err_valid(prot_err, len))
-		return;
-
-	if (cxl_cper_setup_prot_err_work_data(&wd, prot_err, severity))
-		return;
-
-	cxl_cper_handle_prot_err(&wd);
-#endif
-}
-
 static int extlog_print(struct notifier_block *nb, unsigned long val,
 			void *data)
 {
@@ -244,9 +227,9 @@ static int extlog_print(struct notifier_block *nb, unsigned long val,
 			struct cxl_cper_sec_prot_err *prot_err =
 				acpi_hest_get_payload(gdata);
 
-			extlog_cxl_cper_handle_prot_err(prot_err,
-							gdata->error_severity,
-							gdata->error_data_length);
+			cxl_cper_post_prot_err(prot_err,
+					       gdata->error_severity,
+					       gdata->error_data_length);
 		} else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
 			struct cper_sec_pcie *pcie_err = acpi_hest_get_payload(gdata);
 
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 17e4ef555292..b8dbd99da47e 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -752,8 +752,8 @@ static DEFINE_KFIFO(cxl_cper_prot_err_fifo, struct cxl_cper_prot_err_work_data,
 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, u32 len)
+void cxl_cper_post_prot_err(struct cxl_cper_sec_prot_err *prot_err,
+			    int severity, u32 len)
 {
 #ifdef CONFIG_ACPI_APEI_PCIEAER
 	struct cxl_cper_prot_err_work_data wd;
@@ -777,6 +777,7 @@ static void cxl_cper_post_prot_err(struct cxl_cper_sec_prot_err *prot_err,
 	schedule_work(cxl_cper_prot_err_work);
 #endif
 }
+EXPORT_SYMBOL_FOR_MODULES(cxl_cper_post_prot_err, "acpi_extlog");
 
 int cxl_cper_register_prot_err_work(struct work_struct *work)
 {
diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
index 8d7e5caef3f1..4dcbb2c30ea2 100644
--- a/include/acpi/ghes.h
+++ b/include/acpi/ghes.h
@@ -143,4 +143,8 @@ static inline int ghes_notify_sea(void) { return -ENOENT; }
 struct notifier_block;
 extern void ghes_register_report_chain(struct notifier_block *nb);
 extern void ghes_unregister_report_chain(struct notifier_block *nb);
+
+struct cxl_cper_sec_prot_err;
+void cxl_cper_post_prot_err(struct cxl_cper_sec_prot_err *prot_err,
+			    int severity, u32 len);
 #endif /* GHES_H */
-- 
2.55.0