netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Wei Liu <wei.liu2@citrix.com>
To: netdev@vger.kernel.org, xen-devel@lists.xensource.com
Cc: ian.campbell@citrix.com, konrad.wilk@oracle.com,
	Wei Liu <wei.liu2@citrix.com>
Subject: [RFC PATCH V3 08/16] netback: remove unwanted notification generation during NAPI processing.
Date: Mon, 30 Jan 2012 14:45:26 +0000	[thread overview]
Message-ID: <1327934734-8908-9-git-send-email-wei.liu2@citrix.com> (raw)
In-Reply-To: <1327934734-8908-1-git-send-email-wei.liu2@citrix.com>

In original implementation, tx_build_gops tends to update req_event
pointer every time it sees tx error or finish one batch. Remove those
code to only update req_event pointer when we really want to shut down
NAPI.

Tested-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
---
 drivers/net/xen-netback/interface.c |    5 +++--
 drivers/net/xen-netback/netback.c   |    4 +---
 2 files changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index ebed26a..fe37143 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -58,8 +58,8 @@ static irqreturn_t xenvif_interrupt(int irq, void *dev_id)
 	if (xenvif_rx_schedulable(vif))
 		netif_wake_queue(vif->dev);
 
-	if (likely(napi_schedule_prep(&vif->napi)))
-		__napi_schedule(&vif->napi);
+	if (RING_HAS_UNCONSUMED_REQUESTS(&vif->tx))
+		napi_schedule(&vif->napi);
 
 	return IRQ_HANDLED;
 }
@@ -74,6 +74,7 @@ static int xenvif_poll(struct napi_struct *napi, int budget)
 	if (work_done < budget) {
 		int more_to_do = 0;
 		unsigned long flag;
+
 		local_irq_save(flag);
 
 		RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, more_to_do);
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 2a2835e..065cd65 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -662,7 +662,6 @@ static void xenvif_tx_err(struct xenvif *vif,
 		txp = RING_GET_REQUEST(&vif->tx, cons++);
 	} while (1);
 	vif->tx.req_cons = cons;
-	xenvif_check_rx_xenvif(vif);
 }
 
 static int xenvif_count_requests(struct xenvif *vif,
@@ -1047,7 +1046,7 @@ static unsigned xenvif_tx_build_gops(struct xenvif *vif,
 		int pool_idx;
 		struct pending_tx_info *pending_tx_info;
 
-		RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, work_to_do);
+		work_to_do = RING_HAS_UNCONSUMED_REQUESTS(&vif->tx);
 		if (!work_to_do) {
 			break;
 		}
@@ -1187,7 +1186,6 @@ static unsigned xenvif_tx_build_gops(struct xenvif *vif,
 		gop = request_gop;
 
 		vif->tx.req_cons = idx;
-		xenvif_check_rx_xenvif(vif);
 
 		if ((gop - tco) >= MAX_PENDING_REQS)
 			break;
-- 
1.7.2.5

  parent reply	other threads:[~2012-01-30 14:45 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-01-30 14:45 [RFC PATCH V3] Xen netback / netfront improvement Wei Liu
2012-01-30 14:45 ` [RFC PATCH V3 01/16] netback: page pool version 1 Wei Liu
2012-01-30 14:45 ` [RFC PATCH V3 02/16] netback: add module unload function Wei Liu
2012-01-30 14:45 ` [RFC PATCH V3 03/16] netback: switch to NAPI + kthread model Wei Liu
2012-01-30 14:45 ` [RFC PATCH V3 04/16] netback: switch to per-cpu scratch space Wei Liu
2012-01-30 16:49   ` Viral Mehta
2012-01-30 17:05     ` Wei Liu
2012-01-30 14:45 ` [RFC PATCH V3 05/16] netback: add module get/put operations along with vif connect/disconnect Wei Liu
2012-01-31 10:24   ` Ian Campbell
2012-01-31 10:39     ` Wei Liu
2012-01-30 14:45 ` [RFC PATCH V3 06/16] netback: melt xen_netbk into xenvif Wei Liu
2012-01-30 14:45 ` [RFC PATCH V3 07/16] netback: alter internal function/structure names Wei Liu
2012-01-30 14:45 ` Wei Liu [this message]
2012-01-30 14:45 ` [RFC PATCH V3 09/16] netback: nuke xenvif_receive_skb Wei Liu
2012-01-30 14:45 ` [RFC PATCH V3 10/16] netback: rework of per-cpu scratch space Wei Liu
2012-01-30 21:53   ` Konrad Rzeszutek Wilk
2012-01-31 10:48     ` Wei Liu
2012-01-31  1:25   ` Eric Dumazet
2012-01-31 10:43     ` Wei Liu
2012-01-30 14:45 ` [RFC PATCH V3 11/16] netback: print alert and bail when scratch space is not available Wei Liu
2012-01-30 14:45 ` [RFC PATCH V3 12/16] netback: multi-page ring support Wei Liu
2012-01-30 16:35   ` [Xen-devel] " Jan Beulich
2012-01-30 17:10     ` Wei Liu
2012-01-31  9:01       ` Jan Beulich
2012-01-31 11:09         ` Wei Liu
2012-01-31 11:12           ` Ian Campbell
2012-01-31 13:24           ` Jan Beulich
2012-01-31 13:32             ` Wei Liu
2012-01-31 14:48               ` Konrad Rzeszutek Wilk
2012-01-30 14:45 ` [RFC PATCH V3 13/16] netback: stub for multi receive protocol support Wei Liu
2012-01-30 21:47   ` [Xen-devel] " Konrad Rzeszutek Wilk
2012-01-31 11:03     ` Wei Liu
2012-01-31 14:43       ` Konrad Rzeszutek Wilk
2012-01-30 14:45 ` [RFC PATCH V3 14/16] netback: split event channels support Wei Liu
2012-01-31 10:37   ` Ian Campbell
2012-01-31 11:57     ` Wei Liu
2012-01-30 14:45 ` [RFC PATCH V3 15/16] netfront: multi page ring support Wei Liu
2012-01-30 21:39   ` [Xen-devel] " Konrad Rzeszutek Wilk
2012-01-31  9:12     ` Ian Campbell
2012-01-31 11:17       ` Wei Liu
2012-01-31  9:53     ` Jan Beulich
2012-01-31 11:15       ` Wei Liu
2012-01-31 10:58     ` Wei Liu
2012-01-30 14:45 ` [RFC PATCH V3 16/16] netfront: split event channels support Wei Liu
2012-01-30 21:25   ` [Xen-devel] " Konrad Rzeszutek Wilk

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=1327934734-8908-9-git-send-email-wei.liu2@citrix.com \
    --to=wei.liu2@citrix.com \
    --cc=ian.campbell@citrix.com \
    --cc=konrad.wilk@oracle.com \
    --cc=netdev@vger.kernel.org \
    --cc=xen-devel@lists.xensource.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).