diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0750b54b3765..5a8d40f1ffe2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -329,6 +329,7 @@ struct napi_struct { unsigned long state; int weight; + int defer_hard_irqs_count; unsigned long gro_bitmask; int (*poll)(struct napi_struct *, int); #ifdef CONFIG_NETPOLL @@ -1995,6 +1996,7 @@ struct net_device { struct bpf_prog __rcu *xdp_prog; unsigned long gro_flush_timeout; + int napi_defer_hard_irqs; rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; diff --git a/net/core/dev.c b/net/core/dev.c index fb61522b1ce1..67585484ad32 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6227,7 +6227,8 @@ EXPORT_SYMBOL(__napi_schedule_irqoff); bool napi_complete_done(struct napi_struct *n, int work_done) { - unsigned long flags, val, new; + unsigned long flags, val, new, timeout = 0; + bool ret = true; /* * 1) Don't let napi dequeue from the cpu poll list @@ -6239,20 +6240,23 @@ bool napi_complete_done(struct napi_struct *n, int work_done) NAPIF_STATE_IN_BUSY_POLL))) return false; - if (n->gro_bitmask) { - unsigned long timeout = 0; - - if (work_done) + if (work_done) { + if (n->gro_bitmask) timeout = n->dev->gro_flush_timeout; - + n->defer_hard_irqs_count = n->dev->napi_defer_hard_irqs; + } + if (n->defer_hard_irqs_count > 0) { + n->defer_hard_irqs_count--; + timeout = n->dev->gro_flush_timeout; + if (timeout) + ret = false; + } + if (n->gro_bitmask) { /* When the NAPI instance uses a timeout and keeps postponing * it, we need to bound somehow the time packets are kept in * the GRO layer */ napi_gro_flush(n, !!timeout); - if (timeout) - hrtimer_start(&n->timer, ns_to_ktime(timeout), - HRTIMER_MODE_REL_PINNED); } gro_normal_list(n); @@ -6284,7 +6288,10 @@ bool napi_complete_done(struct napi_struct *n, int work_done) return false; } - return true; + if (timeout) + hrtimer_start(&n->timer, ns_to_ktime(timeout), + HRTIMER_MODE_REL_PINNED); + return ret; } EXPORT_SYMBOL(napi_complete_done); @@ -6464,7 +6471,7 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) /* Note : we use a relaxed variant of napi_schedule_prep() not setting * NAPI_STATE_MISSED, since we do not react to a device IRQ. */ - if (napi->gro_bitmask && !napi_disable_pending(napi) && + if (!napi_disable_pending(napi) && !test_and_set_bit(NAPI_STATE_SCHED, &napi->state)) __napi_schedule_irqoff(napi); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 0d9e46de205e..f3b650cd0923 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -382,6 +382,23 @@ static ssize_t gro_flush_timeout_store(struct device *dev, } NETDEVICE_SHOW_RW(gro_flush_timeout, fmt_ulong); +static int change_napi_defer_hard_irqs(struct net_device *dev, unsigned long val) +{ + dev->napi_defer_hard_irqs = val; + return 0; +} + +static ssize_t napi_defer_hard_irqs_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_napi_defer_hard_irqs); +} +NETDEVICE_SHOW_RW(napi_defer_hard_irqs, fmt_dec); + static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { @@ -545,6 +562,7 @@ static struct attribute *net_class_attrs[] __ro_after_init = { &dev_attr_flags.attr, &dev_attr_tx_queue_len.attr, &dev_attr_gro_flush_timeout.attr, + &dev_attr_napi_defer_hard_irqs.attr, &dev_attr_phys_port_id.attr, &dev_attr_phys_port_name.attr, &dev_attr_phys_switch_id.attr,