From: Jon Pan-Doh <pan...@google.com>
Allow userspace to read/write log ratelimits per device (including
enable/disable). Create aer/ sysfs directory to store them and any
future aer configs.
Update AER sysfs ABI filename to reflect the broader scope of AER sysfs
attributes (e.g. stats and ratelimits).
Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats ->
sysfs-bus-pci-devices-aer
Tested using aer-inject[1]. Configured correctable log ratelimit to 5.
Sent 6 AER errors. Observed 5 errors logged while AER stats
(cat /sys/bus/pci/devices/<dev>/aer_dev_correctable) shows 6.
Disabled ratelimiting and sent 6 more AER errors. Observed all 6 errors
logged and accounted in AER stats (12 total errors).
[1] https://git.kernel.org/pub/scm/linux/kernel/git/gong.chen/aer-inject.git
Signed-off-by: Karolina Stolarek <karolina.stola...@oracle.com>
Signed-off-by: Jon Pan-Doh <pan...@google.com>
Signed-off-by: Bjorn Helgaas <bhelg...@google.com>
Acked-by: Paul E. McKenney <paul...@kernel.org>
---
...es-aer_stats => sysfs-bus-pci-devices-aer} | 34 +++++++
Documentation/PCI/pcieaer-howto.rst | 5 +-
drivers/pci/pci-sysfs.c | 1 +
drivers/pci/pci.h | 1 +
drivers/pci/pcie/aer.c | 99 +++++++++++++++++++
5 files changed, 139 insertions(+), 1 deletion(-)
rename Documentation/ABI/testing/{sysfs-bus-pci-devices-aer_stats =>
sysfs-bus-pci-devices-aer} (77%)
diff --git a/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats
b/Documentation/ABI/testing/sysfs-bus-pci-devices-aer
similarity index 77%
rename from Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats
rename to Documentation/ABI/testing/sysfs-bus-pci-devices-aer
index d1f67bb81d5d..771204197b71 100644
--- a/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats
+++ b/Documentation/ABI/testing/sysfs-bus-pci-devices-aer
@@ -117,3 +117,37 @@ Date: July 2018
KernelVersion: 4.19.0
Contact: linux-...@vger.kernel.org, raja...@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-...@vger.kernel.org, pan...@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_burst_cor_log
+Date: March 2025
+KernelVersion: 6.15.0
+Contact: linux-...@vger.kernel.org, pan...@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_burst_uncor_log
+Date: March 2025
+KernelVersion: 6.15.0
+Contact: linux-...@vger.kernel.org, pan...@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.
diff --git a/Documentation/PCI/pcieaer-howto.rst
b/Documentation/PCI/pcieaer-howto.rst
index 896d2a232a90..043cdb3194be 100644
--- a/Documentation/PCI/pcieaer-howto.rst
+++ b/Documentation/PCI/pcieaer-howto.rst
@@ -96,12 +96,15 @@ 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.
+
AER Statistics / Counters
-------------------------
When PCIe AER errors are captured, the counters / statistics are also exposed
in the form of sysfs attributes which are documented at
-Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats
+Documentation/ABI/testing/sysfs-bus-pci-devices-aer.
Developer Guide
===============
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index c6cda56ca52c..278de99b00ce 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -1805,6 +1805,7 @@ 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,
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 65c466279ade..a3261e842d6d 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -963,6 +963,7 @@ 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);
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index c335e0bb9f51..42df5cb963b3 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -627,6 +627,105 @@ const struct attribute_group aer_stats_attr_group = {
.is_visible = aer_stats_attrs_are_visible,
};
+/*
+ * Ratelimit enable toggle
+ * 0: disabled with ratelimit.interval = 0
+ * 1: enabled with ratelimit.interval = nonzero
+ */
+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 enabled = pdev->aer_report->cor_log_ratelimit.interval != 0;
+
+ return sysfs_emit(buf, "%d\n", enabled);
+}
+
+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 (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ 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);
+
+#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); \
+} \
+ \
+ 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 (!capable(CAP_SYS_ADMIN)) \
+ return -EPERM; \
+ \
+ if (kstrtoint(buf, 0, &burst) < 0) \
+ return -EINVAL; \
+ \
+ pdev->aer_report->ratelimit.burst = burst; \
+ \
+ return count; \
+} \
+static DEVICE_ATTR_RW(name)
+
+aer_ratelimit_burst_attr(ratelimit_burst_cor_log, cor_log_ratelimit);
+aer_ratelimit_burst_attr(ratelimit_burst_uncor_log, uncor_log_ratelimit);
+
+static struct attribute *aer_attrs[] = {
+ &dev_attr_ratelimit_log_enable.attr,
+ &dev_attr_ratelimit_burst_cor_log.attr,
+ &dev_attr_ratelimit_burst_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,
+};
+
static void pci_dev_aer_stats_incr(struct pci_dev *pdev,
struct aer_err_info *info)
{
--
2.43.0
