> -----Original Message-----
> From: Jeff Daly <je...@silicom-usa.com>
> Sent: Friday, May 20, 2022 2:03 AM
> To: dev@dpdk.org; Yang, Qiming <qiming.y...@intel.com>; Wu, Wenjun1
> <wenjun1...@intel.com>
> Cc: Stephen Douthit <steph...@silicom-usa.com>
> Subject: [PATCH 1/3] ixgbe: make link update thread periodic
>
> Rather than run-to-completion, allow the link update thread to be periodic.
> This will set the stage for properly handling hot-plugging.
Could you explain more about what's the hot-plugging issue with
run-to-completion you try to fix?
>
> Signed-off-by: Jeff Daly <je...@silicom-usa.com>
> Inspired-by: Stephen Douthit <steph...@silicom-usa.com>
> ---
> drivers/net/ixgbe/base/ixgbe_common.c | 4 +-
> drivers/net/ixgbe/ixgbe_ethdev.c | 180 ++++++++++----------------
> 2 files changed, 71 insertions(+), 113 deletions(-)
>
> diff --git a/drivers/net/ixgbe/base/ixgbe_common.c
> b/drivers/net/ixgbe/base/ixgbe_common.c
> index aa843bd5c4a5..712062306491 100644
> --- a/drivers/net/ixgbe/base/ixgbe_common.c
> +++ b/drivers/net/ixgbe/base/ixgbe_common.c
> @@ -4154,8 +4154,8 @@ s32 ixgbe_check_mac_link_generic(struct
> ixgbe_hw *hw, ixgbe_link_speed *speed,
> break;
> case ixgbe_mac_X550EM_x:
> case ixgbe_mac_X550EM_a:
> - sfp_cage_full = IXGBE_READ_REG(hw, IXGBE_ESDP)
> &
> - IXGBE_ESDP_SDP0;
> + sfp_cage_full = !(IXGBE_READ_REG(hw, IXGBE_ESDP)
> &
> + IXGBE_ESDP_SDP0);
> break;
> default:
> /* sanity check - No SFP+ devices here */ diff --git
Looks like you change the behavior of link status check for x550.
I'm not an ixgbe expert, but I know this is not kernel driver's implementation.
So do you think this is a fix for both DPDK and kernel driver? if it is,
please move this change into a separate patch and we need to reach the right
expert to approve this.
