@@ -117,3 +117,37 @@ Date: July 2018
KernelVersion: 4.19.0
Contact: linux-pci@vger.kernel.org, rajatja@google.com
Description: Total number of ERR_NONFATAL messages reported to rootport.
+
+PCIe AER ratelimits
+-------------------
+
+These attributes show up under all the devices that are AER capable.
+They represent configurable ratelimits of logs per error type.
+
+See Documentation/PCI/pcieaer-howto.rst for more info on ratelimits.
+
+What: /sys/bus/pci/devices/<dev>/aer/ratelimit_log_enable
+Date: March 2025
+KernelVersion: 6.15.0
+Contact: linux-pci@vger.kernel.org, pandoh@google.com
+Description: Writing 1/0 enables/disables AER log ratelimiting. Reading
+ gets whether or not AER is currently enabled. Enabled by
+ default.
+
+What: /sys/bus/pci/devices/<dev>/aer/ratelimit_in_5secs_cor_log
+Date: March 2025
+KernelVersion: 6.15.0
+Contact: linux-pci@vger.kernel.org, pandoh@google.com
+Description: Ratelimit burst for correctable error logs. Writing a value
+ changes the number of errors (burst) allowed per interval
+ (5 second window) before ratelimiting. Reading gets the
+ current ratelimit burst.
+
+What: /sys/bus/pci/devices/<dev>/aer/ratelimit_in_5secs_uncor_log
+Date: March 2025
+KernelVersion: 6.15.0
+Contact: linux-pci@vger.kernel.org, pandoh@google.com
+Description: Ratelimit burst for uncorrectable error logs. Writing a
+ value changes the number of errors (burst) allowed per
+ interval (5 second window) before ratelimiting. Reading
+ gets the current ratelimit burst.
@@ -96,6 +96,9 @@ type (correctable vs. uncorrectable).
AER uses the default ratelimit of DEFAULT_RATELIMIT_BURST (10 events) over
DEFAULT_RATELIMIT_INTERVAL (5 seconds).
+Ratelimits are exposed in the form of sysfs attributes and configurable.
+See Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats.
+
AER Statistics / Counters
-------------------------
@@ -1801,6 +1801,7 @@ const struct attribute_group *pci_dev_attr_groups[] = {
&pcie_dev_attr_group,
#ifdef CONFIG_PCIEAER
&aer_stats_attr_group,
+ &aer_attr_group,
#endif
#ifdef CONFIG_PCIEASPM
&aspm_ctrl_attr_group,
@@ -889,6 +889,7 @@ void pci_no_aer(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;
+extern const struct attribute_group aer_attr_group;
void pci_aer_clear_fatal_status(struct pci_dev *dev);
int pci_aer_clear_status(struct pci_dev *dev);
int pci_aer_raw_clear_status(struct pci_dev *dev);
@@ -631,6 +631,99 @@ const struct attribute_group aer_stats_attr_group = {
.is_visible = aer_stats_attrs_are_visible,
};
+/*
+ * Ratelimit enable toggle uses interval value of
+ * 0: disabled
+ * DEFAULT_RATELIMIT_INTERVAL: enabled
+ */
+static ssize_t ratelimit_log_enable_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ bool enable = pdev->aer_report->cor_log_ratelimit.interval != 0;
+
+ return sysfs_emit(buf, "%d\n", enable);
+}
+
+static ssize_t ratelimit_log_enable_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ bool enable;
+ int interval;
+
+ if (kstrtobool(buf, &enable) < 0)
+ return -EINVAL;
+
+ if (enable)
+ interval = DEFAULT_RATELIMIT_INTERVAL;
+ else
+ interval = 0;
+
+ pdev->aer_report->cor_log_ratelimit.interval = interval;
+ pdev->aer_report->uncor_log_ratelimit.interval = interval;
+ return count;
+}
+static DEVICE_ATTR_RW(ratelimit_log_enable);
+
+/*
+ * Ratelimits are doubled as a given error produces 2 logs (root port
+ * and endpoint) that should be under same ratelimit.
+ */
+#define aer_ratelimit_burst_attr(name, ratelimit) \
+ static ssize_t \
+ name##_show(struct device *dev, struct device_attribute *attr, \
+ char *buf) \
+{ \
+ struct pci_dev *pdev = to_pci_dev(dev); \
+ return sysfs_emit(buf, "%d\n", \
+ pdev->aer_report->ratelimit.burst / 2); \
+} \
+ \
+ static ssize_t \
+ name##_store(struct device *dev, struct device_attribute *attr, \
+ const char *buf, size_t count) \
+{ \
+ struct pci_dev *pdev = to_pci_dev(dev); \
+ int burst; \
+ \
+ if (kstrtoint(buf, 0, &burst) < 0) \
+ return -EINVAL; \
+ \
+ pdev->aer_report->ratelimit.burst = burst * 2; \
+ return count; \
+} \
+static DEVICE_ATTR_RW(name)
+
+aer_ratelimit_burst_attr(ratelimit_in_5secs_cor_log, cor_log_ratelimit);
+aer_ratelimit_burst_attr(ratelimit_in_5secs_uncor_log, uncor_log_ratelimit);
+
+static struct attribute *aer_attrs[] = {
+ &dev_attr_ratelimit_log_enable.attr,
+ &dev_attr_ratelimit_in_5secs_cor_log.attr,
+ &dev_attr_ratelimit_in_5secs_uncor_log.attr,
+ NULL
+};
+
+static umode_t aer_attrs_are_visible(struct kobject *kobj,
+ struct attribute *a, int n)
+{
+ struct device *dev = kobj_to_dev(kobj);
+ struct pci_dev *pdev = to_pci_dev(dev);
+
+ if (!pdev->aer_report)
+ return 0;
+ return a->mode;
+}
+
+const struct attribute_group aer_attr_group = {
+ .name = "aer",
+ .attrs = aer_attrs,
+ .is_visible = aer_attrs_are_visible,
+};
+
void pci_dev_aer_stats_incr(struct pci_dev *pdev, struct aer_err_info *info)
{
unsigned long status = info->status & ~info->mask;