UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge branch 'net-napi-addition-of-napi_defer_hard_irqs' 

Eric Dumazet says:

====================
net: napi: addition of napi_defer_hard_irqs

This patch series augments gro_glush_timeout feature with napi_defer_hard_irqs

As extensively described in first patch changelog, this can suppresss
the chit-chat traffic between NIC and host to signal interrupts and re-arming
them, since this can be an issue on high speed NIC with many queues.

The last patch in this series converts mlx4 TX completion to
napi_complete_done(), to enable this new mechanism.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
David S. Miller 2020-04-23 12:43:20 -07:00
parent e6acd2b6e8 cf4058dbaa
commit 4c532b144f
6 changed files with 52 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
drivers/net/ethernet/mellanox/mlx4/en_rx.c
View File

@ -946,7 +946,7 @@ int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget)
xdp_tx_cq = priv->tx_cq[TX_XDP][cq->ring];
if (xdp_tx_cq->xdp_busy) {
clean_complete = mlx4_en_process_tx_cq(dev, xdp_tx_cq,
budget);
budget) < budget;
xdp_tx_cq->xdp_busy = !clean_complete;
}
}

20
drivers/net/ethernet/mellanox/mlx4/en_tx.c
View File

@ -382,8 +382,8 @@ int mlx4_en_free_tx_buf(struct net_device *dev, struct mlx4_en_tx_ring *ring)
return cnt;
}
bool mlx4_en_process_tx_cq(struct net_device *dev,
struct mlx4_en_cq *cq, int napi_budget)
int mlx4_en_process_tx_cq(struct net_device *dev,
struct mlx4_en_cq *cq, int napi_budget)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_cq *mcq = &cq->mcq;
@ -405,7 +405,7 @@ bool mlx4_en_process_tx_cq(struct net_device *dev,
u32 ring_cons;
if (unlikely(!priv->port_up))
return true;
return 0;
netdev_txq_bql_complete_prefetchw(ring->tx_queue);
@ -480,7 +480,7 @@ bool mlx4_en_process_tx_cq(struct net_device *dev,
WRITE_ONCE(ring->cons, ring_cons + txbbs_skipped);
if (cq->type == TX_XDP)
return done < budget;
return done;
netdev_tx_completed_queue(ring->tx_queue, packets, bytes);
@ -492,7 +492,7 @@ bool mlx4_en_process_tx_cq(struct net_device *dev,
ring->wake_queue++;
}
return done < budget;
return done;
}
void mlx4_en_tx_irq(struct mlx4_cq *mcq)
@ -512,14 +512,14 @@ int mlx4_en_poll_tx_cq(struct napi_struct *napi, int budget)
struct mlx4_en_cq *cq = container_of(napi, struct mlx4_en_cq, napi);
struct net_device *dev = cq->dev;
struct mlx4_en_priv *priv = netdev_priv(dev);
bool clean_complete;
int work_done;
clean_complete = mlx4_en_process_tx_cq(dev, cq, budget);
if (!clean_complete)
work_done = mlx4_en_process_tx_cq(dev, cq, budget);
if (work_done >= budget)
return budget;
napi_complete(napi);
mlx4_en_arm_cq(priv, cq);
if (napi_complete_done(napi, work_done))
mlx4_en_arm_cq(priv, cq);
return 0;
}

4
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
View File

@ -737,8 +737,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev,
int budget);
int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget);
int mlx4_en_poll_tx_cq(struct napi_struct *napi, int budget);
bool mlx4_en_process_tx_cq(struct net_device *dev,
struct mlx4_en_cq *cq, int napi_budget);
int mlx4_en_process_tx_cq(struct net_device *dev,
struct mlx4_en_cq *cq, int napi_budget);
u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
struct mlx4_en_tx_ring *ring,
int index, u64 timestamp,

2
include/linux/netdevice.h
View File

@ -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;

29
net/core/dev.c
View File

@ -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 (work_done) {
if (n->gro_bitmask)
timeout = READ_ONCE(n->dev->gro_flush_timeout);
n->defer_hard_irqs_count = READ_ONCE(n->dev->napi_defer_hard_irqs);
}
if (n->defer_hard_irqs_count > 0) {
n->defer_hard_irqs_count--;
timeout = READ_ONCE(n->dev->gro_flush_timeout);
if (timeout)
ret = false;
}
if (n->gro_bitmask) {
unsigned long timeout = 0;
if (work_done)
timeout = n->dev->gro_flush_timeout;
/* 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);

20
net/core/net-sysfs.c
View File

@ -367,7 +367,7 @@ NETDEVICE_SHOW_RW(tx_queue_len, fmt_dec);
static int change_gro_flush_timeout(struct net_device *dev, unsigned long val)
{
dev->gro_flush_timeout = val;
WRITE_ONCE(dev->gro_flush_timeout, val);
return 0;
}
@ -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)
{
WRITE_ONCE(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,