Merge branch 'remotes/lorenzo/pci/hv'

- Fix hibernation in case interrupts are not re-created (Dexuan Cui)

* remotes/lorenzo/pci/hv:
  PCI: hv: Fix hibernation in case interrupts are not re-created

1 files changed, 47 insertions, 3 deletions

diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index fc4c3a15e570..a9df492fbffa 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -1276,11 +1276,25 @@ static void hv_irq_unmask(struct irq_data *data)
 exit_unlock:
 	spin_unlock_irqrestore(&hbus->retarget_msi_interrupt_lock, flags);
 
-	if (res) {
+	/*
+	 * During hibernation, when a CPU is offlined, the kernel tries
+	 * to move the interrupt to the remaining CPUs that haven't
+	 * been offlined yet. In this case, the below hv_do_hypercall()
+	 * always fails since the vmbus channel has been closed:
+	 * refer to cpu_disable_common() -> fixup_irqs() ->
+	 * irq_migrate_all_off_this_cpu() -> migrate_one_irq().
+	 *
+	 * Suppress the error message for hibernation because the failure
+	 * during hibernation does not matter (at this time all the devices
+	 * have been frozen). Note: the correct affinity info is still updated
+	 * into the irqdata data structure in migrate_one_irq() ->
+	 * irq_do_set_affinity() -> hv_set_affinity(), so later when the VM
+	 * resumes, hv_pci_restore_msi_state() is able to correctly restore
+	 * the interrupt with the correct affinity.
+	 */
+	if (res && hbus->state != hv_pcibus_removing)
 		dev_err(&hbus->hdev->device,
 			"%s() failed: %#llx", __func__, res);
-		return;
-	}
 
 	pci_msi_unmask_irq(data);
 }
@@ -3372,6 +3386,34 @@ static int hv_pci_suspend(struct hv_device *hdev)
 	return 0;
 }
 
+static int hv_pci_restore_msi_msg(struct pci_dev *pdev, void *arg)
+{
+	struct msi_desc *entry;
+	struct irq_data *irq_data;
+
+	for_each_pci_msi_entry(entry, pdev) {
+		irq_data = irq_get_irq_data(entry->irq);
+		if (WARN_ON_ONCE(!irq_data))
+			return -EINVAL;
+
+		hv_compose_msi_msg(irq_data, &entry->msg);
+	}
+
+	return 0;
+}
+
+/*
+ * Upon resume, pci_restore_msi_state() -> ... ->  __pci_write_msi_msg()
+ * directly writes the MSI/MSI-X registers via MMIO, but since Hyper-V
+ * doesn't trap and emulate the MMIO accesses, here hv_compose_msi_msg()
+ * must be used to ask Hyper-V to re-create the IOMMU Interrupt Remapping
+ * Table entries.
+ */
+static void hv_pci_restore_msi_state(struct hv_pcibus_device *hbus)
+{
+	pci_walk_bus(hbus->pci_bus, hv_pci_restore_msi_msg, NULL);
+}
+
 static int hv_pci_resume(struct hv_device *hdev)
 {
 	struct hv_pcibus_device *hbus = hv_get_drvdata(hdev);
@@ -3405,6 +3447,8 @@ static int hv_pci_resume(struct hv_device *hdev)
 
 	prepopulate_bars(hbus);
 
+	hv_pci_restore_msi_state(hbus);
+
 	hbus->state = hv_pcibus_installed;
 	return 0;
 out: