auditsc.c

Kernel code of linux kernel

	if (unlikely(!context))
		return;

	/*
	 * This happens only on certain architectures that make system
	 * calls in kernel_thread via the entry.S interface, instead of
	 * with direct calls.  (If you are porting to a new
	 * architecture, hitting this condition can indicate that you
	 * got the _exit/_leave calls backward in entry.S.)
	 *
	 * i386     no
	 * x86_64   no
	 * ppc64    yes (see arch/powerpc/platforms/iseries/misc.S)
	 *
	 * This also happens with vm86 emulation in a non-nested manner
	 * (entries without exits), so this case must be caught.
	 */
	if (context->in_syscall) {
		struct audit_context *newctx;

#if AUDIT_DEBUG
		printk(KERN_ERR
		       "audit(:%d) pid=%d in syscall=%d;"
		       " entering syscall=%d\n",
		       context->serial, tsk->pid, context->major, major);
#endif
		newctx = audit_alloc_context(context->state);
		if (newctx) {
			newctx->previous   = context;
			context		   = newctx;
			tsk->audit_context = newctx;
		} else	{
			/* If we can't alloc a new context, the best we
			 * can do is to leak memory (any pending putname
			 * will be lost).  The only other alternative is
			 * to abandon auditing. */
			audit_zero_context(context, context->state);
		}
	}
	BUG_ON(context->in_syscall || context->name_count);

	if (!audit_enabled)
		return;

	context->arch	    = arch;
	context->major      = major;
	context->argv[0]    = a1;
	context->argv[1]    = a2;
	context->argv[2]    = a3;
	context->argv[3]    = a4;

	state = context->state;
	context->dummy = !audit_n_rules;
	if (!context->dummy && (state == AUDIT_SETUP_CONTEXT || state == AUDIT_BUILD_CONTEXT))
		state = audit_filter_syscall(tsk, context, &audit_filter_list[AUDIT_FILTER_ENTRY]);
	if (likely(state == AUDIT_DISABLED))
		return;

	context->serial     = 0;
	context->ctime      = CURRENT_TIME;
	context->in_syscall = 1;
	context->auditable  = !!(state == AUDIT_RECORD_CONTEXT);
	context->ppid       = 0;
}

/**
 * audit_syscall_exit - deallocate audit context after a system call
 * @tsk: task being audited
 * @valid: success/failure flag
 * @return_code: syscall return value
 *
 * Tear down after system call.  If the audit context has been marked as
 * auditable (either because of the AUDIT_RECORD_CONTEXT state from
 * filtering, or because some other part of the kernel write an audit
 * message), then write out the syscall information.  In call cases,
 * free the names stored from getname().
 */
void audit_syscall_exit(int valid, long return_code)
{
	struct task_struct *tsk = current;
	struct audit_context *context;

	context = audit_get_context(tsk, valid, return_code);

	if (likely(!context))
		return;

	if (context->in_syscall && context->auditable)
		audit_log_exit(context, tsk);

	context->in_syscall = 0;
	context->auditable  = 0;

	if (context->previous) {
		struct audit_context *new_context = context->previous;
		context->previous  = NULL;
		audit_free_context(context);
		tsk->audit_context = new_context;
	} else {
		audit_free_names(context);
		unroll_tree_refs(context, NULL, 0);
		audit_free_aux(context);
		context->aux = NULL;
		context->aux_pids = NULL;
		context->target_pid = 0;
		context->target_sid = 0;
		kfree(context->filterkey);
		context->filterkey = NULL;
		tsk->audit_context = context;
	}
}

static inline void handle_one(const struct inode *inode)
{
#ifdef CONFIG_AUDIT_TREE
	struct audit_context *context;
	struct audit_tree_refs *p;
	struct audit_chunk *chunk;
	int count;
	if (likely(list_empty(&inode->inotify_watches)))
		return;
	context = current->audit_context;
	p = context->trees;
	count = context->tree_count;
	rcu_read_lock();
	chunk = audit_tree_lookup(inode);
	rcu_read_unlock();
	if (!chunk)
		return;
	if (likely(put_tree_ref(context, chunk)))
		return;
	if (unlikely(!grow_tree_refs(context))) {
		printk(KERN_WARNING "out of memory, audit has lost a tree reference\n");
		audit_set_auditable(context);
		audit_put_chunk(chunk);
		unroll_tree_refs(context, p, count);
		return;
	}
	put_tree_ref(context, chunk);
#endif
}

static void handle_path(const struct dentry *dentry)
{
#ifdef CONFIG_AUDIT_TREE
	struct audit_context *context;
	struct audit_tree_refs *p;
	const struct dentry *d, *parent;
	struct audit_chunk *drop;
	unsigned long seq;
	int count;

	context = current->audit_context;
	p = context->trees;
	count = context->tree_count;
retry:
	drop = NULL;
	d = dentry;
	rcu_read_lock();
	seq = read_seqbegin(&rename_lock);
	for(;;) {
		struct inode *inode = d->d_inode;
		if (inode && unlikely(!list_empty(&inode->inotify_watches))) {
			struct audit_chunk *chunk;
			chunk = audit_tree_lookup(inode);
			if (chunk) {
				if (unlikely(!put_tree_ref(context, chunk))) {
					drop = chunk;
					break;
				}
			}
		}
		parent = d->d_parent;
		if (parent == d)
			break;
		d = parent;
	}
	if (unlikely(read_seqretry(&rename_lock, seq) || drop)) {  /* in this order */
		rcu_read_unlock();
		if (!drop) {
			/* just a race with rename */
			unroll_tree_refs(context, p, count);
			goto retry;
		}
		audit_put_chunk(drop);
		if (grow_tree_refs(context)) {
			/* OK, got more space */
			unroll_tree_refs(context, p, count);
			goto retry;
		}
		/* too bad */
		printk(KERN_WARNING
			"out of memory, audit has lost a tree reference\n");
		unroll_tree_refs(context, p, count);
		audit_set_auditable(context);
		return;
	}
	rcu_read_unlock();
#endif
}

/**
 * audit_getname - add a name to the list
 * @name: name to add
 *
 * Add a name to the list of audit names for this context.
 * Called from fs/namei.c:getname().
 */
void __audit_getname(const char *name)
{
	struct audit_context *context = current->audit_context;

	if (IS_ERR(name) || !name)
		return;

	if (!context->in_syscall) {
#if AUDIT_DEBUG == 2
		printk(KERN_ERR "%s:%d(:%d): ignoring getname(%p)\n",
		       __FILE__, __LINE__, context->serial, name);
		dump_stack();
#endif
		return;
	}
	BUG_ON(context->name_count >= AUDIT_NAMES);
	context->names[context->name_count].name = name;
	context->names[context->name_count].name_len = AUDIT_NAME_FULL;
	context->names[context->name_count].name_put = 1;
	context->names[context->name_count].ino  = (unsigned long)-1;
	context->names[context->name_count].osid = 0;
	++context->name_count;
	if (!context->pwd.dentry) {
		read_lock(&current->fs->lock);
		context->pwd = current->fs->pwd;
		path_get(&current->fs->pwd);
		read_unlock(&current->fs->lock);
	}

}

/* audit_putname - intercept a putname request
 * @name: name to intercept and delay for putname
 *
 * If we have stored the name from getname in the audit context,
 * then we delay the putname until syscall exit.
 * Called from include/linux/fs.h:putname().
 */
void audit_putname(const char *name)
{
	struct audit_context *context = current->audit_context;

	BUG_ON(!context);
	if (!context->in_syscall) {
#if AUDIT_DEBUG == 2
		printk(KERN_ERR "%s:%d(:%d): __putname(%p)\n",
		       __FILE__, __LINE__, context->serial, name);
		if (context->name_count) {
			int i;
			for (i = 0; i < context->name_count; i++)
				printk(KERN_ERR "name[%d] = %p = %s\n", i,
				       context->names[i].name,
				       context->names[i].name ?: "(null)");
		}
#endif
		__putname(name);
	}
#if AUDIT_DEBUG
	else {
		++context->put_count;
		if (context->put_count > context->name_count) {
			printk(KERN_ERR "%s:%d(:%d): major=%d"
			       " in_syscall=%d putname(%p) name_count=%d"
			       " put_count=%d\n",
			       __FILE__, __LINE__,
			       context->serial, context->major,
			       context->in_syscall, name, context->name_count,
			       context->put_count);
			dump_stack();
		}
	}
#endif
}

static int audit_inc_name_count(struct audit_context *context,
				const struct inode *inode)
{
	if (context->name_count >= AUDIT_NAMES) {
		if (inode)
			printk(KERN_DEBUG "name_count maxed, losing inode data: "
			       "dev=%02x:%02x, inode=%lu\n",
			       MAJOR(inode->i_sb->s_dev),
			       MINOR(inode->i_sb->s_dev),
			       inode->i_ino);

		else
			printk(KERN_DEBUG "name_count maxed, losing inode data\n");
		return 1;
	}
	context->name_count++;
#if AUDIT_DEBUG
	context->ino_count++;
#endif
	return 0;
}

/* Copy inode data into an audit_names. */
static void audit_copy_inode(struct audit_names *name, const struct inode *inode)
{
	name->ino   = inode->i_ino;
	name->dev   = inode->i_sb->s_dev;
	name->mode  = inode->i_mode;
	name->uid   = inode->i_uid;
	name->gid   = inode->i_gid;
	name->rdev  = inode->i_rdev;
	security_inode_getsecid(inode, &name->osid);
}

/**
 * audit_inode - store the inode and device from a lookup
 * @name: name being audited
 * @dentry: dentry being audited
 *
 * Called from fs/namei.c:path_lookup().
 */
void __audit_inode(const char *name, const struct dentry *dentry)
{
	int idx;
	struct audit_context *context = current->audit_context;
	const struct inode *inode = dentry->d_inode;

	if (!context->in_syscall)
		return;
	if (context->name_count
	    && context->names[context->name_count-1].name
	    && context->names[context->name_count-1].name == name)
		idx = context->name_count - 1;
	else if (context->name_count > 1
		 && context->names[context->name_count-2].name
		 && context->names[context->name_count-2].name == name)
		idx = context->name_count - 2;
	else {
		/* FIXME: how much do we care about inodes that have no
		 * associated name? */
		if (audit_inc_name_count(context, inode))
			return;
		idx = context->name_count - 1;
		context->names[idx].name = NULL;
	}
	handle_path(dentry);
	audit_copy_inode(&context->names[idx], inode);
}

/**
 * audit_inode_child - collect inode info for created/removed objects
 * @dname: inode's dentry name
 * @dentry: dentry being audited
 * @parent: inode of dentry parent
 *
 * For syscalls that create or remove filesystem objects, audit_inode
 * can only collect information for the filesystem object's parent.
 * This call updates the audit context with the child's information.
 * Syscalls that create a new filesystem object must be hooked after
 * the object is created.  Syscalls that remove a filesystem object
 * must be hooked prior, in order to capture the target inode during
 * unsuccessful attempts.
 */
void __audit_inode_child(const char *dname, const struct dentry *dentry,
			 const struct inode *parent)
{
	int idx;
	struct audit_context *context = current->audit_context;
	const char *found_parent = NULL, *found_child = NULL;
	const struct inode *inode = dentry->d_inode;
	int dirlen = 0;

	if (!context->in_syscall)
		return;

	if (inode)
		handle_one(inode);
	/* determine matching parent */
	if (!dname)
		goto add_names;

	/* parent is more likely, look for it first */
	for (idx = 0; idx < context->name_count; idx++) {
		struct audit_names *n = &context->names[idx];

		if (!n->name)
			continue;

		if (n->ino == parent->i_ino &&
		    !audit_compare_dname_path(dname, n->name, &dirlen)) {
			n->name_len = dirlen; /* update parent data in place */
			found_parent = n->name;
			goto add_names;
		}
	}

	/* no matching parent, look for matching child */
	for (idx = 0; idx < context->name_count; idx++) {
		struct audit_names *n = &context->names[idx];

		if (!n->name)
			continue;

		/* strcmp() is the more likely scenario */
		if (!strcmp(dname, n->name) ||
		     !audit_compare_dname_path(dname, n->name, &dirlen)) {
			if (inode)
				audit_copy_inode(n, inode);
			else
				n->ino = (unsigned long)-1;
			found_child = n->name;
			goto add_names;
		}
	}

add_names:
	if (!found_parent) {
		if (audit_inc_name_count(context, parent))
			return;
		idx = context->name_count - 1;
		context->names[idx].name = NULL;
		audit_copy_inode(&context->names[idx], parent);
	}

	if (!found_child) {
		if (audit_inc_name_count(context, inode))
			return;
		idx = context->name_count - 1;

		/* Re-use the name belonging to the slot for a matching parent
		 * directory. All names for this context are relinquished in
		 * audit_free_names() */
		if (found_parent) {
			context->names[idx].name = found_parent;
			context->names[idx].name_len = AUDIT_NAME_FULL;
			/* don't call __putname() */
			context->names[idx].name_put = 0;
		} else {
			context->names[idx].name = NULL;
		}

		if (inode)
			audit_copy_inode(&context->names[idx], inode);
		else
			context->names[idx].ino = (unsigned long)-1;
	}
}
EXPORT_SYMBOL_GPL(__audit_inode_child);

/**
 * auditsc_get_stamp - get local copies of audit_context values
 * @ctx: audit_context for the task
 * @t: timespec to store time recorded in the audit_context
 * @serial: serial value that is recorded in the audit_context
 *
 * Also sets the context as auditable.
 */
void auditsc_get_stamp(struct audit_context *ctx,
		       struct timespec *t, unsigned int *serial)
{
	if (!ctx->serial)
		ctx->serial = audit_serial();
	t->tv_sec  = ctx->ctime.tv_sec;
	t->tv_nsec = ctx->ctime.tv_nsec;
	*serial    = ctx->serial;
	ctx->auditable = 1;
}

/* global counter which is incremented every time something logs in */
static atomic_t session_id = ATOMIC_INIT(0);

/**
 * audit_set_loginuid - set a task's audit_context loginuid
 * @task: task whose audit context is being modified
 * @loginuid: loginuid value
 *
 * Returns 0.
 *
 * Called (set) from fs/proc/base.c::proc_loginuid_write().
 */
int audit_set_loginuid(struct task_struct *task, uid_t loginuid)
{
	unsigned int sessionid = atomic_inc_return(&session_id);
	struct audit_context *context = task->audit_context;

	if (context && context->in_syscall) {
		struct audit_buffer *ab;

		ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN);
		if (ab) {
			audit_log_format(ab, "login pid=%d uid=%u "
				"old auid=%u new auid=%u"