* [PATCH] net/ixgbe: add vector Rx parameter check
@ 2021-12-02 3:15 Bin Zheng
0 siblings, 0 replies; 3+ messages in thread
From: Bin Zheng @ 2021-12-02 3:15 UTC (permalink / raw)
To: dev; +Cc: haiyue.wang, liangma, Bin Zheng, jia.guo, stable
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 applicaion.
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 applicaion !
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 | 18 +++++++++++++++---
1 file changed, 15 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c b/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c
index 1eed949495..33d2e96266 100644
--- a/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c
+++ b/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c
@@ -364,9 +364,6 @@ _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 */
- /* 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);
-
/* Just the act of getting into the function from the application is
* going to cost about 7 cycles
*/
@@ -380,6 +377,21 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts,
if (rxq->rxrearm_nb > RTE_IXGBE_RXQ_REARM_THRESH)
ixgbe_rxq_rearm(rxq);
+ /*
+ * 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 applicaion.
+ *
+ * So we need to make some restrictions to ensure that
+ * `rx_tail` will not exceed `rxrearm_start`.
+ */
+ if (rxq->rx_tail < rxq->rxrearm_start)
+ nb_pkts = RTE_MIN(nb_pkts, rxq->rxrearm_start - rxq->rx_tail - 1);
+
+ /* 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);
+
/* Before we start moving massive data around, check to see if
* there is actually a packet available
*/
--
2.25.1
^ permalink raw reply [flat|nested] 3+ messages in thread
* RE: [PATCH] net/ixgbe: add vector Rx parameter check
2021-12-02 3:18 Bin Zheng
@ 2021-12-02 5:33 ` Wang, Haiyue
0 siblings, 0 replies; 3+ messages in thread
From: Wang, Haiyue @ 2021-12-02 5:33 UTC (permalink / raw)
To: Bin Zheng, dev; +Cc: liangma, stable
> -----Original Message-----
> From: Bin Zheng <zhengbin.89740@bytedance.com>
> Sent: Thursday, December 2, 2021 11:19
> To: dev@dpdk.org
> Cc: Wang, Haiyue <haiyue.wang@intel.com>; liangma@liangbit.com; Bin Zheng
> <zhengbin.89740@bytedance.com>; jia.guo@intel.com; stable@dpdk.org
> Subject: [PATCH] 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 applicaion.
>
> 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 applicaion !
>
> 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(+)
>
Both ? Or ?
https://patchwork.dpdk.org/project/dpdk/patch/20211202031530.1808112-1-zhengbin.89740@bytedance.com/
https://patchwork.dpdk.org/project/dpdk/patch/20211202031857.1808705-1-zhengbin.89740@bytedance.com/
> diff --git a/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c b/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c
> index 1eed949495..5811749b95 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 applicaion.
> + *
> + * 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
^ permalink raw reply [flat|nested] 3+ messages in thread
* [PATCH] net/ixgbe: add vector Rx parameter check
@ 2021-12-02 3:18 Bin Zheng
2021-12-02 5:33 ` Wang, Haiyue
0 siblings, 1 reply; 3+ messages in thread
From: Bin Zheng @ 2021-12-02 3:18 UTC (permalink / raw)
To: dev; +Cc: haiyue.wang, liangma, Bin Zheng, jia.guo, stable
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 applicaion.
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 applicaion !
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..5811749b95 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 applicaion.
+ *
+ * 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
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2021-12-02 5:33 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-12-02 3:15 [PATCH] net/ixgbe: add vector Rx parameter check Bin Zheng
2021-12-02 3:18 Bin Zheng
2021-12-02 5:33 ` Wang, Haiyue
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).