binder_alloc.c 28.1 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
/* binder_alloc.c
 *
 * Android IPC Subsystem
 *
 * Copyright (C) 2007-2017 Google, Inc.
 *
 * This software is licensed under the terms of the GNU General Public
 * License version 2, as published by the Free Software Foundation, and
 * may be copied, distributed, and modified under those terms.
 *
 * This program is distributed in the hope that 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.
 *
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/list.h>
#include <linux/sched/mm.h>
#include <linux/module.h>
#include <linux/rtmutex.h>
#include <linux/rbtree.h>
#include <linux/seq_file.h>
#include <linux/vmalloc.h>
#include <linux/slab.h>
#include <linux/sched.h>
29
#include <linux/list_lru.h>
30
#include <linux/ratelimit.h>
31
#include <asm/cacheflush.h>
32 33 34
#include "binder_alloc.h"
#include "binder_trace.h"

35 36
struct list_lru binder_alloc_lru;

37 38 39
static DEFINE_MUTEX(binder_alloc_mmap_lock);

enum {
40
	BINDER_DEBUG_USER_ERROR             = 1U << 0,
41 42 43 44
	BINDER_DEBUG_OPEN_CLOSE             = 1U << 1,
	BINDER_DEBUG_BUFFER_ALLOC           = 1U << 2,
	BINDER_DEBUG_BUFFER_ALLOC_ASYNC     = 1U << 3,
};
45
static uint32_t binder_alloc_debug_mask = BINDER_DEBUG_USER_ERROR;
46 47 48 49 50 51 52

module_param_named(debug_mask, binder_alloc_debug_mask,
		   uint, 0644);

#define binder_alloc_debug(mask, x...) \
	do { \
		if (binder_alloc_debug_mask & mask) \
53
			pr_info_ratelimited(x); \
54 55
	} while (0)

56 57 58 59 60 61 62 63 64 65
static struct binder_buffer *binder_buffer_next(struct binder_buffer *buffer)
{
	return list_entry(buffer->entry.next, struct binder_buffer, entry);
}

static struct binder_buffer *binder_buffer_prev(struct binder_buffer *buffer)
{
	return list_entry(buffer->entry.prev, struct binder_buffer, entry);
}

66 67 68 69
static size_t binder_alloc_buffer_size(struct binder_alloc *alloc,
				       struct binder_buffer *buffer)
{
	if (list_is_last(&buffer->entry, &alloc->buffers))
70 71 72
		return (u8 *)alloc->buffer +
			alloc->buffer_size - (u8 *)buffer->data;
	return (u8 *)binder_buffer_next(buffer)->data - (u8 *)buffer->data;
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
}

static void binder_insert_free_buffer(struct binder_alloc *alloc,
				      struct binder_buffer *new_buffer)
{
	struct rb_node **p = &alloc->free_buffers.rb_node;
	struct rb_node *parent = NULL;
	struct binder_buffer *buffer;
	size_t buffer_size;
	size_t new_buffer_size;

	BUG_ON(!new_buffer->free);

	new_buffer_size = binder_alloc_buffer_size(alloc, new_buffer);

	binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
		     "%d: add free buffer, size %zd, at %pK\n",
		      alloc->pid, new_buffer_size, new_buffer);

	while (*p) {
		parent = *p;
		buffer = rb_entry(parent, struct binder_buffer, rb_node);
		BUG_ON(!buffer->free);

		buffer_size = binder_alloc_buffer_size(alloc, buffer);

		if (new_buffer_size < buffer_size)
			p = &parent->rb_left;
		else
			p = &parent->rb_right;
	}
	rb_link_node(&new_buffer->rb_node, parent, p);
	rb_insert_color(&new_buffer->rb_node, &alloc->free_buffers);
}

static void binder_insert_allocated_buffer_locked(
		struct binder_alloc *alloc, struct binder_buffer *new_buffer)
{
	struct rb_node **p = &alloc->allocated_buffers.rb_node;
	struct rb_node *parent = NULL;
	struct binder_buffer *buffer;

	BUG_ON(new_buffer->free);

	while (*p) {
		parent = *p;
		buffer = rb_entry(parent, struct binder_buffer, rb_node);
		BUG_ON(buffer->free);

122
		if (new_buffer->data < buffer->data)
123
			p = &parent->rb_left;
124
		else if (new_buffer->data > buffer->data)
125 126 127 128 129 130 131 132
			p = &parent->rb_right;
		else
			BUG();
	}
	rb_link_node(&new_buffer->rb_node, parent, p);
	rb_insert_color(&new_buffer->rb_node, &alloc->allocated_buffers);
}

133
static struct binder_buffer *binder_alloc_prepare_to_free_locked(
134 135 136 137 138
		struct binder_alloc *alloc,
		uintptr_t user_ptr)
{
	struct rb_node *n = alloc->allocated_buffers.rb_node;
	struct binder_buffer *buffer;
139
	void *kern_ptr;
140

141
	kern_ptr = (void *)(user_ptr - alloc->user_buffer_offset);
142 143 144 145 146

	while (n) {
		buffer = rb_entry(n, struct binder_buffer, rb_node);
		BUG_ON(buffer->free);

147
		if (kern_ptr < buffer->data)
148
			n = n->rb_left;
149
		else if (kern_ptr > buffer->data)
150
			n = n->rb_right;
151 152 153
		else {
			/*
			 * Guard against user threads attempting to
154 155
			 * free the buffer when in use by kernel or
			 * after it's already been freed.
156
			 */
157 158 159
			if (!buffer->allow_user_free)
				return ERR_PTR(-EPERM);
			buffer->allow_user_free = 0;
160
			return buffer;
161
		}
162 163 164 165 166 167 168 169 170 171 172 173 174 175 176
	}
	return NULL;
}

/**
 * binder_alloc_buffer_lookup() - get buffer given user ptr
 * @alloc:	binder_alloc for this proc
 * @user_ptr:	User pointer to buffer data
 *
 * Validate userspace pointer to buffer data and return buffer corresponding to
 * that user pointer. Search the rb tree for buffer that matches user data
 * pointer.
 *
 * Return:	Pointer to buffer or NULL
 */
177 178
struct binder_buffer *binder_alloc_prepare_to_free(struct binder_alloc *alloc,
						   uintptr_t user_ptr)
179 180 181 182
{
	struct binder_buffer *buffer;

	mutex_lock(&alloc->mutex);
183
	buffer = binder_alloc_prepare_to_free_locked(alloc, user_ptr);
184 185 186 187 188
	mutex_unlock(&alloc->mutex);
	return buffer;
}

static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
189
				    void *start, void *end)
190 191 192
{
	void *page_addr;
	unsigned long user_page_addr;
193
	struct binder_lru_page *page;
194
	struct vm_area_struct *vma = NULL;
195 196
	struct mm_struct *mm = NULL;
	bool need_mm = false;
197 198 199 200 201 202 203 204 205 206

	binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
		     "%d: %s pages %pK-%pK\n", alloc->pid,
		     allocate ? "allocate" : "free", start, end);

	if (end <= start)
		return 0;

	trace_binder_update_page_range(alloc, allocate, start, end);

207 208 209 210 211 212 213 214 215 216 217
	if (allocate == 0)
		goto free_range;

	for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
		page = &alloc->pages[(page_addr - alloc->buffer) / PAGE_SIZE];
		if (!page->page_ptr) {
			need_mm = true;
			break;
		}
	}

218
	if (need_mm && mmget_not_zero(alloc->vma_vm_mm))
219
		mm = alloc->vma_vm_mm;
220 221

	if (mm) {
222
		down_read(&mm->mmap_sem);
223 224 225
		vma = alloc->vma;
	}

226
	if (!vma && need_mm) {
227 228 229
		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
				   "%d: binder_alloc_buf failed to map pages in userspace, no vma\n",
				   alloc->pid);
230 231 232 233 234
		goto err_no_vma;
	}

	for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
		int ret;
235
		bool on_lru;
236
		size_t index;
237

238 239
		index = (page_addr - alloc->buffer) / PAGE_SIZE;
		page = &alloc->pages[index];
240

241
		if (page->page_ptr) {
242 243
			trace_binder_alloc_lru_start(alloc, index);

244 245
			on_lru = list_lru_del(&binder_alloc_lru, &page->lru);
			WARN_ON(!on_lru);
246 247

			trace_binder_alloc_lru_end(alloc, index);
248 249 250 251 252 253
			continue;
		}

		if (WARN_ON(!vma))
			goto err_page_ptr_cleared;

254
		trace_binder_alloc_page_start(alloc, index);
255 256 257 258
		page->page_ptr = alloc_page(GFP_KERNEL |
					    __GFP_HIGHMEM |
					    __GFP_ZERO);
		if (!page->page_ptr) {
259 260 261 262
			pr_err("%d: binder_alloc_buf failed for page at %pK\n",
				alloc->pid, page_addr);
			goto err_alloc_page_failed;
		}
263 264 265
		page->alloc = alloc;
		INIT_LIST_HEAD(&page->lru);

266
		ret = map_kernel_range_noflush((unsigned long)page_addr,
267 268
					       PAGE_SIZE, PAGE_KERNEL,
					       &page->page_ptr);
269 270 271 272 273 274 275 276 277
		flush_cache_vmap((unsigned long)page_addr,
				(unsigned long)page_addr + PAGE_SIZE);
		if (ret != 1) {
			pr_err("%d: binder_alloc_buf failed to map page at %pK in kernel\n",
			       alloc->pid, page_addr);
			goto err_map_kernel_failed;
		}
		user_page_addr =
			(uintptr_t)page_addr + alloc->user_buffer_offset;
278
		ret = vm_insert_page(vma, user_page_addr, page[0].page_ptr);
279 280 281 282 283
		if (ret) {
			pr_err("%d: binder_alloc_buf failed to map page at %lx in userspace\n",
			       alloc->pid, user_page_addr);
			goto err_vm_insert_page_failed;
		}
284

285 286 287
		if (index + 1 > alloc->pages_high)
			alloc->pages_high = index + 1;

288
		trace_binder_alloc_page_end(alloc, index);
289 290 291
		/* vm_insert_page does not seem to increment the refcount */
	}
	if (mm) {
292
		up_read(&mm->mmap_sem);
293 294 295 296 297 298 299
		mmput(mm);
	}
	return 0;

free_range:
	for (page_addr = end - PAGE_SIZE; page_addr >= start;
	     page_addr -= PAGE_SIZE) {
300
		bool ret;
301
		size_t index;
302

303 304 305 306
		index = (page_addr - alloc->buffer) / PAGE_SIZE;
		page = &alloc->pages[index];

		trace_binder_free_lru_start(alloc, index);
307 308 309

		ret = list_lru_add(&binder_alloc_lru, &page->lru);
		WARN_ON(!ret);
310 311

		trace_binder_free_lru_end(alloc, index);
312 313
		continue;

314 315 316
err_vm_insert_page_failed:
		unmap_kernel_range((unsigned long)page_addr, PAGE_SIZE);
err_map_kernel_failed:
317 318
		__free_page(page->page_ptr);
		page->page_ptr = NULL;
319
err_alloc_page_failed:
320
err_page_ptr_cleared:
321 322 323 324
		;
	}
err_no_vma:
	if (mm) {
325
		up_read(&mm->mmap_sem);
326 327
		mmput(mm);
	}
328
	return vma ? -ENOMEM : -ESRCH;
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

static inline void binder_alloc_set_vma(struct binder_alloc *alloc,
		struct vm_area_struct *vma)
{
	if (vma)
		alloc->vma_vm_mm = vma->vm_mm;
	/*
	 * If we see alloc->vma is not NULL, buffer data structures set up
	 * completely. Look at smp_rmb side binder_alloc_get_vma.
	 * We also want to guarantee new alloc->vma_vm_mm is always visible
	 * if alloc->vma is set.
	 */
	smp_wmb();
	alloc->vma = vma;
}

static inline struct vm_area_struct *binder_alloc_get_vma(
		struct binder_alloc *alloc)
{
	struct vm_area_struct *vma = NULL;

	if (alloc->vma) {
		/* Look at description in binder_alloc_set_vma */
		smp_rmb();
		vma = alloc->vma;
	}
	return vma;
}

360 361 362 363 364 365
static struct binder_buffer *binder_alloc_new_buf_locked(
				struct binder_alloc *alloc,
				size_t data_size,
				size_t offsets_size,
				size_t extra_buffers_size,
				int is_async)
366 367 368 369 370 371 372 373
{
	struct rb_node *n = alloc->free_buffers.rb_node;
	struct binder_buffer *buffer;
	size_t buffer_size;
	struct rb_node *best_fit = NULL;
	void *has_page_addr;
	void *end_page_addr;
	size_t size, data_offsets_size;
374
	int ret;
375

376
	if (!binder_alloc_get_vma(alloc)) {
377 378 379
		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
				   "%d: binder_alloc_buf, no vma\n",
				   alloc->pid);
380
		return ERR_PTR(-ESRCH);
381 382 383 384 385 386 387 388 389
	}

	data_offsets_size = ALIGN(data_size, sizeof(void *)) +
		ALIGN(offsets_size, sizeof(void *));

	if (data_offsets_size < data_size || data_offsets_size < offsets_size) {
		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
				"%d: got transaction with invalid size %zd-%zd\n",
				alloc->pid, data_size, offsets_size);
390
		return ERR_PTR(-EINVAL);
391 392 393 394 395 396
	}
	size = data_offsets_size + ALIGN(extra_buffers_size, sizeof(void *));
	if (size < data_offsets_size || size < extra_buffers_size) {
		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
				"%d: got transaction with invalid extra_buffers_size %zd\n",
				alloc->pid, extra_buffers_size);
397
		return ERR_PTR(-EINVAL);
398 399 400 401 402 403
	}
	if (is_async &&
	    alloc->free_async_space < size + sizeof(struct binder_buffer)) {
		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
			     "%d: binder_alloc_buf size %zd failed, no async space left\n",
			      alloc->pid, size);
404
		return ERR_PTR(-ENOSPC);
405 406
	}

407 408 409
	/* Pad 0-size buffers so they get assigned unique addresses */
	size = max(size, sizeof(void *));

410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425
	while (n) {
		buffer = rb_entry(n, struct binder_buffer, rb_node);
		BUG_ON(!buffer->free);
		buffer_size = binder_alloc_buffer_size(alloc, buffer);

		if (size < buffer_size) {
			best_fit = n;
			n = n->rb_left;
		} else if (size > buffer_size)
			n = n->rb_right;
		else {
			best_fit = n;
			break;
		}
	}
	if (best_fit == NULL) {
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
		size_t allocated_buffers = 0;
		size_t largest_alloc_size = 0;
		size_t total_alloc_size = 0;
		size_t free_buffers = 0;
		size_t largest_free_size = 0;
		size_t total_free_size = 0;

		for (n = rb_first(&alloc->allocated_buffers); n != NULL;
		     n = rb_next(n)) {
			buffer = rb_entry(n, struct binder_buffer, rb_node);
			buffer_size = binder_alloc_buffer_size(alloc, buffer);
			allocated_buffers++;
			total_alloc_size += buffer_size;
			if (buffer_size > largest_alloc_size)
				largest_alloc_size = buffer_size;
		}
		for (n = rb_first(&alloc->free_buffers); n != NULL;
		     n = rb_next(n)) {
			buffer = rb_entry(n, struct binder_buffer, rb_node);
			buffer_size = binder_alloc_buffer_size(alloc, buffer);
			free_buffers++;
			total_free_size += buffer_size;
			if (buffer_size > largest_free_size)
				largest_free_size = buffer_size;
		}
451 452 453 454 455 456 457 458
		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
				   "%d: binder_alloc_buf size %zd failed, no address space\n",
				   alloc->pid, size);
		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
				   "allocated: %zd (num: %zd largest: %zd), free: %zd (num: %zd largest: %zd)\n",
				   total_alloc_size, allocated_buffers,
				   largest_alloc_size, total_free_size,
				   free_buffers, largest_free_size);
459
		return ERR_PTR(-ENOSPC);
460 461 462 463 464 465 466 467 468 469 470 471
	}
	if (n == NULL) {
		buffer = rb_entry(best_fit, struct binder_buffer, rb_node);
		buffer_size = binder_alloc_buffer_size(alloc, buffer);
	}

	binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
		     "%d: binder_alloc_buf size %zd got buffer %pK size %zd\n",
		      alloc->pid, size, buffer, buffer_size);

	has_page_addr =
		(void *)(((uintptr_t)buffer->data + buffer_size) & PAGE_MASK);
472
	WARN_ON(n && buffer_size != size);
473
	end_page_addr =
474
		(void *)PAGE_ALIGN((uintptr_t)buffer->data + size);
475 476
	if (end_page_addr > has_page_addr)
		end_page_addr = has_page_addr;
477
	ret = binder_update_page_range(alloc, 1,
478
	    (void *)PAGE_ALIGN((uintptr_t)buffer->data), end_page_addr);
479 480
	if (ret)
		return ERR_PTR(ret);
481 482

	if (buffer_size != size) {
483
		struct binder_buffer *new_buffer;
484

485 486 487 488 489 490 491
		new_buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
		if (!new_buffer) {
			pr_err("%s: %d failed to alloc new buffer struct\n",
			       __func__, alloc->pid);
			goto err_alloc_buf_struct_failed;
		}
		new_buffer->data = (u8 *)buffer->data + size;
492 493 494 495
		list_add(&new_buffer->entry, &buffer->entry);
		new_buffer->free = 1;
		binder_insert_free_buffer(alloc, new_buffer);
	}
496 497 498

	rb_erase(best_fit, &alloc->free_buffers);
	buffer->free = 0;
499
	buffer->allow_user_free = 0;
500
	binder_insert_allocated_buffer_locked(alloc, buffer);
501 502 503 504 505 506 507 508 509 510 511 512 513 514
	binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
		     "%d: binder_alloc_buf size %zd got %pK\n",
		      alloc->pid, size, buffer);
	buffer->data_size = data_size;
	buffer->offsets_size = offsets_size;
	buffer->async_transaction = is_async;
	buffer->extra_buffers_size = extra_buffers_size;
	if (is_async) {
		alloc->free_async_space -= size + sizeof(struct binder_buffer);
		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC,
			     "%d: binder_alloc_buf size %zd async free %zd\n",
			      alloc->pid, size, alloc->free_async_space);
	}
	return buffer;
515 516 517 518

err_alloc_buf_struct_failed:
	binder_update_page_range(alloc, 0,
				 (void *)PAGE_ALIGN((uintptr_t)buffer->data),
519
				 end_page_addr);
520
	return ERR_PTR(-ENOMEM);
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
}

/**
 * binder_alloc_new_buf() - Allocate a new binder buffer
 * @alloc:              binder_alloc for this proc
 * @data_size:          size of user data buffer
 * @offsets_size:       user specified buffer offset
 * @extra_buffers_size: size of extra space for meta-data (eg, security context)
 * @is_async:           buffer for async transaction
 *
 * Allocate a new buffer given the requested sizes. Returns
 * the kernel version of the buffer pointer. The size allocated
 * is the sum of the three given sizes (each rounded up to
 * pointer-sized boundary)
 *
 * Return:	The allocated buffer or %NULL if error
 */
struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
					   size_t data_size,
					   size_t offsets_size,
					   size_t extra_buffers_size,
					   int is_async)
{
	struct binder_buffer *buffer;

	mutex_lock(&alloc->mutex);
	buffer = binder_alloc_new_buf_locked(alloc, data_size, offsets_size,
					     extra_buffers_size, is_async);
	mutex_unlock(&alloc->mutex);
	return buffer;
}

static void *buffer_start_page(struct binder_buffer *buffer)
{
555
	return (void *)((uintptr_t)buffer->data & PAGE_MASK);
556 557
}

558
static void *prev_buffer_end_page(struct binder_buffer *buffer)
559
{
560
	return (void *)(((uintptr_t)(buffer->data) - 1) & PAGE_MASK);
561 562 563 564 565 566
}

static void binder_delete_free_buffer(struct binder_alloc *alloc,
				      struct binder_buffer *buffer)
{
	struct binder_buffer *prev, *next = NULL;
567
	bool to_free = true;
568
	BUG_ON(alloc->buffers.next == &buffer->entry);
569
	prev = binder_buffer_prev(buffer);
570
	BUG_ON(!prev->free);
571 572
	if (prev_buffer_end_page(prev) == buffer_start_page(buffer)) {
		to_free = false;
573
		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
574 575
				   "%d: merge free, buffer %pK share page with %pK\n",
				   alloc->pid, buffer->data, prev->data);
576 577 578
	}

	if (!list_is_last(&buffer->entry, &alloc->buffers)) {
579
		next = binder_buffer_next(buffer);
580 581
		if (buffer_start_page(next) == buffer_start_page(buffer)) {
			to_free = false;
582
			binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
583 584 585 586
					   "%d: merge free, buffer %pK share page with %pK\n",
					   alloc->pid,
					   buffer->data,
					   next->data);
587 588
		}
	}
589 590 591 592 593 594 595 596 597

	if (PAGE_ALIGNED(buffer->data)) {
		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
				   "%d: merge free, buffer start %pK is page aligned\n",
				   alloc->pid, buffer->data);
		to_free = false;
	}

	if (to_free) {
598
		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
599 600
				   "%d: merge free, buffer %pK do not share page with %pK or %pK\n",
				   alloc->pid, buffer->data,
601
				   prev->data, next ? next->data : NULL);
602
		binder_update_page_range(alloc, 0, buffer_start_page(buffer),
603
					 buffer_start_page(buffer) + PAGE_SIZE);
604
	}
605 606
	list_del(&buffer->entry);
	kfree(buffer);
607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626
}

static void binder_free_buf_locked(struct binder_alloc *alloc,
				   struct binder_buffer *buffer)
{
	size_t size, buffer_size;

	buffer_size = binder_alloc_buffer_size(alloc, buffer);

	size = ALIGN(buffer->data_size, sizeof(void *)) +
		ALIGN(buffer->offsets_size, sizeof(void *)) +
		ALIGN(buffer->extra_buffers_size, sizeof(void *));

	binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
		     "%d: binder_free_buf %pK size %zd buffer_size %zd\n",
		      alloc->pid, buffer, size, buffer_size);

	BUG_ON(buffer->free);
	BUG_ON(size > buffer_size);
	BUG_ON(buffer->transaction != NULL);
627 628
	BUG_ON(buffer->data < alloc->buffer);
	BUG_ON(buffer->data > alloc->buffer + alloc->buffer_size);
629 630 631 632 633 634 635 636 637 638 639

	if (buffer->async_transaction) {
		alloc->free_async_space += size + sizeof(struct binder_buffer);

		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC,
			     "%d: binder_free_buf size %zd async free %zd\n",
			      alloc->pid, size, alloc->free_async_space);
	}

	binder_update_page_range(alloc, 0,
		(void *)PAGE_ALIGN((uintptr_t)buffer->data),
640
		(void *)(((uintptr_t)buffer->data + buffer_size) & PAGE_MASK));
641 642 643 644

	rb_erase(&buffer->rb_node, &alloc->allocated_buffers);
	buffer->free = 1;
	if (!list_is_last(&buffer->entry, &alloc->buffers)) {
645
		struct binder_buffer *next = binder_buffer_next(buffer);
646 647 648 649 650 651 652

		if (next->free) {
			rb_erase(&next->rb_node, &alloc->free_buffers);
			binder_delete_free_buffer(alloc, next);
		}
	}
	if (alloc->buffers.next != &buffer->entry) {
653
		struct binder_buffer *prev = binder_buffer_prev(buffer);
654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706

		if (prev->free) {
			binder_delete_free_buffer(alloc, buffer);
			rb_erase(&prev->rb_node, &alloc->free_buffers);
			buffer = prev;
		}
	}
	binder_insert_free_buffer(alloc, buffer);
}

/**
 * binder_alloc_free_buf() - free a binder buffer
 * @alloc:	binder_alloc for this proc
 * @buffer:	kernel pointer to buffer
 *
 * Free the buffer allocated via binder_alloc_new_buffer()
 */
void binder_alloc_free_buf(struct binder_alloc *alloc,
			    struct binder_buffer *buffer)
{
	mutex_lock(&alloc->mutex);
	binder_free_buf_locked(alloc, buffer);
	mutex_unlock(&alloc->mutex);
}

/**
 * binder_alloc_mmap_handler() - map virtual address space for proc
 * @alloc:	alloc structure for this proc
 * @vma:	vma passed to mmap()
 *
 * Called by binder_mmap() to initialize the space specified in
 * vma for allocating binder buffers
 *
 * Return:
 *      0 = success
 *      -EBUSY = address space already mapped
 *      -ENOMEM = failed to map memory to given address space
 */
int binder_alloc_mmap_handler(struct binder_alloc *alloc,
			      struct vm_area_struct *vma)
{
	int ret;
	struct vm_struct *area;
	const char *failure_string;
	struct binder_buffer *buffer;

	mutex_lock(&binder_alloc_mmap_lock);
	if (alloc->buffer) {
		ret = -EBUSY;
		failure_string = "already mapped";
		goto err_already_mapped;
	}

707
	area = get_vm_area(vma->vm_end - vma->vm_start, VM_ALLOC);
708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728
	if (area == NULL) {
		ret = -ENOMEM;
		failure_string = "get_vm_area";
		goto err_get_vm_area_failed;
	}
	alloc->buffer = area->addr;
	alloc->user_buffer_offset =
		vma->vm_start - (uintptr_t)alloc->buffer;
	mutex_unlock(&binder_alloc_mmap_lock);

#ifdef CONFIG_CPU_CACHE_VIPT
	if (cache_is_vipt_aliasing()) {
		while (CACHE_COLOUR(
				(vma->vm_start ^ (uint32_t)alloc->buffer))) {
			pr_info("%s: %d %lx-%lx maps %pK bad alignment\n",
				__func__, alloc->pid, vma->vm_start,
				vma->vm_end, alloc->buffer);
			vma->vm_start += PAGE_SIZE;
		}
	}
#endif
K
Kees Cook 已提交
729 730
	alloc->pages = kcalloc((vma->vm_end - vma->vm_start) / PAGE_SIZE,
			       sizeof(alloc->pages[0]),
731 732 733 734 735 736 737 738
			       GFP_KERNEL);
	if (alloc->pages == NULL) {
		ret = -ENOMEM;
		failure_string = "alloc page array";
		goto err_alloc_pages_failed;
	}
	alloc->buffer_size = vma->vm_end - vma->vm_start;

739 740
	buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
	if (!buffer) {
741
		ret = -ENOMEM;
742 743
		failure_string = "alloc buffer struct";
		goto err_alloc_buf_struct_failed;
744
	}
745 746

	buffer->data = alloc->buffer;
747 748 749 750
	list_add(&buffer->entry, &alloc->buffers);
	buffer->free = 1;
	binder_insert_free_buffer(alloc, buffer);
	alloc->free_async_space = alloc->buffer_size / 2;
751
	binder_alloc_set_vma(alloc, vma);
752
	mmgrab(alloc->vma_vm_mm);
753 754 755

	return 0;

756
err_alloc_buf_struct_failed:
757 758 759 760 761 762 763 764 765
	kfree(alloc->pages);
	alloc->pages = NULL;
err_alloc_pages_failed:
	mutex_lock(&binder_alloc_mmap_lock);
	vfree(alloc->buffer);
	alloc->buffer = NULL;
err_get_vm_area_failed:
err_already_mapped:
	mutex_unlock(&binder_alloc_mmap_lock);
766 767 768 769
	binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
			   "%s: %d %lx-%lx %s failed %d\n", __func__,
			   alloc->pid, vma->vm_start, vma->vm_end,
			   failure_string, ret);
770 771 772 773 774 775 776 777
	return ret;
}


void binder_alloc_deferred_release(struct binder_alloc *alloc)
{
	struct rb_node *n;
	int buffers, page_count;
778
	struct binder_buffer *buffer;
779 780 781

	buffers = 0;
	mutex_lock(&alloc->mutex);
782 783
	BUG_ON(alloc->vma);

784 785 786 787 788 789 790 791 792 793
	while ((n = rb_first(&alloc->allocated_buffers))) {
		buffer = rb_entry(n, struct binder_buffer, rb_node);

		/* Transaction should already have been freed */
		BUG_ON(buffer->transaction);

		binder_free_buf_locked(alloc, buffer);
		buffers++;
	}

794 795 796 797 798 799 800 801 802 803
	while (!list_empty(&alloc->buffers)) {
		buffer = list_first_entry(&alloc->buffers,
					  struct binder_buffer, entry);
		WARN_ON(!buffer->free);

		list_del(&buffer->entry);
		WARN_ON_ONCE(!list_empty(&alloc->buffers));
		kfree(buffer);
	}

804 805 806 807 808 809
	page_count = 0;
	if (alloc->pages) {
		int i;

		for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
			void *page_addr;
810
			bool on_lru;
811

812
			if (!alloc->pages[i].page_ptr)
813 814
				continue;

815 816
			on_lru = list_lru_del(&binder_alloc_lru,
					      &alloc->pages[i].lru);
817 818
			page_addr = alloc->buffer + i * PAGE_SIZE;
			binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
819 820 821
				     "%s: %d: page %d at %pK %s\n",
				     __func__, alloc->pid, i, page_addr,
				     on_lru ? "on lru" : "active");
822
			unmap_kernel_range((unsigned long)page_addr, PAGE_SIZE);
823
			__free_page(alloc->pages[i].page_ptr);
824 825 826 827 828 829
			page_count++;
		}
		kfree(alloc->pages);
		vfree(alloc->buffer);
	}
	mutex_unlock(&alloc->mutex);
830 831
	if (alloc->vma_vm_mm)
		mmdrop(alloc->vma_vm_mm);
832 833 834 835 836 837 838 839 840

	binder_alloc_debug(BINDER_DEBUG_OPEN_CLOSE,
		     "%s: %d buffers %d, pages %d\n",
		     __func__, alloc->pid, buffers, page_count);
}

static void print_binder_buffer(struct seq_file *m, const char *prefix,
				struct binder_buffer *buffer)
{
841
	seq_printf(m, "%s %d: %pK size %zd:%zd:%zd %s\n",
842 843
		   prefix, buffer->debug_id, buffer->data,
		   buffer->data_size, buffer->offsets_size,
844
		   buffer->extra_buffers_size,
845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867
		   buffer->transaction ? "active" : "delivered");
}

/**
 * binder_alloc_print_allocated() - print buffer info
 * @m:     seq_file for output via seq_printf()
 * @alloc: binder_alloc for this proc
 *
 * Prints information about every buffer associated with
 * the binder_alloc state to the given seq_file
 */
void binder_alloc_print_allocated(struct seq_file *m,
				  struct binder_alloc *alloc)
{
	struct rb_node *n;

	mutex_lock(&alloc->mutex);
	for (n = rb_first(&alloc->allocated_buffers); n != NULL; n = rb_next(n))
		print_binder_buffer(m, "  buffer",
				    rb_entry(n, struct binder_buffer, rb_node));
	mutex_unlock(&alloc->mutex);
}

868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893
/**
 * binder_alloc_print_pages() - print page usage
 * @m:     seq_file for output via seq_printf()
 * @alloc: binder_alloc for this proc
 */
void binder_alloc_print_pages(struct seq_file *m,
			      struct binder_alloc *alloc)
{
	struct binder_lru_page *page;
	int i;
	int active = 0;
	int lru = 0;
	int free = 0;

	mutex_lock(&alloc->mutex);
	for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
		page = &alloc->pages[i];
		if (!page->page_ptr)
			free++;
		else if (list_empty(&page->lru))
			active++;
		else
			lru++;
	}
	mutex_unlock(&alloc->mutex);
	seq_printf(m, "  pages: %d:%d:%d\n", active, lru, free);
894
	seq_printf(m, "  pages high watermark: %zu\n", alloc->pages_high);
895 896
}

897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925
/**
 * binder_alloc_get_allocated_count() - return count of buffers
 * @alloc: binder_alloc for this proc
 *
 * Return: count of allocated buffers
 */
int binder_alloc_get_allocated_count(struct binder_alloc *alloc)
{
	struct rb_node *n;
	int count = 0;

	mutex_lock(&alloc->mutex);
	for (n = rb_first(&alloc->allocated_buffers); n != NULL; n = rb_next(n))
		count++;
	mutex_unlock(&alloc->mutex);
	return count;
}


/**
 * binder_alloc_vma_close() - invalidate address space
 * @alloc: binder_alloc for this proc
 *
 * Called from binder_vma_close() when releasing address space.
 * Clears alloc->vma to prevent new incoming transactions from
 * allocating more buffers.
 */
void binder_alloc_vma_close(struct binder_alloc *alloc)
{
926
	binder_alloc_set_vma(alloc, NULL);
927 928
}

929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949
/**
 * binder_alloc_free_page() - shrinker callback to free pages
 * @item:   item to free
 * @lock:   lock protecting the item
 * @cb_arg: callback argument
 *
 * Called from list_lru_walk() in binder_shrink_scan() to free
 * up pages when the system is under memory pressure.
 */
enum lru_status binder_alloc_free_page(struct list_head *item,
				       struct list_lru_one *lru,
				       spinlock_t *lock,
				       void *cb_arg)
{
	struct mm_struct *mm = NULL;
	struct binder_lru_page *page = container_of(item,
						    struct binder_lru_page,
						    lru);
	struct binder_alloc *alloc;
	uintptr_t page_addr;
	size_t index;
950
	struct vm_area_struct *vma;
951 952 953 954 955 956 957 958 959 960

	alloc = page->alloc;
	if (!mutex_trylock(&alloc->mutex))
		goto err_get_alloc_mutex_failed;

	if (!page->page_ptr)
		goto err_page_already_freed;

	index = page - alloc->pages;
	page_addr = (uintptr_t)alloc->buffer + index * PAGE_SIZE;
961
	vma = binder_alloc_get_vma(alloc);
962 963 964 965 966 967 968
	if (vma) {
		if (!mmget_not_zero(alloc->vma_vm_mm))
			goto err_mmget;
		mm = alloc->vma_vm_mm;
		if (!down_write_trylock(&mm->mmap_sem))
			goto err_down_write_mmap_sem_failed;
	}
969 970 971

	list_lru_isolate(lru, item);
	spin_unlock(lock);
972

973
	if (vma) {
974 975
		trace_binder_unmap_user_start(alloc, index);

976
		zap_page_range(vma,
977 978 979
			       page_addr + alloc->user_buffer_offset,
			       PAGE_SIZE);

980
		trace_binder_unmap_user_end(alloc, index);
981 982 983

		up_write(&mm->mmap_sem);
		mmput(mm);
984 985
	}

986 987
	trace_binder_unmap_kernel_start(alloc, index);

988 989 990 991
	unmap_kernel_range(page_addr, PAGE_SIZE);
	__free_page(page->page_ptr);
	page->page_ptr = NULL;

992 993
	trace_binder_unmap_kernel_end(alloc, index);

994
	spin_lock(lock);
995
	mutex_unlock(&alloc->mutex);
996
	return LRU_REMOVED_RETRY;
997 998

err_down_write_mmap_sem_failed:
999
	mmput_async(mm);
1000
err_mmget:
1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023
err_page_already_freed:
	mutex_unlock(&alloc->mutex);
err_get_alloc_mutex_failed:
	return LRU_SKIP;
}

static unsigned long
binder_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
{
	unsigned long ret = list_lru_count(&binder_alloc_lru);
	return ret;
}

static unsigned long
binder_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
{
	unsigned long ret;

	ret = list_lru_walk(&binder_alloc_lru, binder_alloc_free_page,
			    NULL, sc->nr_to_scan);
	return ret;
}

1024
static struct shrinker binder_shrinker = {
1025 1026 1027 1028 1029
	.count_objects = binder_shrink_count,
	.scan_objects = binder_shrink_scan,
	.seeks = DEFAULT_SEEKS,
};

1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040
/**
 * binder_alloc_init() - called by binder_open() for per-proc initialization
 * @alloc: binder_alloc for this proc
 *
 * Called from binder_open() to initialize binder_alloc fields for
 * new binder proc
 */
void binder_alloc_init(struct binder_alloc *alloc)
{
	alloc->pid = current->group_leader->pid;
	mutex_init(&alloc->mutex);
1041
	INIT_LIST_HEAD(&alloc->buffers);
1042 1043
}

1044
int binder_alloc_shrinker_init(void)
1045
{
1046 1047 1048 1049 1050 1051 1052 1053
	int ret = list_lru_init(&binder_alloc_lru);

	if (ret == 0) {
		ret = register_shrinker(&binder_shrinker);
		if (ret)
			list_lru_destroy(&binder_alloc_lru);
	}
	return ret;
1054
}