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

mlx4: remove mlx4_en_low_latency_recv() 

Busy polling can now be handled in generic NAPI poll infrastructure.
This removes complexity and fast path overhead :

mlx4 used two spin_lock()/spin_unlock() pair per napi->poll() call
in mlx4_en_cq_lock_napi()/mlx4_en_cq_unlock_napi()

Tested:

Without busy polling :

lpaa23:~# echo 0 >/proc/sys/net/core/busy_read
lpaa24:~# echo 0 >/proc/sys/net/core/busy_read
lpaa23:~# ./netperf -H lpaa24 -t TCP_RR
MIGRATED TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to lpaa24.prod.google.com () port 0 AF_INET : first burst 0
Local /Remote
Socket Size   Request  Resp.   Elapsed  Trans.
Send   Recv   Size     Size    Time     Rate
bytes  Bytes  bytes    bytes   secs.    per sec

16384  87380  1        1       10.00    47330.78

With busy polling :

lpaa23:~# echo 70 >/proc/sys/net/core/busy_read
lpaa24:~# echo 70 >/proc/sys/net/core/busy_read
lpaa23:~# ./netperf -H lpaa24 -t TCP_RR
MIGRATED TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to lpaa24.prod.google.com () port 0 AF_INET : first burst 0
Local /Remote
Socket Size   Request  Resp.   Elapsed  Trans.
Send   Recv   Size     Size    Time     Rate
bytes  Bytes  bytes    bytes   secs.    per sec

16384  87380  1        1       10.00    97643.55

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Eric Dumazet 2015-11-18 06:30:58 -08:00 committed by David S. Miller
parent b59768c6b4
commit 868fdb0606
4 changed files with 2 additions and 198 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
View File

@ -337,11 +337,7 @@ static int mlx4_en_get_sset_count(struct net_device *dev, int sset)
case ETH_SS_STATS:
return bitmap_iterator_count(&it) +
(priv->tx_ring_num * 2) +
#ifdef CONFIG_NET_RX_BUSY_POLL
(priv->rx_ring_num * 5);
#else
(priv->rx_ring_num * 2);
#endif
case ETH_SS_TEST:
return MLX4_EN_NUM_SELF_TEST - !(priv->mdev->dev->caps.flags
& MLX4_DEV_CAP_FLAG_UC_LOOPBACK) * 2;
@ -408,11 +404,6 @@ static void mlx4_en_get_ethtool_stats(struct net_device *dev,
for (i = 0; i < priv->rx_ring_num; i++) {
data[index++] = priv->rx_ring[i]->packets;
data[index++] = priv->rx_ring[i]->bytes;
#ifdef CONFIG_NET_RX_BUSY_POLL
data[index++] = priv->rx_ring[i]->yields;
data[index++] = priv->rx_ring[i]->misses;
data[index++] = priv->rx_ring[i]->cleaned;
#endif
}
spin_unlock_bh(&priv->stats_lock);
@ -486,14 +477,6 @@ static void mlx4_en_get_strings(struct net_device *dev,
"rx%d_packets", i);
sprintf(data + (index++) * ETH_GSTRING_LEN,
"rx%d_bytes", i);
#ifdef CONFIG_NET_RX_BUSY_POLL
sprintf(data + (index++) * ETH_GSTRING_LEN,
"rx%d_napi_yield", i);
sprintf(data + (index++) * ETH_GSTRING_LEN,
"rx%d_misses", i);
sprintf(data + (index++) * ETH_GSTRING_LEN,
"rx%d_cleaned", i);
#endif
}
break;
case ETH_SS_PRIV_FLAGS:

40
drivers/net/ethernet/mellanox/mlx4/en_netdev.c
View File

@ -69,34 +69,6 @@ int mlx4_en_setup_tc(struct net_device *dev, u8 up)
return 0;
}
#ifdef CONFIG_NET_RX_BUSY_POLL
/* must be called with local_bh_disable()d */
static int mlx4_en_low_latency_recv(struct napi_struct *napi)
{
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);
struct mlx4_en_rx_ring *rx_ring = priv->rx_ring[cq->ring];
int done;
if (!priv->port_up)
return LL_FLUSH_FAILED;
if (!mlx4_en_cq_lock_poll(cq))
return LL_FLUSH_BUSY;
done = mlx4_en_process_rx_cq(dev, cq, 4);
if (likely(done))
rx_ring->cleaned += done;
else
rx_ring->misses++;
mlx4_en_cq_unlock_poll(cq);
return done;
}
#endif /* CONFIG_NET_RX_BUSY_POLL */
#ifdef CONFIG_RFS_ACCEL
struct mlx4_en_filter {
@ -1561,8 +1533,6 @@ int mlx4_en_start_port(struct net_device *dev)
for (i = 0; i < priv->rx_ring_num; i++) {
cq = priv->rx_cq[i];
mlx4_en_cq_init_lock(cq);
err = mlx4_en_init_affinity_hint(priv, i);
if (err) {
en_err(priv, "Failed preparing IRQ affinity hint\n");
@ -1859,13 +1829,6 @@ void mlx4_en_stop_port(struct net_device *dev, int detach)
for (i = 0; i < priv->rx_ring_num; i++) {
struct mlx4_en_cq *cq = priv->rx_cq[i];
local_bh_disable();
while (!mlx4_en_cq_lock_napi(cq)) {
pr_info("CQ %d locked\n", i);
mdelay(1);
}
local_bh_enable();
napi_synchronize(&cq->napi);
mlx4_en_deactivate_rx_ring(priv, priv->rx_ring[i]);
mlx4_en_deactivate_cq(priv, cq);
@ -2503,9 +2466,6 @@ static const struct net_device_ops mlx4_netdev_ops = {
.ndo_setup_tc = mlx4_en_setup_tc,
#ifdef CONFIG_RFS_ACCEL
.ndo_rx_flow_steer = mlx4_en_filter_rfs,
#endif
#ifdef CONFIG_NET_RX_BUSY_POLL
.ndo_busy_poll = mlx4_en_low_latency_recv,
#endif
.ndo_get_phys_port_id = mlx4_en_get_phys_port_id,
#ifdef CONFIG_MLX4_EN_VXLAN

15
drivers/net/ethernet/mellanox/mlx4/en_rx.c
View File

@ -873,10 +873,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
* - TCP/IP (v4)
* - without IP options
* - not an IP fragment
* - no LLS polling in progress
*/
if (!mlx4_en_cq_busy_polling(cq) &&
(dev->features & NETIF_F_GRO)) {
if (dev->features & NETIF_F_GRO) {
struct sk_buff *gro_skb = napi_get_frags(&cq->napi);
if (!gro_skb)
goto next;
@ -992,11 +990,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
skb_mark_napi_id(skb, &cq->napi);
if (!mlx4_en_cq_busy_polling(cq))
napi_gro_receive(&cq->napi, skb);
else
netif_receive_skb(skb);
napi_gro_receive(&cq->napi, skb);
next:
for (nr = 0; nr < priv->num_frags; nr++)
mlx4_en_free_frag(priv, frags, nr);
@ -1038,13 +1032,8 @@ int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget)
struct mlx4_en_priv *priv = netdev_priv(dev);
int done;
if (!mlx4_en_cq_lock_napi(cq))
return budget;
done = mlx4_en_process_rx_cq(dev, cq, budget);
mlx4_en_cq_unlock_napi(cq);
/* If we used up all the quota - we're probably not done yet... */
if (done == budget) {
const struct cpumask *aff;

128
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
View File

@ -320,11 +320,6 @@ struct mlx4_en_rx_ring {
void *rx_info;
unsigned long bytes;
unsigned long packets;
#ifdef CONFIG_NET_RX_BUSY_POLL
unsigned long yields;
unsigned long misses;
unsigned long cleaned;
#endif
unsigned long csum_ok;
unsigned long csum_none;
unsigned long csum_complete;
@ -347,18 +342,6 @@ struct mlx4_en_cq {
struct mlx4_cqe *buf;
#define MLX4_EN_OPCODE_ERROR 0x1e
#ifdef CONFIG_NET_RX_BUSY_POLL
unsigned int state;
#define MLX4_EN_CQ_STATE_IDLE 0
#define MLX4_EN_CQ_STATE_NAPI 1 /* NAPI owns this CQ */
#define MLX4_EN_CQ_STATE_POLL 2 /* poll owns this CQ */
#define MLX4_CQ_LOCKED (MLX4_EN_CQ_STATE_NAPI | MLX4_EN_CQ_STATE_POLL)
#define MLX4_EN_CQ_STATE_NAPI_YIELD 4 /* NAPI yielded this CQ */
#define MLX4_EN_CQ_STATE_POLL_YIELD 8 /* poll yielded this CQ */
#define CQ_YIELD (MLX4_EN_CQ_STATE_NAPI_YIELD | MLX4_EN_CQ_STATE_POLL_YIELD)
#define CQ_USER_PEND (MLX4_EN_CQ_STATE_POLL | MLX4_EN_CQ_STATE_POLL_YIELD)
spinlock_t poll_lock; /* protects from LLS/napi conflicts */
#endif /* CONFIG_NET_RX_BUSY_POLL */
struct irq_desc *irq_desc;
};
@ -622,117 +605,6 @@ static inline struct mlx4_cqe *mlx4_en_get_cqe(void *buf, int idx, int cqe_sz)
return buf + idx * cqe_sz;
}
#ifdef CONFIG_NET_RX_BUSY_POLL
static inline void mlx4_en_cq_init_lock(struct mlx4_en_cq *cq)
{
spin_lock_init(&cq->poll_lock);
cq->state = MLX4_EN_CQ_STATE_IDLE;
}
/* called from the device poll rutine to get ownership of a cq */
static inline bool mlx4_en_cq_lock_napi(struct mlx4_en_cq *cq)
{
int rc = true;
spin_lock(&cq->poll_lock);
if (cq->state & MLX4_CQ_LOCKED) {
WARN_ON(cq->state & MLX4_EN_CQ_STATE_NAPI);
cq->state |= MLX4_EN_CQ_STATE_NAPI_YIELD;
rc = false;
} else
/* we don't care if someone yielded */
cq->state = MLX4_EN_CQ_STATE_NAPI;
spin_unlock(&cq->poll_lock);
return rc;
}
/* returns true is someone tried to get the cq while napi had it */
static inline bool mlx4_en_cq_unlock_napi(struct mlx4_en_cq *cq)
{
int rc = false;
spin_lock(&cq->poll_lock);
WARN_ON(cq->state & (MLX4_EN_CQ_STATE_POLL |
MLX4_EN_CQ_STATE_NAPI_YIELD));
if (cq->state & MLX4_EN_CQ_STATE_POLL_YIELD)
rc = true;
cq->state = MLX4_EN_CQ_STATE_IDLE;
spin_unlock(&cq->poll_lock);
return rc;
}
/* called from mlx4_en_low_latency_recv(), BH are disabled */
static inline bool mlx4_en_cq_lock_poll(struct mlx4_en_cq *cq)
{
int rc = true;
spin_lock(&cq->poll_lock);
if ((cq->state & MLX4_CQ_LOCKED)) {
struct net_device *dev = cq->dev;
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_en_rx_ring *rx_ring = priv->rx_ring[cq->ring];
cq->state |= MLX4_EN_CQ_STATE_POLL_YIELD;
rc = false;
rx_ring->yields++;
} else
/* preserve yield marks */
cq->state |= MLX4_EN_CQ_STATE_POLL;
spin_unlock(&cq->poll_lock);
return rc;
}
/* returns true if someone tried to get the cq while it was locked */
static inline bool mlx4_en_cq_unlock_poll(struct mlx4_en_cq *cq)
{
int rc = false;
spin_lock(&cq->poll_lock);
WARN_ON(cq->state & (MLX4_EN_CQ_STATE_NAPI));
if (cq->state & MLX4_EN_CQ_STATE_POLL_YIELD)
rc = true;
cq->state = MLX4_EN_CQ_STATE_IDLE;
spin_unlock(&cq->poll_lock);
return rc;
}
/* true if a socket is polling, even if it did not get the lock */
static inline bool mlx4_en_cq_busy_polling(struct mlx4_en_cq *cq)
{
WARN_ON(!(cq->state & MLX4_CQ_LOCKED));
return cq->state & CQ_USER_PEND;
}
#else
static inline void mlx4_en_cq_init_lock(struct mlx4_en_cq *cq)
{
}
static inline bool mlx4_en_cq_lock_napi(struct mlx4_en_cq *cq)
{
return true;
}
static inline bool mlx4_en_cq_unlock_napi(struct mlx4_en_cq *cq)
{
return false;
}
static inline bool mlx4_en_cq_lock_poll(struct mlx4_en_cq *cq)
{
return false;
}
static inline bool mlx4_en_cq_unlock_poll(struct mlx4_en_cq *cq)
{
return false;
}
static inline bool mlx4_en_cq_busy_polling(struct mlx4_en_cq *cq)
{
return false;
}
#endif /* CONFIG_NET_RX_BUSY_POLL */
#define MLX4_EN_WOL_DO_MODIFY (1ULL << 63)
void mlx4_en_update_loopback_state(struct net_device *dev,