From: Joe Damato <jdamato@fastly.com>
To: netdev@vger.kernel.org
Cc: mkarsten@uwaterloo.ca, kuba@kernel.org, skhawaja@google.com,
sdf@fomichev.me, bjorn@rivosinc.com, amritha.nambiar@intel.com,
sridhar.samudrala@intel.com, Joe Damato <jdamato@fastly.com>,
"David S. Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@google.com>,
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>,
Johannes Berg <johannes.berg@intel.com>,
Breno Leitao <leitao@debian.org>,
Alexander Lobakin <aleksander.lobakin@intel.com>,
linux-doc@vger.kernel.org (open list:DOCUMENTATION),
linux-kernel@vger.kernel.org (open list)
Subject: [RFC net-next v3 3/9] net: napi: Make gro_flush_timeout per-NAPI
Date: Thu, 12 Sep 2024 10:07:11 +0000 [thread overview]
Message-ID: <20240912100738.16567-4-jdamato@fastly.com> (raw)
In-Reply-To: <20240912100738.16567-1-jdamato@fastly.com>
Allow per-NAPI gro_flush_timeout setting.
The existing sysfs parameter is respected; writes to sysfs will write to
all NAPI structs for the device and the net_device gro_flush_timeout
field. Reads from sysfs will read from the net_device field.
The ability to set gro_flush_timeout on specific NAPI instances will be
added in a later commit, via netdev-genl.
Signed-off-by: Joe Damato <jdamato@fastly.com>
---
.../networking/net_cachelines/net_device.rst | 2 +-
include/linux/netdevice.h | 3 +-
net/core/dev.c | 12 +++---
net/core/dev.h | 39 +++++++++++++++++++
net/core/net-sysfs.c | 2 +-
5 files changed, 49 insertions(+), 9 deletions(-)
diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst
index eeeb7c925ec5..3d02ae79c850 100644
--- a/Documentation/networking/net_cachelines/net_device.rst
+++ b/Documentation/networking/net_cachelines/net_device.rst
@@ -98,7 +98,6 @@ struct_netdev_queue* _rx read_mostly
unsigned_int num_rx_queues
unsigned_int real_num_rx_queues - read_mostly get_rps_cpu
struct_bpf_prog* xdp_prog - read_mostly netif_elide_gro()
-unsigned_long gro_flush_timeout - read_mostly napi_complete_done
unsigned_int gro_max_size - read_mostly skb_gro_receive
unsigned_int gro_ipv4_max_size - read_mostly skb_gro_receive
rx_handler_func_t* rx_handler read_mostly - __netif_receive_skb_core
@@ -182,4 +181,5 @@ struct_devlink_port* devlink_port
struct_dpll_pin* dpll_pin
struct hlist_head page_pools
struct dim_irq_moder* irq_moder
+unsigned_long gro_flush_timeout
u32 napi_defer_hard_irqs
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index f28b96c95259..3e07ab8e0295 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -377,6 +377,7 @@ struct napi_struct {
struct list_head dev_list;
struct hlist_node napi_hash_node;
int irq;
+ unsigned long gro_flush_timeout;
u32 defer_hard_irqs;
};
@@ -2075,7 +2076,6 @@ struct net_device {
int ifindex;
unsigned int real_num_rx_queues;
struct netdev_rx_queue *_rx;
- unsigned long gro_flush_timeout;
unsigned int gro_max_size;
unsigned int gro_ipv4_max_size;
rx_handler_func_t __rcu *rx_handler;
@@ -2398,6 +2398,7 @@ struct net_device {
/** @irq_moder: dim parameters used if IS_ENABLED(CONFIG_DIMLIB). */
struct dim_irq_moder *irq_moder;
+ unsigned long gro_flush_timeout;
u32 napi_defer_hard_irqs;
u8 priv[] ____cacheline_aligned
diff --git a/net/core/dev.c b/net/core/dev.c
index d3d0680664b3..f2fd503516de 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6220,12 +6220,12 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
if (work_done) {
if (n->gro_bitmask)
- timeout = READ_ONCE(n->dev->gro_flush_timeout);
+ timeout = napi_get_gro_flush_timeout(n);
n->defer_hard_irqs_count = napi_get_defer_hard_irqs(n);
}
if (n->defer_hard_irqs_count > 0) {
n->defer_hard_irqs_count--;
- timeout = READ_ONCE(n->dev->gro_flush_timeout);
+ timeout = napi_get_gro_flush_timeout(n);
if (timeout)
ret = false;
}
@@ -6360,7 +6360,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock,
if (flags & NAPI_F_PREFER_BUSY_POLL) {
napi->defer_hard_irqs_count = napi_get_defer_hard_irqs(napi);
- timeout = READ_ONCE(napi->dev->gro_flush_timeout);
+ timeout = napi_get_gro_flush_timeout(napi);
if (napi->defer_hard_irqs_count && timeout) {
hrtimer_start(&napi->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED);
skip_schedule = true;
@@ -6642,6 +6642,7 @@ void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi,
hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
napi->timer.function = napi_watchdog;
napi_set_defer_hard_irqs(napi, READ_ONCE(dev->napi_defer_hard_irqs));
+ napi_set_gro_flush_timeout(napi, READ_ONCE(dev->gro_flush_timeout));
init_gro_hash(napi);
napi->skb = NULL;
INIT_LIST_HEAD(&napi->rx_list);
@@ -11023,7 +11024,7 @@ void netdev_sw_irq_coalesce_default_on(struct net_device *dev)
WARN_ON(dev->reg_state == NETREG_REGISTERED);
if (!IS_ENABLED(CONFIG_PREEMPT_RT)) {
- dev->gro_flush_timeout = 20000;
+ netdev_set_gro_flush_timeout(dev, 20000);
netdev_set_defer_hard_irqs(dev, 1);
}
}
@@ -11960,7 +11961,6 @@ static void __init net_dev_struct_check(void)
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ifindex);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, real_num_rx_queues);
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, 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);
@@ -11972,7 +11972,7 @@ 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, 100);
+ CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_rx, 92);
}
/*
diff --git a/net/core/dev.h b/net/core/dev.h
index f24fa38a2cac..a9d5f678564a 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -174,6 +174,45 @@ static inline void netdev_set_defer_hard_irqs(struct net_device *netdev,
napi_set_defer_hard_irqs(napi, defer);
}
+/**
+ * napi_get_gro_flush_timeout - get the gro_flush_timeout
+ * @n: napi struct to get the gro_flush_timeout from
+ *
+ * Return: the per-NAPI value of the gro_flush_timeout field.
+ */
+static inline unsigned long napi_get_gro_flush_timeout(const struct napi_struct *n)
+{
+ return READ_ONCE(n->gro_flush_timeout);
+}
+
+/**
+ * napi_set_gro_flush_timeout - set the gro_flush_timeout for a napi
+ * @n: napi struct to set the gro_flush_timeout
+ * @timeout: timeout value to set
+ *
+ * napi_set_gro_flush_timeout sets the per-NAPI gro_flush_timeout
+ */
+static inline void napi_set_gro_flush_timeout(struct napi_struct *n,
+ unsigned long timeout)
+{
+ WRITE_ONCE(n->gro_flush_timeout, timeout);
+}
+
+/**
+ * netdev_set_gro_flush_timeout - set gro_flush_timeout for all NAPIs of a netdev
+ * @netdev: the net_device for which all NAPIs will have their gro_flush_timeout set
+ * @timeout: the timeout value to set
+ */
+static inline void netdev_set_gro_flush_timeout(struct net_device *netdev,
+ unsigned long timeout)
+{
+ struct napi_struct *napi;
+
+ WRITE_ONCE(netdev->gro_flush_timeout, timeout);
+ list_for_each_entry(napi, &netdev->napi_list, dev_list)
+ napi_set_gro_flush_timeout(napi, timeout);
+}
+
int rps_cpumask_housekeeping(struct cpumask *mask);
#if defined(CONFIG_DEBUG_NET) && defined(CONFIG_BPF_SYSCALL)
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 25125f356a15..2d9afc6e2161 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -409,7 +409,7 @@ NETDEVICE_SHOW_RW(tx_queue_len, fmt_dec);
static int change_gro_flush_timeout(struct net_device *dev, unsigned long val)
{
- WRITE_ONCE(dev->gro_flush_timeout, val);
+ netdev_set_gro_flush_timeout(dev, val);
return 0;
}
--
2.25.1
next prev parent reply other threads:[~2024-09-12 10:08 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-09-12 10:07 [RFC net-next v3 0/9] Add support for per-NAPI config via netlink Joe Damato
2024-09-12 10:07 ` [RFC net-next v3 1/9] net: napi: Make napi_defer_hard_irqs per-NAPI Joe Damato
2024-09-12 10:07 ` [RFC net-next v3 2/9] netdev-genl: Dump napi_defer_hard_irqs Joe Damato
2024-09-12 10:07 ` Joe Damato [this message]
2024-09-15 5:30 ` [RFC net-next v3 3/9] net: napi: Make gro_flush_timeout per-NAPI kernel test robot
2024-09-12 10:07 ` [RFC net-next v3 4/9] netdev-genl: Dump gro_flush_timeout Joe Damato
2024-09-12 10:07 ` [RFC net-next v3 5/9] net: napi: Add napi_config Joe Damato
2024-09-12 15:03 ` Joe Damato
2024-09-13 21:44 ` Willem de Bruijn
2024-09-13 22:10 ` Joe Damato
2024-09-13 17:42 ` Stanislav Fomichev
2024-09-13 18:55 ` Joe Damato
2024-09-13 19:39 ` Joe Damato
2024-09-14 13:00 ` Joe Damato
2024-09-12 10:07 ` [RFC net-next v3 6/9] netdev-genl: Support setting per-NAPI config values Joe Damato
2024-09-12 10:38 ` Joe Damato
2024-09-12 10:07 ` [RFC net-next v3 7/9] bnxt: Add support for napi storage Joe Damato
2024-09-12 10:07 ` [RFC net-next v3 8/9] mlx5: " Joe Damato
2024-09-12 10:07 ` [RFC net-next v3 9/9] mlx4: Add support for napi storage to RX CQs Joe Damato
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=20240912100738.16567-4-jdamato@fastly.com \
--to=jdamato@fastly.com \
--cc=aleksander.lobakin@intel.com \
--cc=amritha.nambiar@intel.com \
--cc=bigeasy@linutronix.de \
--cc=bjorn@rivosinc.com \
--cc=corbet@lwn.net \
--cc=davem@davemloft.net \
--cc=edumazet@google.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=skhawaja@google.com \
--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 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.