torvalds/linux
torvalds/linux
2
0
Fork 0
mirror of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2025-09-04 20:19:47 +08:00
Code

PCI/AER: Add sysfs attributes for log ratelimits

Browse Source 
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@oracle.com>
Signed-off-by: Jon Pan-Doh <pandoh@google.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Link: https://patch.msgid.link/20250522232339.1525671-21-helgaas@kernel.org
This commit is contained in:
Jon Pan-Doh 2025-05-22 18:21:26 -05:00 committed by Bjorn Helgaas
parent 24816cc298
commit b4fe7398de
5 changed files with 155 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

44
Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats → Documentation/ABI/testing/sysfs-bus-pci-devices-aer
View File

@ -117,3 +117,47 @@ 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/correctable_ratelimit_interval_ms
Date: May 2025
KernelVersion: 6.16.0
Contact: linux-pci@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@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@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@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).

5
Documentation/PCI/pcieaer-howto.rst
View File

@ -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
===============

1
drivers/pci/pci-sysfs.c
View File

@ -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,

1
drivers/pci/pci.h
View File

@ -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);

105
drivers/pci/pcie/aer.c
View File

@ -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)
{