From: Kalesh A P <kalesh-anakkur.purayil@broadcom.com>
To: stable@dpdk.org
Subject: [dpdk-stable] [PATCH 18.11 1/3] net/bnxt: fix for memleak during queue restart
Date: Fri, 16 Oct 2020 14:50:45 +0530 [thread overview]
Message-ID: <20201016092047.30846-2-kalesh-anakkur.purayil@broadcom.com> (raw)
In-Reply-To: <20201016092047.30846-1-kalesh-anakkur.purayil@broadcom.com>
From: Rahul Gupta <rahul.gupta@broadcom.com>
[ upstream commit d256c73c11229c0a7eae32a7e0baaa7a457000e1 ]
During port 0 rxq 1 start ie queue start,
bnxt_free_hwrm_rx_ring() we are clearing the pointers to mbuf array.
Due to this we overwrite the queue with fresh mbuf allocations
causing previously allocated mbufs to leak.
Add a check before allocating mbuf to replenish only empty mbuf slots
in the RxQ.
Signed-off-by: Rahul Gupta <rahul.gupta@broadcom.com>
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Ajit Kumar Khaparde <ajit.khaparde@broadcom.com>
---
drivers/net/bnxt/bnxt_hwrm.c | 12 ------------
drivers/net/bnxt/bnxt_rxr.c | 44 +++++++++++++++++++++++++-------------------
2 files changed, 25 insertions(+), 31 deletions(-)
diff --git a/drivers/net/bnxt/bnxt_hwrm.c b/drivers/net/bnxt/bnxt_hwrm.c
index cfb4cb6..0f1f4d1 100644
--- a/drivers/net/bnxt/bnxt_hwrm.c
+++ b/drivers/net/bnxt/bnxt_hwrm.c
@@ -1929,23 +1929,11 @@ void bnxt_free_hwrm_rx_ring(struct bnxt *bp, int queue_index)
HWRM_RING_FREE_INPUT_RING_TYPE_RX);
ring->fw_ring_id = INVALID_HW_RING_ID;
bp->grp_info[queue_index].rx_fw_ring_id = INVALID_HW_RING_ID;
- memset(rxr->rx_desc_ring, 0,
- rxr->rx_ring_struct->ring_size *
- sizeof(*rxr->rx_desc_ring));
- memset(rxr->rx_buf_ring, 0,
- rxr->rx_ring_struct->ring_size *
- sizeof(*rxr->rx_buf_ring));
- rxr->rx_prod = 0;
}
ring = rxr->ag_ring_struct;
if (ring->fw_ring_id != INVALID_HW_RING_ID) {
bnxt_hwrm_ring_free(bp, ring,
HWRM_RING_FREE_INPUT_RING_TYPE_RX);
- ring->fw_ring_id = INVALID_HW_RING_ID;
- memset(rxr->ag_buf_ring, 0,
- rxr->ag_ring_struct->ring_size *
- sizeof(*rxr->ag_buf_ring));
- rxr->ag_prod = 0;
bp->grp_info[queue_index].ag_fw_ring_id = INVALID_HW_RING_ID;
}
if (cpr->cp_ring_struct->fw_ring_id != INVALID_HW_RING_ID)
diff --git a/drivers/net/bnxt/bnxt_rxr.c b/drivers/net/bnxt/bnxt_rxr.c
index 3a1d223..b73561b 100644
--- a/drivers/net/bnxt/bnxt_rxr.c
+++ b/drivers/net/bnxt/bnxt_rxr.c
@@ -768,14 +768,16 @@ int bnxt_init_one_rx_ring(struct bnxt_rx_queue *rxq)
prod = rxr->rx_prod;
for (i = 0; i < ring->ring_size; i++) {
- if (bnxt_alloc_rx_data(rxq, rxr, prod) != 0) {
- PMD_DRV_LOG(WARNING,
- "init'ed rx ring %d with %d/%d mbufs only\n",
- rxq->queue_id, i, ring->ring_size);
- break;
+ if (unlikely(!(rxr->rx_buf_ring[i].mbuf))) {
+ if (bnxt_alloc_rx_data(rxq, rxr, prod) != 0) {
+ PMD_DRV_LOG(WARNING,
+ "init'ed rx ring %d with %d/%d mbufs only\n",
+ rxq->queue_id, i, ring->ring_size);
+ break;
+ }
+ rxr->rx_prod = prod;
+ prod = RING_NEXT(rxr->rx_ring_struct, prod);
}
- rxr->rx_prod = prod;
- prod = RING_NEXT(rxr->rx_ring_struct, prod);
}
ring = rxr->ag_ring_struct;
@@ -784,24 +786,28 @@ int bnxt_init_one_rx_ring(struct bnxt_rx_queue *rxq)
prod = rxr->ag_prod;
for (i = 0; i < ring->ring_size; i++) {
- if (bnxt_alloc_ag_data(rxq, rxr, prod) != 0) {
- PMD_DRV_LOG(WARNING,
- "init'ed AG ring %d with %d/%d mbufs only\n",
- rxq->queue_id, i, ring->ring_size);
- break;
+ if (unlikely(!(rxr->ag_buf_ring[i].mbuf))) {
+ if (bnxt_alloc_ag_data(rxq, rxr, prod) != 0) {
+ PMD_DRV_LOG(WARNING,
+ "init'ed AG ring %d with %d/%d mbufs only\n",
+ rxq->queue_id, i, ring->ring_size);
+ break;
+ }
+ rxr->ag_prod = prod;
+ prod = RING_NEXT(rxr->ag_ring_struct, prod);
}
- rxr->ag_prod = prod;
- prod = RING_NEXT(rxr->ag_ring_struct, prod);
}
PMD_DRV_LOG(DEBUG, "AGG Done!\n");
if (rxr->tpa_info) {
for (i = 0; i < BNXT_TPA_MAX; i++) {
- rxr->tpa_info[i].mbuf =
- __bnxt_alloc_rx_data(rxq->mb_pool);
- if (!rxr->tpa_info[i].mbuf) {
- rte_atomic64_inc(&rxq->rx_mbuf_alloc_fail);
- return -ENOMEM;
+ if (unlikely(!(rxr->tpa_info[i].mbuf))) {
+ rxr->tpa_info[i].mbuf =
+ __bnxt_alloc_rx_data(rxq->mb_pool);
+ if (!rxr->tpa_info[i].mbuf) {
+ rte_atomic64_inc(&rxq->rx_mbuf_alloc_fail);
+ return -ENOMEM;
+ }
}
}
}
--
2.10.1
next prev parent reply other threads:[~2020-10-16 9:06 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-10-16 9:20 [dpdk-stable] [PATCH 18.11 0/3] bnxt patches for 18.11 Kalesh A P
2020-10-16 9:20 ` Kalesh A P [this message]
2020-10-16 9:20 ` [dpdk-stable] [PATCH 18.11 2/3] net/bnxt: fix to advance producer index Kalesh A P
2020-10-16 9:20 ` [dpdk-stable] [PATCH 18.11 3/3] net/bnxt: fix flow error on filter creation Kalesh A P
2020-10-16 12:26 ` [dpdk-stable] [PATCH 18.11 0/3] bnxt patches for 18.11 Kevin Traynor
2020-10-30 13:13 ` Kevin Traynor
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20201016092047.30846-2-kalesh-anakkur.purayil@broadcom.com \
--to=kalesh-anakkur.purayil@broadcom.com \
--cc=stable@dpdk.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).