From: Wei Wang Date: Mon, 8 Feb 2021 11:34:10 -0800 Subject: [PATCH] net: add sysfs attribute to control napi threaded mode This patch adds a new sysfs attribute to the network device class. Said attribute provides a per-device control to enable/disable the threaded mode for all the napi instances of the given network device, without the need for a device up/down. User sets it to 1 or 0 to enable or disable threaded mode. Note: when switching between threaded and the current softirq based mode for a napi instance, it will not immediately take effect if the napi is currently being polled. The mode switch will happen for the next time napi_schedule() is called. Co-developed-by: Paolo Abeni Signed-off-by: Paolo Abeni Co-developed-by: Hannes Frederic Sowa Signed-off-by: Hannes Frederic Sowa Co-developed-by: Felix Fietkau Signed-off-by: Felix Fietkau Signed-off-by: Wei Wang Reviewed-by: Alexander Duyck Signed-off-by: David S. Miller --- --- a/Documentation/ABI/testing/sysfs-class-net +++ b/Documentation/ABI/testing/sysfs-class-net @@ -301,3 +301,18 @@ Contact: netdev@vger.kernel.org Description: 32-bit unsigned integer counting the number of times the link has been down + +What: /sys/class/net//threaded +Date: Jan 2021 +KernelVersion: 5.12 +Contact: netdev@vger.kernel.org +Description: + Boolean value to control the threaded mode per device. User could + set this value to enable/disable threaded mode for all napi + belonging to this device, without the need to do device up/down. + + Possible values: + == ================================== + 0 threaded mode disabled for this dev + 1 threaded mode enabled for this dev + == ================================== --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -498,6 +498,8 @@ static inline bool napi_complete(struct */ bool napi_hash_del(struct napi_struct *napi); +int dev_set_threaded(struct net_device *dev, bool threaded); + /** * napi_disable - prevent NAPI from scheduling * @n: NAPI context --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3914,8 +3914,9 @@ static inline void ____napi_schedule(str if (test_bit(NAPI_STATE_THREADED, &napi->state)) { /* Paired with smp_mb__before_atomic() in - * napi_enable(). Use READ_ONCE() to guarantee - * a complete read on napi->thread. Only call + * napi_enable()/dev_set_threaded(). + * Use READ_ONCE() to guarantee a complete + * read on napi->thread. Only call * wake_up_process() when it's not NULL. */ thread = READ_ONCE(napi->thread); @@ -6293,6 +6294,49 @@ static void init_gro_hash(struct napi_st napi->gro_bitmask = 0; } +int dev_set_threaded(struct net_device *dev, bool threaded) +{ + struct napi_struct *napi; + int err = 0; + + if (dev->threaded == threaded) + return 0; + + if (threaded) { + list_for_each_entry(napi, &dev->napi_list, dev_list) { + if (!napi->thread) { + err = napi_kthread_create(napi); + if (err) { + threaded = false; + break; + } + } + } + } + + dev->threaded = threaded; + + /* Make sure kthread is created before THREADED bit + * is set. + */ + smp_mb__before_atomic(); + + /* Setting/unsetting threaded mode on a napi might not immediately + * take effect, if the current napi instance is actively being + * polled. In this case, the switch between threaded mode and + * softirq mode will happen in the next round of napi_schedule(). + * This should not cause hiccups/stalls to the live traffic. + */ + list_for_each_entry(napi, &dev->napi_list, dev_list) { + if (threaded) + set_bit(NAPI_STATE_THREADED, &napi->state); + else + clear_bit(NAPI_STATE_THREADED, &napi->state); + } + + return err; +} + void netif_napi_add(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight) { --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -557,6 +557,45 @@ static ssize_t phys_switch_id_show(struc } static DEVICE_ATTR_RO(phys_switch_id); +static ssize_t threaded_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct net_device *netdev = to_net_dev(dev); + ssize_t ret = -EINVAL; + + if (!rtnl_trylock()) + return restart_syscall(); + + if (dev_isalive(netdev)) + ret = sprintf(buf, fmt_dec, netdev->threaded); + + rtnl_unlock(); + return ret; +} + +static int modify_napi_threaded(struct net_device *dev, unsigned long val) +{ + int ret; + + if (list_empty(&dev->napi_list)) + return -EOPNOTSUPP; + + if (val != 0 && val != 1) + return -EOPNOTSUPP; + + ret = dev_set_threaded(dev, val); + + return ret; +} + +static ssize_t threaded_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return netdev_store(dev, attr, buf, len, modify_napi_threaded); +} +static DEVICE_ATTR_RW(threaded); + static struct attribute *net_class_attrs[] __ro_after_init = { &dev_attr_netdev_group.attr, &dev_attr_type.attr, @@ -587,6 +626,7 @@ static struct attribute *net_class_attrs &dev_attr_proto_down.attr, &dev_attr_carrier_up_count.attr, &dev_attr_carrier_down_count.attr, + &dev_attr_threaded.attr, NULL, }; ATTRIBUTE_GROUPS(net_class);