netdev - [net-next 1/6] net/dcb: Add dcbnl buffer attribute

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:   Mon, 21 May 2018 14:04:57 -0700
From:   Saeed Mahameed <saeedm@...lanox.com>
To:     "David S. Miller" <davem@...emloft.net>
Cc:     netdev@...r.kernel.org, Huy Nguyen <huyn@...lanox.com>,
        Saeed Mahameed <saeedm@...lanox.com>
Subject: [net-next 1/6] net/dcb: Add dcbnl buffer attribute

From: Huy Nguyen <huyn@...lanox.com>

In this patch, we add dcbnl buffer attribute to allow user
change the NIC's buffer configuration such as priority
to buffer mapping and buffer size of individual buffer.

This attribute combined with pfc attribute allows advance user to
fine tune the qos setting for specific priority queue. For example,
user can give dedicated buffer for one or more prirorities or user
can give large buffer to certain priorities.

We present an use case scenario where dcbnl buffer attribute configured
by advance user helps reduce the latency of messages of different sizes.

Scenarios description:
On ConnectX-5, we run latency sensitive traffic with
small/medium message sizes ranging from 64B to 256KB and bandwidth sensitive
traffic with large messages sizes 512KB and 1MB. We group small, medium,
and large message sizes to their own pfc enables priorities as follow.
  Priorities 1 & 2 (64B, 256B and 1KB)
  Priorities 3 & 4 (4KB, 8KB, 16KB, 64KB, 128KB and 256KB)
  Priorities 5 & 6 (512KB and 1MB)

By default, ConnectX-5 maps all pfc enabled priorities to a single
lossless fixed buffer size of 50% of total available buffer space. The
other 50% is assigned to lossy buffer. Using dcbnl buffer attribute,
we create three equal size lossless buffers. Each buffer has 25% of total
available buffer space. Thus, the lossy buffer size reduces to 25%. Priority
to lossless  buffer mappings are set as follow.
  Priorities 1 & 2 on lossless buffer #1
  Priorities 3 & 4 on lossless buffer #2
  Priorities 5 & 6 on lossless buffer #3

We observe improvements in latency for small and medium message sizes
as follows. Please note that the large message sizes bandwidth performance is
reduced but the total bandwidth remains the same.
  256B message size (42 % latency reduction)
  4K message size (21% latency reduction)
  64K message size (16% latency reduction)

Signed-off-by: Huy Nguyen <huyn@...lanox.com>
Signed-off-by: Saeed Mahameed <saeedm@...lanox.com>
---
 include/net/dcbnl.h        |  4 ++++
 include/uapi/linux/dcbnl.h | 10 ++++++++++
 net/dcb/dcbnl.c            | 20 ++++++++++++++++++++
 3 files changed, 34 insertions(+)

diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h
index 207d9ba1f92c..0e5e91be2d30 100644
--- a/include/net/dcbnl.h
+++ b/include/net/dcbnl.h
@@ -101,6 +101,10 @@ struct dcbnl_rtnl_ops {
 	/* CEE peer */
 	int (*cee_peer_getpg) (struct net_device *, struct cee_pg *);
 	int (*cee_peer_getpfc) (struct net_device *, struct cee_pfc *);
+
+	/* buffer settings */
+	int (*dcbnl_getbuffer)(struct net_device *, struct dcbnl_buffer *);
+	int (*dcbnl_setbuffer)(struct net_device *, struct dcbnl_buffer *);
 };
 
 #endif /* __NET_DCBNL_H__ */
diff --git a/include/uapi/linux/dcbnl.h b/include/uapi/linux/dcbnl.h
index 2c0c6453c3f4..1ddc0a44c172 100644
--- a/include/uapi/linux/dcbnl.h
+++ b/include/uapi/linux/dcbnl.h
@@ -163,6 +163,15 @@ struct ieee_pfc {
 	__u64	indications[IEEE_8021QAZ_MAX_TCS];
 };
 
+#define IEEE_8021Q_MAX_PRIORITIES 8
+#define DCBX_MAX_BUFFERS  8
+struct dcbnl_buffer {
+	/* priority to buffer mapping */
+	__u8    prio2buffer[IEEE_8021Q_MAX_PRIORITIES];
+	/* buffer size in Bytes */
+	__u32   buffer_size[DCBX_MAX_BUFFERS];
+};
+
 /* CEE DCBX std supported values */
 #define CEE_DCBX_MAX_PGS	8
 #define CEE_DCBX_MAX_PRIO	8
@@ -406,6 +415,7 @@ enum ieee_attrs {
 	DCB_ATTR_IEEE_MAXRATE,
 	DCB_ATTR_IEEE_QCN,
 	DCB_ATTR_IEEE_QCN_STATS,
+	DCB_ATTR_DCB_BUFFER,
 	__DCB_ATTR_IEEE_MAX
 };
 #define DCB_ATTR_IEEE_MAX (__DCB_ATTR_IEEE_MAX - 1)
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index bae7d78aa068..d2f4e0c1faaf 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -176,6 +176,7 @@ static const struct nla_policy dcbnl_ieee_policy[DCB_ATTR_IEEE_MAX + 1] = {
 	[DCB_ATTR_IEEE_MAXRATE]   = {.len = sizeof(struct ieee_maxrate)},
 	[DCB_ATTR_IEEE_QCN]         = {.len = sizeof(struct ieee_qcn)},
 	[DCB_ATTR_IEEE_QCN_STATS]   = {.len = sizeof(struct ieee_qcn_stats)},
+	[DCB_ATTR_DCB_BUFFER]       = {.len = sizeof(struct dcbnl_buffer)},
 };
 
 /* DCB number of traffic classes nested attributes. */
@@ -1094,6 +1095,16 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev)
 			return -EMSGSIZE;
 	}
 
+	if (ops->dcbnl_getbuffer) {
+		struct dcbnl_buffer buffer;
+
+		memset(&buffer, 0, sizeof(buffer));
+		err = ops->dcbnl_getbuffer(netdev, &buffer);
+		if (!err &&
+		    nla_put(skb, DCB_ATTR_DCB_BUFFER, sizeof(buffer), &buffer))
+			return -EMSGSIZE;
+	}
+
 	app = nla_nest_start(skb, DCB_ATTR_IEEE_APP_TABLE);
 	if (!app)
 		return -EMSGSIZE;
@@ -1453,6 +1464,15 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh,
 			goto err;
 	}
 
+	if (ieee[DCB_ATTR_DCB_BUFFER] && ops->dcbnl_setbuffer) {
+		struct dcbnl_buffer *buffer =
+			nla_data(ieee[DCB_ATTR_DCB_BUFFER]);
+
+		err = ops->dcbnl_setbuffer(netdev, buffer);
+		if (err)
+			goto err;
+	}
+
 	if (ieee[DCB_ATTR_IEEE_APP_TABLE]) {
 		struct nlattr *attr;
 		int rem;
-- 
2.17.0