DPDK patches and discussions
 help / color / mirror / Atom feed
From: Bhagyada Modali <bhagyada.modali@amd.com>
To: <chandu@amd.com>, <ferruh.yigit@amd.com>
Cc: <dev@dpdk.org>, <stable@dpdk.org>,
	Bhagyada Modali <bhagyada.modali@amd.com>
Subject: [PATCH v2 3/3] net/axgbe: save segment data in scattered Rx
Date: Wed, 7 Sep 2022 23:31:09 -0400	[thread overview]
Message-ID: <20220908033109.126547-3-bhagyada.modali@amd.com> (raw)
In-Reply-To: <20220908033109.126547-1-bhagyada.modali@amd.com>

Saving the current segments of the packet,
when the next segment data is not ready.

Fixes: 965b3127d425 ("net/axgbe: support scattered Rx")
Cc: stable@dpdk.org

Signed-off-by: Bhagyada Modali <bhagyada.modali@amd.com>
---
 drivers/net/axgbe/axgbe_rxtx.c | 11 +++++++++++
 drivers/net/axgbe/axgbe_rxtx.h |  6 ++++++
 2 files changed, 17 insertions(+)

diff --git a/drivers/net/axgbe/axgbe_rxtx.c b/drivers/net/axgbe/axgbe_rxtx.c
index c1f51ed6d6..65bda2a0d3 100644
--- a/drivers/net/axgbe/axgbe_rxtx.c
+++ b/drivers/net/axgbe/axgbe_rxtx.c
@@ -416,11 +416,17 @@ uint16_t eth_axgbe_recv_scattered_pkts(void *rx_queue,
 		mbuf->data_len = data_len;
 		mbuf->pkt_len = data_len;
 
+		if (rxq->saved_mbuf) {
+			first_seg = rxq->saved_mbuf;
+			rxq->saved_mbuf = NULL;
+		}
+
 		if (first_seg != NULL) {
 			if (rte_pktmbuf_chain(first_seg, mbuf) != 0) {
 				rte_pktmbuf_free(first_seg);
 				first_seg = NULL;
 				rte_pktmbuf_free(mbuf);
+				rxq->saved_mbuf = NULL;
 				rxq->errors++;
 				eop = 0;
 				break;
@@ -502,6 +508,11 @@ uint16_t eth_axgbe_recv_scattered_pkts(void *rx_queue,
 		first_seg = NULL;
 	}
 
+	/* Check if we need to save state before leaving */
+	if (first_seg != NULL && eop == 0)
+		rxq->saved_mbuf = first_seg;
+
+
 	/* Save receive context.*/
 	rxq->pkts += nb_rx;
 
diff --git a/drivers/net/axgbe/axgbe_rxtx.h b/drivers/net/axgbe/axgbe_rxtx.h
index 2a330339cd..2da3095547 100644
--- a/drivers/net/axgbe/axgbe_rxtx.h
+++ b/drivers/net/axgbe/axgbe_rxtx.h
@@ -65,6 +65,12 @@ struct axgbe_rx_queue {
 	uint16_t crc_len;
 	/* address of  s/w rx buffers */
 	struct rte_mbuf **sw_ring;
+
+	/* For segemented packets - save the current state
+	 * of packet, if next descriptor is not ready yet
+	 */
+	struct rte_mbuf *saved_mbuf;
+
 	/* Port private data */
 	struct axgbe_port *pdata;
 	/* Number of Rx descriptors in queue */
-- 
2.25.1


  parent reply	other threads:[~2022-09-08  3:32 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-09-07 17:33 [PATCH 1/3] net/axgbe: reset the end of packet in scattered rx Bhagyada Modali
2022-09-07 17:33 ` [PATCH 2/3] net/axgbe: clear buffers in failure scenario " Bhagyada Modali
2022-09-07 17:33 ` [PATCH 3/3] net/axgbe: save segment data in scattered Rx Bhagyada Modali
2022-09-08  3:31 ` [PATCH v2 1/3] net/axgbe: reset the end of packet in scattered rx Bhagyada Modali
2022-09-08  3:31   ` [PATCH v2 2/3] net/axgbe: clear buffers in failure scenario " Bhagyada Modali
2022-09-08  3:31   ` Bhagyada Modali [this message]
2022-09-08 13:56   ` [PATCH v2 1/3] net/axgbe: reset the end of packet " Namburu, Chandu-babu
2022-09-21 14:39     ` Ferruh Yigit

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=20220908033109.126547-3-bhagyada.modali@amd.com \
    --to=bhagyada.modali@amd.com \
    --cc=chandu@amd.com \
    --cc=dev@dpdk.org \
    --cc=ferruh.yigit@amd.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).