netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Wei Wang <weiwan@google.com>
To: "David S . Miller" <davem@davemloft.net>, netdev@vger.kernel.org
Cc: Eric Dumazet <edumazet@google.com>,
	Jakub Kicinski <kuba@kernel.org>,
	Hannes Frederic Sowa <hannes@stressinduktion.org>,
	Paolo Abeni <pabeni@redhat.com>, Felix Fietkau <nbd@nbd.name>,
	Wei Wang <weiwan@google.com>
Subject: [PATCH net-next 4/5] net: modify kthread handler to use __napi_poll()
Date: Wed, 30 Sep 2020 12:21:39 -0700	[thread overview]
Message-ID: <20200930192140.4192859-5-weiwan@google.com> (raw)
In-Reply-To: <20200930192140.4192859-1-weiwan@google.com>

From: Jakub Kicinski <kuba@kernel.org> 

The current kthread handler calls napi_poll() and has to pass a dummy
repoll list to the function, which seems redundent. The new proposed
kthread handler calls the newly proposed __napi_poll(), and respects
napi->weight as before. If repoll is needed, cond_resched() is called
first to give other tasks a chance to run before repolling.
This change is proposed by Jakub Kicinski <kuba@kernel.org> on top of
the previous patch.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Wei Wang <weiwan@google.com>
---
 net/core/dev.c | 62 +++++++++++++++++++-------------------------------
 1 file changed, 24 insertions(+), 38 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index c82522262ca8..b4f33e442b5e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6827,6 +6827,15 @@ static int __napi_poll(struct napi_struct *n, bool *repoll)
 
 	gro_normal_list(n);
 
+	/* Some drivers may have called napi_schedule
+	 * prior to exhausting their budget.
+	 */
+	if (unlikely(!list_empty(&n->poll_list))) {
+		pr_warn_once("%s: Budget exhausted after napi rescheduled\n",
+			     n->dev ? n->dev->name : "backlog");
+		return work;
+	}
+
 	*repoll = true;
 
 	return work;
@@ -6847,15 +6856,6 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 	if (!do_repoll)
 		goto out_unlock;
 
-	/* Some drivers may have called napi_schedule
-	 * prior to exhausting their budget.
-	 */
-	if (unlikely(!list_empty(&n->poll_list))) {
-		pr_warn_once("%s: Budget exhausted after napi rescheduled\n",
-			     n->dev ? n->dev->name : "backlog");
-		goto out_unlock;
-	}
-
 	list_add_tail(&n->poll_list, repoll);
 
 out_unlock:
@@ -6884,40 +6884,26 @@ static int napi_thread_wait(struct napi_struct *napi)
 static int napi_threaded_poll(void *data)
 {
 	struct napi_struct *napi = data;
+	void *have;
 
 	while (!napi_thread_wait(napi)) {
-		struct list_head dummy_repoll;
-		int budget = netdev_budget;
-		unsigned long time_limit;
-		bool again = true;
+		for (;;) {
+			bool repoll = false;
 
-		INIT_LIST_HEAD(&dummy_repoll);
-		local_bh_disable();
-		time_limit = jiffies + 2;
-		do {
-			/* ensure that the poll list is not empty */
-			if (list_empty(&dummy_repoll))
-				list_add(&napi->poll_list, &dummy_repoll);
-
-			budget -= napi_poll(napi, &dummy_repoll);
-			if (unlikely(budget <= 0 ||
-				     time_after_eq(jiffies, time_limit))) {
-				cond_resched();
-
-				/* refresh the budget */
-				budget = netdev_budget;
-				__kfree_skb_flush();
-				time_limit = jiffies + 2;
-			}
+			local_bh_disable();
 
-			if (napi_disable_pending(napi))
-				again = false;
-			else if (!test_bit(NAPI_STATE_SCHED, &napi->state))
-				again = false;
-		} while (again);
+			have = netpoll_poll_lock(napi);
+			__napi_poll(napi, &repoll);
+			netpoll_poll_unlock(have);
 
-		__kfree_skb_flush();
-		local_bh_enable();
+			__kfree_skb_flush();
+			local_bh_enable();
+
+			if (!repoll)
+				break;
+
+			cond_resched();
+		}
 	}
 	return 0;
 }
-- 
2.28.0.709.gb0816b6eb0-goog


  parent reply	other threads:[~2020-09-30 19:22 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-09-30 19:21 [PATCH net-next 0/5] implement kthread based napi poll Wei Wang
2020-09-30 19:21 ` [PATCH net-next 1/5] net: implement threaded-able napi poll loop support Wei Wang
2020-09-30 19:21 ` [PATCH net-next 2/5] net: add sysfs attribute to control napi threaded mode Wei Wang
2020-09-30 19:21 ` [PATCH net-next 3/5] net: extract napi poll functionality to __napi_poll() Wei Wang
2020-09-30 19:21 ` Wei Wang [this message]
2020-09-30 19:21 ` [PATCH net-next 5/5] net: improve napi threaded config Wei Wang
2020-10-01 10:01   ` Felix Fietkau
2020-10-01 17:01     ` Wei Wang
2020-10-01 17:11       ` Felix Fietkau
2020-10-01 18:03         ` Eric Dumazet
2020-10-01 18:37           ` Felix Fietkau
2020-10-01 19:24             ` Wei Wang
2020-10-01 20:48               ` Felix Fietkau
2020-10-01 22:42                 ` Wei Wang
2020-09-30 20:08 ` [PATCH net-next 0/5] implement kthread based napi poll Jakub Kicinski
2020-10-01  7:52   ` Eric Dumazet
2020-10-01 20:26     ` Jakub Kicinski
2020-10-01 22:12       ` Wei Wang
2020-10-01 23:46         ` Jakub Kicinski
2020-10-02  1:44           ` Wei Wang
2020-10-02 22:53             ` Jakub Kicinski
2020-10-02  7:56       ` Eric Dumazet
2020-10-02 22:49         ` Jakub Kicinski
2020-10-02 23:00 ` David Miller
2020-10-02 23:15   ` Alexei Starovoitov
2020-10-03  3:54     ` Eric Dumazet
2020-10-03  4:17       ` Alexei Starovoitov

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=20200930192140.4192859-5-weiwan@google.com \
    --to=weiwan@google.com \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=hannes@stressinduktion.org \
    --cc=kuba@kernel.org \
    --cc=nbd@nbd.name \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@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).