/*
 *  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/swap.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 <linux/slab.h>
#ifdef CONFIG_HARDWALL
#include <asm/hardwall.h>
#endif
#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_task_root(struct task_struct *task, struct path *root)
{
        int result = -ENOENT;

        task_lock(task);
        if (task->fs) {
                get_fs_root(task->fs, root);
                result = 0;
        }
        task_unlock(task);
        return result;
}

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

        if (task) {
                task_lock(task);
                if (task->fs) {
                        get_fs_pwd(task->fs, path);
                        result = 0;
                }
                task_unlock(task);
                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_task_root(task, path);
                put_task_struct(task);
        }
        return result;
}

static struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
{
        struct mm_struct *mm;
        int err;

        err =  mutex_lock_killable(&task->signal->cred_guard_mutex);
        if (err)
                return ERR_PTR(err);

        mm = get_task_mm(task);
        if (mm && mm != current->mm &&
                        !ptrace_may_access(task, mode)) {
                mmput(mm);
                mm = ERR_PTR(-EACCES);
        }
        mutex_unlock(&task->signal->cred_guard_mutex);

        return mm;
}

struct mm_struct *mm_for_maps(struct task_struct *task)
{
        return mm_access(task, PTRACE_MODE_READ);
}

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)
{
        struct mm_struct *mm = mm_for_maps(task);
        int res = PTR_ERR(mm);
        if (mm && !IS_ERR(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 */

static int lock_trace(struct task_struct *task)
{
        int err = mutex_lock_killable(&task->signal->cred_guard_mutex);
        if (err)
                return err;
        if (!ptrace_may_access(task, PTRACE_MODE_ATTACH)) {
                mutex_unlock(&task->signal->cred_guard_mutex);
                return -EPERM;
        }
        return 0;
}

static void unlock_trace(struct task_struct *task)
{
        mutex_unlock(&task->signal->cred_guard_mutex);
}

#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 err;
        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;

        err = lock_trace(task);
        if (!err) {
                save_stack_trace_tsk(task, &trace);

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

        return err;
}
#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++) {
                struct latency_record *lr = &task->latency_record[i];
                if (lr->backtrace[0]) {
                        int q;
                        seq_printf(m, "%i %li %li",
                                   lr->count, lr->time, lr->max);
                        for (q = 0; q < LT_BACKTRACEDEPTH; q++) {
                                unsigned long bt = lr->backtrace[q];
                                if (!bt)
                                        break;
                                if (bt == ULONG_MAX)
                                        break;
                                seq_printf(m, " %ps", (void *)bt);
                        }
                        seq_putc(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

static int proc_oom_score(struct task_struct *task, char *buffer)
{
        unsigned long points = 0;

        read_lock(&tasklist_lock);
        if (pid_alive(task))
                points = oom_badness(task, NULL, NULL,
                                        totalram_pages + total_swap_pages);
        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", "seconds"},
        [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;
        int res = lock_trace(task);
        if (res)
                return res;

        if (task_current_syscall(task, &nr, args, 6, &sp, &pc))
                res = sprintf(buffer, "running\n");
        else if (nr < 0)
                res = sprintf(buffer, "%ld 0x%lx 0x%lx\n", nr, sp, pc);
        else
                res = 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);
        unlock_trace(task);
        return res;
}
#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;
}

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)
                return error;

        if ((attr->ia_valid & ATTR_SIZE) &&
            attr->ia_size != i_size_read(inode)) {
                error = vmtruncate(inode, attr->ia_size);
                if (error)
                        return error;
        }

        setattr_copy(inode, attr);
        mark_inode_dirty(inode);
        return 0;
}

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_task_root(task, &root) == 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->m.poll_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;
        unsigned res = POLLIN | POLLRDNORM;

        poll_wait(file, &p->ns->poll, wait);
        if (mnt_had_events(p))
                res |= POLLERR | POLLPRI;

        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,
        .llseek         = generic_file_llseek,
};

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)
{
        return single_open(filp, proc_single_show, inode);
}

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)
{
        struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
        struct mm_struct *mm;

        if (!task)
                return -ESRCH;

        mm = mm_access(task, PTRACE_MODE_ATTACH);
        put_task_struct(task);

        if (IS_ERR(mm))
                return PTR_ERR(mm);

        if (mm) {
                /* ensure this mm_struct can't be freed */
                atomic_inc(&mm->mm_count);
                /* but do not pin its memory */
                mmput(mm);
        }

        /* OK to pass negative loff_t, we can catch out-of-range */
        file->f_mode |= FMODE_UNSIGNED_OFFSET;
        file->private_data = mm;

        return 0;
}

static ssize_t mem_rw(struct file *file, char __user *buf,
                        size_t count, loff_t *ppos, int write)
{
        struct mm_struct *mm = file->private_data;
        unsigned long addr = *ppos;
        ssize_t copied;
        char *page;

        if (!mm)
                return 0;

        page = (char *)__get_free_page(GFP_TEMPORARY);
        if (!page)
                return -ENOMEM;

        copied = 0;
        if (!atomic_inc_not_zero(&mm->mm_users))
                goto free;

        while (count > 0) {
                int this_len = min_t(int, count, PAGE_SIZE);

                if (write && copy_from_user(page, buf, this_len)) {
                        copied = -EFAULT;
                        break;
                }

                this_len = access_remote_vm(mm, addr, page, this_len, write);
                if (!this_len) {
                        if (!copied)
                                copied = -EIO;
                        break;
                }

                if (!write && copy_to_user(buf, page, this_len)) {
                        copied = -EFAULT;
                        break;
                }

                buf += this_len;
                addr += this_len;
                copied += this_len;
                count -= this_len;
        }
        *ppos = addr;

        mmput(mm);
free:
        free_page((unsigned long) page);
        return copied;
}

static ssize_t mem_read(struct file *file, char __user *buf,
                        size_t count, loff_t *ppos)
{
        return mem_rw(file, buf, count, ppos, 0);
}

static ssize_t mem_write(struct file *file, const char __user *buf,
                         size_t count, loff_t *ppos)
{
        return mem_rw(file, (char __user*)buf, count, ppos, 1);
}

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 int mem_release(struct inode *inode, struct file *file)
{
        struct mm_struct *mm = file->private_data;
        if (mm)
                mmdrop(mm);
        return 0;
}

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

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;

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


        mm = mm_for_maps(task);
        ret = PTR_ERR(mm);
        if (!mm || IS_ERR(mm))
                goto out_free;

        ret = 0;
        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,
        .llseek         = generic_file_llseek,
};

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 = OOM_DISABLE;
        unsigned long flags;

        if (!task)
                return -ESRCH;

        if (lock_task_sighand(task, &flags)) {
                oom_adjust = task->signal->oom_adj;
                unlock_task_sighand(task, &flags);
        }

        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];
        int oom_adjust;
        unsigned long flags;
        int err;

        memset(buffer, 0, sizeof(buffer));
        if (count > sizeof(buffer) - 1)
                count = sizeof(buffer) - 1;
        if (copy_from_user(buffer, buf, count)) {
                err = -EFAULT;
                goto out;
        }

        err = kstrtoint(strstrip(buffer), 0, &oom_adjust);
        if (err)
                goto out;

        if ((oom_adjust < OOM_ADJUST_MIN || oom_adjust > OOM_ADJUST_MAX) &&
             oom_adjust != OOM_DISABLE) {
                err = -EINVAL;
                goto out;
        }

        task = get_proc_task(file->f_path.dentry->d_inode);
        if (!task) {
                err = -ESRCH;
                goto out;
        }

        task_lock(task);
        if (!task->mm) {
                err = -EINVAL;
                goto err_task_lock;
        }

        if (!lock_task_sighand(task, &flags)) {
                err = -ESRCH;
                goto err_task_lock;
        }

        if (oom_adjust < task->signal->oom_adj && !capable(CAP_SYS_RESOURCE)) {
                err = -EACCES;
                goto err_sighand;
        }

        /*
         * Warn that /proc/pid/oom_adj is deprecated, see
         * Documentation/feature-removal-schedule.txt.
         */
        printk_once(KERN_WARNING "%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n",
                  current->comm, task_pid_nr(current), task_pid_nr(task),
                  task_pid_nr(task));
        task->signal->oom_adj = oom_adjust;
        /*
         * Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum
         * value is always attainable.
         */
        if (task->signal->oom_adj == OOM_ADJUST_MAX)
                task->signal->oom_score_adj = OOM_SCORE_ADJ_MAX;
        else
                task->signal->oom_score_adj = (oom_adjust * OOM_SCORE_ADJ_MAX) /
                                                                -OOM_DISABLE;
err_sighand:
        unlock_task_sighand(task, &flags);
err_task_lock:
        task_unlock(task);
        put_task_struct(task);
out:
        return err < 0 ? err : count;
}

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

static ssize_t oom_score_adj_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];
        int oom_score_adj = OOM_SCORE_ADJ_MIN;
        unsigned long flags;
        size_t len;

        if (!task)
                return -ESRCH;
        if (lock_task_sighand(task, &flags)) {
                oom_score_adj = task->signal->oom_score_adj;
                unlock_task_sighand(task, &flags);
        }
        put_task_struct(task);
        len = snprintf(buffer, sizeof(buffer), "%d\n", oom_score_adj);
        return simple_read_from_buffer(buf, count, ppos, buffer, len);
}

static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
                                        size_t count, loff_t *ppos)
{
        struct task_struct *task;
        char buffer[PROC_NUMBUF];
        unsigned long flags;
        int oom_score_adj;
        int err;

        memset(buffer, 0, sizeof(buffer));
        if (count > sizeof(buffer) - 1)
                count = sizeof(buffer) - 1;
        if (copy_from_user(buffer, buf, count)) {
                err = -EFAULT;
                goto out;
        }

        err = kstrtoint(strstrip(buffer), 0, &oom_score_adj);
        if (err)
                goto out;
        if (oom_score_adj < OOM_SCORE_ADJ_MIN ||
                        oom_score_adj > OOM_SCORE_ADJ_MAX) {
                err = -EINVAL;
                goto out;
        }

        task = get_proc_task(file->f_path.dentry->d_inode);
        if (!task) {
                err = -ESRCH;
                goto out;
        }

        task_lock(task);
        if (!task->mm) {
                err = -EINVAL;
                goto err_task_lock;
        }

        if (!lock_task_sighand(task, &flags)) {
                err = -ESRCH;
                goto err_task_lock;
        }

        if (oom_score_adj < task->signal->oom_score_adj_min &&
                        !capable(CAP_SYS_RESOURCE)) {
                err = -EACCES;
                goto err_sighand;
        }

        task->signal->oom_score_adj = oom_score_adj;
        if (has_capability_noaudit(current, CAP_SYS_RESOURCE))
                task->signal->oom_score_adj_min = oom_score_adj;
        /*
         * Scale /proc/pid/oom_adj appropriately ensuring that OOM_DISABLE is
         * always attainable.
         */
        if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
                task->signal->oom_adj = OOM_DISABLE;
        else
                task->signal->oom_adj = (oom_score_adj * OOM_ADJUST_MAX) /
                                                        OOM_SCORE_ADJ_MAX;
err_sighand:
        unlock_task_sighand(task, &flags);
err_task_lock:
        task_unlock(task);
        put_task_struct(task);
out:
        return err < 0 ? err : count;
}

static const struct file_operations proc_oom_score_adj_operations = {
        .read           = oom_score_adj_read,
        .write          = oom_score_adj_write,
        .llseek         = default_llseek,
};

#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;

        rcu_read_lock();
        if (current != pid_task(proc_pid(inode), PIDTYPE_PID)) {
                rcu_read_unlock();
                return -EPERM;
        }
        rcu_read_unlock();

        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,
        .llseek         = generic_file_llseek,
};

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,
        .llseek         = generic_file_llseek,
};
#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(strstrip(buffer), &end, 0);
        if (*end)
                return -EINVAL;
        task = get_proc_task(file->f_dentry->d_inode);
        if (!task)
                return -ESRCH;
        task->make_it_fail = make_it_fail;
        put_task_struct(task);

        return count;
}

static const struct file_operations proc_fault_inject_operations = {
        .read           = proc_fault_inject_read,
        .write          = proc_fault_inject_write,
        .llseek         = generic_file_llseek,
};
#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)
{
        return single_open(filp, sched_show, inode);
}

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

#ifdef CONFIG_SCHED_AUTOGROUP
/*
 * Print out autogroup related information:
 */
static int sched_autogroup_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_autogroup_show_task(p, m);

        put_task_struct(p);

        return 0;
}

static ssize_t
sched_autogroup_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;
        char buffer[PROC_NUMBUF];
        int nice;
        int err;

        memset(buffer, 0, sizeof(buffer));
        if (count > sizeof(buffer) - 1)
                count = sizeof(buffer) - 1;
        if (copy_from_user(buffer, buf, count))
                return -EFAULT;

        err = kstrtoint(strstrip(buffer), 0, &nice);
        if (err < 0)
                return err;

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

        err = nice;
        err = proc_sched_autogroup_set_nice(p, &err);
        if (err)
                count = err;

        put_task_struct(p);

        return count;
}

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

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

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

static const struct file_operations proc_pid_sched_autogroup_operations = {
        .open           = sched_autogroup_open,
        .read           = seq_read,
        .write          = sched_autogroup_write,
        .llseek         = seq_lseek,
        .release        = single_release,
};

#endif /* CONFIG_SCHED_AUTOGROUP */

static ssize_t comm_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;
        char buffer[TASK_COMM_LEN];

        memset(buffer, 0, sizeof(buffer));
        if (count > sizeof(buffer) - 1)
                count = sizeof(buffer) - 1;
        if (copy_from_user(buffer, buf, count))
                return -EFAULT;

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

        if (same_thread_group(current, p))
                set_task_comm(p, buffer);
        else
                count = -EINVAL;

        put_task_struct(p);

        return count;
}

static int comm_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;

        task_lock(p);
        seq_printf(m, "%s\n", p->comm);
        task_unlock(p);

        put_task_struct(p);

        return 0;
}

static int comm_open(struct inode *inode, struct file *filp)
{
        return single_open(filp, comm_show, inode);
}

static const struct file_operations proc_pid_set_comm_operations = {
        .open           = comm_open,
        .read           = seq_read,
        .write          = comm_write,
        .llseek         = seq_lseek,
        .release        = single_release,
};

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);
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;
}

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_ino = get_next_ino();
        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;
}

int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
{
        struct inode *inode = dentry->d_inode;
        struct task_struct *task;
        const struct cred *cred;

        generic_fillattr(inode, stat);

        rcu_read_lock();
        stat->uid = 0;
        stat->gid = 0;
        task = pid_task(proc_pid(inode), PIDTYPE_PID);
        if (task) {
                if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) ||
                    task_dumpable(task)) {
                        cred = __task_cred(task);
                        stat->uid = cred->euid;
                        stat->gid = cred->egid;
                }
        }
        rcu_read_unlock();
        return 0;
}

/* dentry stuff */

/*
 *      Exceptional case: normally we are not allowed to unhash a busy
 * directory. In this case, however, we can do it - no aliasing problems
 * due to the way we treat inodes.
 *
 * Rewrite the inode's ownerships here because the owning task may have
 * performed a setuid(), etc.
 *
 * Before the /proc/pid/status file was created the only way to read
 * the effective uid of a /process was to stat /proc/pid.  Reading
 * /proc/pid/status is slow enough that procps and other packages
 * kept stating /proc/pid.  To keep the rules in /proc simple I have
 * made this apply to all per process world readable and executable
 * directories.
 */
int pid_revalidate(struct dentry *dentry, struct nameidata *nd)
{
        struct inode *inode;
        struct task_struct *task;
        const struct cred *cred;

        if (nd && nd->flags & LOOKUP_RCU)
                return -ECHILD;

        inode = dentry->d_inode;
        task = get_proc_task(inode);

        if (task) {
                if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) ||
                    task_dumpable(task)) {
                        rcu_read_lock();
                        cred = __task_cred(task);
                        inode->i_uid = cred->euid;
                        inode->i_gid = cred->egid;
                        rcu_read_unlock();
                } else {
                        inode->i_uid = 0;
                        inode->i_gid = 0;
                }
                inode->i_mode &= ~(S_ISUID | S_ISGID);
                security_task_to_inode(task, inode);
                put_task_struct(task);
                return 1;
        }
        d_drop(dentry);
        return 0;
}

static int pid_delete_dentry(const struct dentry * dentry)
{
        /* Is the task we represent dead?
         * If so, then don't put the dentry on the lru list,
         * kill it immediately.
         */
        return !proc_pid(dentry->d_inode)->tasks[PIDTYPE_PID].first;
}

const struct dentry_operations pid_dentry_operations =
{
        .d_revalidate   = pid_revalidate,
        .d_delete       = pid_delete_dentry,
};

/* Lookups */

/*
 * Fill a directory entry.
 *
 * If possible create the dcache entry and derive our inode number and
 * file type from dcache entry.
 *
 * Since all of the proc inode numbers are dynamically generated, the inode
 * numbers do not exist until the inode is cache.  This means creating the
 * the dcache entry in readdir is necessary to keep the inode numbers
 * reported by readdir in sync with the inode numbers reported
 * by stat.
 */
int proc_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
        const char *name, int len,
        instantiate_t instantiate, struct task_struct *task, const void *ptr)
{
        struct dentry *child, *dir = filp->f_path.dentry;
        struct inode *inode;
        struct qstr qname;
        ino_t ino = 0;
        unsigned type = DT_UNKNOWN;

        qname.name = name;
        qname.len  = len;
        qname.hash = full_name_hash(name, len);

        child = d_lookup(dir, &qname);
        if (!child) {
                struct dentry *new;
                new = d_alloc(dir, &qname);
                if (new) {
                        child = instantiate(dir->d_inode, new, task, ptr);
                        if (child)
                                dput(new);
                        else
                                child = new;
                }
        }
        if (!child || IS_ERR(child) || !child->d_inode)
                goto end_instantiate;
        inode = child->d_inode;
        if (inode) {
                ino = inode->i_ino;
                type = inode->i_mode >> 12;
        }
        dput(child);
end_instantiate:
        if (!ino)
                ino = find_inode_number(dir, &qname);
        if (!ino)
                ino = 1;
        return filldir(dirent, name, len, filp->f_pos, ino, type);
}

static unsigned name_to_int(struct dentry *dentry)
{
        const char *name = dentry->d_name.name;
        int len = dentry->d_name.len;
        unsigned n = 0;

        if (len > 1 && *name == '0')
                goto out;
        while (len-- > 0) {
                unsigned c = *name++ - '0';
                if (c > 9)
                        goto out;
                if (n >= (~0U-9)/10)
                        goto out;
                n *= 10;
                n += c;
        }
        return n;
out:
        return ~0U;
}

#define PROC_FDINFO_MAX 64

static int proc_fd_info(struct inode *inode, struct path *path, char *info)
{
        struct task_struct *task = get_proc_task(inode);
        struct files_struct *files = NULL;
        struct file *file;
        int fd = proc_fd(inode);

        if (task) {
                files = get_files_struct(task);
                put_task_struct(task);
        }
        if (files) {
                /*
                 * We are not taking a ref to the file structure, so we must
                 * hold ->file_lock.
                 */
                spin_lock(&files->file_lock);
                file = fcheck_files(files, fd);
                if (file) {
                        unsigned int f_flags;
                        struct fdtable *fdt;

                        fdt = files_fdtable(files);
                        f_flags = file->f_flags & ~O_CLOEXEC;
                        if (FD_ISSET(fd, fdt->close_on_exec))
                                f_flags |= O_CLOEXEC;

                        if (path) {
                                *path = file->f_path;
                                path_get(&file->f_path);
                        }
                        if (info)
                                snprintf(info, PROC_FDINFO_MAX,
                                         "pos:\t%lli\n"
                                         "flags:\t0%o\n",
                                         (long long) file->f_pos,
                                         f_flags);
                        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_fd_link(struct inode *inode, struct path *path)
{
        return proc_fd_info(inode, path, NULL);
}

static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd)
{
        struct inode *inode;
        struct task_struct *task;
        int fd;
        struct files_struct *files;
        const struct cred *cred;

        if (nd && nd->flags & LOOKUP_RCU)
                return -ECHILD;

        inode = dentry->d_inode;
        task = get_proc_task(inode);
        fd = proc_fd(inode);

        if (task) {
                files = get_files_struct(task);
                if (files) {
                        rcu_read_lock();
                        if (fcheck_files(files, fd)) {
                                rcu_read_unlock();
                                put_files_struct(files);
                                if (task_dumpable(task)) {
                                        rcu_read_lock();
                                        cred = __task_cred(task);
                                        inode->i_uid = cred->euid;
                                        inode->i_gid = cred->egid;
                                        rcu_read_unlock();
                                } else {
                                        inode->i_uid = 0;
                                        inode->i_gid = 0;
                                }
                                inode->i_mode &= ~(S_ISUID | S_ISGID);
                                security_task_to_inode(task, inode);
                                put_task_struct(task);
                                return 1;
                        }
                        rcu_read_unlock();
                        put_files_struct(files);
                }
                put_task_struct(task);
        }
        d_drop(dentry);
        return 0;
}

static const struct dentry_operations tid_fd_dentry_operations =
{
        .d_revalidate   = tid_fd_revalidate,
        .d_delete       = pid_delete_dentry,
};

static struct dentry *proc_fd_instantiate(struct inode *dir,
        struct dentry *dentry, struct task_struct *task, const void *ptr)
{
        unsigned fd = *(const unsigned *)ptr;
        struct file *file;
        struct files_struct *files;
        struct inode *inode;
        struct proc_inode *ei;
        struct dentry *error = ERR_PTR(-ENOENT);

        inode = proc_pid_make_inode(dir->i_sb, task);
        if (!inode)
                goto out;
        ei = PROC_I(inode);
        ei->fd = fd;
        files = get_files_struct(task);
        if (!files)
                goto out_iput;
        inode->i_mode = S_IFLNK;

        /*
         * We are not taking a ref to the file structure, so we must
         * hold ->file_lock.
         */
        spin_lock(&files->file_lock);
        file = fcheck_files(files, fd);
        if (!file)
                goto out_unlock;
        if (file->f_mode & FMODE_READ)
                inode->i_mode |= S_IRUSR | S_IXUSR;
        if (file->f_mode & FMODE_WRITE)
                inode->i_mode |= S_IWUSR | S_IXUSR;
        spin_unlock(&files->file_lock);
        put_files_struct(files);

        inode->i_op = &proc_pid_link_inode_operations;
        inode->i_size = 64;
        ei->op.proc_get_link = proc_fd_link;
        d_set_d_op(dentry, &tid_fd_dentry_operations);
        d_add(dentry, inode);
        /* Close the race of the process dying before we return the dentry */
        if (tid_fd_revalidate(dentry, NULL))
                error = NULL;

 out:
        return error;
out_unlock:
        spin_unlock(&files->file_lock);
        put_files_struct(files);
out_iput:
        iput(inode);
        goto out;
}

static struct dentry *proc_lookupfd_common(struct inode *dir,
                                           struct dentry *dentry,
                                           instantiate_t instantiate)
{
        struct task_struct *task = get_proc_task(dir);
        unsigned fd = name_to_int(dentry);
        struct dentry *result = ERR_PTR(-ENOENT);

        if (!task)
                goto out_no_task;
        if (fd == ~0U)
                goto out;

        result = instantiate(dir, dentry, task, &fd);
out:
        put_task_struct(task);
out_no_task:
        return result;
}

static int proc_readfd_common(struct file * filp, void * dirent,
                              filldir_t filldir, instantiate_t instantiate)
{
        struct dentry *dentry = filp->f_path.dentry;
        struct inode *inode = dentry->d_inode;
        struct task_struct *p = get_proc_task(inode);
        unsigned int fd, ino;
        int retval;
        struct files_struct * files;

        retval = -ENOENT;
        if (!p)
                goto out_no_task;
        retval = 0;