Initial commit: Linux kernel 4.19 for Unplugged OS

drivers/android/Kconfig

@@ -0,0 +1,68 @@
+# SPDX-License-Identifier: GPL-2.0
+menu "Android"
+
+config ANDROID
+	bool "Android Drivers"
+	---help---
+	  Enable support for various drivers needed on the Android platform
+
+if ANDROID
+
+config ANDROID_BINDER_IPC
+	bool "Android Binder IPC Driver"
+	depends on MMU
+	default n
+	---help---
+	  Binder is used in Android for both communication between processes,
+	  and remote method invocation.
+
+	  This means one Android process can call a method/routine in another
+	  Android process, using Binder to identify, invoke and pass arguments
+	  between said processes.
+
+config ANDROID_BINDERFS
+	bool "Android Binderfs filesystem"
+	depends on ANDROID_BINDER_IPC
+	default n
+	---help---
+	  Binderfs is a pseudo-filesystem for the Android Binder IPC driver
+	  which can be mounted per-ipc namespace allowing to run multiple
+	  instances of Android.
+	  Each binderfs mount initially only contains a binder-control device.
+	  It can be used to dynamically allocate new binder IPC devices via
+	  ioctls.
+
+config ANDROID_BINDER_DEVICES
+	string "Android Binder devices"
+	depends on ANDROID_BINDER_IPC
+	default "binder,hwbinder,vndbinder"
+	---help---
+	  Default value for the binder.devices parameter.
+
+	  The binder.devices parameter is a comma-separated list of strings
+	  that specifies the names of the binder device nodes that will be
+	  created. Each binder device has its own context manager, and is
+	  therefore logically separated from the other devices.
+
+config ANDROID_BINDER_IPC_SELFTEST
+	bool "Android Binder IPC Driver Selftest"
+	depends on ANDROID_BINDER_IPC
+	---help---
+	  This feature allows binder selftest to run.
+
+	  Binder selftest checks the allocation and free of binder buffers
+	  exhaustively with combinations of various buffer sizes and
+	  alignments.
+
+config ANDROID_BINDER_USER_TRACKING
+	bool "Android Binder Transaction Tracking"
+	depends on ANDROID_BINDER_IPC
+	help
+	  Used for track abnormal binder transaction which is over 2 seconds,
+	  when the transaction is done or be free, this transaction would be
+	  checked whether it executed overtime.
+	  If yes, printing out the detailed info.
+
+endif # if ANDROID
+
+endmenu

drivers/android/Makefile

@@ -0,0 +1,5 @@
+ccflags-y += -I$(src)			# needed for trace events
+
+obj-$(CONFIG_ANDROID_BINDERFS)		+= binderfs.o
+obj-$(CONFIG_ANDROID_BINDER_IPC)	+= binder.o binder_alloc.o
+obj-$(CONFIG_ANDROID_BINDER_IPC_SELFTEST) += binder_alloc_selftest.o

drivers/android/binder_alloc.h

@@ -0,0 +1,187 @@
+/*
+ * Copyright (C) 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.
+ *
+ */
+
+#ifndef _LINUX_BINDER_ALLOC_H
+#define _LINUX_BINDER_ALLOC_H
+
+#include <linux/rbtree.h>
+#include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/rtmutex.h>
+#include <linux/vmalloc.h>
+#include <linux/slab.h>
+#include <linux/list_lru.h>
+#include <uapi/linux/android/binder.h>
+
+extern struct list_lru binder_alloc_lru;
+struct binder_transaction;
+
+/**
+ * struct binder_buffer - buffer used for binder transactions
+ * @entry:              entry alloc->buffers
+ * @rb_node:            node for allocated_buffers/free_buffers rb trees
+ * @free:               %true if buffer is free
+ * @allow_user_free:    %true if user is allowed to free buffer
+ * @async_transaction:  %true if buffer is in use for an async txn
+ * @debug_id:           unique ID for debugging
+ * @transaction:        pointer to associated struct binder_transaction
+ * @target_node:        struct binder_node associated with this buffer
+ * @data_size:          size of @transaction data
+ * @offsets_size:       size of array of offsets
+ * @extra_buffers_size: size of space for other objects (like sg lists)
+ * @user_data:          user pointer to base of buffer space
+ * @pid:                pid to attribute the buffer to (caller)
+ *
+ * Bookkeeping structure for binder transaction buffers
+ */
+struct binder_buffer {
+	struct list_head entry; /* free and allocated entries by address */
+	struct rb_node rb_node; /* free entry by size or allocated entry */
+				/* by address */
+	unsigned free:1;
+	unsigned allow_user_free:1;
+	unsigned async_transaction:1;
+	unsigned debug_id:29;
+
+	struct binder_transaction *transaction;
+
+	struct binder_node *target_node;
+	size_t data_size;
+	size_t offsets_size;
+	size_t extra_buffers_size;
+	void __user *user_data;
+	int    pid;
+};
+
+/**
+ * struct binder_lru_page - page object used for binder shrinker
+ * @page_ptr: pointer to physical page in mmap'd space
+ * @lru:      entry in binder_alloc_lru
+ * @alloc:    binder_alloc for a proc
+ */
+struct binder_lru_page {
+	struct list_head lru;
+	struct page *page_ptr;
+	struct binder_alloc *alloc;
+};
+
+/**
+ * struct binder_alloc - per-binder proc state for binder allocator
+ * @vma:                vm_area_struct passed to mmap_handler
+ *                      (invarient after mmap)
+ * @tsk:                tid for task that called init for this proc
+ *                      (invariant after init)
+ * @vma_vm_mm:          copy of vma->vm_mm (invarient after mmap)
+ * @buffer:             base of per-proc address space mapped via mmap
+ * @buffers:            list of all buffers for this proc
+ * @free_buffers:       rb tree of buffers available for allocation
+ *                      sorted by size
+ * @allocated_buffers:  rb tree of allocated buffers sorted by address
+ * @free_async_space:   VA space available for async buffers. This is
+ *                      initialized at mmap time to 1/2 the full VA space
+ * @pages:              array of binder_lru_page
+ * @buffer_size:        size of address space specified via mmap
+ * @pid:                pid for associated binder_proc (invariant after init)
+ * @pages_high:         high watermark of offset in @pages
+ *
+ * Bookkeeping structure for per-proc address space management for binder
+ * buffers. It is normally initialized during binder_init() and binder_mmap()
+ * calls. The address space is used for both user-visible buffers and for
+ * struct binder_buffer objects used to track the user buffers
+ */
+struct binder_alloc {
+	struct mutex mutex;
+	struct vm_area_struct *vma;
+	struct mm_struct *vma_vm_mm;
+	void __user *buffer;
+	struct list_head buffers;
+	struct rb_root free_buffers;
+	struct rb_root allocated_buffers;
+	size_t free_async_space;
+	struct binder_lru_page *pages;
+	size_t buffer_size;
+	uint32_t buffer_free;
+	int pid;
+	size_t pages_high;
+};
+
+#ifdef CONFIG_ANDROID_BINDER_IPC_SELFTEST
+void binder_selftest_alloc(struct binder_alloc *alloc);
+#else
+static inline void binder_selftest_alloc(struct binder_alloc *alloc) {}
+#endif
+enum lru_status binder_alloc_free_page(struct list_head *item,
+				       struct list_lru_one *lru,
+				       spinlock_t *lock, void *cb_arg);
+extern 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,
+						  int pid);
+extern void binder_alloc_init(struct binder_alloc *alloc);
+extern int binder_alloc_shrinker_init(void);
+extern void binder_alloc_vma_close(struct binder_alloc *alloc);
+extern struct binder_buffer *
+binder_alloc_prepare_to_free(struct binder_alloc *alloc,
+			     uintptr_t user_ptr);
+extern void binder_alloc_free_buf(struct binder_alloc *alloc,
+				  struct binder_buffer *buffer);
+extern int binder_alloc_mmap_handler(struct binder_alloc *alloc,
+				     struct vm_area_struct *vma);
+extern void binder_alloc_deferred_release(struct binder_alloc *alloc);
+extern int binder_alloc_get_allocated_count(struct binder_alloc *alloc);
+extern void binder_alloc_print_allocated(struct seq_file *m,
+					 struct binder_alloc *alloc);
+void binder_alloc_print_pages(struct seq_file *m,
+			      struct binder_alloc *alloc);
+
+/**
+ * binder_alloc_get_free_async_space() - get free space available for async
+ * @alloc:	binder_alloc for this proc
+ *
+ * Return:	the bytes remaining in the address-space for async transactions
+ */
+static inline size_t
+binder_alloc_get_free_async_space(struct binder_alloc *alloc)
+{
+	size_t free_async_space;
+
+	mutex_lock(&alloc->mutex);
+	free_async_space = alloc->free_async_space;
+	mutex_unlock(&alloc->mutex);
+	return free_async_space;
+}
+
+unsigned long
+binder_alloc_copy_user_to_buffer(struct binder_alloc *alloc,
+				 struct binder_buffer *buffer,
+				 binder_size_t buffer_offset,
+				 const void __user *from,
+				 size_t bytes);
+
+void binder_alloc_copy_to_buffer(struct binder_alloc *alloc,
+				 struct binder_buffer *buffer,
+				 binder_size_t buffer_offset,
+				 void *src,
+				 size_t bytes);
+
+void binder_alloc_copy_from_buffer(struct binder_alloc *alloc,
+				   void *dest,
+				   struct binder_buffer *buffer,
+				   binder_size_t buffer_offset,
+				   size_t bytes);
+
+#endif /* _LINUX_BINDER_ALLOC_H */
+

drivers/android/binder_alloc_selftest.c

@@ -0,0 +1,311 @@
+/* binder_alloc_selftest.c
+ *
+ * Android IPC Subsystem
+ *
+ * Copyright (C) 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/mm_types.h>
+#include <linux/err.h>
+#include "binder_alloc.h"
+
+#define BUFFER_NUM 5
+#define BUFFER_MIN_SIZE (PAGE_SIZE / 8)
+
+static bool binder_selftest_run = true;
+static int binder_selftest_failures;
+static DEFINE_MUTEX(binder_selftest_lock);
+
+/**
+ * enum buf_end_align_type - Page alignment of a buffer
+ * end with regard to the end of the previous buffer.
+ *
+ * In the pictures below, buf2 refers to the buffer we
+ * are aligning. buf1 refers to previous buffer by addr.
+ * Symbol [ means the start of a buffer, ] means the end
+ * of a buffer, and | means page boundaries.
+ */
+enum buf_end_align_type {
+	/**
+	 * @SAME_PAGE_UNALIGNED: The end of this buffer is on
+	 * the same page as the end of the previous buffer and
+	 * is not page aligned. Examples:
+	 * buf1 ][ buf2 ][ ...
+	 * buf1 ]|[ buf2 ][ ...
+	 */
+	SAME_PAGE_UNALIGNED = 0,
+	/**
+	 * @SAME_PAGE_ALIGNED: When the end of the previous buffer
+	 * is not page aligned, the end of this buffer is on the
+	 * same page as the end of the previous buffer and is page
+	 * aligned. When the previous buffer is page aligned, the
+	 * end of this buffer is aligned to the next page boundary.
+	 * Examples:
+	 * buf1 ][ buf2 ]| ...
+	 * buf1 ]|[ buf2 ]| ...
+	 */
+	SAME_PAGE_ALIGNED,
+	/**
+	 * @NEXT_PAGE_UNALIGNED: The end of this buffer is on
+	 * the page next to the end of the previous buffer and
+	 * is not page aligned. Examples:
+	 * buf1 ][ buf2 | buf2 ][ ...
+	 * buf1 ]|[ buf2 | buf2 ][ ...
+	 */
+	NEXT_PAGE_UNALIGNED,
+	/**
+	 * @NEXT_PAGE_ALIGNED: The end of this buffer is on
+	 * the page next to the end of the previous buffer and
+	 * is page aligned. Examples:
+	 * buf1 ][ buf2 | buf2 ]| ...
+	 * buf1 ]|[ buf2 | buf2 ]| ...
+	 */
+	NEXT_PAGE_ALIGNED,
+	/**
+	 * @NEXT_NEXT_UNALIGNED: The end of this buffer is on
+	 * the page that follows the page after the end of the
+	 * previous buffer and is not page aligned. Examples:
+	 * buf1 ][ buf2 | buf2 | buf2 ][ ...
+	 * buf1 ]|[ buf2 | buf2 | buf2 ][ ...
+	 */
+	NEXT_NEXT_UNALIGNED,
+	LOOP_END,
+};
+
+static void pr_err_size_seq(size_t *sizes, int *seq)
+{
+	int i;
+
+	pr_err("alloc sizes: ");
+	for (i = 0; i < BUFFER_NUM; i++)
+		pr_cont("[%zu]", sizes[i]);
+	pr_cont("\n");
+	pr_err("free seq: ");
+	for (i = 0; i < BUFFER_NUM; i++)
+		pr_cont("[%d]", seq[i]);
+	pr_cont("\n");
+}
+
+static bool check_buffer_pages_allocated(struct binder_alloc *alloc,
+					 struct binder_buffer *buffer,
+					 size_t size)
+{
+	void __user *page_addr;
+	void __user *end;
+	int page_index;
+
+	end = (void __user *)PAGE_ALIGN((uintptr_t)buffer->user_data + size);
+	page_addr = buffer->user_data;
+	for (; page_addr < end; page_addr += PAGE_SIZE) {
+		page_index = (page_addr - alloc->buffer) / PAGE_SIZE;
+		if (!alloc->pages[page_index].page_ptr ||
+		    !list_empty(&alloc->pages[page_index].lru)) {
+			pr_err("expect alloc but is %s at page index %d\n",
+			       alloc->pages[page_index].page_ptr ?
+			       "lru" : "free", page_index);
+			return false;
+		}
+	}
+	return true;
+}
+
+static void binder_selftest_alloc_buf(struct binder_alloc *alloc,
+				      struct binder_buffer *buffers[],
+				      size_t *sizes, int *seq)
+{
+	int i;
+
+	for (i = 0; i < BUFFER_NUM; i++) {
+		buffers[i] = binder_alloc_new_buf(alloc, sizes[i], 0, 0, 0, 0);
+		if (IS_ERR(buffers[i]) ||
+		    !check_buffer_pages_allocated(alloc, buffers[i],
+						  sizes[i])) {
+			pr_err_size_seq(sizes, seq);
+			binder_selftest_failures++;
+		}
+	}
+}
+
+static void binder_selftest_free_buf(struct binder_alloc *alloc,
+				     struct binder_buffer *buffers[],
+				     size_t *sizes, int *seq, size_t end)
+{
+	int i;
+
+	for (i = 0; i < BUFFER_NUM; i++)
+		binder_alloc_free_buf(alloc, buffers[seq[i]]);
+
+	for (i = 0; i < end / PAGE_SIZE; i++) {
+		/**
+		 * Error message on a free page can be false positive
+		 * if binder shrinker ran during binder_alloc_free_buf
+		 * calls above.
+		 */
+		if (list_empty(&alloc->pages[i].lru)) {
+			pr_err_size_seq(sizes, seq);
+			pr_err("expect lru but is %s at page index %d\n",
+			       alloc->pages[i].page_ptr ? "alloc" : "free", i);
+			binder_selftest_failures++;
+		}
+	}
+}
+
+static void binder_selftest_free_page(struct binder_alloc *alloc)
+{
+	int i;
+	unsigned long count;
+
+	while ((count = list_lru_count(&binder_alloc_lru))) {
+		list_lru_walk(&binder_alloc_lru, binder_alloc_free_page,
+			      NULL, count);
+	}
+
+	for (i = 0; i < (alloc->buffer_size / PAGE_SIZE); i++) {
+		if (alloc->pages[i].page_ptr) {
+			pr_err("expect free but is %s at page index %d\n",
+			       list_empty(&alloc->pages[i].lru) ?
+			       "alloc" : "lru", i);
+			binder_selftest_failures++;
+		}
+	}
+}
+
+static void binder_selftest_alloc_free(struct binder_alloc *alloc,
+				       size_t *sizes, int *seq, size_t end)
+{
+	struct binder_buffer *buffers[BUFFER_NUM];
+
+	binder_selftest_alloc_buf(alloc, buffers, sizes, seq);
+	binder_selftest_free_buf(alloc, buffers, sizes, seq, end);
+
+	/* Allocate from lru. */
+	binder_selftest_alloc_buf(alloc, buffers, sizes, seq);
+	if (list_lru_count(&binder_alloc_lru))
+		pr_err("lru list should be empty but is not\n");
+
+	binder_selftest_free_buf(alloc, buffers, sizes, seq, end);
+	binder_selftest_free_page(alloc);
+}
+
+static bool is_dup(int *seq, int index, int val)
+{
+	int i;
+
+	for (i = 0; i < index; i++) {
+		if (seq[i] == val)
+			return true;
+	}
+	return false;
+}
+
+/* Generate BUFFER_NUM factorial free orders. */
+static void binder_selftest_free_seq(struct binder_alloc *alloc,
+				     size_t *sizes, int *seq,
+				     int index, size_t end)
+{
+	int i;
+
+	if (index == BUFFER_NUM) {
+		binder_selftest_alloc_free(alloc, sizes, seq, end);
+		return;
+	}
+	for (i = 0; i < BUFFER_NUM; i++) {
+		if (is_dup(seq, index, i))
+			continue;
+		seq[index] = i;
+		binder_selftest_free_seq(alloc, sizes, seq, index + 1, end);
+	}
+}
+
+static void binder_selftest_alloc_size(struct binder_alloc *alloc,
+				       size_t *end_offset)
+{
+	int i;
+	int seq[BUFFER_NUM] = {0};
+	size_t front_sizes[BUFFER_NUM];
+	size_t back_sizes[BUFFER_NUM];
+	size_t last_offset, offset = 0;
+
+	for (i = 0; i < BUFFER_NUM; i++) {
+		last_offset = offset;
+		offset = end_offset[i];
+		front_sizes[i] = offset - last_offset;
+		back_sizes[BUFFER_NUM - i - 1] = front_sizes[i];
+	}
+	/*
+	 * Buffers share the first or last few pages.
+	 * Only BUFFER_NUM - 1 buffer sizes are adjustable since
+	 * we need one giant buffer before getting to the last page.
+	 */
+	back_sizes[0] += alloc->buffer_size - end_offset[BUFFER_NUM - 1];
+	binder_selftest_free_seq(alloc, front_sizes, seq, 0,
+				 end_offset[BUFFER_NUM - 1]);
+	binder_selftest_free_seq(alloc, back_sizes, seq, 0, alloc->buffer_size);
+}
+
+static void binder_selftest_alloc_offset(struct binder_alloc *alloc,
+					 size_t *end_offset, int index)
+{
+	int align;
+	size_t end, prev;
+
+	if (index == BUFFER_NUM) {
+		binder_selftest_alloc_size(alloc, end_offset);
+		return;
+	}
+	prev = index == 0 ? 0 : end_offset[index - 1];
+	end = prev;
+
+	BUILD_BUG_ON(BUFFER_MIN_SIZE * BUFFER_NUM >= PAGE_SIZE);
+
+	for (align = SAME_PAGE_UNALIGNED; align < LOOP_END; align++) {
+		if (align % 2)
+			end = ALIGN(end, PAGE_SIZE);
+		else
+			end += BUFFER_MIN_SIZE;
+		end_offset[index] = end;
+		binder_selftest_alloc_offset(alloc, end_offset, index + 1);
+	}
+}
+
+/**
+ * binder_selftest_alloc() - Test alloc and free of buffer pages.
+ * @alloc: Pointer to alloc struct.
+ *
+ * Allocate BUFFER_NUM buffers to cover all page alignment cases,
+ * then free them in all orders possible. Check that pages are
+ * correctly allocated, put onto lru when buffers are freed, and
+ * are freed when binder_alloc_free_page is called.
+ */
+void binder_selftest_alloc(struct binder_alloc *alloc)
+{
+	size_t end_offset[BUFFER_NUM];
+
+	if (!binder_selftest_run)
+		return;
+	mutex_lock(&binder_selftest_lock);
+	if (!binder_selftest_run || !alloc->vma)
+		goto done;
+	pr_info("STARTED\n");
+	binder_selftest_alloc_offset(alloc, end_offset, 0);
+	binder_selftest_run = false;
+	if (binder_selftest_failures > 0)
+		pr_info("%d tests FAILED\n", binder_selftest_failures);
+	else
+		pr_info("PASSED\n");
+
+done:
+	mutex_unlock(&binder_selftest_lock);
+}

drivers/android/binder_internal.h

@@ -0,0 +1,155 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_BINDER_INTERNAL_H
+#define _LINUX_BINDER_INTERNAL_H
+
+#include <linux/export.h>
+#include <linux/fs.h>
+#include <linux/list.h>
+#include <linux/miscdevice.h>
+#include <linux/mutex.h>
+#include <linux/refcount.h>
+#include <linux/stddef.h>
+#include <linux/types.h>
+#include <linux/uidgid.h>
+
+#ifdef CONFIG_ANDROID_BINDER_USER_TRACKING
+#include <linux/rtc.h>
+#include <linux/time.h>
+#endif
+
+struct binder_context {
+	struct binder_node *binder_context_mgr_node;
+	struct mutex context_mgr_node_lock;
+	kuid_t binder_context_mgr_uid;
+	const char *name;
+};
+
+/**
+ * struct binder_device - information about a binder device node
+ * @hlist:          list of binder devices (only used for devices requested via
+ *                  CONFIG_ANDROID_BINDER_DEVICES)
+ * @miscdev:        information about a binder character device node
+ * @context:        binder context information
+ * @binderfs_inode: This is the inode of the root dentry of the super block
+ *                  belonging to a binderfs mount.
+ */
+struct binder_device {
+	struct hlist_node hlist;
+	struct miscdevice miscdev;
+	struct binder_context context;
+	struct inode *binderfs_inode;
+	refcount_t ref;
+};
+
+/**
+ * binderfs_mount_opts - mount options for binderfs
+ * @max: maximum number of allocatable binderfs binder devices
+ * @stats_mode: enable binder stats in binderfs.
+ */
+struct binderfs_mount_opts {
+	int max;
+	int stats_mode;
+};
+
+/**
+ * binderfs_info - information about a binderfs mount
+ * @ipc_ns:         The ipc namespace the binderfs mount belongs to.
+ * @control_dentry: This records the dentry of this binderfs mount
+ *                  binder-control device.
+ * @root_uid:       uid that needs to be used when a new binder device is
+ *                  created.
+ * @root_gid:       gid that needs to be used when a new binder device is
+ *                  created.
+ * @mount_opts:     The mount options in use.
+ * @device_count:   The current number of allocated binder devices.
+ * @proc_log_dir:   Pointer to the directory dentry containing process-specific
+ *                  logs.
+ */
+struct binderfs_info {
+	struct ipc_namespace *ipc_ns;
+	struct dentry *control_dentry;
+	kuid_t root_uid;
+	kgid_t root_gid;
+	struct binderfs_mount_opts mount_opts;
+	int device_count;
+	struct dentry *proc_log_dir;
+};
+
+extern const struct file_operations binder_fops;
+
+extern char *binder_devices_param;
+
+#ifdef CONFIG_ANDROID_BINDERFS
+extern bool is_binderfs_device(const struct inode *inode);
+extern struct dentry *binderfs_create_file(struct dentry *dir, const char *name,
+					   const struct file_operations *fops,
+					   void *data);
+extern void binderfs_remove_file(struct dentry *dentry);
+#else
+static inline bool is_binderfs_device(const struct inode *inode)
+{
+	return false;
+}
+static inline struct dentry *binderfs_create_file(struct dentry *dir,
+					   const char *name,
+					   const struct file_operations *fops,
+					   void *data)
+{
+	return NULL;
+}
+static inline void binderfs_remove_file(struct dentry *dentry) {}
+#endif
+
+#ifdef CONFIG_ANDROID_BINDERFS
+extern int __init init_binderfs(void);
+#else
+static inline int __init init_binderfs(void)
+{
+	return 0;
+}
+#endif
+
+int binder_stats_show(struct seq_file *m, void *unused);
+DEFINE_SHOW_ATTRIBUTE(binder_stats);
+
+int binder_state_show(struct seq_file *m, void *unused);
+DEFINE_SHOW_ATTRIBUTE(binder_state);
+
+int binder_transactions_show(struct seq_file *m, void *unused);
+DEFINE_SHOW_ATTRIBUTE(binder_transactions);
+
+int binder_transaction_log_show(struct seq_file *m, void *unused);
+DEFINE_SHOW_ATTRIBUTE(binder_transaction_log);
+
+struct binder_transaction_log_entry {
+	int debug_id;
+	int debug_id_done;
+	int call_type;
+	int from_proc;
+	int from_thread;
+	int target_handle;
+	int to_proc;
+	int to_thread;
+	int to_node;
+	int data_size;
+	int offsets_size;
+	int return_error_line;
+	uint32_t return_error;
+	uint32_t return_error_param;
+	const char *context_name;
+#ifdef CONFIG_ANDROID_BINDER_USER_TRACKING
+	struct timespec timestamp;
+	struct timeval tv;
+#endif
+};
+
+struct binder_transaction_log {
+	atomic_t cur;
+	bool full;
+	struct binder_transaction_log_entry entry[32];
+};
+
+extern struct binder_transaction_log binder_transaction_log;
+extern struct binder_transaction_log binder_transaction_log_failed;
+#endif /* _LINUX_BINDER_INTERNAL_H */

drivers/android/binder_trace.h

@@ -0,0 +1,414 @@
+/*
+ * Copyright (C) 2012 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.
+ *
+ */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM binder
+
+#if !defined(_BINDER_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _BINDER_TRACE_H
+
+#include <linux/tracepoint.h>
+
+struct binder_buffer;
+struct binder_node;
+struct binder_proc;
+struct binder_alloc;
+struct binder_ref_data;
+struct binder_thread;
+struct binder_transaction;
+
+TRACE_EVENT(binder_ioctl,
+	TP_PROTO(unsigned int cmd, unsigned long arg),
+	TP_ARGS(cmd, arg),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, cmd)
+		__field(unsigned long, arg)
+	),
+	TP_fast_assign(
+		__entry->cmd = cmd;
+		__entry->arg = arg;
+	),
+	TP_printk("cmd=0x%x arg=0x%lx", __entry->cmd, __entry->arg)
+);
+
+DECLARE_EVENT_CLASS(binder_lock_class,
+	TP_PROTO(const char *tag),
+	TP_ARGS(tag),
+	TP_STRUCT__entry(
+		__field(const char *, tag)
+	),
+	TP_fast_assign(
+		__entry->tag = tag;
+	),
+	TP_printk("tag=%s", __entry->tag)
+);
+
+#define DEFINE_BINDER_LOCK_EVENT(name)	\
+DEFINE_EVENT(binder_lock_class, name,	\
+	TP_PROTO(const char *func), \
+	TP_ARGS(func))
+
+DEFINE_BINDER_LOCK_EVENT(binder_lock);
+DEFINE_BINDER_LOCK_EVENT(binder_locked);
+DEFINE_BINDER_LOCK_EVENT(binder_unlock);
+
+DECLARE_EVENT_CLASS(binder_function_return_class,
+	TP_PROTO(int ret),
+	TP_ARGS(ret),
+	TP_STRUCT__entry(
+		__field(int, ret)
+	),
+	TP_fast_assign(
+		__entry->ret = ret;
+	),
+	TP_printk("ret=%d", __entry->ret)
+);
+
+#define DEFINE_BINDER_FUNCTION_RETURN_EVENT(name)	\
+DEFINE_EVENT(binder_function_return_class, name,	\
+	TP_PROTO(int ret), \
+	TP_ARGS(ret))
+
+DEFINE_BINDER_FUNCTION_RETURN_EVENT(binder_ioctl_done);
+DEFINE_BINDER_FUNCTION_RETURN_EVENT(binder_write_done);
+DEFINE_BINDER_FUNCTION_RETURN_EVENT(binder_read_done);
+
+TRACE_EVENT(binder_set_priority,
+	TP_PROTO(int proc, int thread, unsigned int old_prio,
+		 unsigned int desired_prio, unsigned int new_prio),
+	TP_ARGS(proc, thread, old_prio, new_prio, desired_prio),
+
+	TP_STRUCT__entry(
+		__field(int, proc)
+		__field(int, thread)
+		__field(unsigned int, old_prio)
+		__field(unsigned int, new_prio)
+		__field(unsigned int, desired_prio)
+	),
+	TP_fast_assign(
+		__entry->proc = proc;
+		__entry->thread = thread;
+		__entry->old_prio = old_prio;
+		__entry->new_prio = new_prio;
+		__entry->desired_prio = desired_prio;
+	),
+	TP_printk("proc=%d thread=%d old=%d => new=%d desired=%d",
+		  __entry->proc, __entry->thread, __entry->old_prio,
+		  __entry->new_prio, __entry->desired_prio)
+);
+
+TRACE_EVENT(binder_wait_for_work,
+	TP_PROTO(bool proc_work, bool transaction_stack, bool thread_todo),
+	TP_ARGS(proc_work, transaction_stack, thread_todo),
+
+	TP_STRUCT__entry(
+		__field(bool, proc_work)
+		__field(bool, transaction_stack)
+		__field(bool, thread_todo)
+	),
+	TP_fast_assign(
+		__entry->proc_work = proc_work;
+		__entry->transaction_stack = transaction_stack;
+		__entry->thread_todo = thread_todo;
+	),
+	TP_printk("proc_work=%d transaction_stack=%d thread_todo=%d",
+		  __entry->proc_work, __entry->transaction_stack,
+		  __entry->thread_todo)
+);
+
+TRACE_EVENT(binder_transaction,
+	TP_PROTO(bool reply, struct binder_transaction *t,
+		 struct binder_node *target_node),
+	TP_ARGS(reply, t, target_node),
+	TP_STRUCT__entry(
+		__field(int, debug_id)
+		__field(int, target_node)
+		__field(int, to_proc)
+		__field(int, to_thread)
+		__field(int, reply)
+		__field(unsigned int, code)
+		__field(unsigned int, flags)
+	),
+	TP_fast_assign(
+		__entry->debug_id = t->debug_id;
+		__entry->target_node = target_node ? target_node->debug_id : 0;
+		__entry->to_proc = t->to_proc->pid;
+		__entry->to_thread = t->to_thread ? t->to_thread->pid : 0;
+		__entry->reply = reply;
+		__entry->code = t->code;
+		__entry->flags = t->flags;
+	),
+	TP_printk("transaction=%d dest_node=%d dest_proc=%d dest_thread=%d reply=%d flags=0x%x code=0x%x",
+		  __entry->debug_id, __entry->target_node,
+		  __entry->to_proc, __entry->to_thread,
+		  __entry->reply, __entry->flags, __entry->code)
+);
+
+TRACE_EVENT(binder_transaction_received,
+	TP_PROTO(struct binder_transaction *t),
+	TP_ARGS(t),
+
+	TP_STRUCT__entry(
+		__field(int, debug_id)
+	),
+	TP_fast_assign(
+		__entry->debug_id = t->debug_id;
+	),
+	TP_printk("transaction=%d", __entry->debug_id)
+);
+
+TRACE_EVENT(binder_transaction_node_to_ref,
+	TP_PROTO(struct binder_transaction *t, struct binder_node *node,
+		 struct binder_ref_data *rdata),
+	TP_ARGS(t, node, rdata),
+
+	TP_STRUCT__entry(
+		__field(int, debug_id)
+		__field(int, node_debug_id)
+		__field(binder_uintptr_t, node_ptr)
+		__field(int, ref_debug_id)
+		__field(uint32_t, ref_desc)
+	),
+	TP_fast_assign(
+		__entry->debug_id = t->debug_id;
+		__entry->node_debug_id = node->debug_id;
+		__entry->node_ptr = node->ptr;
+		__entry->ref_debug_id = rdata->debug_id;
+		__entry->ref_desc = rdata->desc;
+	),
+	TP_printk("transaction=%d node=%d src_ptr=0x%016llx ==> dest_ref=%d dest_desc=%d",
+		  __entry->debug_id, __entry->node_debug_id,
+		  (u64)__entry->node_ptr,
+		  __entry->ref_debug_id, __entry->ref_desc)
+);
+
+TRACE_EVENT(binder_transaction_ref_to_node,
+	TP_PROTO(struct binder_transaction *t, struct binder_node *node,
+		 struct binder_ref_data *rdata),
+	TP_ARGS(t, node, rdata),
+
+	TP_STRUCT__entry(
+		__field(int, debug_id)
+		__field(int, ref_debug_id)
+		__field(uint32_t, ref_desc)
+		__field(int, node_debug_id)
+		__field(binder_uintptr_t, node_ptr)
+	),
+	TP_fast_assign(
+		__entry->debug_id = t->debug_id;
+		__entry->ref_debug_id = rdata->debug_id;
+		__entry->ref_desc = rdata->desc;
+		__entry->node_debug_id = node->debug_id;
+		__entry->node_ptr = node->ptr;
+	),
+	TP_printk("transaction=%d node=%d src_ref=%d src_desc=%d ==> dest_ptr=0x%016llx",
+		  __entry->debug_id, __entry->node_debug_id,
+		  __entry->ref_debug_id, __entry->ref_desc,
+		  (u64)__entry->node_ptr)
+);
+
+TRACE_EVENT(binder_transaction_ref_to_ref,
+	TP_PROTO(struct binder_transaction *t, struct binder_node *node,
+		 struct binder_ref_data *src_ref,
+		 struct binder_ref_data *dest_ref),
+	TP_ARGS(t, node, src_ref, dest_ref),
+
+	TP_STRUCT__entry(
+		__field(int, debug_id)
+		__field(int, node_debug_id)
+		__field(int, src_ref_debug_id)
+		__field(uint32_t, src_ref_desc)
+		__field(int, dest_ref_debug_id)
+		__field(uint32_t, dest_ref_desc)
+	),
+	TP_fast_assign(
+		__entry->debug_id = t->debug_id;
+		__entry->node_debug_id = node->debug_id;
+		__entry->src_ref_debug_id = src_ref->debug_id;
+		__entry->src_ref_desc = src_ref->desc;
+		__entry->dest_ref_debug_id = dest_ref->debug_id;
+		__entry->dest_ref_desc = dest_ref->desc;
+	),
+	TP_printk("transaction=%d node=%d src_ref=%d src_desc=%d ==> dest_ref=%d dest_desc=%d",
+		  __entry->debug_id, __entry->node_debug_id,
+		  __entry->src_ref_debug_id, __entry->src_ref_desc,
+		  __entry->dest_ref_debug_id, __entry->dest_ref_desc)
+);
+
+TRACE_EVENT(binder_transaction_fd,
+	TP_PROTO(struct binder_transaction *t, int src_fd, int dest_fd),
+	TP_ARGS(t, src_fd, dest_fd),
+
+	TP_STRUCT__entry(
+		__field(int, debug_id)
+		__field(int, src_fd)
+		__field(int, dest_fd)
+	),
+	TP_fast_assign(
+		__entry->debug_id = t->debug_id;
+		__entry->src_fd = src_fd;
+		__entry->dest_fd = dest_fd;
+	),
+	TP_printk("transaction=%d src_fd=%d ==> dest_fd=%d",
+		  __entry->debug_id, __entry->src_fd, __entry->dest_fd)
+);
+
+DECLARE_EVENT_CLASS(binder_buffer_class,
+	TP_PROTO(struct binder_buffer *buf),
+	TP_ARGS(buf),
+	TP_STRUCT__entry(
+		__field(int, debug_id)
+		__field(size_t, data_size)
+		__field(size_t, offsets_size)
+		__field(size_t, extra_buffers_size)
+	),
+	TP_fast_assign(
+		__entry->debug_id = buf->debug_id;
+		__entry->data_size = buf->data_size;
+		__entry->offsets_size = buf->offsets_size;
+		__entry->extra_buffers_size = buf->extra_buffers_size;
+	),
+	TP_printk("transaction=%d data_size=%zd offsets_size=%zd extra_buffers_size=%zd",
+		  __entry->debug_id, __entry->data_size, __entry->offsets_size,
+		  __entry->extra_buffers_size)
+);
+
+DEFINE_EVENT(binder_buffer_class, binder_transaction_alloc_buf,
+	TP_PROTO(struct binder_buffer *buffer),
+	TP_ARGS(buffer));
+
+DEFINE_EVENT(binder_buffer_class, binder_transaction_buffer_release,
+	TP_PROTO(struct binder_buffer *buffer),
+	TP_ARGS(buffer));
+
+DEFINE_EVENT(binder_buffer_class, binder_transaction_failed_buffer_release,
+	TP_PROTO(struct binder_buffer *buffer),
+	TP_ARGS(buffer));
+
+TRACE_EVENT(binder_update_page_range,
+	TP_PROTO(struct binder_alloc *alloc, bool allocate,
+		 void __user *start, void __user *end),
+	TP_ARGS(alloc, allocate, start, end),
+	TP_STRUCT__entry(
+		__field(int, proc)
+		__field(bool, allocate)
+		__field(size_t, offset)
+		__field(size_t, size)
+	),
+	TP_fast_assign(
+		__entry->proc = alloc->pid;
+		__entry->allocate = allocate;
+		__entry->offset = start - alloc->buffer;
+		__entry->size = end - start;
+	),
+	TP_printk("proc=%d allocate=%d offset=%zu size=%zu",
+		  __entry->proc, __entry->allocate,
+		  __entry->offset, __entry->size)
+);
+
+DECLARE_EVENT_CLASS(binder_lru_page_class,
+	TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+	TP_ARGS(alloc, page_index),
+	TP_STRUCT__entry(
+		__field(int, proc)
+		__field(size_t, page_index)
+	),
+	TP_fast_assign(
+		__entry->proc = alloc->pid;
+		__entry->page_index = page_index;
+	),
+	TP_printk("proc=%d page_index=%zu",
+		  __entry->proc, __entry->page_index)
+);
+
+DEFINE_EVENT(binder_lru_page_class, binder_alloc_lru_start,
+	TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+	TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_alloc_lru_end,
+	TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+	TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_free_lru_start,
+	TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+	TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_free_lru_end,
+	TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+	TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_alloc_page_start,
+	TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+	TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_alloc_page_end,
+	TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+	TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_unmap_user_start,
+	TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+	TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_unmap_user_end,
+	TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+	TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_unmap_kernel_start,
+	TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+	TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_unmap_kernel_end,
+	TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+	TP_ARGS(alloc, page_index));
+
+TRACE_EVENT(binder_command,
+	TP_PROTO(uint32_t cmd),
+	TP_ARGS(cmd),
+	TP_STRUCT__entry(
+		__field(uint32_t, cmd)
+	),
+	TP_fast_assign(
+		__entry->cmd = cmd;
+	),
+	TP_printk("cmd=0x%x %s",
+		  __entry->cmd,
+		  _IOC_NR(__entry->cmd) < ARRAY_SIZE(binder_command_strings) ?
+			  binder_command_strings[_IOC_NR(__entry->cmd)] :
+			  "unknown")
+);
+
+TRACE_EVENT(binder_return,
+	TP_PROTO(uint32_t cmd),
+	TP_ARGS(cmd),
+	TP_STRUCT__entry(
+		__field(uint32_t, cmd)
+	),
+	TP_fast_assign(
+		__entry->cmd = cmd;
+	),
+	TP_printk("cmd=0x%x %s",
+		  __entry->cmd,
+		  _IOC_NR(__entry->cmd) < ARRAY_SIZE(binder_return_strings) ?
+			  binder_return_strings[_IOC_NR(__entry->cmd)] :
+			  "unknown")
+);
+
+#endif /* _BINDER_TRACE_H */
+
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE binder_trace
+#include <trace/define_trace.h>

drivers/android/binderfs.c

@@ -0,0 +1,794 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/compiler_types.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/fsnotify.h>
+#include <linux/gfp.h>
+#include <linux/idr.h>
+#include <linux/init.h>
+#include <linux/ipc_namespace.h>
+#include <linux/kdev_t.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/namei.h>
+#include <linux/magic.h>
+#include <linux/major.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/mount.h>
+#include <linux/parser.h>
+#include <linux/radix-tree.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/spinlock_types.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/user_namespace.h>
+#include <linux/xarray.h>
+#include <uapi/asm-generic/errno-base.h>
+#include <uapi/linux/android/binder.h>
+#include <uapi/linux/android/binderfs.h>
+
+#include "binder_internal.h"
+
+#define FIRST_INODE 1
+#define SECOND_INODE 2
+#define INODE_OFFSET 3
+#define INTSTRLEN 21
+#define BINDERFS_MAX_MINOR (1U << MINORBITS)
+/* Ensure that the initial ipc namespace always has devices available. */
+#define BINDERFS_MAX_MINOR_CAPPED (BINDERFS_MAX_MINOR - 4)
+
+static dev_t binderfs_dev;
+static DEFINE_MUTEX(binderfs_minors_mutex);
+static DEFINE_IDA(binderfs_minors);
+
+enum {
+	Opt_max,
+	Opt_stats_mode,
+	Opt_err
+};
+
+enum binderfs_stats_mode {
+	STATS_NONE,
+	STATS_GLOBAL,
+};
+
+static const match_table_t tokens = {
+	{ Opt_max, "max=%d" },
+	{ Opt_stats_mode, "stats=%s" },
+	{ Opt_err, NULL     }
+};
+
+static inline struct binderfs_info *BINDERFS_I(const struct inode *inode)
+{
+	return inode->i_sb->s_fs_info;
+}
+
+bool is_binderfs_device(const struct inode *inode)
+{
+	if (inode->i_sb->s_magic == BINDERFS_SUPER_MAGIC)
+		return true;
+
+	return false;
+}
+
+/**
+ * binderfs_binder_device_create - allocate inode from super block of a
+ *                                 binderfs mount
+ * @ref_inode: inode from wich the super block will be taken
+ * @userp:     buffer to copy information about new device for userspace to
+ * @req:       struct binderfs_device as copied from userspace
+ *
+ * This function allocates a new binder_device and reserves a new minor
+ * number for it.
+ * Minor numbers are limited and tracked globally in binderfs_minors. The
+ * function will stash a struct binder_device for the specific binder
+ * device in i_private of the inode.
+ * It will go on to allocate a new inode from the super block of the
+ * filesystem mount, stash a struct binder_device in its i_private field
+ * and attach a dentry to that inode.
+ *
+ * Return: 0 on success, negative errno on failure
+ */
+static int binderfs_binder_device_create(struct inode *ref_inode,
+					 struct binderfs_device __user *userp,
+					 struct binderfs_device *req)
+{
+	int minor, ret;
+	struct dentry *dentry, *root;
+	struct binder_device *device;
+	char *name = NULL;
+	size_t name_len;
+	struct inode *inode = NULL;
+	struct super_block *sb = ref_inode->i_sb;
+	struct binderfs_info *info = sb->s_fs_info;
+#if defined(CONFIG_IPC_NS)
+	bool use_reserve = (info->ipc_ns == &init_ipc_ns);
+#else
+	bool use_reserve = true;
+#endif
+
+	/* Reserve new minor number for the new device. */
+	mutex_lock(&binderfs_minors_mutex);
+	if (++info->device_count <= info->mount_opts.max)
+		minor = ida_alloc_max(&binderfs_minors,
+				      use_reserve ? BINDERFS_MAX_MINOR :
+						    BINDERFS_MAX_MINOR_CAPPED,
+				      GFP_KERNEL);
+	else
+		minor = -ENOSPC;
+	if (minor < 0) {
+		--info->device_count;
+		mutex_unlock(&binderfs_minors_mutex);
+		return minor;
+	}
+	mutex_unlock(&binderfs_minors_mutex);
+
+	ret = -ENOMEM;
+	device = kzalloc(sizeof(*device), GFP_KERNEL);
+	if (!device)
+		goto err;
+
+	inode = new_inode(sb);
+	if (!inode)
+		goto err;
+
+	inode->i_ino = minor + INODE_OFFSET;
+	inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
+	init_special_inode(inode, S_IFCHR | 0600,
+			   MKDEV(MAJOR(binderfs_dev), minor));
+	inode->i_fop = &binder_fops;
+	inode->i_uid = info->root_uid;
+	inode->i_gid = info->root_gid;
+
+	req->name[BINDERFS_MAX_NAME] = '\0'; /* NUL-terminate */
+	name_len = strlen(req->name);
+	/* Make sure to include terminating NUL byte */
+	name = kmemdup(req->name, name_len + 1, GFP_KERNEL);
+	if (!name)
+		goto err;
+
+	refcount_set(&device->ref, 1);
+	device->binderfs_inode = inode;
+	device->context.binder_context_mgr_uid = INVALID_UID;
+	device->context.name = name;
+	device->miscdev.name = name;
+	device->miscdev.minor = minor;
+	mutex_init(&device->context.context_mgr_node_lock);
+
+	req->major = MAJOR(binderfs_dev);
+	req->minor = minor;
+
+	if (userp && copy_to_user(userp, req, sizeof(*req))) {
+		ret = -EFAULT;
+		goto err;
+	}
+
+	root = sb->s_root;
+	inode_lock(d_inode(root));
+
+	/* look it up */
+	dentry = lookup_one_len(name, root, name_len);
+	if (IS_ERR(dentry)) {
+		inode_unlock(d_inode(root));
+		ret = PTR_ERR(dentry);
+		goto err;
+	}
+
+	if (d_really_is_positive(dentry)) {
+		/* already exists */
+		dput(dentry);
+		inode_unlock(d_inode(root));
+		ret = -EEXIST;
+		goto err;
+	}
+
+	inode->i_private = device;
+	d_instantiate(dentry, inode);
+	fsnotify_create(root->d_inode, dentry);
+	inode_unlock(d_inode(root));
+
+	return 0;
+
+err:
+	kfree(name);
+	kfree(device);
+	mutex_lock(&binderfs_minors_mutex);
+	--info->device_count;
+	ida_free(&binderfs_minors, minor);
+	mutex_unlock(&binderfs_minors_mutex);
+	iput(inode);
+
+	return ret;
+}
+
+/**
+ * binderfs_ctl_ioctl - handle binder device node allocation requests
+ *
+ * The request handler for the binder-control device. All requests operate on
+ * the binderfs mount the binder-control device resides in:
+ * - BINDER_CTL_ADD
+ *   Allocate a new binder device.
+ *
+ * Return: 0 on success, negative errno on failure
+ */
+static long binder_ctl_ioctl(struct file *file, unsigned int cmd,
+			     unsigned long arg)
+{
+	int ret = -EINVAL;
+	struct inode *inode = file_inode(file);
+	struct binderfs_device __user *device = (struct binderfs_device __user *)arg;
+	struct binderfs_device device_req;
+
+	switch (cmd) {
+	case BINDER_CTL_ADD:
+		ret = copy_from_user(&device_req, device, sizeof(device_req));
+		if (ret) {
+			ret = -EFAULT;
+			break;
+		}
+
+		ret = binderfs_binder_device_create(inode, device, &device_req);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+static void binderfs_evict_inode(struct inode *inode)
+{
+	struct binder_device *device = inode->i_private;
+	struct binderfs_info *info = BINDERFS_I(inode);
+
+	clear_inode(inode);
+
+	if (!S_ISCHR(inode->i_mode) || !device)
+		return;
+
+	mutex_lock(&binderfs_minors_mutex);
+	--info->device_count;
+	ida_free(&binderfs_minors, device->miscdev.minor);
+	mutex_unlock(&binderfs_minors_mutex);
+
+	if (refcount_dec_and_test(&device->ref)) {
+		kfree(device->context.name);
+		kfree(device);
+	}
+}
+
+/**
+ * binderfs_parse_mount_opts - parse binderfs mount options
+ * @data: options to set (can be NULL in which case defaults are used)
+ */
+static int binderfs_parse_mount_opts(char *data,
+				     struct binderfs_mount_opts *opts)
+{
+	char *p, *stats;
+	opts->max = BINDERFS_MAX_MINOR;
+	opts->stats_mode = STATS_NONE;
+
+	while ((p = strsep(&data, ",")) != NULL) {
+		substring_t args[MAX_OPT_ARGS];
+		int token;
+		int max_devices;
+
+		if (!*p)
+			continue;
+
+		token = match_token(p, tokens, args);
+		switch (token) {
+		case Opt_max:
+			if (match_int(&args[0], &max_devices) ||
+			    (max_devices < 0 ||
+			     (max_devices > BINDERFS_MAX_MINOR)))
+				return -EINVAL;
+
+			opts->max = max_devices;
+			break;
+		case Opt_stats_mode:
+			if (!capable(CAP_SYS_ADMIN))
+				return -EINVAL;
+
+			stats = match_strdup(&args[0]);
+			if (!stats)
+				return -ENOMEM;
+
+			if (strcmp(stats, "global") != 0) {
+				kfree(stats);
+				return -EINVAL;
+			}
+
+			opts->stats_mode = STATS_GLOBAL;
+			kfree(stats);
+			break;
+		default:
+			pr_err("Invalid mount options\n");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int binderfs_remount(struct super_block *sb, int *flags, char *data)
+{
+	int prev_stats_mode, ret;
+	struct binderfs_info *info = sb->s_fs_info;
+
+	prev_stats_mode = info->mount_opts.stats_mode;
+	ret = binderfs_parse_mount_opts(data, &info->mount_opts);
+	if (ret)
+		return ret;
+
+	if (prev_stats_mode != info->mount_opts.stats_mode) {
+		pr_err("Binderfs stats mode cannot be changed during a remount\n");
+		info->mount_opts.stats_mode = prev_stats_mode;
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int binderfs_show_mount_opts(struct seq_file *seq, struct dentry *root)
+{
+	struct binderfs_info *info;
+
+	info = root->d_sb->s_fs_info;
+	if (info->mount_opts.max <= BINDERFS_MAX_MINOR)
+		seq_printf(seq, ",max=%d", info->mount_opts.max);
+	if (info->mount_opts.stats_mode == STATS_GLOBAL)
+		seq_printf(seq, ",stats=global");
+
+	return 0;
+}
+
+static const struct super_operations binderfs_super_ops = {
+	.evict_inode    = binderfs_evict_inode,
+	.remount_fs	= binderfs_remount,
+	.show_options	= binderfs_show_mount_opts,
+	.statfs         = simple_statfs,
+};
+
+static inline bool is_binderfs_control_device(const struct dentry *dentry)
+{
+	struct binderfs_info *info = dentry->d_sb->s_fs_info;
+	return info->control_dentry == dentry;
+}
+
+static int binderfs_rename(struct inode *old_dir, struct dentry *old_dentry,
+			   struct inode *new_dir, struct dentry *new_dentry,
+			   unsigned int flags)
+{
+	if (is_binderfs_control_device(old_dentry) ||
+	    is_binderfs_control_device(new_dentry))
+		return -EPERM;
+
+	return simple_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
+}
+
+static int binderfs_unlink(struct inode *dir, struct dentry *dentry)
+{
+	if (is_binderfs_control_device(dentry))
+		return -EPERM;
+
+	return simple_unlink(dir, dentry);
+}
+
+static const struct file_operations binder_ctl_fops = {
+	.owner		= THIS_MODULE,
+	.open		= nonseekable_open,
+	.unlocked_ioctl	= binder_ctl_ioctl,
+	.compat_ioctl	= binder_ctl_ioctl,
+	.llseek		= noop_llseek,
+};
+
+/**
+ * binderfs_binder_ctl_create - create a new binder-control device
+ * @sb: super block of the binderfs mount
+ *
+ * This function creates a new binder-control device node in the binderfs mount
+ * referred to by @sb.
+ *
+ * Return: 0 on success, negative errno on failure
+ */
+static int binderfs_binder_ctl_create(struct super_block *sb)
+{
+	int minor, ret;
+	struct dentry *dentry;
+	struct binder_device *device;
+	struct inode *inode = NULL;
+	struct dentry *root = sb->s_root;
+	struct binderfs_info *info = sb->s_fs_info;
+#if defined(CONFIG_IPC_NS)
+	bool use_reserve = (info->ipc_ns == &init_ipc_ns);
+#else
+	bool use_reserve = true;
+#endif
+
+	device = kzalloc(sizeof(*device), GFP_KERNEL);
+	if (!device)
+		return -ENOMEM;
+
+	/* If we have already created a binder-control node, return. */
+	if (info->control_dentry) {
+		ret = 0;
+		goto out;
+	}
+
+	ret = -ENOMEM;
+	inode = new_inode(sb);
+	if (!inode)
+		goto out;
+
+	/* Reserve a new minor number for the new device. */
+	mutex_lock(&binderfs_minors_mutex);
+	minor = ida_alloc_max(&binderfs_minors,
+			      use_reserve ? BINDERFS_MAX_MINOR :
+					    BINDERFS_MAX_MINOR_CAPPED,
+			      GFP_KERNEL);
+	mutex_unlock(&binderfs_minors_mutex);
+	if (minor < 0) {
+		ret = minor;
+		goto out;
+	}
+
+	inode->i_ino = SECOND_INODE;
+	inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
+	init_special_inode(inode, S_IFCHR | 0600,
+			   MKDEV(MAJOR(binderfs_dev), minor));
+	inode->i_fop = &binder_ctl_fops;
+	inode->i_uid = info->root_uid;
+	inode->i_gid = info->root_gid;
+
+	refcount_set(&device->ref, 1);
+	device->binderfs_inode = inode;
+	device->miscdev.minor = minor;
+
+	dentry = d_alloc_name(root, "binder-control");
+	if (!dentry)
+		goto out;
+
+	inode->i_private = device;
+	info->control_dentry = dentry;
+	d_add(dentry, inode);
+
+	return 0;
+
+out:
+	kfree(device);
+	iput(inode);
+
+	return ret;
+}
+
+static const struct inode_operations binderfs_dir_inode_operations = {
+	.lookup = simple_lookup,
+	.rename = binderfs_rename,
+	.unlink = binderfs_unlink,
+};
+
+static struct inode *binderfs_make_inode(struct super_block *sb, int mode)
+{
+	struct inode *ret;
+
+	ret = new_inode(sb);
+	if (ret) {
+		ret->i_ino = iunique(sb, BINDERFS_MAX_MINOR + INODE_OFFSET);
+		ret->i_mode = mode;
+		ret->i_atime = ret->i_mtime = ret->i_ctime = current_time(ret);
+	}
+	return ret;
+}
+
+static struct dentry *binderfs_create_dentry(struct dentry *parent,
+					     const char *name)
+{
+	struct dentry *dentry;
+
+	dentry = lookup_one_len(name, parent, strlen(name));
+	if (IS_ERR(dentry))
+		return dentry;
+
+	/* Return error if the file/dir already exists. */
+	if (d_really_is_positive(dentry)) {
+		dput(dentry);
+		return ERR_PTR(-EEXIST);
+	}
+
+	return dentry;
+}
+
+void binderfs_remove_file(struct dentry *dentry)
+{
+	struct inode *parent_inode;
+
+	parent_inode = d_inode(dentry->d_parent);
+	inode_lock(parent_inode);
+	if (simple_positive(dentry)) {
+		dget(dentry);
+		simple_unlink(parent_inode, dentry);
+		d_delete(dentry);
+		dput(dentry);
+	}
+	inode_unlock(parent_inode);
+}
+
+struct dentry *binderfs_create_file(struct dentry *parent, const char *name,
+				    const struct file_operations *fops,
+				    void *data)
+{
+	struct dentry *dentry;
+	struct inode *new_inode, *parent_inode;
+	struct super_block *sb;
+
+	parent_inode = d_inode(parent);
+	inode_lock(parent_inode);
+
+	dentry = binderfs_create_dentry(parent, name);
+	if (IS_ERR(dentry))
+		goto out;
+
+	sb = parent_inode->i_sb;
+	new_inode = binderfs_make_inode(sb, S_IFREG | 0444);
+	if (!new_inode) {
+		dput(dentry);
+		dentry = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	new_inode->i_fop = fops;
+	new_inode->i_private = data;
+	d_instantiate(dentry, new_inode);
+	fsnotify_create(parent_inode, dentry);
+
+out:
+	inode_unlock(parent_inode);
+	return dentry;
+}
+
+static struct dentry *binderfs_create_dir(struct dentry *parent,
+					  const char *name)
+{
+	struct dentry *dentry;
+	struct inode *new_inode, *parent_inode;
+	struct super_block *sb;
+
+	parent_inode = d_inode(parent);
+	inode_lock(parent_inode);
+
+	dentry = binderfs_create_dentry(parent, name);
+	if (IS_ERR(dentry))
+		goto out;
+
+	sb = parent_inode->i_sb;
+	new_inode = binderfs_make_inode(sb, S_IFDIR | 0755);
+	if (!new_inode) {
+		dput(dentry);
+		dentry = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	new_inode->i_fop = &simple_dir_operations;
+	new_inode->i_op = &simple_dir_inode_operations;
+
+	set_nlink(new_inode, 2);
+	d_instantiate(dentry, new_inode);
+	inc_nlink(parent_inode);
+	fsnotify_mkdir(parent_inode, dentry);
+
+out:
+	inode_unlock(parent_inode);
+	return dentry;
+}
+
+static int init_binder_logs(struct super_block *sb)
+{
+	struct dentry *binder_logs_root_dir, *dentry, *proc_log_dir;
+	struct binderfs_info *info;
+	int ret = 0;
+
+	binder_logs_root_dir = binderfs_create_dir(sb->s_root,
+						   "binder_logs");
+	if (IS_ERR(binder_logs_root_dir)) {
+		ret = PTR_ERR(binder_logs_root_dir);
+		goto out;
+	}
+
+	dentry = binderfs_create_file(binder_logs_root_dir, "stats",
+				      &binder_stats_fops, NULL);
+	if (IS_ERR(dentry)) {
+		ret = PTR_ERR(dentry);
+		goto out;
+	}
+
+	dentry = binderfs_create_file(binder_logs_root_dir, "state",
+				      &binder_state_fops, NULL);
+	if (IS_ERR(dentry)) {
+		ret = PTR_ERR(dentry);
+		goto out;
+	}
+
+	dentry = binderfs_create_file(binder_logs_root_dir, "transactions",
+				      &binder_transactions_fops, NULL);
+	if (IS_ERR(dentry)) {
+		ret = PTR_ERR(dentry);
+		goto out;
+	}
+
+	dentry = binderfs_create_file(binder_logs_root_dir,
+				      "transaction_log",
+				      &binder_transaction_log_fops,
+				      &binder_transaction_log);
+	if (IS_ERR(dentry)) {
+		ret = PTR_ERR(dentry);
+		goto out;
+	}
+
+	dentry = binderfs_create_file(binder_logs_root_dir,
+				      "failed_transaction_log",
+				      &binder_transaction_log_fops,
+				      &binder_transaction_log_failed);
+	if (IS_ERR(dentry)) {
+		ret = PTR_ERR(dentry);
+		goto out;
+	}
+
+	proc_log_dir = binderfs_create_dir(binder_logs_root_dir, "proc");
+	if (IS_ERR(proc_log_dir)) {
+		ret = PTR_ERR(proc_log_dir);
+		goto out;
+	}
+	info = sb->s_fs_info;
+	info->proc_log_dir = proc_log_dir;
+
+out:
+	return ret;
+}
+
+static int binderfs_fill_super(struct super_block *sb, void *data, int silent)
+{
+	int ret;
+	struct binderfs_info *info;
+	struct inode *inode = NULL;
+	struct binderfs_device device_info = { 0 };
+	const char *name;
+	size_t len;
+
+	sb->s_blocksize = PAGE_SIZE;
+	sb->s_blocksize_bits = PAGE_SHIFT;
+
+	/*
+	 * The binderfs filesystem can be mounted by userns root in a
+	 * non-initial userns. By default such mounts have the SB_I_NODEV flag
+	 * set in s_iflags to prevent security issues where userns root can
+	 * just create random device nodes via mknod() since it owns the
+	 * filesystem mount. But binderfs does not allow to create any files
+	 * including devices nodes. The only way to create binder devices nodes
+	 * is through the binder-control device which userns root is explicitly
+	 * allowed to do. So removing the SB_I_NODEV flag from s_iflags is both
+	 * necessary and safe.
+	 */
+	sb->s_iflags &= ~SB_I_NODEV;
+	sb->s_iflags |= SB_I_NOEXEC;
+	sb->s_magic = BINDERFS_SUPER_MAGIC;
+	sb->s_op = &binderfs_super_ops;
+	sb->s_time_gran = 1;
+
+	sb->s_fs_info = kzalloc(sizeof(struct binderfs_info), GFP_KERNEL);
+	if (!sb->s_fs_info)
+		return -ENOMEM;
+	info = sb->s_fs_info;
+
+	info->ipc_ns = get_ipc_ns(current->nsproxy->ipc_ns);
+
+	ret = binderfs_parse_mount_opts(data, &info->mount_opts);
+	if (ret)
+		return ret;
+
+	info->root_gid = make_kgid(sb->s_user_ns, 0);
+	if (!gid_valid(info->root_gid))
+		info->root_gid = GLOBAL_ROOT_GID;
+	info->root_uid = make_kuid(sb->s_user_ns, 0);
+	if (!uid_valid(info->root_uid))
+		info->root_uid = GLOBAL_ROOT_UID;
+
+	inode = new_inode(sb);
+	if (!inode)
+		return -ENOMEM;
+
+	inode->i_ino = FIRST_INODE;
+	inode->i_fop = &simple_dir_operations;
+	inode->i_mode = S_IFDIR | 0755;
+	inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
+	inode->i_op = &binderfs_dir_inode_operations;
+	set_nlink(inode, 2);
+
+	sb->s_root = d_make_root(inode);
+	if (!sb->s_root)
+		return -ENOMEM;
+
+	ret = binderfs_binder_ctl_create(sb);
+	if (ret)
+		return ret;
+
+	name = binder_devices_param;
+	for (len = strcspn(name, ","); len > 0; len = strcspn(name, ",")) {
+		strscpy(device_info.name, name, len + 1);
+		ret = binderfs_binder_device_create(inode, NULL, &device_info);
+		if (ret)
+			return ret;
+		name += len;
+		if (*name == ',')
+			name++;
+	}
+
+	if (info->mount_opts.stats_mode == STATS_GLOBAL)
+		return init_binder_logs(sb);
+
+	return 0;
+}
+
+static struct dentry *binderfs_mount(struct file_system_type *fs_type,
+				     int flags, const char *dev_name,
+				     void *data)
+{
+	return mount_nodev(fs_type, flags, data, binderfs_fill_super);
+}
+
+static void binderfs_kill_super(struct super_block *sb)
+{
+	struct binderfs_info *info = sb->s_fs_info;
+
+	kill_litter_super(sb);
+
+	if (info && info->ipc_ns)
+		put_ipc_ns(info->ipc_ns);
+
+	kfree(info);
+}
+
+static struct file_system_type binder_fs_type = {
+	.name		= "binder",
+	.mount		= binderfs_mount,
+	.kill_sb	= binderfs_kill_super,
+	.fs_flags	= FS_USERNS_MOUNT,
+};
+
+int __init init_binderfs(void)
+{
+	int ret;
+	const char *name;
+	size_t len;
+
+	/* Verify that the default binderfs device names are valid. */
+	name = binder_devices_param;
+	for (len = strcspn(name, ","); len > 0; len = strcspn(name, ",")) {
+		if (len > BINDERFS_MAX_NAME)
+			return -E2BIG;
+		name += len;
+		if (*name == ',')
+			name++;
+	}
+
+	/* Allocate new major number for binderfs. */
+	ret = alloc_chrdev_region(&binderfs_dev, 0, BINDERFS_MAX_MINOR,
+				  "binder");
+	if (ret)
+		return ret;
+
+	ret = register_filesystem(&binder_fs_type);
+	if (ret) {
+		unregister_chrdev_region(binderfs_dev, BINDERFS_MAX_MINOR);
+		return ret;
+	}
+
+	return ret;
+}