audit.c

		printk(" (until reboot)");
	}
	printk("\n");

	return 1;
}

__setup("audit=", audit_enable);

static void audit_buffer_free(struct audit_buffer *ab)
{
	unsigned long flags;

	if (!ab)
		return;

	if (ab->skb)
		kfree_skb(ab->skb);

	spin_lock_irqsave(&audit_freelist_lock, flags);
	if (audit_freelist_count > AUDIT_MAXFREE)
		kfree(ab);
	else {
		audit_freelist_count++;
		list_add(&ab->list, &audit_freelist);
	}
	spin_unlock_irqrestore(&audit_freelist_lock, flags);
}

static struct audit_buffer * audit_buffer_alloc(struct audit_context *ctx,
						gfp_t gfp_mask, int type)
{
	unsigned long flags;
	struct audit_buffer *ab = NULL;
	struct nlmsghdr *nlh;

	spin_lock_irqsave(&audit_freelist_lock, flags);
	if (!list_empty(&audit_freelist)) {
		ab = list_entry(audit_freelist.next,
				struct audit_buffer, list);
		list_del(&ab->list);
		--audit_freelist_count;
	}
	spin_unlock_irqrestore(&audit_freelist_lock, flags);

	if (!ab) {
		ab = kmalloc(sizeof(*ab), gfp_mask);
		if (!ab)
			goto err;
	}

	ab->ctx = ctx;
	ab->gfp_mask = gfp_mask;

	ab->skb = nlmsg_new(AUDIT_BUFSIZ, gfp_mask);
	if (!ab->skb)
		goto err;

	nlh = nlmsg_put(ab->skb, 0, 0, type, 0, 0);
	if (!nlh)
		goto out_kfree_skb;

	return ab;

out_kfree_skb:
	kfree_skb(ab->skb);
	ab->skb = NULL;
err:
	audit_buffer_free(ab);
	return NULL;
}

/**
 * audit_serial - compute a serial number for the audit record
 *
 * Compute a serial number for the audit record.  Audit records are
 * written to user-space as soon as they are generated, so a complete
 * audit record may be written in several pieces.  The timestamp of the
 * record and this serial number are used by the user-space tools to
 * determine which pieces belong to the same audit record.  The
 * (timestamp,serial) tuple is unique for each syscall and is live from
 * syscall entry to syscall exit.
 *
 * NOTE: Another possibility is to store the formatted records off the
 * audit context (for those records that have a context), and emit them
 * all at syscall exit.  However, this could delay the reporting of
 * significant errors until syscall exit (or never, if the system
 * halts).
 */
unsigned int audit_serial(void)
{
	static DEFINE_SPINLOCK(serial_lock);
	static unsigned int serial = 0;

	unsigned long flags;
	unsigned int ret;

	spin_lock_irqsave(&serial_lock, flags);
	do {
		ret = ++serial;
	} while (unlikely(!ret));
	spin_unlock_irqrestore(&serial_lock, flags);

	return ret;
}

static inline void audit_get_stamp(struct audit_context *ctx,
				   struct timespec *t, unsigned int *serial)
{
	if (!ctx || !auditsc_get_stamp(ctx, t, serial)) {
		*t = CURRENT_TIME;
		*serial = audit_serial();
	}
}

/*
 * Wait for auditd to drain the queue a little
 */
static void wait_for_auditd(unsigned long sleep_time)
{
	DECLARE_WAITQUEUE(wait, current);
	set_current_state(TASK_INTERRUPTIBLE);
	add_wait_queue(&audit_backlog_wait, &wait);

	if (audit_backlog_limit &&
	    skb_queue_len(&audit_skb_queue) > audit_backlog_limit)
		schedule_timeout(sleep_time);

	__set_current_state(TASK_RUNNING);
	remove_wait_queue(&audit_backlog_wait, &wait);
}

/* Obtain an audit buffer.  This routine does locking to obtain the
 * audit buffer, but then no locking is required for calls to
 * audit_log_*format.  If the tsk is a task that is currently in a
 * syscall, then the syscall is marked as auditable and an audit record
 * will be written at syscall exit.  If there is no associated task, tsk
 * should be NULL. */

/**
 * audit_log_start - obtain an audit buffer
 * @ctx: audit_context (may be NULL)
 * @gfp_mask: type of allocation
 * @type: audit message type
 *
 * Returns audit_buffer pointer on success or NULL on error.
 *
 * Obtain an audit buffer.  This routine does locking to obtain the
 * audit buffer, but then no locking is required for calls to
 * audit_log_*format.  If the task (ctx) is a task that is currently in a
 * syscall, then the syscall is marked as auditable and an audit record
 * will be written at syscall exit.  If there is no associated task, then
 * task context (ctx) should be NULL.
 */
struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
				     int type)
{
	struct audit_buffer	*ab	= NULL;
	struct timespec		t;
	unsigned int		uninitialized_var(serial);
	int reserve;
	unsigned long timeout_start = jiffies;

	if (audit_initialized != AUDIT_INITIALIZED)
		return NULL;

	if (unlikely(audit_filter_type(type)))
		return NULL;

	if (gfp_mask & __GFP_WAIT)
		reserve = 0;
	else
		reserve = 5; /* Allow atomic callers to go up to five
				entries over the normal backlog limit */

	while (audit_backlog_limit
	       && skb_queue_len(&audit_skb_queue) > audit_backlog_limit + reserve) {
		if (gfp_mask & __GFP_WAIT && audit_backlog_wait_time) {
			unsigned long sleep_time;

			sleep_time = timeout_start + audit_backlog_wait_time -
					jiffies;
			if ((long)sleep_time > 0)
				wait_for_auditd(sleep_time);
			continue;
		}
		if (audit_rate_check() && printk_ratelimit())
			printk(KERN_WARNING
			       "audit: audit_backlog=%d > "
			       "audit_backlog_limit=%d\n",
			       skb_queue_len(&audit_skb_queue),
			       audit_backlog_limit);
		audit_log_lost("backlog limit exceeded");
		audit_backlog_wait_time = audit_backlog_wait_overflow;
		wake_up(&audit_backlog_wait);
		return NULL;
	}

	ab = audit_buffer_alloc(ctx, gfp_mask, type);
	if (!ab) {
		audit_log_lost("out of memory in audit_log_start");
		return NULL;
	}

	audit_get_stamp(ab->ctx, &t, &serial);

	audit_log_format(ab, "audit(%lu.%03lu:%u): ",
			 t.tv_sec, t.tv_nsec/1000000, serial);
	return ab;
}

/**
 * audit_expand - expand skb in the audit buffer
 * @ab: audit_buffer
 * @extra: space to add at tail of the skb
 *
 * Returns 0 (no space) on failed expansion, or available space if
 * successful.
 */
static inline int audit_expand(struct audit_buffer *ab, int extra)
{
	struct sk_buff *skb = ab->skb;
	int oldtail = skb_tailroom(skb);
	int ret = pskb_expand_head(skb, 0, extra, ab->gfp_mask);
	int newtail = skb_tailroom(skb);

	if (ret < 0) {
		audit_log_lost("out of memory in audit_expand");
		return 0;
	}

	skb->truesize += newtail - oldtail;
	return newtail;
}

/*
 * Format an audit message into the audit buffer.  If there isn't enough
 * room in the audit buffer, more room will be allocated and vsnprint
 * will be called a second time.  Currently, we assume that a printk
 * can't format message larger than 1024 bytes, so we don't either.
 */
static void audit_log_vformat(struct audit_buffer *ab, const char *fmt,
			      va_list args)
{
	int len, avail;
	struct sk_buff *skb;
	va_list args2;

	if (!ab)
		return;

	BUG_ON(!ab->skb);
	skb = ab->skb;
	avail = skb_tailroom(skb);
	if (avail == 0) {
		avail = audit_expand(ab, AUDIT_BUFSIZ);
		if (!avail)
			goto out;
	}
	va_copy(args2, args);
	len = vsnprintf(skb_tail_pointer(skb), avail, fmt, args);
	if (len >= avail) {
		/* The printk buffer is 1024 bytes long, so if we get
		 * here and AUDIT_BUFSIZ is at least 1024, then we can
		 * log everything that printk could have logged. */
		avail = audit_expand(ab,
			max_t(unsigned, AUDIT_BUFSIZ, 1+len-avail));
		if (!avail)
			goto out_va_end;
		len = vsnprintf(skb_tail_pointer(skb), avail, fmt, args2);
	}
	if (len > 0)
		skb_put(skb, len);
out_va_end:
	va_end(args2);
out:
	return;
}

/**
 * audit_log_format - format a message into the audit buffer.
 * @ab: audit_buffer
 * @fmt: format string
 * @...: optional parameters matching @fmt string
 *
 * All the work is done in audit_log_vformat.
 */
void audit_log_format(struct audit_buffer *ab, const char *fmt, ...)
{
	va_list args;

	if (!ab)
		return;
	va_start(args, fmt);
	audit_log_vformat(ab, fmt, args);
	va_end(args);
}

/**
 * audit_log_hex - convert a buffer to hex and append it to the audit skb
 * @ab: the audit_buffer
 * @buf: buffer to convert to hex
 * @len: length of @buf to be converted
 *
 * No return value; failure to expand is silently ignored.
 *
 * This function will take the passed buf and convert it into a string of
 * ascii hex digits. The new string is placed onto the skb.
 */
void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf,
		size_t len)
{
	int i, avail, new_len;
	unsigned char *ptr;
	struct sk_buff *skb;
	static const unsigned char *hex = "0123456789ABCDEF";

	if (!ab)
		return;

	BUG_ON(!ab->skb);
	skb = ab->skb;
	avail = skb_tailroom(skb);
	new_len = len<<1;
	if (new_len >= avail) {
		/* Round the buffer request up to the next multiple */
		new_len = AUDIT_BUFSIZ*(((new_len-avail)/AUDIT_BUFSIZ) + 1);
		avail = audit_expand(ab, new_len);
		if (!avail)
			return;
	}

	ptr = skb_tail_pointer(skb);
	for (i=0; i<len; i++) {
		*ptr++ = hex[(buf[i] & 0xF0)>>4]; /* Upper nibble */
		*ptr++ = hex[buf[i] & 0x0F];	  /* Lower nibble */
	}
	*ptr = 0;
	skb_put(skb, len << 1); /* new string is twice the old string */
}

/*
 * Format a string of no more than slen characters into the audit buffer,
 * enclosed in quote marks.
 */
void audit_log_n_string(struct audit_buffer *ab, const char *string,
			size_t slen)
{
	int avail, new_len;
	unsigned char *ptr;
	struct sk_buff *skb;

	if (!ab)
		return;

	BUG_ON(!ab->skb);
	skb = ab->skb;
	avail = skb_tailroom(skb);
	new_len = slen + 3;	/* enclosing quotes + null terminator */
	if (new_len > avail) {
		avail = audit_expand(ab, new_len);
		if (!avail)
			return;
	}
	ptr = skb_tail_pointer(skb);
	*ptr++ = '"';
	memcpy(ptr, string, slen);
	ptr += slen;
	*ptr++ = '"';
	*ptr = 0;
	skb_put(skb, slen + 2);	/* don't include null terminator */
}

/**
 * audit_string_contains_control - does a string need to be logged in hex
 * @string: string to be checked
 * @len: max length of the string to check
 */
int audit_string_contains_control(const char *string, size_t len)
{
	const unsigned char *p;
	for (p = string; p < (const unsigned char *)string + len; p++) {
		if (*p == '"' || *p < 0x21 || *p > 0x7e)
			return 1;
	}
	return 0;
}

/**
 * audit_log_n_untrustedstring - log a string that may contain random characters
 * @ab: audit_buffer
 * @len: length of string (not including trailing null)
 * @string: string to be logged
 *
 * This code will escape a string that is passed to it if the string
 * contains a control character, unprintable character, double quote mark,
 * or a space. Unescaped strings will start and end with a double quote mark.
 * Strings that are escaped are printed in hex (2 digits per char).
 *
 * The caller specifies the number of characters in the string to log, which may
 * or may not be the entire string.
 */
void audit_log_n_untrustedstring(struct audit_buffer *ab, const char *string,
				 size_t len)
{
	if (audit_string_contains_control(string, len))
		audit_log_n_hex(ab, string, len);
	else
		audit_log_n_string(ab, string, len);
}

/**
 * audit_log_untrustedstring - log a string that may contain random characters
 * @ab: audit_buffer
 * @string: string to be logged
 *
 * Same as audit_log_n_untrustedstring(), except that strlen is used to
 * determine string length.
 */
void audit_log_untrustedstring(struct audit_buffer *ab, const char *string)
{
	audit_log_n_untrustedstring(ab, string, strlen(string));
}

/* This is a helper-function to print the escaped d_path */
void audit_log_d_path(struct audit_buffer *ab, const char *prefix,
		      const struct path *path)
{
	char *p, *pathname;

	if (prefix)
		audit_log_format(ab, "%s", prefix);

	/* We will allow 11 spaces for ' (deleted)' to be appended */
	pathname = kmalloc(PATH_MAX+11, ab->gfp_mask);
	if (!pathname) {
		audit_log_string(ab, "<no_memory>");
		return;
	}
	p = d_path(path, pathname, PATH_MAX+11);
	if (IS_ERR(p)) { /* Should never happen since we send PATH_MAX */
		/* FIXME: can we save some information here? */
		audit_log_string(ab, "<too_long>");
	} else
		audit_log_untrustedstring(ab, p);
	kfree(pathname);
}

void audit_log_key(struct audit_buffer *ab, char *key)
{
	audit_log_format(ab, " key=");
	if (key)
		audit_log_untrustedstring(ab, key);
	else
		audit_log_format(ab, "(null)");
}

/**
 * audit_log_link_denied - report a link restriction denial
 * @operation: specific link opreation
 * @link: the path that triggered the restriction
 */
void audit_log_link_denied(const char *operation, struct path *link)
{
	struct audit_buffer *ab;

	ab = audit_log_start(current->audit_context, GFP_KERNEL,
			     AUDIT_ANOM_LINK);
	if (!ab)
		return;
	audit_log_format(ab, "op=%s action=denied", operation);
	audit_log_format(ab, " pid=%d comm=", current->pid);
	audit_log_untrustedstring(ab, current->comm);
	audit_log_d_path(ab, " path=", link);
	audit_log_format(ab, " dev=");
	audit_log_untrustedstring(ab, link->dentry->d_inode->i_sb->s_id);
	audit_log_format(ab, " ino=%lu", link->dentry->d_inode->i_ino);
	audit_log_end(ab);
}

/**
 * audit_log_end - end one audit record
 * @ab: the audit_buffer
 *
 * The netlink_* functions cannot be called inside an irq context, so
 * the audit buffer is placed on a queue and a tasklet is scheduled to
 * remove them from the queue outside the irq context.  May be called in
 * any context.
 */
void audit_log_end(struct audit_buffer *ab)
{
	if (!ab)
		return;
	if (!audit_rate_check()) {
		audit_log_lost("rate limit exceeded");
	} else {
		struct nlmsghdr *nlh = nlmsg_hdr(ab->skb);
		nlh->nlmsg_len = ab->skb->len - NLMSG_SPACE(0);

		if (audit_pid) {
			skb_queue_tail(&audit_skb_queue, ab->skb);
			wake_up_interruptible(&kauditd_wait);
		} else {
			audit_printk_skb(ab->skb);
		}
		ab->skb = NULL;
	}
	audit_buffer_free(ab);
}

/**
 * audit_log - Log an audit record
 * @ctx: audit context
 * @gfp_mask: type of allocation
 * @type: audit message type
 * @fmt: format string to use
 * @...: variable parameters matching the format string
 *
 * This is a convenience function that calls audit_log_start,
 * audit_log_vformat, and audit_log_end.  It may be called
 * in any context.
 */
void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type,
	       const char *fmt, ...)
{
	struct audit_buffer *ab;
	va_list args;

	ab = audit_log_start(ctx, gfp_mask, type);
	if (ab) {
		va_start(args, fmt);
		audit_log_vformat(ab, fmt, args);
		va_end(args);
		audit_log_end(ab);
	}
}

#ifdef CONFIG_SECURITY
/**
 * audit_log_secctx - Converts and logs SELinux context
 * @ab: audit_buffer
 * @secid: security number
 *
 * This is a helper function that calls security_secid_to_secctx to convert
 * secid to secctx and then adds the (converted) SELinux context to the audit
 * log by calling audit_log_format, thus also preventing leak of internal secid
 * to userspace. If secid cannot be converted audit_panic is called.
 */
void audit_log_secctx(struct audit_buffer *ab, u32 secid)
{
	u32 len;
	char *secctx;

	if (security_secid_to_secctx(secid, &secctx, &len)) {
		audit_panic("Cannot convert secid to context");
	} else {
		audit_log_format(ab, " obj=%s", secctx);
		security_release_secctx(secctx, len);
	}
}
EXPORT_SYMBOL(audit_log_secctx);
#endif

EXPORT_SYMBOL(audit_log_start);
EXPORT_SYMBOL(audit_log_end);
EXPORT_SYMBOL(audit_log_format);
EXPORT_SYMBOL(audit_log);