From: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
To: dev@dpdk.org
Cc: stable@dpdk.org, rasland@nvidia.com, matan@nvidia.com, orika@nvidia.com
Subject: [dpdk-dev] [PATCH] net/mlx4: fix buffer leakage on device close
Date: Sat, 17 Apr 2021 20:14:14 +0300 [thread overview]
Message-ID: <20210417171414.6117-1-viacheslavo@nvidia.com> (raw)
The mlx4 PMD tracks the buffers (mbufs) for the packets being
transmitted in the dedicated array named as "elts". The tx_burst
routine frees the mbufs from this array once it needs to rearm
the hardware descriptor and store the new mbuf, so it looks
like as replacement mbuf pointer in the elts array.
On the device stop mlx4 PMD freed only the part of elts according
tail and head pointers, leaking the rest of buffers, remained in
the elts array.
Fixes: a2ce2121c01c ("net/mlx4: separate Tx configuration functions")
Cc: stable@dpdk.org
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
---
drivers/net/mlx4/mlx4_rxtx.c | 4 ----
drivers/net/mlx4/mlx4_txq.c | 19 +++++++++----------
2 files changed, 9 insertions(+), 14 deletions(-)
diff --git a/drivers/net/mlx4/mlx4_rxtx.c b/drivers/net/mlx4/mlx4_rxtx.c
index adc1c9bf81..ecf08f53cf 100644
--- a/drivers/net/mlx4/mlx4_rxtx.c
+++ b/drivers/net/mlx4/mlx4_rxtx.c
@@ -921,10 +921,6 @@ mlx4_tx_burst(void *dpdk_txq, struct rte_mbuf **pkts, uint16_t pkts_n)
if (likely(elt->buf != NULL)) {
struct rte_mbuf *tmp = elt->buf;
-#ifdef RTE_LIBRTE_MLX4_DEBUG
- /* Poisoning. */
- memset(&elt->buf, 0x66, sizeof(struct rte_mbuf *));
-#endif
/* Faster than rte_pktmbuf_free(). */
do {
struct rte_mbuf *next = tmp->next;
diff --git a/drivers/net/mlx4/mlx4_txq.c b/drivers/net/mlx4/mlx4_txq.c
index 31ab308050..2df26842fb 100644
--- a/drivers/net/mlx4/mlx4_txq.c
+++ b/drivers/net/mlx4/mlx4_txq.c
@@ -206,19 +206,18 @@ mlx4_tx_uar_uninit_secondary(struct rte_eth_dev *dev __rte_unused)
static void
mlx4_txq_free_elts(struct txq *txq)
{
- unsigned int elts_head = txq->elts_head;
- unsigned int elts_tail = txq->elts_tail;
struct txq_elt (*elts)[txq->elts_n] = txq->elts;
- unsigned int elts_m = txq->elts_n - 1;
+ unsigned int n = txq->elts_n;
- DEBUG("%p: freeing WRs", (void *)txq);
- while (elts_tail != elts_head) {
- struct txq_elt *elt = &(*elts)[elts_tail++ & elts_m];
+ DEBUG("%p: freeing WRs, %u", (void *)txq, n);
+ while (n--) {
+ struct txq_elt *elt = &(*elts)[n];
- MLX4_ASSERT(elt->buf != NULL);
- rte_pktmbuf_free(elt->buf);
- elt->buf = NULL;
- elt->wqe = NULL;
+ if (elt->buf) {
+ rte_pktmbuf_free(elt->buf);
+ elt->buf = NULL;
+ elt->wqe = NULL;
+ }
}
txq->elts_tail = txq->elts_head;
}
--
2.18.1
next reply other threads:[~2021-04-17 17:14 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-04-17 17:14 Viacheslav Ovsiienko [this message]
2021-04-28 9:15 ` Raslan Darawsheh
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=20210417171414.6117-1-viacheslavo@nvidia.com \
--to=viacheslavo@nvidia.com \
--cc=dev@dpdk.org \
--cc=matan@nvidia.com \
--cc=orika@nvidia.com \
--cc=rasland@nvidia.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).