Merge branch 'pci/enumeration'

- Clear LBMS bit after a manual link retrain so we don't try to retrain a
  link when there's no downstream device anymore (Maciej W. Rozycki)

- Revert to the original link speed after retraining fails instead of
  leaving it restricted to 2.5GT/s, so a future device has a chance to use
  higher speeds (Maciej W. Rozycki)

- Correct interpretation of pcie_retrain_link() return status and update it
  to return 0/errno instead of true/false (Maciej W.  Rozycki)

* pci/enumeration:
  PCI: Use an error code with PCIe failed link retraining
  PCI: Correct error reporting with PCIe failed link retraining
  PCI: Revert to the original speed after PCIe failed link retraining
  PCI: Clear the LBMS bit after a link retrain

Author: bjorn-helgaas

drivers/pci/pci.c

@@ -1339,7 +1339,7 @@ static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout)
 		if (delay > PCI_RESET_WAIT) {
 			if (retrain) {
 				retrain = false;
-				if (pcie_failed_link_retrain(bridge)) {
+				if (pcie_failed_link_retrain(bridge) == 0) {
 					delay = 1;
 					continue;
 				}
@@ -4732,7 +4732,15 @@ int pcie_retrain_link(struct pci_dev *pdev, bool use_lt)
 		pcie_capability_clear_word(pdev, PCI_EXP_LNKCTL, PCI_EXP_LNKCTL_RL);
 	}
 
-	return pcie_wait_for_link_status(pdev, use_lt, !use_lt);
+	rc = pcie_wait_for_link_status(pdev, use_lt, !use_lt);
+
+	/*
+	 * Clear LBMS after a manual retrain so that the bit can be used
+	 * to track link speed or width changes made by hardware itself
+	 * in attempt to correct unreliable link operation.
+	 */
+	pcie_capability_write_word(pdev, PCI_EXP_LNKSTA, PCI_EXP_LNKSTA_LBMS);
+	return rc;
 }
 
 /**

drivers/pci/pci.h

@@ -611,7 +611,7 @@ void pci_acs_init(struct pci_dev *dev);
 int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags);
 int pci_dev_specific_enable_acs(struct pci_dev *dev);
 int pci_dev_specific_disable_acs_redir(struct pci_dev *dev);
-bool pcie_failed_link_retrain(struct pci_dev *dev);
+int pcie_failed_link_retrain(struct pci_dev *dev);
 #else
 static inline int pci_dev_specific_acs_enabled(struct pci_dev *dev,
 					       u16 acs_flags)
@@ -626,9 +626,9 @@ static inline int pci_dev_specific_disable_acs_redir(struct pci_dev *dev)
 {
 	return -ENOTTY;
 }
-static inline bool pcie_failed_link_retrain(struct pci_dev *dev)
+static inline int pcie_failed_link_retrain(struct pci_dev *dev)
 {
-	return false;
+	return -ENOTTY;
 }
 #endif
 

drivers/pci/quirks.c

@@ -66,41 +66,53 @@
  * apply this erratum workaround to any downstream ports as long as they
  * support Link Active reporting and have the Link Control 2 register.
  * Restrict the speed to 2.5GT/s then with the Target Link Speed field,
- * request a retrain and wait 200ms for the data link to go up.
+ * request a retrain and check the result.
  *
  * If this turns out successful and we know by the Vendor:Device ID it is
  * safe to do so, then lift the restriction, letting the devices negotiate
  * a higher speed.  Also check for a similar 2.5GT/s speed restriction the
  * firmware may have already arranged and lift it with ports that already
  * report their data link being up.
  *
- * Return TRUE if the link has been successfully retrained, otherwise FALSE.
+ * Otherwise revert the speed to the original setting and request a retrain
+ * again to remove any residual state, ignoring the result as it's supposed
+ * to fail anyway.
+ *
+ * Return 0 if the link has been successfully retrained.  Return an error
+ * if retraining was not needed or we attempted a retrain and it failed.
  */
-bool pcie_failed_link_retrain(struct pci_dev *dev)
+int pcie_failed_link_retrain(struct pci_dev *dev)
 {
 	static const struct pci_device_id ids[] = {
 		{ PCI_VDEVICE(ASMEDIA, 0x2824) }, /* ASMedia ASM2824 */
 		{}
 	};
 	u16 lnksta, lnkctl2;
+	int ret = -ENOTTY;
 
 	if (!pci_is_pcie(dev) || !pcie_downstream_port(dev) ||
 	    !pcie_cap_has_lnkctl2(dev) || !dev->link_active_reporting)
-		return false;
+		return ret;
 
 	pcie_capability_read_word(dev, PCI_EXP_LNKCTL2, &lnkctl2);
 	pcie_capability_read_word(dev, PCI_EXP_LNKSTA, &lnksta);
 	if ((lnksta & (PCI_EXP_LNKSTA_LBMS | PCI_EXP_LNKSTA_DLLLA)) ==
 	    PCI_EXP_LNKSTA_LBMS) {
+		u16 oldlnkctl2 = lnkctl2;
+
 		pci_info(dev, "broken device, retraining non-functional downstream link at 2.5GT/s\n");
 
 		lnkctl2 &= ~PCI_EXP_LNKCTL2_TLS;
 		lnkctl2 |= PCI_EXP_LNKCTL2_TLS_2_5GT;
 		pcie_capability_write_word(dev, PCI_EXP_LNKCTL2, lnkctl2);
 
-		if (pcie_retrain_link(dev, false)) {
+		ret = pcie_retrain_link(dev, false);
+		if (ret) {
 			pci_info(dev, "retraining failed\n");
-			return false;
+			pcie_capability_write_word(dev, PCI_EXP_LNKCTL2,
+						   oldlnkctl2);
+			pcie_retrain_link(dev, true);
+			return ret;
 		}
 
 		pcie_capability_read_word(dev, PCI_EXP_LNKSTA, &lnksta);
@@ -117,13 +129,14 @@ bool pcie_failed_link_retrain(struct pci_dev *dev)
 		lnkctl2 |= lnkcap & PCI_EXP_LNKCAP_SLS;
 		pcie_capability_write_word(dev, PCI_EXP_LNKCTL2, lnkctl2);
 
-		if (pcie_retrain_link(dev, false)) {
+		ret = pcie_retrain_link(dev, false);
+		if (ret) {
 			pci_info(dev, "retraining failed\n");
-			return false;
+			return ret;
 		}
 	}
 
-	return true;
+	return ret;
 }
 
 static ktime_t fixup_debug_start(struct pci_dev *dev,