[PATCH v8 20/20] PCI/AER: Add sysfs attributes for log ratelimits
Bjorn Helgaas
helgaas at kernel.org
Fri May 23 09:21:26 AEST 2025
From: Jon Pan-Doh <pandoh at 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.
The new sysfs files are:
/sys/bus/pci/devices/*/aer/correctable_ratelimit_burst
/sys/bus/pci/devices/*/aer/correctable_ratelimit_interval_ms
/sys/bus/pci/devices/*/aer/nonfatal_ratelimit_burst
/sys/bus/pci/devices/*/aer/nonfatal_ratelimit_interval_ms
The default values are ratelimit_burst=10, ratelimit_interval_ms=5000, so
if we try to emit more than 10 messages in a 5 second period, some are
suppressed.
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
[bhelgaas: note fatal errors are not ratelimited, "aer_report" ->
"aer_info", replace ratelimit_log_enable toggle with *_ratelimit_interval_ms]
Signed-off-by: Karolina Stolarek <karolina.stolarek at oracle.com>
Signed-off-by: Jon Pan-Doh <pandoh at google.com>
Signed-off-by: Bjorn Helgaas <bhelgaas at google.com>
Link: https://patch.msgid.link/20250520215047.1350603-18-helgaas@kernel.org
---
...es-aer_stats => sysfs-bus-pci-devices-aer} | 44 ++++++++
Documentation/PCI/pcieaer-howto.rst | 5 +-
drivers/pci/pci-sysfs.c | 1 +
drivers/pci/pci.h | 1 +
drivers/pci/pcie/aer.c | 105 ++++++++++++++++++
5 files changed, 155 insertions(+), 1 deletion(-)
rename Documentation/ABI/testing/{sysfs-bus-pci-devices-aer_stats => sysfs-bus-pci-devices-aer} (72%)
diff --git a/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats b/Documentation/ABI/testing/sysfs-bus-pci-devices-aer
similarity index 72%
rename from Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats
rename to Documentation/ABI/testing/sysfs-bus-pci-devices-aer
index d1f67bb81d5d..5ed284523956 100644
--- a/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats
+++ b/Documentation/ABI/testing/sysfs-bus-pci-devices-aer
@@ -117,3 +117,47 @@ Date: July 2018
KernelVersion: 4.19.0
Contact: linux-pci at vger.kernel.org, rajatja at 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/correctable_ratelimit_interval_ms
+Date: May 2025
+KernelVersion: 6.16.0
+Contact: linux-pci at vger.kernel.org
+Description: Writing 0 disables AER correctable error log ratelimiting.
+ Writing a positive value sets the ratelimit interval in ms.
+ Default is DEFAULT_RATELIMIT_INTERVAL (5000 ms).
+
+What: /sys/bus/pci/devices/<dev>/aer/correctable_ratelimit_burst
+Date: May 2025
+KernelVersion: 6.16.0
+Contact: linux-pci at vger.kernel.org
+Description: Ratelimit burst for correctable error logs. Writing a value
+ changes the number of errors (burst) allowed per interval
+ before ratelimiting. Reading gets the current ratelimit
+ burst. Default is DEFAULT_RATELIMIT_BURST (10).
+
+What: /sys/bus/pci/devices/<dev>/aer/nonfatal_ratelimit_interval_ms
+Date: May 2025
+KernelVersion: 6.16.0
+Contact: linux-pci at vger.kernel.org
+Description: Writing 0 disables AER non-fatal uncorrectable error log
+ ratelimiting. Writing a positive value sets the ratelimit
+ interval in ms. Default is DEFAULT_RATELIMIT_INTERVAL
+ (5000 ms).
+
+What: /sys/bus/pci/devices/<dev>/aer/nonfatal_ratelimit_burst
+Date: May 2025
+KernelVersion: 6.16.0
+Contact: linux-pci at vger.kernel.org
+Description: Ratelimit burst for non-fatal uncorrectable error logs.
+ Writing a value changes the number of errors (burst)
+ allowed per interval before ratelimiting. Reading gets the
+ current ratelimit burst. Default is DEFAULT_RATELIMIT_BURST
+ (10).
diff --git a/Documentation/PCI/pcieaer-howto.rst b/Documentation/PCI/pcieaer-howto.rst
index 6fb31516fff1..4b71e2f43ca7 100644
--- a/Documentation/PCI/pcieaer-howto.rst
+++ b/Documentation/PCI/pcieaer-howto.rst
@@ -97,12 +97,15 @@ DPC errors, are not ratelimited.
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 3023c68fe485..eca2812cfd25 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -965,6 +965,7 @@ 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 ebac126144fc..6c331695af58 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -627,6 +627,111 @@ const struct attribute_group aer_stats_attr_group = {
.is_visible = aer_stats_attrs_are_visible,
};
+/*
+ * Ratelimit interval
+ * <=0: disabled with ratelimit.interval = 0
+ * >0: enabled with ratelimit.interval in ms
+ */
+#define aer_ratelimit_interval_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_info->ratelimit.interval); \
+ } \
+ \
+ 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 interval; \
+ \
+ if (!capable(CAP_SYS_ADMIN)) \
+ return -EPERM; \
+ \
+ if (kstrtoint(buf, 0, &interval) < 0) \
+ return -EINVAL; \
+ \
+ if (interval <= 0) \
+ interval = 0; \
+ else \
+ interval = msecs_to_jiffies(interval); \
+ \
+ pdev->aer_info->ratelimit.interval = interval; \
+ \
+ return count; \
+ } \
+ static DEVICE_ATTR_RW(name);
+
+#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_info->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_info->ratelimit.burst = burst; \
+ \
+ return count; \
+ } \
+ static DEVICE_ATTR_RW(name);
+
+#define aer_ratelimit_attrs(name) \
+ aer_ratelimit_interval_attr(name##_ratelimit_interval_ms, \
+ name##_ratelimit) \
+ aer_ratelimit_burst_attr(name##_ratelimit_burst, \
+ name##_ratelimit)
+
+aer_ratelimit_attrs(correctable)
+aer_ratelimit_attrs(nonfatal)
+
+static struct attribute *aer_attrs[] = {
+ &dev_attr_correctable_ratelimit_interval_ms.attr,
+ &dev_attr_correctable_ratelimit_burst.attr,
+ &dev_attr_nonfatal_ratelimit_interval_ms.attr,
+ &dev_attr_nonfatal_ratelimit_burst.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_info)
+ 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
More information about the Linuxppc-dev
mailing list