On Wed, 19 Mar 2025, Jon Pan-Doh wrote: > Allow userspace to read/write log ratelimits per device (including > enable/disable). Create aer/ sysfs directory to store them and any > future aer configs. > > 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.stolarek@xxxxxxxxxx> > Signed-off-by: Jon Pan-Doh <pandoh@xxxxxxxxxx> > --- > .../testing/sysfs-bus-pci-devices-aer_stats | 34 +++++++ > Documentation/PCI/pcieaer-howto.rst | 3 + > drivers/pci/pci-sysfs.c | 1 + > drivers/pci/pci.h | 1 + > drivers/pci/pcie/aer.c | 93 +++++++++++++++++++ > 5 files changed, 132 insertions(+) > > diff --git a/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats b/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats > index d1f67bb81d5d..4561653fdbde 100644 > --- a/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats > +++ b/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats > @@ -117,3 +117,37 @@ Date: July 2018 > KernelVersion: 4.19.0 > Contact: linux-pci@xxxxxxxxxxxxxxx, rajatja@xxxxxxxxxx > 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@xxxxxxxxxxxxxxx, pandoh@xxxxxxxxxx > +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@xxxxxxxxxxxxxxx, pandoh@xxxxxxxxxx > +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@xxxxxxxxxxxxxxx, pandoh@xxxxxxxxxx > +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..b45a2e18d1cf 100644 > --- a/Documentation/PCI/pcieaer-howto.rst > +++ b/Documentation/PCI/pcieaer-howto.rst > @@ -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. Why does the next patch immediately modify this? A patch series should try to avoid back and forth changes like that. -- i. > AER Statistics / Counters > ------------------------- > > diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c > index b46ce1a2c554..16de3093294e 100644 > --- a/drivers/pci/pci-sysfs.c > +++ b/drivers/pci/pci-sysfs.c > @@ -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, > diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h > index 9d63d32f041c..34633fe12201 100644 > --- a/drivers/pci/pci.h > +++ b/drivers/pci/pci.h > @@ -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); > diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c > index 0bd20c4993d4..13227a94c9f9 100644 > --- a/drivers/pci/pcie/aer.c > +++ b/drivers/pci/pcie/aer.c > @@ -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; >
