From: Kalesh AP <kalesh-anakkur.pura...@broadcom.com> When the driver receives RESET_NOTIFY async event from FW or detects a FW fatal error condition, it tries to recover from the error. When the driver fails to recover from the error condition, fixed to send device removal event to the application.
Fixes: df6cd7c1f73a ("net/bnxt: handle reset notify async event from FW") Cc: sta...@dpdk.org Signed-off-by: Kalesh AP <kalesh-anakkur.pura...@broadcom.com> Reviewed-by: Somnath Kotur <somnath.ko...@broadcom.com> Reviewed-by: Ajit Khaparde <ajit.khapa...@broadcom.com> --- drivers/net/bnxt/bnxt_ethdev.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/bnxt/bnxt_ethdev.c b/drivers/net/bnxt/bnxt_ethdev.c index e069559..5e8d369 100644 --- a/drivers/net/bnxt/bnxt_ethdev.c +++ b/drivers/net/bnxt/bnxt_ethdev.c @@ -4340,6 +4340,10 @@ static void bnxt_dev_recover(void *arg) err: bp->flags |= BNXT_FLAG_FATAL_ERROR; bnxt_uninit_resources(bp, false); + if (bp->eth_dev->data->dev_conf.intr_conf.rmv) + rte_eth_dev_callback_process(bp->eth_dev, + RTE_ETH_EVENT_INTR_RMV, + NULL); pthread_mutex_unlock(&bp->err_recovery_lock); PMD_DRV_LOG(ERR, "Failed to recover from FW reset\n"); } @@ -6395,6 +6399,7 @@ static int bnxt_pci_remove(struct rte_pci_device *pci_dev) static struct rte_pci_driver bnxt_rte_pmd = { .id_table = bnxt_pci_id_map, .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC | + RTE_PCI_DRV_INTR_RMV | RTE_PCI_DRV_PROBE_AGAIN, /* Needed in case of VF-REPs * and OVS-DPDK */ -- 2.10.1