Merge branch 'pci/reset'

- Wait longer for devices to become ready after resume (as we do for reset)
  to accommodate Intel Titan Ridge xHCI devices (Mika Westerberg)

- Drop pci_bridge_wait_for_secondary_bus() timeout parameter since all
  callers pass the same value (Mika Westerberg)

- Extend D3hot delay for NVIDIA HDA controllers to avoid unrecoverable
  devices after a bus reset (Alex Williamson)

* pci/reset:
  PCI/PM: Extend D3hot delay for NVIDIA HDA controllers
  PCI/PM: Drop pci_bridge_wait_for_secondary_bus() timeout parameter
  PCI/PM: Increase wait time after resume

drivers/pci/pci-driver.c

@@ -572,7 +572,8 @@ static void pci_pm_default_resume_early(struct pci_dev *pci_dev)
 
 static void pci_pm_bridge_power_up_actions(struct pci_dev *pci_dev)
 {
-	pci_bridge_wait_for_secondary_bus(pci_dev, "resume", PCI_RESET_WAIT);
+	pci_bridge_wait_for_secondary_bus(pci_dev, "resume");
+
 	/*
 	 * When powering on a bridge from D3cold, the whole hierarchy may be
 	 * powered on into D0uninitialized state, resume them to give them a

drivers/pci/pci.c

@@ -64,6 +64,14 @@ struct pci_pme_device {
 
 #define PME_TIMEOUT 1000 /* How long between PME checks */
 
+/*
+ * Devices may extend the 1 sec period through Request Retry Status
+ * completions (PCIe r6.0 sec 2.3.1).  The spec does not provide an upper
+ * limit, but 60 sec ought to be enough for any device to become
+ * responsive.
+ */
+#define PCIE_RESET_READY_POLL_MS 60000 /* msec */
+
 static void pci_dev_d3_sleep(struct pci_dev *dev)
 {
 	unsigned int delay_ms = max(dev->d3hot_delay, pci_pm_d3hot_delay);
@@ -4939,7 +4947,6 @@ static int pci_bus_max_d3cold_delay(const struct pci_bus *bus)
  * pci_bridge_wait_for_secondary_bus - Wait for secondary bus to be accessible
  * @dev: PCI bridge
  * @reset_type: reset type in human-readable form
- * @timeout: maximum time to wait for devices on secondary bus (milliseconds)
  *
  * Handle necessary delays before access to the devices on the secondary
  * side of the bridge are permitted after D3cold to D0 transition
@@ -4952,8 +4959,7 @@ static int pci_bus_max_d3cold_delay(const struct pci_bus *bus)
  * Return 0 on success or -ENOTTY if the first device on the secondary bus
  * failed to become accessible.
  */
-int pci_bridge_wait_for_secondary_bus(struct pci_dev *dev, char *reset_type,
-				      int timeout)
+int pci_bridge_wait_for_secondary_bus(struct pci_dev *dev, char *reset_type)
 {
 	struct pci_dev *child;
 	int delay;
@@ -5031,7 +5037,8 @@ int pci_bridge_wait_for_secondary_bus(struct pci_dev *dev, char *reset_type,
 		}
 	}
 
-	return pci_dev_wait(child, reset_type, timeout - delay);
+	return pci_dev_wait(child, reset_type,
+			    PCIE_RESET_READY_POLL_MS - delay);
 }
 
 void pci_reset_secondary_bus(struct pci_dev *dev)
@@ -5068,8 +5075,7 @@ int pci_bridge_secondary_bus_reset(struct pci_dev *dev)
 {
 	pcibios_reset_secondary_bus(dev);
 
-	return pci_bridge_wait_for_secondary_bus(dev, "bus reset",
-						 PCIE_RESET_READY_POLL_MS);
+	return pci_bridge_wait_for_secondary_bus(dev, "bus reset");
 }
 EXPORT_SYMBOL_GPL(pci_bridge_secondary_bus_reset);
 

drivers/pci/pci.h

@@ -70,12 +70,6 @@ struct pci_cap_saved_state *pci_find_saved_ext_cap(struct pci_dev *dev,
  * Reset (PCIe r6.0 sec 5.8).
  */
 #define PCI_RESET_WAIT		1000	/* msec */
-/*
- * Devices may extend the 1 sec period through Request Retry Status completions
- * (PCIe r6.0 sec 2.3.1).  The spec does not provide an upper limit, but 60 sec
- * ought to be enough for any device to become responsive.
- */
-#define PCIE_RESET_READY_POLL_MS 60000	/* msec */
 
 void pci_update_current_state(struct pci_dev *dev, pci_power_t state);
 void pci_refresh_power_state(struct pci_dev *dev);
@@ -100,8 +94,7 @@ void pci_msix_init(struct pci_dev *dev);
 bool pci_bridge_d3_possible(struct pci_dev *dev);
 void pci_bridge_d3_update(struct pci_dev *dev);
 void pci_bridge_reconfigure_ltr(struct pci_dev *dev);
-int pci_bridge_wait_for_secondary_bus(struct pci_dev *dev, char *reset_type,
-				      int timeout);
+int pci_bridge_wait_for_secondary_bus(struct pci_dev *dev, char *reset_type);
 
 static inline void pci_wakeup_event(struct pci_dev *dev)
 {

drivers/pci/pcie/dpc.c

@@ -170,8 +170,7 @@ pci_ers_result_t dpc_reset_link(struct pci_dev *pdev)
 	pci_write_config_word(pdev, cap + PCI_EXP_DPC_STATUS,
 			      PCI_EXP_DPC_STATUS_TRIGGER);
 
-	if (pci_bridge_wait_for_secondary_bus(pdev, "DPC",
-					      PCIE_RESET_READY_POLL_MS)) {
+	if (pci_bridge_wait_for_secondary_bus(pdev, "DPC")) {
 		clear_bit(PCI_DPC_RECOVERED, &pdev->priv_flags);
 		ret = PCI_ERS_RESULT_DISCONNECT;
 	} else {

drivers/pci/quirks.c

@@ -1939,6 +1939,19 @@ static void quirk_radeon_pm(struct pci_dev *dev)
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x6741, quirk_radeon_pm);
 
+/*
+ * NVIDIA Ampere-based HDA controllers can wedge the whole device if a bus
+ * reset is performed too soon after transition to D0, extend d3hot_delay
+ * to previous effective default for all NVIDIA HDA controllers.
+ */
+static void quirk_nvidia_hda_pm(struct pci_dev *dev)
+{
+	quirk_d3hot_delay(dev, 20);
+}
+DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID,
+			      PCI_CLASS_MULTIMEDIA_HD_AUDIO, 8,
+			      quirk_nvidia_hda_pm);
+
 /*
  * Ryzen5/7 XHCI controllers fail upon resume from runtime suspend or s2idle.
  * https://bugzilla.kernel.org/show_bug.cgi?id=205587