[dpdk-dev] [PATCH v4] net/i40e: fix Rx instability with vector mode

[Beilei Xing]

Previously, there is instability during vector Rx if descriptor
number is not power of 2, e.g. process hang and some Rx packets
are unexpectedly empty. That's because vector Rx mode assumes Rx
descriptor number is power of 2 when doing bit mask.
This patch allows vector mode only when the number of Rx descriptor
is power of 2.

Fixes: 8e109464c022 ("i40e: allow vector Rx and Tx usage")
Fixes: a3c83a2527e1 ("net/i40e: enable runtime queue setup")
Cc: stable at dpdk.org

Signed-off-by: Beilei Xing <beilei.xing at intel.com>
---
v4 changes:
 - Configure rx_vec_allowed in i40e_rx_vec_dev_conf_condition_check function.
v3 changes:
 - Add branch for non-first queue during runtime queue setup.
 - Use function rte_is_power_of_2().
 - Configure rx_vec_allowed during setting Rx function.
v2 changes:
 - rx_vec_allowed is global configuration, avoid overwrite.

 doc/guides/nics/i40e.rst                |  7 ++++++
 drivers/net/i40e/i40e_rxtx.c            |  5 +++++
 drivers/net/i40e/i40e_rxtx_vec_common.h | 38 +++++++++++++++++++++++++++++++++
 3 files changed, 50 insertions(+)

diff --git a/doc/guides/nics/i40e.rst b/doc/guides/nics/i40e.rst
index ab3928a..bfacbd1 100644
--- a/doc/guides/nics/i40e.rst
+++ b/doc/guides/nics/i40e.rst
@@ -172,6 +172,13 @@ Runtime Config Options
 
   -w 84:00.0,use-latest-supported-vec=1
 
+Vector RX Pre-conditions
+~~~~~~~~~~~~~~~~~~~~~~~~
+For Vector RX it is assumed that the number of descriptor rings will be a power
+of 2. With this pre-condition, the ring pointer can easily scroll back to the
+head after hitting the tail without a conditional check. In addition Vector RX
+can use this assumption to do a bit mask using ``ring_size - 1``.
+
 Driver compilation and testing
 ------------------------------
 
diff --git a/drivers/net/i40e/i40e_rxtx.c b/drivers/net/i40e/i40e_rxtx.c
index a827456..5bb1a3c 100644
--- a/drivers/net/i40e/i40e_rxtx.c
+++ b/drivers/net/i40e/i40e_rxtx.c
@@ -1741,6 +1741,11 @@ i40e_dev_rx_queue_setup_runtime(struct rte_eth_dev *dev,
 			ad->rx_bulk_alloc_allowed = false;
 		i40e_set_rx_function(dev);
 		return 0;
+	} else if (ad->rx_vec_allowed && !rte_is_power_of_2(rxq->nb_rx_desc)) {
+		PMD_DRV_LOG(ERR, "Vector mode is allowed, but descriptor"
+			    " number %d of queue %d isn't power of 2",
+			    rxq->nb_rx_desc, rxq->queue_id);
+		return -EINVAL;
 	}
 
 	/* check bulk alloc conflict */
diff --git a/drivers/net/i40e/i40e_rxtx_vec_common.h b/drivers/net/i40e/i40e_rxtx_vec_common.h
index f00f6d6..0e6ffa0 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_common.h
+++ b/drivers/net/i40e/i40e_rxtx_vec_common.h
@@ -192,8 +192,13 @@ static inline int
 i40e_rx_vec_dev_conf_condition_check_default(struct rte_eth_dev *dev)
 {
 #ifndef RTE_LIBRTE_IEEE1588
+	struct i40e_adapter *ad =
+		I40E_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
 	struct rte_eth_rxmode *rxmode = &dev->data->dev_conf.rxmode;
 	struct rte_fdir_conf *fconf = &dev->data->dev_conf.fdir_conf;
+	struct i40e_rx_queue *rxq;
+	uint16_t desc, i;
+	bool first_queue;
 
 	/* no fdir support */
 	if (fconf->mode != RTE_FDIR_MODE_NONE)
@@ -207,6 +212,39 @@ i40e_rx_vec_dev_conf_condition_check_default(struct rte_eth_dev *dev)
 	if (rxmode->offloads & DEV_RX_OFFLOAD_VLAN_EXTEND)
 		return -1;
 
+	/**
+	 * Vector mode is allowed only when number of Rx queue
+	 * descriptor is power of 2.
+	 */
+	if (!dev->data->dev_started) {
+		first_queue = true;
+		for (i = 0; i < dev->data->nb_rx_queues; i++) {
+			rxq = dev->data->rx_queues[i];
+			if (!rxq)
+				continue;
+			desc = rxq->nb_rx_desc;
+			if (first_queue)
+				ad->rx_vec_allowed =
+					rte_is_power_of_2(desc);
+			else
+				ad->rx_vec_allowed =
+					ad->rx_vec_allowed ?
+					rte_is_power_of_2(desc) :
+					ad->rx_vec_allowed;
+			first_queue = false;
+		}
+	} else {
+		/* Only check the first queue's descriptor number */
+		for (i = 0; i < dev->data->nb_rx_queues; i++) {
+			rxq = dev->data->rx_queues[i];
+			if (!rxq)
+				continue;
+			desc = rxq->nb_rx_desc;
+			ad->rx_vec_allowed = rte_is_power_of_2(desc);
+			break;
+		}
+	}
+
 	return 0;
 #else
 	RTE_SET_USED(dev);
-- 
2.5.5