DPDK patches and discussions
 help / color / mirror / Atom feed
From: Wenzhuo Lu <wenzhuo.lu@intel.com>
To: dev@dpdk.org
Subject: [dpdk-dev] [PATCH 03/17] ixgbe/base: do not wait for signature rule addition
Date: Fri, 20 Nov 2015 15:17:44 +0800	[thread overview]
Message-ID: <1448003879-29960-4-git-send-email-wenzhuo.lu@intel.com> (raw)
In-Reply-To: <1448003879-29960-1-git-send-email-wenzhuo.lu@intel.com>

Waiting for FDIRCMD completion is an expensive thing to do in the
transmit hot path. This wait was added to catch problems with perfect
filter rules, and, at least in the Linux driver, there is no error
check anyway, so there is no point to adding the delay. So do not wait
for completion. Change the return of the function to void, since it has
no meaningful return value.

Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
---
 drivers/net/ixgbe/base/ixgbe_82599.c | 19 ++++++-------------
 drivers/net/ixgbe/base/ixgbe_api.h   |  8 ++++----
 2 files changed, 10 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ixgbe/base/ixgbe_82599.c b/drivers/net/ixgbe/base/ixgbe_82599.c
index f0deb59..cc65919 100644
--- a/drivers/net/ixgbe/base/ixgbe_82599.c
+++ b/drivers/net/ixgbe/base/ixgbe_82599.c
@@ -1491,16 +1491,15 @@ u32 ixgbe_atr_compute_sig_hash_82599(union ixgbe_atr_hash_dword input,
  * Note that the tunnel bit in input must not be set when the hardware
  * tunneling support does not exist.
  **/
-s32 ixgbe_fdir_add_signature_filter_82599(struct ixgbe_hw *hw,
-					  union ixgbe_atr_hash_dword input,
-					  union ixgbe_atr_hash_dword common,
-					  u8 queue)
+void ixgbe_fdir_add_signature_filter_82599(struct ixgbe_hw *hw,
+					   union ixgbe_atr_hash_dword input,
+					   union ixgbe_atr_hash_dword common,
+					   u8 queue)
 {
 	u64 fdirhashcmd;
 	u8 flow_type;
 	bool tunnel;
 	u32 fdircmd;
-	s32 err;
 
 	DEBUGFUNC("ixgbe_fdir_add_signature_filter_82599");
 
@@ -1522,7 +1521,7 @@ s32 ixgbe_fdir_add_signature_filter_82599(struct ixgbe_hw *hw,
 		break;
 	default:
 		DEBUGOUT(" Error on flow type input\n");
-		return IXGBE_ERR_CONFIG;
+		return;
 	}
 
 	/* configure FDIRCMD register */
@@ -1541,15 +1540,9 @@ s32 ixgbe_fdir_add_signature_filter_82599(struct ixgbe_hw *hw,
 	fdirhashcmd |= ixgbe_atr_compute_sig_hash_82599(input, common);
 	IXGBE_WRITE_REG64(hw, IXGBE_FDIRHASH, fdirhashcmd);
 
-	err = ixgbe_fdir_check_cmd_complete(hw, &fdircmd);
-	if (err) {
-		DEBUGOUT("Flow Director command did not complete!\n");
-		return err;
-	}
-
 	DEBUGOUT2("Tx Queue=%x hash=%x\n", queue, (u32)fdirhashcmd);
 
-	return IXGBE_SUCCESS;
+	return;
 }
 
 #define IXGBE_COMPUTE_BKT_HASH_ITERATION(_n) \
diff --git a/drivers/net/ixgbe/base/ixgbe_api.h b/drivers/net/ixgbe/base/ixgbe_api.h
index bd1208e..c751132 100644
--- a/drivers/net/ixgbe/base/ixgbe_api.h
+++ b/drivers/net/ixgbe/base/ixgbe_api.h
@@ -149,10 +149,10 @@ s32 ixgbe_reinit_fdir_tables_82599(struct ixgbe_hw *hw);
 s32 ixgbe_init_fdir_signature_82599(struct ixgbe_hw *hw, u32 fdirctrl);
 s32 ixgbe_init_fdir_perfect_82599(struct ixgbe_hw *hw, u32 fdirctrl,
 					bool cloud_mode);
-s32 ixgbe_fdir_add_signature_filter_82599(struct ixgbe_hw *hw,
-					  union ixgbe_atr_hash_dword input,
-					  union ixgbe_atr_hash_dword common,
-					  u8 queue);
+void ixgbe_fdir_add_signature_filter_82599(struct ixgbe_hw *hw,
+					   union ixgbe_atr_hash_dword input,
+					   union ixgbe_atr_hash_dword common,
+					   u8 queue);
 s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw,
 				    union ixgbe_atr_input *input_mask, bool cloud_mode);
 s32 ixgbe_fdir_write_perfect_filter_82599(struct ixgbe_hw *hw,
-- 
1.9.3

  parent reply	other threads:[~2015-11-20  7:18 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-11-20  7:17 [dpdk-dev] [PATCH 00/17] Update ixgbe base code Wenzhuo Lu
2015-11-20  7:17 ` [dpdk-dev] [PATCH 01/17] ixgbe/base: update README Wenzhuo Lu
2015-11-20  7:17 ` [dpdk-dev] [PATCH 02/17] ixgbe/base: avoid needless PHY access on copper phys Wenzhuo Lu
2015-11-20  7:17 ` Wenzhuo Lu [this message]
2015-11-20  7:17 ` [dpdk-dev] [PATCH 04/17] ixgbe/base: use mvals values instead of defines Wenzhuo Lu
2015-11-20  7:17 ` [dpdk-dev] [PATCH 05/17] ixgbe/base: add Single-port Sage Pond device ID Wenzhuo Lu
2015-11-20  7:17 ` [dpdk-dev] [PATCH 06/17] ixgbe/base: remove driver config of KX4 PHY Wenzhuo Lu
2015-11-20  7:17 ` [dpdk-dev] [PATCH 07/17] ixgbe/base: add Flow Control Ethertype to ETQF filter list Wenzhuo Lu
2015-11-20  7:17 ` [dpdk-dev] [PATCH 08/17] ixgbe/base: add KR mode support Wenzhuo Lu
2015-11-20  7:17 ` [dpdk-dev] [PATCH 09/17] ixgbe/base: add flow director drop queue Wenzhuo Lu
2015-11-20  7:17 ` [dpdk-dev] [PATCH 10/17] ixgbe/base: check mac type for iosf and phy Wenzhuo Lu
2015-11-20  7:17 ` [dpdk-dev] [PATCH 11/17] ixgbe/base: configure x550 MDIO clock speed Wenzhuo Lu
2015-11-20  7:17 ` [dpdk-dev] [PATCH 12/17] ixgbe/base: fill at least min credits to a TC credit refills Wenzhuo Lu
2015-11-20  7:17 ` [dpdk-dev] [PATCH 13/17] ixgbe/base: support new thermal alarm Wenzhuo Lu
2015-11-20  7:17 ` [dpdk-dev] [PATCH 14/17] ixgbe/base: add new iXFI configuration helper function Wenzhuo Lu
2015-11-20  7:17 ` [dpdk-dev] [PATCH 15/17] ixgbe/base: prevent KR PHY reset in init Wenzhuo Lu
2015-11-20  7:17 ` [dpdk-dev] [PATCH 16/17] ixgbe/base: new defines for FW Wenzhuo Lu
2015-11-20  7:17 ` [dpdk-dev] [PATCH 17/17] ixgbe: add new device X550T1 Wenzhuo Lu
2015-11-20 16:41   ` Stephen Hemminger
2016-01-14  8:48 ` [dpdk-dev] [PATCH 00/17] Update ixgbe base code 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=1448003879-29960-4-git-send-email-wenzhuo.lu@intel.com \
    --to=wenzhuo.lu@intel.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).