netdev - [PATCH net-next v3 5/5] net: improve napi threaded config

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20201118191009.3406652-6-weiwan@google.com>
Date:   Wed, 18 Nov 2020 11:10:09 -0800
From:   Wei Wang <weiwan@...gle.com>
To:     David Miller <davem@...emloft.net>,
        Jakub Kicinski <kuba@...nel.org>, netdev@...r.kernel.org
Cc:     Eric Dumazet <edumazet@...gle.com>, Felix Fietkau <nbd@....name>,
        Paolo Abeni <pabeni@...hat.com>,
        Hannes Frederic Sowa <hannes@...essinduktion.org>,
        Hillf Danton <hdanton@...a.com>, Wei Wang <weiwan@...gle.com>
Subject: [PATCH net-next v3 5/5] net: improve napi threaded config

This commit mainly addresses the threaded config to make the switch
between softirq based and kthread based NAPI processing not require
a device down/up.
It also moves the kthread_run() call to the sysfs handler when user
tries to enable "threaded" on napi, and properly handles the
kthread_run() failure. This is because certain drivers do not have
the napi created and linked to the dev when dev_open() is called. So
the previous implementation does not work properly there.

Signed-off-by: Wei Wang <weiwan@...gle.com>
Reviewed-by: Eric Dumazet <edumazet@...gle.com>
---
 net/core/dev.c       | 53 ++++++++++++++++++++++++++------------------
 net/core/net-sysfs.c |  9 +++-----
 2 files changed, 35 insertions(+), 27 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 88437cdf29f1..7788899b100f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1491,17 +1491,28 @@ EXPORT_SYMBOL(netdev_notify_peers);
 
 static int napi_threaded_poll(void *data);
 
-static void napi_thread_start(struct napi_struct *n)
+static int napi_kthread_create(struct napi_struct *n)
 {
-	if (test_bit(NAPI_STATE_THREADED, &n->state) && !n->thread)
-		n->thread = kthread_create(napi_threaded_poll, n, "%s-%d",
-					   n->dev->name, n->napi_id);
+	int err = 0;
+
+	/* Create and wake up the kthread once to put it in
+	 * TASK_INTERRUPTIBLE mode to avoid the blocked task
+	 * warning and work with loadavg.
+	 */
+	n->thread = kthread_run(napi_threaded_poll, n, "napi/%s-%d",
+				n->dev->name, n->napi_id);
+	if (IS_ERR(n->thread)) {
+		err = PTR_ERR(n->thread);
+		pr_err("kthread_run failed with err %d\n", err);
+		n->thread = NULL;
+	}
+
+	return err;
 }
 
 static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
-	struct napi_struct *n;
 	int ret;
 
 	ASSERT_RTNL();
@@ -1533,9 +1544,6 @@ static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack)
 	if (!ret && ops->ndo_open)
 		ret = ops->ndo_open(dev);
 
-	list_for_each_entry(n, &dev->napi_list, dev_list)
-		napi_thread_start(n);
-
 	netpoll_poll_enable(dev);
 
 	if (ret)
@@ -1586,6 +1594,7 @@ static void napi_thread_stop(struct napi_struct *n)
 	if (!n->thread)
 		return;
 	kthread_stop(n->thread);
+	clear_bit(NAPI_STATE_THREADED, &n->state);
 	n->thread = NULL;
 }
 
@@ -4271,7 +4280,7 @@ int gro_normal_batch __read_mostly = 8;
 static inline void ____napi_schedule(struct softnet_data *sd,
 				     struct napi_struct *napi)
 {
-	if (napi->thread) {
+	if (test_bit(NAPI_STATE_THREADED, &napi->state)) {
 		wake_up_process(napi->thread);
 		return;
 	}
@@ -6700,25 +6709,25 @@ static void init_gro_hash(struct napi_struct *napi)
 
 int napi_set_threaded(struct napi_struct *n, bool threaded)
 {
-	ASSERT_RTNL();
+	int err = 0;
 
-	if (n->dev->flags & IFF_UP)
-		return -EBUSY;
+	ASSERT_RTNL();
 
 	if (threaded == !!test_bit(NAPI_STATE_THREADED, &n->state))
 		return 0;
-	if (threaded)
+	if (threaded) {
+		if (!n->thread) {
+			err = napi_kthread_create(n);
+			if (err)
+				goto out;
+		}
 		set_bit(NAPI_STATE_THREADED, &n->state);
-	else
+	} else {
 		clear_bit(NAPI_STATE_THREADED, &n->state);
+	}
 
-	/* if the device is initializing, nothing todo */
-	if (test_bit(__LINK_STATE_START, &n->dev->state))
-		return 0;
-
-	napi_thread_stop(n);
-	napi_thread_start(n);
-	return 0;
+out:
+	return err;
 }
 EXPORT_SYMBOL(napi_set_threaded);
 
@@ -6763,6 +6772,7 @@ void napi_disable(struct napi_struct *n)
 		msleep(1);
 
 	hrtimer_cancel(&n->timer);
+	napi_thread_stop(n);
 
 	clear_bit(NAPI_STATE_DISABLE, &n->state);
 }
@@ -6883,6 +6893,7 @@ static int napi_thread_wait(struct napi_struct *napi)
 
 	while (!kthread_should_stop() && !napi_disable_pending(napi)) {
 		if (test_bit(NAPI_STATE_SCHED, &napi->state)) {
+			WARN_ON(!list_empty(&napi->poll_list));
 			__set_current_state(TASK_RUNNING);
 			return 0;
 		}
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index df8dd25e5e4b..1e24c1e81ad8 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -609,11 +609,6 @@ static ssize_t threaded_store(struct device *dev,
 		goto unlock;
 	}
 
-	if (netdev->flags & IFF_UP) {
-		ret = -EBUSY;
-		goto unlock;
-	}
-
 	bmap = __alloc_thread_bitmap(netdev, &bits);
 	if (!bmap) {
 		ret = -ENOMEM;
@@ -626,7 +621,9 @@ static ssize_t threaded_store(struct device *dev,
 
 	i = 0;
 	list_for_each_entry(n, &netdev->napi_list, dev_list) {
-		napi_set_threaded(n, test_bit(i, bmap));
+		ret = napi_set_threaded(n, test_bit(i, bmap));
+		if (ret)
+			goto free_unlock;
 		i++;
 	}
 	ret = len;
-- 
2.29.2.454.gaff20da3a2-goog