All of lore.kernel.org
 help / color / mirror / Atom feed
From: Felix Fietkau <nbd@nbd.name>
To: Hillf Danton <hdanton@sina.com>,
	David Laight <David.Laight@ACULAB.COM>,
	Andrew Lunn <andrew@lunn.ch>,
	Rakesh Pillai <pillair@codeaurora.org>
Cc: "netdev@vger.kernel.org" <netdev@vger.kernel.org>,
	"linux-wireless@vger.kernel.org" <linux-wireless@vger.kernel.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"ath10k@lists.infradead.org" <ath10k@lists.infradead.org>,
	"dianders@chromium.org" <dianders@chromium.org>,
	Markus Elfring <Markus.Elfring@web.de>,
	"evgreen@chromium.org" <evgreen@chromium.org>,
	"kuba@kernel.org" <kuba@kernel.org>,
	"johannes@sipsolutions.net" <johannes@sipsolutions.net>,
	"davem@davemloft.net" <davem@davemloft.net>,
	"kvalo@codeaurora.org" <kvalo@codeaurora.org>
Subject: Re: [RFC 0/7] Add support to process rx packets in thread
Date: Sat, 25 Jul 2020 19:57:23 +0200	[thread overview]
Message-ID: <a50ebfba-9733-48db-c90b-5fc106e67f29@nbd.name> (raw)
In-Reply-To: <20200725081633.7432-1-hdanton@sina.com>

On 2020-07-25 10:16, Hillf Danton wrote:
> Hi folks
> 
> Below is a minimunm poc implementation I can imagine on top of workqueue
> to make napi threaded. Thoughts are appreciated.
Hi Hillf,

For some reason I don't see your mails on linux-wireless/netdev.
I've cleaned up your implementation a bit and I ran some tests with mt76
on an mt7621 embedded board. The results look pretty nice, performance
is a lot more consistent in my tests now.

Here are the changes that I've made compared to your version:

- remove the #ifdef, I think it's unnecessary
- add a state bit for threaded NAPI
- make netif_threaded_napi_add inline
- run queue_work outside of local_irq_save/restore (it does that
internally already)

If you don't mind, I'd like to propose this to netdev soon. Can I have
your Signed-off-by for that?

Thanks,

- Felix

---
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -347,6 +347,7 @@ struct napi_struct {
 	struct list_head	dev_list;
 	struct hlist_node	napi_hash_node;
 	unsigned int		napi_id;
+	struct work_struct	work;
 };
 
 enum {
@@ -357,6 +358,7 @@ enum {
 	NAPI_STATE_HASHED,	/* In NAPI hash (busy polling possible) */
 	NAPI_STATE_NO_BUSY_POLL,/* Do not add in napi_hash, no busy polling */
 	NAPI_STATE_IN_BUSY_POLL,/* sk_busy_loop() owns this NAPI */
+	NAPI_STATE_THREADED,	/* Use threaded NAPI */
 };
 
 enum {
@@ -367,6 +369,7 @@ enum {
 	NAPIF_STATE_HASHED	 = BIT(NAPI_STATE_HASHED),
 	NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL),
 	NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL),
+	NAPIF_STATE_THREADED	 = BIT(NAPI_STATE_THREADED),
 };
 
 enum gro_result {
@@ -2315,6 +2318,26 @@ static inline void *netdev_priv(const struct net_device *dev)
 void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 		    int (*poll)(struct napi_struct *, int), int weight);
 
+/**
+ *	netif_threaded_napi_add - initialize a NAPI context
+ *	@dev:  network device
+ *	@napi: NAPI context
+ *	@poll: polling function
+ *	@weight: default weight
+ *
+ * This variant of netif_napi_add() should be used from drivers using NAPI
+ * with CPU intensive poll functions.
+ * This will schedule polling from a high priority workqueue that
+ */
+static inline void netif_threaded_napi_add(struct net_device *dev,
+					   struct napi_struct *napi,
+					   int (*poll)(struct napi_struct *, int),
+					   int weight)
+{
+	set_bit(NAPI_STATE_THREADED, &napi->state);
+	netif_napi_add(dev, napi, poll, weight);
+}
+
 /**
  *	netif_tx_napi_add - initialize a NAPI context
  *	@dev:  network device
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -158,6 +158,7 @@ static DEFINE_SPINLOCK(offload_lock);
 struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
 struct list_head ptype_all __read_mostly;	/* Taps */
 static struct list_head offload_base __read_mostly;
+static struct workqueue_struct *napi_workq;
 
 static int netif_rx_internal(struct sk_buff *skb);
 static int call_netdevice_notifiers_info(unsigned long val,
@@ -6286,6 +6287,11 @@ void __napi_schedule(struct napi_struct *n)
 {
 	unsigned long flags;
 
+	if (test_bit(NAPI_STATE_THREADED, &n->state)) {
+		queue_work(napi_workq, &n->work);
+		return;
+	}
+
 	local_irq_save(flags);
 	____napi_schedule(this_cpu_ptr(&softnet_data), n);
 	local_irq_restore(flags);
@@ -6333,6 +6339,11 @@ EXPORT_SYMBOL(napi_schedule_prep);
  */
 void __napi_schedule_irqoff(struct napi_struct *n)
 {
+	if (test_bit(NAPI_STATE_THREADED, &n->state)) {
+		queue_work(napi_workq, &n->work);
+		return;
+	}
+
 	____napi_schedule(this_cpu_ptr(&softnet_data), n);
 }
 EXPORT_SYMBOL(__napi_schedule_irqoff);
@@ -6601,6 +6612,29 @@ static void init_gro_hash(struct napi_struct *napi)
 	napi->gro_bitmask = 0;
 }
 
+static void napi_workfn(struct work_struct *work)
+{
+	struct napi_struct *n = container_of(work, struct napi_struct, work);
+
+	for (;;) {
+		if (!test_bit(NAPI_STATE_SCHED, &n->state))
+			return;
+
+		if (n->poll(n, n->weight) < n->weight)
+			return;
+
+		if (need_resched()) {
+			/*
+			 * have to pay for the latency of task switch even if
+			 * napi is scheduled
+			 */
+			if (test_bit(NAPI_STATE_SCHED, &n->state))
+				queue_work(napi_workq, work);
+			return;
+		}
+	}
+}
+
 void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 		    int (*poll)(struct napi_struct *, int), int weight)
 {
@@ -6621,6 +6655,7 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 #ifdef CONFIG_NETPOLL
 	napi->poll_owner = -1;
 #endif
+	INIT_WORK(&napi->work, napi_workfn);
 	set_bit(NAPI_STATE_SCHED, &napi->state);
 	napi_hash_add(napi);
 }
@@ -10676,6 +10711,10 @@ static int __init net_dev_init(void)
 		sd->backlog.weight = weight_p;
 	}
 
+	napi_workq = alloc_workqueue("napi_workq", WQ_UNBOUND | WQ_HIGHPRI,
+				     WQ_UNBOUND_MAX_ACTIVE);
+	BUG_ON(!napi_workq);
+
 	dev_boot_phase = 0;
 
 	/* The loopback device is special if any other network devices

WARNING: multiple messages have this Message-ID
From: Felix Fietkau <nbd@nbd.name>
To: Hillf Danton <hdanton@sina.com>,
	David Laight <David.Laight@ACULAB.COM>,
	Andrew Lunn <andrew@lunn.ch>,
	Rakesh Pillai <pillair@codeaurora.org>
Cc: "netdev@vger.kernel.org" <netdev@vger.kernel.org>,
	"linux-wireless@vger.kernel.org" <linux-wireless@vger.kernel.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"ath10k@lists.infradead.org" <ath10k@lists.infradead.org>,
	"dianders@chromium.org" <dianders@chromium.org>,
	Markus Elfring <Markus.Elfring@web.de>,
	"evgreen@chromium.org" <evgreen@chromium.org>,
	"kuba@kernel.org" <kuba@kernel.org>,
	"johannes@sipsolutions.net" <johannes@sipsolutions.net>,
	"davem@davemloft.net" <davem@davemloft.net>,
	"kvalo@codeaurora.org" <kvalo@codeaurora.org>
Subject: Re: [RFC 0/7] Add support to process rx packets in thread
Date: Sat, 25 Jul 2020 19:57:23 +0200	[thread overview]
Message-ID: <a50ebfba-9733-48db-c90b-5fc106e67f29@nbd.name> (raw)
In-Reply-To: <20200725081633.7432-1-hdanton@sina.com>

On 2020-07-25 10:16, Hillf Danton wrote:
> Hi folks
> 
> Below is a minimunm poc implementation I can imagine on top of workqueue
> to make napi threaded. Thoughts are appreciated.
Hi Hillf,

For some reason I don't see your mails on linux-wireless/netdev.
I've cleaned up your implementation a bit and I ran some tests with mt76
on an mt7621 embedded board. The results look pretty nice, performance
is a lot more consistent in my tests now.

Here are the changes that I've made compared to your version:

- remove the #ifdef, I think it's unnecessary
- add a state bit for threaded NAPI
- make netif_threaded_napi_add inline
- run queue_work outside of local_irq_save/restore (it does that
internally already)

If you don't mind, I'd like to propose this to netdev soon. Can I have
your Signed-off-by for that?

Thanks,

- Felix

---
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -347,6 +347,7 @@ struct napi_struct {
 	struct list_head	dev_list;
 	struct hlist_node	napi_hash_node;
 	unsigned int		napi_id;
+	struct work_struct	work;
 };
 
 enum {
@@ -357,6 +358,7 @@ enum {
 	NAPI_STATE_HASHED,	/* In NAPI hash (busy polling possible) */
 	NAPI_STATE_NO_BUSY_POLL,/* Do not add in napi_hash, no busy polling */
 	NAPI_STATE_IN_BUSY_POLL,/* sk_busy_loop() owns this NAPI */
+	NAPI_STATE_THREADED,	/* Use threaded NAPI */
 };
 
 enum {
@@ -367,6 +369,7 @@ enum {
 	NAPIF_STATE_HASHED	 = BIT(NAPI_STATE_HASHED),
 	NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL),
 	NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL),
+	NAPIF_STATE_THREADED	 = BIT(NAPI_STATE_THREADED),
 };
 
 enum gro_result {
@@ -2315,6 +2318,26 @@ static inline void *netdev_priv(const struct net_device *dev)
 void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 		    int (*poll)(struct napi_struct *, int), int weight);
 
+/**
+ *	netif_threaded_napi_add - initialize a NAPI context
+ *	@dev:  network device
+ *	@napi: NAPI context
+ *	@poll: polling function
+ *	@weight: default weight
+ *
+ * This variant of netif_napi_add() should be used from drivers using NAPI
+ * with CPU intensive poll functions.
+ * This will schedule polling from a high priority workqueue that
+ */
+static inline void netif_threaded_napi_add(struct net_device *dev,
+					   struct napi_struct *napi,
+					   int (*poll)(struct napi_struct *, int),
+					   int weight)
+{
+	set_bit(NAPI_STATE_THREADED, &napi->state);
+	netif_napi_add(dev, napi, poll, weight);
+}
+
 /**
  *	netif_tx_napi_add - initialize a NAPI context
  *	@dev:  network device
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -158,6 +158,7 @@ static DEFINE_SPINLOCK(offload_lock);
 struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
 struct list_head ptype_all __read_mostly;	/* Taps */
 static struct list_head offload_base __read_mostly;
+static struct workqueue_struct *napi_workq;
 
 static int netif_rx_internal(struct sk_buff *skb);
 static int call_netdevice_notifiers_info(unsigned long val,
@@ -6286,6 +6287,11 @@ void __napi_schedule(struct napi_struct *n)
 {
 	unsigned long flags;
 
+	if (test_bit(NAPI_STATE_THREADED, &n->state)) {
+		queue_work(napi_workq, &n->work);
+		return;
+	}
+
 	local_irq_save(flags);
 	____napi_schedule(this_cpu_ptr(&softnet_data), n);
 	local_irq_restore(flags);
@@ -6333,6 +6339,11 @@ EXPORT_SYMBOL(napi_schedule_prep);
  */
 void __napi_schedule_irqoff(struct napi_struct *n)
 {
+	if (test_bit(NAPI_STATE_THREADED, &n->state)) {
+		queue_work(napi_workq, &n->work);
+		return;
+	}
+
 	____napi_schedule(this_cpu_ptr(&softnet_data), n);
 }
 EXPORT_SYMBOL(__napi_schedule_irqoff);
@@ -6601,6 +6612,29 @@ static void init_gro_hash(struct napi_struct *napi)
 	napi->gro_bitmask = 0;
 }
 
+static void napi_workfn(struct work_struct *work)
+{
+	struct napi_struct *n = container_of(work, struct napi_struct, work);
+
+	for (;;) {
+		if (!test_bit(NAPI_STATE_SCHED, &n->state))
+			return;
+
+		if (n->poll(n, n->weight) < n->weight)
+			return;
+
+		if (need_resched()) {
+			/*
+			 * have to pay for the latency of task switch even if
+			 * napi is scheduled
+			 */
+			if (test_bit(NAPI_STATE_SCHED, &n->state))
+				queue_work(napi_workq, work);
+			return;
+		}
+	}
+}
+
 void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 		    int (*poll)(struct napi_struct *, int), int weight)
 {
@@ -6621,6 +6655,7 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 #ifdef CONFIG_NETPOLL
 	napi->poll_owner = -1;
 #endif
+	INIT_WORK(&napi->work, napi_workfn);
 	set_bit(NAPI_STATE_SCHED, &napi->state);
 	napi_hash_add(napi);
 }
@@ -10676,6 +10711,10 @@ static int __init net_dev_init(void)
 		sd->backlog.weight = weight_p;
 	}
 
+	napi_workq = alloc_workqueue("napi_workq", WQ_UNBOUND | WQ_HIGHPRI,
+				     WQ_UNBOUND_MAX_ACTIVE);
+	BUG_ON(!napi_workq);
+
 	dev_boot_phase = 0;
 
 	/* The loopback device is special if any other network devices

_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k

  parent reply	other threads:[~2020-07-25 17:57 UTC|newest]

Thread overview: 96+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-21 17:14 Rakesh Pillai
2020-07-21 17:14 ` Rakesh Pillai
2020-07-21 17:14 ` [RFC 1/7] mac80211: Add check for napi handle before WARN_ON Rakesh Pillai
2020-07-21 17:14   ` Rakesh Pillai
2020-07-22 12:56   ` Johannes Berg
2020-07-22 12:56     ` Johannes Berg
2020-07-23 18:26     ` Rakesh Pillai
2020-07-23 18:26       ` Rakesh Pillai
2020-07-23 20:06       ` Johannes Berg
2020-07-23 20:06         ` Johannes Berg
2020-07-24  6:21         ` Rakesh Pillai
2020-07-24  6:21           ` Rakesh Pillai
2020-07-26 16:19         ` Rakesh Pillai
2020-07-26 16:19           ` Rakesh Pillai
2020-07-30 12:40           ` Johannes Berg
2020-07-30 12:40             ` Johannes Berg
2020-07-21 17:14 ` [RFC 2/7] ath10k: Add support to process rx packet in thread Rakesh Pillai
2020-07-21 17:14   ` Rakesh Pillai
2020-07-21 21:53   ` Rajkumar Manoharan
2020-07-21 21:53     ` Rajkumar Manoharan
2020-07-22 12:27     ` Felix Fietkau
2020-07-22 12:27       ` Felix Fietkau
2020-07-22 12:55       ` Johannes Berg
2020-07-22 12:55         ` Johannes Berg
2020-07-22 13:00         ` Felix Fietkau
2020-07-22 13:00           ` Felix Fietkau
2020-07-23  6:09           ` Rajkumar Manoharan
2020-07-23  6:09             ` Rajkumar Manoharan
2021-03-22 23:57           ` Ben Greear
2021-03-22 23:57             ` Ben Greear
2021-03-23  1:20             ` Brian Norris
2021-03-23  1:20               ` Brian Norris
2021-03-23  3:01               ` Ben Greear
2021-03-23  3:01                 ` Ben Greear
2021-03-23  7:45                 ` Felix Fietkau
2021-03-23  7:45                   ` Felix Fietkau
2021-03-25  9:45                   ` Rakesh Pillai
2021-03-25  9:45                     ` Rakesh Pillai
2021-03-25 10:33                     ` Felix Fietkau
2021-03-25 10:33                       ` Felix Fietkau
2020-07-23 18:25     ` Rakesh Pillai
2020-07-23 18:25       ` Rakesh Pillai
2020-07-24 23:11       ` Jacob Keller
2020-07-24 23:11         ` Jacob Keller
2020-07-21 17:14 ` [RFC 3/7] ath10k: Add module param to enable rx thread Rakesh Pillai
2020-07-21 17:14   ` Rakesh Pillai
2020-07-21 17:14 ` [RFC 4/7] ath10k: Do not exhaust budget on process tx completion Rakesh Pillai
2020-07-21 17:14   ` Rakesh Pillai
2020-07-21 17:14 ` [RFC 5/7] ath10k: Handle the rx packet processing in thread Rakesh Pillai
2020-07-21 17:14   ` Rakesh Pillai
2020-07-21 17:14 ` [RFC 6/7] ath10k: Add deliver to stack from thread context Rakesh Pillai
2020-07-21 17:14   ` Rakesh Pillai
2020-07-21 17:14 ` [RFC 7/7] ath10k: Handle rx thread suspend and resume Rakesh Pillai
2020-07-21 17:14   ` Rakesh Pillai
2020-07-23 23:06   ` Sebastian Gottschall
2020-07-23 23:06     ` Sebastian Gottschall
2020-07-24  6:19     ` Rakesh Pillai
2020-07-24  6:19       ` Rakesh Pillai
2020-07-21 17:25 ` [RFC 0/7] Add support to process rx packets in thread Andrew Lunn
2020-07-21 17:25   ` Andrew Lunn
2020-07-21 18:05   ` Florian Fainelli
2020-07-21 18:05     ` Florian Fainelli
2020-07-23 18:21     ` Rakesh Pillai
2020-07-23 18:21       ` Rakesh Pillai
2020-07-23 19:02       ` Florian Fainelli
2020-07-23 19:02         ` Florian Fainelli
2020-07-24  6:20         ` Rakesh Pillai
2020-07-24  6:20           ` Rakesh Pillai
2020-07-24 22:28           ` Florian Fainelli
2020-07-24 22:28             ` Florian Fainelli
2020-07-22  9:12   ` David Laight
2020-07-22  9:12     ` David Laight
2020-07-25  8:16     ` Hillf Danton
2020-07-25 10:38       ` Sebastian Gottschall
2020-07-25 10:38         ` Sebastian Gottschall
2020-07-25 12:25         ` Hillf Danton
2020-07-25 14:08         ` Sebastian Gottschall
2020-07-25 14:08           ` Sebastian Gottschall
2020-07-25 14:57           ` Hillf Danton
2020-07-25 15:41             ` Sebastian Gottschall
2020-07-25 15:41               ` Sebastian Gottschall
2020-07-26 11:16               ` David Laight
2020-07-26 11:16                 ` David Laight
2020-07-28 16:59                 ` Rakesh Pillai
2020-07-28 16:59                   ` Rakesh Pillai
2020-07-29  1:34                   ` Hillf Danton
2020-07-25 17:57       ` Felix Fietkau [this message]
2020-07-25 17:57         ` Felix Fietkau
2020-07-26  1:22         ` Hillf Danton
2020-07-26  8:10           ` Felix Fietkau
2020-07-26  8:10             ` Felix Fietkau
2020-07-26  8:32             ` Hillf Danton
2020-07-26  8:59               ` Felix Fietkau
2020-07-26  8:59                 ` Felix Fietkau
2020-07-22 16:20   ` Jakub Kicinski
2020-07-22 16:20     ` Jakub Kicinski

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=a50ebfba-9733-48db-c90b-5fc106e67f29@nbd.name \
    --to=nbd@nbd.name \
    --cc=David.Laight@ACULAB.COM \
    --cc=Markus.Elfring@web.de \
    --cc=andrew@lunn.ch \
    --cc=ath10k@lists.infradead.org \
    --cc=davem@davemloft.net \
    --cc=dianders@chromium.org \
    --cc=evgreen@chromium.org \
    --cc=hdanton@sina.com \
    --cc=johannes@sipsolutions.net \
    --cc=kuba@kernel.org \
    --cc=kvalo@codeaurora.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-wireless@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=pillair@codeaurora.org \
    --subject='Re: [RFC 0/7] Add support to process rx packets in thread' \
    /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

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.