From: Stephen Hemminger <shemminger@vyatta.com>
To: David Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Subject: [PATCH] net: eliminate refcounting in backlog queue
Date: Fri, 25 Jul 2008 12:32:12 -0700 [thread overview]
Message-ID: <20080725123212.393314a9@extreme> (raw)
Avoid the overhead of atomic increment/decrement on each received packet.
This helps performance of non-NAPI devices (like loopback).
Use cleanup function to walk queue on each cpu and clean out any
left over packets.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
--- a/net/core/dev.c 2008-07-25 11:27:07.000000000 -0700
+++ b/net/core/dev.c 2008-07-25 11:43:55.000000000 -0700
@@ -1909,7 +1909,6 @@ int netif_rx(struct sk_buff *skb)
if (queue->input_pkt_queue.qlen <= netdev_max_backlog) {
if (queue->input_pkt_queue.qlen) {
enqueue:
- dev_hold(skb->dev);
__skb_queue_tail(&queue->input_pkt_queue, skb);
local_irq_restore(flags);
return NET_RX_SUCCESS;
@@ -2270,6 +2269,20 @@ out:
return ret;
}
+/* Network device is going away, flush any packets still pending */
+static void flush_backlog(void *arg)
+{
+ struct net_device *dev = arg;
+ struct softnet_data *queue = &__get_cpu_var(softnet_data);
+ struct sk_buff *skb, *tmp;
+
+ skb_queue_walk_safe(&queue->input_pkt_queue, skb, tmp)
+ if (skb->dev == dev) {
+ __skb_unlink(skb, &queue->input_pkt_queue);
+ kfree_skb(skb);
+ }
+}
+
static int process_backlog(struct napi_struct *napi, int quota)
{
int work = 0;
@@ -2279,7 +2292,6 @@ static int process_backlog(struct napi_s
napi->weight = weight_p;
do {
struct sk_buff *skb;
- struct net_device *dev;
local_irq_disable();
skb = __skb_dequeue(&queue->input_pkt_queue);
@@ -2288,14 +2300,9 @@ static int process_backlog(struct napi_s
local_irq_enable();
break;
}
-
local_irq_enable();
- dev = skb->dev;
-
netif_receive_skb(skb);
-
- dev_put(dev);
} while (++work < quota && jiffies == start_time);
return work;
@@ -4165,6 +4172,8 @@ void netdev_run_todo(void)
dev->reg_state = NETREG_UNREGISTERED;
+ on_each_cpu(flush_backlog, dev, 1);
+
netdev_wait_allrefs(dev);
/* paranoia */
next reply other threads:[~2008-07-25 19:32 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-07-25 19:32 Stephen Hemminger [this message]
2008-08-04 4:30 ` [PATCH] net: eliminate refcounting in backlog queue 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=20080725123212.393314a9@extreme \
--to=shemminger@vyatta.com \
--cc=davem@davemloft.net \
--cc=netdev@vger.kernel.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