On 10/8/22 23:36, Chengwen Feng wrote:
> uint16_t slaves[RTE_MAX_ETHPORTS];
> uint8_t tx_failed_flag = 0;
> uint16_t num_of_slaves;
> + uint16_t num_tx_prep;
>
> uint16_t max_nb_of_tx_pkts = 0;
>
> @@ -1320,12 +1339,18 @@ bond_ethdev_tx_burst_broadcast(void *queue, struct rte_mbuf **bufs,
> for (i = 0; i < nb_pkts; i++)
> rte_pktmbuf_refcnt_update(bufs[i], num_of_slaves - 1);
>
> + /* It is rare that bond different PMDs together, so just call tx-prepare once */
> + num_tx_prep = rte_eth_tx_prepare(slaves[0], bd_tx_q->queue_id,
> + bufs, nb_pkts);
You probably want to do this before you update the refcnt on the mbufs.
Otherwise, the common rte_eth_tx_prepare operation, rte_vlan_insert, will
fail since the refcnt will not be 1.
> + if (unlikely(num_tx_prep < nb_pkts))
> + tx_failed_flag = 1;
> +
> /* Transmit burst on each active slave */
> for (i = 0; i < num_of_slaves; i++) {
> slave_tx_total[i] = rte_eth_tx_burst(slaves[i], bd_tx_q->queue_id,
> - bufs, nb_pkts);
> + bufs, num_tx_prep);
>
> - if (unlikely(slave_tx_total[i] < nb_pkts))
> + if (unlikely(slave_tx_total[i] < num_tx_prep))
> tx_failed_flag = 1;
>
> /* record the value and slave index for the slave which transmits the
> diff --git a/lib/ethdev/rte_ethdev.h b/lib/ethdev/rte_ethdev.h
> index e8d1e1c658..b0396bb86e 100644
> --- a/lib/ethdev/rte_ethdev.h
> +++ b/lib/ethdev/rte_ethdev.h
> @@ -6031,6 +6031,10 @@ uint16_t rte_eth_call_tx_callbacks(uint16_t port_id, uint16_t queue_id,
> * @see rte_eth_tx_prepare to perform some prior checks or adjustments
> * for offloads.
> *
> + * @note This function must not modify mbufs (including packets data) unless
> + * the refcnt is 1. The exception is the bonding PMD, which does not have
> + * tx-prepare function, in this case, mbufs maybe modified.
Exactly. See my comment about calling prepare before you modify the refcnt.
> + *
> * @param port_id
> * The port identifier of the Ethernet device.
> * @param queue_id
Hi Chas,
On 2022/10/11 3:42, Chas Williams wrote:
>
>
> On 10/8/22 23:36, Chengwen Feng wrote:
>> uint16_t slaves[RTE_MAX_ETHPORTS];
>> uint8_t tx_failed_flag = 0;
>> uint16_t num_of_slaves;
>> + uint16_t num_tx_prep;
>> uint16_t max_nb_of_tx_pkts = 0;
>> @@ -1320,12 +1339,18 @@ bond_ethdev_tx_burst_broadcast(void *queue, struct rte_mbuf **bufs,
>> for (i = 0; i < nb_pkts; i++)
>> rte_pktmbuf_refcnt_update(bufs[i], num_of_slaves - 1);
>> + /* It is rare that bond different PMDs together, so just call tx-prepare once */
>> + num_tx_prep = rte_eth_tx_prepare(slaves[0], bd_tx_q->queue_id,
>> + bufs, nb_pkts);
>
> You probably want to do this before you update the refcnt on the mbufs.
> Otherwise, the common rte_eth_tx_prepare operation, rte_vlan_insert, will
> fail since the refcnt will not be 1.
nice catch
v5 already sent to fix it, please review it. Thanks
>
>> + if (unlikely(num_tx_prep < nb_pkts))
>> + tx_failed_flag = 1;
>> +
>> /* Transmit burst on each active slave */
>> for (i = 0; i < num_of_slaves; i++) {
>> slave_tx_total[i] = rte_eth_tx_burst(slaves[i], bd_tx_q->queue_id,
>> - bufs, nb_pkts);
>> + bufs, num_tx_prep);
>> - if (unlikely(slave_tx_total[i] < nb_pkts))
>> + if (unlikely(slave_tx_total[i] < num_tx_prep))
>> tx_failed_flag = 1;
>> /* record the value and slave index for the slave which transmits the
>> diff --git a/lib/ethdev/rte_ethdev.h b/lib/ethdev/rte_ethdev.h
>> index e8d1e1c658..b0396bb86e 100644
>> --- a/lib/ethdev/rte_ethdev.h
>> +++ b/lib/ethdev/rte_ethdev.h
>> @@ -6031,6 +6031,10 @@ uint16_t rte_eth_call_tx_callbacks(uint16_t port_id, uint16_t queue_id,
>> * @see rte_eth_tx_prepare to perform some prior checks or adjustments
>> * for offloads.
>> *
>> + * @note This function must not modify mbufs (including packets data) unless
>> + * the refcnt is 1. The exception is the bonding PMD, which does not have
>> + * tx-prepare function, in this case, mbufs maybe modified.
>
> Exactly. See my comment about calling prepare before you modify the refcnt.
>
>> + *
>> * @param port_id
>> * The port identifier of the Ethernet device.
>> * @param queue_id
> .
@@ -636,9 +636,12 @@ tx_machine(struct bond_dev_private *internals, uint16_t slave_id)
return;
}
} else {
- uint16_t pkts_sent = rte_eth_tx_burst(slave_id,
+ uint16_t pkts_sent = rte_eth_tx_prepare(slave_id,
internals->mode4.dedicated_queues.tx_qid,
&lacp_pkt, 1);
+ pkts_sent = rte_eth_tx_burst(slave_id,
+ internals->mode4.dedicated_queues.tx_qid,
+ &lacp_pkt, pkts_sent);
if (pkts_sent != 1) {
rte_pktmbuf_free(lacp_pkt);
set_warning_flags(port, WRN_TX_QUEUE_FULL);
@@ -1371,9 +1374,12 @@ bond_mode_8023ad_handle_slow_pkt(struct bond_dev_private *internals,
}
} else {
/* Send packet directly to the slow queue */
- uint16_t tx_count = rte_eth_tx_burst(slave_id,
+ uint16_t tx_count = rte_eth_tx_prepare(slave_id,
internals->mode4.dedicated_queues.tx_qid,
&pkt, 1);
+ tx_count = rte_eth_tx_burst(slave_id,
+ internals->mode4.dedicated_queues.tx_qid,
+ &pkt, tx_count);
if (tx_count != 1) {
/* reset timer */
port->rx_marker_timer = 0;
@@ -602,8 +602,11 @@ bond_ethdev_tx_burst_round_robin(void *queue, struct rte_mbuf **bufs,
/* Send packet burst on each slave device */
for (i = 0; i < num_of_slaves; i++) {
if (slave_nb_pkts[i] > 0) {
+ num_tx_slave = rte_eth_tx_prepare(slaves[i],
+ bd_tx_q->queue_id, slave_bufs[i],
+ slave_nb_pkts[i]);
num_tx_slave = rte_eth_tx_burst(slaves[i], bd_tx_q->queue_id,
- slave_bufs[i], slave_nb_pkts[i]);
+ slave_bufs[i], num_tx_slave);
/* if tx burst fails move packets to end of bufs */
if (unlikely(num_tx_slave < slave_nb_pkts[i])) {
@@ -628,6 +631,7 @@ bond_ethdev_tx_burst_active_backup(void *queue,
{
struct bond_dev_private *internals;
struct bond_tx_queue *bd_tx_q;
+ uint16_t nb_prep_pkts;
bd_tx_q = (struct bond_tx_queue *)queue;
internals = bd_tx_q->dev_private;
@@ -635,8 +639,11 @@ bond_ethdev_tx_burst_active_backup(void *queue,
if (internals->active_slave_count < 1)
return 0;
+ nb_prep_pkts = rte_eth_tx_prepare(internals->current_primary_port,
+ bd_tx_q->queue_id, bufs, nb_pkts);
+
return rte_eth_tx_burst(internals->current_primary_port, bd_tx_q->queue_id,
- bufs, nb_pkts);
+ bufs, nb_prep_pkts);
}
static inline uint16_t
@@ -910,7 +917,7 @@ bond_ethdev_tx_burst_tlb(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
struct rte_eth_dev *primary_port =
&rte_eth_devices[internals->primary_port];
- uint16_t num_tx_total = 0;
+ uint16_t num_tx_total = 0, num_tx_prep;
uint16_t i, j;
uint16_t num_of_slaves = internals->active_slave_count;
@@ -951,8 +958,10 @@ bond_ethdev_tx_burst_tlb(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
#endif
}
- num_tx_total += rte_eth_tx_burst(slaves[i], bd_tx_q->queue_id,
+ num_tx_prep = rte_eth_tx_prepare(slaves[i], bd_tx_q->queue_id,
bufs + num_tx_total, nb_pkts - num_tx_total);
+ num_tx_total += rte_eth_tx_burst(slaves[i], bd_tx_q->queue_id,
+ bufs + num_tx_total, num_tx_prep);
if (num_tx_total == nb_pkts)
break;
@@ -1064,8 +1073,10 @@ bond_ethdev_tx_burst_alb(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
/* Send ARP packets on proper slaves */
for (i = 0; i < RTE_MAX_ETHPORTS; i++) {
if (slave_bufs_pkts[i] > 0) {
- num_send = rte_eth_tx_burst(i, bd_tx_q->queue_id,
+ num_send = rte_eth_tx_prepare(i, bd_tx_q->queue_id,
slave_bufs[i], slave_bufs_pkts[i]);
+ num_send = rte_eth_tx_burst(i, bd_tx_q->queue_id,
+ slave_bufs[i], num_send);
for (j = 0; j < slave_bufs_pkts[i] - num_send; j++) {
bufs[nb_pkts - 1 - num_not_send - j] =
slave_bufs[i][nb_pkts - 1 - j];
@@ -1088,8 +1099,10 @@ bond_ethdev_tx_burst_alb(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
/* Send update packets on proper slaves */
for (i = 0; i < RTE_MAX_ETHPORTS; i++) {
if (update_bufs_pkts[i] > 0) {
+ num_send = rte_eth_tx_prepare(i, bd_tx_q->queue_id,
+ update_bufs[i], update_bufs_pkts[i]);
num_send = rte_eth_tx_burst(i, bd_tx_q->queue_id, update_bufs[i],
- update_bufs_pkts[i]);
+ num_send);
for (j = num_send; j < update_bufs_pkts[i]; j++) {
rte_pktmbuf_free(update_bufs[i][j]);
}
@@ -1158,9 +1171,12 @@ tx_burst_balance(void *queue, struct rte_mbuf **bufs, uint16_t nb_bufs,
if (slave_nb_bufs[i] == 0)
continue;
- slave_tx_count = rte_eth_tx_burst(slave_port_ids[i],
+ slave_tx_count = rte_eth_tx_prepare(slave_port_ids[i],
bd_tx_q->queue_id, slave_bufs[i],
slave_nb_bufs[i]);
+ slave_tx_count = rte_eth_tx_burst(slave_port_ids[i],
+ bd_tx_q->queue_id, slave_bufs[i],
+ slave_tx_count);
total_tx_count += slave_tx_count;
@@ -1243,8 +1259,10 @@ tx_burst_8023ad(void *queue, struct rte_mbuf **bufs, uint16_t nb_bufs,
if (rte_ring_dequeue(port->tx_ring,
(void **)&ctrl_pkt) != -ENOENT) {
- slave_tx_count = rte_eth_tx_burst(slave_port_ids[i],
+ slave_tx_count = rte_eth_tx_prepare(slave_port_ids[i],
bd_tx_q->queue_id, &ctrl_pkt, 1);
+ slave_tx_count = rte_eth_tx_burst(slave_port_ids[i],
+ bd_tx_q->queue_id, &ctrl_pkt, slave_tx_count);
/*
* re-enqueue LAG control plane packets to buffering
* ring if transmission fails so the packet isn't lost.
@@ -1298,6 +1316,7 @@ bond_ethdev_tx_burst_broadcast(void *queue, struct rte_mbuf **bufs,
uint16_t slaves[RTE_MAX_ETHPORTS];
uint8_t tx_failed_flag = 0;
uint16_t num_of_slaves;
+ uint16_t num_tx_prep;
uint16_t max_nb_of_tx_pkts = 0;
@@ -1320,12 +1339,18 @@ bond_ethdev_tx_burst_broadcast(void *queue, struct rte_mbuf **bufs,
for (i = 0; i < nb_pkts; i++)
rte_pktmbuf_refcnt_update(bufs[i], num_of_slaves - 1);
+ /* It is rare that bond different PMDs together, so just call tx-prepare once */
+ num_tx_prep = rte_eth_tx_prepare(slaves[0], bd_tx_q->queue_id,
+ bufs, nb_pkts);
+ if (unlikely(num_tx_prep < nb_pkts))
+ tx_failed_flag = 1;
+
/* Transmit burst on each active slave */
for (i = 0; i < num_of_slaves; i++) {
slave_tx_total[i] = rte_eth_tx_burst(slaves[i], bd_tx_q->queue_id,
- bufs, nb_pkts);
+ bufs, num_tx_prep);
- if (unlikely(slave_tx_total[i] < nb_pkts))
+ if (unlikely(slave_tx_total[i] < num_tx_prep))
tx_failed_flag = 1;
/* record the value and slave index for the slave which transmits the
@@ -6031,6 +6031,10 @@ uint16_t rte_eth_call_tx_callbacks(uint16_t port_id, uint16_t queue_id,
* @see rte_eth_tx_prepare to perform some prior checks or adjustments
* for offloads.
*
+ * @note This function must not modify mbufs (including packets data) unless
+ * the refcnt is 1. The exception is the bonding PMD, which does not have
+ * tx-prepare function, in this case, mbufs maybe modified.
+ *
* @param port_id
* The port identifier of the Ethernet device.
* @param queue_id