cma.c 12 KB
Newer Older
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
/*
 * Contiguous Memory Allocator
 *
 * Copyright (c) 2010-2011 by Samsung Electronics.
 * Copyright IBM Corporation, 2013
 * Copyright LG Electronics Inc., 2014
 * Written by:
 *	Marek Szyprowski <m.szyprowski@samsung.com>
 *	Michal Nazarewicz <mina86@mina86.com>
 *	Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
 *	Joonsoo Kim <iamjoonsoo.kim@lge.com>
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation; either version 2 of the
 * License or (at your optional) any later version of the license.
 */

#define pr_fmt(fmt) "cma: " fmt

#ifdef CONFIG_CMA_DEBUG
#ifndef DEBUG
#  define DEBUG
#endif
#endif

#include <linux/memblock.h>
#include <linux/err.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/sizes.h>
#include <linux/slab.h>
#include <linux/log2.h>
#include <linux/cma.h>
35
#include <linux/highmem.h>
36
#include <linux/io.h>
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

struct cma {
	unsigned long	base_pfn;
	unsigned long	count;
	unsigned long	*bitmap;
	unsigned int order_per_bit; /* Order of pages represented by one bit */
	struct mutex	lock;
};

static struct cma cma_areas[MAX_CMA_AREAS];
static unsigned cma_area_count;
static DEFINE_MUTEX(cma_mutex);

phys_addr_t cma_get_base(struct cma *cma)
{
	return PFN_PHYS(cma->base_pfn);
}

unsigned long cma_get_size(struct cma *cma)
{
	return cma->count << PAGE_SHIFT;
}

static unsigned long cma_bitmap_aligned_mask(struct cma *cma, int align_order)
{
62 63 64
	if (align_order <= cma->order_per_bit)
		return 0;
	return (1UL << (align_order - cma->order_per_bit)) - 1;
65 66
}

67 68 69 70
/*
 * Find a PFN aligned to the specified order and return an offset represented in
 * order_per_bits.
 */
71 72 73 74
static unsigned long cma_bitmap_aligned_offset(struct cma *cma, int align_order)
{
	if (align_order <= cma->order_per_bit)
		return 0;
75 76 77

	return (ALIGN(cma->base_pfn, (1UL << align_order))
		- cma->base_pfn) >> cma->order_per_bit;
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
static unsigned long cma_bitmap_maxno(struct cma *cma)
{
	return cma->count >> cma->order_per_bit;
}

static unsigned long cma_bitmap_pages_to_bits(struct cma *cma,
						unsigned long pages)
{
	return ALIGN(pages, 1UL << cma->order_per_bit) >> cma->order_per_bit;
}

static void cma_clear_bitmap(struct cma *cma, unsigned long pfn, int count)
{
	unsigned long bitmap_no, bitmap_count;

	bitmap_no = (pfn - cma->base_pfn) >> cma->order_per_bit;
	bitmap_count = cma_bitmap_pages_to_bits(cma, count);

	mutex_lock(&cma->lock);
	bitmap_clear(cma->bitmap, bitmap_no, bitmap_count);
	mutex_unlock(&cma->lock);
}

static int __init cma_activate_area(struct cma *cma)
{
	int bitmap_size = BITS_TO_LONGS(cma_bitmap_maxno(cma)) * sizeof(long);
	unsigned long base_pfn = cma->base_pfn, pfn = base_pfn;
	unsigned i = cma->count >> pageblock_order;
	struct zone *zone;

	cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL);

	if (!cma->bitmap)
		return -ENOMEM;

	WARN_ON_ONCE(!pfn_valid(pfn));
	zone = page_zone(pfn_to_page(pfn));

	do {
		unsigned j;

		base_pfn = pfn;
		for (j = pageblock_nr_pages; j; --j, pfn++) {
			WARN_ON_ONCE(!pfn_valid(pfn));
			/*
			 * alloc_contig_range requires the pfn range
			 * specified to be in the same zone. Make this
			 * simple by forcing the entire CMA resv range
			 * to be in the same zone.
			 */
			if (page_zone(pfn_to_page(pfn)) != zone)
				goto err;
		}
		init_cma_reserved_pageblock(pfn_to_page(base_pfn));
	} while (--i);

	mutex_init(&cma->lock);
	return 0;

err:
	kfree(cma->bitmap);
141
	cma->count = 0;
142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159
	return -EINVAL;
}

static int __init cma_init_reserved_areas(void)
{
	int i;

	for (i = 0; i < cma_area_count; i++) {
		int ret = cma_activate_area(&cma_areas[i]);

		if (ret)
			return ret;
	}

	return 0;
}
core_initcall(cma_init_reserved_areas);

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
/**
 * cma_init_reserved_mem() - create custom contiguous area from reserved memory
 * @base: Base address of the reserved area
 * @size: Size of the reserved area (in bytes),
 * @order_per_bit: Order of pages represented by one bit on bitmap.
 * @res_cma: Pointer to store the created cma region.
 *
 * This function creates custom contiguous area from already reserved memory.
 */
int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size,
				 int order_per_bit, struct cma **res_cma)
{
	struct cma *cma;
	phys_addr_t alignment;

	/* Sanity checks */
	if (cma_area_count == ARRAY_SIZE(cma_areas)) {
		pr_err("Not enough slots for CMA reserved regions!\n");
		return -ENOSPC;
	}

	if (!size || !memblock_is_region_reserved(base, size))
		return -EINVAL;

	/* ensure minimal alignment requied by mm core */
	alignment = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order);

	/* alignment should be aligned with order_per_bit */
	if (!IS_ALIGNED(alignment >> PAGE_SHIFT, 1 << order_per_bit))
		return -EINVAL;

	if (ALIGN(base, alignment) != base || ALIGN(size, alignment) != size)
		return -EINVAL;

	/*
	 * Each reserved area must be initialised later, when more kernel
	 * subsystems (like slab allocator) are available.
	 */
	cma = &cma_areas[cma_area_count];
	cma->base_pfn = PFN_DOWN(base);
	cma->count = size >> PAGE_SHIFT;
	cma->order_per_bit = order_per_bit;
	*res_cma = cma;
	cma_area_count++;
204
	totalcma_pages += (size / PAGE_SIZE);
205 206 207 208

	return 0;
}

209 210 211
/**
 * cma_declare_contiguous() - reserve custom contiguous area
 * @base: Base address of the reserved area optional, use 0 for any
212
 * @size: Size of the reserved area (in bytes),
213 214 215 216
 * @limit: End address of the reserved memory (optional, 0 for any).
 * @alignment: Alignment for the CMA area, should be power of 2 or zero
 * @order_per_bit: Order of pages represented by one bit on bitmap.
 * @fixed: hint about where to place the reserved area
217
 * @res_cma: Pointer to store the created cma region.
218 219 220 221 222 223 224 225 226
 *
 * This function reserves memory from early allocator. It should be
 * called by arch specific code once the early allocator (memblock or bootmem)
 * has been activated and all other subsystems have already allocated/reserved
 * memory. This function allows to create custom reserved areas.
 *
 * If @fixed is true, reserve contiguous area at exactly @base.  If false,
 * reserve in range from @base to @limit.
 */
227 228
int __init cma_declare_contiguous(phys_addr_t base,
			phys_addr_t size, phys_addr_t limit,
229
			phys_addr_t alignment, unsigned int order_per_bit,
230
			bool fixed, struct cma **res_cma)
231
{
232
	phys_addr_t memblock_end = memblock_end_of_DRAM();
233
	phys_addr_t highmem_start;
234 235
	int ret = 0;

236 237 238 239 240 241 242 243 244 245 246 247
#ifdef CONFIG_X86
	/*
	 * high_memory isn't direct mapped memory so retrieving its physical
	 * address isn't appropriate.  But it would be useful to check the
	 * physical address of the highmem boundary so it's justfiable to get
	 * the physical address from it.  On x86 there is a validation check for
	 * this case, so the following workaround is needed to avoid it.
	 */
	highmem_start = __pa_nodebug(high_memory);
#else
	highmem_start = __pa(high_memory);
#endif
248 249
	pr_debug("%s(size %pa, base %pa, limit %pa alignment %pa)\n",
		__func__, &size, &base, &limit, &alignment);
250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273

	if (cma_area_count == ARRAY_SIZE(cma_areas)) {
		pr_err("Not enough slots for CMA reserved regions!\n");
		return -ENOSPC;
	}

	if (!size)
		return -EINVAL;

	if (alignment && !is_power_of_2(alignment))
		return -EINVAL;

	/*
	 * Sanitise input arguments.
	 * Pages both ends in CMA area could be merged into adjacent unmovable
	 * migratetype page by page allocator's buddy algorithm. In the case,
	 * you couldn't get a contiguous memory, which is not what we want.
	 */
	alignment = max(alignment,
		(phys_addr_t)PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order));
	base = ALIGN(base, alignment);
	size = ALIGN(size, alignment);
	limit &= ~(alignment - 1);

274 275 276
	if (!base)
		fixed = false;

277 278 279 280
	/* size should be aligned with order_per_bit */
	if (!IS_ALIGNED(size >> PAGE_SHIFT, 1 << order_per_bit))
		return -EINVAL;

281
	/*
282 283
	 * If allocating at a fixed base the request region must not cross the
	 * low/high memory boundary.
284
	 */
285
	if (fixed && base < highmem_start && base + size > highmem_start) {
286
		ret = -EINVAL;
287 288
		pr_err("Region at %pa defined on low/high memory boundary (%pa)\n",
			&base, &highmem_start);
289 290 291
		goto err;
	}

292 293 294 295 296 297 298 299
	/*
	 * If the limit is unspecified or above the memblock end, its effective
	 * value will be the memblock end. Set it explicitly to simplify further
	 * checks.
	 */
	if (limit == 0 || limit > memblock_end)
		limit = memblock_end;

300
	/* Reserve memory */
301
	if (fixed) {
302 303 304 305 306 307
		if (memblock_is_region_reserved(base, size) ||
		    memblock_reserve(base, size) < 0) {
			ret = -EBUSY;
			goto err;
		}
	} else {
308 309 310 311 312 313 314 315 316 317 318 319 320 321
		phys_addr_t addr = 0;

		/*
		 * All pages in the reserved area must come from the same zone.
		 * If the requested region crosses the low/high memory boundary,
		 * try allocating from high memory first and fall back to low
		 * memory in case of failure.
		 */
		if (base < highmem_start && limit > highmem_start) {
			addr = memblock_alloc_range(size, alignment,
						    highmem_start, limit);
			limit = highmem_start;
		}

322
		if (!addr) {
323 324 325 326 327 328
			addr = memblock_alloc_range(size, alignment, base,
						    limit);
			if (!addr) {
				ret = -ENOMEM;
				goto err;
			}
329
		}
330

331 332 333 334 335
		/*
		 * kmemleak scans/reads tracked objects for pointers to other
		 * objects but this address isn't mapped and accessible
		 */
		kmemleak_ignore(phys_to_virt(addr));
336
		base = addr;
337 338
	}

339 340 341
	ret = cma_init_reserved_mem(base, size, order_per_bit, res_cma);
	if (ret)
		goto err;
342

343 344
	pr_info("Reserved %ld MiB at %pa\n", (unsigned long)size / SZ_1M,
		&base);
345 346 347
	return 0;

err:
Joonsoo Kim's avatar
Joonsoo Kim committed
348
	pr_err("Failed to reserve %ld MiB\n", (unsigned long)size / SZ_1M);
349 350 351 352 353 354 355 356 357 358 359 360 361 362
	return ret;
}

/**
 * cma_alloc() - allocate pages from contiguous area
 * @cma:   Contiguous memory region for which the allocation is performed.
 * @count: Requested number of pages.
 * @align: Requested alignment of pages (in PAGE_SIZE order).
 *
 * This function allocates part of contiguous memory on specific
 * contiguous memory area.
 */
struct page *cma_alloc(struct cma *cma, int count, unsigned int align)
{
363
	unsigned long mask, offset, pfn, start = 0;
364 365 366 367 368 369 370 371 372 373 374 375 376 377
	unsigned long bitmap_maxno, bitmap_no, bitmap_count;
	struct page *page = NULL;
	int ret;

	if (!cma || !cma->count)
		return NULL;

	pr_debug("%s(cma %p, count %d, align %d)\n", __func__, (void *)cma,
		 count, align);

	if (!count)
		return NULL;

	mask = cma_bitmap_aligned_mask(cma, align);
378
	offset = cma_bitmap_aligned_offset(cma, align);
379 380 381 382 383
	bitmap_maxno = cma_bitmap_maxno(cma);
	bitmap_count = cma_bitmap_pages_to_bits(cma, count);

	for (;;) {
		mutex_lock(&cma->lock);
384 385 386
		bitmap_no = bitmap_find_next_zero_area_off(cma->bitmap,
				bitmap_maxno, start, bitmap_count, mask,
				offset);
387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406
		if (bitmap_no >= bitmap_maxno) {
			mutex_unlock(&cma->lock);
			break;
		}
		bitmap_set(cma->bitmap, bitmap_no, bitmap_count);
		/*
		 * It's safe to drop the lock here. We've marked this region for
		 * our exclusive use. If the migration fails we will take the
		 * lock again and unmark it.
		 */
		mutex_unlock(&cma->lock);

		pfn = cma->base_pfn + (bitmap_no << cma->order_per_bit);
		mutex_lock(&cma_mutex);
		ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA);
		mutex_unlock(&cma_mutex);
		if (ret == 0) {
			page = pfn_to_page(pfn);
			break;
		}
407

408
		cma_clear_bitmap(cma, pfn, count);
409 410 411
		if (ret != -EBUSY)
			break;

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
		pr_debug("%s(): memory range at %p is busy, retrying\n",
			 __func__, pfn_to_page(pfn));
		/* try again with a bit different memory target */
		start = bitmap_no + mask + 1;
	}

	pr_debug("%s(): returned %p\n", __func__, page);
	return page;
}

/**
 * cma_release() - release allocated pages
 * @cma:   Contiguous memory region for which the allocation is performed.
 * @pages: Allocated pages.
 * @count: Number of allocated pages.
 *
 * This function releases memory allocated by alloc_cma().
 * It returns false when provided pages do not belong to contiguous area and
 * true otherwise.
 */
bool cma_release(struct cma *cma, struct page *pages, int count)
{
	unsigned long pfn;

	if (!cma || !pages)
		return false;

	pr_debug("%s(page %p)\n", __func__, (void *)pages);

	pfn = page_to_pfn(pages);

	if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count)
		return false;

	VM_BUG_ON(pfn + count > cma->base_pfn + cma->count);

	free_contig_range(pfn, count);
	cma_clear_bitmap(cma, pfn, count);

	return true;
}