base.c

linux 内核源代码

/*
 *  linux/fs/proc/base.c
 *
 *  Copyright (C) 1991, 1992 Linus Torvalds
 *
 *  proc base directory handling functions
 *
 *  1999, Al Viro. Rewritten. Now it covers the whole per-process part.
 *  Instead of using magical inumbers to determine the kind of object
 *  we allocate and fill in-core inodes upon lookup. They don't even
 *  go into icache. We cache the reference to task_struct upon lookup too.
 *  Eventually it should become a filesystem in its own. We don't use the
 *  rest of procfs anymore.
 *
 *
 *  Changelog:
 *  17-Jan-2005
 *  Allan Bezerra
 *  Bruna Moreira <[e-mail]>
 *  Edjard Mota <[e-mail]>
 *  Ilias Biris <[e-mail]>
 *  Mauricio Lin <[e-mail]>
 *
 *  Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT
 *
 *  A new process specific entry (smaps) included in /proc. It shows the
 *  size of rss for each memory area. The maps entry lacks information
 *  about physical memory size (rss) for each mapped file, i.e.,
 *  rss information for executables and library files.
 *  This additional information is useful for any tools that need to know
 *  about physical memory consumption for a process specific library.
 *
 *  Changelog:
 *  21-Feb-2005
 *  Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT
 *  Pud inclusion in the page table walking.
 *
 *  ChangeLog:
 *  10-Mar-2005
 *  10LE Instituto Nokia de Tecnologia - INdT:
 *  A better way to walks through the page table as suggested by Hugh Dickins.
 *
 *  Simo Piiroinen <[e-mail]>:
 *  Smaps information related to shared, private, clean and dirty pages.
 *
 *  Paul Mundt <[e-mail]>:
 *  Overall revision about smaps.
 */

#include <asm/uaccess.h>

#include <linux/errno.h>
#include <linux/time.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/init.h>
#include <linux/capability.h>
#include <linux/file.h>
#include <linux/string.h>
#include <linux/seq_file.h>
#include <linux/namei.h>
#include <linux/mnt_namespace.h>
#include <linux/mm.h>
#include <linux/rcupdate.h>
#include <linux/kallsyms.h>
#include <linux/resource.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/ptrace.h>
#include <linux/cgroup.h>
#include <linux/cpuset.h>
#include <linux/audit.h>
#include <linux/poll.h>
#include <linux/nsproxy.h>
#include <linux/oom.h>
#include <linux/elf.h>
#include <linux/pid_namespace.h>
#include "internal.h"

/* NOTE:
 *	Implementing inode permission operations in /proc is almost
 *	certainly an error.  Permission checks need to happen during
 *	each system call not at open time.  The reason is that most of
 *	what we wish to check for permissions in /proc varies at runtime.
 *
 *	The classic example of a problem is opening file descriptors
 *	in /proc for a task before it execs a suid executable.
 */


/* Worst case buffer size needed for holding an integer. */
#define PROC_NUMBUF 13

struct pid_entry {
	char *name;
	int len;
	mode_t mode;
	const struct inode_operations *iop;
	const struct file_operations *fop;
	union proc_op op;
};

#define NOD(NAME, MODE, IOP, FOP, OP) {			\
	.name = (NAME),					\
	.len  = sizeof(NAME) - 1,			\
	.mode = MODE,					\
	.iop  = IOP,					\
	.fop  = FOP,					\
	.op   = OP,					\
}

#define DIR(NAME, MODE, OTYPE)							\
	NOD(NAME, (S_IFDIR|(MODE)),						\
		&proc_##OTYPE##_inode_operations, &proc_##OTYPE##_operations,	\
		{} )
#define LNK(NAME, OTYPE)					\
	NOD(NAME, (S_IFLNK|S_IRWXUGO),				\
		&proc_pid_link_inode_operations, NULL,		\
		{ .proc_get_link = &proc_##OTYPE##_link } )
#define REG(NAME, MODE, OTYPE)				\
	NOD(NAME, (S_IFREG|(MODE)), NULL,		\
		&proc_##OTYPE##_operations, {})
#define INF(NAME, MODE, OTYPE)				\
	NOD(NAME, (S_IFREG|(MODE)), 			\
		NULL, &proc_info_file_operations,	\
		{ .proc_read = &proc_##OTYPE } )

int maps_protect;
EXPORT_SYMBOL(maps_protect);

static struct fs_struct *get_fs_struct(struct task_struct *task)
{
	struct fs_struct *fs;
	task_lock(task);
	fs = task->fs;
	if(fs)
		atomic_inc(&fs->count);
	task_unlock(task);
	return fs;
}

static int get_nr_threads(struct task_struct *tsk)
{
	/* Must be called with the rcu_read_lock held */
	unsigned long flags;
	int count = 0;

	if (lock_task_sighand(tsk, &flags)) {
		count = atomic_read(&tsk->signal->count);
		unlock_task_sighand(tsk, &flags);
	}
	return count;
}

static int proc_cwd_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt)
{
	struct task_struct *task = get_proc_task(inode);
	struct fs_struct *fs = NULL;
	int result = -ENOENT;

	if (task) {
		fs = get_fs_struct(task);
		put_task_struct(task);
	}
	if (fs) {
		read_lock(&fs->lock);
		*mnt = mntget(fs->pwdmnt);
		*dentry = dget(fs->pwd);
		read_unlock(&fs->lock);
		result = 0;
		put_fs_struct(fs);
	}
	return result;
}

static int proc_root_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt)
{
	struct task_struct *task = get_proc_task(inode);
	struct fs_struct *fs = NULL;
	int result = -ENOENT;

	if (task) {
		fs = get_fs_struct(task);
		put_task_struct(task);
	}
	if (fs) {
		read_lock(&fs->lock);
		*mnt = mntget(fs->rootmnt);
		*dentry = dget(fs->root);
		read_unlock(&fs->lock);
		result = 0;
		put_fs_struct(fs);
	}
	return result;
}

#define MAY_PTRACE(task) \
	(task == current || \
	(task->parent == current && \
	(task->ptrace & PT_PTRACED) && \
	 (task->state == TASK_STOPPED || task->state == TASK_TRACED) && \
	 security_ptrace(current,task) == 0))

struct mm_struct *mm_for_maps(struct task_struct *task)
{
	struct mm_struct *mm = get_task_mm(task);
	if (!mm)
		return NULL;
	down_read(&mm->mmap_sem);
	task_lock(task);
	if (task->mm != mm)
		goto out;
	if (task->mm != current->mm && __ptrace_may_attach(task) < 0)
		goto out;
	task_unlock(task);
	return mm;
out:
	task_unlock(task);
	up_read(&mm->mmap_sem);
	mmput(mm);
	return NULL;
}

static int proc_pid_cmdline(struct task_struct *task, char * buffer)
{
	int res = 0;
	unsigned int len;
	struct mm_struct *mm = get_task_mm(task);
	if (!mm)
		goto out;
	if (!mm->arg_end)
		goto out_mm;	/* Shh! No looking before we're done */

 	len = mm->arg_end - mm->arg_start;
 
	if (len > PAGE_SIZE)
		len = PAGE_SIZE;
 
	res = access_process_vm(task, mm->arg_start, buffer, len, 0);

	// If the nul at the end of args has been overwritten, then
	// assume application is using setproctitle(3).
	if (res > 0 && buffer[res-1] != '\0' && len < PAGE_SIZE) {
		len = strnlen(buffer, res);
		if (len < res) {
		    res = len;
		} else {
			len = mm->env_end - mm->env_start;
			if (len > PAGE_SIZE - res)
				len = PAGE_SIZE - res;
			res += access_process_vm(task, mm->env_start, buffer+res, len, 0);
			res = strnlen(buffer, res);
		}
	}
out_mm:
	mmput(mm);
out:
	return res;
}

static int proc_pid_auxv(struct task_struct *task, char *buffer)
{
	int res = 0;
	struct mm_struct *mm = get_task_mm(task);
	if (mm) {
		unsigned int nwords = 0;
		do
			nwords += 2;
		while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */
		res = nwords * sizeof(mm->saved_auxv[0]);
		if (res > PAGE_SIZE)
			res = PAGE_SIZE;
		memcpy(buffer, mm->saved_auxv, res);
		mmput(mm);
	}
	return res;
}


#ifdef CONFIG_KALLSYMS
/*
 * Provides a wchan file via kallsyms in a proper one-value-per-file format.
 * Returns the resolved symbol.  If that fails, simply return the address.
 */
static int proc_pid_wchan(struct task_struct *task, char *buffer)
{
	unsigned long wchan;
	char symname[KSYM_NAME_LEN];

	wchan = get_wchan(task);

	if (lookup_symbol_name(wchan, symname) < 0)
		return sprintf(buffer, "%lu", wchan);
	else
		return sprintf(buffer, "%s", symname);
}
#endif /* CONFIG_KALLSYMS */

#ifdef CONFIG_SCHEDSTATS
/*
 * Provides /proc/PID/schedstat
 */
static int proc_pid_schedstat(struct task_struct *task, char *buffer)
{
	return sprintf(buffer, "%llu %llu %lu\n",
			task->sched_info.cpu_time,
			task->sched_info.run_delay,
			task->sched_info.pcount);
}
#endif

/* The badness from the OOM killer */
unsigned long badness(struct task_struct *p, unsigned long uptime);
static int proc_oom_score(struct task_struct *task, char *buffer)
{
	unsigned long points;
	struct timespec uptime;

	do_posix_clock_monotonic_gettime(&uptime);
	read_lock(&tasklist_lock);
	points = badness(task, uptime.tv_sec);
	read_unlock(&tasklist_lock);
	return sprintf(buffer, "%lu\n", points);
}

struct limit_names {
	char *name;
	char *unit;
};

static const struct limit_names lnames[RLIM_NLIMITS] = {
	[RLIMIT_CPU] = {"Max cpu time", "ms"},
	[RLIMIT_FSIZE] = {"Max file size", "bytes"},
	[RLIMIT_DATA] = {"Max data size", "bytes"},
	[RLIMIT_STACK] = {"Max stack size", "bytes"},
	[RLIMIT_CORE] = {"Max core file size", "bytes"},
	[RLIMIT_RSS] = {"Max resident set", "bytes"},
	[RLIMIT_NPROC] = {"Max processes", "processes"},
	[RLIMIT_NOFILE] = {"Max open files", "files"},
	[RLIMIT_MEMLOCK] = {"Max locked memory", "bytes"},
	[RLIMIT_AS] = {"Max address space", "bytes"},
	[RLIMIT_LOCKS] = {"Max file locks", "locks"},
	[RLIMIT_SIGPENDING] = {"Max pending signals", "signals"},
	[RLIMIT_MSGQUEUE] = {"Max msgqueue size", "bytes"},
	[RLIMIT_NICE] = {"Max nice priority", NULL},
	[RLIMIT_RTPRIO] = {"Max realtime priority", NULL},
};

/* Display limits for a process */
static int proc_pid_limits(struct task_struct *task, char *buffer)
{
	unsigned int i;
	int count = 0;
	unsigned long flags;
	char *bufptr = buffer;

	struct rlimit rlim[RLIM_NLIMITS];

	rcu_read_lock();
	if (!lock_task_sighand(task,&flags)) {
		rcu_read_unlock();
		return 0;
	}
	memcpy(rlim, task->signal->rlim, sizeof(struct rlimit) * RLIM_NLIMITS);
	unlock_task_sighand(task, &flags);
	rcu_read_unlock();

	/*
	 * print the file header
	 */
	count += sprintf(&bufptr[count], "%-25s %-20s %-20s %-10s\n",
			"Limit", "Soft Limit", "Hard Limit", "Units");

	for (i = 0; i < RLIM_NLIMITS; i++) {
		if (rlim[i].rlim_cur == RLIM_INFINITY)
			count += sprintf(&bufptr[count], "%-25s %-20s ",
					 lnames[i].name, "unlimited");
		else
			count += sprintf(&bufptr[count], "%-25s %-20lu ",
					 lnames[i].name, rlim[i].rlim_cur);

		if (rlim[i].rlim_max == RLIM_INFINITY)
			count += sprintf(&bufptr[count], "%-20s ", "unlimited");
		else
			count += sprintf(&bufptr[count], "%-20lu ",
					 rlim[i].rlim_max);

		if (lnames[i].unit)
			count += sprintf(&bufptr[count], "%-10s\n",
					 lnames[i].unit);
		else
			count += sprintf(&bufptr[count], "\n");
	}

	return count;
}

/************************************************************************/
/*                       Here the fs part begins                        */
/************************************************************************/

/* permission checks */
static int proc_fd_access_allowed(struct inode *inode)
{
	struct task_struct *task;
	int allowed = 0;
	/* Allow access to a task's file descriptors if it is us or we
	 * may use ptrace attach to the process and find out that
	 * information.
	 */
	task = get_proc_task(inode);
	if (task) {
		allowed = ptrace_may_attach(task);
		put_task_struct(task);
	}
	return allowed;
}

static int proc_setattr(struct dentry *dentry, struct iattr *attr)
{
	int error;
	struct inode *inode = dentry->d_inode;

	if (attr->ia_valid & ATTR_MODE)
		return -EPERM;

	error = inode_change_ok(inode, attr);
	if (!error)
		error = inode_setattr(inode, attr);
	return error;
}

static const struct inode_operations proc_def_inode_operations = {
	.setattr	= proc_setattr,
};

extern struct seq_operations mounts_op;
struct proc_mounts {
	struct seq_file m;
	int event;
};

static int mounts_open(struct inode *inode, struct file *file)
{
	struct task_struct *task = get_proc_task(inode);
	struct nsproxy *nsp;
	struct mnt_namespace *ns = NULL;
	struct proc_mounts *p;
	int ret = -EINVAL;

	if (task) {
		rcu_read_lock();
		nsp = task_nsproxy(task);
		if (nsp) {
			ns = nsp->mnt_ns;
			if (ns)
				get_mnt_ns(ns);
		}
		rcu_read_unlock();

		put_task_struct(task);
	}

	if (ns) {
		ret = -ENOMEM;
		p = kmalloc(sizeof(struct proc_mounts), GFP_KERNEL);
		if (p) {
			file->private_data = &p->m;
			ret = seq_open(file, &mounts_op);
			if (!ret) {
				p->m.private = ns;
				p->event = ns->event;
				return 0;
			}
			kfree(p);
		}
		put_mnt_ns(ns);
	}
	return ret;
}

static int mounts_release(struct inode *inode, struct file *file)
{
	struct seq_file *m = file->private_data;
	struct mnt_namespace *ns = m->private;
	put_mnt_ns(ns);
	return seq_release(inode, file);
}

static unsigned mounts_poll(struct file *file, poll_table *wait)
{
	struct proc_mounts *p = file->private_data;
	struct mnt_namespace *ns = p->m.private;
	unsigned res = 0;

	poll_wait(file, &ns->poll, wait);

	spin_lock(&vfsmount_lock);
	if (p->event != ns->event) {
		p->event = ns->event;
		res = POLLERR;
	}
	spin_unlock(&vfsmount_lock);

	return res;
}

static const struct file_operations proc_mounts_operations = {
	.open		= mounts_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= mounts_release,
	.poll		= mounts_poll,
};

extern struct seq_operations mountstats_op;
static int mountstats_open(struct inode *inode, struct file *file)
{
	int ret = seq_open(file, &mountstats_op);

	if (!ret) {
		struct seq_file *m = file->private_data;
		struct nsproxy *nsp;
		struct mnt_namespace *mnt_ns = NULL;
		struct task_struct *task = get_proc_task(inode);

		if (task) {
			rcu_read_lock();
			nsp = task_nsproxy(task);
			if (nsp) {
				mnt_ns = nsp->mnt_ns;
				if (mnt_ns)
					get_mnt_ns(mnt_ns);
			}
			rcu_read_unlock();

			put_task_struct(task);
		}

		if (mnt_ns)
			m->private = mnt_ns;
		else {
			seq_release(inode, file);
			ret = -EINVAL;
		}
	}
	return ret;
}

static const struct file_operations proc_mountstats_operations = {
	.open		= mountstats_open,