> Subject: [PATCH 5/5] net/iavf: improve VF reset detection on fast ARQ flip
>
> During PF-initiated reset or a remote/ToR switch link-flap,
> the PF toggles the admin receive queue enable bit (ARQLEN1)
> so quickly around a VF reset that the VF's sampling window
> misses it, leaving the PF and the VF states out of sync
> and the data path stalled.
>
> Complement the ARQLEN1 check with VFGEN_RSTAT
> (VIRTCHNL_VFR_INPROGRESS) and shorten the poll interval to
> 5 ms (with a proportionally larger count, keeping the ~10 s
> budget), matching the Linux kernel iavf driver.
> When the VFR is still not observed, proceed with recovery
> instead of bailing out so the PF and the VF states converge.
>
> Fixes: ada64daa1a5b ("net/iavf: fix VF reset for flow director rule")
> Fixes: 80fb3c920458 ("net/iavf: fix crash on VF start")
> Cc: [email protected]
>
> Signed-off-by: Anurag Mandal <[email protected]>
> ---
> drivers/net/intel/iavf/iavf.h | 1 +
> drivers/net/intel/iavf/iavf_ethdev.c | 41 +++++++++++++++++++++-------
> 2 files changed, 32 insertions(+), 10 deletions(-)
>
> diff --git a/drivers/net/intel/iavf/iavf.h b/drivers/net/intel/iavf/iavf.h
> index 037bc8436f..5e49e81447 100644
> --- a/drivers/net/intel/iavf/iavf.h
> +++ b/drivers/net/intel/iavf/iavf.h
> @@ -21,6 +21,7 @@
> #define IAVF_AQ_BUF_SZ 4096
> #define IAVF_RESET_WAIT_CNT 2000
> #define IAVF_RESET_DETECTED_CNT 500
> +#define IAVF_RESET_POLL_SCALE 4 /* Poll-interval scale for reset
> detection
> */
> #define IAVF_BUF_SIZE_MIN 1024
> #define IAVF_FRAME_SIZE_MAX 9728
> #define IAVF_QUEUE_BASE_ADDR_UNIT 128
> diff --git a/drivers/net/intel/iavf/iavf_ethdev.c
> b/drivers/net/intel/iavf/iavf_ethdev.c
> index f6ce339b0c..21bac51467 100644
> --- a/drivers/net/intel/iavf/iavf_ethdev.c
> +++ b/drivers/net/intel/iavf/iavf_ethdev.c
> @@ -3235,7 +3235,9 @@ iavf_dev_close(struct rte_eth_dev *dev)
> /* remove RSS configuration */
> iavf_hash_uninit(adapter);
>
> - iavf_flow_flush(dev, NULL);
> + /* Skip the virtchnl-emitting teardown on a PF-initiated reset */
> + if (!vf->pf_reset_in_progress)
> + iavf_flow_flush(dev, NULL);
This seems like a valid change but unrelated to the rest of the commit.
Consider splitting it out.
> iavf_flow_uninit(adapter);
>
> /*
> @@ -3358,8 +3360,26 @@ iavf_dev_reset(struct rte_eth_dev *dev)
> static inline bool
> iavf_is_reset(struct iavf_hw *hw)
> {
> - return !(IAVF_READ_REG(hw, IAVF_VF_ARQLEN1) &
> - IAVF_VF_ARQLEN1_ARQENABLE_MASK);
> + uint32_t rstat;
> +
> + /* ARQ has been disabled by the PF as part of the VFR. */
> + if (!(IAVF_READ_REG(hw, IAVF_VF_ARQLEN1) &
> + IAVF_VF_ARQLEN1_ARQENABLE_MASK))
> + return true;
> +
> + /*
> + * VFGEN_RSTAT reports VIRTCHNL_VFR_INPROGRESS.
> + * At times, the PF flips ARQENABLE so quickly
> + * around a VFR that the ARQLEN1 sample window
> + * misses it. Using VFGEN_RSTAT, as a
> + * complementary indicator, prevents from
> + * missing a reset that really did happen.
> + */
> + rstat = (IAVF_READ_REG(hw, IAVF_VFGEN_RSTAT) &
> + IAVF_VFGEN_RSTAT_VFR_STATE_MASK) >>
> + IAVF_VFGEN_RSTAT_VFR_STATE_SHIFT;
> +
> + return rstat == VIRTCHNL_VFR_INPROGRESS;
> }
>
> static bool
> @@ -3368,11 +3388,14 @@ iavf_is_reset_detected(struct iavf_adapter
> *adapter)
> struct iavf_hw *hw = IAVF_DEV_PRIVATE_TO_HW(adapter);
> int i;
>
> - /* poll until we see the reset actually happen */
> - for (i = 0; i < IAVF_RESET_DETECTED_CNT; i++) {
> + /*
> + * Poll until the reset actually happen.
> + * Poll every 5 ms to catch the fast ARQ flips.
> + */
> + for (i = 0; i < IAVF_RESET_DETECTED_CNT * IAVF_RESET_POLL_SCALE;
> i++) {
> if (iavf_is_reset(hw))
> return true;
> - rte_delay_ms(20);
> + rte_delay_us(5000);
> }
>
> return false;
> @@ -3423,10 +3446,8 @@ iavf_handle_hw_reset(struct rte_eth_dev *dev,
> bool vf_initiated_reset)
> if (!dev->data->dev_started)
> return;
>
> - if (!iavf_is_reset_detected(adapter)) {
> - PMD_DRV_LOG(DEBUG, "reset not start");
> - return;
> - }
> + if (!iavf_is_reset_detected(adapter))
> + PMD_DRV_LOG(WARNING, "VFR not observed;
> recovering anyway");
> }
>
> vf->in_reset_recovery = true;
> --
> 2.34.1
