#include <linux/file.h>
#include <linux/fs.h> /* struct inode */
#include <linux/fsnotify_backend.h>
#include <linux/idr.h>
#include <linux/init.h> /* fs_initcall */
#include <linux/inotify.h>
#include <linux/kernel.h> /* roundup() */
#include <linux/namei.h> /* LOOKUP_FOLLOW */
#include <linux/sched/signal.h>
#include <linux/slab.h> /* struct kmem_cache */
#include <linux/syscalls.h>
#include <linux/types.h>
#include <linux/anon_inodes.h>
#include <linux/uaccess.h>
#include <linux/poll.h>
#include <linux/wait.h>
#include <linux/memcontrol.h>
#include <linux/security.h>
#include "inotify.h"
#include "../fdinfo.h"
#include <asm/ioctls.h>
#define INOTIFY_WATCH_COST (sizeof(struct inotify_inode_mark) + \
2 * sizeof(struct inode))
static int inotify_max_queued_events __read_mostly;
struct kmem_cache *inotify_inode_mark_cachep __read_mostly;
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
static long it_zero = 0;
static long it_int_max = INT_MAX;
static struct ctl_table inotify_table[] = {
{
.procname = "max_user_instances",
.data = &init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES],
.maxlen = sizeof(long),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
.extra1 = &it_zero,
.extra2 = &it_int_max,
},
{
.procname = "max_user_watches",
.data = &init_user_ns.ucount_max[UCOUNT_INOTIFY_WATCHES],
.maxlen = sizeof(long),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
.extra1 = &it_zero,
.extra2 = &it_int_max,
},
{
.procname = "max_queued_events",
.data = &inotify_max_queued_events,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO
},
{ }
};
static void __init inotify_sysctls_init(void)
{
register_sysctl("fs/inotify", inotify_table);
}
#else
#define inotify_sysctls_init() do { } while (0)
#endif /* CONFIG_SYSCTL */
static inline __u32 inotify_arg_to_mask(struct inode *inode, u32 arg)
{
__u32 mask;
mask = (FS_UNMOUNT);
if (S_ISDIR(inode->i_mode))
mask |= FS_EVENT_ON_CHILD;
mask |= (arg & INOTIFY_USER_MASK);
return mask;
}
#define INOTIFY_MARK_FLAGS \
(FSNOTIFY_MARK_FLAG_EXCL_UNLINK | FSNOTIFY_MARK_FLAG_IN_ONESHOT)
static inline unsigned int inotify_arg_to_flags(u32 arg)
{
unsigned int flags = 0;
if (arg & IN_EXCL_UNLINK)
flags |= FSNOTIFY_MARK_FLAG_EXCL_UNLINK;
if (arg & IN_ONESHOT)
flags |= FSNOTIFY_MARK_FLAG_IN_ONESHOT;
return flags;
}
static inline u32 inotify_mask_to_arg(__u32 mask)
{
return mask & (IN_ALL_EVENTS | IN_ISDIR | IN_UNMOUNT | IN_IGNORED |
IN_Q_OVERFLOW);
}
static __poll_t inotify_poll(struct file *file, poll_table *wait)
{
struct fsnotify_group *group = file->private_data;
__poll_t ret = 0;
poll_wait(file, &group->notification_waitq, wait);
spin_lock(&group->notification_lock);
if (!fsnotify_notify_queue_is_empty(group))
ret = EPOLLIN | EPOLLRDNORM;
spin_unlock(&group->notification_lock);
return ret;
}
static int round_event_name_len(struct fsnotify_event *fsn_event)
{
struct inotify_event_info *event;
event = INOTIFY_E(fsn_event);
if (!event->name_len)
return 0;
return roundup(event->name_len + 1, sizeof(struct inotify_event));
}
static struct fsnotify_event *get_one_event(struct fsnotify_group *group,
size_t count)
{
size_t event_size = sizeof(struct inotify_event);
struct fsnotify_event *event;
event = fsnotify_peek_first_event(group);
if (!event)
return NULL;
pr_debug("%s: group=%p event=%p\n", __func__, group, event);
event_size += round_event_name_len(event);
if (event_size > count)
return ERR_PTR(-EINVAL);
fsnotify_remove_first_event(group);
return event;
}
static ssize_t copy_event_to_user(struct fsnotify_group *group,
struct fsnotify_event *fsn_event,
char __user *buf)
{
struct inotify_event inotify_event;
struct inotify_event_info *event;
size_t event_size = sizeof(struct inotify_event);
size_t name_len;
size_t pad_name_len;
pr_debug("%s: group=%p event=%p\n", __func__, group, fsn_event);
event = INOTIFY_E(fsn_event);
name_len = event->name_len;
pad_name_len = round_event_name_len(fsn_event);
inotify_event.len = pad_name_len;
inotify_event.mask = inotify_mask_to_arg(event->mask);
inotify_event.wd = event->wd;
inotify_event.cookie = event->sync_cookie;
if (copy_to_user(buf, &inotify_event, event_size))
return -EFAULT;
buf += event_size;
if (pad_name_len) {
if (copy_to_user(buf, event->name, name_len))
return -EFAULT;
buf += name_len;
if (clear_user(buf, pad_name_len - name_len))
return -EFAULT;
event_size += pad_name_len;
}
return event_size;
}
static ssize_t inotify_read(struct file *file, char __user *buf,
size_t count, loff_t *pos)
{
struct fsnotify_group *group;
struct fsnotify_event *kevent;
char __user *start;
int ret;
DEFINE_WAIT_FUNC(wait, woken_wake_function);
start = buf;
group = file->private_data;
add_wait_queue(&group->notification_waitq, &wait);
while (1) {
spin_lock(&group->notification_lock);
kevent = get_one_event(group, count);
spin_unlock(&group->notification_lock);
pr_debug("%s: group=%p kevent=%p\n", __func__, group, kevent);
if (kevent) {
ret = PTR_ERR(kevent);
if (IS_ERR(kevent))
break;
ret = copy_event_to_user(group, kevent, buf);
fsnotify_destroy_event(group, kevent);
if (ret < 0)
break;
buf += ret;
count -= ret;
continue;
}
ret = -EAGAIN;
if (file->f_flags & O_NONBLOCK)
break;
ret = -ERESTARTSYS;
if (signal_pending(current))
break;
if (start != buf)
break;
wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
}
remove_wait_queue(&group->notification_waitq, &wait);
if (start != buf && ret != -EFAULT)
ret = buf - start;
return ret;
}
static int inotify_release(struct inode *ignored, struct file *file)
{
struct fsnotify_group *group = file->private_data;
pr_debug("%s: group=%p\n", __func__, group);
fsnotify_destroy_group(group);
return 0;
}
static long inotify_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
struct fsnotify_group *group;
struct fsnotify_event *fsn_event;
void __user *p;
int ret = -ENOTTY;
size_t send_len = 0;
group = file->private_data;
p = (void __user *) arg;
pr_debug("%s: group=%p cmd=%u\n", __func__, group, cmd);
switch (cmd) {
case FIONREAD:
spin_lock(&group->notification_lock);
list_for_each_entry(fsn_event, &group->notification_list,
list) {
send_len += sizeof(struct inotify_event);
send_len += round_event_name_len(fsn_event);
}
spin_unlock(&group->notification_lock);
ret = put_user(send_len, (int __user *) p);
break;
#ifdef CONFIG_CHECKPOINT_RESTORE
case INOTIFY_IOC_SETNEXTWD:
ret = -EINVAL;
if (arg >= 1 && arg <= INT_MAX) {
struct inotify_group_private_data *data;
data = &group->inotify_data;
spin_lock(&data->idr_lock);
idr_set_cursor(&data->idr, (unsigned int)arg);
spin_unlock(&data->idr_lock);
ret = 0;
}
break;
#endif /* CONFIG_CHECKPOINT_RESTORE */
}
return ret;
}
static const struct file_operations inotify_fops = {
.show_fdinfo = inotify_show_fdinfo,
.poll = inotify_poll,
.read = inotify_read,
.fasync = fsnotify_fasync,
.release = inotify_release,
.unlocked_ioctl = inotify_ioctl,
.compat_ioctl = inotify_ioctl,
.llseek = noop_llseek,
};
static int inotify_find_inode(const char __user *dirname, struct path *path,
unsigned int flags, __u64 mask)
{
int error;
error = user_path_at(AT_FDCWD, dirname, flags, path);
if (error)
return error;
error = path_permission(path, MAY_READ);
if (error) {
path_put(path);
return error;
}
error = security_path_notify(path, mask,
FSNOTIFY_OBJ_TYPE_INODE);
if (error)
path_put(path);
return error;
}
static int inotify_add_to_idr(struct idr *idr, spinlock_t *idr_lock,
struct inotify_inode_mark *i_mark)
{
int ret;
idr_preload(GFP_KERNEL);
spin_lock(idr_lock);
ret = idr_alloc_cyclic(idr, i_mark, 1, 0, GFP_NOWAIT);
if (ret >= 0) {
i_mark->wd = ret;
fsnotify_get_mark(&i_mark->fsn_mark);
}
spin_unlock(idr_lock);
idr_preload_end();
return ret < 0 ? ret : 0;
}
static struct inotify_inode_mark *inotify_idr_find_locked(struct fsnotify_group *group,
int wd)
{
struct idr *idr = &group->inotify_data.idr;
spinlock_t *idr_lock = &group->inotify_data.idr_lock;
struct inotify_inode_mark *i_mark;
assert_spin_locked(idr_lock);
i_mark = idr_find(idr, wd);
if (i_mark) {
struct fsnotify_mark *fsn_mark = &i_mark->fsn_mark;
fsnotify_get_mark(fsn_mark);
BUG_ON(refcount_read(&fsn_mark->refcnt) < 2);
}
return i_mark;
}
static struct inotify_inode_mark *inotify_idr_find(struct fsnotify_group *group,
int wd)
{
struct inotify_inode_mark *i_mark;
spinlock_t *idr_lock = &group->inotify_data.idr_lock;
spin_lock(idr_lock);
i_mark = inotify_idr_find_locked(group, wd);
spin_unlock(idr_lock);
return i_mark;
}
static void inotify_remove_from_idr(struct fsnotify_group *group,
struct inotify_inode_mark *i_mark)
{
struct idr *idr = &group->inotify_data.idr;
spinlock_t *idr_lock = &group->inotify_data.idr_lock;
struct inotify_inode_mark *found_i_mark = NULL;
int wd;
spin_lock(idr_lock);
wd = i_mark->wd;
if (wd == -1) {
WARN_ONCE(1, "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p\n",
__func__, i_mark, i_mark->wd, i_mark->fsn_mark.group);
goto out;
}
found_i_mark = inotify_idr_find_locked(group, wd);
if (unlikely(!found_i_mark)) {
WARN_ONCE(1, "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p\n",
__func__, i_mark, i_mark->wd, i_mark->fsn_mark.group);
goto out;
}
if (unlikely(found_i_mark != i_mark)) {
WARN_ONCE(1, "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p "
"found_i_mark=%p found_i_mark->wd=%d "
"found_i_mark->group=%p\n", __func__, i_mark,
i_mark->wd, i_mark->fsn_mark.group, found_i_mark,
found_i_mark->wd, found_i_mark->fsn_mark.group);
goto out;
}
if (unlikely(refcount_read(&i_mark->fsn_mark.refcnt) < 2)) {
printk(KERN_ERR "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p\n",
__func__, i_mark, i_mark->wd, i_mark->fsn_mark.group);
BUG();
}
idr_remove(idr, wd);
fsnotify_put_mark(&i_mark->fsn_mark);
out:
i_mark->wd = -1;
spin_unlock(idr_lock);
if (found_i_mark)
fsnotify_put_mark(&found_i_mark->fsn_mark);
}
void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark,
struct fsnotify_group *group)
{
struct inotify_inode_mark *i_mark;
inotify_handle_inode_event(fsn_mark, FS_IN_IGNORED, NULL, NULL, NULL,
0);
i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
inotify_remove_from_idr(group, i_mark);
dec_inotify_watches(group->inotify_data.ucounts);
}
static int inotify_update_existing_watch(struct fsnotify_group *group,
struct inode *inode,
u32 arg)
{
struct fsnotify_mark *fsn_mark;
struct inotify_inode_mark *i_mark;
__u32 old_mask, new_mask;
int replace = !(arg & IN_MASK_ADD);
int create = (arg & IN_MASK_CREATE);
int ret;
fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, group);
if (!fsn_mark)
return -ENOENT;
else if (create) {
ret = -EEXIST;
goto out;
}
i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
spin_lock(&fsn_mark->lock);
old_mask = fsn_mark->mask;
if (replace) {
fsn_mark->mask = 0;
fsn_mark->flags &= ~INOTIFY_MARK_FLAGS;
}
fsn_mark->mask |= inotify_arg_to_mask(inode, arg);
fsn_mark->flags |= inotify_arg_to_flags(arg);
new_mask = fsn_mark->mask;
spin_unlock(&fsn_mark->lock);
if (old_mask != new_mask) {
int dropped = (old_mask & ~new_mask);
int do_inode = (new_mask & ~inode->i_fsnotify_mask);
if (dropped || do_inode)
fsnotify_recalc_mask(inode->i_fsnotify_marks);
}
ret = i_mark->wd;
out:
fsnotify_put_mark(fsn_mark);
return ret;
}
static int inotify_new_watch(struct fsnotify_group *group,
struct inode *inode,
u32 arg)
{
struct inotify_inode_mark *tmp_i_mark;
int ret;
struct idr *idr = &group->inotify_data.idr;
spinlock_t *idr_lock = &group->inotify_data.idr_lock;
tmp_i_mark = kmem_cache_alloc(inotify_inode_mark_cachep, GFP_KERNEL);
if (unlikely(!tmp_i_mark))
return -ENOMEM;
fsnotify_init_mark(&tmp_i_mark->fsn_mark, group);
tmp_i_mark->fsn_mark.mask = inotify_arg_to_mask(inode, arg);
tmp_i_mark->fsn_mark.flags = inotify_arg_to_flags(arg);
tmp_i_mark->wd = -1;
ret = inotify_add_to_idr(idr, idr_lock, tmp_i_mark);
if (ret)
goto out_err;
if (!inc_inotify_watches(group->inotify_data.ucounts)) {
inotify_remove_from_idr(group, tmp_i_mark);
ret = -ENOSPC;
goto out_err;
}
ret = fsnotify_add_inode_mark_locked(&tmp_i_mark->fsn_mark, inode, 0);
if (ret) {
inotify_remove_from_idr(group, tmp_i_mark);
goto out_err;
}
ret = tmp_i_mark->wd;
out_err:
fsnotify_put_mark(&tmp_i_mark->fsn_mark);
return ret;
}
static int inotify_update_watch(struct fsnotify_group *group, struct inode *inode, u32 arg)
{
int ret = 0;
fsnotify_group_lock(group);
ret = inotify_update_existing_watch(group, inode, arg);
if (ret == -ENOENT)
ret = inotify_new_watch(group, inode, arg);
fsnotify_group_unlock(group);
return ret;
}
static struct fsnotify_group *inotify_new_group(unsigned int max_events)
{
struct fsnotify_group *group;
struct inotify_event_info *oevent;
group = fsnotify_alloc_group(&inotify_fsnotify_ops,
FSNOTIFY_GROUP_USER);
if (IS_ERR(group))
return group;
oevent = kmalloc(sizeof(struct inotify_event_info), GFP_KERNEL_ACCOUNT);
if (unlikely(!oevent)) {
fsnotify_destroy_group(group);
return ERR_PTR(-ENOMEM);
}
group->overflow_event = &oevent->fse;
fsnotify_init_event(group->overflow_event);
oevent->mask = FS_Q_OVERFLOW;
oevent->wd = -1;
oevent->sync_cookie = 0;
oevent->name_len = 0;
group->max_events = max_events;
group->memcg = get_mem_cgroup_from_mm(current->mm);
spin_lock_init(&group->inotify_data.idr_lock);
idr_init(&group->inotify_data.idr);
group->inotify_data.ucounts = inc_ucount(current_user_ns(),
current_euid(),
UCOUNT_INOTIFY_INSTANCES);
if (!group->inotify_data.ucounts) {
fsnotify_destroy_group(group);
return ERR_PTR(-EMFILE);
}
return group;
}
static int do_inotify_init(int flags)
{
struct fsnotify_group *group;
int ret;
BUILD_BUG_ON(IN_CLOEXEC != O_CLOEXEC);
BUILD_BUG_ON(IN_NONBLOCK != O_NONBLOCK);
if (flags & ~(IN_CLOEXEC | IN_NONBLOCK))
return -EINVAL;
group = inotify_new_group(inotify_max_queued_events);
if (IS_ERR(group))
return PTR_ERR(group);
ret = anon_inode_getfd("inotify", &inotify_fops, group,
O_RDONLY | flags);
if (ret < 0)
fsnotify_destroy_group(group);
return ret;
}
SYSCALL_DEFINE1(inotify_init1, int, flags)
{
return do_inotify_init(flags);
}
SYSCALL_DEFINE0(inotify_init)
{
return do_inotify_init(0);
}
SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
u32, mask)
{
struct fsnotify_group *group;
struct inode *inode;
struct path path;
struct fd f;
int ret;
unsigned flags = 0;
if (unlikely(mask & ~ALL_INOTIFY_BITS))
return -EINVAL;
if (unlikely(!(mask & ALL_INOTIFY_BITS)))
return -EINVAL;
f = fdget(fd);
if (unlikely(!f.file))
return -EBADF;
if (unlikely((mask & IN_MASK_ADD) && (mask & IN_MASK_CREATE))) {
ret = -EINVAL;
goto fput_and_out;
}
if (unlikely(f.file->f_op != &inotify_fops)) {
ret = -EINVAL;
goto fput_and_out;
}
if (!(mask & IN_DONT_FOLLOW))
flags |= LOOKUP_FOLLOW;
if (mask & IN_ONLYDIR)
flags |= LOOKUP_DIRECTORY;
ret = inotify_find_inode(pathname, &path, flags,
(mask & IN_ALL_EVENTS));
if (ret)
goto fput_and_out;
inode = path.dentry->d_inode;
group = f.file->private_data;
ret = inotify_update_watch(group, inode, mask);
path_put(&path);
fput_and_out:
fdput(f);
return ret;
}
SYSCALL_DEFINE2(inotify_rm_watch, int, fd, __s32, wd)
{
struct fsnotify_group *group;
struct inotify_inode_mark *i_mark;
struct fd f;
int ret = -EINVAL;
f = fdget(fd);
if (unlikely(!f.file))
return -EBADF;
if (unlikely(f.file->f_op != &inotify_fops))
goto out;
group = f.file->private_data;
i_mark = inotify_idr_find(group, wd);
if (unlikely(!i_mark))
goto out;
ret = 0;
fsnotify_destroy_mark(&i_mark->fsn_mark, group);
fsnotify_put_mark(&i_mark->fsn_mark);
out:
fdput(f);
return ret;
}
static int __init inotify_user_setup(void)
{
unsigned long watches_max;
struct sysinfo si;
si_meminfo(&si);
watches_max = (((si.totalram - si.totalhigh) / 100) << PAGE_SHIFT) /
INOTIFY_WATCH_COST;
watches_max = clamp(watches_max, 8192UL, 1048576UL);
BUILD_BUG_ON(IN_ACCESS != FS_ACCESS);
BUILD_BUG_ON(IN_MODIFY != FS_MODIFY);
BUILD_BUG_ON(IN_ATTRIB != FS_ATTRIB);
BUILD_BUG_ON(IN_CLOSE_WRITE != FS_CLOSE_WRITE);
BUILD_BUG_ON(IN_CLOSE_NOWRITE != FS_CLOSE_NOWRITE);
BUILD_BUG_ON(IN_OPEN != FS_OPEN);
BUILD_BUG_ON(IN_MOVED_FROM != FS_MOVED_FROM);
BUILD_BUG_ON(IN_MOVED_TO != FS_MOVED_TO);
BUILD_BUG_ON(IN_CREATE != FS_CREATE);
BUILD_BUG_ON(IN_DELETE != FS_DELETE);
BUILD_BUG_ON(IN_DELETE_SELF != FS_DELETE_SELF);
BUILD_BUG_ON(IN_MOVE_SELF != FS_MOVE_SELF);
BUILD_BUG_ON(IN_UNMOUNT != FS_UNMOUNT);
BUILD_BUG_ON(IN_Q_OVERFLOW != FS_Q_OVERFLOW);
BUILD_BUG_ON(IN_IGNORED != FS_IN_IGNORED);
BUILD_BUG_ON(IN_ISDIR != FS_ISDIR);
BUILD_BUG_ON(HWEIGHT32(ALL_INOTIFY_BITS) != 22);
inotify_inode_mark_cachep = KMEM_CACHE(inotify_inode_mark,
SLAB_PANIC|SLAB_ACCOUNT);
inotify_max_queued_events = 16384;
init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES] = 128;
init_user_ns.ucount_max[UCOUNT_INOTIFY_WATCHES] = watches_max;
inotify_sysctls_init();
return 0;
}
fs_initcall