app/testpmd: fix testpmd crash when quit with mlx5 avail_thresh enabled
Checks
Commit Message
When testpmd quit with mlx5 avail_thresh enabled, a rte timer handler
delays to reconfigure rx queue to re-arm this event. However at the same
time, testpmd is destroying rx queues.
It's never a valid use case for mlx5 avail_thresh. Before testpmd quit,
user should disable avail_thresh configuration to not handle the events.
This is documented in mlx5 driver guide.
To avoid the crash in such use case, check port status, if it is not
RTE_PORT_STARTED, don't process the avail_thresh event.
Fixes: 0edfc9b08316 ("app/testpmd: add Host Shaper command")
Signed-off-by: Spike Du <spiked@nvidia.com>
---
drivers/net/mlx5/mlx5_testpmd.c | 9 +++++++++
1 file changed, 9 insertions(+)
Comments
On 10/24/2022 8:44 AM, Spike Du wrote:
> When testpmd quit with mlx5 avail_thresh enabled, a rte timer handler
> delays to reconfigure rx queue to re-arm this event. However at the same
> time, testpmd is destroying rx queues.
> It's never a valid use case for mlx5 avail_thresh. Before testpmd quit,
> user should disable avail_thresh configuration to not handle the events.
> This is documented in mlx5 driver guide.
>
> To avoid the crash in such use case, check port status, if it is not
> RTE_PORT_STARTED, don't process the avail_thresh event.
>
> Fixes: 0edfc9b08316 ("app/testpmd: add Host Shaper command")
>
> Signed-off-by: Spike Du <spiked@nvidia.com>
Acked-by: Aman Singh<aman.deep.singh@intel.com>
> ---
> drivers/net/mlx5/mlx5_testpmd.c | 9 +++++++++
> 1 file changed, 9 insertions(+)
>
> diff --git a/drivers/net/mlx5/mlx5_testpmd.c b/drivers/net/mlx5/mlx5_testpmd.c
> index ed84583..1a9ec78 100644
> --- a/drivers/net/mlx5/mlx5_testpmd.c
> +++ b/drivers/net/mlx5/mlx5_testpmd.c
> @@ -25,6 +25,7 @@
>
> static uint8_t host_shaper_avail_thresh_triggered[RTE_MAX_ETHPORTS];
> #define SHAPER_DISABLE_DELAY_US 100000 /* 100ms */
> +extern struct rte_port *ports;
This might not be needed, as we have testpmd.h included.
>
> /**
> * Disable the host shaper and re-arm available descriptor threshold event.
> @@ -39,7 +40,15 @@
> uint16_t port_id = port_rxq_id & 0xffff;
> uint16_t qid = (port_rxq_id >> 16) & 0xffff;
> struct rte_eth_rxq_info qinfo;
> + struct rte_port *port;
>
> + port = &ports[port_id];
> + if (port->port_status != RTE_PORT_STARTED) {
> + printf("%s port_status(%d) is incorrect, stop avail_thresh "
> + "event processing.\n",
> + __func__, port->port_status);
> + return;
> + }
> printf("%s disable shaper\n", __func__);
> if (rte_eth_rx_queue_info_get(port_id, qid, &qinfo)) {
> printf("rx_queue_info_get returns error\n");
@@ -25,6 +25,7 @@
static uint8_t host_shaper_avail_thresh_triggered[RTE_MAX_ETHPORTS];
#define SHAPER_DISABLE_DELAY_US 100000 /* 100ms */
+extern struct rte_port *ports;
/**
* Disable the host shaper and re-arm available descriptor threshold event.
@@ -39,7 +40,15 @@
uint16_t port_id = port_rxq_id & 0xffff;
uint16_t qid = (port_rxq_id >> 16) & 0xffff;
struct rte_eth_rxq_info qinfo;
+ struct rte_port *port;
+ port = &ports[port_id];
+ if (port->port_status != RTE_PORT_STARTED) {
+ printf("%s port_status(%d) is incorrect, stop avail_thresh "
+ "event processing.\n",
+ __func__, port->port_status);
+ return;
+ }
printf("%s disable shaper\n", __func__);
if (rte_eth_rx_queue_info_get(port_id, qid, &qinfo)) {
printf("rx_queue_info_get returns error\n");