From: Saeed Mahameed <saeedm@mellanox.com>
To: "David S. Miller" <davem@davemloft.net>
Cc: netdev@vger.kernel.org, Or Gerlitz <ogerlitz@mellanox.com>,
Boris Pismenny <borisp@mellanox.com>,
Yossi Kuperman <yossiku@mellanox.com>,
Saeed Mahameed <saeedm@mellanox.com>
Subject: [net-next 01/12] net/mlx5e: Add UDP GSO support
Date: Thu, 28 Jun 2018 14:50:52 -0700 [thread overview]
Message-ID: <20180628215103.9141-2-saeedm@mellanox.com> (raw)
In-Reply-To: <20180628215103.9141-1-saeedm@mellanox.com>
From: Boris Pismenny <borisp@mellanox.com>
This patch enables UDP GSO support. We enable this by using two WQEs
the first is a UDP LSO WQE for all segments with equal length, and the
second is for the last segment in case it has different length.
Due to HW limitation, before sending, we must adjust the packet length fields.
We measure performance between two Intel(R) Xeon(R) CPU E5-2643 v2 @3.50GHz
machines connected back-to-back with Connectx4-Lx (40Gbps) NICs.
We compare single stream UDP, UDP GSO and UDP GSO with offload.
Performance:
| MSS (bytes) | Throughput (Gbps) | CPU utilization (%)
UDP GSO offload | 1472 | 35.6 | 8%
UDP GSO | 1472 | 25.5 | 17%
UDP | 1472 | 10.2 | 17%
UDP GSO offload | 1024 | 35.6 | 8%
UDP GSO | 1024 | 19.2 | 17%
UDP | 1024 | 5.7 | 17%
UDP GSO offload | 512 | 33.8 | 16%
UDP GSO | 512 | 10.4 | 17%
UDP | 512 | 3.5 | 17%
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Yossi Kuperman <yossiku@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/Makefile | 4 +-
.../mellanox/mlx5/core/en_accel/en_accel.h | 11 +-
.../mellanox/mlx5/core/en_accel/rxtx.c | 108 ++++++++++++++++++
.../mellanox/mlx5/core/en_accel/rxtx.h | 14 +++
.../net/ethernet/mellanox/mlx5/core/en_main.c | 3 +
.../net/ethernet/mellanox/mlx5/core/en_tx.c | 8 +-
6 files changed, 139 insertions(+), 9 deletions(-)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.c
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.h
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 9efbf193ad5a..d923f2f58608 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -14,8 +14,8 @@ mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
fpga/ipsec.o fpga/tls.o
mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
- en_tx.o en_rx.o en_dim.o en_txrx.o en_stats.o vxlan.o \
- en_arfs.o en_fs_ethtool.o en_selftest.o en/port.o
+ en_tx.o en_rx.o en_dim.o en_txrx.o en_accel/rxtx.o en_stats.o \
+ vxlan.o en_arfs.o en_fs_ethtool.o en_selftest.o en/port.o
mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
index f20074dbef32..39a5d13ba459 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
@@ -34,12 +34,11 @@
#ifndef __MLX5E_EN_ACCEL_H__
#define __MLX5E_EN_ACCEL_H__
-#ifdef CONFIG_MLX5_ACCEL
-
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include "en_accel/ipsec_rxtx.h"
#include "en_accel/tls_rxtx.h"
+#include "en_accel/rxtx.h"
#include "en.h"
static inline struct sk_buff *mlx5e_accel_handle_tx(struct sk_buff *skb,
@@ -64,9 +63,13 @@ static inline struct sk_buff *mlx5e_accel_handle_tx(struct sk_buff *skb,
}
#endif
+ if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) {
+ skb = mlx5e_udp_gso_handle_tx_skb(dev, sq, skb, wqe, pi);
+ if (unlikely(!skb))
+ return NULL;
+ }
+
return skb;
}
-#endif /* CONFIG_MLX5_ACCEL */
-
#endif /* __MLX5E_EN_ACCEL_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.c
new file mode 100644
index 000000000000..4bb1f3b12b96
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.c
@@ -0,0 +1,108 @@
+#include "en_accel/rxtx.h"
+
+static void mlx5e_udp_gso_prepare_last_skb(struct sk_buff *skb,
+ struct sk_buff *nskb,
+ int remaining)
+{
+ int bytes_needed = remaining, remaining_headlen, remaining_page_offset;
+ int headlen = skb_transport_offset(skb) + sizeof(struct udphdr);
+ int payload_len = remaining + sizeof(struct udphdr);
+ int k = 0, i, j;
+
+ skb_copy_bits(skb, 0, nskb->data, headlen);
+ nskb->dev = skb->dev;
+ skb_reset_mac_header(nskb);
+ skb_set_network_header(nskb, skb_network_offset(skb));
+ skb_set_transport_header(nskb, skb_transport_offset(skb));
+ skb_set_tail_pointer(nskb, headlen);
+
+ /* How many frags do we need? */
+ for (i = skb_shinfo(skb)->nr_frags - 1; i >= 0; i--) {
+ bytes_needed -= skb_frag_size(&skb_shinfo(skb)->frags[i]);
+ k++;
+ if (bytes_needed <= 0)
+ break;
+ }
+
+ /* Fill the first frag and split it if necessary */
+ j = skb_shinfo(skb)->nr_frags - k;
+ remaining_page_offset = -bytes_needed;
+ skb_fill_page_desc(nskb, 0,
+ skb_shinfo(skb)->frags[j].page.p,
+ skb_shinfo(skb)->frags[j].page_offset + remaining_page_offset,
+ skb_shinfo(skb)->frags[j].size - remaining_page_offset);
+
+ skb_frag_ref(skb, j);
+
+ /* Fill the rest of the frags */
+ for (i = 1; i < k; i++) {
+ j = skb_shinfo(skb)->nr_frags - k + i;
+
+ skb_fill_page_desc(nskb, i,
+ skb_shinfo(skb)->frags[j].page.p,
+ skb_shinfo(skb)->frags[j].page_offset,
+ skb_shinfo(skb)->frags[j].size);
+ skb_frag_ref(skb, j);
+ }
+ skb_shinfo(nskb)->nr_frags = k;
+
+ remaining_headlen = remaining - skb->data_len;
+
+ /* headlen contains remaining data? */
+ if (remaining_headlen > 0)
+ skb_copy_bits(skb, skb->len - remaining, nskb->data + headlen,
+ remaining_headlen);
+ nskb->len = remaining + headlen;
+ nskb->data_len = payload_len - sizeof(struct udphdr) +
+ max_t(int, 0, remaining_headlen);
+ nskb->protocol = skb->protocol;
+ if (nskb->protocol == htons(ETH_P_IP)) {
+ ip_hdr(nskb)->id = htons(ntohs(ip_hdr(nskb)->id) +
+ skb_shinfo(skb)->gso_segs);
+ ip_hdr(nskb)->tot_len =
+ htons(payload_len + sizeof(struct iphdr));
+ } else {
+ ipv6_hdr(nskb)->payload_len = htons(payload_len);
+ }
+ udp_hdr(nskb)->len = htons(payload_len);
+ skb_shinfo(nskb)->gso_size = 0;
+ nskb->ip_summed = skb->ip_summed;
+ nskb->csum_start = skb->csum_start;
+ nskb->csum_offset = skb->csum_offset;
+ nskb->queue_mapping = skb->queue_mapping;
+}
+
+/* might send skbs and update wqe and pi */
+struct sk_buff *mlx5e_udp_gso_handle_tx_skb(struct net_device *netdev,
+ struct mlx5e_txqsq *sq,
+ struct sk_buff *skb,
+ struct mlx5e_tx_wqe **wqe,
+ u16 *pi)
+{
+ int payload_len = skb_shinfo(skb)->gso_size + sizeof(struct udphdr);
+ int headlen = skb_transport_offset(skb) + sizeof(struct udphdr);
+ int remaining = (skb->len - headlen) % skb_shinfo(skb)->gso_size;
+ struct sk_buff *nskb;
+
+ if (skb->protocol == htons(ETH_P_IP))
+ ip_hdr(skb)->tot_len = htons(payload_len + sizeof(struct iphdr));
+ else
+ ipv6_hdr(skb)->payload_len = htons(payload_len);
+ udp_hdr(skb)->len = htons(payload_len);
+ if (!remaining)
+ return skb;
+
+ nskb = alloc_skb(max_t(int, headlen, headlen + remaining - skb->data_len), GFP_ATOMIC);
+ if (unlikely(!nskb)) {
+ sq->stats->dropped++;
+ return NULL;
+ }
+
+ mlx5e_udp_gso_prepare_last_skb(skb, nskb, remaining);
+
+ skb_shinfo(skb)->gso_segs--;
+ pskb_trim(skb, skb->len - remaining);
+ mlx5e_sq_xmit(sq, skb, *wqe, *pi);
+ mlx5e_sq_fetch_wqe(sq, wqe, pi);
+ return nskb;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.h
new file mode 100644
index 000000000000..ed42699a78b3
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.h
@@ -0,0 +1,14 @@
+
+#ifndef __MLX5E_EN_ACCEL_RX_TX_H__
+#define __MLX5E_EN_ACCEL_RX_TX_H__
+
+#include <linux/skbuff.h>
+#include "en.h"
+
+struct sk_buff *mlx5e_udp_gso_handle_tx_skb(struct net_device *netdev,
+ struct mlx5e_txqsq *sq,
+ struct sk_buff *skb,
+ struct mlx5e_tx_wqe **wqe,
+ u16 *pi);
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 134f20a182b5..e2ef68b1daa2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4592,6 +4592,9 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
netdev->features |= NETIF_F_HIGHDMA;
netdev->features |= NETIF_F_HW_VLAN_STAG_FILTER;
+ netdev->features |= NETIF_F_GSO_UDP_L4;
+ netdev->hw_features |= NETIF_F_GSO_UDP_L4;
+
netdev->priv_flags |= IFF_UNICAST_FLT;
mlx5e_set_netdev_dev_addr(netdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index f29deb44bf3b..f450d9ca31fb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -228,7 +228,10 @@ mlx5e_tx_get_gso_ihs(struct mlx5e_txqsq *sq, struct sk_buff *skb)
stats->tso_inner_packets++;
stats->tso_inner_bytes += skb->len - ihs;
} else {
- ihs = skb_transport_offset(skb) + tcp_hdrlen(skb);
+ if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
+ ihs = skb_transport_offset(skb) + sizeof(struct udphdr);
+ else
+ ihs = skb_transport_offset(skb) + tcp_hdrlen(skb);
stats->tso_packets++;
stats->tso_bytes += skb->len - ihs;
}
@@ -443,12 +446,11 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
sq = priv->txq2sq[skb_get_queue_mapping(skb)];
mlx5e_sq_fetch_wqe(sq, &wqe, &pi);
-#ifdef CONFIG_MLX5_ACCEL
/* might send skbs and update wqe and pi */
skb = mlx5e_accel_handle_tx(skb, sq, dev, &wqe, &pi);
if (unlikely(!skb))
return NETDEV_TX_OK;
-#endif
+
return mlx5e_sq_xmit(sq, skb, wqe, pi);
}
--
2.17.0
next prev parent reply other threads:[~2018-06-28 21:51 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-06-28 21:50 [pull request][net-next 00/12] Mellanox, mlx5e updates 2018-06-28 Saeed Mahameed
2018-06-28 21:50 ` Saeed Mahameed [this message]
2018-06-29 22:19 ` [net-next 01/12] net/mlx5e: Add UDP GSO support Willem de Bruijn
2018-06-30 16:06 ` Boris Pismenny
2018-06-30 19:40 ` Boris Pismenny
[not found] ` <CAKgT0UfFMG+i9z_nxB0vkJesDE4CHWbudCh6kJ_1+=Vd1hv=wA@mail.gmail.com>
2018-07-02 1:45 ` Willem de Bruijn
2018-07-02 5:29 ` Boris Pismenny
2018-07-02 13:34 ` Willem de Bruijn
2018-07-02 14:45 ` Willem de Bruijn
[not found] ` <CAKgT0UdC2c04JagxW8S==-ymBfDZVd6f=7DcLUGjRqiiZA3BwA@mail.gmail.com>
2018-07-02 19:17 ` Boris Pismenny
2018-06-28 21:50 ` [net-next 02/12] net/mlx5e: Add UDP GSO remaining counter Saeed Mahameed
2018-06-28 21:50 ` [net-next 03/12] net/mlx5e: Convert large order kzalloc allocations to kvzalloc Saeed Mahameed
2018-06-28 21:50 ` [net-next 04/12] net/mlx5e: RX, Use existing WQ local variable Saeed Mahameed
2018-06-28 21:50 ` [net-next 05/12] net/mlx5e: Add TX completions statistics Saeed Mahameed
2018-06-28 21:50 ` [net-next 06/12] net/mlx5e: Add XDP_TX " Saeed Mahameed
2018-06-28 21:50 ` [net-next 07/12] net/mlx5e: Add NAPI statistics Saeed Mahameed
2018-06-28 21:50 ` [net-next 08/12] net/mlx5e: Add a counter for congested UMRs Saeed Mahameed
2018-06-28 21:51 ` [net-next 09/12] net/mlx5e: Add channel events counter Saeed Mahameed
2018-06-28 21:51 ` [net-next 10/12] net/mlx5e: Add counter for MPWQE filler strides Saeed Mahameed
2018-06-28 21:51 ` [net-next 11/12] net/mlx5e: Add counter for total num of NOP operations Saeed Mahameed
2018-06-28 21:51 ` [net-next 12/12] net/mlx5e: Update NIC HW stats on demand only Saeed Mahameed
2018-06-29 14:56 ` [pull request][net-next 00/12] Mellanox, mlx5e updates 2018-06-28 David Miller
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=20180628215103.9141-2-saeedm@mellanox.com \
--to=saeedm@mellanox.com \
--cc=borisp@mellanox.com \
--cc=davem@davemloft.net \
--cc=netdev@vger.kernel.org \
--cc=ogerlitz@mellanox.com \
--cc=yossiku@mellanox.com \
/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