97751f7856
[ Upstream commit 0870b0d8b393dde53106678a1e2cec9dfa52f9b7 ]
Typically, busy-polling durations are below 100 usec.
When/if the busy-poller thread migrates to another cpu,
local_clock() can be off by +/-2msec or more for small
values of HZ, depending on the platform.
Use ktimer_get_ns() to ensure deterministic behavior,
which is the whole point of busy-polling.
Fixes: 060212928670 ("net: add low latency socket poll")
Fixes: 9a3c71aa8024 ("net: convert low latency sockets to sched_clock()")
Fixes: 37089834528b ("sched, net: Fixup busy_loop_us_clock()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Link: https://patch.msgid.link/20240827114916.223377-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
144 lines
3.4 KiB
C
Executable file
144 lines
3.4 KiB
C
Executable file
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
/*
|
|
* net busy poll support
|
|
* Copyright(c) 2013 Intel Corporation.
|
|
*
|
|
* Author: Eliezer Tamir
|
|
*
|
|
* Contact Information:
|
|
* e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
|
|
*/
|
|
|
|
#ifndef _LINUX_NET_BUSY_POLL_H
|
|
#define _LINUX_NET_BUSY_POLL_H
|
|
|
|
#include <linux/netdevice.h>
|
|
#include <linux/sched/clock.h>
|
|
#include <linux/sched/signal.h>
|
|
#include <net/ip.h>
|
|
|
|
/* 0 - Reserved to indicate value not set
|
|
* 1..NR_CPUS - Reserved for sender_cpu
|
|
* NR_CPUS+1..~0 - Region available for NAPI IDs
|
|
*/
|
|
#define MIN_NAPI_ID ((unsigned int)(NR_CPUS + 1))
|
|
|
|
#ifdef CONFIG_NET_RX_BUSY_POLL
|
|
|
|
struct napi_struct;
|
|
extern unsigned int sysctl_net_busy_read __read_mostly;
|
|
extern unsigned int sysctl_net_busy_poll __read_mostly;
|
|
|
|
static inline bool net_busy_loop_on(void)
|
|
{
|
|
return READ_ONCE(sysctl_net_busy_poll);
|
|
}
|
|
|
|
static inline bool sk_can_busy_loop(const struct sock *sk)
|
|
{
|
|
return READ_ONCE(sk->sk_ll_usec) && !signal_pending(current);
|
|
}
|
|
|
|
bool sk_busy_loop_end(void *p, unsigned long start_time);
|
|
|
|
void napi_busy_loop(unsigned int napi_id,
|
|
bool (*loop_end)(void *, unsigned long),
|
|
void *loop_end_arg);
|
|
|
|
#else /* CONFIG_NET_RX_BUSY_POLL */
|
|
static inline unsigned long net_busy_loop_on(void)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline bool sk_can_busy_loop(struct sock *sk)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
#endif /* CONFIG_NET_RX_BUSY_POLL */
|
|
|
|
static inline unsigned long busy_loop_current_time(void)
|
|
{
|
|
#ifdef CONFIG_NET_RX_BUSY_POLL
|
|
return (unsigned long)(ktime_get_ns() >> 10);
|
|
#else
|
|
return 0;
|
|
#endif
|
|
}
|
|
|
|
/* in poll/select we use the global sysctl_net_ll_poll value */
|
|
static inline bool busy_loop_timeout(unsigned long start_time)
|
|
{
|
|
#ifdef CONFIG_NET_RX_BUSY_POLL
|
|
unsigned long bp_usec = READ_ONCE(sysctl_net_busy_poll);
|
|
|
|
if (bp_usec) {
|
|
unsigned long end_time = start_time + bp_usec;
|
|
unsigned long now = busy_loop_current_time();
|
|
|
|
return time_after(now, end_time);
|
|
}
|
|
#endif
|
|
return true;
|
|
}
|
|
|
|
static inline bool sk_busy_loop_timeout(struct sock *sk,
|
|
unsigned long start_time)
|
|
{
|
|
#ifdef CONFIG_NET_RX_BUSY_POLL
|
|
unsigned long bp_usec = READ_ONCE(sk->sk_ll_usec);
|
|
|
|
if (bp_usec) {
|
|
unsigned long end_time = start_time + bp_usec;
|
|
unsigned long now = busy_loop_current_time();
|
|
|
|
return time_after(now, end_time);
|
|
}
|
|
#endif
|
|
return true;
|
|
}
|
|
|
|
static inline void sk_busy_loop(struct sock *sk, int nonblock)
|
|
{
|
|
#ifdef CONFIG_NET_RX_BUSY_POLL
|
|
unsigned int napi_id = READ_ONCE(sk->sk_napi_id);
|
|
|
|
if (napi_id >= MIN_NAPI_ID)
|
|
napi_busy_loop(napi_id, nonblock ? NULL : sk_busy_loop_end, sk);
|
|
#endif
|
|
}
|
|
|
|
/* used in the NIC receive handler to mark the skb */
|
|
static inline void skb_mark_napi_id(struct sk_buff *skb,
|
|
struct napi_struct *napi)
|
|
{
|
|
#ifdef CONFIG_NET_RX_BUSY_POLL
|
|
/* If the skb was already marked with a valid NAPI ID, avoid overwriting
|
|
* it.
|
|
*/
|
|
if (skb->napi_id < MIN_NAPI_ID)
|
|
skb->napi_id = napi->napi_id;
|
|
#endif
|
|
}
|
|
|
|
/* used in the protocol hanlder to propagate the napi_id to the socket */
|
|
static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb)
|
|
{
|
|
#ifdef CONFIG_NET_RX_BUSY_POLL
|
|
WRITE_ONCE(sk->sk_napi_id, skb->napi_id);
|
|
#endif
|
|
sk_rx_queue_set(sk, skb);
|
|
}
|
|
|
|
/* variant used for unconnected sockets */
|
|
static inline void sk_mark_napi_id_once(struct sock *sk,
|
|
const struct sk_buff *skb)
|
|
{
|
|
#ifdef CONFIG_NET_RX_BUSY_POLL
|
|
if (!READ_ONCE(sk->sk_napi_id))
|
|
WRITE_ONCE(sk->sk_napi_id, skb->napi_id);
|
|
#endif
|
|
}
|
|
|
|
#endif /* _LINUX_NET_BUSY_POLL_H */
|