Merge branch 'pci/aer'

- Initialize struct aer_err_info before using it to avoid depending on
  stack garbage (Bjorn Helgaas)

- Log the DPC Error Source ID only when it's actually valid (when ERR_FATAL
  or ERR_NONFATAL was received from a downstream device) and decode into
  bus/device/function (Bjorn Helgaas)

- Consolidate AER Error Source ID in one place for message consistency
  (Bjorn Helgaas)

- Update statistics and emit trace events early in AER logging paths,
  before any potential ratelimiting (Bjorn Helgaas)

- Determine AER log level once and save it so all related messages use the
  same level (Karolina Stolarek)

- Use KERN_WARNING, not KERN_ERR, when logging PCIe Correctable Errors.

- Ratelimit PCIe Correctable and Non-Fatal error logging, with sysfs
  controls on interval and burst count, to avoid flooding logs and RCU
  stall warnings (Jon Pan-Doh)

* pci/aer:
  PCI/ERR: Remove misleading TODO regarding kernel panic
  PCI/AER: Add sysfs attributes for log ratelimits
  PCI/AER: Add ratelimits to PCI AER Documentation
  PCI/AER: Ratelimit correctable and non-fatal error logging
  PCI/AER: Simplify add_error_device()
  PCI/AER: Convert aer_get_device_error_info(), aer_print_error() to index
  PCI/AER: Rename struct aer_stats to aer_info
  PCI/AER: Reduce pci_print_aer() correctable error level to KERN_WARNING
  PCI/ERR: Add printk level to pcie_print_tlp_log()
  PCI/AER: Check log level once and remember it
  PCI/AER: Trace error event before ratelimiting
  PCI/AER: Update statistics before ratelimiting
  PCI/AER: Simplify pci_print_aer()
  PCI/AER: Initialize aer_err_info before using it
  PCI/AER: Move aer_print_source() earlier in file
  PCI/AER: Rename aer_print_port_info() to aer_print_source()
  PCI/AER: Extract bus/dev/fn in aer_print_port_info() with PCI_BUS_NUM(), etc
  PCI/AER: Consolidate Error Source ID logging in aer_isr_one_error_type()
  PCI/AER: Factor COR/UNCOR error handling out from aer_isr_one_error()
  PCI/DPC: Log Error Source ID only when valid
  PCI/DPC: Initialize aer_err_info before using it

1 files changed, 9 insertions, 4 deletions

diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index b81e99cd4b62..eca2812cfd25 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -587,12 +587,15 @@ static inline bool pci_dev_test_and_set_removed(struct pci_dev *dev)
 
 struct aer_err_info {
 	struct pci_dev *dev[AER_MAX_MULTI_ERR_DEVICES];
+	int ratelimit_print[AER_MAX_MULTI_ERR_DEVICES];
 	int error_dev_num;
+	const char *level;		/* printk level */
 
 	unsigned int id:16;
 
 	unsigned int severity:2;	/* 0:NONFATAL | 1:FATAL | 2:COR */
-	unsigned int __pad1:5;
+	unsigned int root_ratelimit_print:1;	/* 0=skip, 1=print */
+	unsigned int __pad1:4;
 	unsigned int multi_error_valid:1;
 
 	unsigned int first_error:5;
@@ -604,15 +607,16 @@ struct aer_err_info {
 	struct pcie_tlp_log tlp;	/* TLP Header */
 };
 
-int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info);
-void aer_print_error(struct pci_dev *dev, struct aer_err_info *info);
+int aer_get_device_error_info(struct aer_err_info *info, int i);
+void aer_print_error(struct aer_err_info *info, int i);
 
 int pcie_read_tlp_log(struct pci_dev *dev, int where, int where2,
 		      unsigned int tlp_len, bool flit,
 		      struct pcie_tlp_log *log);
 unsigned int aer_tlp_log_len(struct pci_dev *dev, u32 aercc);
 void pcie_print_tlp_log(const struct pci_dev *dev,
-			const struct pcie_tlp_log *log, const char *pfx);
+			const struct pcie_tlp_log *log, const char *level,
+			const char *pfx);
 #endif	/* CONFIG_PCIEAER */
 
 #ifdef CONFIG_PCIEPORTBUS
@@ -961,6 +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);