blob: 9c8ca6cd3ce42d19809f3104482ac01cee2b5ce1 [file] [log] [blame]
// SPDX-License-Identifier: GPL-2.0
/*
* 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 <linux/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/generic-radix-tree.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/printk.h>
#include <linux/cache.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/user_namespace.h>
#include <linux/fs_struct.h>
#include <linux/slab.h>
#include <linux/sched/autogroup.h>
#include <linux/sched/mm.h>
#include <linux/sched/coredump.h>
#include <linux/sched/debug.h>
#include <linux/sched/stat.h>
#include <linux/posix-timers.h>
#include <trace/events/oom.h>
#include "internal.h"
#include "fd.h"
#include "../../lib/kstrtox.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.
*/
static u8 nlink_tid __ro_after_init;
static u8 nlink_tgid __ro_after_init;
struct pid_entry {
const char *name;
unsigned int len;
umode_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 ONE(NAME, MODE, show) \
NOD(NAME, (S_IFREG|(MODE)), \
NULL, &proc_single_file_operations, \
{ .proc_show = show } )
#define ATTR(LSM, NAME, MODE) \
NOD(NAME, (S_IFREG|(MODE)), \
NULL, &proc_pid_attr_operations, \
{ .lsm = LSM })
/*
* Count the number of hardlinks for the pid_entry table, excluding the .
* and .. links.
*/
static unsigned int __init pid_entry_nlink(const struct pid_entry *entries,
unsigned int n)
{
unsigned int i;
unsigned int count;
count = 2;
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 dentry *dentry, struct path *path)
{
struct task_struct *task = get_proc_task(d_inode(dentry));
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 dentry *dentry, struct path *path)
{
struct task_struct *task = get_proc_task(d_inode(dentry));
int result = -ENOENT;
if (task) {
result = get_task_root(task, path);
put_task_struct(task);
}
return result;
}
static ssize_t get_mm_cmdline(struct mm_struct *mm, char __user *buf,
size_t count, loff_t *ppos)
{
unsigned long arg_start, arg_end, env_start, env_end;
unsigned long pos, len;
char *page;
/* Check if process spawned far enough to have cmdline. */
if (!mm->env_end)
return 0;
spin_lock(&mm->arg_lock);
arg_start = mm->arg_start;
arg_end = mm->arg_end;
env_start = mm->env_start;
env_end = mm->env_end;
spin_unlock(&mm->arg_lock);
if (arg_start >= arg_end)
return 0;
/*
* We have traditionally allowed the user to re-write
* the argument strings and overflow the end result
* into the environment section. But only do that if
* the environment area is contiguous to the arguments.
*/
if (env_start != arg_end || env_start >= env_end)
env_start = env_end = arg_end;
/* .. and limit it to a maximum of one page of slop */
if (env_end >= arg_end + PAGE_SIZE)
env_end = arg_end + PAGE_SIZE - 1;
/* We're not going to care if "*ppos" has high bits set */
pos = arg_start + *ppos;
/* .. but we do check the result is in the proper range */
if (pos < arg_start || pos >= env_end)
return 0;
/* .. and we never go past env_end */
if (env_end - pos < count)
count = env_end - pos;
page = (char *)__get_free_page(GFP_KERNEL);
if (!page)
return -ENOMEM;
len = 0;
while (count) {
int got;
size_t size = min_t(size_t, PAGE_SIZE, count);
long offset;
/*
* Are we already starting past the official end?
* We always include the last byte that is *supposed*
* to be NUL
*/
offset = (pos >= arg_end) ? pos - arg_end + 1 : 0;
got = access_remote_vm(mm, pos - offset, page, size + offset, FOLL_ANON);
if (got <= offset)
break;
got -= offset;
/* Don't walk past a NUL character once you hit arg_end */
if (pos + got >= arg_end) {
int n = 0;
/*
* If we started before 'arg_end' but ended up
* at or after it, we start the NUL character
* check at arg_end-1 (where we expect the normal
* EOF to be).
*
* NOTE! This is smaller than 'got', because
* pos + got >= arg_end
*/
if (pos < arg_end)
n = arg_end - pos - 1;
/* Cut off at first NUL after 'n' */
got = n + strnlen(page+n, offset+got-n);
if (got < offset)
break;
got -= offset;
/* Include the NUL if it existed */
if (got < size)
got++;
}
got -= copy_to_user(buf, page+offset, got);
if (unlikely(!got)) {
if (!len)
len = -EFAULT;
break;
}
pos += got;
buf += got;
len += got;
count -= got;
}
free_page((unsigned long)page);
return len;
}
static ssize_t get_task_cmdline(struct task_struct *tsk, char __user *buf,
size_t count, loff_t *pos)
{
struct mm_struct *mm;
ssize_t ret;
mm = get_task_mm(tsk);
if (!mm)
return 0;
ret = get_mm_cmdline(mm, buf, count, pos);
mmput(mm);
return ret;
}
static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
size_t count, loff_t *pos)
{
struct task_struct *tsk;
ssize_t ret;
BUG_ON(*pos < 0);
tsk = get_proc_task(file_inode(file));
if (!tsk)
return -ESRCH;
ret = get_task_cmdline(tsk, buf, count, pos);
put_task_struct(tsk);
if (ret > 0)
*pos += ret;
return ret;
}
static const struct file_operations proc_pid_cmdline_ops = {
.read = proc_pid_cmdline_read,
.llseek = generic_file_llseek,
};
#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 seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
unsigned long wchan;
char symname[KSYM_NAME_LEN];
if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
goto print0;
wchan = get_wchan(task);
if (wchan && !lookup_symbol_name(wchan, symname)) {
seq_puts(m, symname);
return 0;
}
print0:
seq_putc(m, '0');
return 0;
}
#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_FSCREDS)) {
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)
{
unsigned long *entries;
int err;
/*
* The ability to racily run the kernel stack unwinder on a running task
* and then observe the unwinder output is scary; while it is useful for
* debugging kernel issues, it can also allow an attacker to leak kernel
* stack contents.
* Doing this in a manner that is at least safe from races would require
* some work to ensure that the remote task can not be scheduled; and
* even then, this would still expose the unwinder as local attack
* surface.
* Therefore, this interface is restricted to root.
*/
if (!file_ns_capable(m->file, &init_user_ns, CAP_SYS_ADMIN))
return -EACCES;
entries = kmalloc_array(MAX_STACK_TRACE_DEPTH, sizeof(*entries),
GFP_KERNEL);
if (!entries)
return -ENOMEM;
err = lock_trace(task);
if (!err) {
unsigned int i, nr_entries;
nr_entries = stack_trace_save_tsk(task, entries,
MAX_STACK_TRACE_DEPTH, 0);
for (i = 0; i < nr_entries; i++) {
seq_printf(m, "[<0>] %pB\n", (void *)entries[i]);
}
unlock_trace(task);
}
kfree(entries);
return err;
}
#endif
#ifdef CONFIG_SCHED_INFO
/*
* Provides /proc/PID/schedstat
*/
static int proc_pid_schedstat(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
if (unlikely(!sched_info_on()))
seq_puts(m, "0 0 0\n");
else
seq_printf(m, "%llu %llu %lu\n",
(unsigned long long)task->se.sum_exec_runtime,
(unsigned long long)task->sched_info.run_delay,
task->sched_info.pcount);
return 0;
}
#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 < LT_SAVECOUNT; 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;
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_inode(file));
if (!task)
return -ESRCH;
clear_tsk_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 seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
unsigned long totalpages = totalram_pages() + total_swap_pages;
unsigned long points = 0;
points = oom_badness(task, NULL, NULL, totalpages) *
1000 / totalpages;
seq_printf(m, "%lu\n", points);
return 0;
}
struct limit_names {
const char *name;
const 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 seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
unsigned int i;
unsigned long flags;
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
*/
seq_puts(m, "Limit "
"Soft Limit "
"Hard Limit "
"Units \n");
for (i = 0; i < RLIM_NLIMITS; i++) {
if (rlim[i].rlim_cur == RLIM_INFINITY)
seq_printf(m, "%-25s %-20s ",
lnames[i].name, "unlimited");
else
seq_printf(m, "%-25s %-20lu ",
lnames[i].name, rlim[i].rlim_cur);
if (rlim[i].rlim_max == RLIM_INFINITY)
seq_printf(m, "%-20s ", "unlimited");
else
seq_printf(m, "%-20lu ", rlim[i].rlim_max);
if (lnames[i].unit)
seq_printf(m, "%-10s\n", lnames[i].unit);
else
seq_putc(m, '\n');
}
return 0;
}
#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
static int proc_pid_syscall(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
struct syscall_info info;
u64 *args = &info.data.args[0];
int res;
res = lock_trace(task);
if (res)
return res;
if (task_current_syscall(task, &info))
seq_puts(m, "running\n");
else if (info.data.nr < 0)
seq_printf(m, "%d 0x%llx 0x%llx\n",
info.data.nr, info.sp, info.data.instruction_pointer);
else
seq_printf(m,
"%d 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx\n",
info.data.nr,
args[0], args[1], args[2], args[3], args[4], args[5],
info.sp, info.data.instruction_pointer);
unlock_trace(task);
return 0;
}
#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_FSCREDS);
put_task_struct(task);
}
return allowed;
}
int proc_setattr(struct dentry *dentry, struct iattr *attr)
{
int error;
struct inode *inode = d_inode(dentry);
if (attr->ia_valid & ATTR_MODE)
return -EPERM;
error = setattr_prepare(dentry, attr);
if (error)
return error;
setattr_copy(inode, attr);
mark_inode_dirty(inode);
return 0;
}
/*
* May current process learn task's sched/cmdline info (for hide_pid_min=1)
* or euid/egid (for hide_pid_min=2)?
*/
static bool has_pid_permissions(struct pid_namespace *pid,
struct task_struct *task,
int hide_pid_min)
{
if (pid->hide_pid < hide_pid_min)
return true;
if (in_group_p(pid->pid_gid))
return true;
return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
}
static int proc_pid_permission(struct inode *inode, int mask)
{
struct pid_namespace *pid = proc_pid_ns(inode);
struct task_struct *task;
bool has_perms;
task = get_proc_task(inode);
if (!task)
return -ESRCH;
has_perms = has_pid_permissions(pid, task, HIDEPID_NO_ACCESS);
put_task_struct(task);
if (!has_perms) {
if (pid->hide_pid == HIDEPID_INVISIBLE) {
/*
* Let's make getdents(), stat(), and open()
* consistent with each other. If a process
* may not stat() a file, it shouldn't be seen
* in procfs at all.
*/
return -ENOENT;
}
return -EPERM;
}
return generic_permission(inode, mask);
}
static const struct inode_operations proc_def_inode_operations = {
.setattr = proc_setattr,
};
static int proc_single_show(struct seq_file *m, void *v)
{
struct inode *inode = m->private;
struct pid_namespace *ns = proc_pid_ns(inode);
struct pid *pid = proc_pid(inode);
struct task_struct *task;
int ret;
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,
};
struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode)
{
struct task_struct *task = get_proc_task(inode);
struct mm_struct *mm = ERR_PTR(-ESRCH);
if (task) {
mm = mm_access(task, mode | PTRACE_MODE_FSCREDS);
put_task_struct(task);
if (!IS_ERR_OR_NULL(mm)) {
/* ensure this mm_struct can't be freed */
mmgrab(mm);
/* but do not pin its memory */
mmput(mm);
}
}
return mm;
}
static int __mem_open(struct inode *inode, struct file *file, unsigned int mode)
{
struct mm_struct *mm = proc_mem_open(inode, mode);
if (IS_ERR(mm))
return PTR_ERR(mm);
file->private_data = mm;
return 0;
}
static int mem_open(struct inode *inode, struct file *file)
{
int ret = __mem_open(inode, file, PTRACE_MODE_ATTACH);
/* OK to pass negative loff_t, we can catch out-of-range */
file->f_mode |= FMODE_UNSIGNED_OFFSET;
return ret;
}
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;
unsigned int flags;
if (!mm)
return 0;
page = (char *)__get_free_page(GFP_KERNEL);
if (!page)
return -ENOMEM;
copied = 0;
if (!mmget_not_zero(mm))
goto free;
flags = FOLL_FORCE | (write ? FOLL_WRITE : 0);
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, flags);
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 int environ_open(struct inode *inode, struct file *file)
{
return __mem_open(inode, file, PTRACE_MODE_READ);
}
static ssize_t environ_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
char *page;
unsigned long src = *ppos;
int ret = 0;
struct mm_struct *mm = file->private_data;
unsigned long env_start, env_end;
/* Ensure the process spawned far enough to have an environment. */
if (!mm || !mm->env_end)
return 0;
page = (char *)__get_free_page(GFP_KERNEL);
if (!page)
return -ENOMEM;
ret = 0;
if (!mmget_not_zero(mm))
goto free;
spin_lock(&mm->arg_lock);
env_start = mm->env_start;
env_end = mm->env_end;
spin_unlock(&mm->arg_lock);
while (count > 0) {
size_t this_len, max_len;
int retval;
if (src >= (env_end - env_start))
break;
this_len = env_end - (env_start + src);
max_len = min_t(size_t, PAGE_SIZE, count);
this_len = min(max_len, this_len);
retval = access_remote_vm(mm, (env_start + src), page, this_len, FOLL_ANON);
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);
free:
free_page((unsigned long) page);
return ret;
}
static const struct file_operations proc_environ_operations = {
.open = environ_open,
.read = environ_read,
.llseek = generic_file_llseek,
.release = mem_release,
};
static int auxv_open(struct inode *inode, struct file *file)
{
return __mem_open(inode, file, PTRACE_MODE_READ_FSCREDS);
}
static ssize_t auxv_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
struct mm_struct *mm = file->private_data;
unsigned int nwords = 0;
if (!mm)
return 0;
do {
nwords += 2;
} while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */
return simple_read_from_buffer(buf, count, ppos, mm->saved_auxv,
nwords * sizeof(mm->saved_auxv[0]));
}
static const struct file_operations proc_auxv_operations = {
.open = auxv_open,
.read = auxv_read,
.llseek = generic_file_llseek,
.release = mem_release,
};
static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count,
loff_t *ppos)
{
struct task_struct *task = get_proc_task(file_inode(file));
char buffer[PROC_NUMBUF];
int oom_adj = OOM_ADJUST_MIN;
size_t len;
if (!task)
return -ESRCH;
if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MAX)
oom_adj = OOM_ADJUST_MAX;
else
oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) /
OOM_SCORE_ADJ_MAX;
put_task_struct(task);
len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj);
return simple_read_from_buffer(buf, count, ppos, buffer, len);
}
static int __set_oom_adj(struct file *file, int oom_adj, bool legacy)
{
static DEFINE_MUTEX(oom_adj_mutex);
struct mm_struct *mm = NULL;
struct task_struct *task;
int err = 0;
task = get_proc_task(file_inode(file));
if (!task)
return -ESRCH;
mutex_lock(&oom_adj_mutex);
if (legacy) {
if (oom_adj < task->signal->oom_score_adj &&
!capable(CAP_SYS_RESOURCE)) {
err = -EACCES;
goto err_unlock;
}
/*
* /proc/pid/oom_adj is provided for legacy purposes, ask users to use
* /proc/pid/oom_score_adj instead.
*/
pr_warn_once("%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));
} else {
if ((short)oom_adj < task->signal->oom_score_adj_min &&
!capable(CAP_SYS_RESOURCE)) {
err = -EACCES;
goto err_unlock;
}
}
/*
* Make sure we will check other processes sharing the mm if this is
* not vfrok which wants its own oom_score_adj.
* pin the mm so it doesn't go away and get reused after task_unlock
*/
if (!task->vfork_done) {
struct task_struct *p = find_lock_task_mm(task);
if (p) {
if (atomic_read(&p->mm->mm_users) > 1) {
mm = p->mm;
mmgrab(mm);
}
task_unlock(p);
}
}
task->signal->oom_score_adj = oom_adj;
if (!legacy && has_capability_noaudit(current, CAP_SYS_RESOURCE))
task->signal->oom_score_adj_min = (short)oom_adj;
trace_oom_score_adj_update(task);
if (mm) {
struct task_struct *p;
rcu_read_lock();
for_each_process(p) {
if (same_thread_group(task, p))
continue;
/* do not touch kernel threads or the global init */
if (p->flags & PF_KTHREAD || is_global_init(p))
continue;
task_lock(p);
if (!p->vfork_done && process_shares_mm(p, mm)) {
p->signal->oom_score_adj = oom_adj;
if (!legacy && has_capability_noaudit(current, CAP_SYS_RESOURCE))
p->signal->oom_score_adj_min = (short)oom_adj;
}
task_unlock(p);
}
rcu_read_unlock();
mmdrop(mm);
}
err_unlock:
mutex_unlock(&oom_adj_mutex);
put_task_struct(task);
return err;
}
/*
* /proc/pid/oom_adj exists solely for backwards compatibility with previous
* kernels. The effective policy is defined by oom_score_adj, which has a
* different scale: oom_adj grew exponentially and oom_score_adj grows linearly.
* Values written to oom_adj are simply mapped linearly to oom_score_adj.
* Processes that become oom disabled via oom_adj will still be oom disabled
* with this implementation.
*
* oom_adj cannot be removed since existing userspace binaries use it.
*/
static ssize_t oom_adj_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
char buffer[PROC_NUMBUF];
int oom_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_adj);
if (err)
goto out;
if ((oom_adj < OOM_ADJUST_MIN || oom_adj > OOM_ADJUST_MAX) &&
oom_adj != OOM_DISABLE) {
err = -EINVAL;
goto out;
}
/*
* Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum
* value is always attainable.
*/
if (oom_adj == OOM_ADJUST_MAX)
oom_adj = OOM_SCORE_ADJ_MAX;
else
oom_adj = (oom_adj * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE;
err = __set_oom_adj(file, oom_adj, true);
out:
return err < 0 ? err : count;
}
static const struct file_operations proc_oom_adj_operations = {
.read = oom_adj_read,
.write = oom_adj_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_inode(file));
char buffer[PROC_NUMBUF];
short oom_score_adj = OOM_SCORE_ADJ_MIN;
size_t len;
if (!task)
return -ESRCH;
oom_score_adj = task->signal->oom_score_adj;
put_task_struct(task);
len = snprintf(buffer, sizeof(buffer), "%hd\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)
{
char buffer[PROC_NUMBUF];
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;
}
err = __set_oom_adj(file, oom_score_adj, false);
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_AUDIT
#define TMPBUFLEN 11
static ssize_t proc_loginuid_read(struct file * file, char __user * buf,
size_t count, loff_t *ppos)
{
struct inode * inode = file_inode(file);
struct task_struct *task = get_proc_task(inode);
ssize_t length;
char tmpbuf[TMPBUFLEN];
if (!task)
return -ESRCH;
length = scnprintf(tmpbuf, TMPBUFLEN, "%u",
from_kuid(file->f_cred->user_ns,
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_inode(file);
uid_t loginuid;
kuid_t kloginuid;
int rv;
rcu_read_lock();
if (current != pid_task(proc_pid(inode), PIDTYPE_PID)) {
rcu_read_unlock();
return -EPERM;
}
rcu_read_unlock();
if (*ppos != 0) {
/* No partial writes. */
return -EINVAL;
}
rv = kstrtou32_from_user(buf, count, 10, &loginuid);
if (rv < 0)
return rv;
/* is userspace tring to explicitly UNSET the loginuid? */
if (loginuid == AUDIT_UID_UNSET) {
kloginuid = INVALID_UID;
} else {
kloginuid = make_kuid(file->f_cred->user_ns, loginuid);
if (!uid_valid(kloginuid))
return -EINVAL;
}
rv = audit_set_loginuid(kloginuid);
if (rv < 0)
return rv;
return count;
}
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_inode(file);
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_inode(file));
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];
int make_it_fail;
int rv;
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;
rv = kstrtoint(strstrip(buffer), 0, &make_it_fail);
if (rv < 0)
return rv;
if (make_it_fail < 0 || make_it_fail > 1)
return -EINVAL;
task = get_proc_task(file_inode(file));
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,
};
static ssize_t proc_fail_nth_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
struct task_struct *task;
int err;
unsigned int n;
err = kstrtouint_from_user(buf, count, 0, &n);
if (err)
return err;
task = get_proc_task(file_inode(file));
if (!task)
return -ESRCH;
task->fail_nth = n;
put_task_struct(task);
return count;
}
static ssize_t proc_fail_nth_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
struct task_struct *task;
char numbuf[PROC_NUMBUF];
ssize_t len;
task = get_proc_task(file_inode(file));
if (!task)
return -ESRCH;
len = snprintf(numbuf, sizeof(numbuf), "%u\n", task->fail_nth);
put_task_struct(task);
return simple_read_from_buffer(buf, count, ppos, numbuf, len);
}
static const struct file_operations proc_fail_nth_operations = {
.read = proc_fail_nth_read,
.write = proc_fail_nth_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 pid_namespace *ns = proc_pid_ns(inode);
struct task_struct *p;
p = get_proc_task(inode);
if (!p)
return -ESRCH;
proc_sched_show_task(p, ns, 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_inode(file);
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_inode(file);
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 = proc_sched_autogroup_set_nice(p, nice);
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_inode(file);
struct task_struct *p;
char buffer[TASK_COMM_LEN];
const size_t maxlen = sizeof(buffer) - 1;
memset(buffer, 0, sizeof(buffer));
if (copy_from_user(buffer, buf, count > maxlen ? maxlen : 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;
proc_task_name(m, p, false);
seq_putc(m, '\n');
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 dentry *dentry, struct path *exe_path)
{
struct task_struct *task;
struct file *exe_file;
task = get_proc_task(d_inode(dentry));
if (!task)
return -ENOENT;
exe_file = get_task_exe_file(task);
put_task_struct(task);
if (exe_file) {
*exe_path = exe_file->f_path;
path_get(&exe_file->f_path);
fput(exe_file);
return 0;
} else
return -ENOENT;
}
static const char *proc_pid_get_link(struct dentry *dentry,
struct inode *inode,
struct delayed_call *done)
{
struct path path;
int error = -EACCES;
if (!dentry)
return ERR_PTR(-ECHILD);
/* 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(dentry, &path);
if (error)
goto out;
nd_jump_link(&path);
return NULL;
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_KERNEL);
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 = d_inode(dentry);
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(dentry, &path);
if (error)
goto out;
error = do_proc_readlink(&path, buffer, buflen);
path_put(&path);
out:
return error;
}
const struct inode_operations proc_pid_link_inode_operations = {
.readlink = proc_pid_readlink,
.get_link = proc_pid_get_link,
.setattr = proc_setattr,
};
/* building an inode */
void task_dump_owner(struct task_struct *task, umode_t mode,
kuid_t *ruid, kgid_t *rgid)
{
/* Depending on the state of dumpable compute who should own a
* proc file for a task.
*/
const struct cred *cred;
kuid_t uid;
kgid_t gid;
if (unlikely(task->flags & PF_KTHREAD)) {
*ruid = GLOBAL_ROOT_UID;
*rgid = GLOBAL_ROOT_GID;
return;
}
/* Default to the tasks effective ownership */
rcu_read_lock();
cred = __task_cred(task);
uid = cred->euid;
gid = cred->egid;
rcu_read_unlock();
/*
* 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.
*/
if (mode != (S_IFDIR|S_IRUGO|S_IXUGO)) {
struct mm_struct *mm;
task_lock(task);
mm = task->mm;
/* Make non-dumpable tasks owned by some root */
if (mm) {
if (get_dumpable(mm) != SUID_DUMP_USER) {
struct user_namespace *user_ns = mm->user_ns;
uid = make_kuid(user_ns, 0);
if (!uid_valid(uid))
uid = GLOBAL_ROOT_UID;
gid = make_kgid(user_ns, 0);
if (!gid_valid(gid))
gid = GLOBAL_ROOT_GID;
}
} else {
uid = GLOBAL_ROOT_UID;
gid = GLOBAL_ROOT_GID;
}
task_unlock(task);
}
*ruid = uid;
*rgid = gid;
}
struct inode *proc_pid_make_inode(struct super_block * sb,
struct task_struct *task, umode_t mode)
{
struct inode * inode;
struct proc_inode *ei;
/* We need a new inode */
inode = new_inode(sb);
if (!inode)
goto out;
/* Common stuff */
ei = PROC_I(inode);
inode->i_mode = mode;
inode->i_ino = get_next_ino();
inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
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;
task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid);
security_task_to_inode(task, inode);
out:
return inode;
out_unlock:
iput(inode);
return NULL;
}
int pid_getattr(const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
struct pid_namespace *pid = proc_pid_ns(inode);
struct task_struct *task;
generic_fillattr(inode, stat);
stat->uid = GLOBAL_ROOT_UID;
stat->gid = GLOBAL_ROOT_GID;
rcu_read_lock();
task = pid_task(proc_pid(inode), PIDTYPE_PID);
if (task) {
if (!has_pid_permissions(pid, task, HIDEPID_INVISIBLE)) {
rcu_read_unlock();
/*
* This doesn't prevent learning whether PID exists,
* it only makes getattr() consistent with readdir().
*/
return -ENOENT;
}
task_dump_owner(task, inode->i_mode, &stat->uid, &stat->gid);
}
rcu_read_unlock();
return 0;
}
/* dentry stuff */
/*
* Set <pid>/... inode ownership (can change due to setuid(), etc.)
*/
void pid_update_inode(struct task_struct *task, struct inode *inode)
{
task_dump_owner(task, inode->i_mode, &inode->i_uid, &inode->i_gid);
inode->i_mode &= ~(S_ISUID | S_ISGID);
security_task_to_inode(task, inode);
}
/*
* Rewrite the inode's ownerships here because the owning task may have
* performed a setuid(), etc.
*
*/
static int pid_revalidate(struct dentry *dentry, unsigned int flags)
{
struct inode *inode;
struct task_struct *task;
if (flags & LOOKUP_RCU)
return -ECHILD;
inode = d_inode(dentry);
task = get_proc_task(inode);
if (task) {
pid_update_inode(task, inode);
put_task_struct(task);
return 1;
}
return 0;
}
static inline bool proc_inode_is_dead(struct inode *inode)
{
return !proc_pid(inode)->tasks[PIDTYPE_PID].first;
}
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_inode_is_dead(d_inode(dentry));
}
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.
*/
bool proc_fill_cache(struct file *file, struct dir_context *ctx,
const char *name, unsigned int len,
instantiate_t instantiate, struct task_struct *task, const void *ptr)
{
struct dentry *child, *dir = file->f_path.dentry;
struct qstr qname = QSTR_INIT(name, len);
struct inode *inode;
unsigned type = DT_UNKNOWN;
ino_t ino = 1;
child = d_hash_and_lookup(dir, &qname);
if (!child) {
DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
child = d_alloc_parallel(dir, &qname, &wq);
if (IS_ERR(child))
goto end_instantiate;
if (d_in_lookup(child)) {
struct dentry *res;
res = instantiate(child, task, ptr);
d_lookup_done(child);
if (unlikely(res)) {
dput(child);
child = res;
if (IS_ERR(child))
goto end_instantiate;
}
}
}
inode = d_inode(child);
ino = inode->i_ino;
type = inode->i_mode >> 12;
dput(child);
end_instantiate:
return dir_emit(ctx, name, len, ino, type);
}
/*
* dname_to_vma_addr - maps a dentry name into two unsigned longs
* which represent vma start and end addresses.
*/
static int dname_to_vma_addr(struct dentry *dentry,
unsigned long *start, unsigned long *end)
{
const char *str = dentry->d_name.name;
unsigned long long sval, eval;
unsigned int len;
if (str[0] == '0' && str[1] != '-')
return -EINVAL;
len = _parse_integer(str, 16, &sval);
if (len & KSTRTOX_OVERFLOW)
return -EINVAL;
if (sval != (unsigned long)sval)
return -EINVAL;
str += len;
if (*str != '-')
return -EINVAL;
str++;
if (str[0] == '0' && str[1])
return -EINVAL;
len = _parse_integer(str, 16, &eval);
if (len & KSTRTOX_OVERFLOW)
return -EINVAL;
if (eval != (unsigned long)eval)
return -EINVAL;
str += len;
if (*str != '\0')
return -EINVAL;
*start = sval;
*end = eval;
return 0;
}
static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags)
{
unsigned long vm_start, vm_end;
bool exact_vma_exists = false;
struct mm_struct *mm = NULL;
struct task_struct *task;
struct inode *inode;
int status = 0;
if (flags & LOOKUP_RCU)
return -ECHILD;
inode = d_inode(dentry);
task = get_proc_task(inode);
if (!task)
goto out_notask;
mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
if (IS_ERR_OR_NULL(mm))
goto out;
if (!dname_to_vma_addr(dentry, &vm_start, &vm_end)) {
down_read(&mm->mmap_sem);
exact_vma_exists = !!find_exact_vma(mm, vm_start, vm_end);
up_read(&mm->mmap_sem);
}
mmput(mm);
if (exact_vma_exists) {
task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid);
security_task_to_inode(task, inode);
status = 1;
}
out:
put_task_struct(task);
out_notask:
return status;
}
static const struct dentry_operations tid_map_files_dentry_operations = {
.d_revalidate = map_files_d_revalidate,
.d_delete = pid_delete_dentry,
};
static int map_files_get_link(struct dentry *dentry, struct path *path)
{
unsigned long vm_start, vm_end;
struct vm_area_struct *vma;
struct task_struct *task;
struct mm_struct *mm;
int rc;
rc = -ENOENT;
task = get_proc_task(d_inode(dentry));
if (!task)
goto out;
mm = get_task_mm(task);
put_task_struct(task);
if (!mm)
goto out;
rc = dname_to_vma_addr(dentry, &vm_start, &vm_end);
if (rc)
goto out_mmput;
rc = -ENOENT;
down_read(&mm->mmap_sem);
vma = find_exact_vma(mm, vm_start, vm_end);
if (vma && vma->vm_file) {
*path = vma->vm_file->f_path;
path_get(path);
rc = 0;
}
up_read(&mm->mmap_sem);
out_mmput:
mmput(mm);
out:
return rc;
}
struct map_files_info {
unsigned long start;
unsigned long end;
fmode_t mode;
};
/*
* Only allow CAP_SYS_ADMIN to follow the links, due to concerns about how the
* symlinks may be used to bypass permissions on ancestor directories in the
* path to the file in question.
*/
static const char *
proc_map_files_get_link(struct dentry *dentry,
struct inode *inode,
struct delayed_call *done)
{
if (!capable(CAP_SYS_ADMIN))
return ERR_PTR(-EPERM);
return proc_pid_get_link(dentry, inode, done);
}
/*
* Identical to proc_pid_link_inode_operations except for get_link()
*/
static const struct inode_operations proc_map_files_link_inode_operations = {
.readlink = proc_pid_readlink,
.get_link = proc_map_files_get_link,
.setattr = proc_setattr,
};
static struct dentry *
proc_map_files_instantiate(struct dentry *dentry,
struct task_struct *task, const void *ptr)
{
fmode_t mode = (fmode_t)(unsigned long)ptr;
struct proc_inode *ei;
struct inode *inode;
inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK |
((mode & FMODE_READ ) ? S_IRUSR : 0) |
((mode & FMODE_WRITE) ? S_IWUSR : 0));
if (!inode)
return ERR_PTR(-ENOENT);
ei = PROC_I(inode);
ei->op.proc_get_link = map_files_get_link;
inode->i_op = &proc_map_files_link_inode_operations;
inode->i_size = 64;
d_set_d_op(dentry, &tid_map_files_dentry_operations);
return d_splice_alias(inode, dentry);
}
static struct dentry *proc_map_files_lookup(struct inode *dir,
struct dentry *dentry, unsigned int flags)
{
unsigned long vm_start, vm_end;
struct vm_area_struct *vma;
struct task_struct *task;
struct dentry *result;
struct mm_struct *mm;
result = ERR_PTR(-ENOENT);
task = get_proc_task(dir);
if (!task)
goto out;
result = ERR_PTR(-EACCES);
if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
goto out_put_task;
result = ERR_PTR(-ENOENT);
if (dname_to_vma_addr(dentry, &vm_start, &vm_end))
goto out_put_task;
mm = get_task_mm(task);
if (!mm)
goto out_put_task;
down_read(&mm->mmap_sem);
vma = find_exact_vma(mm, vm_start, vm_end);
if (!vma)
goto out_no_vma;
if (vma->vm_file)
result = proc_map_files_instantiate(dentry, task,
(void *)(unsigned long)vma->vm_file->f_mode);
out_no_vma:
up_read(&mm->mmap_sem);
mmput(mm);
out_put_task:
put_task_struct(task);
out:
return result;
}
static const struct inode_operations proc_map_files_inode_operations = {
.lookup = proc_map_files_lookup,
.permission = proc_fd_permission,
.setattr = proc_setattr,
};
static int
proc_map_files_readdir(struct file *file, struct dir_context *ctx)
{
struct vm_area_struct *vma;
struct task_struct *task;
struct mm_struct *mm;
unsigned long nr_files, pos, i;
GENRADIX(struct map_files_info) fa;
struct map_files_info *p;
int ret;
genradix_init(&fa);
ret = -ENOENT;
task = get_proc_task(file_inode(file));
if (!task)
goto out;
ret = -EACCES;
if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
goto out_put_task;
ret = 0;
if (!dir_emit_dots(file, ctx))
goto out_put_task;
mm = get_task_mm(task);
if (!mm)
goto out_put_task;
down_read(&mm->mmap_sem);
nr_files = 0;
/*
* We need two passes here:
*
* 1) Collect vmas of mapped files with mmap_sem taken
* 2) Release mmap_sem and instantiate entries
*
* otherwise we get lockdep complained, since filldir()
* routine might require mmap_sem taken in might_fault().
*/
for (vma = mm->mmap, pos = 2; vma; vma = vma->vm_next) {
if (!vma->vm_file)
continue;
if (++pos <= ctx->pos)
continue;
p = genradix_ptr_alloc(&fa, nr_files++, GFP_KERNEL);
if (!p) {
ret = -ENOMEM;
up_read(&mm->mmap_sem);
mmput(mm);
goto out_put_task;
}
p->start = vma->vm_start;
p->end = vma->vm_end;
p->mode = vma->vm_file->f_mode;
}
up_read(&mm->mmap_sem);
mmput(mm);
for (i = 0; i < nr_files; i++) {
char buf[4 * sizeof(long) + 2]; /* max: %lx-%lx\0 */
unsigned int len;
p = genradix_ptr(&fa, i);
len = snprintf(buf, sizeof(buf), "%lx-%lx", p->start, p->end);
if (!proc_fill_cache(file, ctx,
buf, len,
proc_map_files_instantiate,
task,
(void *)(unsigned long)p->mode))
break;
ctx->pos++;
}
out_put_task:
put_task_struct(task);
out:
genradix_free(&fa);
return ret;
}
static const struct file_operations proc_map_files_operations = {
.read = generic_read_dir,
.iterate_shared = proc_map_files_readdir,
.llseek = generic_file_llseek,
};
#if defined(CONFIG_CHECKPOINT_RESTORE) && defined(CONFIG_POSIX_TIMERS)
struct timers_private {
struct pid *pid;
struct task_struct *task;
struct sighand_struct *sighand;
struct pid_namespace *ns;
unsigned long flags;
};
static void *timers_start(struct seq_file *m, loff_t *pos)
{
struct timers_private *tp = m->private;
tp->task = get_pid_task(tp->pid, PIDTYPE_PID);
if (!tp->task)
return ERR_PTR(-ESRCH);
tp->sighand = lock_task_sighand(tp->task, &tp->flags);
if (!tp->sighand)
return ERR_PTR(-ESRCH);
return seq_list_start(&tp->task->signal->posix_timers, *pos);
}
static void *timers_next(struct seq_file *m, void *v, loff_t *pos)
{
struct timers_private *tp = m->private;
return seq_list_next(v, &tp->task->signal->posix_timers, pos);
}
static void timers_stop(struct seq_file *m, void *v)
{
struct timers_private *tp = m->private;
if (tp->sighand) {
unlock_task_sighand(tp->task, &tp->flags);
tp->sighand = NULL;
}
if (tp->task) {
put_task_struct(tp->task);
tp->task = NULL;
}
}
static int show_timer(struct seq_file *m, void *v)
{
struct k_itimer *timer;
struct timers_private *tp = m->private;
int notify;
static const char * const nstr[] = {
[SIGEV_SIGNAL] = "signal",
[SIGEV_NONE] = "none",
[SIGEV_THREAD] = "thread",
};
timer = list_entry((struct list_head *)v, struct k_itimer, list);
notify = timer->it_sigev_notify;
seq_printf(m, "ID: %d\n", timer->it_id);
seq_printf(m, "signal: %d/%px\n",
timer->sigq->info.si_signo,
timer->sigq->info.si_value.sival_ptr);
seq_printf(m, "notify: %s/%s.%d\n",
nstr[notify & ~SIGEV_THREAD_ID],
(notify & SIGEV_THREAD_ID) ? "tid" : "pid",
pid_nr_ns(timer->it_pid, tp->ns));
seq_printf(m, "ClockID: %d\n", timer->it_clock);
return 0;
}
static const struct seq_operations proc_timers_seq_ops = {
.start = timers_start,
.next = timers_next,
.stop = timers_stop,
.show = show_timer,
};
static int proc_timers_open(struct inode *inode, struct file *file)
{
struct timers_private *tp;
tp = __seq_open_private(file, &proc_timers_seq_ops,
sizeof(struct timers_private));
if (!tp)
return -ENOMEM;
tp->pid = proc_pid(inode);
tp->ns = proc_pid_ns(inode);
return 0;
}
static const struct file_operations proc_timers_operations = {
.open = proc_timers_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release_private,
};
#endif
static ssize_t timerslack_ns_write(struct file *file, const char __user *buf,
size_t count, loff_t *offset)
{
struct inode *inode = file_inode(file);
struct task_struct *p;
u64 slack_ns;
int err;
err = kstrtoull_from_user(buf, count, 10, &slack_ns);
if (err < 0)
return err;
p = get_proc_task(inode);
if (!p)
return -ESRCH;
if (p != current) {
rcu_read_lock();
if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) {
rcu_read_unlock();
count = -EPERM;
goto out;
}
rcu_read_unlock();
err = security_task_setscheduler(p);
if (err) {
count = err;
goto out;
}
}
task_lock(p);
if (slack_ns == 0)
p->timer_slack_ns = p->default_timer_slack_ns;
else
p->timer_slack_ns = slack_ns;
task_unlock(p);
out:
put_task_struct(p);
return count;
}
static int timerslack_ns_show(struct seq_file *m, void *v)
{
struct inode *inode = m->private;
struct task_struct *p;
int err = 0;
p = get_proc_task(inode);
if (!p)
return -ESRCH;
if (p != current) {
rcu_read_lock();
if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) {
rcu_read_unlock();
err = -EPERM;
goto out;
}
rcu_read_unlock();
err = security_task_getscheduler(p);
if (err)
goto out;
}
task_lock(p);
seq_printf(m, "%llu\n", p->timer_slack_ns);
task_unlock(p);
out:
put_task_struct(p);
return err;
}
static int timerslack_ns_open(struct inode *inode, struct file *filp)
{
return single_open(filp, timerslack_ns_show, inode);
}
static const struct file_operations proc_pid_set_timerslack_ns_operations = {
.open = timerslack_ns_open,
.read = seq_read,
.write = timerslack_ns_write,
.llseek = seq_lseek,
.release = single_release,
};
static struct dentry *proc_pident_instantiate(struct dentry *dentry,
struct task_struct *task, const void *ptr)
{
const struct pid_entry *p = ptr;
struct inode *inode;
struct proc_inode *ei;
inode = proc_pid_make_inode(dentry->d_sb, task, p->mode);
if (!inode)
return ERR_PTR(-ENOENT);
ei = PROC_I(inode);
if (S_ISDIR(inode->i_mode))
set_nlink(inode, 2); /* Use getattr to fix if necessary */
if (p->iop)
inode->i_op = p->iop;
if (p->fop)
inode->i_fop = p->fop;
ei->op = p->op;
pid_update_inode(task, inode);
d_set_d_op(dentry, &pid_dentry_operations);
return d_splice_alias(inode, dentry);
}
static struct dentry *proc_pident_lookup(struct inode *dir,
struct dentry *dentry,
const struct pid_entry *p,
const struct pid_entry *end)
{
struct task_struct *task = get_proc_task(dir);
struct dentry *res = ERR_PTR(-ENOENT);
if (!task)
goto out_no_task;
/*
* Yes, it does not scale. And it should not. Don't add
* new entries into /proc/<tgid>/ without very good reasons.
*/
for (; p < end; p++) {
if (p->len != dentry->d_name.len)
continue;
if (!memcmp(dentry->d_name.name, p->name, p->len)) {
res = proc_pident_instantiate(dentry, task, p);
break;
}
}
put_task_struct(task);
out_no_task:
return res;
}
static int proc_pident_readdir(struct file *file, struct dir_context *ctx,
const struct pid_entry *ents, unsigned int nents)
{
struct task_struct *task = get_proc_task(file_inode(file));
const struct pid_entry *p;
if (!task)
return -ENOENT;
if (!dir_emit_dots(file, ctx))
goto out;
if (ctx->pos >= nents + 2)
goto out;
for (p = ents + (ctx->pos - 2); p < ents + nents; p++) {
if (!proc_fill_cache(file, ctx, p->name, p->len,
proc_pident_instantiate, task, p))
break;
ctx->pos++;
}
out:
put_task_struct(task);
return 0;
}
#ifdef CONFIG_SECURITY
static ssize_t proc_pid_attr_read(struct file * file, char __user * buf,
size_t count, loff_t *ppos)
{
struct inode * inode = file_inode(file);
char *p = NULL;
ssize_t length;
struct task_struct *task = get_proc_task(inode);
if (!task)
return -ESRCH;
length = security_getprocattr(task, PROC_I(inode)->op.lsm,
(char*)file->f_path.dentry->d_name.name,
&p);
put_task_struct(task);
if (length > 0)
length = simple_read_from_buffer(buf, count, ppos, p, length);
kfree(p);
return length;
}
static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
size_t count, loff_t *ppos)
{
struct inode * inode = file_inode(file);
struct task_struct *task;
void *page;
int rv;
rcu_read_lock();
task = pid_task(proc_pid(inode), PIDTYPE_PID);
if (!task) {
rcu_read_unlock();
return -ESRCH;
}
/* A task may only write its own attributes. */
if (current != task) {
rcu_read_unlock();
return -EACCES;
}
/* Prevent changes to overridden credentials. */
if (current_cred() != current_real_cred()) {
rcu_read_unlock();
return -EBUSY;
}
rcu_read_unlock();
if (count > PAGE_SIZE)
count = PAGE_SIZE;
/* No partial writes. */
if (*ppos != 0)
return -EINVAL;
page = memdup_user(buf, count);
if (IS_ERR(page)) {
rv = PTR_ERR(page);
goto out;
}
/* Guard against adverse ptrace interaction */
rv = mutex_lock_interruptible(&current->signal->cred_guard_mutex);
if (rv < 0)
goto out_free;
rv = security_setprocattr(PROC_I(inode)->op.lsm,
file->f_path.dentry->d_name.name, page,
count);
mutex_unlock(&current->signal->cred_guard_mutex);
out_free:
kfree(page);
out:
return rv;
}
static const struct file_operations proc_pid_attr_operations = {
.read = proc_pid_attr_read,
.write = proc_pid_attr_write,
.llseek = generic_file_llseek,
};
#define LSM_DIR_OPS(LSM) \
static int proc_##LSM##_attr_dir_iterate(struct file *filp, \
struct dir_context *ctx) \
{ \
return proc_pident_readdir(filp, ctx, \
LSM##_attr_dir_stuff, \
ARRAY_SIZE(LSM##_attr_dir_stuff)); \
} \
\
static const struct file_operations proc_##LSM##_attr_dir_ops = { \
.read = generic_read_dir, \
.iterate = proc_##LSM##_attr_dir_iterate, \
.llseek = default_llseek, \
}; \
\
static struct dentry *proc_##LSM##_attr_dir_lookup(struct inode *dir, \
struct dentry *dentry, unsigned int flags) \
{ \
return proc_pident_lookup(dir, dentry, \
LSM##_attr_dir_stuff, \
LSM##_attr_dir_stuff + ARRAY_SIZE(LSM##_attr_dir_stuff)); \
} \
\
static const struct inode_operations proc_##LSM##_attr_dir_inode_ops = { \
.lookup = proc_##LSM##_attr_dir_lookup, \
.getattr = pid_getattr, \
.setattr = proc_setattr, \
}
#ifdef CONFIG_SECURITY_SMACK
static const struct pid_entry smack_attr_dir_stuff[] = {
ATTR("smack", "current", 0666),
};
LSM_DIR_OPS(smack);
#endif
static const struct pid_entry attr_dir_stuff[] = {
ATTR(NULL, "current", 0666),
ATTR(NULL, "prev", 0444),
ATTR(NULL, "exec", 0666),
ATTR(NULL, "fscreate", 0666),
ATTR(NULL, "keycreate", 0666),
ATTR(NULL, "sockcreate", 0666),
#ifdef CONFIG_SECURITY_SMACK
DIR("smack", 0555,
proc_smack_attr_dir_inode_ops, proc_smack_attr_dir_ops),
#endif
};
static int proc_attr_dir_readdir(struct file *file, struct dir_context *ctx)
{
return proc_pident_readdir(file, ctx,
attr_dir_stuff, ARRAY_SIZE(attr_dir_stuff));
}
static const struct file_operations proc_attr_dir_operations = {
.read = generic_read_dir,
.iterate_shared = proc_attr_dir_readdir,
.llseek = generic_file_llseek,
};
static struct dentry *proc_attr_dir_lookup(struct inode *dir,
struct dentry *dentry, unsigned int flags)
{
return proc_pident_lookup(dir, dentry,
attr_dir_stuff,
attr_dir_stuff + ARRAY_SIZE(attr_dir_stuff));
}
static const struct inode_operations proc_attr_dir_inode_operations = {
.lookup = proc_attr_dir_lookup,
.getattr = pid_getattr,
.setattr = proc_setattr,
};
#endif
#ifdef CONFIG_ELF_CORE
static ssize_t proc_coredump_filter_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
struct task_struct *task = get_proc_task(file_inode(file));
struct mm_struct *mm;
char buffer[PROC_NUMBUF];
size_t len;
int ret;
if (!task)
return -ESRCH;
ret = 0;
mm = get_task_mm(task);
if (mm) {
len = snprintf(buffer, sizeof(buffer), "%08lx\n",
((mm->flags & MMF_DUMP_FILTER_MASK) >>
MMF_DUMP_FILTER_SHIFT));
mmput(mm);
ret = simple_read_from_buffer(buf, count, ppos, buffer, len);
}
put_task_struct(task);
return ret;
}
static ssize_t proc_coredump_filter_write(struct file *file,
const char __user *buf,
size_t count,
loff_t *ppos)
{
struct task_struct *task;
struct mm_struct *mm;
unsigned int val;
int ret;
int i;
unsigned long mask;
ret = kstrtouint_from_user(buf, count, 0, &val);
if (ret < 0)
return ret;
ret = -ESRCH;
task = get_proc_task(file_inode(file));
if (!task)
goto out_no_task;
mm = get_task_mm(task);
if (!mm)
goto out_no_mm;
ret = 0;
for (i = 0, mask = 1; i < MMF_DUMP_FILTER_BITS; i++, mask <<= 1) {
if (val & mask)
set_bit(i + MMF_DUMP_FILTER_SHIFT, &mm->flags);
else
clear_bit(i + MMF_DUMP_FILTER_SHIFT, &mm->flags);
}
mmput(mm);
out_no_mm:
put_task_struct(task);
out_no_task:
if (ret < 0)
return ret;
return count;
}
static const struct file_operations proc_coredump_filter_operations = {
.read = proc_coredump_filter_read,
.write = proc_coredump_filter_write,
.llseek = generic_file_llseek,
};
#endif
#ifdef CONFIG_TASK_IO_ACCOUNTING
static int do_io_accounting(struct task_struct *task, struct seq_file *m, int whole)
{
struct task_io_accounting acct = task->ioac;
unsigned long flags;
int result;
result = mutex_lock_killable(&task->signal->cred_guard_mutex);
if (result)
return result;
if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
result = -EACCES;
goto out_unlock;
}
if (whole && lock_task_sighand(task, &flags)) {
struct task_struct *t = task;
task_io_accounting_add(&acct, &task->signal->ioac);
while_each_thread(task, t)
task_io_accounting_add(&acct, &t->ioac);
unlock_task_sighand(task, &flags);
}
seq_printf(m,
"rchar: %llu\n"
"wchar: %llu\n"
"syscr: %llu\n"
"syscw: %llu\n"
"read_bytes: %llu\n"
"write_bytes: %llu\n"
"cancelled_write_bytes: %llu\n",
(unsigned long long)acct.rchar,
(unsigned long long)acct.wchar,
(unsigned long long)acct.syscr,
(unsigned long long)acct.syscw,
(unsigned long long)acct.read_bytes,
(unsigned long long)acct.write_bytes,