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: <20240812125717.413108-2-jdamato@fastly.com>
Date: Mon, 12 Aug 2024 12:57:04 +0000
From: Joe Damato <jdamato@...tly.com>
To: netdev@...r.kernel.org
Cc: mkarsten@...terloo.ca,
	amritha.nambiar@...el.com,
	sridhar.samudrala@...el.com,
	sdf@...ichev.me,
	Joe Damato <jdamato@...tly.com>,
	"David S. Miller" <davem@...emloft.net>,
	Eric Dumazet <edumazet@...gle.com>,
	Jakub Kicinski <kuba@...nel.org>,
	Paolo Abeni <pabeni@...hat.com>,
	Jonathan Corbet <corbet@....net>,
	Jiri Pirko <jiri@...nulli.us>,
	Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
	Lorenzo Bianconi <lorenzo@...nel.org>,
	Daniel Borkmann <daniel@...earbox.net>,
	Breno Leitao <leitao@...ian.org>,
	Johannes Berg <johannes.berg@...el.com>,
	Alexander Lobakin <aleksander.lobakin@...el.com>,
	Heiner Kallweit <hkallweit1@...il.com>,
	linux-doc@...r.kernel.org (open list:DOCUMENTATION),
	linux-kernel@...r.kernel.org (open list)
Subject: [RFC net-next 1/5] net: Add sysfs parameter irq_suspend_timeout

From: Martin Karsten <mkarsten@...terloo.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@...terloo.ca>
Co-developed-by: Joe Damato <jdamato@...tly.com>
Signed-off-by: Joe Damato <jdamato@...tly.com>
Tested-by: Joe Damato <jdamato@...tly.com>
Tested-by: Martin Karsten <mkarsten@...terloo.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


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ