cregit-Linux how code gets into the kernel

Release 4.10 fs/notify/inotify/inotify_user.c

 * fs/inotify_user.c - inotify support for userspace
 * Authors:
 *      John McCutchan  <>
 *      Robert Love     <>
 * Copyright (C) 2005 John McCutchan
 * Copyright 2006 Hewlett-Packard Development Company, L.P.
 * Copyright (C) 2009 Eric Paris <Red Hat Inc>
 * inotify was largely rewriten to make use of the fsnotify infrastructure
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License as published by the
 * Free Software Foundation; either version 2, or (at your option) any
 * later version.
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * General Public License for more details.

#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.h> /* struct user */
#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 "inotify.h"
#include "../fdinfo.h"

#include <asm/ioctls.h>

/* these are configurable via /proc/sys/fs/inotify/ */

static int inotify_max_user_instances __read_mostly;

static int inotify_max_queued_events __read_mostly;

static int inotify_max_user_watches __read_mostly;

static struct kmem_cache *inotify_inode_mark_cachep __read_mostly;


#include <linux/sysctl.h>

static int zero;

struct ctl_table inotify_table[] = {
		.procname	= "max_user_instances",
		.data		= &inotify_max_user_instances,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.procname	= "max_user_watches",
		.data		= &inotify_max_user_watches,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.procname	= "max_queued_events",
		.data		= &inotify_max_queued_events,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero
	{ }
#endif /* CONFIG_SYSCTL */

static inline __u32 inotify_arg_to_mask(u32 arg) { __u32 mask; /* * everything should accept their own ignored, cares about children, * and should receive events when the inode is unmounted */ mask = (FS_IN_IGNORED | FS_EVENT_ON_CHILD | FS_UNMOUNT); /* mask off the flags used to open the fd */ mask |= (arg & (IN_ALL_EVENTS | IN_ONESHOT | IN_EXCL_UNLINK)); return mask; }


eric pariseric paris3480.95%375.00%
amy griffisamy griffis819.05%125.00%

static inline u32 inotify_mask_to_arg(__u32 mask) { return mask & (IN_ALL_EVENTS | IN_ISDIR | IN_UNMOUNT | IN_IGNORED | IN_Q_OVERFLOW); }


eric pariseric paris1872.00%150.00%
amy griffisamy griffis728.00%150.00%

/* intofiy userspace file descriptor functions */
static unsigned int inotify_poll(struct file *file, poll_table *wait) { struct fsnotify_group *group = file->private_data; int ret = 0; poll_wait(file, &group->notification_waitq, wait); spin_lock(&group->notification_lock); if (!fsnotify_notify_queue_is_empty(group)) ret = POLLIN | POLLRDNORM; spin_unlock(&group->notification_lock); return ret; }


eric pariseric paris4458.67%133.33%
amy griffisamy griffis2736.00%133.33%
jan karajan kara45.33%133.33%

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)); }


jan karajan kara49100.00%2100.00%

/* * Get an inotify_kernel_event if one exists and is small * enough to fit in "count". Return an error pointer if * not large enough. * * Called with the group->notification_lock held. */
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; if (fsnotify_notify_queue_is_empty(group)) return NULL; event = fsnotify_peek_first_event(group); 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); /* held the notification_lock the whole time, so this is the * same event we peeked above */ fsnotify_remove_first_event(group); return event; }


eric pariseric paris5563.22%233.33%
amy griffisamy griffis2832.18%116.67%
jan karajan kara44.60%350.00%

/* * Copy an event to user space, returning how much we copied. * * We already checked that the event size is smaller than the * buffer we had in "get_one_event()" above. */
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; /* * round up name length so it is a multiple of event_size * plus an extra byte for the terminating '\0'. */ pad_name_len = round_event_name_len(fsn_event); inotify_event.len = pad_name_len; inotify_event.mask = inotify_mask_to_arg(fsn_event->mask); inotify_event.wd = event->wd; inotify_event.cookie = event->sync_cookie; /* send the main event */ if (copy_to_user(buf, &inotify_event, event_size)) return -EFAULT; buf += event_size; /* * fsnotify only stores the pathname, so here we have to send the pathname * and then pad that pathname out to a multiple of sizeof(inotify_event) * with zeros. */ if (pad_name_len) { /* copy the path name */ if (copy_to_user(buf, event->name, name_len)) return -EFAULT; buf += name_len; /* fill userspace with 0's */ if (clear_user(buf, pad_name_len - name_len)) return -EFAULT; event_size += pad_name_len; } return event_size; }


eric pariseric paris10557.38%225.00%
jan karajan kara3318.03%225.00%
amy griffisamy griffis2815.30%112.50%
yan zhengyan zheng126.56%112.50%
brian rogersbrian rogers31.64%112.50%
eric w. biedermaneric w. biederman21.09%112.50%

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; }


eric pariseric paris14359.34%333.33%
amy griffisamy griffis7129.46%222.22%
peter zijlstrapeter zijlstra197.88%111.11%
jan karajan kara72.90%222.22%
ulisses furquimulisses furquim10.41%111.11%

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); /* free this group, matching get was inotify_init->fsnotify_obtain_group */ fsnotify_destroy_group(group); return 0; }


eric pariseric paris3888.37%250.00%
amy griffisamy griffis49.30%125.00%
lino sanfilippolino sanfilippo12.33%125.00%

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; } return ret; }


eric pariseric paris9669.06%228.57%
amy griffisamy griffis3223.02%114.29%
jan karajan kara96.47%342.86%
nick pigginnick piggin21.44%114.29%

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, }; /* * find_inode - resolve a user-given path to a specific inode */
static int inotify_find_inode(const char __user *dirname, struct path *path, unsigned flags) { int error; error = user_path_at(AT_FDCWD, dirname, flags, path); if (error) return error; /* you can only watch an inode if you have read permissions on it */ error = inode_permission(path->dentry->d_inode, MAY_READ); if (error) path_put(path); return error; }


amy griffisamy griffis5478.26%120.00%
al viroal viro1217.39%240.00%
jan blunckjan blunck22.90%120.00%
eric pariseric paris11.45%120.00%

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) { /* we added the mark to the idr, take a reference */ i_mark->wd = ret; fsnotify_get_mark(&i_mark->fsn_mark); } spin_unlock(idr_lock); idr_preload_end(); return ret < 0 ? ret : 0; }


eric pariseric paris6472.73%466.67%
tejun heotejun heo2326.14%116.67%
jeff laytonjeff layton11.14%116.67%

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); /* One ref for being in the idr, one ref we just took */ BUG_ON(atomic_read(&fsn_mark->refcnt) < 2); } return i_mark; }


eric pariseric paris96100.00%5100.00%

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; }


eric pariseric paris54100.00%4100.00%

static void do_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; int wd = i_mark->wd; assert_spin_locked(idr_lock); idr_remove(idr, wd); /* removed from the idr, drop that ref */ fsnotify_put_mark(&i_mark->fsn_mark); }


eric pariseric paris67100.00%3100.00%

/* * Remove the mark from the idr (if present) and drop the reference * on the mark because it was in the idr. */
static void inotify_remove_from_idr(struct fsnotify_group *group, struct inotify_inode_mark *i_mark) { 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; /* * does this i_mark think it is in the idr? we shouldn't get called * if it wasn't.... */ if (wd == -1) { WARN_ONCE(1, "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p" " i_mark->inode=%p\n", __func__, i_mark, i_mark->wd, i_mark->, i_mark->fsn_mark.inode); goto out; } /* Lets look in the idr to see if we find it */ 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" " i_mark->inode=%p\n", __func__, i_mark, i_mark->wd, i_mark->, i_mark->fsn_mark.inode); goto out; } /* * We found an mark in the idr at the right wd, but it's * not the mark we were told to remove. eparis seriously * fucked up somewhere. */ if (unlikely(found_i_mark != i_mark)) { WARN_ONCE(1, "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p " "mark->inode=%p found_i_mark=%p found_i_mark->wd=%d " "found_i_mark->group=%p found_i_mark->inode=%p\n", __func__, i_mark, i_mark->wd, i_mark->, i_mark->fsn_mark.inode, found_i_mark, found_i_mark->wd, found_i_mark->, found_i_mark->fsn_mark.inode); goto out; } /* * One ref for being in the idr * one ref held by the caller trying to kill us * one ref grabbed by inotify_idr_find */ if (unlikely(atomic_read(&i_mark->fsn_mark.refcnt) < 3)) { printk(KERN_ERR "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p" " i_mark->inode=%p\n", __func__, i_mark, i_mark->wd, i_mark->, i_mark->fsn_mark.inode); /* we can't really recover with bad ref cnting.. */ BUG(); } do_inotify_remove_from_idr(group, i_mark); out: /* match the ref taken by inotify_idr_find_locked() */ if (found_i_mark) fsnotify_put_mark(&found_i_mark->fsn_mark); i_mark->wd = -1; spin_unlock(idr_lock); }


eric pariseric paris287100.00%5100.00%

/* * Send IN_IGNORED for this wd, remove this wd from the idr. */
void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark, struct fsnotify_group *group) { struct inotify_inode_mark *i_mark; /* Queue ignore event for the watch */ inotify_handle_event(group, NULL, fsn_mark, NULL, FS_IN_IGNORED, NULL, FSNOTIFY_EVENT_NONE, NULL, 0); i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark); /* remove this mark from the idr */ inotify_remove_from_idr(group, i_mark); atomic_dec(&group->inotify_data.user->inotify_watches); }


eric pariseric paris4560.81%964.29%
jan karajan kara1216.22%214.29%
amy griffisamy griffis1114.86%17.14%
lino sanfilippolino sanfilippo45.41%17.14%
vegard nossumvegard nossum22.70%17.14%

/* ding dong the mark is dead */
static void inotify_free_mark(struct fsnotify_mark *fsn_mark) { struct inotify_inode_mark *i_mark; i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark); kmem_cache_free(inotify_inode_mark_cachep, i_mark); }


eric pariseric paris2365.71%480.00%
vegard nossumvegard nossum1234.29%120.00%

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; __u32 mask; int add = (arg & IN_MASK_ADD); int ret; mask = inotify_arg_to_mask(arg); fsn_mark = fsnotify_find_inode_mark(group, inode); if (!fsn_mark) return -ENOENT; i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark); spin_lock(&fsn_mark->lock); old_mask = fsn_mark->mask; if (add) fsnotify_set_mark_mask_locked(fsn_mark, (fsn_mark->mask | mask)); else fsnotify_set_mark_mask_locked(fsn_mark, mask); new_mask = fsn_mark->mask; spin_unlock(&fsn_mark->lock); if (old_mask != new_mask) { /* more bits in old than in new? */ int dropped = (old_mask & ~new_mask); /* more bits in this fsn_mark than the inode's mask? */ int do_inode = (new_mask & ~inode->i_fsnotify_mask); /* update the inode with this new fsn_mark */ if (dropped || do_inode) fsnotify_recalc_inode_mask(inode); } /* return the wd */ ret = i_mark->wd; /* match the get from fsnotify_find_mark() */ fsnotify_put_mark(fsn_mark); return ret; }


eric pariseric paris16783.92%888.89%
amy griffisamy griffis3216.08%111.11%

static int inotify_new_watch(struct fsnotify_group *group, struct inode *inode, u32 arg) { struct inotify_inode_mark *tmp_i_mark; __u32 mask; int ret; struct idr *idr = &group->inotify_data.idr; spinlock_t *idr_lock = &group->inotify_data.idr_lock; mask = inotify_arg_to_mask(arg); 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, inotify_free_mark); tmp_i_mark->fsn_mark.mask = mask; tmp_i_mark->wd = -1; ret = -ENOSPC; if (atomic_read(&group->inotify_data.user->inotify_watches) >= inotify_max_user_watches) goto out_err; ret = inotify_add_to_idr(idr, idr_lock, tmp_i_mark); if (ret) goto out_err; /* we are on the idr, now get on the inode */ ret = fsnotify_add_mark_locked(&tmp_i_mark->fsn_mark, group, inode, NULL, 0); if (ret) { /* we failed to get on the inode, get off the idr */ inotify_remove_from_idr(group, tmp_i_mark); goto out_err; } /* increment the number of watches the user has */ atomic_inc(&group->inotify_data.user->inotify_watches); /* return the watch descriptor for this new mark */ ret = tmp_i_mark->wd; out_err: /* match the ref from fsnotify_init_mark() */ fsnotify_put_mark(&tmp_i_mark->fsn_mark); return ret; }


eric pariseric paris20091.74%1071.43%
amy griffisamy griffis146.42%17.14%
vegard nossumvegard nossum20.92%17.14%
lino sanfilippolino sanfilippo10.46%17.14%
dmitry antipovdmitry antipov10.46%17.14%

static int inotify_update_watch(struct fsnotify_group *group, struct inode *inode, u32 arg) { int ret = 0; mutex_lock(&group->mark_mutex); /* try to update and existing watch with the new arg */ ret = inotify_update_existing_watch(group, inode, arg); /* no mark present, try to add a new one */ if (ret == -ENOENT) ret = inotify_new_watch(group, inode, arg); mutex_unlock(&group->mark_mutex); return ret; }


eric pariseric paris5168.92%250.00%
lino sanfilippolino sanfilippo1621.62%125.00%
amy griffisamy griffis79.46%125.00%

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); if (IS_ERR(group)) return group; oevent = kmalloc(sizeof(struct inotify_event_info), GFP_KERNEL); if (unlikely(!oevent)) { fsnotify_destroy_group(group); return ERR_PTR(-ENOMEM); } group->overflow_event = &oevent->fse; fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW); oevent->wd = -1; oevent->sync_cookie = 0; oevent->name_len = 0; group->max_events = max_events; spin_lock_init(&group->inotify_data.idr_lock); idr_init(&group->inotify_data.idr); group->inotify_data.user = get_current_user(); if (atomic_inc_return(&group->inotify_data.user->inotify_devs) > inotify_max_user_instances) { fsnotify_destroy_group(group); return ERR_PTR(-EMFILE); } return group; }


eric pariseric paris8245.05%342.86%
jan karajan kara7943.41%114.29%
amy griffisamy griffis189.89%114.29%
dmitry antipovdmitry antipov21.10%114.29%
lino sanfilippolino sanfilippo10.55%114.29%

/* inotify syscalls */ SYSCALL_DEFINE1(inotify_init1, int, flags) { struct fsnotify_group *group; int ret; /* Check the IN_* constants for consistency. */ BUILD_BUG_ON(IN_CLOEXEC != O_CLOEXEC); BUILD_BUG_ON(IN_NONBLOCK != O_NONBLOCK); if (flags & ~(IN_CLOEXEC | IN_NONBLOCK)) return -EINVAL; /* fsnotify_obtain_group took a reference to group, we put this when we kill the file in the end */ 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_DEFINE0(inotify_init) { return sys_inotify_init1(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; /* * We share a lot of code with fs/dnotify. We also share * the bit layout between inotify's IN_* and the fsnotify * FS_*. This check ensures that only the inotify IN_* * bits get passed in and set in watches/events. */ if (unlikely(mask & ~ALL_INOTIFY_BITS)) return -EINVAL; /* * Require at least one valid bit set in the mask. * Without _something_ set, we would have no events to * watch for. */ if (unlikely(!(mask & ALL_INOTIFY_BITS))) return -EINVAL; f = fdget(fd); if (unlikely(!f.file)) return -EBADF; /* verify that this is indeed an inotify instance */ 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); if (ret) goto fput_and_out; /* inode held in place by reference to path; group by fget on fd */ inode = path.dentry->d_inode; group = f.file->private_data; /* cr