v4.19.13 snapshot.
diff --git a/fs/notify/Kconfig b/fs/notify/Kconfig
new file mode 100644
index 0000000..2a24249
--- /dev/null
+++ b/fs/notify/Kconfig
@@ -0,0 +1,7 @@
+config FSNOTIFY
+ def_bool n
+ select SRCU
+
+source "fs/notify/dnotify/Kconfig"
+source "fs/notify/inotify/Kconfig"
+source "fs/notify/fanotify/Kconfig"
diff --git a/fs/notify/Makefile b/fs/notify/Makefile
new file mode 100644
index 0000000..63a4b88
--- /dev/null
+++ b/fs/notify/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_FSNOTIFY) += fsnotify.o notification.o group.o mark.o \
+ fdinfo.o
+
+obj-y += dnotify/
+obj-y += inotify/
+obj-y += fanotify/
diff --git a/fs/notify/dnotify/Kconfig b/fs/notify/dnotify/Kconfig
new file mode 100644
index 0000000..f9c1ca1
--- /dev/null
+++ b/fs/notify/dnotify/Kconfig
@@ -0,0 +1,11 @@
+config DNOTIFY
+ bool "Dnotify support"
+ select FSNOTIFY
+ default y
+ help
+ Dnotify is a directory-based per-fd file change notification system
+ that uses signals to communicate events to user-space. There exist
+ superior alternatives, but some applications may still rely on
+ dnotify.
+
+ If unsure, say Y.
diff --git a/fs/notify/dnotify/Makefile b/fs/notify/dnotify/Makefile
new file mode 100644
index 0000000..f145251
--- /dev/null
+++ b/fs/notify/dnotify/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_DNOTIFY) += dnotify.o
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
new file mode 100644
index 0000000..58d77dc
--- /dev/null
+++ b/fs/notify/dnotify/dnotify.c
@@ -0,0 +1,398 @@
+/*
+ * Directory notifications for Linux.
+ *
+ * Copyright (C) 2000,2001,2002 Stephen Rothwell
+ *
+ * Copyright (C) 2009 Eric Paris <Red Hat Inc>
+ * dnotify was largly rewritten to use the new 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
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#include <linux/fs.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/sched/signal.h>
+#include <linux/dnotify.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/fdtable.h>
+#include <linux/fsnotify_backend.h>
+
+int dir_notify_enable __read_mostly = 1;
+
+static struct kmem_cache *dnotify_struct_cache __read_mostly;
+static struct kmem_cache *dnotify_mark_cache __read_mostly;
+static struct fsnotify_group *dnotify_group __read_mostly;
+
+/*
+ * dnotify will attach one of these to each inode (i_fsnotify_marks) which
+ * is being watched by dnotify. If multiple userspace applications are watching
+ * the same directory with dnotify their information is chained in dn
+ */
+struct dnotify_mark {
+ struct fsnotify_mark fsn_mark;
+ struct dnotify_struct *dn;
+};
+
+/*
+ * When a process starts or stops watching an inode the set of events which
+ * dnotify cares about for that inode may change. This function runs the
+ * list of everything receiving dnotify events about this directory and calculates
+ * the set of all those events. After it updates what dnotify is interested in
+ * it calls the fsnotify function so it can update the set of all events relevant
+ * to this inode.
+ */
+static void dnotify_recalc_inode_mask(struct fsnotify_mark *fsn_mark)
+{
+ __u32 new_mask = 0;
+ struct dnotify_struct *dn;
+ struct dnotify_mark *dn_mark = container_of(fsn_mark,
+ struct dnotify_mark,
+ fsn_mark);
+
+ assert_spin_locked(&fsn_mark->lock);
+
+ for (dn = dn_mark->dn; dn != NULL; dn = dn->dn_next)
+ new_mask |= (dn->dn_mask & ~FS_DN_MULTISHOT);
+ if (fsn_mark->mask == new_mask)
+ return;
+ fsn_mark->mask = new_mask;
+
+ fsnotify_recalc_mask(fsn_mark->connector);
+}
+
+/*
+ * Mains fsnotify call where events are delivered to dnotify.
+ * Find the dnotify mark on the relevant inode, run the list of dnotify structs
+ * on that mark and determine which of them has expressed interest in receiving
+ * events of this type. When found send the correct process and signal and
+ * destroy the dnotify struct if it was not registered to receive multiple
+ * events.
+ */
+static int dnotify_handle_event(struct fsnotify_group *group,
+ struct inode *inode,
+ u32 mask, const void *data, int data_type,
+ const unsigned char *file_name, u32 cookie,
+ struct fsnotify_iter_info *iter_info)
+{
+ struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info);
+ struct dnotify_mark *dn_mark;
+ struct dnotify_struct *dn;
+ struct dnotify_struct **prev;
+ struct fown_struct *fown;
+ __u32 test_mask = mask & ~FS_EVENT_ON_CHILD;
+
+ /* not a dir, dnotify doesn't care */
+ if (!S_ISDIR(inode->i_mode))
+ return 0;
+
+ if (WARN_ON(fsnotify_iter_vfsmount_mark(iter_info)))
+ return 0;
+
+ dn_mark = container_of(inode_mark, struct dnotify_mark, fsn_mark);
+
+ spin_lock(&inode_mark->lock);
+ prev = &dn_mark->dn;
+ while ((dn = *prev) != NULL) {
+ if ((dn->dn_mask & test_mask) == 0) {
+ prev = &dn->dn_next;
+ continue;
+ }
+ fown = &dn->dn_filp->f_owner;
+ send_sigio(fown, dn->dn_fd, POLL_MSG);
+ if (dn->dn_mask & FS_DN_MULTISHOT)
+ prev = &dn->dn_next;
+ else {
+ *prev = dn->dn_next;
+ kmem_cache_free(dnotify_struct_cache, dn);
+ dnotify_recalc_inode_mask(inode_mark);
+ }
+ }
+
+ spin_unlock(&inode_mark->lock);
+
+ return 0;
+}
+
+static void dnotify_free_mark(struct fsnotify_mark *fsn_mark)
+{
+ struct dnotify_mark *dn_mark = container_of(fsn_mark,
+ struct dnotify_mark,
+ fsn_mark);
+
+ BUG_ON(dn_mark->dn);
+
+ kmem_cache_free(dnotify_mark_cache, dn_mark);
+}
+
+static const struct fsnotify_ops dnotify_fsnotify_ops = {
+ .handle_event = dnotify_handle_event,
+ .free_mark = dnotify_free_mark,
+};
+
+/*
+ * Called every time a file is closed. Looks first for a dnotify mark on the
+ * inode. If one is found run all of the ->dn structures attached to that
+ * mark for one relevant to this process closing the file and remove that
+ * dnotify_struct. If that was the last dnotify_struct also remove the
+ * fsnotify_mark.
+ */
+void dnotify_flush(struct file *filp, fl_owner_t id)
+{
+ struct fsnotify_mark *fsn_mark;
+ struct dnotify_mark *dn_mark;
+ struct dnotify_struct *dn;
+ struct dnotify_struct **prev;
+ struct inode *inode;
+ bool free = false;
+
+ inode = file_inode(filp);
+ if (!S_ISDIR(inode->i_mode))
+ return;
+
+ fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, dnotify_group);
+ if (!fsn_mark)
+ return;
+ dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark);
+
+ mutex_lock(&dnotify_group->mark_mutex);
+
+ spin_lock(&fsn_mark->lock);
+ prev = &dn_mark->dn;
+ while ((dn = *prev) != NULL) {
+ if ((dn->dn_owner == id) && (dn->dn_filp == filp)) {
+ *prev = dn->dn_next;
+ kmem_cache_free(dnotify_struct_cache, dn);
+ dnotify_recalc_inode_mask(fsn_mark);
+ break;
+ }
+ prev = &dn->dn_next;
+ }
+
+ spin_unlock(&fsn_mark->lock);
+
+ /* nothing else could have found us thanks to the dnotify_groups
+ mark_mutex */
+ if (dn_mark->dn == NULL) {
+ fsnotify_detach_mark(fsn_mark);
+ free = true;
+ }
+
+ mutex_unlock(&dnotify_group->mark_mutex);
+
+ if (free)
+ fsnotify_free_mark(fsn_mark);
+ fsnotify_put_mark(fsn_mark);
+}
+
+/* this conversion is done only at watch creation */
+static __u32 convert_arg(unsigned long arg)
+{
+ __u32 new_mask = FS_EVENT_ON_CHILD;
+
+ if (arg & DN_MULTISHOT)
+ new_mask |= FS_DN_MULTISHOT;
+ if (arg & DN_DELETE)
+ new_mask |= (FS_DELETE | FS_MOVED_FROM);
+ if (arg & DN_MODIFY)
+ new_mask |= FS_MODIFY;
+ if (arg & DN_ACCESS)
+ new_mask |= FS_ACCESS;
+ if (arg & DN_ATTRIB)
+ new_mask |= FS_ATTRIB;
+ if (arg & DN_RENAME)
+ new_mask |= FS_DN_RENAME;
+ if (arg & DN_CREATE)
+ new_mask |= (FS_CREATE | FS_MOVED_TO);
+
+ return new_mask;
+}
+
+/*
+ * If multiple processes watch the same inode with dnotify there is only one
+ * dnotify mark in inode->i_fsnotify_marks but we chain a dnotify_struct
+ * onto that mark. This function either attaches the new dnotify_struct onto
+ * that list, or it |= the mask onto an existing dnofiy_struct.
+ */
+static int attach_dn(struct dnotify_struct *dn, struct dnotify_mark *dn_mark,
+ fl_owner_t id, int fd, struct file *filp, __u32 mask)
+{
+ struct dnotify_struct *odn;
+
+ odn = dn_mark->dn;
+ while (odn != NULL) {
+ /* adding more events to existing dnofiy_struct? */
+ if ((odn->dn_owner == id) && (odn->dn_filp == filp)) {
+ odn->dn_fd = fd;
+ odn->dn_mask |= mask;
+ return -EEXIST;
+ }
+ odn = odn->dn_next;
+ }
+
+ dn->dn_mask = mask;
+ dn->dn_fd = fd;
+ dn->dn_filp = filp;
+ dn->dn_owner = id;
+ dn->dn_next = dn_mark->dn;
+ dn_mark->dn = dn;
+
+ return 0;
+}
+
+/*
+ * When a process calls fcntl to attach a dnotify watch to a directory it ends
+ * up here. Allocate both a mark for fsnotify to add and a dnotify_struct to be
+ * attached to the fsnotify_mark.
+ */
+int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg)
+{
+ struct dnotify_mark *new_dn_mark, *dn_mark;
+ struct fsnotify_mark *new_fsn_mark, *fsn_mark;
+ struct dnotify_struct *dn;
+ struct inode *inode;
+ fl_owner_t id = current->files;
+ struct file *f;
+ int destroy = 0, error = 0;
+ __u32 mask;
+
+ /* we use these to tell if we need to kfree */
+ new_fsn_mark = NULL;
+ dn = NULL;
+
+ if (!dir_notify_enable) {
+ error = -EINVAL;
+ goto out_err;
+ }
+
+ /* a 0 mask means we are explicitly removing the watch */
+ if ((arg & ~DN_MULTISHOT) == 0) {
+ dnotify_flush(filp, id);
+ error = 0;
+ goto out_err;
+ }
+
+ /* dnotify only works on directories */
+ inode = file_inode(filp);
+ if (!S_ISDIR(inode->i_mode)) {
+ error = -ENOTDIR;
+ goto out_err;
+ }
+
+ /* expect most fcntl to add new rather than augment old */
+ dn = kmem_cache_alloc(dnotify_struct_cache, GFP_KERNEL);
+ if (!dn) {
+ error = -ENOMEM;
+ goto out_err;
+ }
+
+ /* new fsnotify mark, we expect most fcntl calls to add a new mark */
+ new_dn_mark = kmem_cache_alloc(dnotify_mark_cache, GFP_KERNEL);
+ if (!new_dn_mark) {
+ error = -ENOMEM;
+ goto out_err;
+ }
+
+ /* convert the userspace DN_* "arg" to the internal FS_* defines in fsnotify */
+ mask = convert_arg(arg);
+
+ /* set up the new_fsn_mark and new_dn_mark */
+ new_fsn_mark = &new_dn_mark->fsn_mark;
+ fsnotify_init_mark(new_fsn_mark, dnotify_group);
+ new_fsn_mark->mask = mask;
+ new_dn_mark->dn = NULL;
+
+ /* this is needed to prevent the fcntl/close race described below */
+ mutex_lock(&dnotify_group->mark_mutex);
+
+ /* add the new_fsn_mark or find an old one. */
+ fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, dnotify_group);
+ if (fsn_mark) {
+ dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark);
+ spin_lock(&fsn_mark->lock);
+ } else {
+ error = fsnotify_add_inode_mark_locked(new_fsn_mark, inode, 0);
+ if (error) {
+ mutex_unlock(&dnotify_group->mark_mutex);
+ goto out_err;
+ }
+ spin_lock(&new_fsn_mark->lock);
+ fsn_mark = new_fsn_mark;
+ dn_mark = new_dn_mark;
+ /* we used new_fsn_mark, so don't free it */
+ new_fsn_mark = NULL;
+ }
+
+ rcu_read_lock();
+ f = fcheck(fd);
+ rcu_read_unlock();
+
+ /* if (f != filp) means that we lost a race and another task/thread
+ * actually closed the fd we are still playing with before we grabbed
+ * the dnotify_groups mark_mutex and fsn_mark->lock. Since closing the
+ * fd is the only time we clean up the marks we need to get our mark
+ * off the list. */
+ if (f != filp) {
+ /* if we added ourselves, shoot ourselves, it's possible that
+ * the flush actually did shoot this fsn_mark. That's fine too
+ * since multiple calls to destroy_mark is perfectly safe, if
+ * we found a dn_mark already attached to the inode, just sod
+ * off silently as the flush at close time dealt with it.
+ */
+ if (dn_mark == new_dn_mark)
+ destroy = 1;
+ error = 0;
+ goto out;
+ }
+
+ __f_setown(filp, task_pid(current), PIDTYPE_TGID, 0);
+
+ error = attach_dn(dn, dn_mark, id, fd, filp, mask);
+ /* !error means that we attached the dn to the dn_mark, so don't free it */
+ if (!error)
+ dn = NULL;
+ /* -EEXIST means that we didn't add this new dn and used an old one.
+ * that isn't an error (and the unused dn should be freed) */
+ else if (error == -EEXIST)
+ error = 0;
+
+ dnotify_recalc_inode_mask(fsn_mark);
+out:
+ spin_unlock(&fsn_mark->lock);
+
+ if (destroy)
+ fsnotify_detach_mark(fsn_mark);
+ mutex_unlock(&dnotify_group->mark_mutex);
+ if (destroy)
+ fsnotify_free_mark(fsn_mark);
+ fsnotify_put_mark(fsn_mark);
+out_err:
+ if (new_fsn_mark)
+ fsnotify_put_mark(new_fsn_mark);
+ if (dn)
+ kmem_cache_free(dnotify_struct_cache, dn);
+ return error;
+}
+
+static int __init dnotify_init(void)
+{
+ dnotify_struct_cache = KMEM_CACHE(dnotify_struct,
+ SLAB_PANIC|SLAB_ACCOUNT);
+ dnotify_mark_cache = KMEM_CACHE(dnotify_mark, SLAB_PANIC|SLAB_ACCOUNT);
+
+ dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops);
+ if (IS_ERR(dnotify_group))
+ panic("unable to allocate fsnotify group for dnotify\n");
+ return 0;
+}
+
+module_init(dnotify_init)
diff --git a/fs/notify/fanotify/Kconfig b/fs/notify/fanotify/Kconfig
new file mode 100644
index 0000000..41355ce
--- /dev/null
+++ b/fs/notify/fanotify/Kconfig
@@ -0,0 +1,26 @@
+config FANOTIFY
+ bool "Filesystem wide access notification"
+ select FSNOTIFY
+ select ANON_INODES
+ default n
+ ---help---
+ Say Y here to enable fanotify support. fanotify is a file access
+ notification system which differs from inotify in that it sends
+ an open file descriptor to the userspace listener along with
+ the event.
+
+ If unsure, say Y.
+
+config FANOTIFY_ACCESS_PERMISSIONS
+ bool "fanotify permissions checking"
+ depends on FANOTIFY
+ depends on SECURITY
+ default n
+ ---help---
+ Say Y here is you want fanotify listeners to be able to make permissions
+ decisions concerning filesystem events. This is used by some fanotify
+ listeners which need to scan files before allowing the system access to
+ use those files. This is used by some anti-malware vendors and by some
+ hierarchical storage management systems.
+
+ If unsure, say N.
diff --git a/fs/notify/fanotify/Makefile b/fs/notify/fanotify/Makefile
new file mode 100644
index 0000000..0999213
--- /dev/null
+++ b/fs/notify/fanotify/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_FANOTIFY) += fanotify.o fanotify_user.o
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
new file mode 100644
index 0000000..29dee96
--- /dev/null
+++ b/fs/notify/fanotify/fanotify.c
@@ -0,0 +1,290 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/fanotify.h>
+#include <linux/fdtable.h>
+#include <linux/fsnotify_backend.h>
+#include <linux/init.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h> /* UINT_MAX */
+#include <linux/mount.h>
+#include <linux/sched.h>
+#include <linux/sched/user.h>
+#include <linux/sched/signal.h>
+#include <linux/types.h>
+#include <linux/wait.h>
+#include <linux/audit.h>
+#include <linux/sched/mm.h>
+
+#include "fanotify.h"
+
+static bool should_merge(struct fsnotify_event *old_fsn,
+ struct fsnotify_event *new_fsn)
+{
+ struct fanotify_event_info *old, *new;
+
+ pr_debug("%s: old=%p new=%p\n", __func__, old_fsn, new_fsn);
+ old = FANOTIFY_E(old_fsn);
+ new = FANOTIFY_E(new_fsn);
+
+ if (old_fsn->inode == new_fsn->inode && old->tgid == new->tgid &&
+ old->path.mnt == new->path.mnt &&
+ old->path.dentry == new->path.dentry)
+ return true;
+ return false;
+}
+
+/* and the list better be locked by something too! */
+static int fanotify_merge(struct list_head *list, struct fsnotify_event *event)
+{
+ struct fsnotify_event *test_event;
+
+ pr_debug("%s: list=%p event=%p\n", __func__, list, event);
+
+ /*
+ * Don't merge a permission event with any other event so that we know
+ * the event structure we have created in fanotify_handle_event() is the
+ * one we should check for permission response.
+ */
+ if (fanotify_is_perm_event(event->mask))
+ return 0;
+
+ list_for_each_entry_reverse(test_event, list, list) {
+ if (should_merge(test_event, event)) {
+ test_event->mask |= event->mask;
+ return 1;
+ }
+ }
+
+ return 0;
+}
+
+static int fanotify_get_response(struct fsnotify_group *group,
+ struct fanotify_perm_event_info *event,
+ struct fsnotify_iter_info *iter_info)
+{
+ int ret;
+
+ pr_debug("%s: group=%p event=%p\n", __func__, group, event);
+
+ wait_event(group->fanotify_data.access_waitq, event->response);
+
+ /* userspace responded, convert to something usable */
+ switch (event->response & ~FAN_AUDIT) {
+ case FAN_ALLOW:
+ ret = 0;
+ break;
+ case FAN_DENY:
+ default:
+ ret = -EPERM;
+ }
+
+ /* Check if the response should be audited */
+ if (event->response & FAN_AUDIT)
+ audit_fanotify(event->response & ~FAN_AUDIT);
+
+ event->response = 0;
+
+ pr_debug("%s: group=%p event=%p about to return ret=%d\n", __func__,
+ group, event, ret);
+
+ return ret;
+}
+
+static bool fanotify_should_send_event(struct fsnotify_iter_info *iter_info,
+ u32 event_mask, const void *data,
+ int data_type)
+{
+ __u32 marks_mask = 0, marks_ignored_mask = 0;
+ const struct path *path = data;
+ struct fsnotify_mark *mark;
+ int type;
+
+ pr_debug("%s: report_mask=%x mask=%x data=%p data_type=%d\n",
+ __func__, iter_info->report_mask, event_mask, data, data_type);
+
+ /* if we don't have enough info to send an event to userspace say no */
+ if (data_type != FSNOTIFY_EVENT_PATH)
+ return false;
+
+ /* sorry, fanotify only gives a damn about files and dirs */
+ if (!d_is_reg(path->dentry) &&
+ !d_can_lookup(path->dentry))
+ return false;
+
+ fsnotify_foreach_obj_type(type) {
+ if (!fsnotify_iter_should_report_type(iter_info, type))
+ continue;
+ mark = iter_info->marks[type];
+ /*
+ * If the event is for a child and this mark doesn't care about
+ * events on a child, don't send it!
+ */
+ if (event_mask & FS_EVENT_ON_CHILD &&
+ (type != FSNOTIFY_OBJ_TYPE_INODE ||
+ !(mark->mask & FS_EVENT_ON_CHILD)))
+ continue;
+
+ marks_mask |= mark->mask;
+ marks_ignored_mask |= mark->ignored_mask;
+ }
+
+ if (d_is_dir(path->dentry) &&
+ !(marks_mask & FS_ISDIR & ~marks_ignored_mask))
+ return false;
+
+ if (event_mask & FAN_ALL_OUTGOING_EVENTS & marks_mask &
+ ~marks_ignored_mask)
+ return true;
+
+ return false;
+}
+
+struct fanotify_event_info *fanotify_alloc_event(struct fsnotify_group *group,
+ struct inode *inode, u32 mask,
+ const struct path *path)
+{
+ struct fanotify_event_info *event = NULL;
+ gfp_t gfp = GFP_KERNEL_ACCOUNT;
+
+ /*
+ * For queues with unlimited length lost events are not expected and
+ * can possibly have security implications. Avoid losing events when
+ * memory is short.
+ */
+ if (group->max_events == UINT_MAX)
+ gfp |= __GFP_NOFAIL;
+
+ /* Whoever is interested in the event, pays for the allocation. */
+ memalloc_use_memcg(group->memcg);
+
+ if (fanotify_is_perm_event(mask)) {
+ struct fanotify_perm_event_info *pevent;
+
+ pevent = kmem_cache_alloc(fanotify_perm_event_cachep, gfp);
+ if (!pevent)
+ goto out;
+ event = &pevent->fae;
+ pevent->response = 0;
+ goto init;
+ }
+ event = kmem_cache_alloc(fanotify_event_cachep, gfp);
+ if (!event)
+ goto out;
+init: __maybe_unused
+ fsnotify_init_event(&event->fse, inode, mask);
+ event->tgid = get_pid(task_tgid(current));
+ if (path) {
+ event->path = *path;
+ path_get(&event->path);
+ } else {
+ event->path.mnt = NULL;
+ event->path.dentry = NULL;
+ }
+out:
+ memalloc_unuse_memcg();
+ return event;
+}
+
+static int fanotify_handle_event(struct fsnotify_group *group,
+ struct inode *inode,
+ u32 mask, const void *data, int data_type,
+ const unsigned char *file_name, u32 cookie,
+ struct fsnotify_iter_info *iter_info)
+{
+ int ret = 0;
+ struct fanotify_event_info *event;
+ struct fsnotify_event *fsn_event;
+
+ BUILD_BUG_ON(FAN_ACCESS != FS_ACCESS);
+ BUILD_BUG_ON(FAN_MODIFY != FS_MODIFY);
+ BUILD_BUG_ON(FAN_CLOSE_NOWRITE != FS_CLOSE_NOWRITE);
+ BUILD_BUG_ON(FAN_CLOSE_WRITE != FS_CLOSE_WRITE);
+ BUILD_BUG_ON(FAN_OPEN != FS_OPEN);
+ BUILD_BUG_ON(FAN_EVENT_ON_CHILD != FS_EVENT_ON_CHILD);
+ BUILD_BUG_ON(FAN_Q_OVERFLOW != FS_Q_OVERFLOW);
+ BUILD_BUG_ON(FAN_OPEN_PERM != FS_OPEN_PERM);
+ BUILD_BUG_ON(FAN_ACCESS_PERM != FS_ACCESS_PERM);
+ BUILD_BUG_ON(FAN_ONDIR != FS_ISDIR);
+
+ if (!fanotify_should_send_event(iter_info, mask, data, data_type))
+ return 0;
+
+ pr_debug("%s: group=%p inode=%p mask=%x\n", __func__, group, inode,
+ mask);
+
+ if (fanotify_is_perm_event(mask)) {
+ /*
+ * fsnotify_prepare_user_wait() fails if we race with mark
+ * deletion. Just let the operation pass in that case.
+ */
+ if (!fsnotify_prepare_user_wait(iter_info))
+ return 0;
+ }
+
+ event = fanotify_alloc_event(group, inode, mask, data);
+ ret = -ENOMEM;
+ if (unlikely(!event)) {
+ /*
+ * We don't queue overflow events for permission events as
+ * there the access is denied and so no event is in fact lost.
+ */
+ if (!fanotify_is_perm_event(mask))
+ fsnotify_queue_overflow(group);
+ goto finish;
+ }
+
+ fsn_event = &event->fse;
+ ret = fsnotify_add_event(group, fsn_event, fanotify_merge);
+ if (ret) {
+ /* Permission events shouldn't be merged */
+ BUG_ON(ret == 1 && mask & FAN_ALL_PERM_EVENTS);
+ /* Our event wasn't used in the end. Free it. */
+ fsnotify_destroy_event(group, fsn_event);
+
+ ret = 0;
+ } else if (fanotify_is_perm_event(mask)) {
+ ret = fanotify_get_response(group, FANOTIFY_PE(fsn_event),
+ iter_info);
+ fsnotify_destroy_event(group, fsn_event);
+ }
+finish:
+ if (fanotify_is_perm_event(mask))
+ fsnotify_finish_user_wait(iter_info);
+
+ return ret;
+}
+
+static void fanotify_free_group_priv(struct fsnotify_group *group)
+{
+ struct user_struct *user;
+
+ user = group->fanotify_data.user;
+ atomic_dec(&user->fanotify_listeners);
+ free_uid(user);
+}
+
+static void fanotify_free_event(struct fsnotify_event *fsn_event)
+{
+ struct fanotify_event_info *event;
+
+ event = FANOTIFY_E(fsn_event);
+ path_put(&event->path);
+ put_pid(event->tgid);
+ if (fanotify_is_perm_event(fsn_event->mask)) {
+ kmem_cache_free(fanotify_perm_event_cachep,
+ FANOTIFY_PE(fsn_event));
+ return;
+ }
+ kmem_cache_free(fanotify_event_cachep, event);
+}
+
+static void fanotify_free_mark(struct fsnotify_mark *fsn_mark)
+{
+ kmem_cache_free(fanotify_mark_cache, fsn_mark);
+}
+
+const struct fsnotify_ops fanotify_fsnotify_ops = {
+ .handle_event = fanotify_handle_event,
+ .free_group_priv = fanotify_free_group_priv,
+ .free_event = fanotify_free_event,
+ .free_mark = fanotify_free_mark,
+};
diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h
new file mode 100644
index 0000000..8609ba0
--- /dev/null
+++ b/fs/notify/fanotify/fanotify.h
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/fsnotify_backend.h>
+#include <linux/path.h>
+#include <linux/slab.h>
+
+extern struct kmem_cache *fanotify_mark_cache;
+extern struct kmem_cache *fanotify_event_cachep;
+extern struct kmem_cache *fanotify_perm_event_cachep;
+
+/*
+ * Structure for normal fanotify events. It gets allocated in
+ * fanotify_handle_event() and freed when the information is retrieved by
+ * userspace
+ */
+struct fanotify_event_info {
+ struct fsnotify_event fse;
+ /*
+ * We hold ref to this path so it may be dereferenced at any point
+ * during this object's lifetime
+ */
+ struct path path;
+ struct pid *tgid;
+};
+
+/*
+ * Structure for permission fanotify events. It gets allocated and freed in
+ * fanotify_handle_event() since we wait there for user response. When the
+ * information is retrieved by userspace the structure is moved from
+ * group->notification_list to group->fanotify_data.access_list to wait for
+ * user response.
+ */
+struct fanotify_perm_event_info {
+ struct fanotify_event_info fae;
+ int response; /* userspace answer to question */
+ int fd; /* fd we passed to userspace for this event */
+};
+
+static inline struct fanotify_perm_event_info *
+FANOTIFY_PE(struct fsnotify_event *fse)
+{
+ return container_of(fse, struct fanotify_perm_event_info, fae.fse);
+}
+
+static inline bool fanotify_is_perm_event(u32 mask)
+{
+ return IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS) &&
+ mask & FAN_ALL_PERM_EVENTS;
+}
+
+static inline struct fanotify_event_info *FANOTIFY_E(struct fsnotify_event *fse)
+{
+ return container_of(fse, struct fanotify_event_info, fse);
+}
+
+struct fanotify_event_info *fanotify_alloc_event(struct fsnotify_group *group,
+ struct inode *inode, u32 mask,
+ const struct path *path);
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
new file mode 100644
index 0000000..6905488
--- /dev/null
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -0,0 +1,947 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/fanotify.h>
+#include <linux/fcntl.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/anon_inodes.h>
+#include <linux/fsnotify_backend.h>
+#include <linux/init.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/poll.h>
+#include <linux/security.h>
+#include <linux/syscalls.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/compat.h>
+#include <linux/sched/signal.h>
+#include <linux/memcontrol.h>
+
+#include <asm/ioctls.h>
+
+#include "../../mount.h"
+#include "../fdinfo.h"
+#include "fanotify.h"
+
+#define FANOTIFY_DEFAULT_MAX_EVENTS 16384
+#define FANOTIFY_DEFAULT_MAX_MARKS 8192
+#define FANOTIFY_DEFAULT_MAX_LISTENERS 128
+
+/*
+ * All flags that may be specified in parameter event_f_flags of fanotify_init.
+ *
+ * Internal and external open flags are stored together in field f_flags of
+ * struct file. Only external open flags shall be allowed in event_f_flags.
+ * Internal flags like FMODE_NONOTIFY, FMODE_EXEC, FMODE_NOCMTIME shall be
+ * excluded.
+ */
+#define FANOTIFY_INIT_ALL_EVENT_F_BITS ( \
+ O_ACCMODE | O_APPEND | O_NONBLOCK | \
+ __O_SYNC | O_DSYNC | O_CLOEXEC | \
+ O_LARGEFILE | O_NOATIME )
+
+extern const struct fsnotify_ops fanotify_fsnotify_ops;
+
+struct kmem_cache *fanotify_mark_cache __read_mostly;
+struct kmem_cache *fanotify_event_cachep __read_mostly;
+struct kmem_cache *fanotify_perm_event_cachep __read_mostly;
+
+/*
+ * Get an fsnotify notification event if one exists and is small
+ * enough to fit in "count". Return an error pointer if the count
+ * is not large enough.
+ *
+ * Called with the group->notification_lock held.
+ */
+static struct fsnotify_event *get_one_event(struct fsnotify_group *group,
+ size_t count)
+{
+ assert_spin_locked(&group->notification_lock);
+
+ pr_debug("%s: group=%p count=%zd\n", __func__, group, count);
+
+ if (fsnotify_notify_queue_is_empty(group))
+ return NULL;
+
+ if (FAN_EVENT_METADATA_LEN > count)
+ return ERR_PTR(-EINVAL);
+
+ /* held the notification_lock the whole time, so this is the
+ * same event we peeked above */
+ return fsnotify_remove_first_event(group);
+}
+
+static int create_fd(struct fsnotify_group *group,
+ struct fanotify_event_info *event,
+ struct file **file)
+{
+ int client_fd;
+ struct file *new_file;
+
+ pr_debug("%s: group=%p event=%p\n", __func__, group, event);
+
+ client_fd = get_unused_fd_flags(group->fanotify_data.f_flags);
+ if (client_fd < 0)
+ return client_fd;
+
+ /*
+ * we need a new file handle for the userspace program so it can read even if it was
+ * originally opened O_WRONLY.
+ */
+ /* it's possible this event was an overflow event. in that case dentry and mnt
+ * are NULL; That's fine, just don't call dentry open */
+ if (event->path.dentry && event->path.mnt)
+ new_file = dentry_open(&event->path,
+ group->fanotify_data.f_flags | FMODE_NONOTIFY,
+ current_cred());
+ else
+ new_file = ERR_PTR(-EOVERFLOW);
+ if (IS_ERR(new_file)) {
+ /*
+ * we still send an event even if we can't open the file. this
+ * can happen when say tasks are gone and we try to open their
+ * /proc files or we try to open a WRONLY file like in sysfs
+ * we just send the errno to userspace since there isn't much
+ * else we can do.
+ */
+ put_unused_fd(client_fd);
+ client_fd = PTR_ERR(new_file);
+ } else {
+ *file = new_file;
+ }
+
+ return client_fd;
+}
+
+static int fill_event_metadata(struct fsnotify_group *group,
+ struct fanotify_event_metadata *metadata,
+ struct fsnotify_event *fsn_event,
+ struct file **file)
+{
+ int ret = 0;
+ struct fanotify_event_info *event;
+
+ pr_debug("%s: group=%p metadata=%p event=%p\n", __func__,
+ group, metadata, fsn_event);
+
+ *file = NULL;
+ event = container_of(fsn_event, struct fanotify_event_info, fse);
+ metadata->event_len = FAN_EVENT_METADATA_LEN;
+ metadata->metadata_len = FAN_EVENT_METADATA_LEN;
+ metadata->vers = FANOTIFY_METADATA_VERSION;
+ metadata->reserved = 0;
+ metadata->mask = fsn_event->mask & FAN_ALL_OUTGOING_EVENTS;
+ metadata->pid = pid_vnr(event->tgid);
+ if (unlikely(fsn_event->mask & FAN_Q_OVERFLOW))
+ metadata->fd = FAN_NOFD;
+ else {
+ metadata->fd = create_fd(group, event, file);
+ if (metadata->fd < 0)
+ ret = metadata->fd;
+ }
+
+ return ret;
+}
+
+static struct fanotify_perm_event_info *dequeue_event(
+ struct fsnotify_group *group, int fd)
+{
+ struct fanotify_perm_event_info *event, *return_e = NULL;
+
+ spin_lock(&group->notification_lock);
+ list_for_each_entry(event, &group->fanotify_data.access_list,
+ fae.fse.list) {
+ if (event->fd != fd)
+ continue;
+
+ list_del_init(&event->fae.fse.list);
+ return_e = event;
+ break;
+ }
+ spin_unlock(&group->notification_lock);
+
+ pr_debug("%s: found return_re=%p\n", __func__, return_e);
+
+ return return_e;
+}
+
+static int process_access_response(struct fsnotify_group *group,
+ struct fanotify_response *response_struct)
+{
+ struct fanotify_perm_event_info *event;
+ int fd = response_struct->fd;
+ int response = response_struct->response;
+
+ pr_debug("%s: group=%p fd=%d response=%d\n", __func__, group,
+ fd, response);
+ /*
+ * make sure the response is valid, if invalid we do nothing and either
+ * userspace can send a valid response or we will clean it up after the
+ * timeout
+ */
+ switch (response & ~FAN_AUDIT) {
+ case FAN_ALLOW:
+ case FAN_DENY:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (fd < 0)
+ return -EINVAL;
+
+ if ((response & FAN_AUDIT) && !group->fanotify_data.audit)
+ return -EINVAL;
+
+ event = dequeue_event(group, fd);
+ if (!event)
+ return -ENOENT;
+
+ event->response = response;
+ wake_up(&group->fanotify_data.access_waitq);
+
+ return 0;
+}
+
+static ssize_t copy_event_to_user(struct fsnotify_group *group,
+ struct fsnotify_event *event,
+ char __user *buf)
+{
+ struct fanotify_event_metadata fanotify_event_metadata;
+ struct file *f;
+ int fd, ret;
+
+ pr_debug("%s: group=%p event=%p\n", __func__, group, event);
+
+ ret = fill_event_metadata(group, &fanotify_event_metadata, event, &f);
+ if (ret < 0)
+ return ret;
+
+ fd = fanotify_event_metadata.fd;
+ ret = -EFAULT;
+ if (copy_to_user(buf, &fanotify_event_metadata,
+ fanotify_event_metadata.event_len))
+ goto out_close_fd;
+
+ if (fanotify_is_perm_event(event->mask))
+ FANOTIFY_PE(event)->fd = fd;
+
+ if (fd != FAN_NOFD)
+ fd_install(fd, f);
+ return fanotify_event_metadata.event_len;
+
+out_close_fd:
+ if (fd != FAN_NOFD) {
+ put_unused_fd(fd);
+ fput(f);
+ }
+ return ret;
+}
+
+/* intofiy userspace file descriptor functions */
+static __poll_t fanotify_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 ssize_t fanotify_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;
+
+ pr_debug("%s: group=%p\n", __func__, group);
+
+ 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);
+
+ if (IS_ERR(kevent)) {
+ ret = PTR_ERR(kevent);
+ break;
+ }
+
+ if (!kevent) {
+ 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);
+ continue;
+ }
+
+ ret = copy_event_to_user(group, kevent, buf);
+ if (unlikely(ret == -EOPENSTALE)) {
+ /*
+ * We cannot report events with stale fd so drop it.
+ * Setting ret to 0 will continue the event loop and
+ * do the right thing if there are no more events to
+ * read (i.e. return bytes read, -EAGAIN or wait).
+ */
+ ret = 0;
+ }
+
+ /*
+ * Permission events get queued to wait for response. Other
+ * events can be destroyed now.
+ */
+ if (!fanotify_is_perm_event(kevent->mask)) {
+ fsnotify_destroy_event(group, kevent);
+ } else {
+ if (ret <= 0) {
+ FANOTIFY_PE(kevent)->response = FAN_DENY;
+ wake_up(&group->fanotify_data.access_waitq);
+ } else {
+ spin_lock(&group->notification_lock);
+ list_add_tail(&kevent->list,
+ &group->fanotify_data.access_list);
+ spin_unlock(&group->notification_lock);
+ }
+ }
+ if (ret < 0)
+ break;
+ buf += ret;
+ count -= ret;
+ }
+ remove_wait_queue(&group->notification_waitq, &wait);
+
+ if (start != buf && ret != -EFAULT)
+ ret = buf - start;
+ return ret;
+}
+
+static ssize_t fanotify_write(struct file *file, const char __user *buf, size_t count, loff_t *pos)
+{
+ struct fanotify_response response = { .fd = -1, .response = -1 };
+ struct fsnotify_group *group;
+ int ret;
+
+ if (!IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS))
+ return -EINVAL;
+
+ group = file->private_data;
+
+ if (count > sizeof(response))
+ count = sizeof(response);
+
+ pr_debug("%s: group=%p count=%zu\n", __func__, group, count);
+
+ if (copy_from_user(&response, buf, count))
+ return -EFAULT;
+
+ ret = process_access_response(group, &response);
+ if (ret < 0)
+ count = ret;
+
+ return count;
+}
+
+static int fanotify_release(struct inode *ignored, struct file *file)
+{
+ struct fsnotify_group *group = file->private_data;
+ struct fanotify_perm_event_info *event, *next;
+ struct fsnotify_event *fsn_event;
+
+ /*
+ * Stop new events from arriving in the notification queue. since
+ * userspace cannot use fanotify fd anymore, no event can enter or
+ * leave access_list by now either.
+ */
+ fsnotify_group_stop_queueing(group);
+
+ /*
+ * Process all permission events on access_list and notification queue
+ * and simulate reply from userspace.
+ */
+ spin_lock(&group->notification_lock);
+ list_for_each_entry_safe(event, next, &group->fanotify_data.access_list,
+ fae.fse.list) {
+ pr_debug("%s: found group=%p event=%p\n", __func__, group,
+ event);
+
+ list_del_init(&event->fae.fse.list);
+ event->response = FAN_ALLOW;
+ }
+
+ /*
+ * Destroy all non-permission events. For permission events just
+ * dequeue them and set the response. They will be freed once the
+ * response is consumed and fanotify_get_response() returns.
+ */
+ while (!fsnotify_notify_queue_is_empty(group)) {
+ fsn_event = fsnotify_remove_first_event(group);
+ if (!(fsn_event->mask & FAN_ALL_PERM_EVENTS)) {
+ spin_unlock(&group->notification_lock);
+ fsnotify_destroy_event(group, fsn_event);
+ spin_lock(&group->notification_lock);
+ } else {
+ FANOTIFY_PE(fsn_event)->response = FAN_ALLOW;
+ }
+ }
+ spin_unlock(&group->notification_lock);
+
+ /* Response for all permission events it set, wakeup waiters */
+ wake_up(&group->fanotify_data.access_waitq);
+
+ /* matches the fanotify_init->fsnotify_alloc_group */
+ fsnotify_destroy_group(group);
+
+ return 0;
+}
+
+static long fanotify_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;
+
+ switch (cmd) {
+ case FIONREAD:
+ spin_lock(&group->notification_lock);
+ list_for_each_entry(fsn_event, &group->notification_list, list)
+ send_len += FAN_EVENT_METADATA_LEN;
+ spin_unlock(&group->notification_lock);
+ ret = put_user(send_len, (int __user *) p);
+ break;
+ }
+
+ return ret;
+}
+
+static const struct file_operations fanotify_fops = {
+ .show_fdinfo = fanotify_show_fdinfo,
+ .poll = fanotify_poll,
+ .read = fanotify_read,
+ .write = fanotify_write,
+ .fasync = NULL,
+ .release = fanotify_release,
+ .unlocked_ioctl = fanotify_ioctl,
+ .compat_ioctl = fanotify_ioctl,
+ .llseek = noop_llseek,
+};
+
+static int fanotify_find_path(int dfd, const char __user *filename,
+ struct path *path, unsigned int flags)
+{
+ int ret;
+
+ pr_debug("%s: dfd=%d filename=%p flags=%x\n", __func__,
+ dfd, filename, flags);
+
+ if (filename == NULL) {
+ struct fd f = fdget(dfd);
+
+ ret = -EBADF;
+ if (!f.file)
+ goto out;
+
+ ret = -ENOTDIR;
+ if ((flags & FAN_MARK_ONLYDIR) &&
+ !(S_ISDIR(file_inode(f.file)->i_mode))) {
+ fdput(f);
+ goto out;
+ }
+
+ *path = f.file->f_path;
+ path_get(path);
+ fdput(f);
+ } else {
+ unsigned int lookup_flags = 0;
+
+ if (!(flags & FAN_MARK_DONT_FOLLOW))
+ lookup_flags |= LOOKUP_FOLLOW;
+ if (flags & FAN_MARK_ONLYDIR)
+ lookup_flags |= LOOKUP_DIRECTORY;
+
+ ret = user_path_at(dfd, filename, lookup_flags, path);
+ if (ret)
+ goto out;
+ }
+
+ /* you can only watch an inode if you have read permissions on it */
+ ret = inode_permission(path->dentry->d_inode, MAY_READ);
+ if (ret)
+ path_put(path);
+out:
+ return ret;
+}
+
+static __u32 fanotify_mark_remove_from_mask(struct fsnotify_mark *fsn_mark,
+ __u32 mask,
+ unsigned int flags,
+ int *destroy)
+{
+ __u32 oldmask = 0;
+
+ spin_lock(&fsn_mark->lock);
+ if (!(flags & FAN_MARK_IGNORED_MASK)) {
+ __u32 tmask = fsn_mark->mask & ~mask;
+
+ if (flags & FAN_MARK_ONDIR)
+ tmask &= ~FAN_ONDIR;
+
+ oldmask = fsn_mark->mask;
+ fsn_mark->mask = tmask;
+ } else {
+ __u32 tmask = fsn_mark->ignored_mask & ~mask;
+ if (flags & FAN_MARK_ONDIR)
+ tmask &= ~FAN_ONDIR;
+ fsn_mark->ignored_mask = tmask;
+ }
+ *destroy = !(fsn_mark->mask | fsn_mark->ignored_mask);
+ spin_unlock(&fsn_mark->lock);
+
+ return mask & oldmask;
+}
+
+static int fanotify_remove_mark(struct fsnotify_group *group,
+ fsnotify_connp_t *connp, __u32 mask,
+ unsigned int flags)
+{
+ struct fsnotify_mark *fsn_mark = NULL;
+ __u32 removed;
+ int destroy_mark;
+
+ mutex_lock(&group->mark_mutex);
+ fsn_mark = fsnotify_find_mark(connp, group);
+ if (!fsn_mark) {
+ mutex_unlock(&group->mark_mutex);
+ return -ENOENT;
+ }
+
+ removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags,
+ &destroy_mark);
+ if (removed & fsnotify_conn_mask(fsn_mark->connector))
+ fsnotify_recalc_mask(fsn_mark->connector);
+ if (destroy_mark)
+ fsnotify_detach_mark(fsn_mark);
+ mutex_unlock(&group->mark_mutex);
+ if (destroy_mark)
+ fsnotify_free_mark(fsn_mark);
+
+ /* matches the fsnotify_find_mark() */
+ fsnotify_put_mark(fsn_mark);
+ return 0;
+}
+
+static int fanotify_remove_vfsmount_mark(struct fsnotify_group *group,
+ struct vfsmount *mnt, __u32 mask,
+ unsigned int flags)
+{
+ return fanotify_remove_mark(group, &real_mount(mnt)->mnt_fsnotify_marks,
+ mask, flags);
+}
+
+static int fanotify_remove_inode_mark(struct fsnotify_group *group,
+ struct inode *inode, __u32 mask,
+ unsigned int flags)
+{
+ return fanotify_remove_mark(group, &inode->i_fsnotify_marks, mask,
+ flags);
+}
+
+static __u32 fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark,
+ __u32 mask,
+ unsigned int flags)
+{
+ __u32 oldmask = -1;
+
+ spin_lock(&fsn_mark->lock);
+ if (!(flags & FAN_MARK_IGNORED_MASK)) {
+ __u32 tmask = fsn_mark->mask | mask;
+
+ if (flags & FAN_MARK_ONDIR)
+ tmask |= FAN_ONDIR;
+
+ oldmask = fsn_mark->mask;
+ fsn_mark->mask = tmask;
+ } else {
+ __u32 tmask = fsn_mark->ignored_mask | mask;
+ if (flags & FAN_MARK_ONDIR)
+ tmask |= FAN_ONDIR;
+
+ fsn_mark->ignored_mask = tmask;
+ if (flags & FAN_MARK_IGNORED_SURV_MODIFY)
+ fsn_mark->flags |= FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY;
+ }
+ spin_unlock(&fsn_mark->lock);
+
+ return mask & ~oldmask;
+}
+
+static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group,
+ fsnotify_connp_t *connp,
+ unsigned int type)
+{
+ struct fsnotify_mark *mark;
+ int ret;
+
+ if (atomic_read(&group->num_marks) > group->fanotify_data.max_marks)
+ return ERR_PTR(-ENOSPC);
+
+ mark = kmem_cache_alloc(fanotify_mark_cache, GFP_KERNEL);
+ if (!mark)
+ return ERR_PTR(-ENOMEM);
+
+ fsnotify_init_mark(mark, group);
+ ret = fsnotify_add_mark_locked(mark, connp, type, 0);
+ if (ret) {
+ fsnotify_put_mark(mark);
+ return ERR_PTR(ret);
+ }
+
+ return mark;
+}
+
+
+static int fanotify_add_mark(struct fsnotify_group *group,
+ fsnotify_connp_t *connp, unsigned int type,
+ __u32 mask, unsigned int flags)
+{
+ struct fsnotify_mark *fsn_mark;
+ __u32 added;
+
+ mutex_lock(&group->mark_mutex);
+ fsn_mark = fsnotify_find_mark(connp, group);
+ if (!fsn_mark) {
+ fsn_mark = fanotify_add_new_mark(group, connp, type);
+ if (IS_ERR(fsn_mark)) {
+ mutex_unlock(&group->mark_mutex);
+ return PTR_ERR(fsn_mark);
+ }
+ }
+ added = fanotify_mark_add_to_mask(fsn_mark, mask, flags);
+ if (added & ~fsnotify_conn_mask(fsn_mark->connector))
+ fsnotify_recalc_mask(fsn_mark->connector);
+ mutex_unlock(&group->mark_mutex);
+
+ fsnotify_put_mark(fsn_mark);
+ return 0;
+}
+
+static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
+ struct vfsmount *mnt, __u32 mask,
+ unsigned int flags)
+{
+ return fanotify_add_mark(group, &real_mount(mnt)->mnt_fsnotify_marks,
+ FSNOTIFY_OBJ_TYPE_VFSMOUNT, mask, flags);
+}
+
+static int fanotify_add_inode_mark(struct fsnotify_group *group,
+ struct inode *inode, __u32 mask,
+ unsigned int flags)
+{
+ pr_debug("%s: group=%p inode=%p\n", __func__, group, inode);
+
+ /*
+ * If some other task has this inode open for write we should not add
+ * an ignored mark, unless that ignored mark is supposed to survive
+ * modification changes anyway.
+ */
+ if ((flags & FAN_MARK_IGNORED_MASK) &&
+ !(flags & FAN_MARK_IGNORED_SURV_MODIFY) &&
+ (atomic_read(&inode->i_writecount) > 0))
+ return 0;
+
+ return fanotify_add_mark(group, &inode->i_fsnotify_marks,
+ FSNOTIFY_OBJ_TYPE_INODE, mask, flags);
+}
+
+/* fanotify syscalls */
+SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
+{
+ struct fsnotify_group *group;
+ int f_flags, fd;
+ struct user_struct *user;
+ struct fanotify_event_info *oevent;
+
+ pr_debug("%s: flags=%d event_f_flags=%d\n",
+ __func__, flags, event_f_flags);
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+#ifdef CONFIG_AUDITSYSCALL
+ if (flags & ~(FAN_ALL_INIT_FLAGS | FAN_ENABLE_AUDIT))
+#else
+ if (flags & ~FAN_ALL_INIT_FLAGS)
+#endif
+ return -EINVAL;
+
+ if (event_f_flags & ~FANOTIFY_INIT_ALL_EVENT_F_BITS)
+ return -EINVAL;
+
+ switch (event_f_flags & O_ACCMODE) {
+ case O_RDONLY:
+ case O_RDWR:
+ case O_WRONLY:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ user = get_current_user();
+ if (atomic_read(&user->fanotify_listeners) > FANOTIFY_DEFAULT_MAX_LISTENERS) {
+ free_uid(user);
+ return -EMFILE;
+ }
+
+ f_flags = O_RDWR | FMODE_NONOTIFY;
+ if (flags & FAN_CLOEXEC)
+ f_flags |= O_CLOEXEC;
+ if (flags & FAN_NONBLOCK)
+ f_flags |= O_NONBLOCK;
+
+ /* fsnotify_alloc_group takes a ref. Dropped in fanotify_release */
+ group = fsnotify_alloc_group(&fanotify_fsnotify_ops);
+ if (IS_ERR(group)) {
+ free_uid(user);
+ return PTR_ERR(group);
+ }
+
+ group->fanotify_data.user = user;
+ atomic_inc(&user->fanotify_listeners);
+ group->memcg = get_mem_cgroup_from_mm(current->mm);
+
+ oevent = fanotify_alloc_event(group, NULL, FS_Q_OVERFLOW, NULL);
+ if (unlikely(!oevent)) {
+ fd = -ENOMEM;
+ goto out_destroy_group;
+ }
+ group->overflow_event = &oevent->fse;
+
+ if (force_o_largefile())
+ event_f_flags |= O_LARGEFILE;
+ group->fanotify_data.f_flags = event_f_flags;
+ init_waitqueue_head(&group->fanotify_data.access_waitq);
+ INIT_LIST_HEAD(&group->fanotify_data.access_list);
+ switch (flags & FAN_ALL_CLASS_BITS) {
+ case FAN_CLASS_NOTIF:
+ group->priority = FS_PRIO_0;
+ break;
+ case FAN_CLASS_CONTENT:
+ group->priority = FS_PRIO_1;
+ break;
+ case FAN_CLASS_PRE_CONTENT:
+ group->priority = FS_PRIO_2;
+ break;
+ default:
+ fd = -EINVAL;
+ goto out_destroy_group;
+ }
+
+ if (flags & FAN_UNLIMITED_QUEUE) {
+ fd = -EPERM;
+ if (!capable(CAP_SYS_ADMIN))
+ goto out_destroy_group;
+ group->max_events = UINT_MAX;
+ } else {
+ group->max_events = FANOTIFY_DEFAULT_MAX_EVENTS;
+ }
+
+ if (flags & FAN_UNLIMITED_MARKS) {
+ fd = -EPERM;
+ if (!capable(CAP_SYS_ADMIN))
+ goto out_destroy_group;
+ group->fanotify_data.max_marks = UINT_MAX;
+ } else {
+ group->fanotify_data.max_marks = FANOTIFY_DEFAULT_MAX_MARKS;
+ }
+
+ if (flags & FAN_ENABLE_AUDIT) {
+ fd = -EPERM;
+ if (!capable(CAP_AUDIT_WRITE))
+ goto out_destroy_group;
+ group->fanotify_data.audit = true;
+ }
+
+ fd = anon_inode_getfd("[fanotify]", &fanotify_fops, group, f_flags);
+ if (fd < 0)
+ goto out_destroy_group;
+
+ return fd;
+
+out_destroy_group:
+ fsnotify_destroy_group(group);
+ return fd;
+}
+
+static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
+ int dfd, const char __user *pathname)
+{
+ struct inode *inode = NULL;
+ struct vfsmount *mnt = NULL;
+ struct fsnotify_group *group;
+ struct fd f;
+ struct path path;
+ u32 valid_mask = FAN_ALL_EVENTS | FAN_EVENT_ON_CHILD;
+ int ret;
+
+ pr_debug("%s: fanotify_fd=%d flags=%x dfd=%d pathname=%p mask=%llx\n",
+ __func__, fanotify_fd, flags, dfd, pathname, mask);
+
+ /* we only use the lower 32 bits as of right now. */
+ if (mask & ((__u64)0xffffffff << 32))
+ return -EINVAL;
+
+ if (flags & ~FAN_ALL_MARK_FLAGS)
+ return -EINVAL;
+ switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE | FAN_MARK_FLUSH)) {
+ case FAN_MARK_ADD: /* fallthrough */
+ case FAN_MARK_REMOVE:
+ if (!mask)
+ return -EINVAL;
+ break;
+ case FAN_MARK_FLUSH:
+ if (flags & ~(FAN_MARK_MOUNT | FAN_MARK_FLUSH))
+ return -EINVAL;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (mask & FAN_ONDIR) {
+ flags |= FAN_MARK_ONDIR;
+ mask &= ~FAN_ONDIR;
+ }
+
+ if (IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS))
+ valid_mask |= FAN_ALL_PERM_EVENTS;
+
+ if (mask & ~valid_mask)
+ return -EINVAL;
+
+ f = fdget(fanotify_fd);
+ if (unlikely(!f.file))
+ return -EBADF;
+
+ /* verify that this is indeed an fanotify instance */
+ ret = -EINVAL;
+ if (unlikely(f.file->f_op != &fanotify_fops))
+ goto fput_and_out;
+ group = f.file->private_data;
+
+ /*
+ * group->priority == FS_PRIO_0 == FAN_CLASS_NOTIF. These are not
+ * allowed to set permissions events.
+ */
+ ret = -EINVAL;
+ if (mask & FAN_ALL_PERM_EVENTS &&
+ group->priority == FS_PRIO_0)
+ goto fput_and_out;
+
+ if (flags & FAN_MARK_FLUSH) {
+ ret = 0;
+ if (flags & FAN_MARK_MOUNT)
+ fsnotify_clear_vfsmount_marks_by_group(group);
+ else
+ fsnotify_clear_inode_marks_by_group(group);
+ goto fput_and_out;
+ }
+
+ ret = fanotify_find_path(dfd, pathname, &path, flags);
+ if (ret)
+ goto fput_and_out;
+
+ /* inode held in place by reference to path; group by fget on fd */
+ if (!(flags & FAN_MARK_MOUNT))
+ inode = path.dentry->d_inode;
+ else
+ mnt = path.mnt;
+
+ /* create/update an inode mark */
+ switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE)) {
+ case FAN_MARK_ADD:
+ if (flags & FAN_MARK_MOUNT)
+ ret = fanotify_add_vfsmount_mark(group, mnt, mask, flags);
+ else
+ ret = fanotify_add_inode_mark(group, inode, mask, flags);
+ break;
+ case FAN_MARK_REMOVE:
+ if (flags & FAN_MARK_MOUNT)
+ ret = fanotify_remove_vfsmount_mark(group, mnt, mask, flags);
+ else
+ ret = fanotify_remove_inode_mark(group, inode, mask, flags);
+ break;
+ default:
+ ret = -EINVAL;
+ }
+
+ path_put(&path);
+fput_and_out:
+ fdput(f);
+ return ret;
+}
+
+SYSCALL_DEFINE5(fanotify_mark, int, fanotify_fd, unsigned int, flags,
+ __u64, mask, int, dfd,
+ const char __user *, pathname)
+{
+ return do_fanotify_mark(fanotify_fd, flags, mask, dfd, pathname);
+}
+
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE6(fanotify_mark,
+ int, fanotify_fd, unsigned int, flags,
+ __u32, mask0, __u32, mask1, int, dfd,
+ const char __user *, pathname)
+{
+ return do_fanotify_mark(fanotify_fd, flags,
+#ifdef __BIG_ENDIAN
+ ((__u64)mask0 << 32) | mask1,
+#else
+ ((__u64)mask1 << 32) | mask0,
+#endif
+ dfd, pathname);
+}
+#endif
+
+/*
+ * fanotify_user_setup - Our initialization function. Note that we cannot return
+ * error because we have compiled-in VFS hooks. So an (unlikely) failure here
+ * must result in panic().
+ */
+static int __init fanotify_user_setup(void)
+{
+ fanotify_mark_cache = KMEM_CACHE(fsnotify_mark,
+ SLAB_PANIC|SLAB_ACCOUNT);
+ fanotify_event_cachep = KMEM_CACHE(fanotify_event_info, SLAB_PANIC);
+ if (IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS)) {
+ fanotify_perm_event_cachep =
+ KMEM_CACHE(fanotify_perm_event_info, SLAB_PANIC);
+ }
+
+ return 0;
+}
+device_initcall(fanotify_user_setup);
diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c
new file mode 100644
index 0000000..86fcf58
--- /dev/null
+++ b/fs/notify/fdinfo.c
@@ -0,0 +1,173 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/fsnotify_backend.h>
+#include <linux/idr.h>
+#include <linux/init.h>
+#include <linux/inotify.h>
+#include <linux/fanotify.h>
+#include <linux/kernel.h>
+#include <linux/namei.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/seq_file.h>
+#include <linux/proc_fs.h>
+#include <linux/exportfs.h>
+
+#include "inotify/inotify.h"
+#include "fsnotify.h"
+
+#if defined(CONFIG_PROC_FS)
+
+#if defined(CONFIG_INOTIFY_USER) || defined(CONFIG_FANOTIFY)
+
+static void show_fdinfo(struct seq_file *m, struct file *f,
+ void (*show)(struct seq_file *m,
+ struct fsnotify_mark *mark))
+{
+ struct fsnotify_group *group = f->private_data;
+ struct fsnotify_mark *mark;
+
+ mutex_lock(&group->mark_mutex);
+ list_for_each_entry(mark, &group->marks_list, g_list) {
+ show(m, mark);
+ if (seq_has_overflowed(m))
+ break;
+ }
+ mutex_unlock(&group->mark_mutex);
+}
+
+#if defined(CONFIG_EXPORTFS)
+static void show_mark_fhandle(struct seq_file *m, struct inode *inode)
+{
+ struct {
+ struct file_handle handle;
+ u8 pad[MAX_HANDLE_SZ];
+ } f;
+ int size, ret, i;
+
+ f.handle.handle_bytes = sizeof(f.pad);
+ size = f.handle.handle_bytes >> 2;
+
+ ret = exportfs_encode_inode_fh(inode, (struct fid *)f.handle.f_handle, &size, 0);
+ if ((ret == FILEID_INVALID) || (ret < 0)) {
+ WARN_ONCE(1, "Can't encode file handler for inotify: %d\n", ret);
+ return;
+ }
+
+ f.handle.handle_type = ret;
+ f.handle.handle_bytes = size * sizeof(u32);
+
+ seq_printf(m, "fhandle-bytes:%x fhandle-type:%x f_handle:",
+ f.handle.handle_bytes, f.handle.handle_type);
+
+ for (i = 0; i < f.handle.handle_bytes; i++)
+ seq_printf(m, "%02x", (int)f.handle.f_handle[i]);
+}
+#else
+static void show_mark_fhandle(struct seq_file *m, struct inode *inode)
+{
+}
+#endif
+
+#ifdef CONFIG_INOTIFY_USER
+
+static void inotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
+{
+ struct inotify_inode_mark *inode_mark;
+ struct inode *inode;
+
+ if (mark->connector->type != FSNOTIFY_OBJ_TYPE_INODE)
+ return;
+
+ inode_mark = container_of(mark, struct inotify_inode_mark, fsn_mark);
+ inode = igrab(fsnotify_conn_inode(mark->connector));
+ if (inode) {
+ /*
+ * IN_ALL_EVENTS represents all of the mask bits
+ * that we expose to userspace. There is at
+ * least one bit (FS_EVENT_ON_CHILD) which is
+ * used only internally to the kernel.
+ */
+ u32 mask = mark->mask & IN_ALL_EVENTS;
+ seq_printf(m, "inotify wd:%x ino:%lx sdev:%x mask:%x ignored_mask:%x ",
+ inode_mark->wd, inode->i_ino, inode->i_sb->s_dev,
+ mask, mark->ignored_mask);
+ show_mark_fhandle(m, inode);
+ seq_putc(m, '\n');
+ iput(inode);
+ }
+}
+
+void inotify_show_fdinfo(struct seq_file *m, struct file *f)
+{
+ show_fdinfo(m, f, inotify_fdinfo);
+}
+
+#endif /* CONFIG_INOTIFY_USER */
+
+#ifdef CONFIG_FANOTIFY
+
+static void fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
+{
+ unsigned int mflags = 0;
+ struct inode *inode;
+
+ if (mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)
+ mflags |= FAN_MARK_IGNORED_SURV_MODIFY;
+
+ if (mark->connector->type == FSNOTIFY_OBJ_TYPE_INODE) {
+ inode = igrab(fsnotify_conn_inode(mark->connector));
+ if (!inode)
+ return;
+ seq_printf(m, "fanotify ino:%lx sdev:%x mflags:%x mask:%x ignored_mask:%x ",
+ inode->i_ino, inode->i_sb->s_dev,
+ mflags, mark->mask, mark->ignored_mask);
+ show_mark_fhandle(m, inode);
+ seq_putc(m, '\n');
+ iput(inode);
+ } else if (mark->connector->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) {
+ struct mount *mnt = fsnotify_conn_mount(mark->connector);
+
+ seq_printf(m, "fanotify mnt_id:%x mflags:%x mask:%x ignored_mask:%x\n",
+ mnt->mnt_id, mflags, mark->mask, mark->ignored_mask);
+ }
+}
+
+void fanotify_show_fdinfo(struct seq_file *m, struct file *f)
+{
+ struct fsnotify_group *group = f->private_data;
+ unsigned int flags = 0;
+
+ switch (group->priority) {
+ case FS_PRIO_0:
+ flags |= FAN_CLASS_NOTIF;
+ break;
+ case FS_PRIO_1:
+ flags |= FAN_CLASS_CONTENT;
+ break;
+ case FS_PRIO_2:
+ flags |= FAN_CLASS_PRE_CONTENT;
+ break;
+ }
+
+ if (group->max_events == UINT_MAX)
+ flags |= FAN_UNLIMITED_QUEUE;
+
+ if (group->fanotify_data.max_marks == UINT_MAX)
+ flags |= FAN_UNLIMITED_MARKS;
+
+ if (group->fanotify_data.audit)
+ flags |= FAN_ENABLE_AUDIT;
+
+ seq_printf(m, "fanotify flags:%x event-flags:%x\n",
+ flags, group->fanotify_data.f_flags);
+
+ show_fdinfo(m, f, fanotify_fdinfo);
+}
+
+#endif /* CONFIG_FANOTIFY */
+
+#endif /* CONFIG_INOTIFY_USER || CONFIG_FANOTIFY */
+
+#endif /* CONFIG_PROC_FS */
diff --git a/fs/notify/fdinfo.h b/fs/notify/fdinfo.h
new file mode 100644
index 0000000..5c9937e
--- /dev/null
+++ b/fs/notify/fdinfo.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __FSNOTIFY_FDINFO_H__
+#define __FSNOTIFY_FDINFO_H__
+
+#include <linux/errno.h>
+#include <linux/proc_fs.h>
+
+struct seq_file;
+struct file;
+
+#ifdef CONFIG_PROC_FS
+
+#ifdef CONFIG_INOTIFY_USER
+void inotify_show_fdinfo(struct seq_file *m, struct file *f);
+#endif
+
+#ifdef CONFIG_FANOTIFY
+void fanotify_show_fdinfo(struct seq_file *m, struct file *f);
+#endif
+
+#else /* CONFIG_PROC_FS */
+
+#define inotify_show_fdinfo NULL
+#define fanotify_show_fdinfo NULL
+
+#endif /* CONFIG_PROC_FS */
+
+#endif /* __FSNOTIFY_FDINFO_H__ */
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
new file mode 100644
index 0000000..170a733
--- /dev/null
+++ b/fs/notify/fsnotify.c
@@ -0,0 +1,406 @@
+/*
+ * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
+ *
+ * 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
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; see the file COPYING. If not, write to
+ * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include <linux/dcache.h>
+#include <linux/fs.h>
+#include <linux/gfp.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mount.h>
+#include <linux/srcu.h>
+
+#include <linux/fsnotify_backend.h>
+#include "fsnotify.h"
+
+/*
+ * Clear all of the marks on an inode when it is being evicted from core
+ */
+void __fsnotify_inode_delete(struct inode *inode)
+{
+ fsnotify_clear_marks_by_inode(inode);
+}
+EXPORT_SYMBOL_GPL(__fsnotify_inode_delete);
+
+void __fsnotify_vfsmount_delete(struct vfsmount *mnt)
+{
+ fsnotify_clear_marks_by_mount(mnt);
+}
+
+/**
+ * fsnotify_unmount_inodes - an sb is unmounting. handle any watched inodes.
+ * @sb: superblock being unmounted.
+ *
+ * Called during unmount with no locks held, so needs to be safe against
+ * concurrent modifiers. We temporarily drop sb->s_inode_list_lock and CAN block.
+ */
+void fsnotify_unmount_inodes(struct super_block *sb)
+{
+ struct inode *inode, *iput_inode = NULL;
+
+ spin_lock(&sb->s_inode_list_lock);
+ list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+ /*
+ * We cannot __iget() an inode in state I_FREEING,
+ * I_WILL_FREE, or I_NEW which is fine because by that point
+ * the inode cannot have any associated watches.
+ */
+ spin_lock(&inode->i_lock);
+ if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) {
+ spin_unlock(&inode->i_lock);
+ continue;
+ }
+
+ /*
+ * If i_count is zero, the inode cannot have any watches and
+ * doing an __iget/iput with SB_ACTIVE clear would actually
+ * evict all inodes with zero i_count from icache which is
+ * unnecessarily violent and may in fact be illegal to do.
+ */
+ if (!atomic_read(&inode->i_count)) {
+ spin_unlock(&inode->i_lock);
+ continue;
+ }
+
+ __iget(inode);
+ spin_unlock(&inode->i_lock);
+ spin_unlock(&sb->s_inode_list_lock);
+
+ if (iput_inode)
+ iput(iput_inode);
+
+ /* for each watch, send FS_UNMOUNT and then remove it */
+ fsnotify(inode, FS_UNMOUNT, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+
+ fsnotify_inode_delete(inode);
+
+ iput_inode = inode;
+
+ spin_lock(&sb->s_inode_list_lock);
+ }
+ spin_unlock(&sb->s_inode_list_lock);
+
+ if (iput_inode)
+ iput(iput_inode);
+ /* Wait for outstanding inode references from connectors */
+ wait_var_event(&sb->s_fsnotify_inode_refs,
+ !atomic_long_read(&sb->s_fsnotify_inode_refs));
+}
+
+/*
+ * Given an inode, first check if we care what happens to our children. Inotify
+ * and dnotify both tell their parents about events. If we care about any event
+ * on a child we run all of our children and set a dentry flag saying that the
+ * parent cares. Thus when an event happens on a child it can quickly tell if
+ * if there is a need to find a parent and send the event to the parent.
+ */
+void __fsnotify_update_child_dentry_flags(struct inode *inode)
+{
+ struct dentry *alias;
+ int watched;
+
+ if (!S_ISDIR(inode->i_mode))
+ return;
+
+ /* determine if the children should tell inode about their events */
+ watched = fsnotify_inode_watches_children(inode);
+
+ spin_lock(&inode->i_lock);
+ /* run all of the dentries associated with this inode. Since this is a
+ * directory, there damn well better only be one item on this list */
+ hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
+ struct dentry *child;
+
+ /* run all of the children of the original inode and fix their
+ * d_flags to indicate parental interest (their parent is the
+ * original inode) */
+ spin_lock(&alias->d_lock);
+ list_for_each_entry(child, &alias->d_subdirs, d_child) {
+ if (!child->d_inode)
+ continue;
+
+ spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED);
+ if (watched)
+ child->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED;
+ else
+ child->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED;
+ spin_unlock(&child->d_lock);
+ }
+ spin_unlock(&alias->d_lock);
+ }
+ spin_unlock(&inode->i_lock);
+}
+
+/* Notify this dentry's parent about a child's events. */
+int __fsnotify_parent(const struct path *path, struct dentry *dentry, __u32 mask)
+{
+ struct dentry *parent;
+ struct inode *p_inode;
+ int ret = 0;
+
+ if (!dentry)
+ dentry = path->dentry;
+
+ if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED))
+ return 0;
+
+ parent = dget_parent(dentry);
+ p_inode = parent->d_inode;
+
+ if (unlikely(!fsnotify_inode_watches_children(p_inode))) {
+ __fsnotify_update_child_dentry_flags(p_inode);
+ } else if (p_inode->i_fsnotify_mask & mask & ALL_FSNOTIFY_EVENTS) {
+ struct name_snapshot name;
+
+ /* we are notifying a parent so come up with the new mask which
+ * specifies these are events which came from a child. */
+ mask |= FS_EVENT_ON_CHILD;
+
+ take_dentry_name_snapshot(&name, dentry);
+ if (path)
+ ret = fsnotify(p_inode, mask, path, FSNOTIFY_EVENT_PATH,
+ name.name, 0);
+ else
+ ret = fsnotify(p_inode, mask, dentry->d_inode, FSNOTIFY_EVENT_INODE,
+ name.name, 0);
+ release_dentry_name_snapshot(&name);
+ }
+
+ dput(parent);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(__fsnotify_parent);
+
+static int send_to_group(struct inode *to_tell,
+ __u32 mask, const void *data,
+ int data_is, u32 cookie,
+ const unsigned char *file_name,
+ struct fsnotify_iter_info *iter_info)
+{
+ struct fsnotify_group *group = NULL;
+ __u32 test_mask = (mask & ALL_FSNOTIFY_EVENTS);
+ __u32 marks_mask = 0;
+ __u32 marks_ignored_mask = 0;
+ struct fsnotify_mark *mark;
+ int type;
+
+ if (WARN_ON(!iter_info->report_mask))
+ return 0;
+
+ /* clear ignored on inode modification */
+ if (mask & FS_MODIFY) {
+ fsnotify_foreach_obj_type(type) {
+ if (!fsnotify_iter_should_report_type(iter_info, type))
+ continue;
+ mark = iter_info->marks[type];
+ if (mark &&
+ !(mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY))
+ mark->ignored_mask = 0;
+ }
+ }
+
+ fsnotify_foreach_obj_type(type) {
+ if (!fsnotify_iter_should_report_type(iter_info, type))
+ continue;
+ mark = iter_info->marks[type];
+ /* does the object mark tell us to do something? */
+ if (mark) {
+ group = mark->group;
+ marks_mask |= mark->mask;
+ marks_ignored_mask |= mark->ignored_mask;
+ }
+ }
+
+ pr_debug("%s: group=%p to_tell=%p mask=%x marks_mask=%x marks_ignored_mask=%x"
+ " data=%p data_is=%d cookie=%d\n",
+ __func__, group, to_tell, mask, marks_mask, marks_ignored_mask,
+ data, data_is, cookie);
+
+ if (!(test_mask & marks_mask & ~marks_ignored_mask))
+ return 0;
+
+ return group->ops->handle_event(group, to_tell, mask, data, data_is,
+ file_name, cookie, iter_info);
+}
+
+static struct fsnotify_mark *fsnotify_first_mark(struct fsnotify_mark_connector **connp)
+{
+ struct fsnotify_mark_connector *conn;
+ struct hlist_node *node = NULL;
+
+ conn = srcu_dereference(*connp, &fsnotify_mark_srcu);
+ if (conn)
+ node = srcu_dereference(conn->list.first, &fsnotify_mark_srcu);
+
+ return hlist_entry_safe(node, struct fsnotify_mark, obj_list);
+}
+
+static struct fsnotify_mark *fsnotify_next_mark(struct fsnotify_mark *mark)
+{
+ struct hlist_node *node = NULL;
+
+ if (mark)
+ node = srcu_dereference(mark->obj_list.next,
+ &fsnotify_mark_srcu);
+
+ return hlist_entry_safe(node, struct fsnotify_mark, obj_list);
+}
+
+/*
+ * iter_info is a multi head priority queue of marks.
+ * Pick a subset of marks from queue heads, all with the
+ * same group and set the report_mask for selected subset.
+ * Returns the report_mask of the selected subset.
+ */
+static unsigned int fsnotify_iter_select_report_types(
+ struct fsnotify_iter_info *iter_info)
+{
+ struct fsnotify_group *max_prio_group = NULL;
+ struct fsnotify_mark *mark;
+ int type;
+
+ /* Choose max prio group among groups of all queue heads */
+ fsnotify_foreach_obj_type(type) {
+ mark = iter_info->marks[type];
+ if (mark &&
+ fsnotify_compare_groups(max_prio_group, mark->group) > 0)
+ max_prio_group = mark->group;
+ }
+
+ if (!max_prio_group)
+ return 0;
+
+ /* Set the report mask for marks from same group as max prio group */
+ iter_info->report_mask = 0;
+ fsnotify_foreach_obj_type(type) {
+ mark = iter_info->marks[type];
+ if (mark &&
+ fsnotify_compare_groups(max_prio_group, mark->group) == 0)
+ fsnotify_iter_set_report_type(iter_info, type);
+ }
+
+ return iter_info->report_mask;
+}
+
+/*
+ * Pop from iter_info multi head queue, the marks that were iterated in the
+ * current iteration step.
+ */
+static void fsnotify_iter_next(struct fsnotify_iter_info *iter_info)
+{
+ int type;
+
+ fsnotify_foreach_obj_type(type) {
+ if (fsnotify_iter_should_report_type(iter_info, type))
+ iter_info->marks[type] =
+ fsnotify_next_mark(iter_info->marks[type]);
+ }
+}
+
+/*
+ * This is the main call to fsnotify. The VFS calls into hook specific functions
+ * in linux/fsnotify.h. Those functions then in turn call here. Here will call
+ * out to all of the registered fsnotify_group. Those groups can then use the
+ * notification event in whatever means they feel necessary.
+ */
+int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is,
+ const unsigned char *file_name, u32 cookie)
+{
+ struct fsnotify_iter_info iter_info = {};
+ struct mount *mnt;
+ int ret = 0;
+ __u32 test_mask = (mask & ALL_FSNOTIFY_EVENTS);
+
+ if (data_is == FSNOTIFY_EVENT_PATH)
+ mnt = real_mount(((const struct path *)data)->mnt);
+ else
+ mnt = NULL;
+
+ /* An event "on child" is not intended for a mount mark */
+ if (mask & FS_EVENT_ON_CHILD)
+ mnt = NULL;
+
+ /*
+ * Optimization: srcu_read_lock() has a memory barrier which can
+ * be expensive. It protects walking the *_fsnotify_marks lists.
+ * However, if we do not walk the lists, we do not have to do
+ * SRCU because we have no references to any objects and do not
+ * need SRCU to keep them "alive".
+ */
+ if (!to_tell->i_fsnotify_marks &&
+ (!mnt || !mnt->mnt_fsnotify_marks))
+ return 0;
+ /*
+ * if this is a modify event we may need to clear the ignored masks
+ * otherwise return if neither the inode nor the vfsmount care about
+ * this type of event.
+ */
+ if (!(mask & FS_MODIFY) &&
+ !(test_mask & to_tell->i_fsnotify_mask) &&
+ !(mnt && test_mask & mnt->mnt_fsnotify_mask))
+ return 0;
+
+ iter_info.srcu_idx = srcu_read_lock(&fsnotify_mark_srcu);
+
+ iter_info.marks[FSNOTIFY_OBJ_TYPE_INODE] =
+ fsnotify_first_mark(&to_tell->i_fsnotify_marks);
+ if (mnt) {
+ iter_info.marks[FSNOTIFY_OBJ_TYPE_VFSMOUNT] =
+ fsnotify_first_mark(&mnt->mnt_fsnotify_marks);
+ }
+
+ /*
+ * We need to merge inode & vfsmount mark lists so that inode mark
+ * ignore masks are properly reflected for mount mark notifications.
+ * That's why this traversal is so complicated...
+ */
+ while (fsnotify_iter_select_report_types(&iter_info)) {
+ ret = send_to_group(to_tell, mask, data, data_is, cookie,
+ file_name, &iter_info);
+
+ if (ret && (mask & ALL_FSNOTIFY_PERM_EVENTS))
+ goto out;
+
+ fsnotify_iter_next(&iter_info);
+ }
+ ret = 0;
+out:
+ srcu_read_unlock(&fsnotify_mark_srcu, iter_info.srcu_idx);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(fsnotify);
+
+extern struct kmem_cache *fsnotify_mark_connector_cachep;
+
+static __init int fsnotify_init(void)
+{
+ int ret;
+
+ BUG_ON(hweight32(ALL_FSNOTIFY_BITS) != 23);
+
+ ret = init_srcu_struct(&fsnotify_mark_srcu);
+ if (ret)
+ panic("initializing fsnotify_mark_srcu");
+
+ fsnotify_mark_connector_cachep = KMEM_CACHE(fsnotify_mark_connector,
+ SLAB_PANIC);
+
+ return 0;
+}
+core_initcall(fsnotify_init);
diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h
new file mode 100644
index 0000000..7902653
--- /dev/null
+++ b/fs/notify/fsnotify.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __FS_NOTIFY_FSNOTIFY_H_
+#define __FS_NOTIFY_FSNOTIFY_H_
+
+#include <linux/list.h>
+#include <linux/fsnotify.h>
+#include <linux/srcu.h>
+#include <linux/types.h>
+
+#include "../mount.h"
+
+static inline struct inode *fsnotify_conn_inode(
+ struct fsnotify_mark_connector *conn)
+{
+ return container_of(conn->obj, struct inode, i_fsnotify_marks);
+}
+
+static inline struct mount *fsnotify_conn_mount(
+ struct fsnotify_mark_connector *conn)
+{
+ return container_of(conn->obj, struct mount, mnt_fsnotify_marks);
+}
+
+/* destroy all events sitting in this groups notification queue */
+extern void fsnotify_flush_notify(struct fsnotify_group *group);
+
+/* protects reads of inode and vfsmount marks list */
+extern struct srcu_struct fsnotify_mark_srcu;
+
+/* compare two groups for sorting of marks lists */
+extern int fsnotify_compare_groups(struct fsnotify_group *a,
+ struct fsnotify_group *b);
+
+/* Destroy all marks attached to an object via connector */
+extern void fsnotify_destroy_marks(fsnotify_connp_t *connp);
+/* run the list of all marks associated with inode and destroy them */
+static inline void fsnotify_clear_marks_by_inode(struct inode *inode)
+{
+ fsnotify_destroy_marks(&inode->i_fsnotify_marks);
+}
+/* run the list of all marks associated with vfsmount and destroy them */
+static inline void fsnotify_clear_marks_by_mount(struct vfsmount *mnt)
+{
+ fsnotify_destroy_marks(&real_mount(mnt)->mnt_fsnotify_marks);
+}
+/* Wait until all marks queued for destruction are destroyed */
+extern void fsnotify_wait_marks_destroyed(void);
+
+/*
+ * update the dentry->d_flags of all of inode's children to indicate if inode cares
+ * about events that happen to its children.
+ */
+extern void __fsnotify_update_child_dentry_flags(struct inode *inode);
+
+/* allocate and destroy and event holder to attach events to notification/access queues */
+extern struct fsnotify_event_holder *fsnotify_alloc_event_holder(void);
+extern void fsnotify_destroy_event_holder(struct fsnotify_event_holder *holder);
+
+#endif /* __FS_NOTIFY_FSNOTIFY_H_ */
diff --git a/fs/notify/group.c b/fs/notify/group.c
new file mode 100644
index 0000000..c03b836
--- /dev/null
+++ b/fs/notify/group.c
@@ -0,0 +1,159 @@
+/*
+ * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
+ *
+ * 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
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; see the file COPYING. If not, write to
+ * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/srcu.h>
+#include <linux/rculist.h>
+#include <linux/wait.h>
+#include <linux/memcontrol.h>
+
+#include <linux/fsnotify_backend.h>
+#include "fsnotify.h"
+
+#include <linux/atomic.h>
+
+/*
+ * Final freeing of a group
+ */
+static void fsnotify_final_destroy_group(struct fsnotify_group *group)
+{
+ if (group->ops->free_group_priv)
+ group->ops->free_group_priv(group);
+
+ mem_cgroup_put(group->memcg);
+
+ kfree(group);
+}
+
+/*
+ * Stop queueing new events for this group. Once this function returns
+ * fsnotify_add_event() will not add any new events to the group's queue.
+ */
+void fsnotify_group_stop_queueing(struct fsnotify_group *group)
+{
+ spin_lock(&group->notification_lock);
+ group->shutdown = true;
+ spin_unlock(&group->notification_lock);
+}
+
+/*
+ * Trying to get rid of a group. Remove all marks, flush all events and release
+ * the group reference.
+ * Note that another thread calling fsnotify_clear_marks_by_group() may still
+ * hold a ref to the group.
+ */
+void fsnotify_destroy_group(struct fsnotify_group *group)
+{
+ /*
+ * Stop queueing new events. The code below is careful enough to not
+ * require this but fanotify needs to stop queuing events even before
+ * fsnotify_destroy_group() is called and this makes the other callers
+ * of fsnotify_destroy_group() to see the same behavior.
+ */
+ fsnotify_group_stop_queueing(group);
+
+ /* Clear all marks for this group and queue them for destruction */
+ fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_ALL_TYPES_MASK);
+
+ /*
+ * Some marks can still be pinned when waiting for response from
+ * userspace. Wait for those now. fsnotify_prepare_user_wait() will
+ * not succeed now so this wait is race-free.
+ */
+ wait_event(group->notification_waitq, !atomic_read(&group->user_waits));
+
+ /*
+ * Wait until all marks get really destroyed. We could actually destroy
+ * them ourselves instead of waiting for worker to do it, however that
+ * would be racy as worker can already be processing some marks before
+ * we even entered fsnotify_destroy_group().
+ */
+ fsnotify_wait_marks_destroyed();
+
+ /*
+ * Since we have waited for fsnotify_mark_srcu in
+ * fsnotify_mark_destroy_list() there can be no outstanding event
+ * notification against this group. So clearing the notification queue
+ * of all events is reliable now.
+ */
+ fsnotify_flush_notify(group);
+
+ /*
+ * Destroy overflow event (we cannot use fsnotify_destroy_event() as
+ * that deliberately ignores overflow events.
+ */
+ if (group->overflow_event)
+ group->ops->free_event(group->overflow_event);
+
+ fsnotify_put_group(group);
+}
+
+/*
+ * Get reference to a group.
+ */
+void fsnotify_get_group(struct fsnotify_group *group)
+{
+ refcount_inc(&group->refcnt);
+}
+
+/*
+ * Drop a reference to a group. Free it if it's through.
+ */
+void fsnotify_put_group(struct fsnotify_group *group)
+{
+ if (refcount_dec_and_test(&group->refcnt))
+ fsnotify_final_destroy_group(group);
+}
+
+/*
+ * Create a new fsnotify_group and hold a reference for the group returned.
+ */
+struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops)
+{
+ struct fsnotify_group *group;
+
+ group = kzalloc(sizeof(struct fsnotify_group), GFP_KERNEL);
+ if (!group)
+ return ERR_PTR(-ENOMEM);
+
+ /* set to 0 when there a no external references to this group */
+ refcount_set(&group->refcnt, 1);
+ atomic_set(&group->num_marks, 0);
+ atomic_set(&group->user_waits, 0);
+
+ spin_lock_init(&group->notification_lock);
+ INIT_LIST_HEAD(&group->notification_list);
+ init_waitqueue_head(&group->notification_waitq);
+ group->max_events = UINT_MAX;
+
+ mutex_init(&group->mark_mutex);
+ INIT_LIST_HEAD(&group->marks_list);
+
+ group->ops = ops;
+
+ return group;
+}
+
+int fsnotify_fasync(int fd, struct file *file, int on)
+{
+ struct fsnotify_group *group = file->private_data;
+
+ return fasync_helper(fd, file, on, &group->fsn_fa) >= 0 ? 0 : -EIO;
+}
diff --git a/fs/notify/inotify/Kconfig b/fs/notify/inotify/Kconfig
new file mode 100644
index 0000000..b981fc0
--- /dev/null
+++ b/fs/notify/inotify/Kconfig
@@ -0,0 +1,17 @@
+config INOTIFY_USER
+ bool "Inotify support for userspace"
+ select ANON_INODES
+ select FSNOTIFY
+ default y
+ ---help---
+ Say Y here to enable inotify support for userspace, including the
+ associated system calls. Inotify allows monitoring of both files and
+ directories via a single open fd. Events are read from the file
+ descriptor, which is also select()- and poll()-able.
+ Inotify fixes numerous shortcomings in dnotify and introduces several
+ new features including multiple file events, one-shot support, and
+ unmount notification.
+
+ For more information, see <file:Documentation/filesystems/inotify.txt>
+
+ If unsure, say Y.
diff --git a/fs/notify/inotify/Makefile b/fs/notify/inotify/Makefile
new file mode 100644
index 0000000..a380dab
--- /dev/null
+++ b/fs/notify/inotify/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_INOTIFY_USER) += inotify_fsnotify.o inotify_user.o
diff --git a/fs/notify/inotify/inotify.h b/fs/notify/inotify/inotify.h
new file mode 100644
index 0000000..7e4578d
--- /dev/null
+++ b/fs/notify/inotify/inotify.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/fsnotify_backend.h>
+#include <linux/inotify.h>
+#include <linux/slab.h> /* struct kmem_cache */
+
+struct inotify_event_info {
+ struct fsnotify_event fse;
+ int wd;
+ u32 sync_cookie;
+ int name_len;
+ char name[];
+};
+
+struct inotify_inode_mark {
+ struct fsnotify_mark fsn_mark;
+ int wd;
+};
+
+static inline struct inotify_event_info *INOTIFY_E(struct fsnotify_event *fse)
+{
+ return container_of(fse, struct inotify_event_info, fse);
+}
+
+extern void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark,
+ struct fsnotify_group *group);
+extern int inotify_handle_event(struct fsnotify_group *group,
+ struct inode *inode,
+ u32 mask, const void *data, int data_type,
+ const unsigned char *file_name, u32 cookie,
+ struct fsnotify_iter_info *iter_info);
+
+extern const struct fsnotify_ops inotify_fsnotify_ops;
+extern struct kmem_cache *inotify_inode_mark_cachep;
+
+#ifdef CONFIG_INOTIFY_USER
+static inline void dec_inotify_instances(struct ucounts *ucounts)
+{
+ dec_ucount(ucounts, UCOUNT_INOTIFY_INSTANCES);
+}
+
+static inline struct ucounts *inc_inotify_watches(struct ucounts *ucounts)
+{
+ return inc_ucount(ucounts->ns, ucounts->uid, UCOUNT_INOTIFY_WATCHES);
+}
+
+static inline void dec_inotify_watches(struct ucounts *ucounts)
+{
+ dec_ucount(ucounts, UCOUNT_INOTIFY_WATCHES);
+}
+#endif
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
new file mode 100644
index 0000000..f4184b4
--- /dev/null
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -0,0 +1,206 @@
+/*
+ * fs/inotify_user.c - inotify support for userspace
+ *
+ * Authors:
+ * John McCutchan <ttb@tentacle.dhs.org>
+ * Robert Love <rml@novell.com>
+ *
+ * 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
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/dcache.h> /* d_unlinked */
+#include <linux/fs.h> /* struct inode */
+#include <linux/fsnotify_backend.h>
+#include <linux/inotify.h>
+#include <linux/path.h> /* struct path */
+#include <linux/slab.h> /* kmem_* */
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <linux/sched/user.h>
+#include <linux/sched/mm.h>
+
+#include "inotify.h"
+
+/*
+ * Check if 2 events contain the same information.
+ */
+static bool event_compare(struct fsnotify_event *old_fsn,
+ struct fsnotify_event *new_fsn)
+{
+ struct inotify_event_info *old, *new;
+
+ if (old_fsn->mask & FS_IN_IGNORED)
+ return false;
+ old = INOTIFY_E(old_fsn);
+ new = INOTIFY_E(new_fsn);
+ if ((old_fsn->mask == new_fsn->mask) &&
+ (old_fsn->inode == new_fsn->inode) &&
+ (old->name_len == new->name_len) &&
+ (!old->name_len || !strcmp(old->name, new->name)))
+ return true;
+ return false;
+}
+
+static int inotify_merge(struct list_head *list,
+ struct fsnotify_event *event)
+{
+ struct fsnotify_event *last_event;
+
+ last_event = list_entry(list->prev, struct fsnotify_event, list);
+ return event_compare(last_event, event);
+}
+
+int inotify_handle_event(struct fsnotify_group *group,
+ struct inode *inode,
+ u32 mask, const void *data, int data_type,
+ const unsigned char *file_name, u32 cookie,
+ struct fsnotify_iter_info *iter_info)
+{
+ struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info);
+ struct inotify_inode_mark *i_mark;
+ struct inotify_event_info *event;
+ struct fsnotify_event *fsn_event;
+ int ret;
+ int len = 0;
+ int alloc_len = sizeof(struct inotify_event_info);
+
+ if (WARN_ON(fsnotify_iter_vfsmount_mark(iter_info)))
+ return 0;
+
+ if ((inode_mark->mask & FS_EXCL_UNLINK) &&
+ (data_type == FSNOTIFY_EVENT_PATH)) {
+ const struct path *path = data;
+
+ if (d_unlinked(path->dentry))
+ return 0;
+ }
+ if (file_name) {
+ len = strlen(file_name);
+ alloc_len += len + 1;
+ }
+
+ pr_debug("%s: group=%p inode=%p mask=%x\n", __func__, group, inode,
+ mask);
+
+ i_mark = container_of(inode_mark, struct inotify_inode_mark,
+ fsn_mark);
+
+ /* Whoever is interested in the event, pays for the allocation. */
+ memalloc_use_memcg(group->memcg);
+ event = kmalloc(alloc_len, GFP_KERNEL_ACCOUNT);
+ memalloc_unuse_memcg();
+
+ if (unlikely(!event)) {
+ /*
+ * Treat lost event due to ENOMEM the same way as queue
+ * overflow to let userspace know event was lost.
+ */
+ fsnotify_queue_overflow(group);
+ return -ENOMEM;
+ }
+
+ fsn_event = &event->fse;
+ fsnotify_init_event(fsn_event, inode, mask);
+ event->wd = i_mark->wd;
+ event->sync_cookie = cookie;
+ event->name_len = len;
+ if (len)
+ strcpy(event->name, file_name);
+
+ ret = fsnotify_add_event(group, fsn_event, inotify_merge);
+ if (ret) {
+ /* Our event wasn't used in the end. Free it. */
+ fsnotify_destroy_event(group, fsn_event);
+ }
+
+ if (inode_mark->mask & IN_ONESHOT)
+ fsnotify_destroy_mark(inode_mark, group);
+
+ return 0;
+}
+
+static void inotify_freeing_mark(struct fsnotify_mark *fsn_mark, struct fsnotify_group *group)
+{
+ inotify_ignored_and_remove_idr(fsn_mark, group);
+}
+
+/*
+ * This is NEVER supposed to be called. Inotify marks should either have been
+ * removed from the idr when the watch was removed or in the
+ * fsnotify_destroy_mark_by_group() call when the inotify instance was being
+ * torn down. This is only called if the idr is about to be freed but there
+ * are still marks in it.
+ */
+static int idr_callback(int id, void *p, void *data)
+{
+ struct fsnotify_mark *fsn_mark;
+ struct inotify_inode_mark *i_mark;
+ static bool warned = false;
+
+ if (warned)
+ return 0;
+
+ warned = true;
+ fsn_mark = p;
+ i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
+
+ WARN(1, "inotify closing but id=%d for fsn_mark=%p in group=%p still in "
+ "idr. Probably leaking memory\n", id, p, data);
+
+ /*
+ * I'm taking the liberty of assuming that the mark in question is a
+ * valid address and I'm dereferencing it. This might help to figure
+ * out why we got here and the panic is no worse than the original
+ * BUG() that was here.
+ */
+ if (fsn_mark)
+ printk(KERN_WARNING "fsn_mark->group=%p wd=%d\n",
+ fsn_mark->group, i_mark->wd);
+ return 0;
+}
+
+static void inotify_free_group_priv(struct fsnotify_group *group)
+{
+ /* ideally the idr is empty and we won't hit the BUG in the callback */
+ idr_for_each(&group->inotify_data.idr, idr_callback, group);
+ idr_destroy(&group->inotify_data.idr);
+ if (group->inotify_data.ucounts)
+ dec_inotify_instances(group->inotify_data.ucounts);
+}
+
+static void inotify_free_event(struct fsnotify_event *fsn_event)
+{
+ kfree(INOTIFY_E(fsn_event));
+}
+
+/* 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);
+}
+
+const struct fsnotify_ops inotify_fsnotify_ops = {
+ .handle_event = inotify_handle_event,
+ .free_group_priv = inotify_free_group_priv,
+ .free_event = inotify_free_event,
+ .freeing_mark = inotify_freeing_mark,
+ .free_mark = inotify_free_mark,
+};
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
new file mode 100644
index 0000000..ac6978d
--- /dev/null
+++ b/fs/notify/inotify/inotify_user.c
@@ -0,0 +1,829 @@
+/*
+ * fs/inotify_user.c - inotify support for userspace
+ *
+ * Authors:
+ * John McCutchan <ttb@tentacle.dhs.org>
+ * Robert Love <rml@novell.com>
+ *
+ * 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
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * 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/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 "inotify.h"
+#include "../fdinfo.h"
+
+#include <asm/ioctls.h>
+
+/* configurable via /proc/sys/fs/inotify/ */
+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 int zero;
+
+struct ctl_table inotify_table[] = {
+ {
+ .procname = "max_user_instances",
+ .data = &init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES],
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ },
+ {
+ .procname = "max_user_watches",
+ .data = &init_user_ns.ucount_max[UCOUNT_INOTIFY_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;
+}
+
+static inline u32 inotify_mask_to_arg(__u32 mask)
+{
+ return mask & (IN_ALL_EVENTS | IN_ISDIR | IN_UNMOUNT | IN_IGNORED |
+ IN_Q_OVERFLOW);
+}
+
+/* intofiy userspace file descriptor functions */
+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));
+}
+
+/*
+ * 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;
+}
+
+/*
+ * 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;
+}
+
+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);
+
+ /* free this group, matching get was inotify_init->fsnotify_obtain_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,
+};
+
+
+/*
+ * 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;
+}
+
+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;
+}
+
+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(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;
+}
+
+/*
+ * 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)
+{
+ 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;
+
+ /*
+ * 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\n",
+ __func__, i_mark, i_mark->wd, i_mark->fsn_mark.group);
+ 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\n",
+ __func__, i_mark, i_mark->wd, i_mark->fsn_mark.group);
+ 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 "
+ "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;
+ }
+
+ /*
+ * One ref for being in the idr
+ * one ref grabbed by inotify_idr_find
+ */
+ 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);
+ /* we can't really recover with bad ref cnting.. */
+ BUG();
+ }
+
+ idr_remove(idr, wd);
+ /* Removed from the idr, drop that ref. */
+ fsnotify_put_mark(&i_mark->fsn_mark);
+out:
+ i_mark->wd = -1;
+ spin_unlock(idr_lock);
+ /* match the ref taken by inotify_idr_find_locked() */
+ if (found_i_mark)
+ fsnotify_put_mark(&found_i_mark->fsn_mark);
+}
+
+/*
+ * 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;
+ struct fsnotify_iter_info iter_info = { };
+
+ fsnotify_iter_set_report_type_mark(&iter_info, FSNOTIFY_OBJ_TYPE_INODE,
+ fsn_mark);
+
+ /* Queue ignore event for the watch */
+ inotify_handle_event(group, NULL, FS_IN_IGNORED, NULL,
+ FSNOTIFY_EVENT_NONE, NULL, 0, &iter_info);
+
+ 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);
+
+ 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;
+ __u32 mask;
+ int add = (arg & IN_MASK_ADD);
+ int create = (arg & IN_MASK_CREATE);
+ int ret;
+
+ mask = inotify_arg_to_mask(arg);
+
+ fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, group);
+ if (!fsn_mark)
+ return -ENOENT;
+ else if (create)
+ return -EEXIST;
+
+ i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
+
+ spin_lock(&fsn_mark->lock);
+ old_mask = fsn_mark->mask;
+ if (add)
+ fsn_mark->mask |= mask;
+ else
+ fsn_mark->mask = 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_mask(inode->i_fsnotify_marks);
+
+ }
+
+ /* return the wd */
+ ret = i_mark->wd;
+
+ /* match the get from fsnotify_find_mark() */
+ 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;
+ __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, group);
+ tmp_i_mark->fsn_mark.mask = mask;
+ tmp_i_mark->wd = -1;
+
+ ret = inotify_add_to_idr(idr, idr_lock, tmp_i_mark);
+ if (ret)
+ goto out_err;
+
+ /* increment the number of watches the user has */
+ if (!inc_inotify_watches(group->inotify_data.ucounts)) {
+ inotify_remove_from_idr(group, tmp_i_mark);
+ ret = -ENOSPC;
+ goto out_err;
+ }
+
+ /* we are on the idr, now get on the inode */
+ ret = fsnotify_add_inode_mark_locked(&tmp_i_mark->fsn_mark, inode, 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;
+ }
+
+
+ /* 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;
+}
+
+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;
+}
+
+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;
+ 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;
+}
+
+
+/* inotify syscalls */
+static int do_inotify_init(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_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;
+
+ /*
+ * 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;
+
+ /* IN_MASK_ADD and IN_MASK_CREATE don't make sense together */
+ if (unlikely((mask & IN_MASK_ADD) && (mask & IN_MASK_CREATE)))
+ return -EINVAL;
+
+ /* 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;
+
+ /* create/update an inode mark */
+ 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 = 0;
+
+ f = fdget(fd);
+ if (unlikely(!f.file))
+ return -EBADF;
+
+ /* verify that this is indeed an inotify instance */
+ ret = -EINVAL;
+ if (unlikely(f.file->f_op != &inotify_fops))
+ goto out;
+
+ group = f.file->private_data;
+
+ ret = -EINVAL;
+ i_mark = inotify_idr_find(group, wd);
+ if (unlikely(!i_mark))
+ goto out;
+
+ ret = 0;
+
+ fsnotify_destroy_mark(&i_mark->fsn_mark, group);
+
+ /* match ref taken by inotify_idr_find */
+ fsnotify_put_mark(&i_mark->fsn_mark);
+
+out:
+ fdput(f);
+ return ret;
+}
+
+/*
+ * inotify_user_setup - Our initialization function. Note that we cannot return
+ * error because we have compiled-in VFS hooks. So an (unlikely) failure here
+ * must result in panic().
+ */
+static int __init inotify_user_setup(void)
+{
+ 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_EXCL_UNLINK != FS_EXCL_UNLINK);
+ BUILD_BUG_ON(IN_ISDIR != FS_ISDIR);
+ BUILD_BUG_ON(IN_ONESHOT != FS_IN_ONESHOT);
+
+ 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] = 8192;
+
+ return 0;
+}
+fs_initcall(inotify_user_setup);
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
new file mode 100644
index 0000000..09535f6
--- /dev/null
+++ b/fs/notify/mark.c
@@ -0,0 +1,807 @@
+/*
+ * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
+ *
+ * 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
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; see the file COPYING. If not, write to
+ * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+/*
+ * fsnotify inode mark locking/lifetime/and refcnting
+ *
+ * REFCNT:
+ * The group->recnt and mark->refcnt tell how many "things" in the kernel
+ * currently are referencing the objects. Both kind of objects typically will
+ * live inside the kernel with a refcnt of 2, one for its creation and one for
+ * the reference a group and a mark hold to each other.
+ * If you are holding the appropriate locks, you can take a reference and the
+ * object itself is guaranteed to survive until the reference is dropped.
+ *
+ * LOCKING:
+ * There are 3 locks involved with fsnotify inode marks and they MUST be taken
+ * in order as follows:
+ *
+ * group->mark_mutex
+ * mark->lock
+ * mark->connector->lock
+ *
+ * group->mark_mutex protects the marks_list anchored inside a given group and
+ * each mark is hooked via the g_list. It also protects the groups private
+ * data (i.e group limits).
+
+ * mark->lock protects the marks attributes like its masks and flags.
+ * Furthermore it protects the access to a reference of the group that the mark
+ * is assigned to as well as the access to a reference of the inode/vfsmount
+ * that is being watched by the mark.
+ *
+ * mark->connector->lock protects the list of marks anchored inside an
+ * inode / vfsmount and each mark is hooked via the i_list.
+ *
+ * A list of notification marks relating to inode / mnt is contained in
+ * fsnotify_mark_connector. That structure is alive as long as there are any
+ * marks in the list and is also protected by fsnotify_mark_srcu. A mark gets
+ * detached from fsnotify_mark_connector when last reference to the mark is
+ * dropped. Thus having mark reference is enough to protect mark->connector
+ * pointer and to make sure fsnotify_mark_connector cannot disappear. Also
+ * because we remove mark from g_list before dropping mark reference associated
+ * with that, any mark found through g_list is guaranteed to have
+ * mark->connector set until we drop group->mark_mutex.
+ *
+ * LIFETIME:
+ * Inode marks survive between when they are added to an inode and when their
+ * refcnt==0. Marks are also protected by fsnotify_mark_srcu.
+ *
+ * The inode mark can be cleared for a number of different reasons including:
+ * - The inode is unlinked for the last time. (fsnotify_inode_remove)
+ * - The inode is being evicted from cache. (fsnotify_inode_delete)
+ * - The fs the inode is on is unmounted. (fsnotify_inode_delete/fsnotify_unmount_inodes)
+ * - Something explicitly requests that it be removed. (fsnotify_destroy_mark)
+ * - The fsnotify_group associated with the mark is going away and all such marks
+ * need to be cleaned up. (fsnotify_clear_marks_by_group)
+ *
+ * This has the very interesting property of being able to run concurrently with
+ * any (or all) other directions.
+ */
+
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/kthread.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/srcu.h>
+
+#include <linux/atomic.h>
+
+#include <linux/fsnotify_backend.h>
+#include "fsnotify.h"
+
+#define FSNOTIFY_REAPER_DELAY (1) /* 1 jiffy */
+
+struct srcu_struct fsnotify_mark_srcu;
+struct kmem_cache *fsnotify_mark_connector_cachep;
+
+static DEFINE_SPINLOCK(destroy_lock);
+static LIST_HEAD(destroy_list);
+static struct fsnotify_mark_connector *connector_destroy_list;
+
+static void fsnotify_mark_destroy_workfn(struct work_struct *work);
+static DECLARE_DELAYED_WORK(reaper_work, fsnotify_mark_destroy_workfn);
+
+static void fsnotify_connector_destroy_workfn(struct work_struct *work);
+static DECLARE_WORK(connector_reaper_work, fsnotify_connector_destroy_workfn);
+
+void fsnotify_get_mark(struct fsnotify_mark *mark)
+{
+ WARN_ON_ONCE(!refcount_read(&mark->refcnt));
+ refcount_inc(&mark->refcnt);
+}
+
+static __u32 *fsnotify_conn_mask_p(struct fsnotify_mark_connector *conn)
+{
+ if (conn->type == FSNOTIFY_OBJ_TYPE_INODE)
+ return &fsnotify_conn_inode(conn)->i_fsnotify_mask;
+ else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT)
+ return &fsnotify_conn_mount(conn)->mnt_fsnotify_mask;
+ return NULL;
+}
+
+__u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn)
+{
+ if (WARN_ON(!fsnotify_valid_obj_type(conn->type)))
+ return 0;
+
+ return *fsnotify_conn_mask_p(conn);
+}
+
+static void __fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
+{
+ u32 new_mask = 0;
+ struct fsnotify_mark *mark;
+
+ assert_spin_locked(&conn->lock);
+ /* We can get detached connector here when inode is getting unlinked. */
+ if (!fsnotify_valid_obj_type(conn->type))
+ return;
+ hlist_for_each_entry(mark, &conn->list, obj_list) {
+ if (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)
+ new_mask |= mark->mask;
+ }
+ *fsnotify_conn_mask_p(conn) = new_mask;
+}
+
+/*
+ * Calculate mask of events for a list of marks. The caller must make sure
+ * connector and connector->obj cannot disappear under us. Callers achieve
+ * this by holding a mark->lock or mark->group->mark_mutex for a mark on this
+ * list.
+ */
+void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
+{
+ if (!conn)
+ return;
+
+ spin_lock(&conn->lock);
+ __fsnotify_recalc_mask(conn);
+ spin_unlock(&conn->lock);
+ if (conn->type == FSNOTIFY_OBJ_TYPE_INODE)
+ __fsnotify_update_child_dentry_flags(
+ fsnotify_conn_inode(conn));
+}
+
+/* Free all connectors queued for freeing once SRCU period ends */
+static void fsnotify_connector_destroy_workfn(struct work_struct *work)
+{
+ struct fsnotify_mark_connector *conn, *free;
+
+ spin_lock(&destroy_lock);
+ conn = connector_destroy_list;
+ connector_destroy_list = NULL;
+ spin_unlock(&destroy_lock);
+
+ synchronize_srcu(&fsnotify_mark_srcu);
+ while (conn) {
+ free = conn;
+ conn = conn->destroy_next;
+ kmem_cache_free(fsnotify_mark_connector_cachep, free);
+ }
+}
+
+static void *fsnotify_detach_connector_from_object(
+ struct fsnotify_mark_connector *conn,
+ unsigned int *type)
+{
+ struct inode *inode = NULL;
+
+ *type = conn->type;
+ if (conn->type == FSNOTIFY_OBJ_TYPE_DETACHED)
+ return NULL;
+
+ if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) {
+ inode = fsnotify_conn_inode(conn);
+ inode->i_fsnotify_mask = 0;
+ atomic_long_inc(&inode->i_sb->s_fsnotify_inode_refs);
+ } else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) {
+ fsnotify_conn_mount(conn)->mnt_fsnotify_mask = 0;
+ }
+
+ rcu_assign_pointer(*(conn->obj), NULL);
+ conn->obj = NULL;
+ conn->type = FSNOTIFY_OBJ_TYPE_DETACHED;
+
+ return inode;
+}
+
+static void fsnotify_final_mark_destroy(struct fsnotify_mark *mark)
+{
+ struct fsnotify_group *group = mark->group;
+
+ if (WARN_ON_ONCE(!group))
+ return;
+ group->ops->free_mark(mark);
+ fsnotify_put_group(group);
+}
+
+/* Drop object reference originally held by a connector */
+static void fsnotify_drop_object(unsigned int type, void *objp)
+{
+ struct inode *inode;
+ struct super_block *sb;
+
+ if (!objp)
+ return;
+ /* Currently only inode references are passed to be dropped */
+ if (WARN_ON_ONCE(type != FSNOTIFY_OBJ_TYPE_INODE))
+ return;
+ inode = objp;
+ sb = inode->i_sb;
+ iput(inode);
+ if (atomic_long_dec_and_test(&sb->s_fsnotify_inode_refs))
+ wake_up_var(&sb->s_fsnotify_inode_refs);
+}
+
+void fsnotify_put_mark(struct fsnotify_mark *mark)
+{
+ struct fsnotify_mark_connector *conn;
+ void *objp = NULL;
+ unsigned int type = FSNOTIFY_OBJ_TYPE_DETACHED;
+ bool free_conn = false;
+
+ /* Catch marks that were actually never attached to object */
+ if (!mark->connector) {
+ if (refcount_dec_and_test(&mark->refcnt))
+ fsnotify_final_mark_destroy(mark);
+ return;
+ }
+
+ /*
+ * We have to be careful so that traversals of obj_list under lock can
+ * safely grab mark reference.
+ */
+ if (!refcount_dec_and_lock(&mark->refcnt, &mark->connector->lock))
+ return;
+
+ conn = mark->connector;
+ hlist_del_init_rcu(&mark->obj_list);
+ if (hlist_empty(&conn->list)) {
+ objp = fsnotify_detach_connector_from_object(conn, &type);
+ free_conn = true;
+ } else {
+ __fsnotify_recalc_mask(conn);
+ }
+ mark->connector = NULL;
+ spin_unlock(&conn->lock);
+
+ fsnotify_drop_object(type, objp);
+
+ if (free_conn) {
+ spin_lock(&destroy_lock);
+ conn->destroy_next = connector_destroy_list;
+ connector_destroy_list = conn;
+ spin_unlock(&destroy_lock);
+ queue_work(system_unbound_wq, &connector_reaper_work);
+ }
+ /*
+ * Note that we didn't update flags telling whether inode cares about
+ * what's happening with children. We update these flags from
+ * __fsnotify_parent() lazily when next event happens on one of our
+ * children.
+ */
+ spin_lock(&destroy_lock);
+ list_add(&mark->g_list, &destroy_list);
+ spin_unlock(&destroy_lock);
+ queue_delayed_work(system_unbound_wq, &reaper_work,
+ FSNOTIFY_REAPER_DELAY);
+}
+
+/*
+ * Get mark reference when we found the mark via lockless traversal of object
+ * list. Mark can be already removed from the list by now and on its way to be
+ * destroyed once SRCU period ends.
+ *
+ * Also pin the group so it doesn't disappear under us.
+ */
+static bool fsnotify_get_mark_safe(struct fsnotify_mark *mark)
+{
+ if (!mark)
+ return true;
+
+ if (refcount_inc_not_zero(&mark->refcnt)) {
+ spin_lock(&mark->lock);
+ if (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) {
+ /* mark is attached, group is still alive then */
+ atomic_inc(&mark->group->user_waits);
+ spin_unlock(&mark->lock);
+ return true;
+ }
+ spin_unlock(&mark->lock);
+ fsnotify_put_mark(mark);
+ }
+ return false;
+}
+
+/*
+ * Puts marks and wakes up group destruction if necessary.
+ *
+ * Pairs with fsnotify_get_mark_safe()
+ */
+static void fsnotify_put_mark_wake(struct fsnotify_mark *mark)
+{
+ if (mark) {
+ struct fsnotify_group *group = mark->group;
+
+ fsnotify_put_mark(mark);
+ /*
+ * We abuse notification_waitq on group shutdown for waiting for
+ * all marks pinned when waiting for userspace.
+ */
+ if (atomic_dec_and_test(&group->user_waits) && group->shutdown)
+ wake_up(&group->notification_waitq);
+ }
+}
+
+bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info)
+{
+ int type;
+
+ fsnotify_foreach_obj_type(type) {
+ /* This can fail if mark is being removed */
+ if (!fsnotify_get_mark_safe(iter_info->marks[type]))
+ goto fail;
+ }
+
+ /*
+ * Now that both marks are pinned by refcount in the inode / vfsmount
+ * lists, we can drop SRCU lock, and safely resume the list iteration
+ * once userspace returns.
+ */
+ srcu_read_unlock(&fsnotify_mark_srcu, iter_info->srcu_idx);
+
+ return true;
+
+fail:
+ for (type--; type >= 0; type--)
+ fsnotify_put_mark_wake(iter_info->marks[type]);
+ return false;
+}
+
+void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info)
+{
+ int type;
+
+ iter_info->srcu_idx = srcu_read_lock(&fsnotify_mark_srcu);
+ fsnotify_foreach_obj_type(type)
+ fsnotify_put_mark_wake(iter_info->marks[type]);
+}
+
+/*
+ * Mark mark as detached, remove it from group list. Mark still stays in object
+ * list until its last reference is dropped. Note that we rely on mark being
+ * removed from group list before corresponding reference to it is dropped. In
+ * particular we rely on mark->connector being valid while we hold
+ * group->mark_mutex if we found the mark through g_list.
+ *
+ * Must be called with group->mark_mutex held. The caller must either hold
+ * reference to the mark or be protected by fsnotify_mark_srcu.
+ */
+void fsnotify_detach_mark(struct fsnotify_mark *mark)
+{
+ struct fsnotify_group *group = mark->group;
+
+ WARN_ON_ONCE(!mutex_is_locked(&group->mark_mutex));
+ WARN_ON_ONCE(!srcu_read_lock_held(&fsnotify_mark_srcu) &&
+ refcount_read(&mark->refcnt) < 1 +
+ !!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED));
+
+ spin_lock(&mark->lock);
+ /* something else already called this function on this mark */
+ if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) {
+ spin_unlock(&mark->lock);
+ return;
+ }
+ mark->flags &= ~FSNOTIFY_MARK_FLAG_ATTACHED;
+ list_del_init(&mark->g_list);
+ spin_unlock(&mark->lock);
+
+ atomic_dec(&group->num_marks);
+
+ /* Drop mark reference acquired in fsnotify_add_mark_locked() */
+ fsnotify_put_mark(mark);
+}
+
+/*
+ * Free fsnotify mark. The mark is actually only marked as being freed. The
+ * freeing is actually happening only once last reference to the mark is
+ * dropped from a workqueue which first waits for srcu period end.
+ *
+ * Caller must have a reference to the mark or be protected by
+ * fsnotify_mark_srcu.
+ */
+void fsnotify_free_mark(struct fsnotify_mark *mark)
+{
+ struct fsnotify_group *group = mark->group;
+
+ spin_lock(&mark->lock);
+ /* something else already called this function on this mark */
+ if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE)) {
+ spin_unlock(&mark->lock);
+ return;
+ }
+ mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE;
+ spin_unlock(&mark->lock);
+
+ /*
+ * Some groups like to know that marks are being freed. This is a
+ * callback to the group function to let it know that this mark
+ * is being freed.
+ */
+ if (group->ops->freeing_mark)
+ group->ops->freeing_mark(mark, group);
+}
+
+void fsnotify_destroy_mark(struct fsnotify_mark *mark,
+ struct fsnotify_group *group)
+{
+ mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
+ fsnotify_detach_mark(mark);
+ mutex_unlock(&group->mark_mutex);
+ fsnotify_free_mark(mark);
+}
+
+/*
+ * Sorting function for lists of fsnotify marks.
+ *
+ * Fanotify supports different notification classes (reflected as priority of
+ * notification group). Events shall be passed to notification groups in
+ * decreasing priority order. To achieve this marks in notification lists for
+ * inodes and vfsmounts are sorted so that priorities of corresponding groups
+ * are descending.
+ *
+ * Furthermore correct handling of the ignore mask requires processing inode
+ * and vfsmount marks of each group together. Using the group address as
+ * further sort criterion provides a unique sorting order and thus we can
+ * merge inode and vfsmount lists of marks in linear time and find groups
+ * present in both lists.
+ *
+ * A return value of 1 signifies that b has priority over a.
+ * A return value of 0 signifies that the two marks have to be handled together.
+ * A return value of -1 signifies that a has priority over b.
+ */
+int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b)
+{
+ if (a == b)
+ return 0;
+ if (!a)
+ return 1;
+ if (!b)
+ return -1;
+ if (a->priority < b->priority)
+ return 1;
+ if (a->priority > b->priority)
+ return -1;
+ if (a < b)
+ return 1;
+ return -1;
+}
+
+static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp,
+ unsigned int type)
+{
+ struct inode *inode = NULL;
+ struct fsnotify_mark_connector *conn;
+
+ conn = kmem_cache_alloc(fsnotify_mark_connector_cachep, GFP_KERNEL);
+ if (!conn)
+ return -ENOMEM;
+ spin_lock_init(&conn->lock);
+ INIT_HLIST_HEAD(&conn->list);
+ conn->type = type;
+ conn->obj = connp;
+ if (conn->type == FSNOTIFY_OBJ_TYPE_INODE)
+ inode = igrab(fsnotify_conn_inode(conn));
+ /*
+ * cmpxchg() provides the barrier so that readers of *connp can see
+ * only initialized structure
+ */
+ if (cmpxchg(connp, NULL, conn)) {
+ /* Someone else created list structure for us */
+ if (inode)
+ iput(inode);
+ kmem_cache_free(fsnotify_mark_connector_cachep, conn);
+ }
+
+ return 0;
+}
+
+/*
+ * Get mark connector, make sure it is alive and return with its lock held.
+ * This is for users that get connector pointer from inode or mount. Users that
+ * hold reference to a mark on the list may directly lock connector->lock as
+ * they are sure list cannot go away under them.
+ */
+static struct fsnotify_mark_connector *fsnotify_grab_connector(
+ fsnotify_connp_t *connp)
+{
+ struct fsnotify_mark_connector *conn;
+ int idx;
+
+ idx = srcu_read_lock(&fsnotify_mark_srcu);
+ conn = srcu_dereference(*connp, &fsnotify_mark_srcu);
+ if (!conn)
+ goto out;
+ spin_lock(&conn->lock);
+ if (conn->type == FSNOTIFY_OBJ_TYPE_DETACHED) {
+ spin_unlock(&conn->lock);
+ srcu_read_unlock(&fsnotify_mark_srcu, idx);
+ return NULL;
+ }
+out:
+ srcu_read_unlock(&fsnotify_mark_srcu, idx);
+ return conn;
+}
+
+/*
+ * Add mark into proper place in given list of marks. These marks may be used
+ * for the fsnotify backend to determine which event types should be delivered
+ * to which group and for which inodes. These marks are ordered according to
+ * priority, highest number first, and then by the group's location in memory.
+ */
+static int fsnotify_add_mark_list(struct fsnotify_mark *mark,
+ fsnotify_connp_t *connp, unsigned int type,
+ int allow_dups)
+{
+ struct fsnotify_mark *lmark, *last = NULL;
+ struct fsnotify_mark_connector *conn;
+ int cmp;
+ int err = 0;
+
+ if (WARN_ON(!fsnotify_valid_obj_type(type)))
+ return -EINVAL;
+restart:
+ spin_lock(&mark->lock);
+ conn = fsnotify_grab_connector(connp);
+ if (!conn) {
+ spin_unlock(&mark->lock);
+ err = fsnotify_attach_connector_to_object(connp, type);
+ if (err)
+ return err;
+ goto restart;
+ }
+
+ /* is mark the first mark? */
+ if (hlist_empty(&conn->list)) {
+ hlist_add_head_rcu(&mark->obj_list, &conn->list);
+ goto added;
+ }
+
+ /* should mark be in the middle of the current list? */
+ hlist_for_each_entry(lmark, &conn->list, obj_list) {
+ last = lmark;
+
+ if ((lmark->group == mark->group) &&
+ (lmark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) &&
+ !allow_dups) {
+ err = -EEXIST;
+ goto out_err;
+ }
+
+ cmp = fsnotify_compare_groups(lmark->group, mark->group);
+ if (cmp >= 0) {
+ hlist_add_before_rcu(&mark->obj_list, &lmark->obj_list);
+ goto added;
+ }
+ }
+
+ BUG_ON(last == NULL);
+ /* mark should be the last entry. last is the current last entry */
+ hlist_add_behind_rcu(&mark->obj_list, &last->obj_list);
+added:
+ mark->connector = conn;
+out_err:
+ spin_unlock(&conn->lock);
+ spin_unlock(&mark->lock);
+ return err;
+}
+
+/*
+ * Attach an initialized mark to a given group and fs object.
+ * These marks may be used for the fsnotify backend to determine which
+ * event types should be delivered to which group.
+ */
+int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
+ fsnotify_connp_t *connp, unsigned int type,
+ int allow_dups)
+{
+ struct fsnotify_group *group = mark->group;
+ int ret = 0;
+
+ BUG_ON(!mutex_is_locked(&group->mark_mutex));
+
+ /*
+ * LOCKING ORDER!!!!
+ * group->mark_mutex
+ * mark->lock
+ * mark->connector->lock
+ */
+ spin_lock(&mark->lock);
+ mark->flags |= FSNOTIFY_MARK_FLAG_ALIVE | FSNOTIFY_MARK_FLAG_ATTACHED;
+
+ list_add(&mark->g_list, &group->marks_list);
+ atomic_inc(&group->num_marks);
+ fsnotify_get_mark(mark); /* for g_list */
+ spin_unlock(&mark->lock);
+
+ ret = fsnotify_add_mark_list(mark, connp, type, allow_dups);
+ if (ret)
+ goto err;
+
+ if (mark->mask)
+ fsnotify_recalc_mask(mark->connector);
+
+ return ret;
+err:
+ spin_lock(&mark->lock);
+ mark->flags &= ~(FSNOTIFY_MARK_FLAG_ALIVE |
+ FSNOTIFY_MARK_FLAG_ATTACHED);
+ list_del_init(&mark->g_list);
+ spin_unlock(&mark->lock);
+ atomic_dec(&group->num_marks);
+
+ fsnotify_put_mark(mark);
+ return ret;
+}
+
+int fsnotify_add_mark(struct fsnotify_mark *mark, fsnotify_connp_t *connp,
+ unsigned int type, int allow_dups)
+{
+ int ret;
+ struct fsnotify_group *group = mark->group;
+
+ mutex_lock(&group->mark_mutex);
+ ret = fsnotify_add_mark_locked(mark, connp, type, allow_dups);
+ mutex_unlock(&group->mark_mutex);
+ return ret;
+}
+
+/*
+ * Given a list of marks, find the mark associated with given group. If found
+ * take a reference to that mark and return it, else return NULL.
+ */
+struct fsnotify_mark *fsnotify_find_mark(fsnotify_connp_t *connp,
+ struct fsnotify_group *group)
+{
+ struct fsnotify_mark_connector *conn;
+ struct fsnotify_mark *mark;
+
+ conn = fsnotify_grab_connector(connp);
+ if (!conn)
+ return NULL;
+
+ hlist_for_each_entry(mark, &conn->list, obj_list) {
+ if (mark->group == group &&
+ (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) {
+ fsnotify_get_mark(mark);
+ spin_unlock(&conn->lock);
+ return mark;
+ }
+ }
+ spin_unlock(&conn->lock);
+ return NULL;
+}
+
+/* Clear any marks in a group with given type mask */
+void fsnotify_clear_marks_by_group(struct fsnotify_group *group,
+ unsigned int type_mask)
+{
+ struct fsnotify_mark *lmark, *mark;
+ LIST_HEAD(to_free);
+ struct list_head *head = &to_free;
+
+ /* Skip selection step if we want to clear all marks. */
+ if (type_mask == FSNOTIFY_OBJ_ALL_TYPES_MASK) {
+ head = &group->marks_list;
+ goto clear;
+ }
+ /*
+ * We have to be really careful here. Anytime we drop mark_mutex, e.g.
+ * fsnotify_clear_marks_by_inode() can come and free marks. Even in our
+ * to_free list so we have to use mark_mutex even when accessing that
+ * list. And freeing mark requires us to drop mark_mutex. So we can
+ * reliably free only the first mark in the list. That's why we first
+ * move marks to free to to_free list in one go and then free marks in
+ * to_free list one by one.
+ */
+ mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
+ list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) {
+ if ((1U << mark->connector->type) & type_mask)
+ list_move(&mark->g_list, &to_free);
+ }
+ mutex_unlock(&group->mark_mutex);
+
+clear:
+ while (1) {
+ mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
+ if (list_empty(head)) {
+ mutex_unlock(&group->mark_mutex);
+ break;
+ }
+ mark = list_first_entry(head, struct fsnotify_mark, g_list);
+ fsnotify_get_mark(mark);
+ fsnotify_detach_mark(mark);
+ mutex_unlock(&group->mark_mutex);
+ fsnotify_free_mark(mark);
+ fsnotify_put_mark(mark);
+ }
+}
+
+/* Destroy all marks attached to an object via connector */
+void fsnotify_destroy_marks(fsnotify_connp_t *connp)
+{
+ struct fsnotify_mark_connector *conn;
+ struct fsnotify_mark *mark, *old_mark = NULL;
+ void *objp;
+ unsigned int type;
+
+ conn = fsnotify_grab_connector(connp);
+ if (!conn)
+ return;
+ /*
+ * We have to be careful since we can race with e.g.
+ * fsnotify_clear_marks_by_group() and once we drop the conn->lock, the
+ * list can get modified. However we are holding mark reference and
+ * thus our mark cannot be removed from obj_list so we can continue
+ * iteration after regaining conn->lock.
+ */
+ hlist_for_each_entry(mark, &conn->list, obj_list) {
+ fsnotify_get_mark(mark);
+ spin_unlock(&conn->lock);
+ if (old_mark)
+ fsnotify_put_mark(old_mark);
+ old_mark = mark;
+ fsnotify_destroy_mark(mark, mark->group);
+ spin_lock(&conn->lock);
+ }
+ /*
+ * Detach list from object now so that we don't pin inode until all
+ * mark references get dropped. It would lead to strange results such
+ * as delaying inode deletion or blocking unmount.
+ */
+ objp = fsnotify_detach_connector_from_object(conn, &type);
+ spin_unlock(&conn->lock);
+ if (old_mark)
+ fsnotify_put_mark(old_mark);
+ fsnotify_drop_object(type, objp);
+}
+
+/*
+ * Nothing fancy, just initialize lists and locks and counters.
+ */
+void fsnotify_init_mark(struct fsnotify_mark *mark,
+ struct fsnotify_group *group)
+{
+ memset(mark, 0, sizeof(*mark));
+ spin_lock_init(&mark->lock);
+ refcount_set(&mark->refcnt, 1);
+ fsnotify_get_group(group);
+ mark->group = group;
+}
+
+/*
+ * Destroy all marks in destroy_list, waits for SRCU period to finish before
+ * actually freeing marks.
+ */
+static void fsnotify_mark_destroy_workfn(struct work_struct *work)
+{
+ struct fsnotify_mark *mark, *next;
+ struct list_head private_destroy_list;
+
+ spin_lock(&destroy_lock);
+ /* exchange the list head */
+ list_replace_init(&destroy_list, &private_destroy_list);
+ spin_unlock(&destroy_lock);
+
+ synchronize_srcu(&fsnotify_mark_srcu);
+
+ list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) {
+ list_del_init(&mark->g_list);
+ fsnotify_final_mark_destroy(mark);
+ }
+}
+
+/* Wait for all marks queued for destruction to be actually destroyed */
+void fsnotify_wait_marks_destroyed(void)
+{
+ flush_delayed_work(&reaper_work);
+}
diff --git a/fs/notify/notification.c b/fs/notify/notification.c
new file mode 100644
index 0000000..3c3e367
--- /dev/null
+++ b/fs/notify/notification.c
@@ -0,0 +1,216 @@
+/*
+ * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
+ *
+ * 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
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; see the file COPYING. If not, write to
+ * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+/*
+ * Basic idea behind the notification queue: An fsnotify group (like inotify)
+ * sends the userspace notification about events asynchronously some time after
+ * the event happened. When inotify gets an event it will need to add that
+ * event to the group notify queue. Since a single event might need to be on
+ * multiple group's notification queues we can't add the event directly to each
+ * queue and instead add a small "event_holder" to each queue. This event_holder
+ * has a pointer back to the original event. Since the majority of events are
+ * going to end up on one, and only one, notification queue we embed one
+ * event_holder into each event. This means we have a single allocation instead
+ * of always needing two. If the embedded event_holder is already in use by
+ * another group a new event_holder (from fsnotify_event_holder_cachep) will be
+ * allocated and used.
+ */
+
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mount.h>
+#include <linux/mutex.h>
+#include <linux/namei.h>
+#include <linux/path.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include <linux/atomic.h>
+
+#include <linux/fsnotify_backend.h>
+#include "fsnotify.h"
+
+static atomic_t fsnotify_sync_cookie = ATOMIC_INIT(0);
+
+/**
+ * fsnotify_get_cookie - return a unique cookie for use in synchronizing events.
+ * Called from fsnotify_move, which is inlined into filesystem modules.
+ */
+u32 fsnotify_get_cookie(void)
+{
+ return atomic_inc_return(&fsnotify_sync_cookie);
+}
+EXPORT_SYMBOL_GPL(fsnotify_get_cookie);
+
+/* return true if the notify queue is empty, false otherwise */
+bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group)
+{
+ assert_spin_locked(&group->notification_lock);
+ return list_empty(&group->notification_list) ? true : false;
+}
+
+void fsnotify_destroy_event(struct fsnotify_group *group,
+ struct fsnotify_event *event)
+{
+ /* Overflow events are per-group and we don't want to free them */
+ if (!event || event->mask == FS_Q_OVERFLOW)
+ return;
+ /*
+ * If the event is still queued, we have a problem... Do an unreliable
+ * lockless check first to avoid locking in the common case. The
+ * locking may be necessary for permission events which got removed
+ * from the list by a different CPU than the one freeing the event.
+ */
+ if (!list_empty(&event->list)) {
+ spin_lock(&group->notification_lock);
+ WARN_ON(!list_empty(&event->list));
+ spin_unlock(&group->notification_lock);
+ }
+ group->ops->free_event(event);
+}
+
+/*
+ * Add an event to the group notification queue. The group can later pull this
+ * event off the queue to deal with. The function returns 0 if the event was
+ * added to the queue, 1 if the event was merged with some other queued event,
+ * 2 if the event was not queued - either the queue of events has overflown
+ * or the group is shutting down.
+ */
+int fsnotify_add_event(struct fsnotify_group *group,
+ struct fsnotify_event *event,
+ int (*merge)(struct list_head *,
+ struct fsnotify_event *))
+{
+ int ret = 0;
+ struct list_head *list = &group->notification_list;
+
+ pr_debug("%s: group=%p event=%p\n", __func__, group, event);
+
+ spin_lock(&group->notification_lock);
+
+ if (group->shutdown) {
+ spin_unlock(&group->notification_lock);
+ return 2;
+ }
+
+ if (event == group->overflow_event ||
+ group->q_len >= group->max_events) {
+ ret = 2;
+ /* Queue overflow event only if it isn't already queued */
+ if (!list_empty(&group->overflow_event->list)) {
+ spin_unlock(&group->notification_lock);
+ return ret;
+ }
+ event = group->overflow_event;
+ goto queue;
+ }
+
+ if (!list_empty(list) && merge) {
+ ret = merge(list, event);
+ if (ret) {
+ spin_unlock(&group->notification_lock);
+ return ret;
+ }
+ }
+
+queue:
+ group->q_len++;
+ list_add_tail(&event->list, list);
+ spin_unlock(&group->notification_lock);
+
+ wake_up(&group->notification_waitq);
+ kill_fasync(&group->fsn_fa, SIGIO, POLL_IN);
+ return ret;
+}
+
+/*
+ * Remove and return the first event from the notification list. It is the
+ * responsibility of the caller to destroy the obtained event
+ */
+struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group *group)
+{
+ struct fsnotify_event *event;
+
+ assert_spin_locked(&group->notification_lock);
+
+ pr_debug("%s: group=%p\n", __func__, group);
+
+ event = list_first_entry(&group->notification_list,
+ struct fsnotify_event, list);
+ /*
+ * We need to init list head for the case of overflow event so that
+ * check in fsnotify_add_event() works
+ */
+ list_del_init(&event->list);
+ group->q_len--;
+
+ return event;
+}
+
+/*
+ * This will not remove the event, that must be done with
+ * fsnotify_remove_first_event()
+ */
+struct fsnotify_event *fsnotify_peek_first_event(struct fsnotify_group *group)
+{
+ assert_spin_locked(&group->notification_lock);
+
+ return list_first_entry(&group->notification_list,
+ struct fsnotify_event, list);
+}
+
+/*
+ * Called when a group is being torn down to clean up any outstanding
+ * event notifications.
+ */
+void fsnotify_flush_notify(struct fsnotify_group *group)
+{
+ struct fsnotify_event *event;
+
+ spin_lock(&group->notification_lock);
+ while (!fsnotify_notify_queue_is_empty(group)) {
+ event = fsnotify_remove_first_event(group);
+ spin_unlock(&group->notification_lock);
+ fsnotify_destroy_event(group, event);
+ spin_lock(&group->notification_lock);
+ }
+ spin_unlock(&group->notification_lock);
+}
+
+/*
+ * fsnotify_create_event - Allocate a new event which will be sent to each
+ * group's handle_event function if the group was interested in this
+ * particular event.
+ *
+ * @inode the inode which is supposed to receive the event (sometimes a
+ * parent of the inode to which the event happened.
+ * @mask what actually happened.
+ * @data pointer to the object which was actually affected
+ * @data_type flag indication if the data is a file, path, inode, nothing...
+ * @name the filename, if available
+ */
+void fsnotify_init_event(struct fsnotify_event *event, struct inode *inode,
+ u32 mask)
+{
+ INIT_LIST_HEAD(&event->list);
+ event->inode = inode;
+ event->mask = mask;
+}