iommu/amd: Invalidate IRT cache for DMA aliases

DMA aliasing causes interrupt remapping table entries (IRTEs) to be shared
between multiple device IDs. See commit 3c12443
("iommu/amd: Support multiple PCI DMA aliases in IRQ Remapping") for more
information on this. However, the AMD IOMMU driver currently invalidates
IRTE cache entries on a per-device basis whenever an IRTE is updated, not
for each alias.

This approach leaves stale IRTE cache entries when an IRTE is cached under
one DMA alias but later updated and invalidated through a different alias.
In such cases, the original device ID is never invalidated, since it is
programmed via aliasing.

This incoherency bug has been observed when IRTEs are cached for one
Non-Transparent Bridge (NTB) DMA alias, later updated via another.

Fix this by invalidating the interrupt remapping table cache for all DMA
aliases when updating an IRTE.

Co-developed-by: Lars B. Kristiansen <larsk@dolphinics.com>
Signed-off-by: Lars B. Kristiansen <larsk@dolphinics.com>
Co-developed-by: Jonas Markussen <jonas@dolphinics.com>
Signed-off-by: Jonas Markussen <jonas@dolphinics.com>
Co-developed-by: Tore H. Larsen <torel@simula.no>
Signed-off-by: Tore H. Larsen <torel@simula.no>
Signed-off-by: Magnus Kalland <magnus@dolphinics.com>
Link: https://lore.kernel.org/linux-iommu/9204da81-f821-4034-b8ad-501e43383b56@amd.com/
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>

Author: Magnus Kalland

drivers/iommu/amd/iommu.c

@@ -3167,26 +3167,44 @@ const struct iommu_ops amd_iommu_ops = {
 static struct irq_chip amd_ir_chip;
 static DEFINE_SPINLOCK(iommu_table_lock);
 
+static int iommu_flush_dev_irt(struct pci_dev *unused, u16 devid, void *data)
+{
+	int ret;
+	struct iommu_cmd cmd;
+	struct amd_iommu *iommu = data;
+
+	build_inv_irt(&cmd, devid);
+	ret = __iommu_queue_command_sync(iommu, &cmd, true);
+	return ret;
+}
+
 static void iommu_flush_irt_and_complete(struct amd_iommu *iommu, u16 devid)
 {
 	int ret;
 	u64 data;
 	unsigned long flags;
-	struct iommu_cmd cmd, cmd2;
+	struct iommu_cmd cmd;
+	struct pci_dev *pdev = NULL;
+	struct iommu_dev_data *dev_data = search_dev_data(iommu, devid);
 
 	if (iommu->irtcachedis_enabled)
 		return;
 
-	build_inv_irt(&cmd, devid);
+	if (dev_data && dev_data->dev && dev_is_pci(dev_data->dev))
+		pdev = to_pci_dev(dev_data->dev);
 
 	raw_spin_lock_irqsave(&iommu->lock, flags);
 	data = get_cmdsem_val(iommu);
-	build_completion_wait(&cmd2, iommu, data);
+	build_completion_wait(&cmd, iommu, data);
 
-	ret = __iommu_queue_command_sync(iommu, &cmd, true);
+	if (pdev)
+		ret = pci_for_each_dma_alias(pdev, iommu_flush_dev_irt, iommu);
+	else
+		ret = iommu_flush_dev_irt(NULL, devid, iommu);
 	if (ret)
 		goto out_err;
-	ret = __iommu_queue_command_sync(iommu, &cmd2, false);
+
+	ret = __iommu_queue_command_sync(iommu, &cmd, false);
 	if (ret)
 		goto out_err;
 	raw_spin_unlock_irqrestore(&iommu->lock, flags);