1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
|
/*
* net busy poll support
* Copyright(c) 2013 Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*
* You should have received a copy of the GNU General Public License along with
* this program; if not, write to the Free Software Foundation, Inc.,
* 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
*
* 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 <net/ip.h>
#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;
/* return values from ndo_ll_poll */
#define LL_FLUSH_FAILED -1
#define LL_FLUSH_BUSY -2
static inline bool net_busy_loop_on(void)
{
return sysctl_net_busy_poll;
}
/* a wrapper to make debug_smp_processor_id() happy
* we can use sched_clock() because we don't care much about precision
* we only care that the average is bounded
*/
#ifdef CONFIG_DEBUG_PREEMPT
static inline u64 busy_loop_us_clock(void)
{
u64 rc;
preempt_disable_notrace();
rc = sched_clock();
preempt_enable_no_resched_notrace();
return rc >> 10;
}
#else /* CONFIG_DEBUG_PREEMPT */
static inline u64 busy_loop_us_clock(void)
{
return sched_clock() >> 10;
}
#endif /* CONFIG_DEBUG_PREEMPT */
static inline unsigned long sk_busy_loop_end_time(struct sock *sk)
{
return busy_loop_us_clock() + ACCESS_ONCE(sk->sk_ll_usec);
}
/* in poll/select we use the global sysctl_net_ll_poll value */
static inline unsigned long busy_loop_end_time(void)
{
return busy_loop_us_clock() + ACCESS_ONCE(sysctl_net_busy_poll);
}
static inline bool sk_can_busy_loop(struct sock *sk)
{
return sk->sk_ll_usec && sk->sk_napi_id &&
!need_resched() && !signal_pending(current);
}
static inline bool busy_loop_timeout(unsigned long end_time)
{
unsigned long now = busy_loop_us_clock();
return time_after(now, end_time);
}
/* when used in sock_poll() nonblock is known at compile time to be true
* so the loop and end_time will be optimized out
*/
static inline bool sk_busy_loop(struct sock *sk, int nonblock)
{
unsigned long end_time = !nonblock ? sk_busy_loop_end_time(sk) : 0;
const struct net_device_ops *ops;
struct napi_struct *napi;
int rc = false;
/*
* rcu read lock for napi hash
* bh so we don't race with net_rx_action
*/
rcu_read_lock_bh();
napi = napi_by_id(sk->sk_napi_id);
if (!napi)
goto out;
ops = napi->dev->netdev_ops;
if (!ops->ndo_busy_poll)
goto out;
do {
rc = ops->ndo_busy_poll(napi);
if (rc == LL_FLUSH_FAILED)
break; /* permanent failure */
if (rc > 0)
/* local bh are disabled so it is ok to use _BH */
NET_ADD_STATS_BH(sock_net(sk),
LINUX_MIB_LOWLATENCYRXPACKETS, rc);
} while (!nonblock && skb_queue_empty(&sk->sk_receive_queue) &&
!need_resched() && !busy_loop_timeout(end_time));
rc = !skb_queue_empty(&sk->sk_receive_queue);
out:
rcu_read_unlock_bh();
return rc;
}
/* 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)
{
skb->napi_id = napi->napi_id;
}
/* used in the protocol hanlder to propagate the napi_id to the socket */
static inline void sk_mark_napi_id(struct sock *sk, struct sk_buff *skb)
{
sk->sk_napi_id = skb->napi_id;
}
#else /* CONFIG_NET_RX_BUSY_POLL */
static inline unsigned long net_busy_loop_on(void)
{
return 0;
}
static inline unsigned long busy_loop_end_time(void)
{
return 0;
}
static inline bool sk_can_busy_loop(struct sock *sk)
{
return false;
}
static inline void skb_mark_napi_id(struct sk_buff *skb,
struct napi_struct *napi)
{
}
static inline void sk_mark_napi_id(struct sock *sk, struct sk_buff *skb)
{
}
static inline bool busy_loop_timeout(unsigned long end_time)
{
return true;
}
static inline bool sk_busy_loop(struct sock *sk, int nonblock)
{
return false;
}
#endif /* CONFIG_NET_RX_BUSY_POLL */
#endif /* _LINUX_NET_BUSY_POLL_H */
|