Merge branch 'pci/aer'

  - Decode AER errors with names similar to "lspci" (Tyler Baicar)

  - Expose AER statistics in sysfs (Rajat Jain)

  - Clear AER status bits selectively based on the type of recovery (Oza
    Pawandeep)

  - Honor "pcie_ports=native" even if HEST sets FIRMWARE_FIRST (Alexandru
    Gagniuc)

  - Don't clear AER status bits if we're using the "Firmware-First"
    strategy where firmware owns the registers (Alexandru Gagniuc)

* pci/aer:
  PCI/AER: Don't clear AER bits if error handling is Firmware-First
  PCI/AER: Remove duplicate PCI_EXP_AER_FLAGS definition
  PCI/portdrv: Remove pcie_portdrv_err_handler.slot_reset
  PCI/AER: Clear device status bits during ERR_COR handling
  PCI/AER: Clear device status bits during ERR_FATAL and ERR_NONFATAL
  PCI/AER: Remove ERR_FATAL code from ERR_NONFATAL path
  PCI/AER: Factor out ERR_NONFATAL status bit clearing
  PCI/AER: Clear only ERR_NONFATAL bits during non-fatal recovery
  PCI/AER: Clear only ERR_FATAL status bits during fatal recovery
  PCI/AER: Honor "pcie_ports=native" even if HEST sets FIRMWARE_FIRST
  PCI/AER: Add sysfs attributes for rootport cumulative stats
  PCI/AER: Add sysfs attributes to provide AER stats and breakdown
  PCI/AER: Define aer_stats structure for AER capable devices
  PCI/AER: Move internal declarations to drivers/pci/pci.h
  PCI/AER: Adopt lspci names for AER error decoding
  PCI/AER: Expose internal API for obtaining AER information

# Conflicts:
#	drivers/pci/pci.h

Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats

+==========================
+PCIe Device AER statistics
+==========================
+These attributes show up under all the devices that are AER capable. These
+statistical counters indicate the errors "as seen/reported by the device".
+Note that this may mean that if an endpoint is causing problems, the AER
+counters may increment at its link partner (e.g. root port) because the
+errors may be "seen" / reported by the link partner and not the
+problematic endpoint itself (which may report all counters as 0 as it never
+saw any problems).
+
+Where:		/sys/bus/pci/devices/<dev>/aer_dev_correctable
+Date:		July 2018
+Kernel Version: 4.19.0
+Contact:	linux-pci@vger.kernel.org, rajatja@google.com
+Description:	List of correctable errors seen and reported by this
+		PCI device using ERR_COR. Note that since multiple errors may
+		be reported using a single ERR_COR message, thus
+		TOTAL_ERR_COR at the end of the file may not match the actual
+		total of all the errors in the file. Sample output:
+-------------------------------------------------------------------------
+localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_correctable
+Receiver Error 2
+Bad TLP 0
+Bad DLLP 0
+RELAY_NUM Rollover 0
+Replay Timer Timeout 0
+Advisory Non-Fatal 0
+Corrected Internal Error 0
+Header Log Overflow 0
+TOTAL_ERR_COR 2
+-------------------------------------------------------------------------
+
+Where:		/sys/bus/pci/devices/<dev>/aer_dev_fatal
+Date:		July 2018
+Kernel Version: 4.19.0
+Contact:	linux-pci@vger.kernel.org, rajatja@google.com
+Description:	List of uncorrectable fatal errors seen and reported by this
+		PCI device using ERR_FATAL. Note that since multiple errors may
+		be reported using a single ERR_FATAL message, thus
+		TOTAL_ERR_FATAL at the end of the file may not match the actual
+		total of all the errors in the file. Sample output:
+-------------------------------------------------------------------------
+localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_fatal
+Undefined 0
+Data Link Protocol 0
+Surprise Down Error 0
+Poisoned TLP 0
+Flow Control Protocol 0
+Completion Timeout 0
+Completer Abort 0
+Unexpected Completion 0
+Receiver Overflow 0
+Malformed TLP 0
+ECRC 0
+Unsupported Request 0
+ACS Violation 0
+Uncorrectable Internal Error 0
+MC Blocked TLP 0
+AtomicOp Egress Blocked 0
+TLP Prefix Blocked Error 0
+TOTAL_ERR_FATAL 0
+-------------------------------------------------------------------------
+
+Where:		/sys/bus/pci/devices/<dev>/aer_dev_nonfatal
+Date:		July 2018
+Kernel Version: 4.19.0
+Contact:	linux-pci@vger.kernel.org, rajatja@google.com
+Description:	List of uncorrectable nonfatal errors seen and reported by this
+		PCI device using ERR_NONFATAL. Note that since multiple errors
+		may be reported using a single ERR_FATAL message, thus
+		TOTAL_ERR_NONFATAL at the end of the file may not match the
+		actual total of all the errors in the file. Sample output:
+-------------------------------------------------------------------------
+localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_nonfatal
+Undefined 0
+Data Link Protocol 0
+Surprise Down Error 0
+Poisoned TLP 0
+Flow Control Protocol 0
+Completion Timeout 0
+Completer Abort 0
+Unexpected Completion 0
+Receiver Overflow 0
+Malformed TLP 0
+ECRC 0
+Unsupported Request 0
+ACS Violation 0
+Uncorrectable Internal Error 0
+MC Blocked TLP 0
+AtomicOp Egress Blocked 0
+TLP Prefix Blocked Error 0
+TOTAL_ERR_NONFATAL 0
+-------------------------------------------------------------------------
+
+============================
+PCIe Rootport AER statistics
+============================
+These attributes show up under only the rootports (or root complex event
+collectors) that are AER capable. These indicate the number of error messages as
+"reported to" the rootport. Please note that the rootports also transmit
+(internally) the ERR_* messages for errors seen by the internal rootport PCI
+device, so these counters include them and are thus cumulative of all the error
+messages on the PCI hierarchy originating at that root port.
+
+Where:		/sys/bus/pci/devices/<dev>/aer_stats/aer_rootport_total_err_cor
+Date:		July 2018
+Kernel Version: 4.19.0
+Contact:	linux-pci@vger.kernel.org, rajatja@google.com
+Description:	Total number of ERR_COR messages reported to rootport.
+
+Where:	    /sys/bus/pci/devices/<dev>/aer_stats/aer_rootport_total_err_fatal
+Date:		July 2018
+Kernel Version: 4.19.0
+Contact:	linux-pci@vger.kernel.org, rajatja@google.com
+Description:	Total number of ERR_FATAL messages reported to rootport.
+
+Where:	    /sys/bus/pci/devices/<dev>/aer_stats/aer_rootport_total_err_nonfatal
+Date:		July 2018
+Kernel Version: 4.19.0
+Contact:	linux-pci@vger.kernel.org, rajatja@google.com
+Description:	Total number of ERR_NONFATAL messages reported to rootport.

Documentation/PCI/pcieaer-howto.txt

@@ -73,6 +73,11 @@ In the example, 'Requester ID' means the ID of the device who sends
 the error message to root port. Pls. refer to pci express specs for
 other fields.
 
+2.4 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
 
 3. Developer Guide
 

drivers/pci/pci-sysfs.c

@@ -1746,6 +1746,9 @@ static const struct attribute_group *pci_dev_attr_groups[] = {
 #endif
 	&pci_bridge_attr_group,
 	&pcie_dev_attr_group,
+#ifdef CONFIG_PCIEAER
+	&aer_stats_attr_group,
+#endif
 	NULL,
 };
 

drivers/pci/pci.h

@@ -311,6 +311,34 @@ static inline bool pci_dev_is_added(const struct pci_dev *dev)
 	return test_bit(PCI_DEV_ADDED, &dev->priv_flags);
 }
 
+#ifdef CONFIG_PCIEAER
+#include <linux/aer.h>
+
+#define AER_MAX_MULTI_ERR_DEVICES	5	/* Not likely to have more */
+
+struct aer_err_info {
+	struct pci_dev *dev[AER_MAX_MULTI_ERR_DEVICES];
+	int error_dev_num;
+
+	unsigned int id:16;
+
+	unsigned int severity:2;	/* 0:NONFATAL | 1:FATAL | 2:COR */
+	unsigned int __pad1:5;
+	unsigned int multi_error_valid:1;
+
+	unsigned int first_error:5;
+	unsigned int __pad2:2;
+	unsigned int tlp_header_valid:1;
+
+	unsigned int status;		/* COR/UNCOR Error Status */
+	unsigned int mask;		/* COR/UNCOR Error Mask */
+	struct aer_header_log_regs 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);
+#endif	/* CONFIG_PCIEAER */
+
 #ifdef CONFIG_PCI_ATS
 void pci_restore_ats_state(struct pci_dev *dev);
 #else
@@ -467,4 +495,19 @@ static inline int devm_of_pci_get_host_bridge_resources(struct device *dev,
 }
 #endif
 
+#ifdef CONFIG_PCIEAER
+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;
+void pci_aer_clear_fatal_status(struct pci_dev *dev);
+void pci_aer_clear_device_status(struct pci_dev *dev);
+#else
+static inline void pci_no_aer(void) { }
+static inline int pci_aer_init(struct pci_dev *d) { return -ENODEV; }
+static inline void pci_aer_exit(struct pci_dev *d) { }
+static inline void pci_aer_clear_fatal_status(struct pci_dev *dev) { }
+static inline void pci_aer_clear_device_status(struct pci_dev *dev) { }
+#endif
+
 #endif /* DRIVERS_PCI_H */

drivers/pci/pcie/err.c

@@ -252,6 +252,7 @@ static pci_ers_result_t broadcast_error_message(struct pci_dev *dev,
 			dev->error_state = state;
 		pci_walk_bus(dev->subordinate, cb, &result_data);
 		if (cb == report_resume) {
+			pci_aer_clear_device_status(dev);
 			pci_cleanup_aer_uncorrect_error_status(dev);
 			dev->error_state = pci_channel_io_normal;
 		}
@@ -259,15 +260,10 @@ static pci_ers_result_t broadcast_error_message(struct pci_dev *dev,
 		/*
 		 * If the error is reported by an end point, we think this
 		 * error is related to the upstream link of the end point.
+		 * The error is non fatal so the bus is ok; just invoke
+		 * the callback for the function that logged the error.
 		 */
-		if (state == pci_channel_io_normal)
-			/*
-			 * the error is non fatal so the bus is ok, just invoke
-			 * the callback for the function that logged the error.
-			 */
-			cb(dev, &result_data);
-		else
-			pci_walk_bus(dev->bus, cb, &result_data);
+		cb(dev, &result_data);
 	}
 
 	return result_data.result;
@@ -317,7 +313,8 @@ void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service)
 		 * do error recovery on all subordinates of the bridge instead
 		 * of the bridge and clear the error status of the bridge.
 		 */
-		pci_cleanup_aer_uncorrect_error_status(dev);
+		pci_aer_clear_fatal_status(dev);
+		pci_aer_clear_device_status(dev);
 	}
 
 	if (result == PCI_ERS_RESULT_RECOVERED) {

drivers/pci/pcie/portdrv_pci.c

@@ -42,17 +42,6 @@ __setup("pcie_ports=", pcie_port_setup);
 
 /* global data */
 
-static int pcie_portdrv_restore_config(struct pci_dev *dev)
-{
-	int retval;
-
-	retval = pci_enable_device(dev);
-	if (retval)
-		return retval;
-	pci_set_master(dev);
-	return 0;
-}
-
 #ifdef CONFIG_PM
 static int pcie_port_runtime_suspend(struct device *dev)
 {
@@ -160,19 +149,6 @@ static pci_ers_result_t pcie_portdrv_mmio_enabled(struct pci_dev *dev)
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
-static pci_ers_result_t pcie_portdrv_slot_reset(struct pci_dev *dev)
-{
-	/* If fatal, restore cfg space for possible link reset at upstream */
-	if (dev->error_state == pci_channel_io_frozen) {
-		dev->state_saved = true;
-		pci_restore_state(dev);
-		pcie_portdrv_restore_config(dev);
-		pci_enable_pcie_error_reporting(dev);
-	}
-
-	return PCI_ERS_RESULT_RECOVERED;
-}
-
 static int resume_iter(struct device *device, void *data)
 {
 	struct pcie_device *pcie_device;
@@ -208,7 +184,6 @@ static const struct pci_device_id port_pci_ids[] = { {
 static const struct pci_error_handlers pcie_portdrv_err_handler = {
 	.error_detected = pcie_portdrv_error_detected,
 	.mmio_enabled = pcie_portdrv_mmio_enabled,
-	.slot_reset = pcie_portdrv_slot_reset,
 	.resume = pcie_portdrv_err_resume,
 };
 

drivers/pci/probe.c

@@ -2064,6 +2064,7 @@ static void pci_configure_device(struct pci_dev *dev)
 
 static void pci_release_capabilities(struct pci_dev *dev)
 {
+	pci_aer_exit(dev);
 	pci_vpd_release(dev);
 	pci_iov_release(dev);
 	pci_free_cap_save_buffers(dev);

include/linux/pci.h

@@ -299,6 +299,7 @@ struct pci_dev {
 	u8		hdr_type;	/* PCI header type (`multi' flag masked out) */
 #ifdef CONFIG_PCIEAER
 	u16		aer_cap;	/* AER capability offset */
+	struct aer_stats *aer_stats;	/* AER stats for this device */
 #endif
 	u8		pcie_cap;	/* PCIe capability offset */
 	u8		msi_cap;	/* MSI capability offset */
@@ -1469,13 +1470,9 @@ static inline bool pcie_aspm_support_enabled(void) { return false; }
 #endif
 
 #ifdef CONFIG_PCIEAER
-void pci_no_aer(void);
 bool pci_aer_available(void);
-int pci_aer_init(struct pci_dev *dev);
 #else
-static inline void pci_no_aer(void) { }
 static inline bool pci_aer_available(void) { return false; }
-static inline int pci_aer_init(struct pci_dev *d) { return -ENODEV; }
 #endif
 
 #ifdef CONFIG_PCIE_ECRC