Checks
Commit Message
From: Qiming Chen <chenqiming_huawei@163.com>
A local test found that repeated port start and stop operations during
the continuous SSE vector bufflist receiving process will cause the mbuf
resource to run out. The final positioning is when the port is stopped,
the mbuf of the pkt_first_seg pointer is not released. Resources lead.
The patch scheme is to judge whether the pointer is empty when the port
is stopped, and release the corresponding mbuf if it is not empty.
Fixes: 5c9222058df7 ("i40e: move to drivers/net/")
Cc: stable@dpdk.org
Signed-off-by: Qiming Chen <chenqiming_huawei@163.com>
---
drivers/net/i40e/i40e_rxtx.c | 4 ++++
1 file changed, 4 insertions(+)
Comments
> -----Original Message-----
> From: dev <dev-bounces@dpdk.org> On Behalf Of
> chenqiming_huawei@163.com
> Sent: Monday, August 23, 2021 9:51 AM
> To: dev@dpdk.org
> Cc: Xing, Beilei <beilei.xing@intel.com>; Qiming Chen
> <chenqiming_huawei@163.com>; stable@dpdk.org
> Subject: [dpdk-dev] [PATCH] net/i40e: fix mbuf leak
>
> From: Qiming Chen <chenqiming_huawei@163.com>
>
> A local test found that repeated port start and stop operations during the
> continuous SSE vector bufflist receiving process will cause the mbuf resource
> to run out. The final positioning is when the port is stopped, the mbuf of the
> pkt_first_seg pointer is not released. Resources lead.
> The patch scheme is to judge whether the pointer is empty when the port is
> stopped, and release the corresponding mbuf if it is not empty.
>
> Fixes: 5c9222058df7 ("i40e: move to drivers/net/")
Fixes: 4861cde46116 ("i40e: new poll mode driver")
> Cc: stable@dpdk.org
>
> Signed-off-by: Qiming Chen <chenqiming_huawei@163.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Applied to dpdk-next-net-intel.
Thanks
Qi
On 9/13/2021 3:29 AM, Zhang, Qi Z wrote:
>
>
>> -----Original Message-----
>> From: dev <dev-bounces@dpdk.org> On Behalf Of
>> chenqiming_huawei@163.com
>> Sent: Monday, August 23, 2021 9:51 AM
>> To: dev@dpdk.org
>> Cc: Xing, Beilei <beilei.xing@intel.com>; Qiming Chen
>> <chenqiming_huawei@163.com>; stable@dpdk.org
>> Subject: [dpdk-dev] [PATCH] net/i40e: fix mbuf leak
>>
>> From: Qiming Chen <chenqiming_huawei@163.com>
>>
>> A local test found that repeated port start and stop operations during the
>> continuous SSE vector bufflist receiving process will cause the mbuf resource
>> to run out. The final positioning is when the port is stopped, the mbuf of the
>> pkt_first_seg pointer is not released. Resources lead.
s/lead/leak/
Will update on next-net
>> The patch scheme is to judge whether the pointer is empty when the port is
>> stopped, and release the corresponding mbuf if it is not empty.
>>
>> Fixes: 5c9222058df7 ("i40e: move to drivers/net/")
>
> Fixes: 4861cde46116 ("i40e: new poll mode driver")
>
>> Cc: stable@dpdk.org
>>
>> Signed-off-by: Qiming Chen <chenqiming_huawei@163.com>
>
> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
>
> Applied to dpdk-next-net-intel.
>
> Thanks
> Qi
>
>
@@ -2590,6 +2590,10 @@ i40e_reset_rx_queue(struct i40e_rx_queue *rxq)
#endif /* RTE_LIBRTE_I40E_RX_ALLOW_BULK_ALLOC */
rxq->rx_tail = 0;
rxq->nb_rx_hold = 0;
+
+ if (rxq->pkt_first_seg != NULL)
+ rte_pktmbuf_free(rxq->pkt_first_seg);
+
rxq->pkt_first_seg = NULL;
rxq->pkt_last_seg = NULL;