base.c

/*
 *  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 <bruna.moreira@indt.org.br>
 *  Edjard Mota <edjard.mota@indt.org.br>
 *  Ilias Biris <ilias.biris@indt.org.br>
 *  Mauricio Lin <mauricio.lin@indt.org.br>
 *
 *  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 <simo.piiroinen@nokia.com>:
 *  Smaps information related to shared, private, clean and dirty pages.
 *
 *  Paul Mundt <paul.mundt@nokia.com>:
 *  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/task_io_accounting_ops.h>
#include <linux/init.h>
#include <linux/capability.h>
#include <linux/file.h>
#include <linux/fdtable.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/stacktrace.h>
#include <linux/resource.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/ptrace.h>
#include <linux/tracehook.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 <linux/fs_struct.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.
 */

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, iops, fops)	\
	NOD(NAME, (S_IFDIR|(MODE)), &iops, &fops, {} )
#define LNK(NAME, get_link)					\
	NOD(NAME, (S_IFLNK|S_IRWXUGO),				\
		&proc_pid_link_inode_operations, NULL,		\
		{ .proc_get_link = get_link } )
#define REG(NAME, MODE, fops)				\
	NOD(NAME, (S_IFREG|(MODE)), NULL, &fops, {})
#define INF(NAME, MODE, read)				\
	NOD(NAME, (S_IFREG|(MODE)), 			\
		NULL, &proc_info_file_operations,	\
		{ .proc_read = read } )
#define ONE(NAME, MODE, show)				\
	NOD(NAME, (S_IFREG|(MODE)), 			\
		NULL, &proc_single_file_operations,	\
		{ .proc_show = show } )

/*
 * Count the number of hardlinks for the pid_entry table, excluding the .
 * and .. links.
 */
static unsigned int pid_entry_count_dirs(const struct pid_entry *entries,
	unsigned int n)
{
	unsigned int i;
	unsigned int count;

	count = 0;
	for (i = 0; i < n; ++i) {
		if (S_ISDIR(entries[i].mode))
			++count;
	}

	return count;
}

static int get_fs_path(struct task_struct *task, struct path *path, bool root)
{
	struct fs_struct *fs;
	int result = -ENOENT;

	task_lock(task);
	fs = task->fs;
	if (fs) {
		read_lock(&fs->lock);
		*path = root ? fs->root : fs->pwd;
		path_get(path);
		read_unlock(&fs->lock);
		result = 0;
	}
	task_unlock(task);
	return result;
}

static int get_nr_threads(struct task_struct *tsk)
{
	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 path *path)
{
	struct task_struct *task = get_proc_task(inode);
	int result = -ENOENT;

	if (task) {
		result = get_fs_path(task, path, 0);
		put_task_struct(task);
	}
	return result;
}

static int proc_root_link(struct inode *inode, struct path *path)
{
	struct task_struct *task = get_proc_task(inode);
	int result = -ENOENT;

	if (task) {
		result = get_fs_path(task, path, 1);
		put_task_struct(task);
	}
	return result;
}

/*
 * Return zero if current may access user memory in @task, -error if not.
 */
static int check_mem_permission(struct task_struct *task)
{
	/*
	 * A task can always look at itself, in case it chooses
	 * to use system calls instead of load instructions.
	 */
	if (task == current)
		return 0;

	/*
	 * If current is actively ptrace'ing, and would also be
	 * permitted to freshly attach with ptrace now, permit it.
	 */
	if (task_is_stopped_or_traced(task)) {
		int match;
		rcu_read_lock();
		match = (tracehook_tracer_task(task) == current);
		rcu_read_unlock();
		if (match && ptrace_may_access(task, PTRACE_MODE_ATTACH))
			return 0;
	}

	/*
	 * Noone else is allowed.
	 */
	return -EPERM;
}

struct mm_struct *mm_for_maps(struct task_struct *task)
{
	struct mm_struct *mm;

	if (mutex_lock_killable(&task->cred_guard_mutex))
		return NULL;

	mm = get_task_mm(task);
	if (mm && mm != current->mm &&
			!ptrace_may_access(task, PTRACE_MODE_READ)) {
		mmput(mm);
		mm = NULL;
	}
	mutex_unlock(&task->cred_guard_mutex);

	return mm;
}

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)
		if (!ptrace_may_access(task, PTRACE_MODE_READ))
			return 0;
		else
			return sprintf(buffer, "%lu", wchan);
	else
		return sprintf(buffer, "%s", symname);
}
#endif /* CONFIG_KALLSYMS */

#ifdef CONFIG_STACKTRACE

#define MAX_STACK_TRACE_DEPTH	64

static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns,
			  struct pid *pid, struct task_struct *task)
{
	struct stack_trace trace;
	unsigned long *entries;
	int i;

	entries = kmalloc(MAX_STACK_TRACE_DEPTH * sizeof(*entries), GFP_KERNEL);
	if (!entries)
		return -ENOMEM;

	trace.nr_entries	= 0;
	trace.max_entries	= MAX_STACK_TRACE_DEPTH;
	trace.entries		= entries;
	trace.skip		= 0;
	save_stack_trace_tsk(task, &trace);

	for (i = 0; i < trace.nr_entries; i++) {
		seq_printf(m, "[<%p>] %pS\n",
			   (void *)entries[i], (void *)entries[i]);
	}
	kfree(entries);

	return 0;
}
#endif

#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",
			(unsigned long long)task->se.sum_exec_runtime,
			(unsigned long long)task->sched_info.run_delay,
			task->sched_info.pcount);
}
#endif

#ifdef CONFIG_LATENCYTOP
static int lstats_show_proc(struct seq_file *m, void *v)
{
	int i;
	struct inode *inode = m->private;
	struct task_struct *task = get_proc_task(inode);

	if (!task)
		return -ESRCH;
	seq_puts(m, "Latency Top version : v0.1\n");
	for (i = 0; i < 32; i++) {
		if (task->latency_record[i].backtrace[0]) {
			int q;
			seq_printf(m, "%i %li %li ",
				task->latency_record[i].count,
				task->latency_record[i].time,
				task->latency_record[i].max);
			for (q = 0; q < LT_BACKTRACEDEPTH; q++) {
				char sym[KSYM_SYMBOL_LEN];
				char *c;
				if (!task->latency_record[i].backtrace[q])
					break;
				if (task->latency_record[i].backtrace[q] == ULONG_MAX)
					break;
				sprint_symbol(sym, task->latency_record[i].backtrace[q]);
				c = strchr(sym, '+');
				if (c)
					*c = 0;
				seq_printf(m, "%s ", sym);
			}
			seq_printf(m, "\n");
		}

	}
	put_task_struct(task);
	return 0;
}

static int lstats_open(struct inode *inode, struct file *file)
{
	return single_open(file, lstats_show_proc, inode);
}

static ssize_t lstats_write(struct file *file, const char __user *buf,
			    size_t count, loff_t *offs)
{
	struct task_struct *task = get_proc_task(file->f_dentry->d_inode);

	if (!task)
		return -ESRCH;
	clear_all_latency_tracing(task);
	put_task_struct(task);

	return count;
}

static const struct file_operations proc_lstats_operations = {
	.open		= lstats_open,
	.read		= seq_read,
	.write		= lstats_write,
	.llseek		= seq_lseek,
	.release	= single_release,
};

#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},
	[RLIMIT_RTTIME] = {"Max realtime timeout", "us"},
};

/* 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];

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

	/*
	 * 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;
}

#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
static int proc_pid_syscall(struct task_struct *task, char *buffer)
{
	long nr;
	unsigned long args[6], sp, pc;

	if (task_current_syscall(task, &nr, args, 6, &sp, &pc))
		return sprintf(buffer, "running\n");

	if (nr < 0)
		return sprintf(buffer, "%ld 0x%lx 0x%lx\n", nr, sp, pc);

	return sprintf(buffer,
		       "%ld 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx\n",
		       nr,
		       args[0], args[1], args[2], args[3], args[4], args[5],
		       sp, pc);
}
#endif /* CONFIG_HAVE_ARCH_TRACEHOOK */

/************************************************************************/
/*                       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_access(task, PTRACE_MODE_READ);
		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,
};

static int mounts_open_common(struct inode *inode, struct file *file,
			      const struct seq_operations *op)
{
	struct task_struct *task = get_proc_task(inode);
	struct nsproxy *nsp;
	struct mnt_namespace *ns = NULL;
	struct path root;
	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();
		if (ns && get_fs_path(task, &root, 1) == 0)
			ret = 0;
		put_task_struct(task);
	}

	if (!ns)
		goto err;
	if (ret)
		goto err_put_ns;

	ret = -ENOMEM;
	p = kmalloc(sizeof(struct proc_mounts), GFP_KERNEL);
	if (!p)
		goto err_put_path;

	file->private_data = &p->m;
	ret = seq_open(file, op);
	if (ret)
		goto err_free;

	p->m.private = p;
	p->ns = ns;
	p->root = root;
	p->event = ns->event;

	return 0;

 err_free:
	kfree(p);
 err_put_path:
	path_put(&root);
 err_put_ns:
	put_mnt_ns(ns);
 err:
	return ret;
}

static int mounts_release(struct inode *inode, struct file *file)
{
	struct proc_mounts *p = file->private_data;
	path_put(&p->root);
	put_mnt_ns(p->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->ns;
	unsigned res = POLLIN | POLLRDNORM;

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

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

	return res;
}

static int mounts_open(struct inode *inode, struct file *file)
{
	return mounts_open_common(inode, file, &mounts_op);
}

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

static int mountinfo_open(struct inode *inode, struct file *file)
{
	return mounts_open_common(inode, file, &mountinfo_op);
}

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

static int mountstats_open(struct inode *inode, struct file *file)
{
	return mounts_open_common(inode, file, &mountstats_op);
}

static const struct file_operations proc_mountstats_operations = {
	.open		= mountstats_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_path.dentry->d_inode;
	unsigned long page;
	ssize_t length;
	struct task_struct *task = get_proc_task(inode);

	length = -ESRCH;
	if (!task)
		goto out_no_task;

	if (count > PROC_BLOCK_SIZE)
		count = PROC_BLOCK_SIZE;

	length = -ENOMEM;
	if (!(page = __get_free_page(GFP_TEMPORARY)))
		goto out;

	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);
out:
	put_task_struct(task);
out_no_task:
	return length;
}

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

static int proc_single_show(struct seq_file *m, void *v)
{
	struct inode *inode = m->private;
	struct pid_namespace *ns;
	struct pid *pid;
	struct task_struct *task;
	int ret;

	ns = inode->i_sb->s_fs_info;
	pid = proc_pid(inode);
	task = get_pid_task(pid, PIDTYPE_PID);
	if (!task)
		return -ESRCH;

	ret = PROC_I(inode)->op.proc_show(m, ns, pid, task);

	put_task_struct(task);
	return ret;
}

static int proc_single_open(struct inode *inode, struct file *filp)
{
	int ret;
	ret = single_open(filp, proc_single_show, NULL);
	if (!ret) {
		struct seq_file *m = filp->private_data;

		m->private = inode;
	}
	return ret;
}

static const struct file_operations proc_single_file_operations = {
	.open		= proc_single_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= single_release,
};

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 = get_proc_task(file->f_path.dentry->d_inode);
	char *page;
	unsigned long src = *ppos;
	int ret = -ESRCH;
	struct mm_struct *mm;

	if (!task)
		goto out_no_task;

	if (check_mem_permission(task))
		goto out;

	ret = -ENOMEM;
	page = (char *)__get_free_page(GFP_TEMPORARY);
	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 || check_mem_permission(task)) {
			if (!ret)
				ret = -EIO;
			break;
		}

		if (copy_to_user(buf, page, retval)) {
			ret = -EFAULT;
			break;
		}
 
		ret += retval;
		src += retval;
		buf += retval;
		count -= retval;
	}
	*ppos = src;

out_put:
	mmput(mm);
out_free:
	free_page((unsigned long) page);
out:
	put_task_struct(task);
out_no_task:
	return ret;
}

#define mem_write NULL

#ifndef mem_write
/* This is a security hazard */
static ssize_t mem_write(struct file * file, const char __user *buf,
			 size_t count, loff_t *ppos)
{
	int copied;
	char *page;
	struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
	unsigned long dst = *ppos;

	copied = -ESRCH;
	if (!task)
		goto out_no_task;

	if (check_mem_permission(task))
		goto out;

	copied = -ENOMEM;
	page = (char *)__get_free_page(GFP_TEMPORARY);
	if (!page)
		goto out;

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

		this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count;
		if (copy_from_user(page, buf, this_len)) {
			copied = -EFAULT;
			break;
		}
		retval = access_process_vm(task, dst, page, this_len, 1);
		if (!retval) {
			if (!copied)
				copied = -EIO;
			break;
		}
		copied += retval;
		buf += retval;
		dst += retval;
		count -= retval;			
	}
	*ppos = dst;
	free_page((unsigned long) page);
out:
	put_task_struct(task);
out_no_task:
	return copied;
}
#endif

loff_t mem_lseek(struct file *file, loff_t offset, int orig)
{
	switch (orig) {
	case 0:
		file->f_pos = offset;
		break;
	case 1:
		file->f_pos += offset;
		break;
	default:
		return -EINVAL;
	}
	force_successful_syscall_return();
	return file->f_pos;
}

static const struct file_operations proc_mem_operations = {
	.llseek		= mem_lseek,
	.read		= mem_read,
	.write		= mem_write,
	.open		= mem_open,
};

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

	if (!task)
		goto out_no_task;

	if (!ptrace_may_access(task, PTRACE_MODE_READ))
		goto out;

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

	ret = 0;

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

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

		this_len = mm->env_end - (mm->env_start + src);

		if (this_len <= 0)
			break;

		max_len = (count > PAGE_SIZE) ? PAGE_SIZE : count;
		this_len = (this_len > max_len) ? max_len : this_len;

		retval = access_process_vm(task, (mm->env_start + src),
			page, this_len, 0);

		if (retval <= 0) {
			ret = retval;
			break;
		}

		if (copy_to_user(buf, page, retval)) {
			ret = -EFAULT;
			break;
		}

		ret += retval;
		src += retval;
		buf += retval;
		count -= retval;
	}
	*ppos = src;

	mmput(mm);
out_free:
	free_page((unsigned long) page);
out:
	put_task_struct(task);
out_no_task:
	return ret;
}

static const struct file_operations proc_environ_operations = {
	.read		= environ_read,
};

static ssize_t oom_adjust_read(struct file *file, char __user *buf,
				size_t count, loff_t *ppos)
{
	struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
	char buffer[PROC_NUMBUF];
	size_t len;
	int oom_adjust;

	if (!task)
		return -ESRCH;
	task_lock(task);
	if (task->mm)
		oom_adjust = task->mm->oom_adj;
	else
		oom_adjust = OOM_DISABLE;
	task_unlock(task);
	put_task_struct(task);

	len = snprintf(buffer, sizeof(buffer), "%i\n", oom_adjust);

	return simple_read_from_buffer(buf, count, ppos, buffer, len);
}

static ssize_t oom_adjust_write(struct file *file, const char __user *buf,
				size_t count, loff_t *ppos)
{
	struct task_struct *task;
	char buffer[PROC_NUMBUF], *end;
	int oom_adjust;

	memset(buffer, 0, sizeof(buffer));
	if (count > sizeof(buffer) - 1)
		count = sizeof(buffer) - 1;
	if (copy_from_user(buffer, buf, count))
		return -EFAULT;
	oom_adjust = simple_strtol(buffer, &end, 0);
	if ((oom_adjust < OOM_ADJUST_MIN || oom_adjust > OOM_ADJUST_MAX) &&
	     oom_adjust != OOM_DISABLE)
		return -EINVAL;
	if (*end == '\n')
		end++;
	task = get_proc_task(file->f_path.dentry->d_inode);
	if (!task)
		return -ESRCH;
	task_lock(task);
	if (!task->mm) {
		task_unlock(task);
		put_task_struct(task);
		return -EINVAL;
	}
	if (oom_adjust < task->mm->oom_adj && !capable(CAP_SYS_RESOURCE)) {
		task_unlock(task);
		put_task_struct(task);
		return -EACCES;
	}
	task->mm->oom_adj = oom_adjust;
	task_unlock(task);
	put_task_struct(task);
	if (end - buffer == 0)
		return -EIO;
	return end - buffer;
}

static const struct file_operations proc_oom_adjust_operations = {
	.read		= oom_adjust_read,
	.write		= oom_adjust_write,
};

#ifdef CONFIG_AUDITSYSCALL
#define TMPBUFLEN 21
static ssize_t proc_loginuid_read(struct file * file, char __user * buf,
				  size_t count, loff_t *ppos)
{
	struct inode * inode = file->f_path.dentry->d_inode;
	struct task_struct *task = get_proc_task(inode);
	ssize_t length;
	char tmpbuf[TMPBUFLEN];

	if (!task)
		return -ESRCH;
	length = scnprintf(tmpbuf, TMPBUFLEN, "%u",
				audit_get_loginuid(task));
	put_task_struct(task);
	return simple_read_from_buffer(buf, count, ppos, tmpbuf, length);
}

static ssize_t proc_loginuid_write(struct file * file, const char __user * buf,
				   size_t count, loff_t *ppos)
{
	struct inode * inode = file->f_path.dentry->d_inode;
	char *page, *tmp;
	ssize_t length;
	uid_t loginuid;

	if (!capable(CAP_AUDIT_CONTROL))
		return -EPERM;

	if (current != pid_task(proc_pid(inode), PIDTYPE_PID))
		return -EPERM;

	if (count >= PAGE_SIZE)
		count = PAGE_SIZE - 1;

	if (*ppos != 0) {
		/* No partial writes. */
		return -EINVAL;
	}
	page = (char*)__get_free_page(GFP_TEMPORARY);
	if (!page)
		return -ENOMEM;
	length = -EFAULT;
	if (copy_from_user(page, buf, count))
		goto out_free_page;

	page[count] = '\0';
	loginuid = simple_strtoul(page, &tmp, 10);
	if (tmp == page) {
		length = -EINVAL;
		goto out_free_page;

	}
	length = audit_set_loginuid(current, loginuid);
	if (likely(length == 0))
		length = count;

out_free_page:
	free_page((unsigned long) page);
	return length;
}

static const struct file_operations proc_loginuid_operations = {
	.read		= proc_loginuid_read,
	.write		= proc_loginuid_write,
};

static ssize_t proc_sessionid_read(struct file * file, char __user * buf,
				  size_t count, loff_t *ppos)
{
	struct inode * inode = file->f_path.dentry->d_inode;
	struct task_struct *task = get_proc_task(inode);
	ssize_t length;
	char tmpbuf[TMPBUFLEN];

	if (!task)
		return -ESRCH;
	length = scnprintf(tmpbuf, TMPBUFLEN, "%u",
				audit_get_sessionid(task));
	put_task_struct(task);
	return simple_read_from_buffer(buf, count, ppos, tmpbuf, length);
}

static const struct file_operations proc_sessionid_operations = {
	.read		= proc_sessionid_read,
};
#endif

#ifdef CONFIG_FAULT_INJECTION
static ssize_t proc_fault_inject_read(struct file * file, char __user * buf,
				      size_t count, loff_t *ppos)
{
	struct task_struct *task = get_proc_task(file->f_dentry->d_inode);
	char buffer[PROC_NUMBUF];
	size_t len;
	int make_it_fail;

	if (!task)
		return -ESRCH;
	make_it_fail = task->make_it_fail;
	put_task_struct(task);

	len = snprintf(buffer, sizeof(buffer), "%i\n", make_it_fail);

	return simple_read_from_buffer(buf, count, ppos, buffer, len);
}

static ssize_t proc_fault_inject_write(struct file * file,
			const char __user * buf, size_t count, loff_t *ppos)
{
	struct task_struct *task;
	char buffer[PROC_NUMBUF], *end;
	int make_it_fail;

	if (!capable(CAP_SYS_RESOURCE))
		return -EPERM;
	memset(buffer, 0, sizeof(buffer));
	if (count > sizeof(buffer) - 1)
		count = sizeof(buffer) - 1;
	if (copy_from_user(buffer, buf, count))
		return -EFAULT;
	make_it_fail = simple_strtol(buffer, &end, 0);
	if (*end == '\n')
		end++;
	task = get_proc_task(file->f_dentry->d_inode);
	if (!task)
		return -ESRCH;
	task->make_it_fail = make_it_fail;
	put_task_struct(task);
	if (end - buffer == 0)
		return -EIO;
	return end - buffer;
}

static const struct file_operations proc_fault_inject_operations = {
	.read		= proc_fault_inject_read,
	.write		= proc_fault_inject_write,
};
#endif


#ifdef CONFIG_SCHED_DEBUG
/*
 * Print out various scheduling related per-task fields:
 */
static int sched_show(struct seq_file *m, void *v)
{
	struct inode *inode = m->private;
	struct task_struct *p;

	p = get_proc_task(inode);
	if (!p)
		return -ESRCH;
	proc_sched_show_task(p, m);

	put_task_struct(p);

	return 0;
}

static ssize_t
sched_write(struct file *file, const char __user *buf,
	    size_t count, loff_t *offset)
{
	struct inode *inode = file->f_path.dentry->d_inode;
	struct task_struct *p;

	p = get_proc_task(inode);
	if (!p)
		return -ESRCH;
	proc_sched_set_task(p);

	put_task_struct(p);

	return count;
}

static int sched_open(struct inode *inode, struct file *filp)
{
	int ret;

	ret = single_open(filp, sched_show, NULL);
	if (!ret) {
		struct seq_file *m = filp->private_data;

		m->private = inode;
	}
	return ret;
}

static const struct file_operations proc_pid_sched_operations = {
	.open		= sched_open,
	.read		= seq_read,
	.write		= sched_write,
	.llseek		= seq_lseek,
	.release	= single_release,
};

#endif

/*
 * We added or removed a vma mapping the executable. The vmas are only mapped
 * during exec and are not mapped with the mmap system call.
 * Callers must hold down_write() on the mm's mmap_sem for these
 */
void added_exe_file_vma(struct mm_struct *mm)
{
	mm->num_exe_file_vmas++;
}

void removed_exe_file_vma(struct mm_struct *mm)
{
	mm->num_exe_file_vmas--;
	if ((mm->num_exe_file_vmas == 0) && mm->exe_file){
		fput(mm->exe_file);
		mm->exe_file = NULL;
	}

}

void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
{
	if (new_exe_file)
		get_file(new_exe_file);
	if (mm->exe_file)
		fput(mm->exe_file);
	mm->exe_file = new_exe_file;
	mm->num_exe_file_vmas = 0;
}

struct file *get_mm_exe_file(struct mm_struct *mm)
{
	struct file *exe_file;

	/* We need mmap_sem to protect against races with removal of
	 * VM_EXECUTABLE vmas */
	down_read(&mm->mmap_sem);
	exe_file = mm->exe_file;
	if (exe_file)
		get_file(exe_file);
	up_read(&mm->mmap_sem);
	return exe_file;
}

void dup_mm_exe_file(struct mm_struct *oldmm, struct mm_struct *newmm)
{
	/* It's safe to write the exe_file pointer without exe_file_lock because
	 * this is called during fork when the task is not yet in /proc */
	newmm->exe_file = get_mm_exe_file(oldmm);
}

static int proc_exe_link(struct inode *inode, struct path *exe_path)
{
	struct task_struct *task;
	struct mm_struct *mm;
	struct file *exe_file;

	task = get_proc_task(inode);
	if (!task)
		return -ENOENT;
	mm = get_task_mm(task);
	put_task_struct(task);
	if (!mm)
		return -ENOENT;
	exe_file = get_mm_exe_file(mm);
	mmput(mm);
	if (exe_file) {
		*exe_path = exe_file->f_path;
		path_get(&exe_file->f_path);
		fput(exe_file);
		return 0;
	} else
		return -ENOENT;
}

static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd)
{
	struct inode *inode = dentry->d_inode;
	int error = -EACCES;

	/* We don't need a base pointer in the /proc filesystem */
	path_put(&nd->path);

	/* Are we allowed to snoop on the tasks file descriptors? */
	if (!proc_fd_access_allowed(inode))
		goto out;

	error = PROC_I(inode)->op.proc_get_link(inode, &nd->path);
	nd->last_type = LAST_BIND;
out:
	return ERR_PTR(error);
}

static int do_proc_readlink(struct path *path, char __user *buffer, int buflen)
{
	char *tmp = (char*)__get_free_page(GFP_TEMPORARY);
	char *pathname;
	int len;

	if (!tmp)
		return -ENOMEM;

	pathname = d_path(path, tmp, PAGE_SIZE);
	len = PTR_ERR(pathname);
	if (IS_ERR(pathname))
		goto out;
	len = tmp + PAGE_SIZE - 1 - pathname;

	if (len > buflen)
		len = buflen;
	if (copy_to_user(buffer, pathname, len))
		len = -EFAULT;
 out:
	free_page((unsigned long)tmp);
	return len;
}

static int proc_pid_readlink(struct dentry * dentry, char __user * buffer, int buflen)
{
	int error = -EACCES;
	struct inode *inode = dentry->d_inode;
	struct path path;

	/* Are we allowed to snoop on the tasks file descriptors? */
	if (!proc_fd_access_allowed(inode))
		goto out;

	error = PROC_I(inode)->op.proc_get_link(inode, &path);
	if (error)
		goto out;

	error = do_proc_readlink(&path, buffer, buflen);
	path_put(&path);
out:
	return error;
}

static const struct inode_operations proc_pid_link_inode_operations = {
	.readlink	= proc_pid_readlink,
	.follow_link	= proc_pid_follow_link,
	.setattr	= proc_setattr,
};


/* building an inode */

static int task_dumpable(struct task_struct *task)
{
	int dumpable = 0;
	struct mm_struct *mm;

	task_lock(task);
	mm = task->mm;
	if (mm)
		dumpable = get_dumpable(mm);
	task_unlock(task);
	if(dumpable == 1)
		return 1;
	return 0;
}


static struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task)
{
	struct inode * inode;
	struct proc_inode *ei;
	const struct cred *cred;

	/* We need a new inode */

	inode = new_inode(sb);
	if (!inode)
		goto out;

	/* Common stuff */
	ei = PROC_I(inode);
	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
	inode->i_op = &proc_def_inode_operations;

	/*
	 * grab the reference to task.
	 */
	ei->pid = get_task_pid(task, PIDTYPE_PID);
	if (!ei->pid)
		goto out_unlock;

	if (task_dumpable(task)) {
		rcu_read_lock();
		cred = __task_cred(task);
		inode->i_uid = cred->euid;
		inode->i_gid = cred->egid;
		rcu_read_unlock();
	}
	security_task_to_inode(task, inode);

out:
	return inode;

out_unlock:
	iput(inode);
	return NULL;
}