logger.c

Go to the documentation of this file.

/*
 * drivers/misc/logger.c
 *
 * A Logging Subsystem
 *
 * Copyright (C) 2007-2008 Google, Inc.
 *
 * Robert Love <[email protected]>
 *
 * 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) "logger: " fmt

#include <linux/sched.h>
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/miscdevice.h>
#include <linux/uaccess.h>
#include <linux/poll.h>
#include <linux/slab.h>
#include <linux/time.h>
#include <linux/vmalloc.h>
#include "logger.h"

#include <asm/ioctls.h>

struct logger_log {
    unsigned char       *buffer;
    struct miscdevice   misc;
    wait_queue_head_t   wq;
    struct list_head    readers;
    struct mutex        mutex;
    size_t          w_off;
    size_t          head;
    size_t          size;
    struct list_head    logs;
};

static LIST_HEAD(log_list);


struct logger_reader {
    struct logger_log   *log;
    struct list_head    list;
    size_t          r_off;
};

/* logger_offset - returns index 'n' into the log via (optimized) modulus */
static size_t logger_offset(struct logger_log *log, size_t n)
{
    return n & (log->size - 1);
}


/*
 * 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)
{
    if (file->f_mode & FMODE_READ) {
        struct logger_reader *reader = file->private_data;
        return reader->log;
    } else
        return file->private_data;
}

/*
 * get_entry_len - Grabs the length of the payload of the next entry starting
 * from 'off'.
 *
 * An entry length is 2 bytes (16 bits) in host endian order.
 * In the log, the length does not include the size of the log entry structure.
 * This function returns the size including the log entry structure.
 *
 * Caller needs to hold log->mutex.
 */
static __u32 get_entry_len(struct logger_log *log, size_t off)
{
    __u16 val;

    /* copy 2 bytes from buffer, in memcpy order, */
    /* handling possible wrap at end of buffer */

    ((__u8 *)&val)[0] = log->buffer[off];
    if (likely(off+1 < log->size))
        ((__u8 *)&val)[1] = log->buffer[off+1];
    else
        ((__u8 *)&val)[1] = log->buffer[0];

    return sizeof(struct logger_entry) + val;
}

/*
 * 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;

    /*
     * 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(log, reader->r_off + count);

    return count;
}

/*
 * 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) {
        mutex_lock(&log->mutex);

        prepare_to_wait(&log->wq, &wait, TASK_INTERRUPTIBLE);

        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;
}

/*
 * 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(log, off + nr);
        count += nr;
    } while (count < len);

    return off;
}

/*
 * is_between - is a < c < b, accounting for wrapping of a, b, and c
 *    positions in the buffer
 *
 * That is, if a<b, check for c between a and b
 * and if a>b, check for c outside (not between) a and b
 *
 * |------- a xxxxxxxx b --------|
 *               c^
 *
 * |xxxxx b --------- a xxxxxxxxx|
 *    c^
 *  or                    c^
 */
static inline int is_between(size_t a, size_t b, size_t c)
{
    if (a < b) {
        /* is c between a and b? */
        if (a < c && c <= b)
            return 1;
    } else {
        /* is c outside of b through a? */
        if (c <= b || a < 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(log, old + len);
    struct logger_reader *reader;

    if (is_between(old, new, log->head))
        log->head = get_next_entry(log, log->head, len);

    list_for_each_entry(reader, &log->readers, list)
        if (is_between(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;

    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, 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))
            /*
             * Note that by not updating w_off, this abandons the
             * portion of the new entry that *was* successfully
             * copied, just above.  This is intentional to avoid
             * message corruption from missing fragments.
             */
            return -EFAULT;

    log->w_off = logger_offset(log, 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.
 */
static 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 minor)
{
    struct logger_log *log;

    list_for_each_entry(log, &log_list, logs)
        if (log->misc.minor == minor)
            return log;
    return NULL;
}

/*
 * 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;
}

/*
 * 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)
{
    if (file->f_mode & FMODE_READ) {
        struct logger_reader *reader = file->private_data;
        struct logger_log *log = reader->log;

        mutex_lock(&log->mutex);
        list_del(&reader->list);
        mutex_unlock(&log->mutex);

        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;

    if (!(file->f_mode & FMODE_READ))
        return ret;

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

    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;
}

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;
}

static const 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,
};

/*
 * Log size must be a power of two, greater than LOGGER_ENTRY_MAX_LEN,
 * and less than LONG_MAX minus LOGGER_ENTRY_MAX_LEN.
 */
static int __init create_log(char *log_name, int size)
{
    int ret = 0;
    struct logger_log *log;
    unsigned char *buffer;

    buffer = vmalloc(size);
    if (buffer == NULL)
        return -ENOMEM;

    log = kzalloc(sizeof(struct logger_log), GFP_KERNEL);
    if (log == NULL) {
        ret = -ENOMEM;
        goto out_free_buffer;
    }
    log->buffer = buffer;

    log->misc.minor = MISC_DYNAMIC_MINOR;
    log->misc.name = kstrdup(log_name, GFP_KERNEL);
    if (log->misc.name == NULL) {
        ret = -ENOMEM;
        goto out_free_log;
    }

    log->misc.fops = &logger_fops;
    log->misc.parent = NULL;

    init_waitqueue_head(&log->wq);
    INIT_LIST_HEAD(&log->readers);
    mutex_init(&log->mutex);
    log->w_off = 0;
    log->head = 0;
    log->size = size;

    INIT_LIST_HEAD(&log->logs);
    list_add_tail(&log->logs, &log_list);

    /* finally, initialize the misc device for this log */
    ret = misc_register(&log->misc);
    if (unlikely(ret)) {
        pr_err("failed to register misc device for log '%s'!\n",
                log->misc.name);
        goto out_free_log;
    }

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

    return 0;

out_free_log:
    kfree(log);

out_free_buffer:
    vfree(buffer);
    return ret;
}

static int __init logger_init(void)
{
    int ret;

    ret = create_log(LOGGER_LOG_MAIN, 256*1024);
    if (unlikely(ret))
        goto out;

    ret = create_log(LOGGER_LOG_EVENTS, 256*1024);
    if (unlikely(ret))
        goto out;

    ret = create_log(LOGGER_LOG_RADIO, 256*1024);
    if (unlikely(ret))
        goto out;

    ret = create_log(LOGGER_LOG_SYSTEM, 256*1024);
    if (unlikely(ret))
        goto out;

out:
    return ret;
}
device_initcall(logger_init);