參考：http://blog.csdn.net/luoshengyang/article/details/6595744
內核中的日誌文件：
kernel/common/drivers/staging/android/logger.h
kernel/common/drivers/staging/android/logger.c
一、Logger的數據結構：
#ifndef _LINUX_LOGGER_H
#define _LINUX_LOGGER_H
#include <linux/types.h>
#include <linux/ioctl.h>
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 */
};
#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 */
#define LOGGER_ENTRY_MAX_LEN (4*1024)
#define LOGGER_ENTRY_MAX_PAYLOAD \
(LOGGER_ENTRY_MAX_LEN - sizeof(struct logger_entry))
#define __LOGGERIO 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 */
#endif /* _LINUX_LOGGER_H */struct logger_entry是一個用於描述一條Log記錄的結構體。
len成員變量：記錄了這條記錄的有效負載的長度，有效負載指定的日誌記錄本身的長度，但是不包括用於描述這個記錄的struct logger_entry結構體。回憶一下我們調用android.util.Log接口來使用日誌系統時，會指定日誌的優先級別Priority、Tag字符串以及Msg字符串，Priority + Tag + Msg三者內容的長度加起來就是記錄的有效負載長度了。
__pad成員變量：是用來對齊結構體的。
pid和tid成員變量：分別用來記錄是哪條進程寫入了這條記錄。
sec和nsec成員變量：記錄日誌寫的時間。
msg成員變量：記錄的就有效負載的內容了，它的大小由len成員變量來確定。
接着定義兩個宏：
#define LOGGER_ENTRY_MAX_LEN (4*1024)
#define LOGGER_ENTRY_MAX_PAYLOAD \
(LOGGER_ENTRY_MAX_LEN - sizeof(struct logger_entry))
從這兩個宏可以看出，每條日誌記錄的有效負載長度加上結構體logger_entry的長度不能超過4K個字節。
再看logger.c
/*
* 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 */
};
/*
* 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 */
};
/* logger_offset - returns index 'n' into the log via (optimized) modulus */
#define logger_offset(n) ((n) & (log->size - 1))buffer成員變量：是用保存日誌信息的內存緩衝區，它的大小由size成員變量確定。
misc成員變量：可以看出，logger驅動程序使用的設備屬於misc類型的設備，通過在Android模擬器上執行cat /proc/devices命令可以看出，misc類型設備的主設備號是10。
wq成員變量：是一個等待隊列，用於保存正在等待讀取日誌的進程。
readers成員變量：用來保存當前正在讀取日誌的進程，正在讀取日誌的進程由結構體logger_reader來描述。
mutex成員變量：是一個互斥量，用來保護log的併發訪問。可以看出，這裏的日誌系統的讀寫問題，其實是一個生產者-消費者的問題，因此，需要互斥量來保護log的併發訪問。
w_off成員變量：用來記錄下一條日誌應該從哪裏開始寫。
head成員變量：用來表示打開日誌文件中，應該從哪一個位置開始讀取日誌。
結構體struct logger_reader用來表示一個讀取日誌的進程，log成員變量指向要讀取的日誌緩衝區。list成員變量用來連接其它讀者進程。r_off成員變量表示當前要讀取的日誌在緩衝區中的位置。
struct logger_log結構體中用於保存日誌信息的內存緩衝區buffer是一個循環使用的環形緩衝區，緩衝區中保存的內容是以struct logger_entry爲單位的，每個單位的組成爲：
struct logger_entry | priority | tag | msg
由於是內存緩衝區buffer是一個循環使用的環形緩衝區，給定一個偏移值，它在buffer中的位置由下logger_offset來確定：
#define logger_offset(n) ((n) & (log->size - 1)) 很常用的一種取緩衝器的方法
二. Logger驅動程序模塊的初始化過程分析
繼續看logger.c文件，定義了三個日誌設備：
/*
* 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, \
};
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)
#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 */
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,
};
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);
static int __init init_log(struct logger_log *log)
{
int ret;
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;
}/**
* misc_register - register a miscellaneous device
* @misc: device structure
*
* Register a miscellaneous device with the kernel. If the minor
* number is set to %MISC_DYNAMIC_MINOR a minor number is assigned
* and placed in the minor field of the structure. For other cases
* the minor number requested is used.
*
* The structure passed is linked into the kernel and may not be
* destroyed until it has been unregistered.
*
* A zero is returned on success and a negative errno code for
* failure.
*/
int misc_register(struct miscdevice * misc)
{
struct miscdevice *c;
dev_t dev;
int err = 0;
INIT_LIST_HEAD(&misc->list);
mutex_lock(&misc_mtx);
list_for_each_entry(c, &misc_list, list) {
if (c->minor == misc->minor) {
mutex_unlock(&misc_mtx);
return -EBUSY;
}
}
if (misc->minor == MISC_DYNAMIC_MINOR) {
int i = DYNAMIC_MINORS;
while (--i >= 0)
if ( (misc_minors[i>>3] & (1 << (i&7))) == 0)
break;
if (i<0) {
mutex_unlock(&misc_mtx);
return -EBUSY;
}
misc->minor = i;
}
if (misc->minor < DYNAMIC_MINORS)
misc_minors[misc->minor >> 3] |= 1 << (misc->minor & 7);
dev = MKDEV(MISC_MAJOR, misc->minor);
misc->this_device = device_create(misc_class, misc->parent, dev, NULL,
"%s", misc->name);
if (IS_ERR(misc->this_device)) {
err = PTR_ERR(misc->this_device);
goto out;
}
/*
* Add it to the front, so that later devices can "override"
* earlier defaults
*/
list_add(&misc->list, &misc_list);
out:
mutex_unlock(&misc_mtx);
return err;
}三. Logger驅動程序的日誌記錄讀取過程分析。
繼續看logger.c 文件，註冊的讀取日誌設備文件的方法爲logger_read：
/*
* 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);
start:
while (1) {
prepare_to_wait(&log->wq, &wait, TASK_INTERRUPTIBLE);
mutex_lock(&log->mutex);
ret = (log->w_off == reader->r_off);
mutex_unlock(&log->mutex);
if (!ret)
break;
if (file->f_flags & O_NONBLOCK) {
ret = -EAGAIN;
break;
}
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;
}/*
* 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);
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;
}
start標號處的while循環是在等待日誌可讀，如果已經沒有新的日誌可讀了，那麼就要讀進程就要進入休眠狀態，等待新的日誌寫入後再喚醒，這是通過prepare_wait和schedule兩個調用來實現的。如果沒有新的日誌可讀，並且設備文件不是以非阻塞O_NONBLOCK的方式打開或者這時有信號要處理（signal_pending(current)），那麼就直接返回，不再等待新的日誌寫入。判斷當前是否有新的日誌可讀的方法是：
ret = (log->w_off == reader->r_off);
即判斷當前緩衝區的寫入位置和當前讀進程的讀取位置是否相等，如果不相等，則說明有新的日誌可讀。
w_off : 當前緩衝區的寫入位置
r_off : 當前讀進程的讀取位置
繼續向下看，如果有新的日誌可讀，那麼就，首先通過get_entry_len來獲取下一條可讀的日誌記錄的長度，從這裏可以看出，日誌讀取進程是以日誌記錄爲單位進行讀取的，一次只讀取一條記錄。get_entry_len的函數實現如下：
/*
* 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;
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);
}
return sizeof(struct logger_entry) + val;
}接着往下看，得到了要讀取的記錄的長度，就調用do_read_log_to_user函數來執行真正的讀取動作：
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;
/*
* 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.
*/
if (count != len)
if (copy_to_user(buf + len, log->buffer, count - len))
return -EFAULT;
reader->r_off = logger_offset(reader->r_off + count);
return count;
}
四. Logger驅動程序的日誌記錄寫入過程分析。
繼續看logger.c 文件，註冊的寫入日誌設備文件的方法爲logger_aio_write：
/*
* 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;
}輸入的參數:
iocb: 表示io上下文
iov: 表示要寫入的內容
nr_segs: 長度，表示有nr_segs個段的內容要寫入。我們知道，每個要寫入的日誌的結構形式爲：
struct logger_entry | priority | tag | msg
其中， priority、tag和msg這三個段的內容是由iov參數從用戶空間傳遞下來的，分別對應iov裏面的三個元素。
而logger_entry是由內核空間來構造的：
struct logger_entry header;
struct timespec now;
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);
然後調用do_write_log首先把logger_entry結構體寫入到日誌緩衝區中：
/*
* 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;
len = min(count, log->size - log->w_off);
memcpy(log->buffer + log->w_off, buf, len);
if (count != len)
memcpy(log->buffer, buf + len, count - len);
log->w_off = logger_offset(log->w_off + count);
}
接着，通過一個while循環把iov的內容寫入到日誌緩衝區中，也就是日誌的優先級別priority、日誌Tag和日誌主體Msg：
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;
}由於iov的內容是由用戶空間傳下來的，需要調用do_write_log_from_user來寫入：
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;
}
/*
* 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);
/*
* 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;
if (clock_interval(old, new, log->head))
log->head = get_next_entry(log, log->head, len);
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);
}/*
* 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;
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;
}
/* wake up any blocked readers */
wake_up_interruptible(&log->wq);