[PATCH] PCI: hv: Fix hibernation in case interrupts are not re-created

[Dexuan Cui]

Hyper-V doesn't trap and emulate the accesses to the MSI/MSI-X registers,
and we must use hv_compose_msi_msg() to ask Hyper-V to create the IOMMU
Interrupt Remapping Table Entries. This is not an issue for a lot of
PCI device drivers (e.g. NVMe driver, Mellanox NIC drivers), which
destroy and re-create the interrupts across hibernation, so
hv_compose_msi_msg() is called automatically. However, some other PCI
device drivers (e.g. the Nvidia driver) may not destroy and re-create
the interrupts across hibernation, so hv_pci_resume() has to call
hv_compose_msi_msg(), otherwise the PCI device drivers can no longer
receive MSI/MSI-X interrupts after hibernation.

Fixes: ac82fc832708 ("PCI: hv: Add hibernation support")
Cc: Jake Oshins <jakeo@xxxxxxxxxxxxx>
Signed-off-by: Dexuan Cui <decui@xxxxxxxxxxxxx>
---
 drivers/pci/controller/pci-hyperv.c | 44 +++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index fc4c3a15e570..abefff9a20e1 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -1211,6 +1211,21 @@ static void hv_irq_unmask(struct irq_data *data)
 	pbus = pdev->bus;
 	hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata);
 
+	if (hbus->state == hv_pcibus_removing) {
+		/*
+		 * During hibernatin, 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, so we
+		 * should not call the hypercall, but we still need
+		 * pci_msi_unmask_irq() to reset the mask bit in desc->masked:
+		 * see cpu_disable_common() -> fixup_irqs() ->
+		 * irq_migrate_all_off_this_cpu() -> migrate_one_irq().
+		 */
+		pci_msi_unmask_irq(data);
+		return;
+	}
+
 	spin_lock_irqsave(&hbus->retarget_msi_interrupt_lock, flags);
 
 	params = &hbus->retarget_msi_interrupt_params;
@@ -3372,6 +3387,33 @@ 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()
+ * re-writes the MSI/MSI-X registers, but since Hyper-V doesn't trap and
+ * emulate the accesses, we have to call hv_compose_msi_msg() 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:
-- 
2.19.1