bus/pci: forbid IOVA mode if IOMMU address width too small

Intel VT-d supports different address widths for the IOVAs, from
39 bits to 56 bits.

While recent processors support at least 48 bits, VT-d emulation
currently only supports 39 bits. It makes DMA mapping to fail in this
case when using VA as IOVA mode, as user-space virtual addresses uses
up to 47 bits (see kernel's Documentation/x86/x86_64/mm.txt).

This patch parses VT-d CAP register value available in sysfs, and
forbid VA as IOVA mode if the GAW is 39 bits or unknown.

Fixes: f37dfab ("drivers/net: enable IOVA mode for Intel PMDs")
Cc: stable@dpdk.org

Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Tested-by: Chas Williams <chas3@att.com>

drivers/bus/pci/linux/pci.c

@@ -547,6 +547,82 @@ pci_one_device_has_iova_va(void)
 	return 0;
 }
 
+#if defined(RTE_ARCH_X86)
+static bool
+pci_one_device_iommu_support_va(struct rte_pci_device *dev)
+{
+#define VTD_CAP_MGAW_SHIFT	16
+#define VTD_CAP_MGAW_MASK	(0x3fULL << VTD_CAP_MGAW_SHIFT)
+#define X86_VA_WIDTH 47 /* From Documentation/x86/x86_64/mm.txt */
+	struct rte_pci_addr *addr = &dev->addr;
+	char filename[PATH_MAX];
+	FILE *fp;
+	uint64_t mgaw, vtd_cap_reg = 0;
+
+	snprintf(filename, sizeof(filename),
+		 "%s/" PCI_PRI_FMT "/iommu/intel-iommu/cap",
+		 rte_pci_get_sysfs_path(), addr->domain, addr->bus, addr->devid,
+		 addr->function);
+	if (access(filename, F_OK) == -1) {
+		/* We don't have an Intel IOMMU, assume VA supported*/
+		return true;
+	}
+
+	/* We have an intel IOMMU */
+	fp = fopen(filename, "r");
+	if (fp == NULL) {
+		RTE_LOG(ERR, EAL, "%s(): can't open %s\n", __func__, filename);
+		return false;
+	}
+
+	if (fscanf(fp, "%" PRIx64, &vtd_cap_reg) != 1) {
+		RTE_LOG(ERR, EAL, "%s(): can't read %s\n", __func__, filename);
+		fclose(fp);
+		return false;
+	}
+
+	fclose(fp);
+
+	mgaw = ((vtd_cap_reg & VTD_CAP_MGAW_MASK) >> VTD_CAP_MGAW_SHIFT) + 1;
+	if (mgaw < X86_VA_WIDTH)
+		return false;
+
+	return true;
+}
+#elif defined(RTE_ARCH_PPC_64)
+static bool
+pci_one_device_iommu_support_va(__rte_unused struct rte_pci_device *dev)
+{
+	return false;
+}
+#else
+static bool
+pci_one_device_iommu_support_va(__rte_unused struct rte_pci_device *dev)
+{
+	return true;
+}
+#endif
+
+/*
+ * All devices IOMMUs support VA as IOVA
+ */
+static bool
+pci_devices_iommu_support_va(void)
+{
+	struct rte_pci_device *dev = NULL;
+	struct rte_pci_driver *drv = NULL;
+
+	FOREACH_DRIVER_ON_PCIBUS(drv) {
+		FOREACH_DEVICE_ON_PCIBUS(dev) {
+			if (!rte_pci_match(drv, dev))
+				continue;
+			if (!pci_one_device_iommu_support_va(dev))
+				return false;
+		}
+	}
+	return true;
+}
+
 /*
  * Get iommu class of PCI devices on the bus.
  */
@@ -557,26 +633,22 @@ rte_pci_get_iommu_class(void)
 	bool is_vfio_noiommu_enabled = true;
 	bool has_iova_va;
 	bool is_bound_uio;
-	bool spapr_iommu =
-#if defined(RTE_ARCH_PPC_64)
-		true;
-#else
-		false;
-#endif
+	bool iommu_no_va;
 
 	is_bound = pci_one_device_is_bound();
 	if (!is_bound)
 		return RTE_IOVA_DC;
 
 	has_iova_va = pci_one_device_has_iova_va();
 	is_bound_uio = pci_one_device_bound_uio();
+	iommu_no_va = !pci_devices_iommu_support_va();
 #ifdef VFIO_PRESENT
 	is_vfio_noiommu_enabled = rte_vfio_noiommu_is_enabled() == true ?
 					true : false;
 #endif
 
 	if (has_iova_va && !is_bound_uio && !is_vfio_noiommu_enabled &&
-			!spapr_iommu)
+			!iommu_no_va)
 		return RTE_IOVA_VA;
 
 	if (has_iova_va) {
@@ -585,8 +657,8 @@ rte_pci_get_iommu_class(void)
 			RTE_LOG(WARNING, EAL, "vfio-noiommu mode configured\n");
 		if (is_bound_uio)
 			RTE_LOG(WARNING, EAL, "few device bound to UIO\n");
-		if (spapr_iommu)
-			RTE_LOG(WARNING, EAL, "sPAPR IOMMU does not support IOVA as VA\n");
+		if (iommu_no_va)
+			RTE_LOG(WARNING, EAL, "IOMMU does not support IOVA as VA\n");
 	}
 
 	return RTE_IOVA_PA;