base.c

来自「Linux Kernel 2.6.9 for OMAP1710」· C语言 代码 · 共 1,839 行 · 第 1/3 页

/*
 *  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.
 */

#include <asm/uaccess.h>

#include <linux/config.h>
#include <linux/errno.h>
#include <linux/time.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/init.h>
#include <linux/file.h>
#include <linux/string.h>
#include <linux/seq_file.h>
#include <linux/namei.h>
#include <linux/namespace.h>
#include <linux/mm.h>
#include <linux/smp_lock.h>
#include <linux/kallsyms.h>
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/ptrace.h>

/*
 * For hysterical raisins we keep the same inumbers as in the old procfs.
 * Feel free to change the macro below - just keep the range distinct from
 * inumbers of the rest of procfs (currently those are in 0x0000--0xffff).
 * As soon as we'll get a separate superblock we will be able to forget
 * about magical ranges too.
 */

#define fake_ino(pid,ino) (((pid)<<16)|(ino))

enum pid_directory_inos {
	PROC_TGID_INO = 2,
	PROC_TGID_TASK,
	PROC_TGID_STATUS,
	PROC_TGID_MEM,
	PROC_TGID_CWD,
	PROC_TGID_ROOT,
	PROC_TGID_EXE,
	PROC_TGID_FD,
	PROC_TGID_ENVIRON,
	PROC_TGID_AUXV,
	PROC_TGID_CMDLINE,
	PROC_TGID_STAT,
	PROC_TGID_STATM,
	PROC_TGID_MAPS,
	PROC_TGID_MOUNTS,
	PROC_TGID_WCHAN,
#ifdef CONFIG_SCHEDSTATS
	PROC_TGID_SCHEDSTAT,
#endif
#ifdef CONFIG_SECURITY
	PROC_TGID_ATTR,
	PROC_TGID_ATTR_CURRENT,
	PROC_TGID_ATTR_PREV,
	PROC_TGID_ATTR_EXEC,
	PROC_TGID_ATTR_FSCREATE,
#endif
	PROC_TGID_FD_DIR,
	PROC_TID_INO,
	PROC_TID_STATUS,
	PROC_TID_MEM,
	PROC_TID_CWD,
	PROC_TID_ROOT,
	PROC_TID_EXE,
	PROC_TID_FD,
	PROC_TID_ENVIRON,
	PROC_TID_AUXV,
	PROC_TID_CMDLINE,
	PROC_TID_STAT,
	PROC_TID_STATM,
	PROC_TID_MAPS,
	PROC_TID_MOUNTS,
	PROC_TID_WCHAN,
#ifdef CONFIG_SCHEDSTATS
	PROC_TID_SCHEDSTAT,
#endif
#ifdef CONFIG_SECURITY
	PROC_TID_ATTR,
	PROC_TID_ATTR_CURRENT,
	PROC_TID_ATTR_PREV,
	PROC_TID_ATTR_EXEC,
	PROC_TID_ATTR_FSCREATE,
#endif
	PROC_TID_FD_DIR = 0x8000,	/* 0x8000-0xffff */
};

struct pid_entry {
	int type;
	int len;
	char *name;
	mode_t mode;
};

#define E(type,name,mode) {(type),sizeof(name)-1,(name),(mode)}

static struct pid_entry tgid_base_stuff[] = {
	E(PROC_TGID_TASK,      "task",    S_IFDIR|S_IRUGO|S_IXUGO),
	E(PROC_TGID_FD,        "fd",      S_IFDIR|S_IRUSR|S_IXUSR),
	E(PROC_TGID_ENVIRON,   "environ", S_IFREG|S_IRUSR),
	E(PROC_TGID_AUXV,      "auxv",	  S_IFREG|S_IRUSR),
	E(PROC_TGID_STATUS,    "status",  S_IFREG|S_IRUGO),
	E(PROC_TGID_CMDLINE,   "cmdline", S_IFREG|S_IRUGO),
	E(PROC_TGID_STAT,      "stat",    S_IFREG|S_IRUGO),
	E(PROC_TGID_STATM,     "statm",   S_IFREG|S_IRUGO),
	E(PROC_TGID_MAPS,      "maps",    S_IFREG|S_IRUGO),
	E(PROC_TGID_MEM,       "mem",     S_IFREG|S_IRUSR|S_IWUSR),
	E(PROC_TGID_CWD,       "cwd",     S_IFLNK|S_IRWXUGO),
	E(PROC_TGID_ROOT,      "root",    S_IFLNK|S_IRWXUGO),
	E(PROC_TGID_EXE,       "exe",     S_IFLNK|S_IRWXUGO),
	E(PROC_TGID_MOUNTS,    "mounts",  S_IFREG|S_IRUGO),
#ifdef CONFIG_SECURITY
	E(PROC_TGID_ATTR,      "attr",    S_IFDIR|S_IRUGO|S_IXUGO),
#endif
#ifdef CONFIG_KALLSYMS
	E(PROC_TGID_WCHAN,     "wchan",   S_IFREG|S_IRUGO),
#endif
#ifdef CONFIG_SCHEDSTATS
	E(PROC_TGID_SCHEDSTAT, "schedstat", S_IFREG|S_IRUGO),
#endif
	{0,0,NULL,0}
};
static struct pid_entry tid_base_stuff[] = {
	E(PROC_TID_FD,         "fd",      S_IFDIR|S_IRUSR|S_IXUSR),
	E(PROC_TID_ENVIRON,    "environ", S_IFREG|S_IRUSR),
	E(PROC_TID_AUXV,       "auxv",	  S_IFREG|S_IRUSR),
	E(PROC_TID_STATUS,     "status",  S_IFREG|S_IRUGO),
	E(PROC_TID_CMDLINE,    "cmdline", S_IFREG|S_IRUGO),
	E(PROC_TID_STAT,       "stat",    S_IFREG|S_IRUGO),
	E(PROC_TID_STATM,      "statm",   S_IFREG|S_IRUGO),
	E(PROC_TID_MAPS,       "maps",    S_IFREG|S_IRUGO),
	E(PROC_TID_MEM,        "mem",     S_IFREG|S_IRUSR|S_IWUSR),
	E(PROC_TID_CWD,        "cwd",     S_IFLNK|S_IRWXUGO),
	E(PROC_TID_ROOT,       "root",    S_IFLNK|S_IRWXUGO),
	E(PROC_TID_EXE,        "exe",     S_IFLNK|S_IRWXUGO),
	E(PROC_TID_MOUNTS,     "mounts",  S_IFREG|S_IRUGO),
#ifdef CONFIG_SECURITY
	E(PROC_TID_ATTR,       "attr",    S_IFDIR|S_IRUGO|S_IXUGO),
#endif
#ifdef CONFIG_KALLSYMS
	E(PROC_TID_WCHAN,      "wchan",   S_IFREG|S_IRUGO),
#endif
#ifdef CONFIG_SCHEDSTATS
	E(PROC_TID_SCHEDSTAT, "schedstat",S_IFREG|S_IRUGO),
#endif
	{0,0,NULL,0}
};

#ifdef CONFIG_SECURITY
static struct pid_entry tgid_attr_stuff[] = {
	E(PROC_TGID_ATTR_CURRENT,  "current",  S_IFREG|S_IRUGO|S_IWUGO),
	E(PROC_TGID_ATTR_PREV,     "prev",     S_IFREG|S_IRUGO),
	E(PROC_TGID_ATTR_EXEC,     "exec",     S_IFREG|S_IRUGO|S_IWUGO),
	E(PROC_TGID_ATTR_FSCREATE, "fscreate", S_IFREG|S_IRUGO|S_IWUGO),
	{0,0,NULL,0}
};
static struct pid_entry tid_attr_stuff[] = {
	E(PROC_TID_ATTR_CURRENT,   "current",  S_IFREG|S_IRUGO|S_IWUGO),
	E(PROC_TID_ATTR_PREV,      "prev",     S_IFREG|S_IRUGO),
	E(PROC_TID_ATTR_EXEC,      "exec",     S_IFREG|S_IRUGO|S_IWUGO),
	E(PROC_TID_ATTR_FSCREATE,  "fscreate", S_IFREG|S_IRUGO|S_IWUGO),
	{0,0,NULL,0}
};
#endif

#undef E

static inline struct task_struct *proc_task(struct inode *inode)
{
	return PROC_I(inode)->task;
}

static inline int proc_type(struct inode *inode)
{
	return PROC_I(inode)->type;
}

int proc_pid_stat(struct task_struct*,char*);
int proc_pid_status(struct task_struct*,char*);
int proc_pid_statm(struct task_struct*,char*);

static int proc_fd_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt)
{
	struct task_struct *task = proc_task(inode);
	struct files_struct *files;
	struct file *file;
	int fd = proc_type(inode) - PROC_TID_FD_DIR;

	files = get_files_struct(task);
	if (files) {
		spin_lock(&files->file_lock);
		file = fcheck_files(files, fd);
		if (file) {
			*mnt = mntget(file->f_vfsmnt);
			*dentry = dget(file->f_dentry);
			spin_unlock(&files->file_lock);
			put_files_struct(files);
			return 0;
		}
		spin_unlock(&files->file_lock);
		put_files_struct(files);
	}
	return -ENOENT;
}

static int proc_exe_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt)
{
	struct vm_area_struct * vma;
	int result = -ENOENT;
	struct task_struct *task = proc_task(inode);
	struct mm_struct * mm = get_task_mm(task);

	if (!mm)
		goto out;
	down_read(&mm->mmap_sem);
	vma = mm->mmap;
	while (vma) {
		if ((vma->vm_flags & VM_EXECUTABLE) && 
		    vma->vm_file) {
			*mnt = mntget(vma->vm_file->f_vfsmnt);
			*dentry = dget(vma->vm_file->f_dentry);
			result = 0;
			break;
		}
		vma = vma->vm_next;
	}
	up_read(&mm->mmap_sem);
	mmput(mm);
out:
	return result;
}

static int proc_cwd_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt)
{
	struct fs_struct *fs;
	int result = -ENOENT;
	task_lock(proc_task(inode));
	fs = proc_task(inode)->fs;
	if(fs)
		atomic_inc(&fs->count);
	task_unlock(proc_task(inode));
	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 fs_struct *fs;
	int result = -ENOENT;
	task_lock(proc_task(inode));
	fs = proc_task(inode)->fs;
	if(fs)
		atomic_inc(&fs->count);
	task_unlock(proc_task(inode));
	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))

static int may_ptrace_attach(struct task_struct *task)
{
	int retval = 0;

	task_lock(task);

	if (!task->mm)
		goto out;
	if (((current->uid != task->euid) ||
	     (current->uid != task->suid) ||
	     (current->uid != task->uid) ||
	     (current->gid != task->egid) ||
	     (current->gid != task->sgid) ||
	     (current->gid != task->gid)) && !capable(CAP_SYS_PTRACE))
		goto out;
	rmb();
	if (!task->mm->dumpable && !capable(CAP_SYS_PTRACE))
		goto out;
	if (security_ptrace(current, task))
		goto out;

	retval = 1;
out:
	task_unlock(task);
	return retval;
}

static int proc_pid_environ(struct task_struct *task, char * buffer)
{
	int res = 0;
	struct mm_struct *mm = get_task_mm(task);
	if (mm) {
		unsigned int len = mm->env_end - mm->env_start;
		if (len > PAGE_SIZE)
			len = PAGE_SIZE;
		res = access_process_vm(task, mm->env_start, buffer, len, 0);
		if (!may_ptrace_attach(task))
			res = -ESRCH;
		mmput(mm);
	}
	return res;
}

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;	/* 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);
		}
	}
	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)
{
	char *modname;
	const char *sym_name;
	unsigned long wchan, size, offset;
	char namebuf[128];

	wchan = get_wchan(task);

	sym_name = kallsyms_lookup(wchan, &size, &offset, &modname, namebuf);
	if (sym_name)
		return sprintf(buffer, "%s", sym_name);
	return sprintf(buffer, "%lu", wchan);
}
#endif /* CONFIG_KALLSYMS */

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

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

/* permission checks */

static int proc_check_root(struct inode *inode)
{
	struct dentry *de, *base, *root;
	struct vfsmount *our_vfsmnt, *vfsmnt, *mnt;
	int res = 0;

	if (proc_root_link(inode, &root, &vfsmnt)) /* Ewww... */
		return -ENOENT;
	read_lock(&current->fs->lock);
	our_vfsmnt = mntget(current->fs->rootmnt);
	base = dget(current->fs->root);
	read_unlock(&current->fs->lock);

	spin_lock(&vfsmount_lock);
	de = root;
	mnt = vfsmnt;

	while (vfsmnt != our_vfsmnt) {
		if (vfsmnt == vfsmnt->mnt_parent)
			goto out;
		de = vfsmnt->mnt_mountpoint;
		vfsmnt = vfsmnt->mnt_parent;
	}

	if (!is_subdir(de, base))
		goto out;
	spin_unlock(&vfsmount_lock);

exit:
	dput(base);
	mntput(our_vfsmnt);
	dput(root);
	mntput(mnt);
	return res;
out:
	spin_unlock(&vfsmount_lock);
	res = -EACCES;
	goto exit;
}

static int proc_permission(struct inode *inode, int mask, struct nameidata *nd)
{
	if (vfs_permission(inode, mask) != 0)
		return -EACCES;
	return proc_check_root(inode);
}

extern struct seq_operations proc_pid_maps_op;
static int maps_open(struct inode *inode, struct file *file)
{
	struct task_struct *task = proc_task(inode);
	int ret = seq_open(file, &proc_pid_maps_op);
	if (!ret) {
		struct seq_file *m = file->private_data;
		m->private = task;
	}
	return ret;
}

static struct file_operations proc_maps_operations = {
	.open		= maps_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release,
};

extern struct seq_operations mounts_op;
static int mounts_open(struct inode *inode, struct file *file)
{
	struct task_struct *task = proc_task(inode);
	int ret = seq_open(file, &mounts_op);

	if (!ret) {
		struct seq_file *m = file->private_data;
		struct namespace *namespace;
		task_lock(task);
		namespace = task->namespace;
		if (namespace)
			get_namespace(namespace);
		task_unlock(task);

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

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

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

#define PROC_BLOCK_SIZE	(3*1024)		/* 4K page size but our output routines use some slack for overruns */

static ssize_t proc_info_read(struct file * file, char __user * buf,
			  size_t count, loff_t *ppos)
{
	struct inode * inode = file->f_dentry->d_inode;
	unsigned long page;
	ssize_t length;
	struct task_struct *task = proc_task(inode);

	if (count > PROC_BLOCK_SIZE)
		count = PROC_BLOCK_SIZE;
	if (!(page = __get_free_page(GFP_KERNEL)))
		return -ENOMEM;

	length = PROC_I(inode)->op.proc_read(task, (char*)page);

	if (length >= 0)
		length = simple_read_from_buffer(buf, count, ppos, (char *)page, length);
	free_page(page);
	return length;
}

static struct file_operations proc_info_file_operations = {
	.read		= proc_info_read,
};

static int mem_open(struct inode* inode, struct file* file)
{
	file->private_data = (void*)((long)current->self_exec_id);
	return 0;
}

static ssize_t mem_read(struct file * file, char __user * buf,
			size_t count, loff_t *ppos)
{
	struct task_struct *task = proc_task(file->f_dentry->d_inode);
	char *page;
	unsigned long src = *ppos;
	int ret = -ESRCH;
	struct mm_struct *mm;

	if (!MAY_PTRACE(task) || !may_ptrace_attach(task))
		goto out;

	ret = -ENOMEM;
	page = (char *)__get_free_page(GFP_USER);
	if (!page)
		goto out;

	ret = 0;
 
	mm = get_task_mm(task);
	if (!mm)
		goto out_free;

	ret = -EIO;
 
	if (file->private_data != (void*)((long)current->self_exec_id))
		goto out_put;

	ret = 0;
 
	while (count > 0) {
		int this_len, retval;

		this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count;
		retval = access_process_vm(task, src, page, this_len, 0);
		if (!retval || !MAY_PTRACE(task) || !may_ptrace_attach(task)) {
			if (!ret)
				ret = -EIO;
			break;
		}

		if (copy_to_user(buf, page, retval)) {