[dpdk-dev] [PATCH v12 1/2] kni: add IOVA=VA mode support

[<vattunuru@marvell.com>]

From: Vamsi Attunuru <vattunuru@marvell.com>

Current KNI implementation only operates in IOVA_PA mode
patch adds required functionality to enable KNI in
IOVA_VA mode.

KNI can operate in IOVA_VA mode when this mode is requested
using eal option (`iova-mode=va`) or when bus iommu scheme is
selected as RTE_IOVA_VA.

During KNI creation, app's iova_mode details are passed to
the KNI kernel module, accordingly kernel module translates
PA/IOVA addresses to KVA and vice-versa.

Signed-off-by: Vamsi Attunuru <vattunuru@marvell.com>
Signed-off-by: Kiran Kumar K <kirankumark@marvell.com>
Suggested-by: Ferruh Yigit <ferruh.yigit@intel.com>
---
 doc/guides/prog_guide/kernel_nic_interface.rst    |  9 +++++++
 doc/guides/rel_notes/release_19_11.rst            |  5 ++++
 lib/librte_eal/linux/eal/eal.c                    | 29 +++++++++++++----------
 lib/librte_eal/linux/eal/include/rte_kni_common.h |  1 +
 lib/librte_kni/rte_kni.c                          |  7 ++----
 5 files changed, 34 insertions(+), 17 deletions(-)

diff --git a/doc/guides/prog_guide/kernel_nic_interface.rst b/doc/guides/prog_guide/kernel_nic_interface.rst
index 2fd58e1..f869493 100644
--- a/doc/guides/prog_guide/kernel_nic_interface.rst
+++ b/doc/guides/prog_guide/kernel_nic_interface.rst
@@ -300,6 +300,15 @@ The sk_buff is then freed and the mbuf sent in the tx_q FIFO.
 The DPDK TX thread dequeues the mbuf and sends it to the PMD via ``rte_eth_tx_burst()``.
 It then puts the mbuf back in the cache.
 
+IOVA = VA: Support
+------------------
+
+KNI operates in IOVA_VA scheme when
+
+- LINUX_VERSION_CODE >= KERNEL_VERSION(4, 6, 0) and
+- eal option `iova-mode=va` is passed or bus IOVA scheme in the DPDK is selected
+  as RTE_IOVA_VA.
+
 Ethtool
 -------
 
diff --git a/doc/guides/rel_notes/release_19_11.rst b/doc/guides/rel_notes/release_19_11.rst
index ae8e7b2..e5d2996 100644
--- a/doc/guides/rel_notes/release_19_11.rst
+++ b/doc/guides/rel_notes/release_19_11.rst
@@ -231,6 +231,11 @@ New Features
   * Added a console command to testpmd app, ``show port (port_id) ptypes`` which
     gives ability to print port supported ptypes in different protocol layers.
 
+* **Added IOVA as VA support for KNI.**
+
+  Added IOVA = VA support for KNI, KNI can operate in IOVA = VA mode when
+  `iova-mode=va` eal option is passed to the application or when bus IOVA
+  scheme is selected as RTE_IOVA_VA.
 
 Removed Items
 -------------
diff --git a/lib/librte_eal/linux/eal/eal.c b/lib/librte_eal/linux/eal/eal.c
index 9e2d50c..a1c5bf6 100644
--- a/lib/librte_eal/linux/eal/eal.c
+++ b/lib/librte_eal/linux/eal/eal.c
@@ -922,6 +922,19 @@ static int rte_eal_vfio_setup(void)
 }
 #endif
 
+static enum rte_iova_mode
+rte_eal_kni_get_iova_mode(enum rte_iova_mode iova_mode)
+{
+	if (iova_mode == RTE_IOVA_VA) {
+#if KERNEL_VERSION(4, 6, 0) > LINUX_VERSION_CODE
+		iova_mode = RTE_IOVA_PA;
+		RTE_LOG(WARNING, EAL, "Forcing IOVA as 'PA' because KNI module does not support VA\n");
+#endif
+	}
+
+	return iova_mode;
+}
+
 static void rte_eal_init_alert(const char *msg)
 {
 	fprintf(stderr, "EAL: FATAL: %s\n", msg);
@@ -1085,24 +1098,16 @@ rte_eal_init(int argc, char **argv)
 				RTE_LOG(DEBUG, EAL, "IOMMU is not available, selecting IOVA as PA mode.\n");
 			}
 		}
-#ifdef RTE_LIBRTE_KNI
-		/* Workaround for KNI which requires physical address to work */
-		if (iova_mode == RTE_IOVA_VA &&
-				rte_eal_check_module("rte_kni") == 1) {
-			if (phys_addrs) {
-				iova_mode = RTE_IOVA_PA;
-				RTE_LOG(WARNING, EAL, "Forcing IOVA as 'PA' because KNI module is loaded\n");
-			} else {
-				RTE_LOG(DEBUG, EAL, "KNI can not work since physical addresses are unavailable\n");
-			}
-		}
-#endif
 		rte_eal_get_configuration()->iova_mode = iova_mode;
 	} else {
 		rte_eal_get_configuration()->iova_mode =
 			internal_config.iova_mode;
 	}
 
+	if (rte_eal_check_module("rte_kni") == 1)
+		rte_eal_get_configuration()->iova_mode =
+				rte_eal_kni_get_iova_mode(rte_eal_iova_mode());
+
 	if (rte_eal_iova_mode() == RTE_IOVA_PA && !phys_addrs) {
 		rte_eal_init_alert("Cannot use IOVA as 'PA' since physical addresses are not available");
 		rte_errno = EINVAL;
diff --git a/lib/librte_eal/linux/eal/include/rte_kni_common.h b/lib/librte_eal/linux/eal/include/rte_kni_common.h
index 46f75a7..2427a96 100644
--- a/lib/librte_eal/linux/eal/include/rte_kni_common.h
+++ b/lib/librte_eal/linux/eal/include/rte_kni_common.h
@@ -125,6 +125,7 @@ struct rte_kni_device_info {
 	unsigned int min_mtu;
 	unsigned int max_mtu;
 	uint8_t mac_addr[6];
+	uint8_t iova_mode;
 };
 
 #define KNI_DEVICE "kni"
diff --git a/lib/librte_kni/rte_kni.c b/lib/librte_kni/rte_kni.c
index 7fbcf22..7221280 100644
--- a/lib/librte_kni/rte_kni.c
+++ b/lib/librte_kni/rte_kni.c
@@ -97,11 +97,6 @@ static volatile int kni_fd = -1;
 int
 rte_kni_init(unsigned int max_kni_ifaces __rte_unused)
 {
-	if (rte_eal_iova_mode() != RTE_IOVA_PA) {
-		RTE_LOG(ERR, KNI, "KNI requires IOVA as PA\n");
-		return -1;
-	}
-
 	/* Check FD and open */
 	if (kni_fd < 0) {
 		kni_fd = open("/dev/" KNI_DEVICE, O_RDWR);
@@ -302,6 +297,8 @@ rte_kni_alloc(struct rte_mempool *pktmbuf_pool,
 	kni->group_id = conf->group_id;
 	kni->mbuf_size = conf->mbuf_size;
 
+	dev_info.iova_mode = (rte_eal_iova_mode() == RTE_IOVA_VA) ? 1 : 0;
+
 	ret = ioctl(kni_fd, RTE_KNI_IOCTL_CREATE, &dev_info);
 	if (ret < 0)
 		goto ioctl_fail;
-- 
2.8.4