From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
To: davem@davemloft.net
Cc: Jesse Brandeburg <jesse.brandeburg@intel.com>,
netdev@vger.kernel.org, nhorman@redhat.com, sassmann@redhat.com,
jogreene@redhat.com, Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Subject: [net-next 06/14] i40e/i40evf: Faster RX via avoiding FCoE
Date: Wed, 6 Apr 2016 20:29:31 -0700 [thread overview]
Message-ID: <1459999779-22254-7-git-send-email-jeffrey.t.kirsher@intel.com> (raw)
In-Reply-To: <1459999779-22254-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
As it turns out, calling into other files from hot path hurts
performance a lot. In this case the majority of the time we
call "check FCoE" and the packet is *not* FCoE, but this call
was taking 5% of our total cycles spent on receive.
Change-ID: I080552c26e7060bc7b78504dc2763f6f0b3d8c76
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_fcoe.c | 12 +-----------
drivers/net/ethernet/intel/i40e/i40e_txrx.c | 8 ++++++--
drivers/net/ethernet/intel/i40e/i40e_txrx.h | 10 ++++++++++
drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 4 +++-
drivers/net/ethernet/intel/i40evf/i40e_txrx.h | 10 ++++++++++
5 files changed, 30 insertions(+), 14 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_fcoe.c b/drivers/net/ethernet/intel/i40e/i40e_fcoe.c
index 92d2208..58e6c15 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_fcoe.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_fcoe.c
@@ -1,7 +1,7 @@
/*******************************************************************************
*
* Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2015 Intel Corporation.
+ * Copyright(c) 2013 - 2016 Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
@@ -38,16 +38,6 @@
#include "i40e_fcoe.h"
/**
- * i40e_rx_is_fcoe - returns true if the rx packet type is FCoE
- * @ptype: the packet type field from rx descriptor write-back
- **/
-static inline bool i40e_rx_is_fcoe(u16 ptype)
-{
- return (ptype >= I40E_RX_PTYPE_L2_FCOE_PAY3) &&
- (ptype <= I40E_RX_PTYPE_L2_FCOE_VFT_FCOTHER);
-}
-
-/**
* i40e_fcoe_sof_is_class2 - returns true if this is a FC Class 2 SOF
* @sof: the FCoE start of frame delimiter
**/
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index f4e4d3d..29ffed2 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1703,7 +1703,9 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, const int budget)
? le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1)
: 0;
#ifdef I40E_FCOE
- if (!i40e_fcoe_handle_offload(rx_ring, rx_desc, skb)) {
+ if (unlikely(
+ i40e_rx_is_fcoe(rx_ptype) &&
+ !i40e_fcoe_handle_offload(rx_ring, rx_desc, skb))) {
dev_kfree_skb_any(skb);
continue;
}
@@ -1834,7 +1836,9 @@ static int i40e_clean_rx_irq_1buf(struct i40e_ring *rx_ring, int budget)
? le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1)
: 0;
#ifdef I40E_FCOE
- if (!i40e_fcoe_handle_offload(rx_ring, rx_desc, skb)) {
+ if (unlikely(
+ i40e_rx_is_fcoe(rx_ptype) &&
+ !i40e_fcoe_handle_offload(rx_ring, rx_desc, skb))) {
dev_kfree_skb_any(skb);
continue;
}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index 9e654e6..77ccdde 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -448,4 +448,14 @@ static inline bool i40e_chk_linearize(struct sk_buff *skb, int count)
return __i40e_chk_linearize(skb);
}
+
+/**
+ * i40e_rx_is_fcoe - returns true if the Rx packet type is FCoE
+ * @ptype: the packet type field from Rx descriptor write-back
+ **/
+static inline bool i40e_rx_is_fcoe(u16 ptype)
+{
+ return (ptype >= I40E_RX_PTYPE_L2_FCOE_PAY3) &&
+ (ptype <= I40E_RX_PTYPE_L2_FCOE_VFT_FCOTHER);
+}
#endif /* _I40E_TXRX_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index ec1f447..0c912a4 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -1160,7 +1160,9 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, const int budget)
? le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1)
: 0;
#ifdef I40E_FCOE
- if (!i40e_fcoe_handle_offload(rx_ring, rx_desc, skb)) {
+ if (unlikely(
+ i40e_rx_is_fcoe(rx_ptype) &&
+ !i40e_fcoe_handle_offload(rx_ring, rx_desc, skb))) {
dev_kfree_skb_any(skb);
continue;
}
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
index 3ec0ea5..84c28aa6 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
@@ -430,4 +430,14 @@ static inline bool i40e_chk_linearize(struct sk_buff *skb, int count)
return __i40evf_chk_linearize(skb);
}
+
+/**
+ * i40e_rx_is_fcoe - returns true if the Rx packet type is FCoE
+ * @ptype: the packet type field from Rx descriptor write-back
+ **/
+static inline bool i40e_rx_is_fcoe(u16 ptype)
+{
+ return (ptype >= I40E_RX_PTYPE_L2_FCOE_PAY3) &&
+ (ptype <= I40E_RX_PTYPE_L2_FCOE_VFT_FCOTHER);
+}
#endif /* _I40E_TXRX_H_ */
--
2.5.5
next prev parent reply other threads:[~2016-04-07 3:29 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-04-07 3:29 [net-next 00/14][pull request] 40GbE Intel Wired LAN Driver Updates 2016-04-06 Jeff Kirsher
2016-04-07 3:29 ` [net-next 01/14] i40e: Inserting a HW capability display info Jeff Kirsher
2016-04-07 3:29 ` [net-next 02/14] i40e: Leave debug_mask cleared at init Jeff Kirsher
2016-04-07 3:29 ` [net-next 03/14] i40e: Move HW flush Jeff Kirsher
2016-04-07 3:29 ` [net-next 04/14] i40e/i40evf: Move stack var deeper Jeff Kirsher
2016-04-07 3:29 ` [net-next 05/14] i40e/i40evf: Drop unused tx_ring argument Jeff Kirsher
2016-04-07 3:29 ` Jeff Kirsher [this message]
2016-04-07 3:29 ` [net-next 07/14] i40e: Patch to support trusted VF Jeff Kirsher
2016-04-07 3:29 ` [net-next 08/14] i40e: Restrict VF poll mode to only single function mode devices Jeff Kirsher
2016-04-07 3:29 ` [net-next 09/14] i40e: Move NVM variable out of AQ struct Jeff Kirsher
2016-04-07 3:29 ` [net-next 10/14] i40e: Add RSS configuration to virtual channel Jeff Kirsher
2016-04-07 3:29 ` [net-next 11/14] i40e: Move NVM event wait check to NVM code Jeff Kirsher
2016-04-07 3:29 ` [net-next 12/14] i40e: Input set mask constants for RSS, flow director, and flex bytes Jeff Kirsher
2016-04-07 3:29 ` [net-next 13/14] i40e/i40evf: Bump patch from 1.5.2 to 1.5.5 Jeff Kirsher
2016-04-07 3:29 ` [net-next 14/14] i40evf: properly handle VLAN features Jeff Kirsher
2016-04-07 4:11 ` [net-next 00/14][pull request] 40GbE Intel Wired LAN Driver Updates 2016-04-06 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=1459999779-22254-7-git-send-email-jeffrey.t.kirsher@intel.com \
--to=jeffrey.t.kirsher@intel.com \
--cc=davem@davemloft.net \
--cc=jesse.brandeburg@intel.com \
--cc=jogreene@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=nhorman@redhat.com \
--cc=sassmann@redhat.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).