Skip to contentSkip to conversation

net/null: fix multi-process rx and tx

PATCH Applied Yasufumi Ogawa 2 participants 4 messages Sep 29, 2019 – Oct 3, 2019 Network drivers

lore
Share & tools
lore
#0 lore raw

PATCH 1/1 net/null: fix multi-process rx and tx

Packet processing in secondary process cannot work because rx_pkt_burst and tx_pkt_burst in eth_dev are not initialized while probing device. This patch is to the initialization.

---
 drivers/net/null/rte_eth_null.c | 7 +++++++
 1 file changed, 7 insertions(+)
drivers/net/null/rte_eth_null.c +7 -0
index 0c60d241a..5a2010e3e 100644
@@ -586,6 +586,13 @@ rte_pmd_null_probe(struct rte_vdev_device *dev)
 		/* TODO: request info from primary to set up Rx and Tx */
 		eth_dev->dev_ops = &ops;
 		eth_dev->device = &dev->device;
+		if (packet_copy) {
+			eth_dev->rx_pkt_burst = eth_null_copy_rx;
+			eth_dev->tx_pkt_burst = eth_null_copy_tx;
+		} else {
+			eth_dev->rx_pkt_burst = eth_null_rx;
+			eth_dev->tx_pkt_burst = eth_null_tx;
+		}
 		rte_eth_dev_probing_finish(eth_dev);
 		return 0;
 	}
Signature · 1 line
2.17.1
Reviewed-by on v1 1/1
#1 lore raw
Quoted 18 lines · Yasufumi Ogawa

Packet processing in secondary process cannot work because rx_pkt_burst and tx_pkt_burst in eth_dev are not initialized while probing device. This patch is to the initialization.

---
 drivers/net/null/rte_eth_null.c | 7 +++++++
 1 file changed, 7 insertions(+)
drivers/net/null/rte_eth_null.c +0 -0
index 0c60d241a..5a2010e3e 100644
@@ -586,6 +586,13 @@ rte_pmd_null_probe(struct rte_vdev_device *dev)
 		/* TODO: request info from primary to set up Rx and Tx */
 		eth_dev->dev_ops = &ops;
 		eth_dev->device = &dev->device;

drivers/net/null/rte_eth_null.c rte_pmd_null_probe(struct rte_vdev_device *dev) · line 598

Quoted 10 lines
drivers/net/null/rte_eth_null.c +7 -0
+		if (packet_copy) {
+			eth_dev->rx_pkt_burst = eth_null_copy_rx;
+			eth_dev->tx_pkt_burst = eth_null_copy_tx;
+		} else {
+			eth_dev->rx_pkt_burst = eth_null_rx;
+			eth_dev->tx_pkt_burst = eth_null_tx;
+		}
 		rte_eth_dev_probing_finish(eth_dev);
 		return 0;
 	}

But this seems the issue for other virtual PMDs too, @Yasufumi, can you please check others too if you have any bandwidth for it?

I assume this is missing for a long time because there is not easy way to test them in secondary process, testpmd doesn't support the multi process. cc'ed testpmd and multi process maintainers, what do you think about adding multi process support to testpmd?

I tested with "examples/multi_process/symmetric_mp" sample app, it required fixing with null pmd:
1- Requested offload config was not supported by null pmd
2- promics_enable dev_ops was not implemented in null pmd

We should fix sample app / virtual pmds too so they can work together...

Applied
#2 lore raw
Quoted 24 lines · Ferruh Yigit
Quoted 23 lines · Yasufumi Ogawa

Packet processing in secondary process cannot work because rx_pkt_burst and tx_pkt_burst in eth_dev are not initialized while probing device. This patch is to the initialization.

---
 drivers/net/null/rte_eth_null.c | 7 +++++++
 1 file changed, 7 insertions(+)
drivers/net/null/rte_eth_null.c +6 -0
index 0c60d241a..5a2010e3e 100644
@@ -586,6 +586,13 @@ rte_pmd_null_probe(struct rte_vdev_device *dev)
 		/* TODO: request info from primary to set up Rx and Tx */
 		eth_dev->dev_ops = &ops;
 		eth_dev->device = &dev->device;
+		if (packet_copy) {
+			eth_dev->rx_pkt_burst = eth_null_copy_rx;
+			eth_dev->tx_pkt_burst = eth_null_copy_tx;
+		} else {
+			eth_dev->rx_pkt_burst = eth_null_rx;
+			eth_dev->tx_pkt_burst = eth_null_tx;
Quoted 8 lines

drivers/net/null/rte_eth_null.c rte_pmd_null_probe(struct rte_vdev_device *dev) · line 598

Quoted 5 lines
drivers/net/null/rte_eth_null.c +1 -0
+		}
 		rte_eth_dev_probing_finish(eth_dev);
 		return 0;
 	}
Fixes ee27edbe0c10 ("drivers/net: share vdev data to secondary process")

Applied to dpdk-next-net/master, thanks.

#3 lore raw
In reply to Ferruh Yigit
Quoted 33 lines · Ferruh Yigit
Quoted 18 lines · Yasufumi Ogawa

Packet processing in secondary process cannot work because rx_pkt_burst and tx_pkt_burst in eth_dev are not initialized while probing device. This patch is to the initialization.

---
  drivers/net/null/rte_eth_null.c | 7 +++++++
  1 file changed, 7 insertions(+)
drivers/net/null/rte_eth_null.c +0 -0
index 0c60d241a..5a2010e3e 100644
@@ -586,6 +586,13 @@ rte_pmd_null_probe(struct rte_vdev_device *dev)
  		/* TODO: request info from primary to set up Rx and Tx */
  		eth_dev->dev_ops = &ops;
  		eth_dev->device = &dev->device;

drivers/net/null/rte_eth_null.c rte_pmd_null_probe(struct rte_vdev_device *dev) · line 598

Quoted 10 lines
drivers/net/null/rte_eth_null.c +7 -0
+		if (packet_copy) {
+			eth_dev->rx_pkt_burst = eth_null_copy_rx;
+			eth_dev->tx_pkt_burst = eth_null_copy_tx;
+		} else {
+			eth_dev->rx_pkt_burst = eth_null_rx;
+			eth_dev->tx_pkt_burst = eth_null_tx;
+		}
  		rte_eth_dev_probing_finish(eth_dev);
  		return 0;
  	}
Quoted 2 lines

But this seems the issue for other virtual PMDs too, @Yasufumi, can you please check others too if you have any bandwidth for it?

Yes. I have also tried to fix other PMDs, and would like to make some updates for vhost and virtio next if possible.

Yasufumi

Quoted 15 lines

I assume this is missing for a long time because there is not easy way to test them in secondary process, testpmd doesn't support the multi process. cc'ed testpmd and multi process maintainers, what do you think about adding multi process support to testpmd?

I tested with "examples/multi_process/symmetric_mp" sample app, it required fixing with null pmd:
1- Requested offload config was not supported by null pmd
2- promics_enable dev_ops was not implemented in null pmd

We should fix sample app / virtual pmds too so they can work together...