DPDK patches and discussions
 help / color / mirror / Atom feed
From: Adrien Mazarguil <adrien.mazarguil@6wind.com>
To: dev@dpdk.org
Subject: [dpdk-dev] [PATCH 2/2] mlx5: fix wrong hash RX queue type in RSS mode
Date: Tue,  3 Nov 2015 18:15:14 +0100	[thread overview]
Message-ID: <1446570914-25996-2-git-send-email-adrien.mazarguil@6wind.com> (raw)
In-Reply-To: <1446570914-25996-1-git-send-email-adrien.mazarguil@6wind.com>

Only seen since IPv6 RSS support was added, confusion about the purpose of
the hash_rxq_type_from_n() function has caused it to return invalid hash RX
queue types.

Refactor function for its intended purpose, rename it
hash_rxq_type_from_pos() and update comment with a better description.

Fixes: a76133214d88 ("mlx5: use separate indirection table for default hash Rx queue")

Reported-by: Olga Shern <olgas@mellanox.com>
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Signed-off-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
---
 drivers/net/mlx5/mlx5_rxq.c | 32 +++++++++++++++++++-------------
 1 file changed, 19 insertions(+), 13 deletions(-)

diff --git a/drivers/net/mlx5/mlx5_rxq.c b/drivers/net/mlx5/mlx5_rxq.c
index 3d7ae7e..37b4efd 100644
--- a/drivers/net/mlx5/mlx5_rxq.c
+++ b/drivers/net/mlx5/mlx5_rxq.c
@@ -259,23 +259,29 @@ hash_rxq_flow_attr(const struct hash_rxq *hash_rxq,
 }
 
 /**
- * Return the type corresponding to the n'th bit set.
+ * Convert hash type position in indirection table initializer to
+ * hash RX queue type.
  *
  * @param table
- *   The indirection table.
- * @param n
- *   The n'th bit set.
+ *   Indirection table initializer.
+ * @param pos
+ *   Hash type position.
  *
  * @return
- *   The corresponding hash_rxq_type.
+ *   Hash RX queue type.
  */
 static enum hash_rxq_type
-hash_rxq_type_from_n(const struct ind_table_init *table, unsigned int n)
+hash_rxq_type_from_pos(const struct ind_table_init *table, unsigned int pos)
 {
-	assert(n < table->hash_types_n);
-	while (((table->hash_types >> n) & 0x1) == 0)
-		++n;
-	return n;
+	enum hash_rxq_type type = 0;
+
+	assert(pos < table->hash_types_n);
+	do {
+		if ((table->hash_types & (1 << type)) && (pos-- == 0))
+			break;
+		++type;
+	} while (1);
+	return type;
 }
 
 /**
@@ -429,7 +435,7 @@ priv_create_hash_rxqs(struct priv *priv)
 	     ++i) {
 		struct hash_rxq *hash_rxq = &(*hash_rxqs)[i];
 		enum hash_rxq_type type =
-			hash_rxq_type_from_n(&ind_table_init[j], k);
+			hash_rxq_type_from_pos(&ind_table_init[j], k);
 		struct rte_eth_rss_conf *priv_rss_conf =
 			(*priv->rss_conf)[type];
 		struct ibv_exp_rx_hash_conf hash_conf = {
@@ -453,8 +459,8 @@ priv_create_hash_rxqs(struct priv *priv)
 			.port_num = priv->port,
 		};
 
-		DEBUG("using indirection table %u for hash RX queue %u",
-		      j, i);
+		DEBUG("using indirection table %u for hash RX queue %u type %d",
+		      j, i, type);
 		*hash_rxq = (struct hash_rxq){
 			.priv = priv,
 			.qp = ibv_exp_create_qp(priv->ctx, &qp_init_attr),
-- 
2.1.0

  reply	other threads:[~2015-11-03 17:15 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-11-03 17:15 [dpdk-dev] [PATCH 1/2] mlx5: fix compilation error with debugging enabled Adrien Mazarguil
2015-11-03 17:15 ` Adrien Mazarguil [this message]
2015-11-03 22:00   ` [dpdk-dev] [PATCH 2/2] mlx5: fix wrong hash RX queue type in RSS mode Thomas Monjalon

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=1446570914-25996-2-git-send-email-adrien.mazarguil@6wind.com \
    --to=adrien.mazarguil@6wind.com \
    --cc=dev@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).