aboutsummaryrefslogtreecommitdiffstats
path: root/net/core/stream.c
blob: 1e27a57b5a9754858be142c1dec91cf096b5329f (plain) (blame)
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
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
/*
 *     SUCS NET3:
 *
 *     Generic stream handling routines. These are generic for most
 *     protocols. Even IP. Tonight 8-).
 *     This is used because TCP, LLC (others too) layer all have mostly
 *     identical sendmsg() and recvmsg() code.
 *     So we (will) share it here.
 *
 *     Authors:        Arnaldo Carvalho de Melo <acme@conectiva.com.br>
 *                     (from old tcp.c code)
 *                     Alan Cox <alan@redhat.com> (Borrowed comments 8-))
 */

#include <linux/module.h>
#include <linux/net.h>
#include <linux/signal.h>
#include <linux/tcp.h>
#include <linux/wait.h>
#include <net/sock.h>

/**
 * sk_stream_write_space - stream socket write_space callback.
 * sk - socket
 *
 * FIXME: write proper description
 */
void sk_stream_write_space(struct sock *sk)
{
	struct socket *sock = sk->sk_socket;

	if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) && sock) {
		clear_bit(SOCK_NOSPACE, &sock->flags);

		if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
			wake_up_interruptible(sk->sk_sleep);
		if (sock->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN))
			sock_wake_async(sock, 2, POLL_OUT);
	}
}

EXPORT_SYMBOL(sk_stream_write_space);

/**
 * sk_stream_wait_connect - Wait for a socket to get into the connected state
 * @sk - sock to wait on
 * @timeo_p - for how long to wait
 *
 * Must be called with the socket locked.
 */
int sk_stream_wait_connect(struct sock *sk, long *timeo_p)
{
	struct task_struct *tsk = current;
	DEFINE_WAIT(wait);

	while (1) {
		if (sk->sk_err)
			return sock_error(sk);
		if ((1 << sk->sk_state) & ~(TCPF_SYN_SENT | TCPF_SYN_RECV))
			return -EPIPE;
		if (!*timeo_p)
			return -EAGAIN;
		if (signal_pending(tsk))
			return sock_intr_errno(*timeo_p);

		prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
		sk->sk_write_pending++;
		if (sk_wait_event(sk, timeo_p,
				  !((1 << sk->sk_state) & 
				    ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT))))
			break;
		finish_wait(sk->sk_sleep, &wait);
		sk->sk_write_pending--;
	}
	return 0;
}

EXPORT_SYMBOL(sk_stream_wait_connect);

/**
 * sk_stream_closing - Return 1 if we still have things to send in our buffers.
 * @sk - socket to verify
 */
static inline int sk_stream_closing(struct sock *sk)
{
	return (1 << sk->sk_state) &
	       (TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK);
}

void sk_stream_wait_close(struct sock *sk, long timeout)
{
	if (timeout) {
		DEFINE_WAIT(wait);

		do {
			prepare_to_wait(sk->sk_sleep, &wait,
					TASK_INTERRUPTIBLE);
			if (sk_wait_event(sk, &timeout, !sk_stream_closing(sk)))
				break;
		} while (!signal_pending(current) && timeout);

		finish_wait(sk->sk_sleep, &wait);
	}
}

EXPORT_SYMBOL(sk_stream_wait_close);

/**
 * sk_stream_wait_memory - Wait for more memory for a socket
 * @sk - socket to wait for memory
 * @timeo_p - for how long
 */
int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
{
	int err = 0;
	long vm_wait = 0;
	long current_timeo = *timeo_p;
	DEFINE_WAIT(wait);

	if (sk_stream_memory_free(sk))
		current_timeo = vm_wait = (net_random() % (HZ / 5)) + 2;

	while (1) {
		set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);

		prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);

		if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
			goto do_error;
		if (!*timeo_p)
			goto do_nonblock;
		if (signal_pending(current))
			goto do_interrupted;
		clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
		if (sk_stream_memory_free(sk) && !vm_wait)
			break;

		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
		sk->sk_write_pending++;
		sk_wait_event(sk, &current_timeo, sk_stream_memory_free(sk) &&
						  vm_wait);
		sk->sk_write_pending--;

		if (vm_wait) {
			vm_wait -= current_timeo;
			current_timeo = *timeo_p;
			if (current_timeo != MAX_SCHEDULE_TIMEOUT &&
			    (current_timeo -= vm_wait) < 0)
				current_timeo = 0;
			vm_wait = 0;
		}
		*timeo_p = current_timeo;
	}
out:
	finish_wait(sk->sk_sleep, &wait);
	return err;

do_error:
	err = -EPIPE;
	goto out;
do_nonblock:
	err = -EAGAIN;
	goto out;
do_interrupted:
	err = sock_intr_errno(*timeo_p);
	goto out;
}

EXPORT_SYMBOL(sk_stream_wait_memory);

void sk_stream_rfree(struct sk_buff *skb)
{
	struct sock *sk = skb->sk;

	atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
	sk->sk_forward_alloc += skb->truesize;
}

EXPORT_SYMBOL(sk_stream_rfree);

int sk_stream_error(struct sock *sk, int flags, int err)
{
	if (err == -EPIPE)
		err = sock_error(sk) ? : -EPIPE;
	if (err == -EPIPE && !(flags & MSG_NOSIGNAL))
		send_sig(SIGPIPE, current, 0);
	return err;
}

EXPORT_SYMBOL(sk_stream_error);

void __sk_stream_mem_reclaim(struct sock *sk)
{
	if (sk->sk_forward_alloc >= SK_STREAM_MEM_QUANTUM) {
		atomic_sub(sk->sk_forward_alloc / SK_STREAM_MEM_QUANTUM,
			   sk->sk_prot->memory_allocated);
		sk->sk_forward_alloc &= SK_STREAM_MEM_QUANTUM - 1;
		if (*sk->sk_prot->memory_pressure &&
		    (atomic_read(sk->sk_prot->memory_allocated) <
		     sk->sk_prot->sysctl_mem[0]))
			*sk->sk_prot->memory_pressure = 0;
	}
}

EXPORT_SYMBOL(__sk_stream_mem_reclaim);

int sk_stream_mem_schedule(struct sock *sk, int size, int kind)
{
	int amt = sk_stream_pages(size);

	sk->sk_forward_alloc += amt * SK_STREAM_MEM_QUANTUM;
	atomic_add(amt, sk->sk_prot->memory_allocated);

	/* Under limit. */
	if (atomic_read(sk->sk_prot->memory_allocated) < sk->sk_prot->sysctl_mem[0]) {
		if (*sk->sk_prot->memory_pressure)
			*sk->sk_prot->memory_pressure = 0;
		return 1;
	}

	/* Over hard limit. */
	if (atomic_read(sk->sk_prot->memory_allocated) > sk->sk_prot->sysctl_mem[2]) {
		sk->sk_prot->enter_memory_pressure();
		goto suppress_allocation;
	}

	/* Under pressure. */
	if (atomic_read(sk->sk_prot->memory_allocated) > sk->sk_prot->sysctl_mem[1])
		sk->sk_prot->enter_memory_pressure();

	if (kind) {
		if (atomic_read(&sk->sk_rmem_alloc) < sk->sk_prot->sysctl_rmem[0])
			return 1;
	} else if (sk->sk_wmem_queued < sk->sk_prot->sysctl_wmem[0])
		return 1;

	if (!*sk->sk_prot->memory_pressure ||
	    sk->sk_prot->sysctl_mem[2] > atomic_read(sk->sk_prot->sockets_allocated) *
				sk_stream_pages(sk->sk_wmem_queued +
						atomic_read(&sk->sk_rmem_alloc) +
						sk->sk_forward_alloc))
		return 1;

suppress_allocation:

	if (!kind) {
		sk_stream_moderate_sndbuf(sk);

		/* Fail only if socket is _under_ its sndbuf.
		 * In this case we cannot block, so that we have to fail.
		 */
		if (sk->sk_wmem_queued + size >= sk->sk_sndbuf)
			return 1;
	}

	/* Alas. Undo changes. */
	sk->sk_forward_alloc -= amt * SK_STREAM_MEM_QUANTUM;
	atomic_sub(amt, sk->sk_prot->memory_allocated);
	return 0;
}

EXPORT_SYMBOL(sk_stream_mem_schedule);

void sk_stream_kill_queues(struct sock *sk)
{
	/* First the read buffer. */
	__skb_queue_purge(&sk->sk_receive_queue);

	/* Next, the error queue. */
	__skb_queue_purge(&sk->sk_error_queue);

	/* Next, the write queue. */
	BUG_TRAP(skb_queue_empty(&sk->sk_write_queue));

	/* Account for returned memory. */
	sk_stream_mem_reclaim(sk);

	BUG_TRAP(!sk->sk_wmem_queued);
	BUG_TRAP(!sk->sk_forward_alloc);

	/* It is _impossible_ for the backlog to contain anything
	 * when we get here.  All user references to this socket
	 * have gone away, only the net layer knows can touch it.
	 */
}

EXPORT_SYMBOL(sk_stream_kill_queues);