binder_alloc.c 27.2 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
/* 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 <asm/cacheflush.h>
#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>
30
#include <linux/list_lru.h>
31 32 33
#include "binder_alloc.h"
#include "binder_trace.h"

34 35
struct list_lru binder_alloc_lru;

36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53
static DEFINE_MUTEX(binder_alloc_mmap_lock);

enum {
	BINDER_DEBUG_OPEN_CLOSE             = 1U << 1,
	BINDER_DEBUG_BUFFER_ALLOC           = 1U << 2,
	BINDER_DEBUG_BUFFER_ALLOC_ASYNC     = 1U << 3,
};
static uint32_t binder_alloc_debug_mask;

module_param_named(debug_mask, binder_alloc_debug_mask,
		   uint, 0644);

#define binder_alloc_debug(mask, x...) \
	do { \
		if (binder_alloc_debug_mask & mask) \
			pr_info(x); \
	} while (0)

54 55 56 57 58 59 60 61 62 63
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);
}

64 65 66 67
static size_t binder_alloc_buffer_size(struct binder_alloc *alloc,
				       struct binder_buffer *buffer)
{
	if (list_is_last(&buffer->entry, &alloc->buffers))
68 69 70
		return (u8 *)alloc->buffer +
			alloc->buffer_size - (u8 *)buffer->data;
	return (u8 *)binder_buffer_next(buffer)->data - (u8 *)buffer->data;
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
}

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);

120
		if (new_buffer->data < buffer->data)
121
			p = &parent->rb_left;
122
		else if (new_buffer->data > buffer->data)
123 124 125 126 127 128 129 130
			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);
}

131
static struct binder_buffer *binder_alloc_prepare_to_free_locked(
132 133 134 135 136
		struct binder_alloc *alloc,
		uintptr_t user_ptr)
{
	struct rb_node *n = alloc->allocated_buffers.rb_node;
	struct binder_buffer *buffer;
137
	void *kern_ptr;
138

139
	kern_ptr = (void *)(user_ptr - alloc->user_buffer_offset);
140 141 142 143 144

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

145
		if (kern_ptr < buffer->data)
146
			n = n->rb_left;
147
		else if (kern_ptr > buffer->data)
148
			n = n->rb_right;
149 150 151 152 153 154 155 156 157 158 159
		else {
			/*
			 * Guard against user threads attempting to
			 * free the buffer twice
			 */
			if (buffer->free_in_progress) {
				pr_err("%d:%d FREE_BUFFER u%016llx user freed buffer twice\n",
				       alloc->pid, current->pid, (u64)user_ptr);
				return NULL;
			}
			buffer->free_in_progress = 1;
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;
220 221 222 223 224 225

	if (mm) {
		down_write(&mm->mmap_sem);
		vma = alloc->vma;
	}

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

	for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
		int ret;
234
		bool on_lru;
235
		size_t index;
236

237 238
		index = (page_addr - alloc->buffer) / PAGE_SIZE;
		page = &alloc->pages[index];
239

240
		if (page->page_ptr) {
241 242
			trace_binder_alloc_lru_start(alloc, index);

243 244
			on_lru = list_lru_del(&binder_alloc_lru, &page->lru);
			WARN_ON(!on_lru);
245 246

			trace_binder_alloc_lru_end(alloc, index);
247 248 249 250 251 252
			continue;
		}

		if (WARN_ON(!vma))
			goto err_page_ptr_cleared;

253
		trace_binder_alloc_page_start(alloc, index);
254 255 256 257
		page->page_ptr = alloc_page(GFP_KERNEL |
					    __GFP_HIGHMEM |
					    __GFP_ZERO);
		if (!page->page_ptr) {
258 259 260 261
			pr_err("%d: binder_alloc_buf failed for page at %pK\n",
				alloc->pid, page_addr);
			goto err_alloc_page_failed;
		}
262 263 264
		page->alloc = alloc;
		INIT_LIST_HEAD(&page->lru);

265
		ret = map_kernel_range_noflush((unsigned long)page_addr,
266 267
					       PAGE_SIZE, PAGE_KERNEL,
					       &page->page_ptr);
268 269 270 271 272 273 274 275 276
		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;
277
		ret = vm_insert_page(vma, user_page_addr, page[0].page_ptr);
278 279 280 281 282
		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;
		}
283

284 285 286
		if (index + 1 > alloc->pages_high)
			alloc->pages_high = index + 1;

287
		trace_binder_alloc_page_end(alloc, index);
288 289 290 291 292 293 294 295 296 297 298
		/* vm_insert_page does not seem to increment the refcount */
	}
	if (mm) {
		up_write(&mm->mmap_sem);
		mmput(mm);
	}
	return 0;

free_range:
	for (page_addr = end - PAGE_SIZE; page_addr >= start;
	     page_addr -= PAGE_SIZE) {
299
		bool ret;
300
		size_t index;
301

302 303 304 305
		index = (page_addr - alloc->buffer) / PAGE_SIZE;
		page = &alloc->pages[index];

		trace_binder_free_lru_start(alloc, index);
306 307 308

		ret = list_lru_add(&binder_alloc_lru, &page->lru);
		WARN_ON(!ret);
309 310

		trace_binder_free_lru_end(alloc, index);
311 312
		continue;

313 314 315
err_vm_insert_page_failed:
		unmap_kernel_range((unsigned long)page_addr, PAGE_SIZE);
err_map_kernel_failed:
316 317
		__free_page(page->page_ptr);
		page->page_ptr = NULL;
318
err_alloc_page_failed:
319
err_page_ptr_cleared:
320 321 322 323 324 325 326
		;
	}
err_no_vma:
	if (mm) {
		up_write(&mm->mmap_sem);
		mmput(mm);
	}
327
	return vma ? -ENOMEM : -ESRCH;
328 329
}

330 331 332 333 334 335
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)
336 337 338 339 340 341 342 343
{
	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;
344
	int ret;
345 346 347 348

	if (alloc->vma == NULL) {
		pr_err("%d: binder_alloc_buf, no vma\n",
		       alloc->pid);
349
		return ERR_PTR(-ESRCH);
350 351 352 353 354 355 356 357 358
	}

	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);
359
		return ERR_PTR(-EINVAL);
360 361 362 363 364 365
	}
	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);
366
		return ERR_PTR(-EINVAL);
367 368 369 370 371 372
	}
	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);
373
		return ERR_PTR(-ENOSPC);
374 375
	}

376 377 378
	/* Pad 0-size buffers so they get assigned unique addresses */
	size = max(size, sizeof(void *));

379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394
	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) {
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
		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;
		}
420 421
		pr_err("%d: binder_alloc_buf size %zd failed, no address space\n",
			alloc->pid, size);
422 423 424
		pr_err("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);
425
		return ERR_PTR(-ENOSPC);
426 427 428 429 430 431 432 433 434 435 436 437
	}
	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);
438
	WARN_ON(n && buffer_size != size);
439
	end_page_addr =
440
		(void *)PAGE_ALIGN((uintptr_t)buffer->data + size);
441 442
	if (end_page_addr > has_page_addr)
		end_page_addr = has_page_addr;
443
	ret = binder_update_page_range(alloc, 1,
444
	    (void *)PAGE_ALIGN((uintptr_t)buffer->data), end_page_addr);
445 446
	if (ret)
		return ERR_PTR(ret);
447 448

	if (buffer_size != size) {
449
		struct binder_buffer *new_buffer;
450

451 452 453 454 455 456 457
		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;
458 459 460 461
		list_add(&new_buffer->entry, &buffer->entry);
		new_buffer->free = 1;
		binder_insert_free_buffer(alloc, new_buffer);
	}
462 463 464 465 466

	rb_erase(best_fit, &alloc->free_buffers);
	buffer->free = 0;
	buffer->free_in_progress = 0;
	binder_insert_allocated_buffer_locked(alloc, buffer);
467 468 469 470 471 472 473 474 475 476 477 478 479 480
	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;
481 482 483 484

err_alloc_buf_struct_failed:
	binder_update_page_range(alloc, 0,
				 (void *)PAGE_ALIGN((uintptr_t)buffer->data),
485
				 end_page_addr);
486
	return ERR_PTR(-ENOMEM);
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
}

/**
 * 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)
{
521
	return (void *)((uintptr_t)buffer->data & PAGE_MASK);
522 523
}

524
static void *prev_buffer_end_page(struct binder_buffer *buffer)
525
{
526
	return (void *)(((uintptr_t)(buffer->data) - 1) & PAGE_MASK);
527 528 529 530 531 532
}

static void binder_delete_free_buffer(struct binder_alloc *alloc,
				      struct binder_buffer *buffer)
{
	struct binder_buffer *prev, *next = NULL;
533
	bool to_free = true;
534
	BUG_ON(alloc->buffers.next == &buffer->entry);
535
	prev = binder_buffer_prev(buffer);
536
	BUG_ON(!prev->free);
537 538
	if (prev_buffer_end_page(prev) == buffer_start_page(buffer)) {
		to_free = false;
539
		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
540 541
				   "%d: merge free, buffer %pK share page with %pK\n",
				   alloc->pid, buffer->data, prev->data);
542 543 544
	}

	if (!list_is_last(&buffer->entry, &alloc->buffers)) {
545
		next = binder_buffer_next(buffer);
546 547
		if (buffer_start_page(next) == buffer_start_page(buffer)) {
			to_free = false;
548
			binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
549 550 551 552
					   "%d: merge free, buffer %pK share page with %pK\n",
					   alloc->pid,
					   buffer->data,
					   next->data);
553 554
		}
	}
555 556 557 558 559 560 561 562 563

	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) {
564
		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
565 566
				   "%d: merge free, buffer %pK do not share page with %pK or %pK\n",
				   alloc->pid, buffer->data,
567
				   prev->data, next ? next->data : NULL);
568
		binder_update_page_range(alloc, 0, buffer_start_page(buffer),
569
					 buffer_start_page(buffer) + PAGE_SIZE);
570
	}
571 572
	list_del(&buffer->entry);
	kfree(buffer);
573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592
}

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);
593 594
	BUG_ON(buffer->data < alloc->buffer);
	BUG_ON(buffer->data > alloc->buffer + alloc->buffer_size);
595 596 597 598 599 600 601 602 603 604 605

	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),
606
		(void *)(((uintptr_t)buffer->data + buffer_size) & PAGE_MASK));
607 608 609 610

	rb_erase(&buffer->rb_node, &alloc->allocated_buffers);
	buffer->free = 1;
	if (!list_is_last(&buffer->entry, &alloc->buffers)) {
611
		struct binder_buffer *next = binder_buffer_next(buffer);
612 613 614 615 616 617 618

		if (next->free) {
			rb_erase(&next->rb_node, &alloc->free_buffers);
			binder_delete_free_buffer(alloc, next);
		}
	}
	if (alloc->buffers.next != &buffer->entry) {
619
		struct binder_buffer *prev = binder_buffer_prev(buffer);
620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672

		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;
	}

673
	area = get_vm_area(vma->vm_end - vma->vm_start, VM_ALLOC);
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
	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
	alloc->pages = kzalloc(sizeof(alloc->pages[0]) *
				   ((vma->vm_end - vma->vm_start) / PAGE_SIZE),
			       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;

705 706
	buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
	if (!buffer) {
707
		ret = -ENOMEM;
708 709
		failure_string = "alloc buffer struct";
		goto err_alloc_buf_struct_failed;
710
	}
711 712

	buffer->data = alloc->buffer;
713 714 715 716 717 718 719
	list_add(&buffer->entry, &alloc->buffers);
	buffer->free = 1;
	binder_insert_free_buffer(alloc, buffer);
	alloc->free_async_space = alloc->buffer_size / 2;
	barrier();
	alloc->vma = vma;
	alloc->vma_vm_mm = vma->vm_mm;
720
	mmgrab(alloc->vma_vm_mm);
721 722 723

	return 0;

724
err_alloc_buf_struct_failed:
725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743
	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);
	pr_err("%s: %d %lx-%lx %s failed %d\n", __func__,
	       alloc->pid, vma->vm_start, vma->vm_end, failure_string, ret);
	return ret;
}


void binder_alloc_deferred_release(struct binder_alloc *alloc)
{
	struct rb_node *n;
	int buffers, page_count;
744
	struct binder_buffer *buffer;
745 746 747 748 749 750 751 752 753 754 755 756 757 758 759

	BUG_ON(alloc->vma);

	buffers = 0;
	mutex_lock(&alloc->mutex);
	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++;
	}

760 761 762 763 764 765 766 767 768 769
	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);
	}

770 771 772 773 774 775
	page_count = 0;
	if (alloc->pages) {
		int i;

		for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
			void *page_addr;
776
			bool on_lru;
777

778
			if (!alloc->pages[i].page_ptr)
779 780
				continue;

781 782
			on_lru = list_lru_del(&binder_alloc_lru,
					      &alloc->pages[i].lru);
783 784
			page_addr = alloc->buffer + i * PAGE_SIZE;
			binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
785 786 787
				     "%s: %d: page %d at %pK %s\n",
				     __func__, alloc->pid, i, page_addr,
				     on_lru ? "on lru" : "active");
788
			unmap_kernel_range((unsigned long)page_addr, PAGE_SIZE);
789
			__free_page(alloc->pages[i].page_ptr);
790 791 792 793 794 795
			page_count++;
		}
		kfree(alloc->pages);
		vfree(alloc->buffer);
	}
	mutex_unlock(&alloc->mutex);
796 797
	if (alloc->vma_vm_mm)
		mmdrop(alloc->vma_vm_mm);
798 799 800 801 802 803 804 805 806

	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)
{
807
	seq_printf(m, "%s %d: %pK size %zd:%zd:%zd %s\n",
808 809
		   prefix, buffer->debug_id, buffer->data,
		   buffer->data_size, buffer->offsets_size,
810
		   buffer->extra_buffers_size,
811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833
		   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);
}

834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859
/**
 * 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);
860
	seq_printf(m, "  pages high watermark: %zu\n", alloc->pages_high);
861 862
}

863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894
/**
 * 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)
{
	WRITE_ONCE(alloc->vma, NULL);
}

895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915
/**
 * 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;
916
	struct vm_area_struct *vma;
917 918 919 920 921 922 923 924 925 926

	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;
927 928
	vma = alloc->vma;
	if (vma) {
929 930 931
		if (!mmget_not_zero(alloc->vma_vm_mm))
			goto err_mmget;
		mm = alloc->vma_vm_mm;
932 933
		if (!down_write_trylock(&mm->mmap_sem))
			goto err_down_write_mmap_sem_failed;
934 935 936 937
	}

	list_lru_isolate(lru, item);
	spin_unlock(lock);
938

939
	if (vma) {
940 941
		trace_binder_unmap_user_start(alloc, index);

942
		zap_page_range(vma,
943 944 945
			       page_addr + alloc->user_buffer_offset,
			       PAGE_SIZE);

946 947
		trace_binder_unmap_user_end(alloc, index);

948 949 950 951
		up_write(&mm->mmap_sem);
		mmput(mm);
	}

952 953
	trace_binder_unmap_kernel_start(alloc, index);

954 955 956 957
	unmap_kernel_range(page_addr, PAGE_SIZE);
	__free_page(page->page_ptr);
	page->page_ptr = NULL;

958 959
	trace_binder_unmap_kernel_end(alloc, index);

960
	spin_lock(lock);
961
	mutex_unlock(&alloc->mutex);
962
	return LRU_REMOVED_RETRY;
963 964

err_down_write_mmap_sem_failed:
965
	mmput_async(mm);
966
err_mmget:
967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989
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;
}

990
static struct shrinker binder_shrinker = {
991 992 993 994 995
	.count_objects = binder_shrink_count,
	.scan_objects = binder_shrink_scan,
	.seeks = DEFAULT_SEEKS,
};

996 997 998 999 1000 1001 1002 1003 1004 1005 1006
/**
 * 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);
1007
	INIT_LIST_HEAD(&alloc->buffers);
1008 1009
}

1010
int binder_alloc_shrinker_init(void)
1011
{
1012 1013 1014 1015 1016 1017 1018 1019
	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;
1020
}