netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Veaceslav Falico <vfalico@redhat.com>
To: netdev@vger.kernel.org
Cc: davem@davemloft.net, richardcochran@gmail.com,
	tshimizu818@gmail.com, andy.cress@us.kontron.com,
	erwan.velu@zodiacaerospace.com, agospoda@redhat.com
Subject: [PATCH 2/3] pch_gbe: don't re-set RX_FIFO_ERR flag in napi_poll
Date: Mon, 22 Oct 2012 16:43:24 +0200	[thread overview]
Message-ID: <1350917005-26350-3-git-send-email-vfalico@redhat.com> (raw)
In-Reply-To: <1350917005-26350-1-git-send-email-vfalico@redhat.com>

If we were in RX_FIFO_ERR state and entered pch_gbe_napi_poll(), we'll
anyway clean some rx space and thus can continue to receive more packets.
Currently, we re-set the RX_FIFO_ERR in situations when we've exhausted our
budget for RX cleaning or cleaned some TX packets. Removing it gives us
+20%-40% speed increase and a lot less of RX_FIFO_ERRors reported.

Signed-off-by: Veaceslav Falico <vfalico@redhat.com>
---
 .../net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c   |   19 ++++++-------------
 1 files changed, 6 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index d5190bf..4ffad78 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -2419,7 +2419,6 @@ static int pch_gbe_napi_poll(struct napi_struct *napi, int budget)
 	int work_done = 0;
 	bool poll_end_flag = false;
 	bool cleaned = false;
-	u32 int_en;
 
 	pr_debug("budget : %d\n", budget);
 
@@ -2436,19 +2435,13 @@ static int pch_gbe_napi_poll(struct napi_struct *napi, int budget)
 
 	if (poll_end_flag) {
 		napi_complete(napi);
-		if (adapter->rx_stop_flag) {
-			adapter->rx_stop_flag = false;
-			pch_gbe_start_receive(&adapter->hw);
-		}
 		pch_gbe_irq_enable(adapter);
-	} else
-		if (adapter->rx_stop_flag) {
-			adapter->rx_stop_flag = false;
-			pch_gbe_start_receive(&adapter->hw);
-			int_en = ioread32(&adapter->hw.reg->INT_EN);
-			iowrite32((int_en | PCH_GBE_INT_RX_FIFO_ERR),
-				&adapter->hw.reg->INT_EN);
-		}
+	}
+
+	if (adapter->rx_stop_flag) {
+		adapter->rx_stop_flag = false;
+		pch_gbe_start_receive(&adapter->hw);
+	}
 
 	pr_debug("poll_end_flag : %d  work_done : %d  budget : %d\n",
 		 poll_end_flag, work_done, budget);
-- 
1.7.1

  parent reply	other threads:[~2012-10-22 14:43 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-10-22 14:43 [PATCH 0/3] pch_gbe: fix CRC errors and improve speed Veaceslav Falico
2012-10-22 14:43 ` [PATCH 1/3] pch_gbe: create functions for MAC_RX {en,dis}able Veaceslav Falico
2012-10-22 14:43 ` Veaceslav Falico [this message]
2012-10-22 14:43 ` [PATCH 3/3] pch_gbe: don't reset MAC_RX on FIFO overflow Veaceslav Falico
2012-10-23  6:31 ` [PATCH 0/3] pch_gbe: fix CRC errors and improve speed 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=1350917005-26350-3-git-send-email-vfalico@redhat.com \
    --to=vfalico@redhat.com \
    --cc=agospoda@redhat.com \
    --cc=andy.cress@us.kontron.com \
    --cc=davem@davemloft.net \
    --cc=erwan.velu@zodiacaerospace.com \
    --cc=netdev@vger.kernel.org \
    --cc=richardcochran@gmail.com \
    --cc=tshimizu818@gmail.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).