[PATCH 1/2] PCI: Add pci=noaer_recovery kernel boot option

[Yury Murashka <yurypm@arista.com>]

AER error recovery is part of the AER error handling subsystem in the
Linux kernel. On large modular systems with a complex PCIe tree, AER
recovery could cause unexpected behavior and side effects. Sometimes it
would be nice to have the option to keep the system in an unmodified
state and be able to handle PCIe errors from userspace.

Add pci=noaer_recovery kernel boot option to disable AER error recovery
when an uncorrectable error is reported. When this option is set, the
error status bits are still cleared, but no recovery actions are taken.

Signed-off-by: Yury Murashka <yurypm@arista.com>
---
 Documentation/admin-guide/kernel-parameters.txt |  4 ++++
 drivers/pci/pci.c                               |  2 ++
 drivers/pci/pci.h                               |  2 ++
 drivers/pci/pcie/err.c                          | 15 +++++++++++++++
 4 files changed, 23 insertions(+)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 97007f4f69d4..cfec12d37677 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -5068,6 +5068,10 @@ Kernel parameters
 		noaer		[PCIE] If the PCIEAER kernel config parameter is
 				enabled, this kernel boot option can be used to
 				disable the use of PCIE advanced error reporting.
+		noaer_recovery	[PCIE] If the PCIEAER kernel config parameter is
+				enabled, this kernel boot option can be used to
+				disable AER error recovery when an uncorrectable
+				error is reported.
 		nodomains	[PCI] Disable support for multiple PCI
 				root domains (aka PCI segments, in ACPI-speak).
 		nommconf	[X86] Disable use of MMCONFIG for PCI
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index d34266651ad0..1f71f9c773c4 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -6725,6 +6725,8 @@ static int __init pci_setup(char *str)
 				pcie_ats_disabled = true;
 			} else if (!strcmp(str, "noaer")) {
 				pci_no_aer();
+			} else if (!strcmp(str, "noaer_recovery")) {
+				pci_no_aer_recovery();
 			} else if (!strcmp(str, "earlydump")) {
 				pci_early_dump = true;
 			} else if (!strncmp(str, "realloc=", 8)) {
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 4a14f88e543a..7a79df0ae712 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -1283,6 +1283,7 @@ static inline void of_pci_remove_host_bridge_node(struct pci_host_bridge *bridge
 
 #ifdef CONFIG_PCIEAER
 void pci_no_aer(void);
+void pci_no_aer_recovery(void);
 void pci_aer_init(struct pci_dev *dev);
 void pci_aer_exit(struct pci_dev *dev);
 extern const struct attribute_group aer_stats_attr_group;
@@ -1294,6 +1295,7 @@ void pci_save_aer_state(struct pci_dev *dev);
 void pci_restore_aer_state(struct pci_dev *dev);
 #else
 static inline void pci_no_aer(void) { }
+static inline void pci_no_aer_recovery(void) { }
 static inline void pci_aer_init(struct pci_dev *d) { }
 static inline void pci_aer_exit(struct pci_dev *d) { }
 static inline void pci_aer_clear_fatal_status(struct pci_dev *dev) { }
diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index bebe4bc111d7..c022cfd85b93 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -21,6 +21,13 @@
 #include "portdrv.h"
 #include "../pci.h"
 
+static int pcie_aer_recovery_disable;
+
+void pci_no_aer_recovery(void)
+{
+	pcie_aer_recovery_disable = 1;
+}
+
 static pci_ers_result_t merge_result(enum pci_ers_result orig,
 				  enum pci_ers_result new)
 {
@@ -216,6 +223,14 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
 	pci_ers_result_t status = PCI_ERS_RESULT_CAN_RECOVER;
 	struct pci_host_bridge *host = pci_find_host_bridge(dev->bus);
 
+	if (pcie_aer_recovery_disable) {
+		if (host->native_aer || pcie_ports_native) {
+			pcie_clear_device_status(dev);
+			pci_aer_clear_nonfatal_status(dev);
+		}
+		return status;
+	}
+
 	/*
 	 * If the error was detected by a Root Port, Downstream Port, RCEC,
 	 * or RCiEP, recovery runs on the device itself.  For Ports, that
-- 
2.51.0