mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Joe Damato <jdamato@fastly.com>
To: netdev@vger.kernel.org
Cc: mkarsten@uwaterloo.ca, amritha.nambiar@intel.com,
	sridhar.samudrala@intel.com, sdf@fomichev.me,
	Joe Damato <jdamato@fastly.com>,
	"David S. Miller" <davem@davemloft.net>,
	Eric Dumazet <edumazet@google.com>,
	Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
	Jonathan Corbet <corbet@lwn.net>, Jiri Pirko <jiri@resnulli.us>,
	Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
	Lorenzo Bianconi <lorenzo@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Breno Leitao <leitao@debian.org>,
	Johannes Berg <johannes.berg@intel.com>,
	Alexander Lobakin <aleksander.lobakin@intel.com>,
	Heiner Kallweit <hkallweit1@gmail.com>,
	linux-doc@vger.kernel.org (open list:DOCUMENTATION),
	linux-kernel@vger.kernel.org (open list)
Subject: [RFC net-next 1/5] net: Add sysfs parameter irq_suspend_timeout
Date: Mon, 12 Aug 2024 12:57:04 +0000	[thread overview]
Message-ID: <20240812125717.413108-2-jdamato@fastly.com> (raw)
In-Reply-To: <20240812125717.413108-1-jdamato@fastly.com>

From: Martin Karsten <mkarsten@uwaterloo.ca>

This patch doesn't change any behavior but prepares the code for other
changes in the following commits which use irq_suspend_timeout as a
timeout for IRQ suspension.

Signed-off-by: Martin Karsten <mkarsten@uwaterloo.ca>
Co-developed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: Joe Damato <jdamato@fastly.com>
Tested-by: Joe Damato <jdamato@fastly.com>
Tested-by: Martin Karsten <mkarsten@uwaterloo.ca>
---
 Documentation/networking/napi.rst |  3 +++
 include/linux/netdevice.h         |  2 ++
 net/core/dev.c                    |  3 ++-
 net/core/net-sysfs.c              | 18 ++++++++++++++++++
 4 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/Documentation/networking/napi.rst b/Documentation/networking/napi.rst
index 7bf7b95c4f7a..0a029dd6d77e 100644
--- a/Documentation/networking/napi.rst
+++ b/Documentation/networking/napi.rst
@@ -192,6 +192,9 @@ The ``gro_flush_timeout`` sysfs configuration of the netdevice
 is reused to control the delay of the timer, while
 ``napi_defer_hard_irqs`` controls the number of consecutive empty polls
 before NAPI gives up and goes back to using hardware IRQs.
+``irq_suspend_timeout`` is used to determine how long an application can
+completely suspend IRQs. It is used in combination with SO_PREFER_BUSY_POLL,
+which can be set on a per-epoll context basis with EPIOCSPARAMS ioctl.
 
 .. _poll:
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 0ef3eaa23f4b..31867bb2ff65 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1857,6 +1857,7 @@ enum netdev_reg_state {
  *	@gro_flush_timeout:	timeout for GRO layer in NAPI
  *	@napi_defer_hard_irqs:	If not zero, provides a counter that would
  *				allow to avoid NIC hard IRQ, on busy queues.
+ *	@irq_suspend_timeout:	IRQ suspension timeout
  *
  *	@rx_handler:		handler for received packets
  *	@rx_handler_data: 	XXX: need comments on this one
@@ -2060,6 +2061,7 @@ struct net_device {
 	struct netdev_rx_queue	*_rx;
 	unsigned long		gro_flush_timeout;
 	int			napi_defer_hard_irqs;
+	unsigned long		irq_suspend_timeout;
 	unsigned int		gro_max_size;
 	unsigned int		gro_ipv4_max_size;
 	rx_handler_func_t __rcu	*rx_handler;
diff --git a/net/core/dev.c b/net/core/dev.c
index 751d9b70e6ad..bf45c90aebcd 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -11937,6 +11937,7 @@ static void __init net_dev_struct_check(void)
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, _rx);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_flush_timeout);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, napi_defer_hard_irqs);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, irq_suspend_timeout);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_max_size);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_ipv4_max_size);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, rx_handler);
@@ -11948,7 +11949,7 @@ static void __init net_dev_struct_check(void)
 #ifdef CONFIG_NET_XGRESS
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, tcx_ingress);
 #endif
-	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_rx, 104);
+	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_rx, 112);
 }
 
 /*
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 0e2084ce7b75..fb6f3327310f 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -440,6 +440,23 @@ static ssize_t napi_defer_hard_irqs_store(struct device *dev,
 }
 NETDEVICE_SHOW_RW(napi_defer_hard_irqs, fmt_dec);
 
+static int change_irq_suspend_timeout(struct net_device *dev, unsigned long val)
+{
+	WRITE_ONCE(dev->irq_suspend_timeout, val);
+	return 0;
+}
+
+static ssize_t irq_suspend_timeout_store(struct device *dev,
+					 struct device_attribute *attr,
+					 const char *buf, size_t len)
+{
+	if (!capable(CAP_NET_ADMIN))
+		return -EPERM;
+
+	return netdev_store(dev, attr, buf, len, change_irq_suspend_timeout);
+}
+NETDEVICE_SHOW_RW(irq_suspend_timeout, fmt_ulong);
+
 static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr,
 			     const char *buf, size_t len)
 {
@@ -664,6 +681,7 @@ static struct attribute *net_class_attrs[] __ro_after_init = {
 	&dev_attr_tx_queue_len.attr,
 	&dev_attr_gro_flush_timeout.attr,
 	&dev_attr_napi_defer_hard_irqs.attr,
+	&dev_attr_irq_suspend_timeout.attr,
 	&dev_attr_phys_port_id.attr,
 	&dev_attr_phys_port_name.attr,
 	&dev_attr_phys_switch_id.attr,
-- 
2.25.1


  reply	other threads:[~2024-08-12 12:57 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-08-12 12:57 [RFC net-next 0/5] Suspend IRQs during preferred busy poll Joe Damato
2024-08-12 12:57 ` Joe Damato [this message]
2024-08-12 12:57 ` [RFC net-next 2/5] net: Suspend softirq when prefer_busy_poll is set Joe Damato
2024-08-12 12:57 ` [RFC net-next 3/5] net: Add control functions for irq suspension Joe Damato
2024-08-12 12:57 ` [RFC net-next 4/5] eventpoll: Trigger napi_busy_loop, if prefer_busy_poll is set Joe Damato
2024-08-12 13:19   ` Christoph Hellwig
2024-08-12 16:17     ` Matthew Wilcox
2024-08-12 17:49       ` Joe Damato
2024-08-12 17:46     ` Joe Damato
2024-08-12 12:57 ` [RFC net-next 5/5] eventpoll: Control irq suspension for prefer_busy_poll Joe Damato
2024-08-12 20:20   ` Stanislav Fomichev
2024-08-12 21:47     ` Martin Karsten
2024-08-12 20:19 ` [RFC net-next 0/5] Suspend IRQs during preferred busy poll Stanislav Fomichev
2024-08-12 21:46   ` Martin Karsten
2024-08-12 23:03     ` Stanislav Fomichev
2024-08-13  0:04       ` Martin Karsten
2024-08-13  1:54         ` Stanislav Fomichev
2024-08-13  2:35           ` Martin Karsten
2024-08-13  4:07             ` Stanislav Fomichev
2024-08-13 13:18               ` Martin Karsten
2024-08-14  3:16                 ` Willem de Bruijn
2024-08-14 14:19                   ` Joe Damato
2024-08-14 15:08                     ` Willem de Bruijn
2024-08-14 15:46                       ` Joe Damato
2024-08-14 19:53                 ` Samiullah Khawaja
2024-08-14 20:42                   ` Martin Karsten
2024-08-16 14:27                     ` Willem de Bruijn
2024-08-16 14:59                       ` Willem de Bruijn
2024-08-16 15:25                         ` Joe Damato
2024-08-16 17:01                           ` Willem de Bruijn
2024-08-16 20:03                             ` Martin Karsten
2024-08-16 20:58                               ` Willem de Bruijn
2024-08-17 18:15                                 ` Martin Karsten
2024-08-18 12:55                                   ` Willem de Bruijn
2024-08-18 14:51                                     ` Martin Karsten
2024-08-20  2:36                                       ` Jakub Kicinski
2024-08-20 14:28                                         ` Martin Karsten
2024-08-17 10:00                             ` Joe Damato
2024-08-14  0:10     ` Jakub Kicinski
2024-08-14  1:14       ` Martin Karsten
2024-08-20  2:07         ` Jakub Kicinski
2024-08-20 14:27           ` Martin Karsten

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=20240812125717.413108-2-jdamato@fastly.com \
    --to=jdamato@fastly.com \
    --cc=aleksander.lobakin@intel.com \
    --cc=amritha.nambiar@intel.com \
    --cc=bigeasy@linutronix.de \
    --cc=corbet@lwn.net \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=hkallweit1@gmail.com \
    --cc=jiri@resnulli.us \
    --cc=johannes.berg@intel.com \
    --cc=kuba@kernel.org \
    --cc=leitao@debian.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lorenzo@kernel.org \
    --cc=mkarsten@uwaterloo.ca \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=sdf@fomichev.me \
    --cc=sridhar.samudrala@intel.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

all inboxes | Powered by JetHome®