summaryrefslogtreecommitdiff
path: root/include/net/ll_poll.h
blob: 6c06f7c0a22de8f3354832c82b65d950f51bdbe2 (plain)
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
186
187
188
189
190
191
192
/*
 * Low Latency Sockets
 * 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_LL_POLL_H
#define _LINUX_NET_LL_POLL_H

#include <linux/netdevice.h>
#include <net/ip.h>

#ifdef CONFIG_NET_LL_RX_POLL

struct napi_struct;
extern unsigned int sysctl_net_ll_read __read_mostly;
extern unsigned int sysctl_net_ll_poll __read_mostly;

/* return values from ndo_ll_poll */
#define LL_FLUSH_FAILED		-1
#define LL_FLUSH_BUSY		-2

static inline unsigned int ll_get_flag(void)
{
	return sysctl_net_ll_poll ? POLL_LL : 0;
}

/* 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 ll_sched_clock(void)
{
	u64 rc;

	preempt_disable_notrace();
	rc = sched_clock();
	preempt_enable_no_resched_notrace();

	return rc;
}
#else /* CONFIG_DEBUG_PREEMPT */
static inline u64 ll_sched_clock(void)
{
	return sched_clock();
}
#endif /* CONFIG_DEBUG_PREEMPT */

/* we don't mind a ~2.5% imprecision so <<10 instead of *1000
 * sk->sk_ll_usec is a u_int so this can't overflow
 */
static inline u64 ll_sk_end_time(struct sock *sk)
{
	return ((u64)ACCESS_ONCE(sk->sk_ll_usec) << 10) + ll_sched_clock();
}

/* in poll/select we use the global sysctl_net_ll_poll value
 * only call sched_clock() if enabled
 */
static inline u64 ll_end_time(void)
{
	u64 end_time = ACCESS_ONCE(sysctl_net_ll_poll);

	return end_time ? (end_time << 10) + ll_sched_clock() : 0;
}

static inline bool sk_valid_ll(struct sock *sk)
{
	return sk->sk_ll_usec && sk->sk_napi_id &&
	       !need_resched() && !signal_pending(current);
}

static inline bool can_poll_ll(u64 end_time)
{
	return !time_after64(ll_sched_clock(), 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_poll_ll(struct sock *sk, int nonblock)
{
	u64 end_time = nonblock ? 0 : ll_sk_end_time(sk);
	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_ll_poll)
		goto out;

	do {
		rc = ops->ndo_ll_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) &&
		 can_poll_ll(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_ll(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_ll(struct sock *sk, struct sk_buff *skb)
{
	sk->sk_napi_id = skb->napi_id;
}

#else /* CONFIG_NET_LL_RX_POLL */
static inline unsigned long ll_get_flag(void)
{
	return 0;
}

static inline u64 sk_ll_end_time(struct sock *sk)
{
	return 0;
}

static inline u64 ll_end_time(void)
{
	return 0;
}

static inline bool sk_valid_ll(struct sock *sk)
{
	return false;
}

static inline bool sk_poll_ll(struct sock *sk, int nonblock)
{
	return false;
}

static inline void skb_mark_ll(struct sk_buff *skb, struct napi_struct *napi)
{
}

static inline void sk_mark_ll(struct sock *sk, struct sk_buff *skb)
{
}

static inline bool can_poll_ll(u64 end_time)
{
	return false;
}

#endif /* CONFIG_NET_LL_RX_POLL */
#endif /* _LINUX_NET_LL_POLL_H */