[dpdk-dev] [PATCH v1 4/4] net/virtio: add election for packed vector NEON path

[Joyce Kong <joyce.kong@arm.com>]

Add NEON vectorized path selection logic. Default setting comes from
vectorized devarg, then checks each criteria.

Packed ring vectorized neon path need:
    NEON is supported by compiler and host
    VERSION_1 and IN_ORDER features are negotiated
    mergeable feature is not negotiated
    LRO offloading is disabled

Signed-off-by: Joyce Kong <joyce.kong@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
---
 doc/guides/nics/virtio.rst              |  6 +++---
 drivers/net/virtio/meson.build          |  1 +
 drivers/net/virtio/virtio_ethdev.c      | 19 +++++++++++++++----
 drivers/net/virtio/virtio_rxtx_packed.c |  2 ++
 drivers/net/virtio/virtio_user_ethdev.c |  2 +-
 5 files changed, 22 insertions(+), 8 deletions(-)

diff --git a/doc/guides/nics/virtio.rst b/doc/guides/nics/virtio.rst
index c03c2d0fe..b7be3aca1 100644
--- a/doc/guides/nics/virtio.rst
+++ b/doc/guides/nics/virtio.rst
@@ -483,11 +483,11 @@ according to below configuration:
 #. Packed virtqueue in-order non-mergeable path: If in-order feature is negotiated and
    Rx mergeable is not negotiated, this path will be selected.
 #. Packed virtqueue vectorized Rx path: If building and running environment support
-   AVX512 && in-order feature is negotiated && Rx mergeable is not negotiated &&
-   TCP_LRO Rx offloading is disabled && vectorized option enabled,
+   (AVX512 || NEON) && in-order feature is negotiated && Rx mergeable
+   is not negotiated && TCP_LRO Rx offloading is disabled && vectorized option enabled,
    this path will be selected.
 #. Packed virtqueue vectorized Tx path: If building and running environment support
-   AVX512 && in-order feature is negotiated && vectorized option enabled,
+   (AVX512 || NEON)  && in-order feature is negotiated && vectorized option enabled,
    this path will be selected.
 
 Rx/Tx callbacks of each Virtio path
diff --git a/drivers/net/virtio/meson.build b/drivers/net/virtio/meson.build
index 01b8de6d4..738d66746 100644
--- a/drivers/net/virtio/meson.build
+++ b/drivers/net/virtio/meson.build
@@ -32,6 +32,7 @@ if arch_subdir == 'x86'
 elif arch_subdir == 'ppc'
 	sources += files('virtio_rxtx_simple_altivec.c')
 elif arch_subdir == 'arm' and host_machine.cpu_family().startswith('aarch64')
+	sources += files('virtio_rxtx_packed.c')
 	sources += files('virtio_rxtx_simple_neon.c')
 endif
 
diff --git a/drivers/net/virtio/virtio_ethdev.c b/drivers/net/virtio/virtio_ethdev.c
index 6c233b75b..54a6d6ca9 100644
--- a/drivers/net/virtio/virtio_ethdev.c
+++ b/drivers/net/virtio/virtio_ethdev.c
@@ -1967,12 +1967,12 @@ eth_virtio_dev_init(struct rte_eth_dev *eth_dev)
 		if (!vtpci_packed_queue(hw)) {
 			hw->use_vec_rx = 1;
 		} else {
-#if !defined(CC_AVX512_SUPPORT)
-			PMD_DRV_LOG(INFO,
-				"building environment do not support packed ring vectorized");
-#else
+#if defined(CC_AVX512_SUPPORT) || defined(RTE_ARCH_ARM)
 			hw->use_vec_rx = 1;
 			hw->use_vec_tx = 1;
+#else
+			PMD_DRV_LOG(INFO,
+				"building environment do not support packed ring vectorized");
 #endif
 		}
 	}
@@ -2320,6 +2320,17 @@ virtio_dev_configure(struct rte_eth_dev *dev)
 			hw->use_vec_rx = 0;
 			hw->use_vec_tx = 0;
 		}
+#elif defined(RTE_ARCH_ARM)
+		if ((hw->use_vec_rx || hw->use_vec_tx) &&
+		    (!rte_cpu_get_flag_enabled(RTE_CPUFLAG_NEON) ||
+		     !vtpci_with_feature(hw, VIRTIO_F_IN_ORDER) ||
+		     !vtpci_with_feature(hw, VIRTIO_F_VERSION_1) ||
+		     rte_vect_get_max_simd_bitwidth() < RTE_VECT_SIMD_128)) {
+			PMD_DRV_LOG(INFO,
+				"disabled packed ring vectorized path for requirements not met");
+			hw->use_vec_rx = 0;
+			hw->use_vec_tx = 0;
+		}
 #else
 		hw->use_vec_rx = 0;
 		hw->use_vec_tx = 0;
diff --git a/drivers/net/virtio/virtio_rxtx_packed.c b/drivers/net/virtio/virtio_rxtx_packed.c
index 99d9a5a99..882dca36e 100644
--- a/drivers/net/virtio/virtio_rxtx_packed.c
+++ b/drivers/net/virtio/virtio_rxtx_packed.c
@@ -18,6 +18,8 @@
 
 #ifdef CC_AVX512_SUPPORT
 #include "virtio_rxtx_packed_avx.h"
+#elif defined(RTE_ARCH_ARM)
+#include "virtio_rxtx_packed_neon.h"
 #endif
 
 uint16_t
diff --git a/drivers/net/virtio/virtio_user_ethdev.c b/drivers/net/virtio/virtio_user_ethdev.c
index 40345193e..241808cd8 100644
--- a/drivers/net/virtio/virtio_user_ethdev.c
+++ b/drivers/net/virtio/virtio_user_ethdev.c
@@ -856,7 +856,7 @@ virtio_user_pmd_probe(struct rte_vdev_device *dev)
 
 	if (vectorized) {
 		if (packed_vq) {
-#if defined(CC_AVX512_SUPPORT)
+#if defined(CC_AVX512_SUPPORT) || defined(RTE_ARCH_ARM)
 			hw->use_vec_rx = 1;
 			hw->use_vec_tx = 1;
 #else
-- 
2.28.0