From: Jerin Jacob Kollanukkaran <jerinj@marvell.com>
To: "qi.z.zhang@intel.com" <qi.z.zhang@intel.com>,
"keith.wiles@intel.com" <keith.wiles@intel.com>,
"ferruh.yigit@intel.com" <ferruh.yigit@intel.com>,
"bruce.richardson@intel.com" <bruce.richardson@intel.com>,
"konstantin.ananyev@intel.com" <konstantin.ananyev@intel.com>
Cc: "bernard.iremonger@intel.com" <bernard.iremonger@intel.com>,
"dev@dpdk.org" <dev@dpdk.org>,
"wenzhuo.lu@intel.com" <wenzhuo.lu@intel.com>
Subject: Re: [dpdk-dev] [EXT] [PATCH v2 2/3] app/testpmd: improve MAC swap performance for x86
Date: Thu, 13 Dec 2018 19:50:07 +0000 [thread overview]
Message-ID: <470f02192a8a08a0fb4181c81d5c731b3fecf30b.camel@marvell.com> (raw)
In-Reply-To: <20181211055511.32284-3-qi.z.zhang@intel.com>
On Tue, 2018-12-11 at 13:55 +0800, Qi Zhang wrote:
>
> The patch optimizes the mac swap operation by taking advantage
> of SSE instructions, it only impacts x86 platform.
>
> Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
> ---
> app/test-pmd/macswap.c | 4 ++++
> app/test-pmd/macswap_common.h | 1 -
> app/test-pmd/macswap_sse.h | 45
> +++++++++++++++++++++++++++++++++++++++++++
> 3 files changed, 49 insertions(+), 1 deletion(-)
> create mode 100644 app/test-pmd/macswap_sse.h
>
> diff --git a/app/test-pmd/macswap.c b/app/test-pmd/macswap.c
> index 849194fe2..cbb41b728 100644
> --- a/app/test-pmd/macswap.c
> +++ b/app/test-pmd/macswap.c
> @@ -66,7 +66,11 @@
> #include <rte_flow.h>
>
> #include "testpmd.h"
> +#ifdef RTE_ARCH_X86
> +#include "macswap_sse.h"
> +#else
> #include "macswap.h"
> +#endif
>
> /*
> * MAC swap forwarding mode: Swap the source and the destination
> Ethernet
> diff --git a/app/test-pmd/macswap_common.h b/app/test-
> pmd/macswap_common.h
> index ab0a5b5ef..8c5518596 100644
> --- a/app/test-pmd/macswap_common.h
> +++ b/app/test-pmd/macswap_common.h
> @@ -44,4 +44,3 @@ mbuf_field_set(struct rte_mbuf *mb, uint64_t
> ol_flags)
> }
>
> #endif /* _BPF_CMD_H_ */
> -
> diff --git a/app/test-pmd/macswap_sse.h b/app/test-pmd/macswap_sse.h
> new file mode 100644
> index 000000000..79f4f9a7c
> --- /dev/null
> +++ b/app/test-pmd/macswap_sse.h
> @@ -0,0 +1,45 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2018 Intel Corporation
> + */
> +
> +#ifndef _L2FWD_SSE_H_
> +#define _L2FWD_SSE_H_
Copy paste error.
> +
> +#include "macswap_common.h"
> +
> +static inline void
> +do_macswap(struct rte_mbuf *pkts[], uint16_t nb,
> + struct rte_port *txp)
> +{
> + struct ether_hdr *eth_hdr;
> + struct rte_mbuf *mb;
> + uint64_t ol_flags;
> + int i;
> + __m128i addr;
> + __m128i shfl_msk = _mm_set_epi8(15, 14, 13, 12,
> + 5, 4, 3, 2,
> + 1, 0, 11, 10,
> + 9, 8, 7, 6);
> +
> + ol_flags = ol_flags_init(txp->dev_conf.txmode.offloads);
> + vlan_qinq_set(pkts, nb, ol_flags,
> + txp->tx_vlan_id, txp->tx_vlan_id_outer);
> +
> + for (i = 0; i < nb; i++) {
> + if (likely(i < nb - 1))
> + rte_prefetch0(rte_pktmbuf_mtod(pkts[i+1],
> void *));
> + mb = pkts[i];
> +
> + eth_hdr = rte_pktmbuf_mtod(mb, struct ether_hdr *);
> +
> + /* Swap dest and src mac addresses. */
> + addr = _mm_loadu_si128((__m128i *)eth_hdr);
> + addr = _mm_shuffle_epi8(addr, shfl_msk);
> + _mm_storeu_si128((__m128i *)eth_hdr, addr);
> +
> + mbuf_field_set(mb, ol_flags);
> + }
> +}
> +
> +#endif /* _BPF_CMD_H_ */
Copy paste error.
> +
> --
> 2.13.6
>
next prev parent reply other threads:[~2018-12-13 19:50 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-11-22 17:26 [dpdk-dev] [PATCH 0/3] improve MAC swap performance Qi Zhang
2018-11-22 17:26 ` [dpdk-dev] [PATCH 1/3] app/testpmd: code refactory for macswap Qi Zhang
2018-11-22 17:26 ` [dpdk-dev] [PATCH 2/3] app/testpmd: improve MAC swap performance for x86 Qi Zhang
2018-11-22 17:26 ` [dpdk-dev] [PATCH 3/3] app/testpmd: further " Qi Zhang
2018-11-22 17:38 ` [dpdk-dev] [PATCH v2 0/3] improve MAC swap performance Qi Zhang
2018-11-22 17:38 ` [dpdk-dev] [PATCH v2 1/3] app/testpmd: code refactory for macswap Qi Zhang
2018-12-10 17:44 ` Ferruh Yigit
2018-12-11 4:02 ` Zhang, Qi Z
2018-11-22 17:38 ` [dpdk-dev] [PATCH v2 2/3] app/testpmd: improve MAC swap performance for x86 Qi Zhang
2018-12-10 17:44 ` Ferruh Yigit
2018-11-22 17:38 ` [dpdk-dev] [PATCH v2 3/3] app/testpmd: further " Qi Zhang
2018-12-11 5:55 ` [dpdk-dev] [PATCH v2 0/3] improve MAC swap performance Qi Zhang
2018-12-11 5:55 ` [dpdk-dev] [PATCH v2 1/3] app/testpmd: code refactory for macswap Qi Zhang
2018-12-11 15:48 ` Ferruh Yigit
2018-12-14 11:14 ` Iremonger, Bernard
2018-12-14 11:21 ` Zhang, Qi Z
2018-12-11 5:55 ` [dpdk-dev] [PATCH v2 2/3] app/testpmd: improve MAC swap performance for x86 Qi Zhang
2018-12-13 19:50 ` Jerin Jacob Kollanukkaran [this message]
2018-12-14 11:21 ` Iremonger, Bernard
2018-12-14 11:36 ` Zhang, Qi Z
2018-12-11 5:55 ` [dpdk-dev] [PATCH v2 3/3] app/testpmd: further " Qi Zhang
2018-12-16 0:58 ` [dpdk-dev] [PATCH v3 0/3] improve MAC swap performance Qi Zhang
2018-12-16 0:58 ` [dpdk-dev] [PATCH v3 1/3] app/testpmd: code refactory for macswap Qi Zhang
2018-12-18 11:06 ` Iremonger, Bernard
2018-12-16 0:58 ` [dpdk-dev] [PATCH v3 2/3] app/testpmd: improve MAC swap performance for x86 Qi Zhang
2018-12-18 11:07 ` Iremonger, Bernard
2018-12-16 0:58 ` [dpdk-dev] [PATCH v3 3/3] app/testpmd: further " Qi Zhang
2018-12-18 11:09 ` Iremonger, Bernard
2018-12-18 0:15 ` [dpdk-dev] [PATCH v3 0/3] improve MAC swap performance Ferruh Yigit
2018-12-18 16:29 ` 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=470f02192a8a08a0fb4181c81d5c731b3fecf30b.camel@marvell.com \
--to=jerinj@marvell.com \
--cc=bernard.iremonger@intel.com \
--cc=bruce.richardson@intel.com \
--cc=dev@dpdk.org \
--cc=ferruh.yigit@intel.com \
--cc=keith.wiles@intel.com \
--cc=konstantin.ananyev@intel.com \
--cc=qi.z.zhang@intel.com \
--cc=wenzhuo.lu@intel.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;
as well as URLs for NNTP newsgroup(s).