Source

go-sunos / src / pkg / runtime / netpoll.goc

The port-sunos branch has multiple heads

  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
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
// Copyright 2013 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.

// +build darwin dragonfly freebsd linux netbsd openbsd solaris windows

package net

#include "runtime.h"
#include "defs_GOOS_GOARCH.h"
#include "arch_GOARCH.h"
#include "malloc.h"

// Integrated network poller (platform-independent part).
// A particular implementation (epoll/kqueue) must define the following functions:
// void runtime·netpollinit(void);			// to initialize the poller
// int32 runtime·netpollopen(uintptr fd, PollDesc *pd);	// to arm edge-triggered notifications
							// and associate fd with pd.
// An implementation must call the following function to denote that the pd is ready.
// void runtime·netpollready(G **gpp, PollDesc *pd, int32 mode);

// PollDesc contains 2 binary semaphores, rg and wg, to park reader and writer
// goroutines respectively. The semaphore can be in the following states:
// READY - io readiness notification is pending;
//         a goroutine consumes the notification by changing the state to nil.
// WAIT - a goroutine prepares to park on the semaphore, but not yet parked;
//        the goroutine commits to park by changing the state to G pointer,
//        or, alternatively, concurrent io notification changes the state to READY,
//        or, alternatively, concurrent timeout/close changes the state to nil.
// G pointer - the goroutine is blocked on the semaphore;
//             io notification or timeout/close changes the state to READY or nil respectively
//             and unparks the goroutine.
// nil - nothing of the above.
#define READY ((G*)1)
#define WAIT  ((G*)2)

enum
{
	PollBlockSize	= 4*1024,
};

struct PollDesc
{
	PollDesc* link;	// in pollcache, protected by pollcache.Lock

	// The lock protects pollOpen, pollSetDeadline, pollUnblock and deadlineimpl operations.
	// This fully covers seq, rt and wt variables. fd is constant throughout the PollDesc lifetime.
	// pollReset, pollWait, pollWaitCanceled and runtime·netpollready (IO rediness notification)
	// proceed w/o taking the lock. So closing, rg, rd, wg and wd are manipulated
	// in a lock-free way by all operations.
	Lock;		// protectes the following fields
	uintptr	fd;
	bool	closing;
	uintptr	seq;	// protects from stale timers and ready notifications
	G*	rg;	// READY, WAIT, G waiting for read or nil
	Timer	rt;	// read deadline timer (set if rt.fv != nil)
	int64	rd;	// read deadline
	G*	wg;	// READY, WAIT, G waiting for write or nil
	Timer	wt;	// write deadline timer
	int64	wd;	// write deadline
	void*	user;	// user settable cookie
};

static struct
{
	Lock;
	PollDesc*	first;
	// PollDesc objects must be type-stable,
	// because we can get ready notification from epoll/kqueue
	// after the descriptor is closed/reused.
	// Stale notifications are detected using seq variable,
	// seq is incremented when deadlines are changed or descriptor is reused.
} pollcache;

static bool	netpollblock(PollDesc*, int32, bool);
static G*	netpollunblock(PollDesc*, int32, bool);
static void	deadline(int64, Eface);
static void	readDeadline(int64, Eface);
static void	writeDeadline(int64, Eface);
static PollDesc*	allocPollDesc(void);
static intgo	checkerr(PollDesc *pd, int32 mode);

static FuncVal deadlineFn	= {(void(*)(void))deadline};
static FuncVal readDeadlineFn	= {(void(*)(void))readDeadline};
static FuncVal writeDeadlineFn	= {(void(*)(void))writeDeadline};

// runtimeNano returns the current value of the runtime clock in nanoseconds.
func runtimeNano() (ns int64) {
	ns = runtime·nanotime();
}

func runtime_pollServerInit() {
	runtime·netpollinit();
}

func runtime_pollOpen(fd uintptr) (pd *PollDesc, errno int) {
	pd = allocPollDesc();
	runtime·lock(pd);
	if(pd->wg != nil && pd->wg != READY)
		runtime·throw("runtime_pollOpen: blocked write on free descriptor");
	if(pd->rg != nil && pd->rg != READY)
		runtime·throw("runtime_pollOpen: blocked read on free descriptor");
	pd->fd = fd;
	pd->closing = false;
	pd->seq++;
	pd->rg = nil;
	pd->rd = 0;
	pd->wg = nil;
	pd->wd = 0;
	runtime·unlock(pd);

	errno = runtime·netpollopen(fd, pd);
}

func runtime_pollClose(pd *PollDesc) {
	if(!pd->closing)
		runtime·throw("runtime_pollClose: close w/o unblock");
	if(pd->wg != nil && pd->wg != READY)
		runtime·throw("runtime_pollClose: blocked write on closing descriptor");
	if(pd->rg != nil && pd->rg != READY)
		runtime·throw("runtime_pollClose: blocked read on closing descriptor");
	runtime·netpollclose(pd->fd);
	runtime·lock(&pollcache);
	pd->link = pollcache.first;
	pollcache.first = pd;
	runtime·unlock(&pollcache);
}

func runtime_pollReset(pd *PollDesc, mode int) (err int) {
	err = checkerr(pd, mode);
	if(err)
		goto ret;
	if(mode == 'r')
		pd->rg = nil;
	else if(mode == 'w')
		pd->wg = nil;
ret:
}

func runtime_pollWait(pd *PollDesc, mode int) (err int) {
	err = checkerr(pd, mode);
	if(err == 0) {
		// As for now only Solaris uses level-triggered IO.
		if(Solaris)
			runtime·netpollarm(pd, mode);
		while(!netpollblock(pd, mode, false)) {
			err = checkerr(pd, mode);
			if(err != 0)
				break;
			// Can happen if timeout has fired and unblocked us,
			// but before we had a chance to run, timeout has been reset.
			// Pretend it has not happened and retry.
		}
	}
}

func runtime_pollWaitCanceled(pd *PollDesc, mode int) {
	// This function is used only on windows after a failed attempt to cancel
	// a pending async IO operation. Wait for ioready, ignore closing or timeouts.
	while(!netpollblock(pd, mode, true))
		;
}

func runtime_pollSetDeadline(pd *PollDesc, d int64, mode int) {
	G *rg, *wg;

	runtime·lock(pd);
	if(pd->closing) {
		runtime·unlock(pd);
		return;
	}
	pd->seq++;  // invalidate current timers
	// Reset current timers.
	if(pd->rt.fv) {
		runtime·deltimer(&pd->rt);
		pd->rt.fv = nil;
	}
	if(pd->wt.fv) {
		runtime·deltimer(&pd->wt);
		pd->wt.fv = nil;
	}
	// Setup new timers.
	if(d != 0 && d <= runtime·nanotime())
		d = -1;
	if(mode == 'r' || mode == 'r'+'w')
		pd->rd = d;
	if(mode == 'w' || mode == 'r'+'w')
		pd->wd = d;
	if(pd->rd > 0 && pd->rd == pd->wd) {
		pd->rt.fv = &deadlineFn;
		pd->rt.when = pd->rd;
		// Copy current seq into the timer arg.
		// Timer func will check the seq against current descriptor seq,
		// if they differ the descriptor was reused or timers were reset.
		pd->rt.arg.type = (Type*)pd->seq;
		pd->rt.arg.data = pd;
		runtime·addtimer(&pd->rt);
	} else {
		if(pd->rd > 0) {
			pd->rt.fv = &readDeadlineFn;
			pd->rt.when = pd->rd;
			pd->rt.arg.type = (Type*)pd->seq;
			pd->rt.arg.data = pd;
			runtime·addtimer(&pd->rt);
		}
		if(pd->wd > 0) {
			pd->wt.fv = &writeDeadlineFn;
			pd->wt.when = pd->wd;
			pd->wt.arg.type = (Type*)pd->seq;
			pd->wt.arg.data = pd;
			runtime·addtimer(&pd->wt);
		}
	}
	// If we set the new deadline in the past, unblock currently pending IO if any.
	rg = nil;
	runtime·atomicstorep(&wg, nil);  // full memory barrier between stores to rd/wd and load of rg/wg in netpollunblock
	if(pd->rd < 0)
		rg = netpollunblock(pd, 'r', false);
	if(pd->wd < 0)
		wg = netpollunblock(pd, 'w', false);
	runtime·unlock(pd);
	if(rg)
		runtime·ready(rg);
	if(wg)
		runtime·ready(wg);
}

func runtime_pollUnblock(pd *PollDesc) {
	G *rg, *wg;

	runtime·lock(pd);
	if(pd->closing)
		runtime·throw("runtime_pollUnblock: already closing");
	pd->closing = true;
	pd->seq++;
	runtime·atomicstorep(&rg, nil);  // full memory barrier between store to closing and read of rg/wg in netpollunblock
	rg = netpollunblock(pd, 'r', false);
	wg = netpollunblock(pd, 'w', false);
	if(pd->rt.fv) {
		runtime·deltimer(&pd->rt);
		pd->rt.fv = nil;
	}
	if(pd->wt.fv) {
		runtime·deltimer(&pd->wt);
		pd->wt.fv = nil;
	}
	runtime·unlock(pd);
	if(rg)
		runtime·ready(rg);
	if(wg)
		runtime·ready(wg);
}

uintptr
runtime·netpollfd(PollDesc *pd)
{
	return pd->fd;
}

void**
runtime·netpolluser(PollDesc *pd)
{
	return &pd->user;
}

// make pd ready, newly runnable goroutines (if any) are enqueued info gpp list
void
runtime·netpollready(G **gpp, PollDesc *pd, int32 mode)
{
	G *rg, *wg;

	rg = wg = nil;
	if(mode == 'r' || mode == 'r'+'w')
		rg = netpollunblock(pd, 'r', true);
	if(mode == 'w' || mode == 'r'+'w')
		wg = netpollunblock(pd, 'w', true);
	if(rg) {
		rg->schedlink = *gpp;
		*gpp = rg;
	}
	if(wg) {
		wg->schedlink = *gpp;
		*gpp = wg;
	}
}

static intgo
checkerr(PollDesc *pd, int32 mode)
{
	if(pd->closing)
		return 1;  // errClosing
	if((mode == 'r' && pd->rd < 0) || (mode == 'w' && pd->wd < 0))
		return 2;  // errTimeout
	return 0;
}

static bool
blockcommit(G *gp, G **gpp)
{
	return runtime·casp(gpp, WAIT, gp);
}

// returns true if IO is ready, or false if timedout or closed
// waitio - wait only for completed IO, ignore errors
static bool
netpollblock(PollDesc *pd, int32 mode, bool waitio)
{
	G **gpp, *old;

	gpp = &pd->rg;
	if(mode == 'w')
		gpp = &pd->wg;

	// set the gpp semaphore to WAIT
	for(;;) {
		old = *gpp;
		if(old == READY) {
			*gpp = nil;
			return true;
		}
		if(old != nil)
			runtime·throw("netpollblock: double wait");
		if(runtime·casp(gpp, nil, WAIT))
			break;
	}

	// need to recheck error states after setting gpp to WAIT
	// this is necessary because runtime_pollUnblock/runtime_pollSetDeadline/deadlineimpl
	// do the opposite: store to closing/rd/wd, membarrier, load of rg/wg
	if(waitio || checkerr(pd, mode) == 0)
		runtime·park((bool(*)(G*, void*))blockcommit, gpp, "IO wait");
	// be careful to not lose concurrent READY notification
	old = runtime·xchgp(gpp, nil);
	if(old > WAIT)
		runtime·throw("netpollblock: corrupted state");
	return old == READY;
}

static G*
netpollunblock(PollDesc *pd, int32 mode, bool ioready)
{
	G **gpp, *old, *new;

	gpp = &pd->rg;
	if(mode == 'w')
		gpp = &pd->wg;

	for(;;) {
		old = *gpp;
		if(old == READY)
			return nil;
		if(old == nil && !ioready) {
			// Only set READY for ioready. runtime_pollWait
			// will check for timeout/cancel before waiting.
			return nil;
		}
		new = nil;
		if(ioready)
			new = READY;
		if(runtime·casp(gpp, old, new))
			break;
	}
	if(old > WAIT)
		return old;  // must be G*
	return nil;
}

static void
deadlineimpl(int64 now, Eface arg, bool read, bool write)
{
	PollDesc *pd;
	uint32 seq;
	G *rg, *wg;

	USED(now);
	pd = (PollDesc*)arg.data;
	// This is the seq when the timer was set.
	// If it's stale, ignore the timer event.
	seq = (uintptr)arg.type;
	rg = wg = nil;
	runtime·lock(pd);
	if(seq != pd->seq) {
		// The descriptor was reused or timers were reset.
		runtime·unlock(pd);
		return;
	}
	if(read) {
		if(pd->rd <= 0 || pd->rt.fv == nil)
			runtime·throw("deadlineimpl: inconsistent read deadline");
		pd->rd = -1;
		runtime·atomicstorep(&pd->rt.fv, nil);  // full memory barrier between store to rd and load of rg in netpollunblock
		rg = netpollunblock(pd, 'r', false);
	}
	if(write) {
		if(pd->wd <= 0 || (pd->wt.fv == nil && !read))
			runtime·throw("deadlineimpl: inconsistent write deadline");
		pd->wd = -1;
		runtime·atomicstorep(&pd->wt.fv, nil);  // full memory barrier between store to wd and load of wg in netpollunblock
		wg = netpollunblock(pd, 'w', false);
	}
	runtime·unlock(pd);
	if(rg)
		runtime·ready(rg);
	if(wg)
		runtime·ready(wg);
}

static void
deadline(int64 now, Eface arg)
{
	deadlineimpl(now, arg, true, true);
}

static void
readDeadline(int64 now, Eface arg)
{
	deadlineimpl(now, arg, true, false);
}

static void
writeDeadline(int64 now, Eface arg)
{
	deadlineimpl(now, arg, false, true);
}

static PollDesc*
allocPollDesc(void)
{
	PollDesc *pd;
	uint32 i, n;

	runtime·lock(&pollcache);
	if(pollcache.first == nil) {
		n = PollBlockSize/sizeof(*pd);
		if(n == 0)
			n = 1;
		// Must be in non-GC memory because can be referenced
		// only from epoll/kqueue internals.
		pd = runtime·persistentalloc(n*sizeof(*pd), 0, &mstats.other_sys);
		for(i = 0; i < n; i++) {
			pd[i].link = pollcache.first;
			pollcache.first = &pd[i];
		}
	}
	pd = pollcache.first;
	pollcache.first = pd->link;
	runtime·unlock(&pollcache);
	return pd;
}