base.c

linux 内核源代码

	INF("statm",      S_IRUGO, pid_statm),
	REG("maps",       S_IRUGO, maps),
#ifdef CONFIG_NUMA
	REG("numa_maps",  S_IRUGO, numa_maps),
#endif
	REG("mem",        S_IRUSR|S_IWUSR, mem),
	LNK("cwd",        cwd),
	LNK("root",       root),
	LNK("exe",        exe),
	REG("mounts",     S_IRUGO, mounts),
	REG("mountstats", S_IRUSR, mountstats),
#ifdef CONFIG_MMU
	REG("clear_refs", S_IWUSR, clear_refs),
	REG("smaps",      S_IRUGO, smaps),
#endif
#ifdef CONFIG_SECURITY
	DIR("attr",       S_IRUGO|S_IXUGO, attr_dir),
#endif
#ifdef CONFIG_KALLSYMS
	INF("wchan",      S_IRUGO, pid_wchan),
#endif
#ifdef CONFIG_SCHEDSTATS
	INF("schedstat",  S_IRUGO, pid_schedstat),
#endif
#ifdef CONFIG_PROC_PID_CPUSET
	REG("cpuset",     S_IRUGO, cpuset),
#endif
#ifdef CONFIG_CGROUPS
	REG("cgroup",  S_IRUGO, cgroup),
#endif
	INF("oom_score",  S_IRUGO, oom_score),
	REG("oom_adj",    S_IRUGO|S_IWUSR, oom_adjust),
#ifdef CONFIG_AUDITSYSCALL
	REG("loginuid",   S_IWUSR|S_IRUGO, loginuid),
#endif
#ifdef CONFIG_FAULT_INJECTION
	REG("make-it-fail", S_IRUGO|S_IWUSR, fault_inject),
#endif
#if defined(USE_ELF_CORE_DUMP) && defined(CONFIG_ELF_CORE)
	REG("coredump_filter", S_IRUGO|S_IWUSR, coredump_filter),
#endif
#ifdef CONFIG_TASK_IO_ACCOUNTING
	INF("io",	S_IRUGO, pid_io_accounting),
#endif
};

static int proc_tgid_base_readdir(struct file * filp,
			     void * dirent, filldir_t filldir)
{
	return proc_pident_readdir(filp,dirent,filldir,
				   tgid_base_stuff,ARRAY_SIZE(tgid_base_stuff));
}

static const struct file_operations proc_tgid_base_operations = {
	.read		= generic_read_dir,
	.readdir	= proc_tgid_base_readdir,
};

static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){
	return proc_pident_lookup(dir, dentry,
				  tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff));
}

static const struct inode_operations proc_tgid_base_inode_operations = {
	.lookup		= proc_tgid_base_lookup,
	.getattr	= pid_getattr,
	.setattr	= proc_setattr,
};

static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid)
{
	struct dentry *dentry, *leader, *dir;
	char buf[PROC_NUMBUF];
	struct qstr name;

	name.name = buf;
	name.len = snprintf(buf, sizeof(buf), "%d", pid);
	dentry = d_hash_and_lookup(mnt->mnt_root, &name);
	if (dentry) {
		shrink_dcache_parent(dentry);
		d_drop(dentry);
		dput(dentry);
	}

	if (tgid == 0)
		goto out;

	name.name = buf;
	name.len = snprintf(buf, sizeof(buf), "%d", tgid);
	leader = d_hash_and_lookup(mnt->mnt_root, &name);
	if (!leader)
		goto out;

	name.name = "task";
	name.len = strlen(name.name);
	dir = d_hash_and_lookup(leader, &name);
	if (!dir)
		goto out_put_leader;

	name.name = buf;
	name.len = snprintf(buf, sizeof(buf), "%d", pid);
	dentry = d_hash_and_lookup(dir, &name);
	if (dentry) {
		shrink_dcache_parent(dentry);
		d_drop(dentry);
		dput(dentry);
	}

	dput(dir);
out_put_leader:
	dput(leader);
out:
	return;
}

/**
 * proc_flush_task -  Remove dcache entries for @task from the /proc dcache.
 * @task: task that should be flushed.
 *
 * When flushing dentries from proc, one needs to flush them from global
 * proc (proc_mnt) and from all the namespaces' procs this task was seen
 * in. This call is supposed to do all of this job.
 *
 * Looks in the dcache for
 * /proc/@pid
 * /proc/@tgid/task/@pid
 * if either directory is present flushes it and all of it'ts children
 * from the dcache.
 *
 * It is safe and reasonable to cache /proc entries for a task until
 * that task exits.  After that they just clog up the dcache with
 * useless entries, possibly causing useful dcache entries to be
 * flushed instead.  This routine is proved to flush those useless
 * dcache entries at process exit time.
 *
 * NOTE: This routine is just an optimization so it does not guarantee
 *       that no dcache entries will exist at process exit time it
 *       just makes it very unlikely that any will persist.
 */

void proc_flush_task(struct task_struct *task)
{
	int i;
	struct pid *pid, *tgid = NULL;
	struct upid *upid;

	pid = task_pid(task);
	if (thread_group_leader(task))
		tgid = task_tgid(task);

	for (i = 0; i <= pid->level; i++) {
		upid = &pid->numbers[i];
		proc_flush_task_mnt(upid->ns->proc_mnt, upid->nr,
			tgid ? tgid->numbers[i].nr : 0);
	}

	upid = &pid->numbers[pid->level];
	if (upid->nr == 1)
		pid_ns_release_proc(upid->ns);
}

static struct dentry *proc_pid_instantiate(struct inode *dir,
					   struct dentry * dentry,
					   struct task_struct *task, const void *ptr)
{
	struct dentry *error = ERR_PTR(-ENOENT);
	struct inode *inode;

	inode = proc_pid_make_inode(dir->i_sb, task);
	if (!inode)
		goto out;

	inode->i_mode = S_IFDIR|S_IRUGO|S_IXUGO;
	inode->i_op = &proc_tgid_base_inode_operations;
	inode->i_fop = &proc_tgid_base_operations;
	inode->i_flags|=S_IMMUTABLE;
	inode->i_nlink = 5;
#ifdef CONFIG_SECURITY
	inode->i_nlink += 1;
#endif

	dentry->d_op = &pid_dentry_operations;

	d_add(dentry, inode);
	/* Close the race of the process dying before we return the dentry */
	if (pid_revalidate(dentry, NULL))
		error = NULL;
out:
	return error;
}

struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd)
{
	struct dentry *result = ERR_PTR(-ENOENT);
	struct task_struct *task;
	unsigned tgid;
	struct pid_namespace *ns;

	result = proc_base_lookup(dir, dentry);
	if (!IS_ERR(result) || PTR_ERR(result) != -ENOENT)
		goto out;

	tgid = name_to_int(dentry);
	if (tgid == ~0U)
		goto out;

	ns = dentry->d_sb->s_fs_info;
	rcu_read_lock();
	task = find_task_by_pid_ns(tgid, ns);
	if (task)
		get_task_struct(task);
	rcu_read_unlock();
	if (!task)
		goto out;

	result = proc_pid_instantiate(dir, dentry, task, NULL);
	put_task_struct(task);
out:
	return result;
}

/*
 * Find the first task with tgid >= tgid
 *
 */
struct tgid_iter {
	unsigned int tgid;
	struct task_struct *task;
};
static struct tgid_iter next_tgid(struct pid_namespace *ns, struct tgid_iter iter)
{
	struct pid *pid;

	if (iter.task)
		put_task_struct(iter.task);
	rcu_read_lock();
retry:
	iter.task = NULL;
	pid = find_ge_pid(iter.tgid, ns);
	if (pid) {
		iter.tgid = pid_nr_ns(pid, ns);
		iter.task = pid_task(pid, PIDTYPE_PID);
		/* What we to know is if the pid we have find is the
		 * pid of a thread_group_leader.  Testing for task
		 * being a thread_group_leader is the obvious thing
		 * todo but there is a window when it fails, due to
		 * the pid transfer logic in de_thread.
		 *
		 * So we perform the straight forward test of seeing
		 * if the pid we have found is the pid of a thread
		 * group leader, and don't worry if the task we have
		 * found doesn't happen to be a thread group leader.
		 * As we don't care in the case of readdir.
		 */
		if (!iter.task || !has_group_leader_pid(iter.task)) {
			iter.tgid += 1;
			goto retry;
		}
		get_task_struct(iter.task);
	}
	rcu_read_unlock();
	return iter;
}

#define TGID_OFFSET (FIRST_PROCESS_ENTRY + ARRAY_SIZE(proc_base_stuff))

static int proc_pid_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
	struct tgid_iter iter)
{
	char name[PROC_NUMBUF];
	int len = snprintf(name, sizeof(name), "%d", iter.tgid);
	return proc_fill_cache(filp, dirent, filldir, name, len,
				proc_pid_instantiate, iter.task, NULL);
}

/* for the /proc/ directory itself, after non-process stuff has been done */
int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir)
{
	unsigned int nr = filp->f_pos - FIRST_PROCESS_ENTRY;
	struct task_struct *reaper = get_proc_task(filp->f_path.dentry->d_inode);
	struct tgid_iter iter;
	struct pid_namespace *ns;

	if (!reaper)
		goto out_no_task;

	for (; nr < ARRAY_SIZE(proc_base_stuff); filp->f_pos++, nr++) {
		const struct pid_entry *p = &proc_base_stuff[nr];
		if (proc_base_fill_cache(filp, dirent, filldir, reaper, p) < 0)
			goto out;
	}

	ns = filp->f_dentry->d_sb->s_fs_info;
	iter.task = NULL;
	iter.tgid = filp->f_pos - TGID_OFFSET;
	for (iter = next_tgid(ns, iter);
	     iter.task;
	     iter.tgid += 1, iter = next_tgid(ns, iter)) {
		filp->f_pos = iter.tgid + TGID_OFFSET;
		if (proc_pid_fill_cache(filp, dirent, filldir, iter) < 0) {
			put_task_struct(iter.task);
			goto out;
		}
	}
	filp->f_pos = PID_MAX_LIMIT + TGID_OFFSET;
out:
	put_task_struct(reaper);
out_no_task:
	return 0;
}

/*
 * Tasks
 */
static const struct pid_entry tid_base_stuff[] = {
	DIR("fd",        S_IRUSR|S_IXUSR, fd),
	DIR("fdinfo",    S_IRUSR|S_IXUSR, fdinfo),
	REG("environ",   S_IRUSR, environ),
	INF("auxv",      S_IRUSR, pid_auxv),
	INF("status",    S_IRUGO, pid_status),
	INF("limits",	 S_IRUSR, pid_limits),
#ifdef CONFIG_SCHED_DEBUG
	REG("sched",     S_IRUGO|S_IWUSR, pid_sched),
#endif
	INF("cmdline",   S_IRUGO, pid_cmdline),
	INF("stat",      S_IRUGO, tid_stat),
	INF("statm",     S_IRUGO, pid_statm),
	REG("maps",      S_IRUGO, maps),
#ifdef CONFIG_NUMA
	REG("numa_maps", S_IRUGO, numa_maps),
#endif
	REG("mem",       S_IRUSR|S_IWUSR, mem),
	LNK("cwd",       cwd),
	LNK("root",      root),
	LNK("exe",       exe),
	REG("mounts",    S_IRUGO, mounts),
#ifdef CONFIG_MMU
	REG("clear_refs", S_IWUSR, clear_refs),
	REG("smaps",     S_IRUGO, smaps),
#endif
#ifdef CONFIG_SECURITY
	DIR("attr",      S_IRUGO|S_IXUGO, attr_dir),
#endif
#ifdef CONFIG_KALLSYMS
	INF("wchan",     S_IRUGO, pid_wchan),
#endif
#ifdef CONFIG_SCHEDSTATS
	INF("schedstat", S_IRUGO, pid_schedstat),
#endif
#ifdef CONFIG_PROC_PID_CPUSET
	REG("cpuset",    S_IRUGO, cpuset),
#endif
#ifdef CONFIG_CGROUPS
	REG("cgroup",  S_IRUGO, cgroup),
#endif
	INF("oom_score", S_IRUGO, oom_score),
	REG("oom_adj",   S_IRUGO|S_IWUSR, oom_adjust),
#ifdef CONFIG_AUDITSYSCALL
	REG("loginuid",  S_IWUSR|S_IRUGO, loginuid),
#endif
#ifdef CONFIG_FAULT_INJECTION
	REG("make-it-fail", S_IRUGO|S_IWUSR, fault_inject),
#endif
};

static int proc_tid_base_readdir(struct file * filp,
			     void * dirent, filldir_t filldir)
{
	return proc_pident_readdir(filp,dirent,filldir,
				   tid_base_stuff,ARRAY_SIZE(tid_base_stuff));
}

static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){
	return proc_pident_lookup(dir, dentry,
				  tid_base_stuff, ARRAY_SIZE(tid_base_stuff));
}

static const struct file_operations proc_tid_base_operations = {
	.read		= generic_read_dir,
	.readdir	= proc_tid_base_readdir,
};

static const struct inode_operations proc_tid_base_inode_operations = {
	.lookup		= proc_tid_base_lookup,
	.getattr	= pid_getattr,
	.setattr	= proc_setattr,
};

static struct dentry *proc_task_instantiate(struct inode *dir,
	struct dentry *dentry, struct task_struct *task, const void *ptr)
{
	struct dentry *error = ERR_PTR(-ENOENT);
	struct inode *inode;
	inode = proc_pid_make_inode(dir->i_sb, task);

	if (!inode)
		goto out;
	inode->i_mode = S_IFDIR|S_IRUGO|S_IXUGO;
	inode->i_op = &proc_tid_base_inode_operations;
	inode->i_fop = &proc_tid_base_operations;
	inode->i_flags|=S_IMMUTABLE;
	inode->i_nlink = 4;
#ifdef CONFIG_SECURITY
	inode->i_nlink += 1;
#endif

	dentry->d_op = &pid_dentry_operations;

	d_add(dentry, inode);
	/* Close the race of the process dying before we return the dentry */
	if (pid_revalidate(dentry, NULL))
		error = NULL;
out:
	return error;
}

static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd)
{
	struct dentry *result = ERR_PTR(-ENOENT);
	struct task_struct *task;
	struct task_struct *leader = get_proc_task(dir);
	unsigned tid;
	struct pid_namespace *ns;

	if (!leader)
		goto out_no_task;

	tid = name_to_int(dentry);
	if (tid == ~0U)
		goto out;

	ns = dentry->d_sb->s_fs_info;
	rcu_read_lock();
	task = find_task_by_pid_ns(tid, ns);
	if (task)
		get_task_struct(task);
	rcu_read_unlock();
	if (!task)
		goto out;
	if (!same_thread_group(leader, task))
		goto out_drop_task;

	result = proc_task_instantiate(dir, dentry, task, NULL);
out_drop_task:
	put_task_struct(task);
out:
	put_task_struct(leader);
out_no_task:
	return result;
}

/*
 * Find the first tid of a thread group to return to user space.
 *
 * Usually this is just the thread group leader, but if the users
 * buffer was too small or there was a seek into the middle of the
 * directory we have more work todo.
 *
 * In the case of a short read we start with find_task_by_pid.
 *
 * In the case of a seek we start with the leader and walk nr
 * threads past it.
 */
static struct task_struct *first_tid(struct task_struct *leader,
		int tid, int nr, struct pid_namespace *ns)
{
	struct task_struct *pos;

	rcu_read_lock();
	/* Attempt to start with the pid of a thread */
	if (tid && (nr > 0)) {
		pos = find_task_by_pid_ns(tid, ns);
		if (pos && (pos->group_leader == leader))
			goto found;
	}

	/* If nr exceeds the number of threads there is nothing todo */
	pos = NULL;
	if (nr && nr >= get_nr_threads(leader))
		goto out;

	/* If we haven't found our starting place yet start
	 * with the leader and walk nr threads forward.
	 */
	for (pos = leader; nr > 0; --nr) {
		pos = next_thread(pos);
		if (pos == leader) {
			pos = NULL;
			goto out;
		}
	}
found:
	get_task_struct(pos);
out:
	rcu_read_unlock();
	return pos;
}

/*
 * Find the next thread in the thread list.
 * Return NULL if there is an error or no next thread.
 *
 * The reference to the input task_struct is released.
 */
static struct task_struct *next_tid(struct task_struct *start)
{
	struct task_struct *pos = NULL;
	rcu_read_lock();
	if (pid_alive(start)) {
		pos = next_thread(start);
		if (thread_group_leader(pos))
			pos = NULL;
		else
			get_task_struct(pos);
	}
	rcu_read_unlock();
	put_task_struct(start);
	return pos;
}

static int proc_task_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
	struct task_struct *task, int tid)
{
	char name[PROC_NUMBUF];
	int len = snprintf(name, sizeof(name), "%d", tid);
	return proc_fill_cache(filp, dirent, filldir, name, len,
				proc_task_instantiate, task, NULL);
}

/* for the /proc/TGID/task/ directories */
static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldir)
{
	struct dentry *dentry = filp->f_path.dentry;
	struct inode *inode = dentry->d_inode;
	struct task_struct *leader = NULL;
	struct task_struct *task;
	int retval = -ENOENT;
	ino_t ino;
	int tid;
	unsigned long pos = filp->f_pos;  /* avoiding "long long" filp->f_pos */
	struct pid_namespace *ns;

	task = get_proc_task(inode);
	if (!task)
		goto out_no_task;
	rcu_read_lock();
	if (pid_alive(task)) {
		leader