[PATCH v2 1/1] bus/pci: add RTE_PCI_DRV_NEED_IOVA_AS_PA flag

[liujie5@linkdatatechnology.com]

From: liufeng1 <liufeng1@sugon.com>

Add a new PCI driver flag, RTE_PCI_DRV_NEED_IOVA_AS_PA, that allows a
driver to tell the PCI bus layer it cannot work with IOVA as VA and
must use IOVA as PA.

The existing RTE_PCI_DRV_NEED_IOVA_AS_VA flag already provides the
opposite requirement. Some PCI devices, however, are managed by a
kernel driver that uses an identity-mapped IOMMU domain (e.g. when the
		kernel is booted with iommu=pt). The user-space PMD for such devices
must use IOVA as PA, because the DMA addresses programmed by DPDK must
match the identity mapping programmed by the kernel driver.

Without this flag, a PCI driver bound to a non-VFIO/UIO kernel driver
has no way to force IOVA as PA. pci_device_iova_mode() returns
RTE_IOVA_DC for those devices, and rte_eal_init() then sees an enabled
IOMMU and selects RTE_IOVA_VA, which breaks identity-domain PMDs and
forces users to pass --iova-mode=pa on the command line.

When RTE_PCI_DRV_NEED_IOVA_AS_PA is set, pci_device_iova_mode()
returns RTE_IOVA_PA for the device. The requirement is propagated
through rte_pci_get_iommu_class() to rte_bus_get_iommu_class(), so
rte_eal_init() selects IOVA as PA automatically.

If a driver sets both RTE_PCI_DRV_NEED_IOVA_AS_VA and
RTE_PCI_DRV_NEED_IOVA_AS_PA at the same time, a warning is emitted
and the conflicting requirement is ignored (RTE_IOVA_DC), because
the two flags are mutually exclusive.

This is a generic mechanism: any PCI driver whose underlying kernel
driver uses an identity IOMMU domain can set the flag.

Signed-off-by: Jie Liu <liujie5@linkdatatechnology.com>
---
 drivers/bus/pci/bus_pci_driver.h |  2 ++
 drivers/bus/pci/linux/pci.c      | 13 +++++++++++++
 drivers/bus/pci/pci_common.c     |  3 +--
 3 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/bus/pci/bus_pci_driver.h b/drivers/bus/pci/bus_pci_driver.h
index c04ebddf59..5d5efbbb3e 100644
--- a/drivers/bus/pci/bus_pci_driver.h
+++ b/drivers/bus/pci/bus_pci_driver.h
@@ -140,6 +140,8 @@ struct rte_pci_driver {
 #define RTE_PCI_DRV_KEEP_MAPPED_RES 0x0020
 /** Device driver needs IOVA as VA and cannot work with IOVA as PA */
 #define RTE_PCI_DRV_NEED_IOVA_AS_VA 0x0040
+/** Device driver needs IOVA as PA and cannot work with IOVA as VA */
+#define RTE_PCI_DRV_NEED_IOVA_AS_PA 0x0080
 
 /**
  * Register a PCI driver.
diff --git a/drivers/bus/pci/linux/pci.c b/drivers/bus/pci/linux/pci.c
index bcf0a409da..4e03d81ed2 100644
--- a/drivers/bus/pci/linux/pci.c
+++ b/drivers/bus/pci/linux/pci.c
@@ -595,6 +595,15 @@ pci_device_iova_mode(const struct rte_pci_driver *pdrv,
 {
 	enum rte_iova_mode iova_mode = RTE_IOVA_DC;
 
+	if ((pdrv->drv_flags &
+		(RTE_PCI_DRV_NEED_IOVA_AS_VA | RTE_PCI_DRV_NEED_IOVA_AS_PA)) ==
+		(RTE_PCI_DRV_NEED_IOVA_AS_VA | RTE_PCI_DRV_NEED_IOVA_AS_PA)) {
+		RTE_LOG(WARNING, EAL,
+				"PCI driver '%s' sets both NEED_IOVA_AS_VA and NEED_IOVA_AS_PA flags, ignoring\n",
+				pdrv->driver.name);
+		return iova_mode;
+	}
+
 	switch (pdev->kdrv) {
 	case RTE_PCI_KDRV_VFIO: {
 		static int is_vfio_noiommu_enabled = -1;
@@ -609,6 +618,8 @@ pci_device_iova_mode(const struct rte_pci_driver *pdrv,
 			iova_mode = RTE_IOVA_PA;
 		else if ((pdrv->drv_flags & RTE_PCI_DRV_NEED_IOVA_AS_VA) != 0)
 			iova_mode = RTE_IOVA_VA;
+		else if ((pdrv->drv_flags & RTE_PCI_DRV_NEED_IOVA_AS_PA) != 0)
+			iova_mode = RTE_IOVA_PA;
 		break;
 	}
 
@@ -620,6 +631,8 @@ pci_device_iova_mode(const struct rte_pci_driver *pdrv,
 	default:
 		if ((pdrv->drv_flags & RTE_PCI_DRV_NEED_IOVA_AS_VA) != 0)
 			iova_mode = RTE_IOVA_VA;
+		else if ((pdrv->drv_flags & RTE_PCI_DRV_NEED_IOVA_AS_PA) != 0)
+			iova_mode = RTE_IOVA_PA;
 		break;
 	}
 	return iova_mode;
diff --git a/drivers/bus/pci/pci_common.c b/drivers/bus/pci/pci_common.c
index dc8db80d3b..9893306c8e 100644
--- a/drivers/bus/pci/pci_common.c
+++ b/drivers/bus/pci/pci_common.c
@@ -533,8 +533,7 @@ rte_pci_get_iommu_class(void)
 			iommu_no_va = pci_device_iommu_support_va(dev)
 					? 0 : 1;
 
-		if (dev->kdrv == RTE_PCI_KDRV_UNKNOWN ||
-		    dev->kdrv == RTE_PCI_KDRV_NONE)
+		if (dev->kdrv == RTE_PCI_KDRV_NONE)
 			continue;
 		RTE_BUS_FOREACH_DRV(drv, &rte_pci_bus) {
 			enum rte_iova_mode dev_iova_mode;
-- 
2.52.0