From: Maciej W. Rozycki <macro@orcam.me.uk>
Date: Sun, 11 Jun 2023 17:20:06 +0000 (+0100)
Subject: PCI: Add failed link recovery for device reset events
X-Git-Url: http://git.maquefel.me/?a=commitdiff_plain;h=08e3ed12ca8615b078ea19488fb45b084e5de16b;p=linux.git

PCI: Add failed link recovery for device reset events

Request failed link recovery with any upstream PCIe bridge where a device
has not come back after reset within PCI_RESET_WAIT time.  Reset the
polling interval if recovery succeeded, otherwise continue as usual.

[bhelgaas: inline pcie_parent_link_retrain()]
Link: https://lore.kernel.org/r/alpine.DEB.2.21.2306111631050.64925@angie.orcam.me.uk
Signed-off-by: Maciej W. Rozycki <macro@orcam.me.uk>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index f599d321c881e..64f1a87902d89 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1156,7 +1156,14 @@ void pci_resume_bus(struct pci_bus *bus)
 static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout)
 {
 	int delay = 1;
-	u32 id;
+	bool retrain = false;
+	struct pci_dev *bridge;
+
+	if (pci_is_pcie(dev)) {
+		bridge = pci_upstream_bridge(dev);
+		if (bridge)
+			retrain = true;
+	}
 
 	/*
 	 * After reset, the device should not silently discard config
@@ -1170,21 +1177,33 @@ static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout)
 	 * Command register instead of Vendor ID so we don't have to
 	 * contend with the CRS SV value.
 	 */
-	pci_read_config_dword(dev, PCI_COMMAND, &id);
-	while (PCI_POSSIBLE_ERROR(id)) {
+	for (;;) {
+		u32 id;
+
+		pci_read_config_dword(dev, PCI_COMMAND, &id);
+		if (!PCI_POSSIBLE_ERROR(id))
+			break;
+
 		if (delay > timeout) {
 			pci_warn(dev, "not ready %dms after %s; giving up\n",
 				 delay - 1, reset_type);
 			return -ENOTTY;
 		}
 
-		if (delay > PCI_RESET_WAIT)
+		if (delay > PCI_RESET_WAIT) {
+			if (retrain) {
+				retrain = false;
+				if (pcie_failed_link_retrain(bridge)) {
+					delay = 1;
+					continue;
+				}
+			}
 			pci_info(dev, "not ready %dms after %s; waiting\n",
 				 delay - 1, reset_type);
+		}
 
 		msleep(delay);
 		delay *= 2;
-		pci_read_config_dword(dev, PCI_COMMAND, &id);
 	}
 
 	if (delay > PCI_RESET_WAIT)