RE: [PATCH v3] net/ixgbe: add vector Rx parameter check

["Rong, Leyi" <leyi.rong@intel.com>]

> -----Original Message-----
> From: Bin Zheng <zhengbin.89740@bytedance.com>
> Sent: Friday, December 10, 2021 4:22 PM
> To: dev@dpdk.org
> Cc: Wang, Haiyue <haiyue.wang@intel.com>; liangma@liangbit.com;
> stable@dpdk.org; Rong, Leyi <leyi.rong@intel.com>; Bin Zheng
> <zhengbin.89740@bytedance.com>; jia.guo@intel.com
> Subject: [PATCH v3] net/ixgbe: add vector Rx parameter check
> 
> Under the circumstance that `rx_tail` wrap back to zero and the advance speed
> of `rx_tail` is greater than `rxrearm_start`, `rx_tail` will catch up with
> `rxrearm_start` and surpass it.
> This may cause some mbufs be reused by application.
> 
> So we need to make some restrictions to ensure that  `rx_tail` will not exceed
> `rxrearm_start`.
> 
> e.g.
> 
> RDH: 972 RDT: 991 rxrearm_nb: 991 rxrearm_start: 992 rx_tail: 959
> RDH: 1004 RDT: 1023 rxrearm_nb: 991 rxrearm_start: 0 rx_tail: 991
> RDH: 12 RDT: 31 rxrearm_nb: 991 rxrearm_start: 32 rx_tail: 1023
> RDH: 31 RDT: 63 rxrearm_nb: 960 rxrearm_start: 64 rx_tail: 0
> RDH: 95 RDT: 95 rxrearm_nb: 1016 rxrearm_start: 96 rx_tail: 88
> RDH: 95 RDT: 127 rxrearm_nb: 991 rxrearm_start: 128 rx_tail: 95 ...
> RDH: 908 RDT: 927 rxrearm_nb: 991 rxrearm_start: 928 rx_tail: 895
> RDH: 940 RDT: 959 rxrearm_nb: 991 rxrearm_start: 960 rx_tail: 927
> RDH: 980 RDT: 991 rxrearm_nb: 991 rxrearm_start: 992 rx_tail: 959
> RDH: 991 RDT: 991 rxrearm_nb: 1026 rxrearm_start: 992 rx_tail: 994
> 
> when `rx_tail` catches up with `rxrearm_start`,
> 2(994 - 992) mbufs be reused by application !
> 
> Bugzilla ID: 882
> Fixes: 5a3cca342417 ("net/ixgbe: fix vector Rx")
> Cc: jia.guo@intel.com
> Cc: stable@dpdk.org
> 
> Signed-off-by: Bin Zheng <zhengbin.89740@bytedance.com>
> ---
>  drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c | 11 +++++++++++
>  1 file changed, 11 insertions(+)
> 
> diff --git a/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c
> b/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c
> index 1eed949495..4654d0adec 100644
> --- a/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c
> +++ b/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c
> @@ -364,6 +364,17 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq,
> struct rte_mbuf **rx_pkts,
>  	uint8_t vlan_flags;
>  	uint16_t udp_p_flag = 0; /* Rx Descriptor UDP header present */
> 
> +	/*
> +	 * Under the circumstance that `rx_tail` wrap back to zero
> +	 * and the advance speed of `rx_tail` is greater than `rxrearm_start`,
> +	 * `rx_tail` will catch up with `rxrearm_start` and surpass it.
> +	 * This may cause some mbufs be reused by application.
> +	 *
> +	 * So we need to make some restrictions to ensure that
> +	 * `rx_tail` will not exceed `rxrearm_start`.
> +	 */
> +	nb_pkts = RTE_MIN(nb_pkts, RTE_IXGBE_RXQ_REARM_THRESH);
> +
>  	/* nb_pkts has to be floor-aligned to RTE_IXGBE_DESCS_PER_LOOP */
>  	nb_pkts = RTE_ALIGN_FLOOR(nb_pkts, RTE_IXGBE_DESCS_PER_LOOP);
> 
> --
> 2.25.1

Acked-by: Leyi Rong <leyi.rong@intel.com>