Android日志系统分析之日志设备驱动程序代码阅读

android日志系统中定义了设备驱动的实现代码位于kernel/common/drivers/staging/android/logger.h和kernel/common/drivers/staging/android/logger.c中。

首先，我们阅读logger.h文件代码。

struct logger_entry {
	__u16		len;	/* length of the payload */
	__u16		__pad;	/* no matter what, we get 2 bytes of padding */
	__s32		pid;	/* generating process's pid */
	__s32		tid;	/* generating process's tid */
	__s32		sec;	/* seconds since Epoch */
	__s32		nsec;	/* nanoseconds */
	char		msg[0];	/* the entry's payload */
};
/*
结构体logger_entry定义了日志系统数据的头部信息，其中len定义了负载的长度，__pad主要是用作数据域的对齐，提高数据结构访问的效率。pid是输出日志信息的进程的pid，　tid是输出日志信息的进程的tid。sec和nsec构成了日志输出时的时间。msg代表负载的开始处。负载就是我们要输出的一些字符串信息，它们的大小本身是不会影响logger_entry结构体本身的大小。事实上，logger_entry结构体可视为一个可变大小的结构体定义的范例。
*/
#define LOGGER_LOG_RADIO	"log_radio"	/* radio-related messages */
#define LOGGER_LOG_EVENTS	"log_events"	/* system/hardware events */
#define LOGGER_LOG_MAIN		"log_main"	/* everything else */
//上述三个宏定义了日志信息的三种类型。
#define LOGGER_ENTRY_MAX_LEN		(4*1024)
#define LOGGER_ENTRY_MAX_PAYLOAD	\
	(LOGGER_ENTRY_MAX_LEN - sizeof(struct logger_entry))
//上述宏实际上定义了日志缓冲区的最大值。
#define __LOGGERIO	0xAE
//定义ioctl命令码的设备类型为0xAE
#define LOGGER_GET_LOG_BUF_SIZE		_IO(__LOGGERIO, 1) /* size of log */
#define LOGGER_GET_LOG_LEN		_IO(__LOGGERIO, 2) /* used log len */
#define LOGGER_GET_NEXT_ENTRY_LEN	_IO(__LOGGERIO, 3) /* next entry len */
#define LOGGER_FLUSH_LOG		_IO(__LOGGERIO, 4) /* flush log */

再来阅读logger.c代码：

/*
 * struct logger_log - represents a specific log, such as 'main' or 'radio'
 *
 * This structure lives from module insertion until module removal, so it does
 * not need additional reference counting. The structure is protected by the
 * mutex 'mutex'.
 */
struct logger_log {
	unsigned char *		buffer;	/* the ring buffer itself */
	struct miscdevice	misc;	/* misc device representing the log */
	wait_queue_head_t	wq;	/* wait queue for readers */
	struct list_head	readers; /* this log's readers */
	struct mutex		mutex;	/* mutex protecting buffer */
	size_t			w_off;	/* current write head offset */
	size_t			head;	/* new readers start here */
	size_t			size;	/* size of the log */
};
/*该结构体定义了日志的结构，在该数据结构中，定义了一个环形缓冲区*/
/*
 * struct logger_reader - a logging device open for reading
 *
 * This object lives from open to release, so we don't need additional
 * reference counting. The structure is protected by log->mutex.
 */
struct logger_reader {
	struct logger_log *	log;	/* associated log */
	struct list_head	list;	/* entry in logger_log's list */
	size_t			r_off;	/* current read head offset */
};
/*该数据结构定义了一个设备结构体，用于读日志信息*/
/* logger_offset - returns index 'n' into the log via (optimized) modulus */
#define logger_offset(n)	((n) & (log->size - 1))
/*通过模运算返回索引号n在log中对应的offset。*/
/*
 * file_get_log - Given a file structure, return the associated log
 *
 * This isn't aesthetic. We have several goals:
 *
 * 	1) Need to quickly obtain the associated log during an I/O operation
 * 	2) Readers need to maintain state (logger_reader)
 * 	3) Writers need to be very fast (open() should be a near no-op)
 *
 * In the reader case, we can trivially go file->logger_reader->logger_log.
 * For a writer, we don't want to maintain a logger_reader, so we just go
 * file->logger_log. Thus what file->private_data points at depends on whether
 * or not the file was opened for reading. This function hides that dirtiness.
 */
static inline struct logger_log * file_get_log(struct file *file)
{
　　　/*当在读模式下时*/
	if (file->f_mode & FMODE_READ) {
		struct logger_reader *reader = file->private_data;
		return reader->log;
	} else
		return file->private_data;
}
/*返回与file相关联的logger_log结构体。*/
/*
 * get_entry_len - Grabs the length of the payload of the next entry starting
 * from 'off'.
 *
 * Caller needs to hold log->mutex.
 */
static __u32 get_entry_len(struct logger_log *log, size_t off)
{
	__u16 val;
　　　//log->buffer的开始处是头，而头的前两个字节记录了负载的长度
	switch (log->size - off) {
	case 1:
		memcpy(&val, log->buffer + off, 1);
		memcpy(((char *) &val) + 1, log->buffer, 1);
		break;
	default:
		memcpy(&val, log->buffer + off, 2);
	}
　　　//因为负载的长度不包含头的数据结构大小，所以要加上头部大小
	return sizeof(struct logger_entry) + val;
}
/*返回位于下一个位于off处的日志项负载的大小，注意该大小包括日志项结构体本身的大小*/
/*
 * do_read_log_to_user - reads exactly 'count' bytes from 'log' into the
 * user-space buffer 'buf'. Returns 'count' on success.
 *
 * Caller must hold log->mutex.
 */
static ssize_t do_read_log_to_user(struct logger_log *log,
				   struct logger_reader *reader,
				   char __user *buf,
				   size_t count)
{
	size_t len;
      /*因为缓冲区是环形的，所以当从offset开始到缓冲区的最后一位之间的大小小于count时，就要分两步读，第一次读到缓冲区末尾，第二次从缓冲区开始处读取剩余的字节大小的数据*/
	/*
	 * We read from the log in two disjoint operations. First, we read from
	 * the current read head offset up to 'count' bytes or to the end of
	 * the log, whichever comes first.
	 */
	len = min(count, log->size - reader->r_off);
	if (copy_to_user(buf, log->buffer + reader->r_off, len))
		return -EFAULT;

	/*
	 * Second, we read any remaining bytes, starting back at the head of
	 * the log.
	 */
　　　/*当count == len时，表明缓冲区从当前位置到结尾处的大小大于count*/
	if (count != len)
		if (copy_to_user(buf + len, log->buffer, count - len))
			return -EFAULT;
　　　//重新计算当前的offset
	reader->r_off = logger_offset(reader->r_off + count);

	return count;
}
/*返回log中的数据到用户空间的缓冲区*/
/*
 * logger_read - our log's read() method
 *
 * Behavior:
 *
 * 	- O_NONBLOCK works
 * 	- If there are no log entries to read, blocks until log is written to
 * 	- Atomically reads exactly one log entry
 *
 * Optimal read size is LOGGER_ENTRY_MAX_LEN. Will set errno to EINVAL if read
 * buffer is insufficient to hold next entry.
 */
static ssize_t logger_read(struct file *file, char __user *buf,
			   size_t count, loff_t *pos)
{
	struct logger_reader *reader = file->private_data;
	struct logger_log *log = reader->log;
	ssize_t ret;
	DEFINE_WAIT(wait);
　　　//定义一个等待队列项，它将在等待队列log->wq上休眠

start:
	while (1) {
		prepare_to_wait(&log->wq, &wait, TASK_INTERRUPTIBLE);
　　　　　　//将当前进程加入等待队列中，等待可中断
		mutex_lock(&log->mutex);
		ret = (log->w_off == reader->r_off);
		mutex_unlock(&log->mutex);
		if (!ret)　//只要log->w_off != reader->r_off即可读
			break;
　　　　　　//在非阻塞状态下，立即返回
		if (file->f_flags & O_NONBLOCK) {
			ret = -EAGAIN;
			break;
		}
　　　　　　//处理收到的系统信号
		if (signal_pending(current)) {
			ret = -EINTR;
			break;
		}

		schedule();
	}

	finish_wait(&log->wq, &wait);
	if (ret)
		return ret;

	mutex_lock(&log->mutex);

	/* is there still something to read or did we race? */
	if (unlikely(log->w_off == reader->r_off)) {
		mutex_unlock(&log->mutex);
		goto start;
	}

	/* get the size of the next entry */
	ret = get_entry_len(log, reader->r_off);
	if (count < ret) {
		ret = -EINVAL;
		goto out;
	}

	/* get exactly one entry from the log */
	ret = do_read_log_to_user(log, reader, buf, ret);

out:
	mutex_unlock(&log->mutex);

	return ret;
}

/*
 * get_next_entry - return the offset of the first valid entry at least 'len'
 * bytes after 'off'.
 *
 * Caller must hold log->mutex.
 */
static size_t get_next_entry(struct logger_log *log, size_t off, size_t len)
{
	size_t count = 0;
　　　//找到第一个超过当off至少len长的第一个合法的日志项的offset。
	do {
		size_t nr = get_entry_len(log, off);
		off = logger_offset(off + nr);
		count += nr;
	} while (count < len);

	return off;
}

/*
 * clock_interval - is a < c < b in mod-space? Put another way, does the line
 * from a to b cross c?
 */
static inline int clock_interval(size_t a, size_t b, size_t c)
{
	if (b < a) {
		if (a < c || b >= c)
			return 1;
	} else {
		if (a < c && b >= c)
			return 1;
	}

	return 0;
}

/*
 * fix_up_readers - walk the list of all readers and "fix up" any who were
 * lapped by the writer; also do the same for the default "start head".
 * We do this by "pulling forward" the readers and start head to the first
 * entry after the new write head.
 *
 * The caller needs to hold log->mutex.
 */
static void fix_up_readers(struct logger_log *log, size_t len)
{
	size_t old = log->w_off;
	size_t new = logger_offset(old + len);
	struct logger_reader *reader;
      //修正log->head，　将其后移len
	if (clock_interval(old, new, log->head))
		log->head = get_next_entry(log, log->head, len);
　　　//修正所有当前的reader->r_off与log->w_off的距离小于len的日志项，将reader->r_off后移len个单位。
	list_for_each_entry(reader, &log->readers, list)
		if (clock_interval(old, new, reader->r_off))
			reader->r_off = get_next_entry(log, reader->r_off, len);
}

/*
 * do_write_log - writes 'len' bytes from 'buf' to 'log'
 *
 * The caller needs to hold log->mutex.
 */
static void do_write_log(struct logger_log *log, const void *buf, size_t count)
{
	size_t len;
　　　//写入count个字节的数据，
	len = min(count, log->size - log->w_off);
	memcpy(log->buffer + log->w_off, buf, len);
　　　//当count-len大于零时，将剩余的数据从开头处开始写入
	if (count != len)
		memcpy(log->buffer, buf + len, count - len);

	log->w_off = logger_offset(log->w_off + count);

}

/*
 * do_write_log_user - writes 'len' bytes from the user-space buffer 'buf' to
 * the log 'log'
 *
 * The caller needs to hold log->mutex.
 *
 * Returns 'count' on success, negative error code on failure.
 */
static ssize_t do_write_log_from_user(struct logger_log *log,
				      const void __user *buf, size_t count)
{
	size_t len;

	len = min(count, log->size - log->w_off);
	if (len && copy_from_user(log->buffer + log->w_off, buf, len))
		return -EFAULT;

	if (count != len)
		if (copy_from_user(log->buffer, buf + len, count - len))
			return -EFAULT;

	log->w_off = logger_offset(log->w_off + count);

	return count;
}

/*
 * logger_aio_write - our write method, implementing support for write(),
 * writev(), and aio_write(). Writes are our fast path, and we try to optimize
 * them above all else.
 */
ssize_t logger_aio_write(struct kiocb *iocb, const struct iovec *iov,
			 unsigned long nr_segs, loff_t ppos)
{
	struct logger_log *log = file_get_log(iocb->ki_filp);
	size_t orig = log->w_off;
	struct logger_entry header;
	struct timespec now;
	ssize_t ret = 0;

	now = current_kernel_time();

	header.pid = current->tgid;
	header.tid = current->pid;
	header.sec = now.tv_sec;
	header.nsec = now.tv_nsec;
	header.len = min_t(size_t, iocb->ki_left, LOGGER_ENTRY_MAX_PAYLOAD);

	/* null writes succeed, return zero */
	if (unlikely(!header.len))
		return 0;

	mutex_lock(&log->mutex);

	/*
	 * Fix up any readers, pulling them forward to the first readable
	 * entry after (what will be) the new write offset. We do this now
	 * because if we partially fail, we can end up with clobbered log
	 * entries that encroach on readable buffer.
	 */
	fix_up_readers(log, sizeof(struct logger_entry) + header.len);

	do_write_log(log, &header, sizeof(struct logger_entry));

	while (nr_segs-- > 0) {
		size_t len;
		ssize_t nr;

		/* figure out how much of this vector we can keep */
		len = min_t(size_t, iov->iov_len, header.len - ret);

		/* write out this segment's payload */
		nr = do_write_log_from_user(log, iov->iov_base, len);
		if (unlikely(nr < 0)) {
			log->w_off = orig;
			mutex_unlock(&log->mutex);
			return nr;
		}

		iov++;
		ret += nr;
	}

	mutex_unlock(&log->mutex);

	/* wake up any blocked readers */
	wake_up_interruptible(&log->wq);

	return ret;
}

static struct logger_log * get_log_from_minor(int);

/*
 * logger_open - the log's open() file operation
 *
 * Note how near a no-op this is in the write-only case. Keep it that way!
 */
static int logger_open(struct inode *inode, struct file *file)
{
	struct logger_log *log;
	int ret;

	ret = nonseekable_open(inode, file);
	if (ret)
		return ret;

	log = get_log_from_minor(MINOR(inode->i_rdev));
	if (!log)
		return -ENODEV;

	if (file->f_mode & FMODE_READ) {
		struct logger_reader *reader;

		reader = kmalloc(sizeof(struct logger_reader), GFP_KERNEL);
		if (!reader)
			return -ENOMEM;

		reader->log = log;
		INIT_LIST_HEAD(&reader->list);

		mutex_lock(&log->mutex);
　　　　　　//设置reader->r_off的初始值为log当前的读位置
		reader->r_off = log->head;
		list_add_tail(&reader->list, &log->readers);
		mutex_unlock(&log->mutex);

		file->private_data = reader;
	} else
		file->private_data = log;

	return 0;
}

/*
 * logger_release - the log's release file operation
 *
 * Note this is a total no-op in the write-only case. Keep it that way!
 */
static int logger_release(struct inode *ignored, struct file *file)
{
　　　//只有在读模式下才会去释放分配的内存空间
	if (file->f_mode & FMODE_READ) {
		struct logger_reader *reader = file->private_data;
		list_del(&reader->list);
		kfree(reader);
	}

	return 0;
}

/*
 * logger_poll - the log's poll file operation, for poll/select/epoll
 *
 * Note we always return POLLOUT, because you can always write() to the log.
 * Note also that, strictly speaking, a return value of POLLIN does not
 * guarantee that the log is readable without blocking, as there is a small
 * chance that the writer can lap the reader in the interim between poll()
 * returning and the read() request.
 */
static unsigned int logger_poll(struct file *file, poll_table *wait)
{
	struct logger_reader *reader;
	struct logger_log *log;
	unsigned int ret = POLLOUT | POLLWRNORM;
　　　//总是可写的
	if (!(file->f_mode & FMODE_READ))
		return ret;

	reader = file->private_data;
	log = reader->log;
　　　//将当前进行添加到wait指定的等待列表(轮询表)中
	poll_wait(file, &log->wq, wait);

	mutex_lock(&log->mutex);
	if (log->w_off != reader->r_off)
		ret |= POLLIN | POLLRDNORM;
	mutex_unlock(&log->mutex);

	return ret;
}
//ioctl实现函数
static long logger_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
	struct logger_log *log = file_get_log(file);
	struct logger_reader *reader;
	long ret = -ENOTTY;

	mutex_lock(&log->mutex);

	switch (cmd) {
	case LOGGER_GET_LOG_BUF_SIZE:
		ret = log->size;
		break;
	case LOGGER_GET_LOG_LEN:
		if (!(file->f_mode & FMODE_READ)) {
			ret = -EBADF;
			break;
		}
		reader = file->private_data;
		if (log->w_off >= reader->r_off)
			ret = log->w_off - reader->r_off;
		else
			ret = (log->size - reader->r_off) + log->w_off;
		break;
	case LOGGER_GET_NEXT_ENTRY_LEN:
		if (!(file->f_mode & FMODE_READ)) {
			ret = -EBADF;
			break;
		}
		reader = file->private_data;
		if (log->w_off != reader->r_off)
			ret = get_entry_len(log, reader->r_off);
		else
			ret = 0;
		break;
	case LOGGER_FLUSH_LOG:
		if (!(file->f_mode & FMODE_WRITE)) {
			ret = -EBADF;
			break;
		}
		list_for_each_entry(reader, &log->readers, list)
			reader->r_off = log->w_off;
		log->head = log->w_off;
		ret = 0;
		break;
	}

	mutex_unlock(&log->mutex);

	return ret;
}
//定义字符设备操作
static struct file_operations logger_fops = {
	.owner = THIS_MODULE,
	.read = logger_read,
	.aio_write = logger_aio_write,
	.poll = logger_poll,
	.unlocked_ioctl = logger_ioctl,
	.compat_ioctl = logger_ioctl,
	.open = logger_open,
	.release = logger_release,
};

/*
 * Defines a log structure with name 'NAME' and a size of 'SIZE' bytes, which
 * must be a power of two, greater than LOGGER_ENTRY_MAX_LEN, and less than
 * LONG_MAX minus LOGGER_ENTRY_MAX_LEN.
 */
#define DEFINE_LOGGER_DEVICE(VAR, NAME, SIZE) \
static unsigned char _buf_ ## VAR[SIZE]; \
static struct logger_log VAR = { \
	.buffer = _buf_ ## VAR, \
	.misc = { \
		.minor = MISC_DYNAMIC_MINOR, \
		.name = NAME, \
		.fops = &logger_fops, \
		.parent = NULL, \
	}, \
	.wq = __WAIT_QUEUE_HEAD_INITIALIZER(VAR .wq), \
	.readers = LIST_HEAD_INIT(VAR .readers), \
	.mutex = __MUTEX_INITIALIZER(VAR .mutex), \
	.w_off = 0, \
	.head = 0, \
	.size = SIZE, \
};
//分别定义三个不同的字符设备
DEFINE_LOGGER_DEVICE(log_main, LOGGER_LOG_MAIN, 64*1024)
DEFINE_LOGGER_DEVICE(log_events, LOGGER_LOG_EVENTS, 256*1024)
DEFINE_LOGGER_DEVICE(log_radio, LOGGER_LOG_RADIO, 64*1024)
//根据次设备号返回相应的设备
static struct logger_log * get_log_from_minor(int minor)
{
	if (log_main.misc.minor == minor)
		return &log_main;
	if (log_events.misc.minor == minor)
		return &log_events;
	if (log_radio.misc.minor == minor)
		return &log_radio;
	return NULL;
}

static int __init init_log(struct logger_log *log)
{
	int ret;
　　　//注册混杂字符设备
	ret = misc_register(&log->misc);
	if (unlikely(ret)) {
		printk(KERN_ERR "logger: failed to register misc "
		       "device for log '%s'!\n", log->misc.name);
		return ret;
	}

	printk(KERN_INFO "logger: created %luK log '%s'\n",
	       (unsigned long) log->size >> 10, log->misc.name);

	return 0;
}
//字符设备初始化
static int __init logger_init(void)
{
	int ret;

	ret = init_log(&log_main);
	if (unlikely(ret))
		goto out;

	ret = init_log(&log_events);
	if (unlikely(ret))
		goto out;

	ret = init_log(&log_radio);
	if (unlikely(ret))
		goto out;

out:
	return ret;
}
device_initcall(logger_init);