summaryrefslogtreecommitdiffstats
path: root/sys/kern/kern_malloc.c
blob: 3d6307a14dc1def6ac8ac0293552c291c754cfcd (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
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
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
/*
 * Copyright (c) 1987, 1991, 1993
 *	The Regents of the University of California.  All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. All advertising materials mentioning features or use of this software
 *    must display the following acknowledgement:
 *	This product includes software developed by the University of
 *	California, Berkeley and its contributors.
 * 4. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 *
 *	@(#)kern_malloc.c	8.3 (Berkeley) 1/4/94
 * $FreeBSD$
 */

#include "opt_vm.h"

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/mutex.h>
#include <sys/vmmeter.h>
#include <sys/proc.h>
#include <sys/sysctl.h>

#include <vm/vm.h>
#include <vm/pmap.h>
#include <vm/vm_param.h>
#include <vm/vm_kern.h>
#include <vm/vm_extern.h>
#include <vm/vm_map.h>
#include <vm/vm_page.h>
#include <vm/uma.h>
#include <vm/uma_int.h>
#include <vm/uma_dbg.h>

#if defined(INVARIANTS) && defined(__i386__)
#include <machine/cpu.h>
#endif

/*
 * When realloc() is called, if the new size is sufficiently smaller than
 * the old size, realloc() will allocate a new, smaller block to avoid
 * wasting memory. 'Sufficiently smaller' is defined as: newsize <=
 * oldsize / 2^n, where REALLOC_FRACTION defines the value of 'n'.
 */
#ifndef REALLOC_FRACTION
#define	REALLOC_FRACTION	1	/* new block if <= half the size */
#endif

MALLOC_DEFINE(M_CACHE, "cache", "Various Dynamically allocated caches");
MALLOC_DEFINE(M_DEVBUF, "devbuf", "device driver memory");
MALLOC_DEFINE(M_TEMP, "temp", "misc temporary data buffers");

MALLOC_DEFINE(M_IP6OPT, "ip6opt", "IPv6 options");
MALLOC_DEFINE(M_IP6NDP, "ip6ndp", "IPv6 Neighbor Discovery");

static void kmeminit(void *);
SYSINIT(kmem, SI_SUB_KMEM, SI_ORDER_FIRST, kmeminit, NULL)

static MALLOC_DEFINE(M_FREE, "free", "should be on free list");

static struct malloc_type *kmemstatistics;
static char *kmembase;
static char *kmemlimit;

#define KMEM_ZSHIFT	4
#define KMEM_ZBASE	16
#define KMEM_ZMASK	(KMEM_ZBASE - 1)

#define KMEM_ZMAX	65536
#define KMEM_ZSIZE	(KMEM_ZMAX >> KMEM_ZSHIFT)
static u_int8_t kmemsize[KMEM_ZSIZE + 1];

/* These won't be powers of two for long */
struct {
	int kz_size;
	char *kz_name;
	uma_zone_t kz_zone;
} kmemzones[] = {
	{16, "16", NULL},
	{32, "32", NULL},
	{64, "64", NULL},
	{128, "128", NULL},
	{256, "256", NULL},
	{512, "512", NULL},
	{1024, "1024", NULL},
	{2048, "2048", NULL},
	{4096, "4096", NULL},
	{8192, "8192", NULL},
	{16384, "16384", NULL},
	{32768, "32768", NULL},
	{65536, "65536", NULL},
	{0, NULL},
};

u_int vm_kmem_size;

/*
 * The malloc_mtx protects the kmemstatistics linked list.
 */

struct mtx malloc_mtx;

#ifdef MALLOC_PROFILE
uint64_t krequests[KMEM_ZSIZE + 1];

static int sysctl_kern_mprof(SYSCTL_HANDLER_ARGS);
#endif

static int sysctl_kern_malloc(SYSCTL_HANDLER_ARGS);

/*
 *	malloc:
 *
 *	Allocate a block of memory.
 *
 *	If M_NOWAIT is set, this routine will not block and return NULL if
 *	the allocation fails.
 */
void *
malloc(size, type, flags)
	unsigned long size;
	struct malloc_type *type;
	int flags;
{
	int indx;
	caddr_t va;
	uma_zone_t zone;
	register struct malloc_type *ksp = type;

#if 0
	if (size == 0)
		Debugger("zero size malloc");
#endif
	if (!(flags & M_NOWAIT))
		KASSERT(curthread->td_intr_nesting_level == 0,
		   ("malloc(M_WAITOK) in interrupt context"));
	if (size <= KMEM_ZMAX) {
		if (size & KMEM_ZMASK)
			size = (size & ~KMEM_ZMASK) + KMEM_ZBASE;
		indx = kmemsize[size >> KMEM_ZSHIFT];
		zone = kmemzones[indx].kz_zone;
#ifdef MALLOC_PROFILE
		krequests[size >> KMEM_ZSHIFT]++;
#endif
		va = uma_zalloc(zone, flags);
		mtx_lock(&ksp->ks_mtx);
		if (va == NULL) 
			goto out;

		ksp->ks_size |= 1 << indx;
		size = zone->uz_size;
	} else {
		size = roundup(size, PAGE_SIZE);
		zone = NULL;
		va = uma_large_malloc(size, flags);
		mtx_lock(&ksp->ks_mtx);
		if (va == NULL)
			goto out;
	}
	ksp->ks_memuse += size;
	ksp->ks_inuse++;
out:
	ksp->ks_calls++;
	if (ksp->ks_memuse > ksp->ks_maxused)
		ksp->ks_maxused = ksp->ks_memuse;

	mtx_unlock(&ksp->ks_mtx);
	return ((void *) va);
}

/*
 *	free:
 *
 *	Free a block of memory allocated by malloc.
 *
 *	This routine may not block.
 */
void
free(addr, type)
	void *addr;
	struct malloc_type *type;
{
	register struct malloc_type *ksp = type;
	uma_slab_t slab;
	u_long size;

	/* free(NULL, ...) does nothing */
	if (addr == NULL)
		return;

	size = 0;

	slab = vtoslab((vm_offset_t)addr & (~UMA_SLAB_MASK));

	if (slab == NULL)
		panic("free: address %p(%p) has not been allocated.\n",
		    addr, (void *)((u_long)addr & (~UMA_SLAB_MASK)));


	if (!(slab->us_flags & UMA_SLAB_MALLOC)) {
#ifdef INVARIANTS
		struct malloc_type **mtp = addr;
#endif
		size = slab->us_zone->uz_size;
#ifdef INVARIANTS
		/*
		 * Cache a pointer to the malloc_type that most recently freed
		 * this memory here.  This way we know who is most likely to
		 * have stepped on it later.
		 *
		 * This code assumes that size is a multiple of 8 bytes for
		 * 64 bit machines
		 */
		mtp = (struct malloc_type **)
		    ((unsigned long)mtp & ~UMA_ALIGN_PTR);
		mtp += (size - sizeof(struct malloc_type *)) /
		    sizeof(struct malloc_type *);
		*mtp = type;
#endif
		uma_zfree_arg(slab->us_zone, addr, slab);
	} else {
		size = slab->us_size;
		uma_large_free(slab);
	}
	mtx_lock(&ksp->ks_mtx);
	ksp->ks_memuse -= size;
	ksp->ks_inuse--;
	mtx_unlock(&ksp->ks_mtx);
}

/*
 *	realloc: change the size of a memory block
 */
void *
realloc(addr, size, type, flags)
	void *addr;
	unsigned long size;
	struct malloc_type *type;
	int flags;
{
	uma_slab_t slab;
	unsigned long alloc;
	void *newaddr;

	/* realloc(NULL, ...) is equivalent to malloc(...) */
	if (addr == NULL)
		return (malloc(size, type, flags));

	slab = vtoslab((vm_offset_t)addr & ~(UMA_SLAB_MASK));

	/* Sanity check */
	KASSERT(slab != NULL,
	    ("realloc: address %p out of range", (void *)addr));

	/* Get the size of the original block */
	if (slab->us_zone)
		alloc = slab->us_zone->uz_size;
	else
		alloc = slab->us_size;

	/* Reuse the original block if appropriate */
	if (size <= alloc
	    && (size > (alloc >> REALLOC_FRACTION) || alloc == MINALLOCSIZE))
		return (addr);

	/* Allocate a new, bigger (or smaller) block */
	if ((newaddr = malloc(size, type, flags)) == NULL)
		return (NULL);

	/* Copy over original contents */
	bcopy(addr, newaddr, min(size, alloc));
	free(addr, type);
	return (newaddr);
}

/*
 *	reallocf: same as realloc() but free memory on failure.
 */
void *
reallocf(addr, size, type, flags)
	void *addr;
	unsigned long size;
	struct malloc_type *type;
	int flags;
{
	void *mem;

	if ((mem = realloc(addr, size, type, flags)) == NULL)
		free(addr, type);
	return (mem);
}

/*
 * Initialize the kernel memory allocator
 */
/* ARGSUSED*/
static void
kmeminit(dummy)
	void *dummy;
{
	u_int8_t indx;
	u_long npg;
	u_long mem_size;
	int i;
 
	mtx_init(&malloc_mtx, "malloc", NULL, MTX_DEF);

	/*
	 * Try to auto-tune the kernel memory size, so that it is
	 * more applicable for a wider range of machine sizes.
	 * On an X86, a VM_KMEM_SIZE_SCALE value of 4 is good, while
	 * a VM_KMEM_SIZE of 12MB is a fair compromise.  The
	 * VM_KMEM_SIZE_MAX is dependent on the maximum KVA space
	 * available, and on an X86 with a total KVA space of 256MB,
	 * try to keep VM_KMEM_SIZE_MAX at 80MB or below.
	 *
	 * Note that the kmem_map is also used by the zone allocator,
	 * so make sure that there is enough space.
	 */
	vm_kmem_size = VM_KMEM_SIZE;
	mem_size = cnt.v_page_count * PAGE_SIZE;

#if defined(VM_KMEM_SIZE_SCALE)
	if ((mem_size / VM_KMEM_SIZE_SCALE) > vm_kmem_size)
		vm_kmem_size = mem_size / VM_KMEM_SIZE_SCALE;
#endif

#if defined(VM_KMEM_SIZE_MAX)
	if (vm_kmem_size >= VM_KMEM_SIZE_MAX)
		vm_kmem_size = VM_KMEM_SIZE_MAX;
#endif

	/* Allow final override from the kernel environment */
	TUNABLE_INT_FETCH("kern.vm.kmem.size", &vm_kmem_size);

	/*
	 * Limit kmem virtual size to twice the physical memory.
	 * This allows for kmem map sparseness, but limits the size
	 * to something sane. Be careful to not overflow the 32bit
	 * ints while doing the check.
	 */
	if ((vm_kmem_size / 2) > (cnt.v_page_count * PAGE_SIZE))
		vm_kmem_size = 2 * cnt.v_page_count * PAGE_SIZE;

	/*
	 * In mbuf_init(), we set up submaps for mbufs and clusters, in which
	 * case we rounddown() (nmbufs * MSIZE) and (nmbclusters * MCLBYTES),
	 * respectively. Mathematically, this means that what we do here may
	 * amount to slightly more address space than we need for the submaps,
	 * but it never hurts to have an extra page in kmem_map.
	 */
	npg = (nmbufs * MSIZE + nmbclusters * MCLBYTES + nmbcnt *
	    sizeof(u_int) + vm_kmem_size) / PAGE_SIZE;

	kmem_map = kmem_suballoc(kernel_map, (vm_offset_t *)&kmembase,
		(vm_offset_t *)&kmemlimit, (vm_size_t)(npg * PAGE_SIZE));
	kmem_map->system_map = 1;

	uma_startup2();

	for (i = 0, indx = 0; kmemzones[indx].kz_size != 0; indx++) {
		int size = kmemzones[indx].kz_size;
		char *name = kmemzones[indx].kz_name;

		kmemzones[indx].kz_zone = uma_zcreate(name, size,
#ifdef INVARIANTS
		    mtrash_ctor, mtrash_dtor, mtrash_init, mtrash_fini,
#else
		    NULL, NULL, NULL, NULL,
#endif
		    UMA_ALIGN_PTR, UMA_ZONE_MALLOC);
		    
		for (;i <= size; i+= KMEM_ZBASE)
			kmemsize[i >> KMEM_ZSHIFT] = indx;
		
	}
}

void
malloc_init(data)
	void *data;
{
	struct malloc_type *type = (struct malloc_type *)data;

	mtx_lock(&malloc_mtx);
	if (type->ks_magic != M_MAGIC)
		panic("malloc type lacks magic");

	if (cnt.v_page_count == 0)
		panic("malloc_init not allowed before vm init");

	if (type->ks_next != NULL)
		return;

	type->ks_next = kmemstatistics;	
	kmemstatistics = type;
	mtx_init(&type->ks_mtx, type->ks_shortdesc, "Malloc Stats", MTX_DEF);
	mtx_unlock(&malloc_mtx);
}

void
malloc_uninit(data)
	void *data;
{
	struct malloc_type *type = (struct malloc_type *)data;
	struct malloc_type *t;

	mtx_lock(&malloc_mtx);
	mtx_lock(&type->ks_mtx);
	if (type->ks_magic != M_MAGIC)
		panic("malloc type lacks magic");

	if (cnt.v_page_count == 0)
		panic("malloc_uninit not allowed before vm init");

	if (type == kmemstatistics)
		kmemstatistics = type->ks_next;
	else {
		for (t = kmemstatistics; t->ks_next != NULL; t = t->ks_next) {
			if (t->ks_next == type) {
				t->ks_next = type->ks_next;
				break;
			}
		}
	}
	type->ks_next = NULL;
	mtx_destroy(&type->ks_mtx);
	mtx_unlock(&malloc_mtx);
}

static int
sysctl_kern_malloc(SYSCTL_HANDLER_ARGS)
{
	struct malloc_type *type;
	int linesize = 128;
	int curline;
	int bufsize;
	int first;
	int error;
	char *buf;
	char *p;
	int cnt;
	int len;
	int i;

	cnt = 0;

	mtx_lock(&malloc_mtx);
	for (type = kmemstatistics; type != NULL; type = type->ks_next)
		cnt++;

	mtx_unlock(&malloc_mtx);
	bufsize = linesize * (cnt + 1);
	p = buf = (char *)malloc(bufsize, M_TEMP, M_WAITOK|M_ZERO);
	mtx_lock(&malloc_mtx);

	len = snprintf(p, linesize,
	    "\n        Type  InUse MemUse HighUse Requests  Size(s)\n");
	p += len;

	for (type = kmemstatistics; cnt != 0 && type != NULL;
	    type = type->ks_next, cnt--) {
		if (type->ks_calls == 0)
			continue;

		curline = linesize - 2;	/* Leave room for the \n */
		len = snprintf(p, curline, "%13s%6lu%6luK%7luK%9llu",
			type->ks_shortdesc,
			type->ks_inuse,
			(type->ks_memuse + 1023) / 1024,
			(type->ks_maxused + 1023) / 1024,
			(long long unsigned)type->ks_calls);
		curline -= len;
		p += len;

		first = 1;
		for (i = 0; i < sizeof(kmemzones) / sizeof(kmemzones[0]) - 1;
		    i++) {
			if (type->ks_size & (1 << i)) {
				if (first)
					len = snprintf(p, curline, "  ");
				else
					len = snprintf(p, curline, ",");
				curline -= len;
				p += len;

				len = snprintf(p, curline,
				    "%s", kmemzones[i].kz_name);
				curline -= len;
				p += len;

				first = 0;
			}
		}

		len = snprintf(p, 2, "\n");
		p += len;
	}

	mtx_unlock(&malloc_mtx);
	error = SYSCTL_OUT(req, buf, p - buf);

	free(buf, M_TEMP);
	return (error);
}

SYSCTL_OID(_kern, OID_AUTO, malloc, CTLTYPE_STRING|CTLFLAG_RD,
    NULL, 0, sysctl_kern_malloc, "A", "Malloc Stats");

#ifdef MALLOC_PROFILE

static int
sysctl_kern_mprof(SYSCTL_HANDLER_ARGS)
{
	int linesize = 64;
	uint64_t count;
	uint64_t waste;
	uint64_t mem;
	int bufsize;
	int error;
	char *buf;
	int rsize;
	int size;
	char *p;
	int len;
	int i;

	bufsize = linesize * (KMEM_ZSIZE + 1);
	bufsize += 128; 	/* For the stats line */
	bufsize += 128; 	/* For the banner line */
	waste = 0;
	mem = 0;

	p = buf = (char *)malloc(bufsize, M_TEMP, M_WAITOK|M_ZERO);
	len = snprintf(p, bufsize,
	    "\n  Size                    Requests  Real Size\n");
	bufsize -= len;
	p += len;

	for (i = 0; i < KMEM_ZSIZE; i++) {
		size = i << KMEM_ZSHIFT;
		rsize = kmemzones[kmemsize[i]].kz_size;
		count = (long long unsigned)krequests[i];

		len = snprintf(p, bufsize, "%6d%28llu%11d\n",
		    size, (unsigned long long)count, rsize);
		bufsize -= len;
		p += len;

		if ((rsize * count) > (size * count))
			waste += (rsize * count) - (size * count);
		mem += (rsize * count);
	}

	len = snprintf(p, bufsize,
	    "\nTotal memory used:\t%30llu\nTotal Memory wasted:\t%30llu\n",
	    (unsigned long long)mem, (unsigned long long)waste);
	p += len;

	error = SYSCTL_OUT(req, buf, p - buf);

	free(buf, M_TEMP);
	return (error);
}

SYSCTL_OID(_kern, OID_AUTO, mprof, CTLTYPE_STRING|CTLFLAG_RD,
    NULL, 0, sysctl_kern_mprof, "A", "Malloc Profiling");
#endif /* MALLOC_PROFILE */
OpenPOWER on IntegriCloud