From patchwork series 403338

https://patchwork.ozlabs.org//project/linuxppc-dev/list/?series=403338

Author: Fox Snowpatch

drivers/pci/pci.h

@@ -412,6 +412,7 @@ struct aer_err_info {
 
 	unsigned int status;		/* COR/UNCOR Error Status */
 	unsigned int mask;		/* COR/UNCOR Error Mask */
+	unsigned int anfe_status;	/* UNCOR Error Status for ANFE */
 	struct pcie_tlp_log tlp;	/* TLP Header */
 };
 

drivers/pci/pcie/aer.c

@@ -107,6 +107,12 @@ struct aer_stats {
 					PCI_ERR_ROOT_MULTI_COR_RCV |	\
 					PCI_ERR_ROOT_MULTI_UNCOR_RCV)
 
+#define AER_ERR_ANFE_UNC_MASK		(PCI_ERR_UNC_POISON_TLP |	\
+					PCI_ERR_UNC_COMP_TIME |		\
+					PCI_ERR_UNC_COMP_ABORT |	\
+					PCI_ERR_UNC_UNX_COMP |		\
+					PCI_ERR_UNC_UNSUP)
+
 static int pcie_aer_disable;
 static pci_ers_result_t aer_root_reset(struct pci_dev *dev);
 
@@ -675,6 +681,7 @@ static void __aer_print_error(struct pci_dev *dev,
 {
 	const char **strings;
 	unsigned long status = info->status & ~info->mask;
+	unsigned long anfe_status = info->anfe_status;
 	const char *level, *errmsg;
 	int i;
 
@@ -695,6 +702,20 @@ static void __aer_print_error(struct pci_dev *dev,
 				info->first_error == i ? " (First)" : "");
 	}
 	pci_dev_aer_stats_incr(dev, info);
+
+	if (!anfe_status)
+		return;
+
+	strings = aer_uncorrectable_error_string;
+	pci_printk(level, dev, "Uncorrectable errors that may cause Advisory Non-Fatal:\n");
+
+	for_each_set_bit(i, &anfe_status, 32) {
+		errmsg = strings[i];
+		if (!errmsg)
+			errmsg = "Unknown Error Bit";
+
+		pci_printk(level, dev, "   [%2d] %s\n", i, errmsg);
+	}
 }
 
 void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
@@ -1094,9 +1115,14 @@ static void pci_aer_handle_error(struct pci_dev *dev, struct aer_err_info *info)
 		 * Correctable error does not need software intervention.
 		 * No need to go through error recovery process.
 		 */
-		if (aer)
+		if (aer) {
 			pci_write_config_dword(dev, aer + PCI_ERR_COR_STATUS,
 					info->status);
+			if (info->anfe_status)
+				pci_write_config_dword(dev,
+						       aer + PCI_ERR_UNCOR_STATUS,
+						       info->anfe_status);
+		}
 		if (pcie_aer_is_native(dev)) {
 			struct pci_driver *pdrv = dev->driver;
 
@@ -1196,6 +1222,41 @@ void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn,
 EXPORT_SYMBOL_GPL(aer_recover_queue);
 #endif
 
+static void anfe_get_uc_status(struct pci_dev *dev, struct aer_err_info *info)
+{
+	u32 uncor_mask, uncor_status;
+	u16 device_status;
+	int aer = dev->aer_cap;
+
+	if (pcie_capability_read_word(dev, PCI_EXP_DEVSTA, &device_status))
+		return;
+	/*
+	 * Take the most conservative route here. If there are
+	 * Non-Fatal/Fatal errors detected, do not assume any
+	 * bit in uncor_status is set by ANFE.
+	 */
+	if (device_status & (PCI_EXP_DEVSTA_NFED | PCI_EXP_DEVSTA_FED))
+		return;
+
+	pci_read_config_dword(dev, aer + PCI_ERR_UNCOR_STATUS, &uncor_status);
+	pci_read_config_dword(dev, aer + PCI_ERR_UNCOR_MASK, &uncor_mask);
+	/*
+	 * According to PCIe Base Specification Revision 6.1,
+	 * Section 6.2.3.2.4, if an UNCOR error is raised as
+	 * Advisory Non-Fatal error, it will match the following
+	 * conditions:
+	 *	a. The severity of the error is Non-Fatal.
+	 *	b. The error is one of the following:
+	 *		1. Poisoned TLP           (Section 6.2.3.2.4.3)
+	 *		2. Completion Timeout     (Section 6.2.3.2.4.4)
+	 *		3. Completer Abort        (Section 6.2.3.2.4.1)
+	 *		4. Unexpected Completion  (Section 6.2.3.2.4.5)
+	 *		5. Unsupported Request    (Section 6.2.3.2.4.1)
+	 */
+	info->anfe_status = uncor_status & ~uncor_mask & ~info->severity &
+			    AER_ERR_ANFE_UNC_MASK;
+}
+
 /**
  * aer_get_device_error_info - read error status from dev and store it to info
  * @dev: pointer to the device expected to have a error record
@@ -1213,6 +1274,7 @@ int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info)
 
 	/* Must reset in this function */
 	info->status = 0;
+	info->anfe_status = 0;
 	info->tlp_header_valid = 0;
 
 	/* The device might not support AER */
@@ -1226,6 +1288,9 @@ int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info)
 			&info->mask);
 		if (!(info->status & ~info->mask))
 			return 0;
+
+		if (info->status & PCI_ERR_COR_ADV_NFAT)
+			anfe_get_uc_status(dev, info);
 	} else if (type == PCI_EXP_TYPE_ROOT_PORT ||
 		   type == PCI_EXP_TYPE_RC_EC ||
 		   type == PCI_EXP_TYPE_DOWNSTREAM ||