PCI/AER: Add kernel.aer_print_skip_mask to control aer log

Commit Message

Bijie Xu Jan. 8, 2025, 7:57 a.m. UTC

Sometimes certain PCIE devices installed on some servers occasionally
produce large number of AER correctable error logs, which is quite
annoying. Add this sysctl parameter kernel.aer_print_skip_mask to
skip printing AER errors of certain severity.

The AER severity can be 0(NONFATAL), 1(FATAL), 2(CORRECTABLE). The 3
low bits of the mask are used to skip these 3 severities. Set bit 0
can skip printing NONFATAL AER errors, and set bit 1 can skip printing
FATAL AER errors, set bit 2 can skip printing CORRECTABLE AER errors.
And multiple bits can be set to skip multiple severities.

Signed-off-by: Bijie Xu <[e-mail]>
---
 drivers/pci/pcie/aer.c | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

Patch

diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 80c5ba8d8296..b46973526bcf 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -698,6 +698,7 @@  static void __aer_print_error(struct pci_dev *dev,
 	pci_dev_aer_stats_incr(dev, info);
 }
 
+unsigned int aer_print_skip_mask __read_mostly;
 void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
 {
 	int layer, agent;
@@ -710,6 +711,9 @@  void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
 		goto out;
 	}
 
+	if ((1 << info->severity) & aer_print_skip_mask)
+		goto out;
+
 	layer = AER_GET_LAYER_ERROR(info->severity, info->status);
 	agent = AER_GET_AGENT(info->severity, info->status);
 
@@ -1596,3 +1600,22 @@  int __init pcie_aer_init(void)
 		return -ENXIO;
 	return pcie_port_service_register(&aerdriver);
 }
+
+static const struct ctl_table aer_print_skip_mask_sysctls[] = {
+	{
+		.procname       = "aer_print_skip_mask",
+		.data           = &aer_print_skip_mask,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = &proc_douintvec,
+	},
+	{}
+};
+
+static int __init aer_print_skip_mask_sysctl_init(void)
+{
+	register_sysctl_init("kernel", aer_print_skip_mask_sysctls);
+	return 0;
+}
+
+late_initcall(aer_print_skip_mask_sysctl_init);