summaryrefslogtreecommitdiffstats
path: root/fs/notify
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-07 18:49:45 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-07 18:49:45 +0000
commit2c3c1048746a4622d8c89a29670120dc8fab93c4 (patch)
tree848558de17fb3008cdf4d861b01ac7781903ce39 /fs/notify
parentInitial commit. (diff)
downloadlinux-2c3c1048746a4622d8c89a29670120dc8fab93c4.tar.xz
linux-2c3c1048746a4622d8c89a29670120dc8fab93c4.zip
Adding upstream version 6.1.76.upstream/6.1.76
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'fs/notify')
-rw-r--r--fs/notify/Kconfig8
-rw-r--r--fs/notify/Makefile7
-rw-r--r--fs/notify/dnotify/Kconfig12
-rw-r--r--fs/notify/dnotify/Makefile2
-rw-r--r--fs/notify/dnotify/dnotify.c412
-rw-r--r--fs/notify/fanotify/Kconfig27
-rw-r--r--fs/notify/fanotify/Makefile2
-rw-r--r--fs/notify/fanotify/fanotify.c1076
-rw-r--r--fs/notify/fanotify/fanotify.h500
-rw-r--r--fs/notify/fanotify/fanotify_user.c1900
-rw-r--r--fs/notify/fdinfo.c148
-rw-r--r--fs/notify/fdinfo.h28
-rw-r--r--fs/notify/fsnotify.c601
-rw-r--r--fs/notify/fsnotify.h81
-rw-r--r--fs/notify/group.c171
-rw-r--r--fs/notify/inotify/Kconfig17
-rw-r--r--fs/notify/inotify/Makefile2
-rw-r--r--fs/notify/inotify/inotify.h69
-rw-r--r--fs/notify/inotify/inotify_fsnotify.c209
-rw-r--r--fs/notify/inotify/inotify_user.c875
-rw-r--r--fs/notify/mark.c911
-rw-r--r--fs/notify/notification.c193
22 files changed, 7251 insertions, 0 deletions
diff --git a/fs/notify/Kconfig b/fs/notify/Kconfig
new file mode 100644
index 000000000..c020d26ba
--- /dev/null
+++ b/fs/notify/Kconfig
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0-only
+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 000000000..63a4b8828
--- /dev/null
+++ b/fs/notify/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_FSNOTIFY) += fsnotify.o notification.o group.o mark.o \
+ fdinfo.o
+
+obj-y += dnotify/
+obj-y += inotify/
+obj-y += fanotify/
diff --git a/fs/notify/dnotify/Kconfig b/fs/notify/dnotify/Kconfig
new file mode 100644
index 000000000..3df7def17
--- /dev/null
+++ b/fs/notify/dnotify/Kconfig
@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config DNOTIFY
+ bool "Dnotify support"
+ select FSNOTIFY
+ default y
+ help
+ Dnotify is a directory-based per-fd file change notification system
+ that uses signals to communicate events to user-space. There exist
+ superior alternatives, but some applications may still rely on
+ dnotify.
+
+ If unsure, say Y.
diff --git a/fs/notify/dnotify/Makefile b/fs/notify/dnotify/Makefile
new file mode 100644
index 000000000..121b4dd6b
--- /dev/null
+++ b/fs/notify/dnotify/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_DNOTIFY) += dnotify.o
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
new file mode 100644
index 000000000..190aa717f
--- /dev/null
+++ b/fs/notify/dnotify/dnotify.c
@@ -0,0 +1,412 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * 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
+ */
+#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/security.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/fdtable.h>
+#include <linux/fsnotify_backend.h>
+
+static int dir_notify_enable __read_mostly = 1;
+#ifdef CONFIG_SYSCTL
+static struct ctl_table dnotify_sysctls[] = {
+ {
+ .procname = "dir-notify-enable",
+ .data = &dir_notify_enable,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {}
+};
+static void __init dnotify_sysctl_init(void)
+{
+ register_sysctl_init("fs", dnotify_sysctls);
+}
+#else
+#define dnotify_sysctl_init() do { } while (0)
+#endif
+
+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_mark *inode_mark, u32 mask,
+ struct inode *inode, struct inode *dir,
+ const struct qstr *name, u32 cookie)
+{
+ 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 (!dir && !(mask & FS_ISDIR))
+ 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_inode_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);
+
+ fsnotify_group_lock(dnotify_group);
+
+ 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;
+ }
+
+ fsnotify_group_unlock(dnotify_group);
+
+ 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_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;
+ }
+
+ /*
+ * convert the userspace DN_* "arg" to the internal FS_*
+ * defined in fsnotify
+ */
+ mask = convert_arg(arg);
+
+ error = security_path_notify(&filp->f_path, mask,
+ FSNOTIFY_OBJ_TYPE_INODE);
+ if (error)
+ 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;
+ }
+
+ /* 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 */
+ fsnotify_group_lock(dnotify_group);
+
+ /* 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) {
+ fsnotify_group_unlock(dnotify_group);
+ 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 = lookup_fd_rcu(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);
+ fsnotify_group_unlock(dnotify_group);
+ 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,
+ FSNOTIFY_GROUP_NOFS);
+ if (IS_ERR(dnotify_group))
+ panic("unable to allocate fsnotify group for dnotify\n");
+ dnotify_sysctl_init();
+ return 0;
+}
+
+module_init(dnotify_init)
diff --git a/fs/notify/fanotify/Kconfig b/fs/notify/fanotify/Kconfig
new file mode 100644
index 000000000..a511f9d86
--- /dev/null
+++ b/fs/notify/fanotify/Kconfig
@@ -0,0 +1,27 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config FANOTIFY
+ bool "Filesystem wide access notification"
+ select FSNOTIFY
+ select EXPORTFS
+ 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 000000000..25ef22291
--- /dev/null
+++ b/fs/notify/fanotify/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+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 000000000..a2a15bc4d
--- /dev/null
+++ b/fs/notify/fanotify/fanotify.c
@@ -0,0 +1,1076 @@
+// 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 <linux/statfs.h>
+#include <linux/stringhash.h>
+
+#include "fanotify.h"
+
+static bool fanotify_path_equal(const struct path *p1, const struct path *p2)
+{
+ return p1->mnt == p2->mnt && p1->dentry == p2->dentry;
+}
+
+static unsigned int fanotify_hash_path(const struct path *path)
+{
+ return hash_ptr(path->dentry, FANOTIFY_EVENT_HASH_BITS) ^
+ hash_ptr(path->mnt, FANOTIFY_EVENT_HASH_BITS);
+}
+
+static inline bool fanotify_fsid_equal(__kernel_fsid_t *fsid1,
+ __kernel_fsid_t *fsid2)
+{
+ return fsid1->val[0] == fsid2->val[0] && fsid1->val[1] == fsid2->val[1];
+}
+
+static unsigned int fanotify_hash_fsid(__kernel_fsid_t *fsid)
+{
+ return hash_32(fsid->val[0], FANOTIFY_EVENT_HASH_BITS) ^
+ hash_32(fsid->val[1], FANOTIFY_EVENT_HASH_BITS);
+}
+
+static bool fanotify_fh_equal(struct fanotify_fh *fh1,
+ struct fanotify_fh *fh2)
+{
+ if (fh1->type != fh2->type || fh1->len != fh2->len)
+ return false;
+
+ return !fh1->len ||
+ !memcmp(fanotify_fh_buf(fh1), fanotify_fh_buf(fh2), fh1->len);
+}
+
+static unsigned int fanotify_hash_fh(struct fanotify_fh *fh)
+{
+ long salt = (long)fh->type | (long)fh->len << 8;
+
+ /*
+ * full_name_hash() works long by long, so it handles fh buf optimally.
+ */
+ return full_name_hash((void *)salt, fanotify_fh_buf(fh), fh->len);
+}
+
+static bool fanotify_fid_event_equal(struct fanotify_fid_event *ffe1,
+ struct fanotify_fid_event *ffe2)
+{
+ /* Do not merge fid events without object fh */
+ if (!ffe1->object_fh.len)
+ return false;
+
+ return fanotify_fsid_equal(&ffe1->fsid, &ffe2->fsid) &&
+ fanotify_fh_equal(&ffe1->object_fh, &ffe2->object_fh);
+}
+
+static bool fanotify_info_equal(struct fanotify_info *info1,
+ struct fanotify_info *info2)
+{
+ if (info1->dir_fh_totlen != info2->dir_fh_totlen ||
+ info1->dir2_fh_totlen != info2->dir2_fh_totlen ||
+ info1->file_fh_totlen != info2->file_fh_totlen ||
+ info1->name_len != info2->name_len ||
+ info1->name2_len != info2->name2_len)
+ return false;
+
+ if (info1->dir_fh_totlen &&
+ !fanotify_fh_equal(fanotify_info_dir_fh(info1),
+ fanotify_info_dir_fh(info2)))
+ return false;
+
+ if (info1->dir2_fh_totlen &&
+ !fanotify_fh_equal(fanotify_info_dir2_fh(info1),
+ fanotify_info_dir2_fh(info2)))
+ return false;
+
+ if (info1->file_fh_totlen &&
+ !fanotify_fh_equal(fanotify_info_file_fh(info1),
+ fanotify_info_file_fh(info2)))
+ return false;
+
+ if (info1->name_len &&
+ memcmp(fanotify_info_name(info1), fanotify_info_name(info2),
+ info1->name_len))
+ return false;
+
+ return !info1->name2_len ||
+ !memcmp(fanotify_info_name2(info1), fanotify_info_name2(info2),
+ info1->name2_len);
+}
+
+static bool fanotify_name_event_equal(struct fanotify_name_event *fne1,
+ struct fanotify_name_event *fne2)
+{
+ struct fanotify_info *info1 = &fne1->info;
+ struct fanotify_info *info2 = &fne2->info;
+
+ /* Do not merge name events without dir fh */
+ if (!info1->dir_fh_totlen)
+ return false;
+
+ if (!fanotify_fsid_equal(&fne1->fsid, &fne2->fsid))
+ return false;
+
+ return fanotify_info_equal(info1, info2);
+}
+
+static bool fanotify_error_event_equal(struct fanotify_error_event *fee1,
+ struct fanotify_error_event *fee2)
+{
+ /* Error events against the same file system are always merged. */
+ if (!fanotify_fsid_equal(&fee1->fsid, &fee2->fsid))
+ return false;
+
+ return true;
+}
+
+static bool fanotify_should_merge(struct fanotify_event *old,
+ struct fanotify_event *new)
+{
+ pr_debug("%s: old=%p new=%p\n", __func__, old, new);
+
+ if (old->hash != new->hash ||
+ old->type != new->type || old->pid != new->pid)
+ return false;
+
+ /*
+ * We want to merge many dirent events in the same dir (i.e.
+ * creates/unlinks/renames), but we do not want to merge dirent
+ * events referring to subdirs with dirent events referring to
+ * non subdirs, otherwise, user won't be able to tell from a
+ * mask FAN_CREATE|FAN_DELETE|FAN_ONDIR if it describes mkdir+
+ * unlink pair or rmdir+create pair of events.
+ */
+ if ((old->mask & FS_ISDIR) != (new->mask & FS_ISDIR))
+ return false;
+
+ /*
+ * FAN_RENAME event is reported with special info record types,
+ * so we cannot merge it with other events.
+ */
+ if ((old->mask & FAN_RENAME) != (new->mask & FAN_RENAME))
+ return false;
+
+ switch (old->type) {
+ case FANOTIFY_EVENT_TYPE_PATH:
+ return fanotify_path_equal(fanotify_event_path(old),
+ fanotify_event_path(new));
+ case FANOTIFY_EVENT_TYPE_FID:
+ return fanotify_fid_event_equal(FANOTIFY_FE(old),
+ FANOTIFY_FE(new));
+ case FANOTIFY_EVENT_TYPE_FID_NAME:
+ return fanotify_name_event_equal(FANOTIFY_NE(old),
+ FANOTIFY_NE(new));
+ case FANOTIFY_EVENT_TYPE_FS_ERROR:
+ return fanotify_error_event_equal(FANOTIFY_EE(old),
+ FANOTIFY_EE(new));
+ default:
+ WARN_ON_ONCE(1);
+ }
+
+ return false;
+}
+
+/* Limit event merges to limit CPU overhead per event */
+#define FANOTIFY_MAX_MERGE_EVENTS 128
+
+/* and the list better be locked by something too! */
+static int fanotify_merge(struct fsnotify_group *group,
+ struct fsnotify_event *event)
+{
+ struct fanotify_event *old, *new = FANOTIFY_E(event);
+ unsigned int bucket = fanotify_event_hash_bucket(group, new);
+ struct hlist_head *hlist = &group->fanotify_data.merge_hash[bucket];
+ int i = 0;
+
+ pr_debug("%s: group=%p event=%p bucket=%u\n", __func__,
+ group, event, bucket);
+
+ /*
+ * 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(new->mask))
+ return 0;
+
+ hlist_for_each_entry(old, hlist, merge_list) {
+ if (++i > FANOTIFY_MAX_MERGE_EVENTS)
+ break;
+ if (fanotify_should_merge(old, new)) {
+ old->mask |= new->mask;
+
+ if (fanotify_is_error_event(old->mask))
+ FANOTIFY_EE(old)->err_count++;
+
+ return 1;
+ }
+ }
+
+ return 0;
+}
+
+/*
+ * Wait for response to permission event. The function also takes care of
+ * freeing the permission event (or offloads that in case the wait is canceled
+ * by a signal). The function returns 0 in case access got allowed by userspace,
+ * -EPERM in case userspace disallowed the access, and -ERESTARTSYS in case
+ * the wait got interrupted by a signal.
+ */
+static int fanotify_get_response(struct fsnotify_group *group,
+ struct fanotify_perm_event *event,
+ struct fsnotify_iter_info *iter_info)
+{
+ int ret;
+
+ pr_debug("%s: group=%p event=%p\n", __func__, group, event);
+
+ ret = wait_event_killable(group->fanotify_data.access_waitq,
+ event->state == FAN_EVENT_ANSWERED);
+ /* Signal pending? */
+ if (ret < 0) {
+ spin_lock(&group->notification_lock);
+ /* Event reported to userspace and no answer yet? */
+ if (event->state == FAN_EVENT_REPORTED) {
+ /* Event will get freed once userspace answers to it */
+ event->state = FAN_EVENT_CANCELED;
+ spin_unlock(&group->notification_lock);
+ return ret;
+ }
+ /* Event not yet reported? Just remove it. */
+ if (event->state == FAN_EVENT_INIT) {
+ fsnotify_remove_queued_event(group, &event->fae.fse);
+ /* Permission events are not supposed to be hashed */
+ WARN_ON_ONCE(!hlist_unhashed(&event->fae.merge_list));
+ }
+ /*
+ * Event may be also answered in case signal delivery raced
+ * with wakeup. In that case we have nothing to do besides
+ * freeing the event and reporting error.
+ */
+ spin_unlock(&group->notification_lock);
+ goto out;
+ }
+
+ /* 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);
+
+ pr_debug("%s: group=%p event=%p about to return ret=%d\n", __func__,
+ group, event, ret);
+out:
+ fsnotify_destroy_event(group, &event->fae.fse);
+
+ return ret;
+}
+
+/*
+ * This function returns a mask for an event that only contains the flags
+ * that have been specifically requested by the user. Flags that may have
+ * been included within the event mask, but have not been explicitly
+ * requested by the user, will not be present in the returned mask.
+ */
+static u32 fanotify_group_event_mask(struct fsnotify_group *group,
+ struct fsnotify_iter_info *iter_info,
+ u32 *match_mask, u32 event_mask,
+ const void *data, int data_type,
+ struct inode *dir)
+{
+ __u32 marks_mask = 0, marks_ignore_mask = 0;
+ __u32 test_mask, user_mask = FANOTIFY_OUTGOING_EVENTS |
+ FANOTIFY_EVENT_FLAGS;
+ const struct path *path = fsnotify_data_path(data, data_type);
+ unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
+ struct fsnotify_mark *mark;
+ bool ondir = event_mask & FAN_ONDIR;
+ 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 (!fid_mode) {
+ /* Do we have path to open a file descriptor? */
+ if (!path)
+ return 0;
+ /* Path type events are only relevant for files and dirs */
+ if (!d_is_reg(path->dentry) && !d_can_lookup(path->dentry))
+ return 0;
+ } else if (!(fid_mode & FAN_REPORT_FID)) {
+ /* Do we have a directory inode to report? */
+ if (!dir && !ondir)
+ return 0;
+ }
+
+ fsnotify_foreach_iter_mark_type(iter_info, mark, type) {
+ /*
+ * Apply ignore mask depending on event flags in ignore mask.
+ */
+ marks_ignore_mask |=
+ fsnotify_effective_ignore_mask(mark, ondir, type);
+
+ /*
+ * Send the event depending on event flags in mark mask.
+ */
+ if (!fsnotify_mask_applicable(mark->mask, ondir, type))
+ continue;
+
+ marks_mask |= mark->mask;
+
+ /* Record the mark types of this group that matched the event */
+ *match_mask |= 1U << type;
+ }
+
+ test_mask = event_mask & marks_mask & ~marks_ignore_mask;
+
+ /*
+ * For dirent modification events (create/delete/move) that do not carry
+ * the child entry name information, we report FAN_ONDIR for mkdir/rmdir
+ * so user can differentiate them from creat/unlink.
+ *
+ * For backward compatibility and consistency, do not report FAN_ONDIR
+ * to user in legacy fanotify mode (reporting fd) and report FAN_ONDIR
+ * to user in fid mode for all event types.
+ *
+ * We never report FAN_EVENT_ON_CHILD to user, but we do pass it in to
+ * fanotify_alloc_event() when group is reporting fid as indication
+ * that event happened on child.
+ */
+ if (fid_mode) {
+ /* Do not report event flags without any event */
+ if (!(test_mask & ~FANOTIFY_EVENT_FLAGS))
+ return 0;
+ } else {
+ user_mask &= ~FANOTIFY_EVENT_FLAGS;
+ }
+
+ return test_mask & user_mask;
+}
+
+/*
+ * Check size needed to encode fanotify_fh.
+ *
+ * Return size of encoded fh without fanotify_fh header.
+ * Return 0 on failure to encode.
+ */
+static int fanotify_encode_fh_len(struct inode *inode)
+{
+ int dwords = 0;
+ int fh_len;
+
+ if (!inode)
+ return 0;
+
+ exportfs_encode_inode_fh(inode, NULL, &dwords, NULL);
+ fh_len = dwords << 2;
+
+ /*
+ * struct fanotify_error_event might be preallocated and is
+ * limited to MAX_HANDLE_SZ. This should never happen, but
+ * safeguard by forcing an invalid file handle.
+ */
+ if (WARN_ON_ONCE(fh_len > MAX_HANDLE_SZ))
+ return 0;
+
+ return fh_len;
+}
+
+/*
+ * Encode fanotify_fh.
+ *
+ * Return total size of encoded fh including fanotify_fh header.
+ * Return 0 on failure to encode.
+ */
+static int fanotify_encode_fh(struct fanotify_fh *fh, struct inode *inode,
+ unsigned int fh_len, unsigned int *hash,
+ gfp_t gfp)
+{
+ int dwords, type = 0;
+ char *ext_buf = NULL;
+ void *buf = fh->buf;
+ int err;
+
+ fh->type = FILEID_ROOT;
+ fh->len = 0;
+ fh->flags = 0;
+
+ /*
+ * Invalid FHs are used by FAN_FS_ERROR for errors not
+ * linked to any inode. The f_handle won't be reported
+ * back to userspace.
+ */
+ if (!inode)
+ goto out;
+
+ /*
+ * !gpf means preallocated variable size fh, but fh_len could
+ * be zero in that case if encoding fh len failed.
+ */
+ err = -ENOENT;
+ if (fh_len < 4 || WARN_ON_ONCE(fh_len % 4) || fh_len > MAX_HANDLE_SZ)
+ goto out_err;
+
+ /* No external buffer in a variable size allocated fh */
+ if (gfp && fh_len > FANOTIFY_INLINE_FH_LEN) {
+ /* Treat failure to allocate fh as failure to encode fh */
+ err = -ENOMEM;
+ ext_buf = kmalloc(fh_len, gfp);
+ if (!ext_buf)
+ goto out_err;
+
+ *fanotify_fh_ext_buf_ptr(fh) = ext_buf;
+ buf = ext_buf;
+ fh->flags |= FANOTIFY_FH_FLAG_EXT_BUF;
+ }
+
+ dwords = fh_len >> 2;
+ type = exportfs_encode_inode_fh(inode, buf, &dwords, NULL);
+ err = -EINVAL;
+ if (!type || type == FILEID_INVALID || fh_len != dwords << 2)
+ goto out_err;
+
+ fh->type = type;
+ fh->len = fh_len;
+
+out:
+ /*
+ * Mix fh into event merge key. Hash might be NULL in case of
+ * unhashed FID events (i.e. FAN_FS_ERROR).
+ */
+ if (hash)
+ *hash ^= fanotify_hash_fh(fh);
+
+ return FANOTIFY_FH_HDR_LEN + fh_len;
+
+out_err:
+ pr_warn_ratelimited("fanotify: failed to encode fid (type=%d, len=%d, err=%i)\n",
+ type, fh_len, err);
+ kfree(ext_buf);
+ *fanotify_fh_ext_buf_ptr(fh) = NULL;
+ /* Report the event without a file identifier on encode error */
+ fh->type = FILEID_INVALID;
+ fh->len = 0;
+ return 0;
+}
+
+/*
+ * FAN_REPORT_FID is ambiguous in that it reports the fid of the child for
+ * some events and the fid of the parent for create/delete/move events.
+ *
+ * With the FAN_REPORT_TARGET_FID flag, the fid of the child is reported
+ * also in create/delete/move events in addition to the fid of the parent
+ * and the name of the child.
+ */
+static inline bool fanotify_report_child_fid(unsigned int fid_mode, u32 mask)
+{
+ if (mask & ALL_FSNOTIFY_DIRENT_EVENTS)
+ return (fid_mode & FAN_REPORT_TARGET_FID);
+
+ return (fid_mode & FAN_REPORT_FID) && !(mask & FAN_ONDIR);
+}
+
+/*
+ * The inode to use as identifier when reporting fid depends on the event
+ * and the group flags.
+ *
+ * With the group flag FAN_REPORT_TARGET_FID, always report the child fid.
+ *
+ * Without the group flag FAN_REPORT_TARGET_FID, report the modified directory
+ * fid on dirent events and the child fid otherwise.
+ *
+ * For example:
+ * FS_ATTRIB reports the child fid even if reported on a watched parent.
+ * FS_CREATE reports the modified dir fid without FAN_REPORT_TARGET_FID.
+ * and reports the created child fid with FAN_REPORT_TARGET_FID.
+ */
+static struct inode *fanotify_fid_inode(u32 event_mask, const void *data,
+ int data_type, struct inode *dir,
+ unsigned int fid_mode)
+{
+ if ((event_mask & ALL_FSNOTIFY_DIRENT_EVENTS) &&
+ !(fid_mode & FAN_REPORT_TARGET_FID))
+ return dir;
+
+ return fsnotify_data_inode(data, data_type);
+}
+
+/*
+ * The inode to use as identifier when reporting dir fid depends on the event.
+ * Report the modified directory inode on dirent modification events.
+ * Report the "victim" inode if "victim" is a directory.
+ * Report the parent inode if "victim" is not a directory and event is
+ * reported to parent.
+ * Otherwise, do not report dir fid.
+ */
+static struct inode *fanotify_dfid_inode(u32 event_mask, const void *data,
+ int data_type, struct inode *dir)
+{
+ struct inode *inode = fsnotify_data_inode(data, data_type);
+
+ if (event_mask & ALL_FSNOTIFY_DIRENT_EVENTS)
+ return dir;
+
+ if (inode && S_ISDIR(inode->i_mode))
+ return inode;
+
+ return dir;
+}
+
+static struct fanotify_event *fanotify_alloc_path_event(const struct path *path,
+ unsigned int *hash,
+ gfp_t gfp)
+{
+ struct fanotify_path_event *pevent;
+
+ pevent = kmem_cache_alloc(fanotify_path_event_cachep, gfp);
+ if (!pevent)
+ return NULL;
+
+ pevent->fae.type = FANOTIFY_EVENT_TYPE_PATH;
+ pevent->path = *path;
+ *hash ^= fanotify_hash_path(path);
+ path_get(path);
+
+ return &pevent->fae;
+}
+
+static struct fanotify_event *fanotify_alloc_perm_event(const struct path *path,
+ gfp_t gfp)
+{
+ struct fanotify_perm_event *pevent;
+
+ pevent = kmem_cache_alloc(fanotify_perm_event_cachep, gfp);
+ if (!pevent)
+ return NULL;
+
+ pevent->fae.type = FANOTIFY_EVENT_TYPE_PATH_PERM;
+ pevent->response = 0;
+ pevent->state = FAN_EVENT_INIT;
+ pevent->path = *path;
+ path_get(path);
+
+ return &pevent->fae;
+}
+
+static struct fanotify_event *fanotify_alloc_fid_event(struct inode *id,
+ __kernel_fsid_t *fsid,
+ unsigned int *hash,
+ gfp_t gfp)
+{
+ struct fanotify_fid_event *ffe;
+
+ ffe = kmem_cache_alloc(fanotify_fid_event_cachep, gfp);
+ if (!ffe)
+ return NULL;
+
+ ffe->fae.type = FANOTIFY_EVENT_TYPE_FID;
+ ffe->fsid = *fsid;
+ *hash ^= fanotify_hash_fsid(fsid);
+ fanotify_encode_fh(&ffe->object_fh, id, fanotify_encode_fh_len(id),
+ hash, gfp);
+
+ return &ffe->fae;
+}
+
+static struct fanotify_event *fanotify_alloc_name_event(struct inode *dir,
+ __kernel_fsid_t *fsid,
+ const struct qstr *name,
+ struct inode *child,
+ struct dentry *moved,
+ unsigned int *hash,
+ gfp_t gfp)
+{
+ struct fanotify_name_event *fne;
+ struct fanotify_info *info;
+ struct fanotify_fh *dfh, *ffh;
+ struct inode *dir2 = moved ? d_inode(moved->d_parent) : NULL;
+ const struct qstr *name2 = moved ? &moved->d_name : NULL;
+ unsigned int dir_fh_len = fanotify_encode_fh_len(dir);
+ unsigned int dir2_fh_len = fanotify_encode_fh_len(dir2);
+ unsigned int child_fh_len = fanotify_encode_fh_len(child);
+ unsigned long name_len = name ? name->len : 0;
+ unsigned long name2_len = name2 ? name2->len : 0;
+ unsigned int len, size;
+
+ /* Reserve terminating null byte even for empty name */
+ size = sizeof(*fne) + name_len + name2_len + 2;
+ if (dir_fh_len)
+ size += FANOTIFY_FH_HDR_LEN + dir_fh_len;
+ if (dir2_fh_len)
+ size += FANOTIFY_FH_HDR_LEN + dir2_fh_len;
+ if (child_fh_len)
+ size += FANOTIFY_FH_HDR_LEN + child_fh_len;
+ fne = kmalloc(size, gfp);
+ if (!fne)
+ return NULL;
+
+ fne->fae.type = FANOTIFY_EVENT_TYPE_FID_NAME;
+ fne->fsid = *fsid;
+ *hash ^= fanotify_hash_fsid(fsid);
+ info = &fne->info;
+ fanotify_info_init(info);
+ if (dir_fh_len) {
+ dfh = fanotify_info_dir_fh(info);
+ len = fanotify_encode_fh(dfh, dir, dir_fh_len, hash, 0);
+ fanotify_info_set_dir_fh(info, len);
+ }
+ if (dir2_fh_len) {
+ dfh = fanotify_info_dir2_fh(info);
+ len = fanotify_encode_fh(dfh, dir2, dir2_fh_len, hash, 0);
+ fanotify_info_set_dir2_fh(info, len);
+ }
+ if (child_fh_len) {
+ ffh = fanotify_info_file_fh(info);
+ len = fanotify_encode_fh(ffh, child, child_fh_len, hash, 0);
+ fanotify_info_set_file_fh(info, len);
+ }
+ if (name_len) {
+ fanotify_info_copy_name(info, name);
+ *hash ^= full_name_hash((void *)name_len, name->name, name_len);
+ }
+ if (name2_len) {
+ fanotify_info_copy_name2(info, name2);
+ *hash ^= full_name_hash((void *)name2_len, name2->name,
+ name2_len);
+ }
+
+ pr_debug("%s: size=%u dir_fh_len=%u child_fh_len=%u name_len=%u name='%.*s'\n",
+ __func__, size, dir_fh_len, child_fh_len,
+ info->name_len, info->name_len, fanotify_info_name(info));
+
+ if (dir2_fh_len) {
+ pr_debug("%s: dir2_fh_len=%u name2_len=%u name2='%.*s'\n",
+ __func__, dir2_fh_len, info->name2_len,
+ info->name2_len, fanotify_info_name2(info));
+ }
+
+ return &fne->fae;
+}
+
+static struct fanotify_event *fanotify_alloc_error_event(
+ struct fsnotify_group *group,
+ __kernel_fsid_t *fsid,
+ const void *data, int data_type,
+ unsigned int *hash)
+{
+ struct fs_error_report *report =
+ fsnotify_data_error_report(data, data_type);
+ struct inode *inode;
+ struct fanotify_error_event *fee;
+ int fh_len;
+
+ if (WARN_ON_ONCE(!report))
+ return NULL;
+
+ fee = mempool_alloc(&group->fanotify_data.error_events_pool, GFP_NOFS);
+ if (!fee)
+ return NULL;
+
+ fee->fae.type = FANOTIFY_EVENT_TYPE_FS_ERROR;
+ fee->error = report->error;
+ fee->err_count = 1;
+ fee->fsid = *fsid;
+
+ inode = report->inode;
+ fh_len = fanotify_encode_fh_len(inode);
+
+ /* Bad fh_len. Fallback to using an invalid fh. Should never happen. */
+ if (!fh_len && inode)
+ inode = NULL;
+
+ fanotify_encode_fh(&fee->object_fh, inode, fh_len, NULL, 0);
+
+ *hash ^= fanotify_hash_fsid(fsid);
+
+ return &fee->fae;
+}
+
+static struct fanotify_event *fanotify_alloc_event(
+ struct fsnotify_group *group,
+ u32 mask, const void *data, int data_type,
+ struct inode *dir, const struct qstr *file_name,
+ __kernel_fsid_t *fsid, u32 match_mask)
+{
+ struct fanotify_event *event = NULL;
+ gfp_t gfp = GFP_KERNEL_ACCOUNT;
+ unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
+ struct inode *id = fanotify_fid_inode(mask, data, data_type, dir,
+ fid_mode);
+ struct inode *dirid = fanotify_dfid_inode(mask, data, data_type, dir);
+ const struct path *path = fsnotify_data_path(data, data_type);
+ struct mem_cgroup *old_memcg;
+ struct dentry *moved = NULL;
+ struct inode *child = NULL;
+ bool name_event = false;
+ unsigned int hash = 0;
+ bool ondir = mask & FAN_ONDIR;
+ struct pid *pid;
+
+ if ((fid_mode & FAN_REPORT_DIR_FID) && dirid) {
+ /*
+ * For certain events and group flags, report the child fid
+ * in addition to reporting the parent fid and maybe child name.
+ */
+ if (fanotify_report_child_fid(fid_mode, mask) && id != dirid)
+ child = id;
+
+ id = dirid;
+
+ /*
+ * We record file name only in a group with FAN_REPORT_NAME
+ * and when we have a directory inode to report.
+ *
+ * For directory entry modification event, we record the fid of
+ * the directory and the name of the modified entry.
+ *
+ * For event on non-directory that is reported to parent, we
+ * record the fid of the parent and the name of the child.
+ *
+ * Even if not reporting name, we need a variable length
+ * fanotify_name_event if reporting both parent and child fids.
+ */
+ if (!(fid_mode & FAN_REPORT_NAME)) {
+ name_event = !!child;
+ file_name = NULL;
+ } else if ((mask & ALL_FSNOTIFY_DIRENT_EVENTS) || !ondir) {
+ name_event = true;
+ }
+
+ /*
+ * In the special case of FAN_RENAME event, use the match_mask
+ * to determine if we need to report only the old parent+name,
+ * only the new parent+name or both.
+ * 'dirid' and 'file_name' are the old parent+name and
+ * 'moved' has the new parent+name.
+ */
+ if (mask & FAN_RENAME) {
+ bool report_old, report_new;
+
+ if (WARN_ON_ONCE(!match_mask))
+ return NULL;
+
+ /* Report both old and new parent+name if sb watching */
+ report_old = report_new =
+ match_mask & (1U << FSNOTIFY_ITER_TYPE_SB);
+ report_old |=
+ match_mask & (1U << FSNOTIFY_ITER_TYPE_INODE);
+ report_new |=
+ match_mask & (1U << FSNOTIFY_ITER_TYPE_INODE2);
+
+ if (!report_old) {
+ /* Do not report old parent+name */
+ dirid = NULL;
+ file_name = NULL;
+ }
+ if (report_new) {
+ /* Report new parent+name */
+ moved = fsnotify_data_dentry(data, data_type);
+ }
+ }
+ }
+
+ /*
+ * For queues with unlimited length lost events are not expected and
+ * can possibly have security implications. Avoid losing events when
+ * memory is short. For the limited size queues, avoid OOM killer in the
+ * target monitoring memcg as it may have security repercussion.
+ */
+ if (group->max_events == UINT_MAX)
+ gfp |= __GFP_NOFAIL;
+ else
+ gfp |= __GFP_RETRY_MAYFAIL;
+
+ /* Whoever is interested in the event, pays for the allocation. */
+ old_memcg = set_active_memcg(group->memcg);
+
+ if (fanotify_is_perm_event(mask)) {
+ event = fanotify_alloc_perm_event(path, gfp);
+ } else if (fanotify_is_error_event(mask)) {
+ event = fanotify_alloc_error_event(group, fsid, data,
+ data_type, &hash);
+ } else if (name_event && (file_name || moved || child)) {
+ event = fanotify_alloc_name_event(dirid, fsid, file_name, child,
+ moved, &hash, gfp);
+ } else if (fid_mode) {
+ event = fanotify_alloc_fid_event(id, fsid, &hash, gfp);
+ } else {
+ event = fanotify_alloc_path_event(path, &hash, gfp);
+ }
+
+ if (!event)
+ goto out;
+
+ if (FAN_GROUP_FLAG(group, FAN_REPORT_TID))
+ pid = get_pid(task_pid(current));
+ else
+ pid = get_pid(task_tgid(current));
+
+ /* Mix event info, FAN_ONDIR flag and pid into event merge key */
+ hash ^= hash_long((unsigned long)pid | ondir, FANOTIFY_EVENT_HASH_BITS);
+ fanotify_init_event(event, hash, mask);
+ event->pid = pid;
+
+out:
+ set_active_memcg(old_memcg);
+ return event;
+}
+
+/*
+ * Get cached fsid of the filesystem containing the object from any connector.
+ * All connectors are supposed to have the same fsid, but we do not verify that
+ * here.
+ */
+static __kernel_fsid_t fanotify_get_fsid(struct fsnotify_iter_info *iter_info)
+{
+ struct fsnotify_mark *mark;
+ int type;
+ __kernel_fsid_t fsid = {};
+
+ fsnotify_foreach_iter_mark_type(iter_info, mark, type) {
+ struct fsnotify_mark_connector *conn;
+
+ conn = READ_ONCE(mark->connector);
+ /* Mark is just getting destroyed or created? */
+ if (!conn)
+ continue;
+ if (!(conn->flags & FSNOTIFY_CONN_FLAG_HAS_FSID))
+ continue;
+ /* Pairs with smp_wmb() in fsnotify_add_mark_list() */
+ smp_rmb();
+ fsid = conn->fsid;
+ if (WARN_ON_ONCE(!fsid.val[0] && !fsid.val[1]))
+ continue;
+ return fsid;
+ }
+
+ return fsid;
+}
+
+/*
+ * Add an event to hash table for faster merge.
+ */
+static void fanotify_insert_event(struct fsnotify_group *group,
+ struct fsnotify_event *fsn_event)
+{
+ struct fanotify_event *event = FANOTIFY_E(fsn_event);
+ unsigned int bucket = fanotify_event_hash_bucket(group, event);
+ struct hlist_head *hlist = &group->fanotify_data.merge_hash[bucket];
+
+ assert_spin_locked(&group->notification_lock);
+
+ if (!fanotify_is_hashed_event(event->mask))
+ return;
+
+ pr_debug("%s: group=%p event=%p bucket=%u\n", __func__,
+ group, event, bucket);
+
+ hlist_add_head(&event->merge_list, hlist);
+}
+
+static int fanotify_handle_event(struct fsnotify_group *group, u32 mask,
+ const void *data, int data_type,
+ struct inode *dir,
+ const struct qstr *file_name, u32 cookie,
+ struct fsnotify_iter_info *iter_info)
+{
+ int ret = 0;
+ struct fanotify_event *event;
+ struct fsnotify_event *fsn_event;
+ __kernel_fsid_t fsid = {};
+ u32 match_mask = 0;
+
+ BUILD_BUG_ON(FAN_ACCESS != FS_ACCESS);
+ BUILD_BUG_ON(FAN_MODIFY != FS_MODIFY);
+ BUILD_BUG_ON(FAN_ATTRIB != FS_ATTRIB);
+ 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_MOVED_TO != FS_MOVED_TO);
+ BUILD_BUG_ON(FAN_MOVED_FROM != FS_MOVED_FROM);
+ BUILD_BUG_ON(FAN_CREATE != FS_CREATE);
+ BUILD_BUG_ON(FAN_DELETE != FS_DELETE);
+ BUILD_BUG_ON(FAN_DELETE_SELF != FS_DELETE_SELF);
+ BUILD_BUG_ON(FAN_MOVE_SELF != FS_MOVE_SELF);
+ 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);
+ BUILD_BUG_ON(FAN_OPEN_EXEC != FS_OPEN_EXEC);
+ BUILD_BUG_ON(FAN_OPEN_EXEC_PERM != FS_OPEN_EXEC_PERM);
+ BUILD_BUG_ON(FAN_FS_ERROR != FS_ERROR);
+ BUILD_BUG_ON(FAN_RENAME != FS_RENAME);
+
+ BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 21);
+
+ mask = fanotify_group_event_mask(group, iter_info, &match_mask,
+ mask, data, data_type, dir);
+ if (!mask)
+ return 0;
+
+ pr_debug("%s: group=%p mask=%x report_mask=%x\n", __func__,
+ group, mask, match_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;
+ }
+
+ if (FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS)) {
+ fsid = fanotify_get_fsid(iter_info);
+ /* Racing with mark destruction or creation? */
+ if (!fsid.val[0] && !fsid.val[1])
+ return 0;
+ }
+
+ event = fanotify_alloc_event(group, mask, data, data_type, dir,
+ file_name, &fsid, match_mask);
+ 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_insert_event(group, fsn_event, fanotify_merge,
+ fanotify_insert_event);
+ if (ret) {
+ /* Permission events shouldn't be merged */
+ BUG_ON(ret == 1 && mask & FANOTIFY_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_PERM(event),
+ iter_info);
+ }
+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)
+{
+ kfree(group->fanotify_data.merge_hash);
+ if (group->fanotify_data.ucounts)
+ dec_ucount(group->fanotify_data.ucounts,
+ UCOUNT_FANOTIFY_GROUPS);
+
+ if (mempool_initialized(&group->fanotify_data.error_events_pool))
+ mempool_exit(&group->fanotify_data.error_events_pool);
+}
+
+static void fanotify_free_path_event(struct fanotify_event *event)
+{
+ path_put(fanotify_event_path(event));
+ kmem_cache_free(fanotify_path_event_cachep, FANOTIFY_PE(event));
+}
+
+static void fanotify_free_perm_event(struct fanotify_event *event)
+{
+ path_put(fanotify_event_path(event));
+ kmem_cache_free(fanotify_perm_event_cachep, FANOTIFY_PERM(event));
+}
+
+static void fanotify_free_fid_event(struct fanotify_event *event)
+{
+ struct fanotify_fid_event *ffe = FANOTIFY_FE(event);
+
+ if (fanotify_fh_has_ext_buf(&ffe->object_fh))
+ kfree(fanotify_fh_ext_buf(&ffe->object_fh));
+ kmem_cache_free(fanotify_fid_event_cachep, ffe);
+}
+
+static void fanotify_free_name_event(struct fanotify_event *event)
+{
+ kfree(FANOTIFY_NE(event));
+}
+
+static void fanotify_free_error_event(struct fsnotify_group *group,
+ struct fanotify_event *event)
+{
+ struct fanotify_error_event *fee = FANOTIFY_EE(event);
+
+ mempool_free(fee, &group->fanotify_data.error_events_pool);
+}
+
+static void fanotify_free_event(struct fsnotify_group *group,
+ struct fsnotify_event *fsn_event)
+{
+ struct fanotify_event *event;
+
+ event = FANOTIFY_E(fsn_event);
+ put_pid(event->pid);
+ switch (event->type) {
+ case FANOTIFY_EVENT_TYPE_PATH:
+ fanotify_free_path_event(event);
+ break;
+ case FANOTIFY_EVENT_TYPE_PATH_PERM:
+ fanotify_free_perm_event(event);
+ break;
+ case FANOTIFY_EVENT_TYPE_FID:
+ fanotify_free_fid_event(event);
+ break;
+ case FANOTIFY_EVENT_TYPE_FID_NAME:
+ fanotify_free_name_event(event);
+ break;
+ case FANOTIFY_EVENT_TYPE_OVERFLOW:
+ kfree(event);
+ break;
+ case FANOTIFY_EVENT_TYPE_FS_ERROR:
+ fanotify_free_error_event(group, event);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ }
+}
+
+static void fanotify_freeing_mark(struct fsnotify_mark *mark,
+ struct fsnotify_group *group)
+{
+ if (!FAN_GROUP_FLAG(group, FAN_UNLIMITED_MARKS))
+ dec_ucount(group->fanotify_data.ucounts, UCOUNT_FANOTIFY_MARKS);
+}
+
+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,
+ .freeing_mark = fanotify_freeing_mark,
+ .free_mark = fanotify_free_mark,
+};
diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h
new file mode 100644
index 000000000..57f51a9a3
--- /dev/null
+++ b/fs/notify/fanotify/fanotify.h
@@ -0,0 +1,500 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/fsnotify_backend.h>
+#include <linux/path.h>
+#include <linux/slab.h>
+#include <linux/exportfs.h>
+#include <linux/hashtable.h>
+
+extern struct kmem_cache *fanotify_mark_cache;
+extern struct kmem_cache *fanotify_fid_event_cachep;
+extern struct kmem_cache *fanotify_path_event_cachep;
+extern struct kmem_cache *fanotify_perm_event_cachep;
+
+/* Possible states of the permission event */
+enum {
+ FAN_EVENT_INIT,
+ FAN_EVENT_REPORTED,
+ FAN_EVENT_ANSWERED,
+ FAN_EVENT_CANCELED,
+};
+
+/*
+ * 3 dwords are sufficient for most local fs (64bit ino, 32bit generation).
+ * fh buf should be dword aligned. On 64bit arch, the ext_buf pointer is
+ * stored in either the first or last 2 dwords.
+ */
+#define FANOTIFY_INLINE_FH_LEN (3 << 2)
+#define FANOTIFY_FH_HDR_LEN offsetof(struct fanotify_fh, buf)
+
+/* Fixed size struct for file handle */
+struct fanotify_fh {
+ u8 type;
+ u8 len;
+#define FANOTIFY_FH_FLAG_EXT_BUF 1
+ u8 flags;
+ u8 pad;
+ unsigned char buf[];
+} __aligned(4);
+
+/* Variable size struct for dir file handle + child file handle + name */
+struct fanotify_info {
+ /* size of dir_fh/file_fh including fanotify_fh hdr size */
+ u8 dir_fh_totlen;
+ u8 dir2_fh_totlen;
+ u8 file_fh_totlen;
+ u8 name_len;
+ u8 name2_len;
+ u8 pad[3];
+ unsigned char buf[];
+ /*
+ * (struct fanotify_fh) dir_fh starts at buf[0]
+ * (optional) dir2_fh starts at buf[dir_fh_totlen]
+ * (optional) file_fh starts at buf[dir_fh_totlen + dir2_fh_totlen]
+ * name starts at buf[dir_fh_totlen + dir2_fh_totlen + file_fh_totlen]
+ * ...
+ */
+#define FANOTIFY_DIR_FH_SIZE(info) ((info)->dir_fh_totlen)
+#define FANOTIFY_DIR2_FH_SIZE(info) ((info)->dir2_fh_totlen)
+#define FANOTIFY_FILE_FH_SIZE(info) ((info)->file_fh_totlen)
+#define FANOTIFY_NAME_SIZE(info) ((info)->name_len + 1)
+#define FANOTIFY_NAME2_SIZE(info) ((info)->name2_len + 1)
+
+#define FANOTIFY_DIR_FH_OFFSET(info) 0
+#define FANOTIFY_DIR2_FH_OFFSET(info) \
+ (FANOTIFY_DIR_FH_OFFSET(info) + FANOTIFY_DIR_FH_SIZE(info))
+#define FANOTIFY_FILE_FH_OFFSET(info) \
+ (FANOTIFY_DIR2_FH_OFFSET(info) + FANOTIFY_DIR2_FH_SIZE(info))
+#define FANOTIFY_NAME_OFFSET(info) \
+ (FANOTIFY_FILE_FH_OFFSET(info) + FANOTIFY_FILE_FH_SIZE(info))
+#define FANOTIFY_NAME2_OFFSET(info) \
+ (FANOTIFY_NAME_OFFSET(info) + FANOTIFY_NAME_SIZE(info))
+
+#define FANOTIFY_DIR_FH_BUF(info) \
+ ((info)->buf + FANOTIFY_DIR_FH_OFFSET(info))
+#define FANOTIFY_DIR2_FH_BUF(info) \
+ ((info)->buf + FANOTIFY_DIR2_FH_OFFSET(info))
+#define FANOTIFY_FILE_FH_BUF(info) \
+ ((info)->buf + FANOTIFY_FILE_FH_OFFSET(info))
+#define FANOTIFY_NAME_BUF(info) \
+ ((info)->buf + FANOTIFY_NAME_OFFSET(info))
+#define FANOTIFY_NAME2_BUF(info) \
+ ((info)->buf + FANOTIFY_NAME2_OFFSET(info))
+} __aligned(4);
+
+static inline bool fanotify_fh_has_ext_buf(struct fanotify_fh *fh)
+{
+ return (fh->flags & FANOTIFY_FH_FLAG_EXT_BUF);
+}
+
+static inline char **fanotify_fh_ext_buf_ptr(struct fanotify_fh *fh)
+{
+ BUILD_BUG_ON(FANOTIFY_FH_HDR_LEN % 4);
+ BUILD_BUG_ON(__alignof__(char *) - 4 + sizeof(char *) >
+ FANOTIFY_INLINE_FH_LEN);
+ return (char **)ALIGN((unsigned long)(fh->buf), __alignof__(char *));
+}
+
+static inline void *fanotify_fh_ext_buf(struct fanotify_fh *fh)
+{
+ return *fanotify_fh_ext_buf_ptr(fh);
+}
+
+static inline void *fanotify_fh_buf(struct fanotify_fh *fh)
+{
+ return fanotify_fh_has_ext_buf(fh) ? fanotify_fh_ext_buf(fh) : fh->buf;
+}
+
+static inline int fanotify_info_dir_fh_len(struct fanotify_info *info)
+{
+ if (!info->dir_fh_totlen ||
+ WARN_ON_ONCE(info->dir_fh_totlen < FANOTIFY_FH_HDR_LEN))
+ return 0;
+
+ return info->dir_fh_totlen - FANOTIFY_FH_HDR_LEN;
+}
+
+static inline struct fanotify_fh *fanotify_info_dir_fh(struct fanotify_info *info)
+{
+ BUILD_BUG_ON(offsetof(struct fanotify_info, buf) % 4);
+
+ return (struct fanotify_fh *)FANOTIFY_DIR_FH_BUF(info);
+}
+
+static inline int fanotify_info_dir2_fh_len(struct fanotify_info *info)
+{
+ if (!info->dir2_fh_totlen ||
+ WARN_ON_ONCE(info->dir2_fh_totlen < FANOTIFY_FH_HDR_LEN))
+ return 0;
+
+ return info->dir2_fh_totlen - FANOTIFY_FH_HDR_LEN;
+}
+
+static inline struct fanotify_fh *fanotify_info_dir2_fh(struct fanotify_info *info)
+{
+ return (struct fanotify_fh *)FANOTIFY_DIR2_FH_BUF(info);
+}
+
+static inline int fanotify_info_file_fh_len(struct fanotify_info *info)
+{
+ if (!info->file_fh_totlen ||
+ WARN_ON_ONCE(info->file_fh_totlen < FANOTIFY_FH_HDR_LEN))
+ return 0;
+
+ return info->file_fh_totlen - FANOTIFY_FH_HDR_LEN;
+}
+
+static inline struct fanotify_fh *fanotify_info_file_fh(struct fanotify_info *info)
+{
+ return (struct fanotify_fh *)FANOTIFY_FILE_FH_BUF(info);
+}
+
+static inline char *fanotify_info_name(struct fanotify_info *info)
+{
+ if (!info->name_len)
+ return NULL;
+
+ return FANOTIFY_NAME_BUF(info);
+}
+
+static inline char *fanotify_info_name2(struct fanotify_info *info)
+{
+ if (!info->name2_len)
+ return NULL;
+
+ return FANOTIFY_NAME2_BUF(info);
+}
+
+static inline void fanotify_info_init(struct fanotify_info *info)
+{
+ BUILD_BUG_ON(FANOTIFY_FH_HDR_LEN + MAX_HANDLE_SZ > U8_MAX);
+ BUILD_BUG_ON(NAME_MAX > U8_MAX);
+
+ info->dir_fh_totlen = 0;
+ info->dir2_fh_totlen = 0;
+ info->file_fh_totlen = 0;
+ info->name_len = 0;
+ info->name2_len = 0;
+}
+
+/* These set/copy helpers MUST be called by order */
+static inline void fanotify_info_set_dir_fh(struct fanotify_info *info,
+ unsigned int totlen)
+{
+ if (WARN_ON_ONCE(info->dir2_fh_totlen > 0) ||
+ WARN_ON_ONCE(info->file_fh_totlen > 0) ||
+ WARN_ON_ONCE(info->name_len > 0) ||
+ WARN_ON_ONCE(info->name2_len > 0))
+ return;
+
+ info->dir_fh_totlen = totlen;
+}
+
+static inline void fanotify_info_set_dir2_fh(struct fanotify_info *info,
+ unsigned int totlen)
+{
+ if (WARN_ON_ONCE(info->file_fh_totlen > 0) ||
+ WARN_ON_ONCE(info->name_len > 0) ||
+ WARN_ON_ONCE(info->name2_len > 0))
+ return;
+
+ info->dir2_fh_totlen = totlen;
+}
+
+static inline void fanotify_info_set_file_fh(struct fanotify_info *info,
+ unsigned int totlen)
+{
+ if (WARN_ON_ONCE(info->name_len > 0) ||
+ WARN_ON_ONCE(info->name2_len > 0))
+ return;
+
+ info->file_fh_totlen = totlen;
+}
+
+static inline void fanotify_info_copy_name(struct fanotify_info *info,
+ const struct qstr *name)
+{
+ if (WARN_ON_ONCE(name->len > NAME_MAX) ||
+ WARN_ON_ONCE(info->name2_len > 0))
+ return;
+
+ info->name_len = name->len;
+ strcpy(fanotify_info_name(info), name->name);
+}
+
+static inline void fanotify_info_copy_name2(struct fanotify_info *info,
+ const struct qstr *name)
+{
+ if (WARN_ON_ONCE(name->len > NAME_MAX))
+ return;
+
+ info->name2_len = name->len;
+ strcpy(fanotify_info_name2(info), name->name);
+}
+
+/*
+ * Common structure for fanotify events. Concrete structs are allocated in
+ * fanotify_handle_event() and freed when the information is retrieved by
+ * userspace. The type of event determines how it was allocated, how it will
+ * be freed and which concrete struct it may be cast to.
+ */
+enum fanotify_event_type {
+ FANOTIFY_EVENT_TYPE_FID, /* fixed length */
+ FANOTIFY_EVENT_TYPE_FID_NAME, /* variable length */
+ FANOTIFY_EVENT_TYPE_PATH,
+ FANOTIFY_EVENT_TYPE_PATH_PERM,
+ FANOTIFY_EVENT_TYPE_OVERFLOW, /* struct fanotify_event */
+ FANOTIFY_EVENT_TYPE_FS_ERROR, /* struct fanotify_error_event */
+ __FANOTIFY_EVENT_TYPE_NUM
+};
+
+#define FANOTIFY_EVENT_TYPE_BITS \
+ (ilog2(__FANOTIFY_EVENT_TYPE_NUM - 1) + 1)
+#define FANOTIFY_EVENT_HASH_BITS \
+ (32 - FANOTIFY_EVENT_TYPE_BITS)
+
+struct fanotify_event {
+ struct fsnotify_event fse;
+ struct hlist_node merge_list; /* List for hashed merge */
+ u32 mask;
+ struct {
+ unsigned int type : FANOTIFY_EVENT_TYPE_BITS;
+ unsigned int hash : FANOTIFY_EVENT_HASH_BITS;
+ };
+ struct pid *pid;
+};
+
+static inline void fanotify_init_event(struct fanotify_event *event,
+ unsigned int hash, u32 mask)
+{
+ fsnotify_init_event(&event->fse);
+ INIT_HLIST_NODE(&event->merge_list);
+ event->hash = hash;
+ event->mask = mask;
+ event->pid = NULL;
+}
+
+#define FANOTIFY_INLINE_FH(name, size) \
+struct { \
+ struct fanotify_fh (name); \
+ /* Space for object_fh.buf[] - access with fanotify_fh_buf() */ \
+ unsigned char _inline_fh_buf[(size)]; \
+}
+
+struct fanotify_fid_event {
+ struct fanotify_event fae;
+ __kernel_fsid_t fsid;
+
+ FANOTIFY_INLINE_FH(object_fh, FANOTIFY_INLINE_FH_LEN);
+};
+
+static inline struct fanotify_fid_event *
+FANOTIFY_FE(struct fanotify_event *event)
+{
+ return container_of(event, struct fanotify_fid_event, fae);
+}
+
+struct fanotify_name_event {
+ struct fanotify_event fae;
+ __kernel_fsid_t fsid;
+ struct fanotify_info info;
+};
+
+static inline struct fanotify_name_event *
+FANOTIFY_NE(struct fanotify_event *event)
+{
+ return container_of(event, struct fanotify_name_event, fae);
+}
+
+struct fanotify_error_event {
+ struct fanotify_event fae;
+ s32 error; /* Error reported by the Filesystem. */
+ u32 err_count; /* Suppressed errors count */
+
+ __kernel_fsid_t fsid; /* FSID this error refers to. */
+
+ FANOTIFY_INLINE_FH(object_fh, MAX_HANDLE_SZ);
+};
+
+static inline struct fanotify_error_event *
+FANOTIFY_EE(struct fanotify_event *event)
+{
+ return container_of(event, struct fanotify_error_event, fae);
+}
+
+static inline __kernel_fsid_t *fanotify_event_fsid(struct fanotify_event *event)
+{
+ if (event->type == FANOTIFY_EVENT_TYPE_FID)
+ return &FANOTIFY_FE(event)->fsid;
+ else if (event->type == FANOTIFY_EVENT_TYPE_FID_NAME)
+ return &FANOTIFY_NE(event)->fsid;
+ else if (event->type == FANOTIFY_EVENT_TYPE_FS_ERROR)
+ return &FANOTIFY_EE(event)->fsid;
+ else
+ return NULL;
+}
+
+static inline struct fanotify_fh *fanotify_event_object_fh(
+ struct fanotify_event *event)
+{
+ if (event->type == FANOTIFY_EVENT_TYPE_FID)
+ return &FANOTIFY_FE(event)->object_fh;
+ else if (event->type == FANOTIFY_EVENT_TYPE_FID_NAME)
+ return fanotify_info_file_fh(&FANOTIFY_NE(event)->info);
+ else if (event->type == FANOTIFY_EVENT_TYPE_FS_ERROR)
+ return &FANOTIFY_EE(event)->object_fh;
+ else
+ return NULL;
+}
+
+static inline struct fanotify_info *fanotify_event_info(
+ struct fanotify_event *event)
+{
+ if (event->type == FANOTIFY_EVENT_TYPE_FID_NAME)
+ return &FANOTIFY_NE(event)->info;
+ else
+ return NULL;
+}
+
+static inline int fanotify_event_object_fh_len(struct fanotify_event *event)
+{
+ struct fanotify_info *info = fanotify_event_info(event);
+ struct fanotify_fh *fh = fanotify_event_object_fh(event);
+
+ if (info)
+ return info->file_fh_totlen ? fh->len : 0;
+ else
+ return fh ? fh->len : 0;
+}
+
+static inline int fanotify_event_dir_fh_len(struct fanotify_event *event)
+{
+ struct fanotify_info *info = fanotify_event_info(event);
+
+ return info ? fanotify_info_dir_fh_len(info) : 0;
+}
+
+static inline int fanotify_event_dir2_fh_len(struct fanotify_event *event)
+{
+ struct fanotify_info *info = fanotify_event_info(event);
+
+ return info ? fanotify_info_dir2_fh_len(info) : 0;
+}
+
+static inline bool fanotify_event_has_object_fh(struct fanotify_event *event)
+{
+ /* For error events, even zeroed fh are reported. */
+ if (event->type == FANOTIFY_EVENT_TYPE_FS_ERROR)
+ return true;
+ return fanotify_event_object_fh_len(event) > 0;
+}
+
+static inline bool fanotify_event_has_dir_fh(struct fanotify_event *event)
+{
+ return fanotify_event_dir_fh_len(event) > 0;
+}
+
+static inline bool fanotify_event_has_dir2_fh(struct fanotify_event *event)
+{
+ return fanotify_event_dir2_fh_len(event) > 0;
+}
+
+static inline bool fanotify_event_has_any_dir_fh(struct fanotify_event *event)
+{
+ return fanotify_event_has_dir_fh(event) ||
+ fanotify_event_has_dir2_fh(event);
+}
+
+struct fanotify_path_event {
+ struct fanotify_event fae;
+ struct path path;
+};
+
+static inline struct fanotify_path_event *
+FANOTIFY_PE(struct fanotify_event *event)
+{
+ return container_of(event, struct fanotify_path_event, fae);
+}
+
+/*
+ * 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 {
+ struct fanotify_event fae;
+ struct path path;
+ unsigned short response; /* userspace answer to the event */
+ unsigned short state; /* state of the event */
+ int fd; /* fd we passed to userspace for this event */
+};
+
+static inline struct fanotify_perm_event *
+FANOTIFY_PERM(struct fanotify_event *event)
+{
+ return container_of(event, struct fanotify_perm_event, fae);
+}
+
+static inline bool fanotify_is_perm_event(u32 mask)
+{
+ return IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS) &&
+ mask & FANOTIFY_PERM_EVENTS;
+}
+
+static inline struct fanotify_event *FANOTIFY_E(struct fsnotify_event *fse)
+{
+ return container_of(fse, struct fanotify_event, fse);
+}
+
+static inline bool fanotify_is_error_event(u32 mask)
+{
+ return mask & FAN_FS_ERROR;
+}
+
+static inline const struct path *fanotify_event_path(struct fanotify_event *event)
+{
+ if (event->type == FANOTIFY_EVENT_TYPE_PATH)
+ return &FANOTIFY_PE(event)->path;
+ else if (event->type == FANOTIFY_EVENT_TYPE_PATH_PERM)
+ return &FANOTIFY_PERM(event)->path;
+ else
+ return NULL;
+}
+
+/*
+ * Use 128 size hash table to speed up events merge.
+ */
+#define FANOTIFY_HTABLE_BITS (7)
+#define FANOTIFY_HTABLE_SIZE (1 << FANOTIFY_HTABLE_BITS)
+#define FANOTIFY_HTABLE_MASK (FANOTIFY_HTABLE_SIZE - 1)
+
+/*
+ * Permission events and overflow event do not get merged - don't hash them.
+ */
+static inline bool fanotify_is_hashed_event(u32 mask)
+{
+ return !(fanotify_is_perm_event(mask) ||
+ fsnotify_is_overflow_event(mask));
+}
+
+static inline unsigned int fanotify_event_hash_bucket(
+ struct fsnotify_group *group,
+ struct fanotify_event *event)
+{
+ return event->hash & FANOTIFY_HTABLE_MASK;
+}
+
+static inline unsigned int fanotify_mark_user_flags(struct fsnotify_mark *mark)
+{
+ unsigned int mflags = 0;
+
+ if (mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)
+ mflags |= FAN_MARK_IGNORED_SURV_MODIFY;
+ if (mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF)
+ mflags |= FAN_MARK_EVICTABLE;
+ if (mark->flags & FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS)
+ mflags |= FAN_MARK_IGNORE;
+
+ return mflags;
+}
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
new file mode 100644
index 000000000..9df5db0f1
--- /dev/null
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -0,0 +1,1900 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/fanotify.h>
+#include <linux/fcntl.h>
+#include <linux/fdtable.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 <linux/statfs.h>
+#include <linux/exportfs.h>
+
+#include <asm/ioctls.h>
+
+#include "../../mount.h"
+#include "../fdinfo.h"
+#include "fanotify.h"
+
+#define FANOTIFY_DEFAULT_MAX_EVENTS 16384
+#define FANOTIFY_OLD_DEFAULT_MAX_MARKS 8192
+#define FANOTIFY_DEFAULT_MAX_GROUPS 128
+#define FANOTIFY_DEFAULT_FEE_POOL_SIZE 32
+
+/*
+ * Legacy fanotify marks limits (8192) is per group and we introduced a tunable
+ * limit of marks per user, similar to inotify. Effectively, the legacy limit
+ * of fanotify marks per user is <max marks per group> * <max groups per user>.
+ * This default limit (1M) also happens to match the increased limit of inotify
+ * max_user_watches since v5.10.
+ */
+#define FANOTIFY_DEFAULT_MAX_USER_MARKS \
+ (FANOTIFY_OLD_DEFAULT_MAX_MARKS * FANOTIFY_DEFAULT_MAX_GROUPS)
+
+/*
+ * Most of the memory cost of adding an inode mark is pinning the marked inode.
+ * The size of the filesystem inode struct is not uniform across filesystems,
+ * so double the size of a VFS inode is used as a conservative approximation.
+ */
+#define INODE_MARK_COST (2 * sizeof(struct inode))
+
+/* configurable via /proc/sys/fs/fanotify/ */
+static int fanotify_max_queued_events __read_mostly;
+
+#ifdef CONFIG_SYSCTL
+
+#include <linux/sysctl.h>
+
+static long ft_zero = 0;
+static long ft_int_max = INT_MAX;
+
+static struct ctl_table fanotify_table[] = {
+ {
+ .procname = "max_user_groups",
+ .data = &init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS],
+ .maxlen = sizeof(long),
+ .mode = 0644,
+ .proc_handler = proc_doulongvec_minmax,
+ .extra1 = &ft_zero,
+ .extra2 = &ft_int_max,
+ },
+ {
+ .procname = "max_user_marks",
+ .data = &init_user_ns.ucount_max[UCOUNT_FANOTIFY_MARKS],
+ .maxlen = sizeof(long),
+ .mode = 0644,
+ .proc_handler = proc_doulongvec_minmax,
+ .extra1 = &ft_zero,
+ .extra2 = &ft_int_max,
+ },
+ {
+ .procname = "max_queued_events",
+ .data = &fanotify_max_queued_events,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO
+ },
+ { }
+};
+
+static void __init fanotify_sysctls_init(void)
+{
+ register_sysctl("fs/fanotify", fanotify_table);
+}
+#else
+#define fanotify_sysctls_init() do { } while (0)
+#endif /* CONFIG_SYSCTL */
+
+/*
+ * 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_fid_event_cachep __read_mostly;
+struct kmem_cache *fanotify_path_event_cachep __read_mostly;
+struct kmem_cache *fanotify_perm_event_cachep __read_mostly;
+
+#define FANOTIFY_EVENT_ALIGN 4
+#define FANOTIFY_FID_INFO_HDR_LEN \
+ (sizeof(struct fanotify_event_info_fid) + sizeof(struct file_handle))
+#define FANOTIFY_PIDFD_INFO_HDR_LEN \
+ sizeof(struct fanotify_event_info_pidfd)
+#define FANOTIFY_ERROR_INFO_LEN \
+ (sizeof(struct fanotify_event_info_error))
+
+static int fanotify_fid_info_len(int fh_len, int name_len)
+{
+ int info_len = fh_len;
+
+ if (name_len)
+ info_len += name_len + 1;
+
+ return roundup(FANOTIFY_FID_INFO_HDR_LEN + info_len,
+ FANOTIFY_EVENT_ALIGN);
+}
+
+/* FAN_RENAME may have one or two dir+name info records */
+static int fanotify_dir_name_info_len(struct fanotify_event *event)
+{
+ struct fanotify_info *info = fanotify_event_info(event);
+ int dir_fh_len = fanotify_event_dir_fh_len(event);
+ int dir2_fh_len = fanotify_event_dir2_fh_len(event);
+ int info_len = 0;
+
+ if (dir_fh_len)
+ info_len += fanotify_fid_info_len(dir_fh_len,
+ info->name_len);
+ if (dir2_fh_len)
+ info_len += fanotify_fid_info_len(dir2_fh_len,
+ info->name2_len);
+
+ return info_len;
+}
+
+static size_t fanotify_event_len(unsigned int info_mode,
+ struct fanotify_event *event)
+{
+ size_t event_len = FAN_EVENT_METADATA_LEN;
+ int fh_len;
+ int dot_len = 0;
+
+ if (!info_mode)
+ return event_len;
+
+ if (fanotify_is_error_event(event->mask))
+ event_len += FANOTIFY_ERROR_INFO_LEN;
+
+ if (fanotify_event_has_any_dir_fh(event)) {
+ event_len += fanotify_dir_name_info_len(event);
+ } else if ((info_mode & FAN_REPORT_NAME) &&
+ (event->mask & FAN_ONDIR)) {
+ /*
+ * With group flag FAN_REPORT_NAME, if name was not recorded in
+ * event on a directory, we will report the name ".".
+ */
+ dot_len = 1;
+ }
+
+ if (info_mode & FAN_REPORT_PIDFD)
+ event_len += FANOTIFY_PIDFD_INFO_HDR_LEN;
+
+ if (fanotify_event_has_object_fh(event)) {
+ fh_len = fanotify_event_object_fh_len(event);
+ event_len += fanotify_fid_info_len(fh_len, dot_len);
+ }
+
+ return event_len;
+}
+
+/*
+ * Remove an hashed event from merge hash table.
+ */
+static void fanotify_unhash_event(struct fsnotify_group *group,
+ struct fanotify_event *event)
+{
+ assert_spin_locked(&group->notification_lock);
+
+ pr_debug("%s: group=%p event=%p bucket=%u\n", __func__,
+ group, event, fanotify_event_hash_bucket(group, event));
+
+ if (WARN_ON_ONCE(hlist_unhashed(&event->merge_list)))
+ return;
+
+ hlist_del_init(&event->merge_list);
+}
+
+/*
+ * Get an fanotify notification event if one exists and is small
+ * enough to fit in "count". Return an error pointer if the count
+ * is not large enough. When permission event is dequeued, its state is
+ * updated accordingly.
+ */
+static struct fanotify_event *get_one_event(struct fsnotify_group *group,
+ size_t count)
+{
+ size_t event_size;
+ struct fanotify_event *event = NULL;
+ struct fsnotify_event *fsn_event;
+ unsigned int info_mode = FAN_GROUP_FLAG(group, FANOTIFY_INFO_MODES);
+
+ pr_debug("%s: group=%p count=%zd\n", __func__, group, count);
+
+ spin_lock(&group->notification_lock);
+ fsn_event = fsnotify_peek_first_event(group);
+ if (!fsn_event)
+ goto out;
+
+ event = FANOTIFY_E(fsn_event);
+ event_size = fanotify_event_len(info_mode, event);
+
+ if (event_size > count) {
+ event = ERR_PTR(-EINVAL);
+ goto out;
+ }
+
+ /*
+ * Held the notification_lock the whole time, so this is the
+ * same event we peeked above.
+ */
+ fsnotify_remove_first_event(group);
+ if (fanotify_is_perm_event(event->mask))
+ FANOTIFY_PERM(event)->state = FAN_EVENT_REPORTED;
+ if (fanotify_is_hashed_event(event->mask))
+ fanotify_unhash_event(group, event);
+out:
+ spin_unlock(&group->notification_lock);
+ return event;
+}
+
+static int create_fd(struct fsnotify_group *group, const struct path *path,
+ struct file **file)
+{
+ int client_fd;
+ struct file *new_file;
+
+ 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.
+ */
+ new_file = dentry_open(path,
+ group->fanotify_data.f_flags | __FMODE_NONOTIFY,
+ current_cred());
+ 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;
+}
+
+/*
+ * Finish processing of permission event by setting it to ANSWERED state and
+ * drop group->notification_lock.
+ */
+static void finish_permission_event(struct fsnotify_group *group,
+ struct fanotify_perm_event *event,
+ unsigned int response)
+ __releases(&group->notification_lock)
+{
+ bool destroy = false;
+
+ assert_spin_locked(&group->notification_lock);
+ event->response = response;
+ if (event->state == FAN_EVENT_CANCELED)
+ destroy = true;
+ else
+ event->state = FAN_EVENT_ANSWERED;
+ spin_unlock(&group->notification_lock);
+ if (destroy)
+ fsnotify_destroy_event(group, &event->fae.fse);
+}
+
+static int process_access_response(struct fsnotify_group *group,
+ struct fanotify_response *response_struct)
+{
+ struct fanotify_perm_event *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) && !FAN_GROUP_FLAG(group, FAN_ENABLE_AUDIT))
+ return -EINVAL;
+
+ 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);
+ finish_permission_event(group, event, response);
+ wake_up(&group->fanotify_data.access_waitq);
+ return 0;
+ }
+ spin_unlock(&group->notification_lock);
+
+ return -ENOENT;
+}
+
+static size_t copy_error_info_to_user(struct fanotify_event *event,
+ char __user *buf, int count)
+{
+ struct fanotify_event_info_error info = { };
+ struct fanotify_error_event *fee = FANOTIFY_EE(event);
+
+ info.hdr.info_type = FAN_EVENT_INFO_TYPE_ERROR;
+ info.hdr.len = FANOTIFY_ERROR_INFO_LEN;
+
+ if (WARN_ON(count < info.hdr.len))
+ return -EFAULT;
+
+ info.error = fee->error;
+ info.error_count = fee->err_count;
+
+ if (copy_to_user(buf, &info, sizeof(info)))
+ return -EFAULT;
+
+ return info.hdr.len;
+}
+
+static int copy_fid_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh,
+ int info_type, const char *name,
+ size_t name_len,
+ char __user *buf, size_t count)
+{
+ struct fanotify_event_info_fid info = { };
+ struct file_handle handle = { };
+ unsigned char bounce[FANOTIFY_INLINE_FH_LEN], *fh_buf;
+ size_t fh_len = fh ? fh->len : 0;
+ size_t info_len = fanotify_fid_info_len(fh_len, name_len);
+ size_t len = info_len;
+
+ pr_debug("%s: fh_len=%zu name_len=%zu, info_len=%zu, count=%zu\n",
+ __func__, fh_len, name_len, info_len, count);
+
+ if (WARN_ON_ONCE(len < sizeof(info) || len > count))
+ return -EFAULT;
+
+ /*
+ * Copy event info fid header followed by variable sized file handle
+ * and optionally followed by variable sized filename.
+ */
+ switch (info_type) {
+ case FAN_EVENT_INFO_TYPE_FID:
+ case FAN_EVENT_INFO_TYPE_DFID:
+ if (WARN_ON_ONCE(name_len))
+ return -EFAULT;
+ break;
+ case FAN_EVENT_INFO_TYPE_DFID_NAME:
+ case FAN_EVENT_INFO_TYPE_OLD_DFID_NAME:
+ case FAN_EVENT_INFO_TYPE_NEW_DFID_NAME:
+ if (WARN_ON_ONCE(!name || !name_len))
+ return -EFAULT;
+ break;
+ default:
+ return -EFAULT;
+ }
+
+ info.hdr.info_type = info_type;
+ info.hdr.len = len;
+ info.fsid = *fsid;
+ if (copy_to_user(buf, &info, sizeof(info)))
+ return -EFAULT;
+
+ buf += sizeof(info);
+ len -= sizeof(info);
+ if (WARN_ON_ONCE(len < sizeof(handle)))
+ return -EFAULT;
+
+ handle.handle_type = fh->type;
+ handle.handle_bytes = fh_len;
+
+ /* Mangle handle_type for bad file_handle */
+ if (!fh_len)
+ handle.handle_type = FILEID_INVALID;
+
+ if (copy_to_user(buf, &handle, sizeof(handle)))
+ return -EFAULT;
+
+ buf += sizeof(handle);
+ len -= sizeof(handle);
+ if (WARN_ON_ONCE(len < fh_len))
+ return -EFAULT;
+
+ /*
+ * For an inline fh and inline file name, copy through stack to exclude
+ * the copy from usercopy hardening protections.
+ */
+ fh_buf = fanotify_fh_buf(fh);
+ if (fh_len <= FANOTIFY_INLINE_FH_LEN) {
+ memcpy(bounce, fh_buf, fh_len);
+ fh_buf = bounce;
+ }
+ if (copy_to_user(buf, fh_buf, fh_len))
+ return -EFAULT;
+
+ buf += fh_len;
+ len -= fh_len;
+
+ if (name_len) {
+ /* Copy the filename with terminating null */
+ name_len++;
+ if (WARN_ON_ONCE(len < name_len))
+ return -EFAULT;
+
+ if (copy_to_user(buf, name, name_len))
+ return -EFAULT;
+
+ buf += name_len;
+ len -= name_len;
+ }
+
+ /* Pad with 0's */
+ WARN_ON_ONCE(len < 0 || len >= FANOTIFY_EVENT_ALIGN);
+ if (len > 0 && clear_user(buf, len))
+ return -EFAULT;
+
+ return info_len;
+}
+
+static int copy_pidfd_info_to_user(int pidfd,
+ char __user *buf,
+ size_t count)
+{
+ struct fanotify_event_info_pidfd info = { };
+ size_t info_len = FANOTIFY_PIDFD_INFO_HDR_LEN;
+
+ if (WARN_ON_ONCE(info_len > count))
+ return -EFAULT;
+
+ info.hdr.info_type = FAN_EVENT_INFO_TYPE_PIDFD;
+ info.hdr.len = info_len;
+ info.pidfd = pidfd;
+
+ if (copy_to_user(buf, &info, info_len))
+ return -EFAULT;
+
+ return info_len;
+}
+
+static int copy_info_records_to_user(struct fanotify_event *event,
+ struct fanotify_info *info,
+ unsigned int info_mode, int pidfd,
+ char __user *buf, size_t count)
+{
+ int ret, total_bytes = 0, info_type = 0;
+ unsigned int fid_mode = info_mode & FANOTIFY_FID_BITS;
+ unsigned int pidfd_mode = info_mode & FAN_REPORT_PIDFD;
+
+ /*
+ * Event info records order is as follows:
+ * 1. dir fid + name
+ * 2. (optional) new dir fid + new name
+ * 3. (optional) child fid
+ */
+ if (fanotify_event_has_dir_fh(event)) {
+ info_type = info->name_len ? FAN_EVENT_INFO_TYPE_DFID_NAME :
+ FAN_EVENT_INFO_TYPE_DFID;
+
+ /* FAN_RENAME uses special info types */
+ if (event->mask & FAN_RENAME)
+ info_type = FAN_EVENT_INFO_TYPE_OLD_DFID_NAME;
+
+ ret = copy_fid_info_to_user(fanotify_event_fsid(event),
+ fanotify_info_dir_fh(info),
+ info_type,
+ fanotify_info_name(info),
+ info->name_len, buf, count);
+ if (ret < 0)
+ return ret;
+
+ buf += ret;
+ count -= ret;
+ total_bytes += ret;
+ }
+
+ /* New dir fid+name may be reported in addition to old dir fid+name */
+ if (fanotify_event_has_dir2_fh(event)) {
+ info_type = FAN_EVENT_INFO_TYPE_NEW_DFID_NAME;
+ ret = copy_fid_info_to_user(fanotify_event_fsid(event),
+ fanotify_info_dir2_fh(info),
+ info_type,
+ fanotify_info_name2(info),
+ info->name2_len, buf, count);
+ if (ret < 0)
+ return ret;
+
+ buf += ret;
+ count -= ret;
+ total_bytes += ret;
+ }
+
+ if (fanotify_event_has_object_fh(event)) {
+ const char *dot = NULL;
+ int dot_len = 0;
+
+ if (fid_mode == FAN_REPORT_FID || info_type) {
+ /*
+ * With only group flag FAN_REPORT_FID only type FID is
+ * reported. Second info record type is always FID.
+ */
+ info_type = FAN_EVENT_INFO_TYPE_FID;
+ } else if ((fid_mode & FAN_REPORT_NAME) &&
+ (event->mask & FAN_ONDIR)) {
+ /*
+ * With group flag FAN_REPORT_NAME, if name was not
+ * recorded in an event on a directory, report the name
+ * "." with info type DFID_NAME.
+ */
+ info_type = FAN_EVENT_INFO_TYPE_DFID_NAME;
+ dot = ".";
+ dot_len = 1;
+ } else if ((event->mask & ALL_FSNOTIFY_DIRENT_EVENTS) ||
+ (event->mask & FAN_ONDIR)) {
+ /*
+ * With group flag FAN_REPORT_DIR_FID, a single info
+ * record has type DFID for directory entry modification
+ * event and for event on a directory.
+ */
+ info_type = FAN_EVENT_INFO_TYPE_DFID;
+ } else {
+ /*
+ * With group flags FAN_REPORT_DIR_FID|FAN_REPORT_FID,
+ * a single info record has type FID for event on a
+ * non-directory, when there is no directory to report.
+ * For example, on FAN_DELETE_SELF event.
+ */
+ info_type = FAN_EVENT_INFO_TYPE_FID;
+ }
+
+ ret = copy_fid_info_to_user(fanotify_event_fsid(event),
+ fanotify_event_object_fh(event),
+ info_type, dot, dot_len,
+ buf, count);
+ if (ret < 0)
+ return ret;
+
+ buf += ret;
+ count -= ret;
+ total_bytes += ret;
+ }
+
+ if (pidfd_mode) {
+ ret = copy_pidfd_info_to_user(pidfd, buf, count);
+ if (ret < 0)
+ return ret;
+
+ buf += ret;
+ count -= ret;
+ total_bytes += ret;
+ }
+
+ if (fanotify_is_error_event(event->mask)) {
+ ret = copy_error_info_to_user(event, buf, count);
+ if (ret < 0)
+ return ret;
+ buf += ret;
+ count -= ret;
+ total_bytes += ret;
+ }
+
+ return total_bytes;
+}
+
+static ssize_t copy_event_to_user(struct fsnotify_group *group,
+ struct fanotify_event *event,
+ char __user *buf, size_t count)
+{
+ struct fanotify_event_metadata metadata;
+ const struct path *path = fanotify_event_path(event);
+ struct fanotify_info *info = fanotify_event_info(event);
+ unsigned int info_mode = FAN_GROUP_FLAG(group, FANOTIFY_INFO_MODES);
+ unsigned int pidfd_mode = info_mode & FAN_REPORT_PIDFD;
+ struct file *f = NULL;
+ int ret, pidfd = FAN_NOPIDFD, fd = FAN_NOFD;
+
+ pr_debug("%s: group=%p event=%p\n", __func__, group, event);
+
+ metadata.event_len = fanotify_event_len(info_mode, event);
+ metadata.metadata_len = FAN_EVENT_METADATA_LEN;
+ metadata.vers = FANOTIFY_METADATA_VERSION;
+ metadata.reserved = 0;
+ metadata.mask = event->mask & FANOTIFY_OUTGOING_EVENTS;
+ metadata.pid = pid_vnr(event->pid);
+ /*
+ * For an unprivileged listener, event->pid can be used to identify the
+ * events generated by the listener process itself, without disclosing
+ * the pids of other processes.
+ */
+ if (FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV) &&
+ task_tgid(current) != event->pid)
+ metadata.pid = 0;
+
+ /*
+ * For now, fid mode is required for an unprivileged listener and
+ * fid mode does not report fd in events. Keep this check anyway
+ * for safety in case fid mode requirement is relaxed in the future
+ * to allow unprivileged listener to get events with no fd and no fid.
+ */
+ if (!FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV) &&
+ path && path->mnt && path->dentry) {
+ fd = create_fd(group, path, &f);
+ if (fd < 0)
+ return fd;
+ }
+ metadata.fd = fd;
+
+ if (pidfd_mode) {
+ /*
+ * Complain if the FAN_REPORT_PIDFD and FAN_REPORT_TID mutual
+ * exclusion is ever lifted. At the time of incoporating pidfd
+ * support within fanotify, the pidfd API only supported the
+ * creation of pidfds for thread-group leaders.
+ */
+ WARN_ON_ONCE(FAN_GROUP_FLAG(group, FAN_REPORT_TID));
+
+ /*
+ * The PIDTYPE_TGID check for an event->pid is performed
+ * preemptively in an attempt to catch out cases where the event
+ * listener reads events after the event generating process has
+ * already terminated. Report FAN_NOPIDFD to the event listener
+ * in those cases, with all other pidfd creation errors being
+ * reported as FAN_EPIDFD.
+ */
+ if (metadata.pid == 0 ||
+ !pid_has_task(event->pid, PIDTYPE_TGID)) {
+ pidfd = FAN_NOPIDFD;
+ } else {
+ pidfd = pidfd_create(event->pid, 0);
+ if (pidfd < 0)
+ pidfd = FAN_EPIDFD;
+ }
+ }
+
+ ret = -EFAULT;
+ /*
+ * Sanity check copy size in case get_one_event() and
+ * event_len sizes ever get out of sync.
+ */
+ if (WARN_ON_ONCE(metadata.event_len > count))
+ goto out_close_fd;
+
+ if (copy_to_user(buf, &metadata, FAN_EVENT_METADATA_LEN))
+ goto out_close_fd;
+
+ buf += FAN_EVENT_METADATA_LEN;
+ count -= FAN_EVENT_METADATA_LEN;
+
+ if (fanotify_is_perm_event(event->mask))
+ FANOTIFY_PERM(event)->fd = fd;
+
+ if (info_mode) {
+ ret = copy_info_records_to_user(event, info, info_mode, pidfd,
+ buf, count);
+ if (ret < 0)
+ goto out_close_fd;
+ }
+
+ if (f)
+ fd_install(fd, f);
+
+ return metadata.event_len;
+
+out_close_fd:
+ if (fd != FAN_NOFD) {
+ put_unused_fd(fd);
+ fput(f);
+ }
+
+ if (pidfd >= 0)
+ close_fd(pidfd);
+
+ 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 fanotify_event *event;
+ 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) {
+ /*
+ * User can supply arbitrarily large buffer. Avoid softlockups
+ * in case there are lots of available events.
+ */
+ cond_resched();
+ event = get_one_event(group, count);
+ if (IS_ERR(event)) {
+ ret = PTR_ERR(event);
+ break;
+ }
+
+ if (!event) {
+ 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, event, buf, count);
+ 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(event->mask)) {
+ fsnotify_destroy_event(group, &event->fse);
+ } else {
+ if (ret <= 0) {
+ spin_lock(&group->notification_lock);
+ finish_permission_event(group,
+ FANOTIFY_PERM(event), FAN_DENY);
+ wake_up(&group->fanotify_data.access_waitq);
+ } else {
+ spin_lock(&group->notification_lock);
+ list_add_tail(&event->fse.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))
+ return -EINVAL;
+
+ 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 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);
+ while (!list_empty(&group->fanotify_data.access_list)) {
+ struct fanotify_perm_event *event;
+
+ event = list_first_entry(&group->fanotify_data.access_list,
+ struct fanotify_perm_event, fae.fse.list);
+ list_del_init(&event->fae.fse.list);
+ finish_permission_event(group, event, FAN_ALLOW);
+ spin_lock(&group->notification_lock);
+ }
+
+ /*
+ * 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 ((fsn_event = fsnotify_remove_first_event(group))) {
+ struct fanotify_event *event = FANOTIFY_E(fsn_event);
+
+ if (!(event->mask & FANOTIFY_PERM_EVENTS)) {
+ spin_unlock(&group->notification_lock);
+ fsnotify_destroy_event(group, fsn_event);
+ } else {
+ finish_permission_event(group, FANOTIFY_PERM(event),
+ FAN_ALLOW);
+ }
+ spin_lock(&group->notification_lock);
+ }
+ 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 = compat_ptr_ioctl,
+ .llseek = noop_llseek,
+};
+
+static int fanotify_find_path(int dfd, const char __user *filename,
+ struct path *path, unsigned int flags, __u64 mask,
+ unsigned int obj_type)
+{
+ 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 = path_permission(path, MAY_READ);
+ if (ret) {
+ path_put(path);
+ goto out;
+ }
+
+ ret = security_path_notify(path, mask, obj_type);
+ 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,
+ __u32 umask, int *destroy)
+{
+ __u32 oldmask, newmask;
+
+ /* umask bits cannot be removed by user */
+ mask &= ~umask;
+ spin_lock(&fsn_mark->lock);
+ oldmask = fsnotify_calc_mask(fsn_mark);
+ if (!(flags & FANOTIFY_MARK_IGNORE_BITS)) {
+ fsn_mark->mask &= ~mask;
+ } else {
+ fsn_mark->ignore_mask &= ~mask;
+ }
+ newmask = fsnotify_calc_mask(fsn_mark);
+ /*
+ * We need to keep the mark around even if remaining mask cannot
+ * result in any events (e.g. mask == FAN_ONDIR) to support incremenal
+ * changes to the mask.
+ * Destroy mark when only umask bits remain.
+ */
+ *destroy = !((fsn_mark->mask | fsn_mark->ignore_mask) & ~umask);
+ spin_unlock(&fsn_mark->lock);
+
+ return oldmask & ~newmask;
+}
+
+static int fanotify_remove_mark(struct fsnotify_group *group,
+ fsnotify_connp_t *connp, __u32 mask,
+ unsigned int flags, __u32 umask)
+{
+ struct fsnotify_mark *fsn_mark = NULL;
+ __u32 removed;
+ int destroy_mark;
+
+ fsnotify_group_lock(group);
+ fsn_mark = fsnotify_find_mark(connp, group);
+ if (!fsn_mark) {
+ fsnotify_group_unlock(group);
+ return -ENOENT;
+ }
+
+ removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags,
+ umask, &destroy_mark);
+ if (removed & fsnotify_conn_mask(fsn_mark->connector))
+ fsnotify_recalc_mask(fsn_mark->connector);
+ if (destroy_mark)
+ fsnotify_detach_mark(fsn_mark);
+ fsnotify_group_unlock(group);
+ 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, __u32 umask)
+{
+ return fanotify_remove_mark(group, &real_mount(mnt)->mnt_fsnotify_marks,
+ mask, flags, umask);
+}
+
+static int fanotify_remove_sb_mark(struct fsnotify_group *group,
+ struct super_block *sb, __u32 mask,
+ unsigned int flags, __u32 umask)
+{
+ return fanotify_remove_mark(group, &sb->s_fsnotify_marks, mask,
+ flags, umask);
+}
+
+static int fanotify_remove_inode_mark(struct fsnotify_group *group,
+ struct inode *inode, __u32 mask,
+ unsigned int flags, __u32 umask)
+{
+ return fanotify_remove_mark(group, &inode->i_fsnotify_marks, mask,
+ flags, umask);
+}
+
+static bool fanotify_mark_update_flags(struct fsnotify_mark *fsn_mark,
+ unsigned int fan_flags)
+{
+ bool want_iref = !(fan_flags & FAN_MARK_EVICTABLE);
+ unsigned int ignore = fan_flags & FANOTIFY_MARK_IGNORE_BITS;
+ bool recalc = false;
+
+ /*
+ * When using FAN_MARK_IGNORE for the first time, mark starts using
+ * independent event flags in ignore mask. After that, trying to
+ * update the ignore mask with the old FAN_MARK_IGNORED_MASK API
+ * will result in EEXIST error.
+ */
+ if (ignore == FAN_MARK_IGNORE)
+ fsn_mark->flags |= FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS;
+
+ /*
+ * Setting FAN_MARK_IGNORED_SURV_MODIFY for the first time may lead to
+ * the removal of the FS_MODIFY bit in calculated mask if it was set
+ * because of an ignore mask that is now going to survive FS_MODIFY.
+ */
+ if (ignore && (fan_flags & FAN_MARK_IGNORED_SURV_MODIFY) &&
+ !(fsn_mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)) {
+ fsn_mark->flags |= FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY;
+ if (!(fsn_mark->mask & FS_MODIFY))
+ recalc = true;
+ }
+
+ if (fsn_mark->connector->type != FSNOTIFY_OBJ_TYPE_INODE ||
+ want_iref == !(fsn_mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF))
+ return recalc;
+
+ /*
+ * NO_IREF may be removed from a mark, but not added.
+ * When removed, fsnotify_recalc_mask() will take the inode ref.
+ */
+ WARN_ON_ONCE(!want_iref);
+ fsn_mark->flags &= ~FSNOTIFY_MARK_FLAG_NO_IREF;
+
+ return true;
+}
+
+static bool fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark,
+ __u32 mask, unsigned int fan_flags)
+{
+ bool recalc;
+
+ spin_lock(&fsn_mark->lock);
+ if (!(fan_flags & FANOTIFY_MARK_IGNORE_BITS))
+ fsn_mark->mask |= mask;
+ else
+ fsn_mark->ignore_mask |= mask;
+
+ recalc = fsnotify_calc_mask(fsn_mark) &
+ ~fsnotify_conn_mask(fsn_mark->connector);
+
+ recalc |= fanotify_mark_update_flags(fsn_mark, fan_flags);
+ spin_unlock(&fsn_mark->lock);
+
+ return recalc;
+}
+
+static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group,
+ fsnotify_connp_t *connp,
+ unsigned int obj_type,
+ unsigned int fan_flags,
+ __kernel_fsid_t *fsid)
+{
+ struct ucounts *ucounts = group->fanotify_data.ucounts;
+ struct fsnotify_mark *mark;
+ int ret;
+
+ /*
+ * Enforce per user marks limits per user in all containing user ns.
+ * A group with FAN_UNLIMITED_MARKS does not contribute to mark count
+ * in the limited groups account.
+ */
+ if (!FAN_GROUP_FLAG(group, FAN_UNLIMITED_MARKS) &&
+ !inc_ucount(ucounts->ns, ucounts->uid, UCOUNT_FANOTIFY_MARKS))
+ return ERR_PTR(-ENOSPC);
+
+ mark = kmem_cache_alloc(fanotify_mark_cache, GFP_KERNEL);
+ if (!mark) {
+ ret = -ENOMEM;
+ goto out_dec_ucounts;
+ }
+
+ fsnotify_init_mark(mark, group);
+ if (fan_flags & FAN_MARK_EVICTABLE)
+ mark->flags |= FSNOTIFY_MARK_FLAG_NO_IREF;
+
+ ret = fsnotify_add_mark_locked(mark, connp, obj_type, 0, fsid);
+ if (ret) {
+ fsnotify_put_mark(mark);
+ goto out_dec_ucounts;
+ }
+
+ return mark;
+
+out_dec_ucounts:
+ if (!FAN_GROUP_FLAG(group, FAN_UNLIMITED_MARKS))
+ dec_ucount(ucounts, UCOUNT_FANOTIFY_MARKS);
+ return ERR_PTR(ret);
+}
+
+static int fanotify_group_init_error_pool(struct fsnotify_group *group)
+{
+ if (mempool_initialized(&group->fanotify_data.error_events_pool))
+ return 0;
+
+ return mempool_init_kmalloc_pool(&group->fanotify_data.error_events_pool,
+ FANOTIFY_DEFAULT_FEE_POOL_SIZE,
+ sizeof(struct fanotify_error_event));
+}
+
+static int fanotify_may_update_existing_mark(struct fsnotify_mark *fsn_mark,
+ unsigned int fan_flags)
+{
+ /*
+ * Non evictable mark cannot be downgraded to evictable mark.
+ */
+ if (fan_flags & FAN_MARK_EVICTABLE &&
+ !(fsn_mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF))
+ return -EEXIST;
+
+ /*
+ * New ignore mask semantics cannot be downgraded to old semantics.
+ */
+ if (fan_flags & FAN_MARK_IGNORED_MASK &&
+ fsn_mark->flags & FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS)
+ return -EEXIST;
+
+ /*
+ * An ignore mask that survives modify could never be downgraded to not
+ * survive modify. With new FAN_MARK_IGNORE semantics we make that rule
+ * explicit and return an error when trying to update the ignore mask
+ * without the original FAN_MARK_IGNORED_SURV_MODIFY value.
+ */
+ if (fan_flags & FAN_MARK_IGNORE &&
+ !(fan_flags & FAN_MARK_IGNORED_SURV_MODIFY) &&
+ fsn_mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)
+ return -EEXIST;
+
+ return 0;
+}
+
+static int fanotify_add_mark(struct fsnotify_group *group,
+ fsnotify_connp_t *connp, unsigned int obj_type,
+ __u32 mask, unsigned int fan_flags,
+ __kernel_fsid_t *fsid)
+{
+ struct fsnotify_mark *fsn_mark;
+ bool recalc;
+ int ret = 0;
+
+ fsnotify_group_lock(group);
+ fsn_mark = fsnotify_find_mark(connp, group);
+ if (!fsn_mark) {
+ fsn_mark = fanotify_add_new_mark(group, connp, obj_type,
+ fan_flags, fsid);
+ if (IS_ERR(fsn_mark)) {
+ fsnotify_group_unlock(group);
+ return PTR_ERR(fsn_mark);
+ }
+ }
+
+ /*
+ * Check if requested mark flags conflict with an existing mark flags.
+ */
+ ret = fanotify_may_update_existing_mark(fsn_mark, fan_flags);
+ if (ret)
+ goto out;
+
+ /*
+ * Error events are pre-allocated per group, only if strictly
+ * needed (i.e. FAN_FS_ERROR was requested).
+ */
+ if (!(fan_flags & FANOTIFY_MARK_IGNORE_BITS) &&
+ (mask & FAN_FS_ERROR)) {
+ ret = fanotify_group_init_error_pool(group);
+ if (ret)
+ goto out;
+ }
+
+ recalc = fanotify_mark_add_to_mask(fsn_mark, mask, fan_flags);
+ if (recalc)
+ fsnotify_recalc_mask(fsn_mark->connector);
+
+out:
+ fsnotify_group_unlock(group);
+
+ fsnotify_put_mark(fsn_mark);
+ return ret;
+}
+
+static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
+ struct vfsmount *mnt, __u32 mask,
+ unsigned int flags, __kernel_fsid_t *fsid)
+{
+ return fanotify_add_mark(group, &real_mount(mnt)->mnt_fsnotify_marks,
+ FSNOTIFY_OBJ_TYPE_VFSMOUNT, mask, flags, fsid);
+}
+
+static int fanotify_add_sb_mark(struct fsnotify_group *group,
+ struct super_block *sb, __u32 mask,
+ unsigned int flags, __kernel_fsid_t *fsid)
+{
+ return fanotify_add_mark(group, &sb->s_fsnotify_marks,
+ FSNOTIFY_OBJ_TYPE_SB, mask, flags, fsid);
+}
+
+static int fanotify_add_inode_mark(struct fsnotify_group *group,
+ struct inode *inode, __u32 mask,
+ unsigned int flags, __kernel_fsid_t *fsid)
+{
+ 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 ignore mask, unless that ignore mask is supposed to survive
+ * modification changes anyway.
+ */
+ if ((flags & FANOTIFY_MARK_IGNORE_BITS) &&
+ !(flags & FAN_MARK_IGNORED_SURV_MODIFY) &&
+ inode_is_open_for_write(inode))
+ return 0;
+
+ return fanotify_add_mark(group, &inode->i_fsnotify_marks,
+ FSNOTIFY_OBJ_TYPE_INODE, mask, flags, fsid);
+}
+
+static struct fsnotify_event *fanotify_alloc_overflow_event(void)
+{
+ struct fanotify_event *oevent;
+
+ oevent = kmalloc(sizeof(*oevent), GFP_KERNEL_ACCOUNT);
+ if (!oevent)
+ return NULL;
+
+ fanotify_init_event(oevent, 0, FS_Q_OVERFLOW);
+ oevent->type = FANOTIFY_EVENT_TYPE_OVERFLOW;
+
+ return &oevent->fse;
+}
+
+static struct hlist_head *fanotify_alloc_merge_hash(void)
+{
+ struct hlist_head *hash;
+
+ hash = kmalloc(sizeof(struct hlist_head) << FANOTIFY_HTABLE_BITS,
+ GFP_KERNEL_ACCOUNT);
+ if (!hash)
+ return NULL;
+
+ __hash_init(hash, FANOTIFY_HTABLE_SIZE);
+
+ return hash;
+}
+
+/* fanotify syscalls */
+SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
+{
+ struct fsnotify_group *group;
+ int f_flags, fd;
+ unsigned int fid_mode = flags & FANOTIFY_FID_BITS;
+ unsigned int class = flags & FANOTIFY_CLASS_BITS;
+ unsigned int internal_flags = 0;
+
+ pr_debug("%s: flags=%x event_f_flags=%x\n",
+ __func__, flags, event_f_flags);
+
+ if (!capable(CAP_SYS_ADMIN)) {
+ /*
+ * An unprivileged user can setup an fanotify group with
+ * limited functionality - an unprivileged group is limited to
+ * notification events with file handles and it cannot use
+ * unlimited queue/marks.
+ */
+ if ((flags & FANOTIFY_ADMIN_INIT_FLAGS) || !fid_mode)
+ return -EPERM;
+
+ /*
+ * Setting the internal flag FANOTIFY_UNPRIV on the group
+ * prevents setting mount/filesystem marks on this group and
+ * prevents reporting pid and open fd in events.
+ */
+ internal_flags |= FANOTIFY_UNPRIV;
+ }
+
+#ifdef CONFIG_AUDITSYSCALL
+ if (flags & ~(FANOTIFY_INIT_FLAGS | FAN_ENABLE_AUDIT))
+#else
+ if (flags & ~FANOTIFY_INIT_FLAGS)
+#endif
+ return -EINVAL;
+
+ /*
+ * A pidfd can only be returned for a thread-group leader; thus
+ * FAN_REPORT_PIDFD and FAN_REPORT_TID need to remain mutually
+ * exclusive.
+ */
+ if ((flags & FAN_REPORT_PIDFD) && (flags & FAN_REPORT_TID))
+ 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;
+ }
+
+ if (fid_mode && class != FAN_CLASS_NOTIF)
+ return -EINVAL;
+
+ /*
+ * Child name is reported with parent fid so requires dir fid.
+ * We can report both child fid and dir fid with or without name.
+ */
+ if ((fid_mode & FAN_REPORT_NAME) && !(fid_mode & FAN_REPORT_DIR_FID))
+ return -EINVAL;
+
+ /*
+ * FAN_REPORT_TARGET_FID requires FAN_REPORT_NAME and FAN_REPORT_FID
+ * and is used as an indication to report both dir and child fid on all
+ * dirent events.
+ */
+ if ((fid_mode & FAN_REPORT_TARGET_FID) &&
+ (!(fid_mode & FAN_REPORT_NAME) || !(fid_mode & FAN_REPORT_FID)))
+ return -EINVAL;
+
+ 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,
+ FSNOTIFY_GROUP_USER | FSNOTIFY_GROUP_NOFS);
+ if (IS_ERR(group)) {
+ return PTR_ERR(group);
+ }
+
+ /* Enforce groups limits per user in all containing user ns */
+ group->fanotify_data.ucounts = inc_ucount(current_user_ns(),
+ current_euid(),
+ UCOUNT_FANOTIFY_GROUPS);
+ if (!group->fanotify_data.ucounts) {
+ fd = -EMFILE;
+ goto out_destroy_group;
+ }
+
+ group->fanotify_data.flags = flags | internal_flags;
+ group->memcg = get_mem_cgroup_from_mm(current->mm);
+
+ group->fanotify_data.merge_hash = fanotify_alloc_merge_hash();
+ if (!group->fanotify_data.merge_hash) {
+ fd = -ENOMEM;
+ goto out_destroy_group;
+ }
+
+ group->overflow_event = fanotify_alloc_overflow_event();
+ if (unlikely(!group->overflow_event)) {
+ fd = -ENOMEM;
+ goto out_destroy_group;
+ }
+
+ 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 (class) {
+ 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_max_queued_events;
+ }
+
+ if (flags & FAN_UNLIMITED_MARKS) {
+ fd = -EPERM;
+ if (!capable(CAP_SYS_ADMIN))
+ goto out_destroy_group;
+ }
+
+ if (flags & FAN_ENABLE_AUDIT) {
+ fd = -EPERM;
+ if (!capable(CAP_AUDIT_WRITE))
+ goto out_destroy_group;
+ }
+
+ 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 fanotify_test_fsid(struct dentry *dentry, __kernel_fsid_t *fsid)
+{
+ __kernel_fsid_t root_fsid;
+ int err;
+
+ /*
+ * Make sure dentry is not of a filesystem with zero fsid (e.g. fuse).
+ */
+ err = vfs_get_fsid(dentry, fsid);
+ if (err)
+ return err;
+
+ if (!fsid->val[0] && !fsid->val[1])
+ return -ENODEV;
+
+ /*
+ * Make sure dentry is not of a filesystem subvolume (e.g. btrfs)
+ * which uses a different fsid than sb root.
+ */
+ err = vfs_get_fsid(dentry->d_sb->s_root, &root_fsid);
+ if (err)
+ return err;
+
+ if (root_fsid.val[0] != fsid->val[0] ||
+ root_fsid.val[1] != fsid->val[1])
+ return -EXDEV;
+
+ return 0;
+}
+
+/* Check if filesystem can encode a unique fid */
+static int fanotify_test_fid(struct dentry *dentry)
+{
+ /*
+ * We need to make sure that the file system supports at least
+ * encoding a file handle so user can use name_to_handle_at() to
+ * compare fid returned with event to the file handle of watched
+ * objects. However, name_to_handle_at() requires that the
+ * filesystem also supports decoding file handles.
+ */
+ if (!dentry->d_sb->s_export_op ||
+ !dentry->d_sb->s_export_op->fh_to_dentry)
+ return -EOPNOTSUPP;
+
+ return 0;
+}
+
+static int fanotify_events_supported(struct fsnotify_group *group,
+ const struct path *path, __u64 mask,
+ unsigned int flags)
+{
+ unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS;
+ /* Strict validation of events in non-dir inode mask with v5.17+ APIs */
+ bool strict_dir_events = FAN_GROUP_FLAG(group, FAN_REPORT_TARGET_FID) ||
+ (mask & FAN_RENAME) ||
+ (flags & FAN_MARK_IGNORE);
+
+ /*
+ * Some filesystems such as 'proc' acquire unusual locks when opening
+ * files. For them fanotify permission events have high chances of
+ * deadlocking the system - open done when reporting fanotify event
+ * blocks on this "unusual" lock while another process holding the lock
+ * waits for fanotify permission event to be answered. Just disallow
+ * permission events for such filesystems.
+ */
+ if (mask & FANOTIFY_PERM_EVENTS &&
+ path->mnt->mnt_sb->s_type->fs_flags & FS_DISALLOW_NOTIFY_PERM)
+ return -EINVAL;
+
+ /*
+ * mount and sb marks are not allowed on kernel internal pseudo fs,
+ * like pipe_mnt, because that would subscribe to events on all the
+ * anonynous pipes in the system.
+ *
+ * SB_NOUSER covers all of the internal pseudo fs whose objects are not
+ * exposed to user's mount namespace, but there are other SB_KERNMOUNT
+ * fs, like nsfs, debugfs, for which the value of allowing sb and mount
+ * mark is questionable. For now we leave them alone.
+ */
+ if (mark_type != FAN_MARK_INODE &&
+ path->mnt->mnt_sb->s_flags & SB_NOUSER)
+ return -EINVAL;
+
+ /*
+ * We shouldn't have allowed setting dirent events and the directory
+ * flags FAN_ONDIR and FAN_EVENT_ON_CHILD in mask of non-dir inode,
+ * but because we always allowed it, error only when using new APIs.
+ */
+ if (strict_dir_events && mark_type == FAN_MARK_INODE &&
+ !d_is_dir(path->dentry) && (mask & FANOTIFY_DIRONLY_EVENT_BITS))
+ return -ENOTDIR;
+
+ return 0;
+}
+
+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;
+ __kernel_fsid_t __fsid, *fsid = NULL;
+ u32 valid_mask = FANOTIFY_EVENTS | FANOTIFY_EVENT_FLAGS;
+ unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS;
+ unsigned int mark_cmd = flags & FANOTIFY_MARK_CMD_BITS;
+ unsigned int ignore = flags & FANOTIFY_MARK_IGNORE_BITS;
+ unsigned int obj_type, fid_mode;
+ u32 umask = 0;
+ 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 (upper_32_bits(mask))
+ return -EINVAL;
+
+ if (flags & ~FANOTIFY_MARK_FLAGS)
+ return -EINVAL;
+
+ switch (mark_type) {
+ case FAN_MARK_INODE:
+ obj_type = FSNOTIFY_OBJ_TYPE_INODE;
+ break;
+ case FAN_MARK_MOUNT:
+ obj_type = FSNOTIFY_OBJ_TYPE_VFSMOUNT;
+ break;
+ case FAN_MARK_FILESYSTEM:
+ obj_type = FSNOTIFY_OBJ_TYPE_SB;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ switch (mark_cmd) {
+ case FAN_MARK_ADD:
+ case FAN_MARK_REMOVE:
+ if (!mask)
+ return -EINVAL;
+ break;
+ case FAN_MARK_FLUSH:
+ if (flags & ~(FANOTIFY_MARK_TYPE_BITS | FAN_MARK_FLUSH))
+ return -EINVAL;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS))
+ valid_mask |= FANOTIFY_PERM_EVENTS;
+
+ if (mask & ~valid_mask)
+ return -EINVAL;
+
+
+ /* We don't allow FAN_MARK_IGNORE & FAN_MARK_IGNORED_MASK together */
+ if (ignore == (FAN_MARK_IGNORE | FAN_MARK_IGNORED_MASK))
+ return -EINVAL;
+
+ /*
+ * Event flags (FAN_ONDIR, FAN_EVENT_ON_CHILD) have no effect with
+ * FAN_MARK_IGNORED_MASK.
+ */
+ if (ignore == FAN_MARK_IGNORED_MASK) {
+ mask &= ~FANOTIFY_EVENT_FLAGS;
+ umask = FANOTIFY_EVENT_FLAGS;
+ }
+
+ 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;
+
+ /*
+ * An unprivileged user is not allowed to setup mount nor filesystem
+ * marks. This also includes setting up such marks by a group that
+ * was initialized by an unprivileged user.
+ */
+ ret = -EPERM;
+ if ((!capable(CAP_SYS_ADMIN) ||
+ FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV)) &&
+ mark_type != FAN_MARK_INODE)
+ goto fput_and_out;
+
+ /*
+ * group->priority == FS_PRIO_0 == FAN_CLASS_NOTIF. These are not
+ * allowed to set permissions events.
+ */
+ ret = -EINVAL;
+ if (mask & FANOTIFY_PERM_EVENTS &&
+ group->priority == FS_PRIO_0)
+ goto fput_and_out;
+
+ if (mask & FAN_FS_ERROR &&
+ mark_type != FAN_MARK_FILESYSTEM)
+ goto fput_and_out;
+
+ /*
+ * Evictable is only relevant for inode marks, because only inode object
+ * can be evicted on memory pressure.
+ */
+ if (flags & FAN_MARK_EVICTABLE &&
+ mark_type != FAN_MARK_INODE)
+ goto fput_and_out;
+
+ /*
+ * Events that do not carry enough information to report
+ * event->fd require a group that supports reporting fid. Those
+ * events are not supported on a mount mark, because they do not
+ * carry enough information (i.e. path) to be filtered by mount
+ * point.
+ */
+ fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
+ if (mask & ~(FANOTIFY_FD_EVENTS|FANOTIFY_EVENT_FLAGS) &&
+ (!fid_mode || mark_type == FAN_MARK_MOUNT))
+ goto fput_and_out;
+
+ /*
+ * FAN_RENAME uses special info type records to report the old and
+ * new parent+name. Reporting only old and new parent id is less
+ * useful and was not implemented.
+ */
+ if (mask & FAN_RENAME && !(fid_mode & FAN_REPORT_NAME))
+ goto fput_and_out;
+
+ if (mark_cmd == FAN_MARK_FLUSH) {
+ ret = 0;
+ if (mark_type == FAN_MARK_MOUNT)
+ fsnotify_clear_vfsmount_marks_by_group(group);
+ else if (mark_type == FAN_MARK_FILESYSTEM)
+ fsnotify_clear_sb_marks_by_group(group);
+ else
+ fsnotify_clear_inode_marks_by_group(group);
+ goto fput_and_out;
+ }
+
+ ret = fanotify_find_path(dfd, pathname, &path, flags,
+ (mask & ALL_FSNOTIFY_EVENTS), obj_type);
+ if (ret)
+ goto fput_and_out;
+
+ if (mark_cmd == FAN_MARK_ADD) {
+ ret = fanotify_events_supported(group, &path, mask, flags);
+ if (ret)
+ goto path_put_and_out;
+ }
+
+ if (fid_mode) {
+ ret = fanotify_test_fsid(path.dentry, &__fsid);
+ if (ret)
+ goto path_put_and_out;
+
+ ret = fanotify_test_fid(path.dentry);
+ if (ret)
+ goto path_put_and_out;
+
+ fsid = &__fsid;
+ }
+
+ /* inode held in place by reference to path; group by fget on fd */
+ if (mark_type == FAN_MARK_INODE)
+ inode = path.dentry->d_inode;
+ else
+ mnt = path.mnt;
+
+ ret = mnt ? -EINVAL : -EISDIR;
+ /* FAN_MARK_IGNORE requires SURV_MODIFY for sb/mount/dir marks */
+ if (mark_cmd == FAN_MARK_ADD && ignore == FAN_MARK_IGNORE &&
+ (mnt || S_ISDIR(inode->i_mode)) &&
+ !(flags & FAN_MARK_IGNORED_SURV_MODIFY))
+ goto path_put_and_out;
+
+ /* Mask out FAN_EVENT_ON_CHILD flag for sb/mount/non-dir marks */
+ if (mnt || !S_ISDIR(inode->i_mode)) {
+ mask &= ~FAN_EVENT_ON_CHILD;
+ umask = FAN_EVENT_ON_CHILD;
+ /*
+ * If group needs to report parent fid, register for getting
+ * events with parent/name info for non-directory.
+ */
+ if ((fid_mode & FAN_REPORT_DIR_FID) &&
+ (flags & FAN_MARK_ADD) && !ignore)
+ mask |= FAN_EVENT_ON_CHILD;
+ }
+
+ /* create/update an inode mark */
+ switch (mark_cmd) {
+ case FAN_MARK_ADD:
+ if (mark_type == FAN_MARK_MOUNT)
+ ret = fanotify_add_vfsmount_mark(group, mnt, mask,
+ flags, fsid);
+ else if (mark_type == FAN_MARK_FILESYSTEM)
+ ret = fanotify_add_sb_mark(group, mnt->mnt_sb, mask,
+ flags, fsid);
+ else
+ ret = fanotify_add_inode_mark(group, inode, mask,
+ flags, fsid);
+ break;
+ case FAN_MARK_REMOVE:
+ if (mark_type == FAN_MARK_MOUNT)
+ ret = fanotify_remove_vfsmount_mark(group, mnt, mask,
+ flags, umask);
+ else if (mark_type == FAN_MARK_FILESYSTEM)
+ ret = fanotify_remove_sb_mark(group, mnt->mnt_sb, mask,
+ flags, umask);
+ else
+ ret = fanotify_remove_inode_mark(group, inode, mask,
+ flags, umask);
+ break;
+ default:
+ ret = -EINVAL;
+ }
+
+path_put_and_out:
+ path_put(&path);
+fput_and_out:
+ fdput(f);
+ return ret;
+}
+
+#ifndef CONFIG_ARCH_SPLIT_ARG64
+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);
+}
+#endif
+
+#if defined(CONFIG_ARCH_SPLIT_ARG64) || defined(CONFIG_COMPAT)
+SYSCALL32_DEFINE6(fanotify_mark,
+ int, fanotify_fd, unsigned int, flags,
+ SC_ARG64(mask), int, dfd,
+ const char __user *, pathname)
+{
+ return do_fanotify_mark(fanotify_fd, flags, SC_VAL64(__u64, mask),
+ 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)
+{
+ struct sysinfo si;
+ int max_marks;
+
+ si_meminfo(&si);
+ /*
+ * Allow up to 1% of addressable memory to be accounted for per user
+ * marks limited to the range [8192, 1048576]. mount and sb marks are
+ * a lot cheaper than inode marks, but there is no reason for a user
+ * to have many of those, so calculate by the cost of inode marks.
+ */
+ max_marks = (((si.totalram - si.totalhigh) / 100) << PAGE_SHIFT) /
+ INODE_MARK_COST;
+ max_marks = clamp(max_marks, FANOTIFY_OLD_DEFAULT_MAX_MARKS,
+ FANOTIFY_DEFAULT_MAX_USER_MARKS);
+
+ BUILD_BUG_ON(FANOTIFY_INIT_FLAGS & FANOTIFY_INTERNAL_GROUP_FLAGS);
+ BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 12);
+ BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 11);
+
+ fanotify_mark_cache = KMEM_CACHE(fsnotify_mark,
+ SLAB_PANIC|SLAB_ACCOUNT);
+ fanotify_fid_event_cachep = KMEM_CACHE(fanotify_fid_event,
+ SLAB_PANIC);
+ fanotify_path_event_cachep = KMEM_CACHE(fanotify_path_event,
+ SLAB_PANIC);
+ if (IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS)) {
+ fanotify_perm_event_cachep =
+ KMEM_CACHE(fanotify_perm_event, SLAB_PANIC);
+ }
+
+ fanotify_max_queued_events = FANOTIFY_DEFAULT_MAX_EVENTS;
+ init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS] =
+ FANOTIFY_DEFAULT_MAX_GROUPS;
+ init_user_ns.ucount_max[UCOUNT_FANOTIFY_MARKS] = max_marks;
+ fanotify_sysctls_init();
+
+ return 0;
+}
+device_initcall(fanotify_user_setup);
diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c
new file mode 100644
index 000000000..55081ae3a
--- /dev/null
+++ b/fs/notify/fdinfo.c
@@ -0,0 +1,148 @@
+// 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/exportfs.h>
+
+#include "inotify/inotify.h"
+#include "fanotify/fanotify.h"
+#include "fdinfo.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;
+
+ fsnotify_group_lock(group);
+ list_for_each_entry(mark, &group->marks_list, g_list) {
+ show(m, mark);
+ if (seq_has_overflowed(m))
+ break;
+ }
+ fsnotify_group_unlock(group);
+}
+
+#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, NULL);
+ 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) {
+ seq_printf(m, "inotify wd:%x ino:%lx sdev:%x mask:%x ignored_mask:0 ",
+ inode_mark->wd, inode->i_ino, inode->i_sb->s_dev,
+ inotify_mark_user_mask(mark));
+ 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 = fanotify_mark_user_flags(mark);
+ struct inode *inode;
+
+ 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->ignore_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->ignore_mask);
+ } else if (mark->connector->type == FSNOTIFY_OBJ_TYPE_SB) {
+ struct super_block *sb = fsnotify_conn_sb(mark->connector);
+
+ seq_printf(m, "fanotify sdev:%x mflags:%x mask:%x ignored_mask:%x\n",
+ sb->s_dev, mflags, mark->mask, mark->ignore_mask);
+ }
+}
+
+void fanotify_show_fdinfo(struct seq_file *m, struct file *f)
+{
+ struct fsnotify_group *group = f->private_data;
+
+ seq_printf(m, "fanotify flags:%x event-flags:%x\n",
+ group->fanotify_data.flags & FANOTIFY_INIT_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 000000000..5c9937e02
--- /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 000000000..7974e91ff
--- /dev/null
+++ b/fs/notify/fsnotify.c
@@ -0,0 +1,601 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
+ */
+
+#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.
+ */
+static 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.
+ * However, we should have been called /after/ evict_inodes
+ * removed all zero refcount inodes, in any case. Test to
+ * be sure.
+ */
+ 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);
+
+ iput(iput_inode);
+
+ /* for each watch, send FS_UNMOUNT and then remove it */
+ fsnotify_inode(inode, FS_UNMOUNT);
+
+ fsnotify_inode_delete(inode);
+
+ iput_inode = inode;
+
+ cond_resched();
+ spin_lock(&sb->s_inode_list_lock);
+ }
+ spin_unlock(&sb->s_inode_list_lock);
+
+ iput(iput_inode);
+}
+
+void fsnotify_sb_delete(struct super_block *sb)
+{
+ fsnotify_unmount_inodes(sb);
+ fsnotify_clear_marks_by_sb(sb);
+ /* Wait for outstanding object references from connectors */
+ wait_var_event(&sb->s_fsnotify_connectors,
+ !atomic_long_read(&sb->s_fsnotify_connectors));
+}
+
+/*
+ * 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 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);
+}
+
+/* Are inode/sb/mount interested in parent and name info with this event? */
+static bool fsnotify_event_needs_parent(struct inode *inode, struct mount *mnt,
+ __u32 mask)
+{
+ __u32 marks_mask = 0;
+
+ /* We only send parent/name to inode/sb/mount for events on non-dir */
+ if (mask & FS_ISDIR)
+ return false;
+
+ /*
+ * All events that are possible on child can also may be reported with
+ * parent/name info to inode/sb/mount. Otherwise, a watching parent
+ * could result in events reported with unexpected name info to sb/mount.
+ */
+ BUILD_BUG_ON(FS_EVENTS_POSS_ON_CHILD & ~FS_EVENTS_POSS_TO_PARENT);
+
+ /* Did either inode/sb/mount subscribe for events with parent/name? */
+ marks_mask |= fsnotify_parent_needed_mask(inode->i_fsnotify_mask);
+ marks_mask |= fsnotify_parent_needed_mask(inode->i_sb->s_fsnotify_mask);
+ if (mnt)
+ marks_mask |= fsnotify_parent_needed_mask(mnt->mnt_fsnotify_mask);
+
+ /* Did they subscribe for this event with parent/name info? */
+ return mask & marks_mask;
+}
+
+/*
+ * Notify this dentry's parent about a child's events with child name info
+ * if parent is watching or if inode/sb/mount are interested in events with
+ * parent and name info.
+ *
+ * Notify only the child without name info if parent is not watching and
+ * inode/sb/mount are not interested in events with parent and name info.
+ */
+int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data,
+ int data_type)
+{
+ const struct path *path = fsnotify_data_path(data, data_type);
+ struct mount *mnt = path ? real_mount(path->mnt) : NULL;
+ struct inode *inode = d_inode(dentry);
+ struct dentry *parent;
+ bool parent_watched = dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED;
+ bool parent_needed, parent_interested;
+ __u32 p_mask;
+ struct inode *p_inode = NULL;
+ struct name_snapshot name;
+ struct qstr *file_name = NULL;
+ int ret = 0;
+
+ /*
+ * Do inode/sb/mount care about parent and name info on non-dir?
+ * Do they care about any event at all?
+ */
+ if (!inode->i_fsnotify_marks && !inode->i_sb->s_fsnotify_marks &&
+ (!mnt || !mnt->mnt_fsnotify_marks) && !parent_watched)
+ return 0;
+
+ parent = NULL;
+ parent_needed = fsnotify_event_needs_parent(inode, mnt, mask);
+ if (!parent_watched && !parent_needed)
+ goto notify;
+
+ /* Does parent inode care about events on children? */
+ parent = dget_parent(dentry);
+ p_inode = parent->d_inode;
+ p_mask = fsnotify_inode_watches_children(p_inode);
+ if (unlikely(parent_watched && !p_mask))
+ __fsnotify_update_child_dentry_flags(p_inode);
+
+ /*
+ * Include parent/name in notification either if some notification
+ * groups require parent info or the parent is interested in this event.
+ */
+ parent_interested = mask & p_mask & ALL_FSNOTIFY_EVENTS;
+ if (parent_needed || parent_interested) {
+ /* When notifying parent, child should be passed as data */
+ WARN_ON_ONCE(inode != fsnotify_data_inode(data, data_type));
+
+ /* Notify both parent and child with child name info */
+ take_dentry_name_snapshot(&name, dentry);
+ file_name = &name.name;
+ if (parent_interested)
+ mask |= FS_EVENT_ON_CHILD;
+ }
+
+notify:
+ ret = fsnotify(mask, data, data_type, p_inode, file_name, inode, 0);
+
+ if (file_name)
+ release_dentry_name_snapshot(&name);
+ dput(parent);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(__fsnotify_parent);
+
+static int fsnotify_handle_inode_event(struct fsnotify_group *group,
+ struct fsnotify_mark *inode_mark,
+ u32 mask, const void *data, int data_type,
+ struct inode *dir, const struct qstr *name,
+ u32 cookie)
+{
+ const struct path *path = fsnotify_data_path(data, data_type);
+ struct inode *inode = fsnotify_data_inode(data, data_type);
+ const struct fsnotify_ops *ops = group->ops;
+
+ if (WARN_ON_ONCE(!ops->handle_inode_event))
+ return 0;
+
+ if (WARN_ON_ONCE(!inode && !dir))
+ return 0;
+
+ if ((inode_mark->flags & FSNOTIFY_MARK_FLAG_EXCL_UNLINK) &&
+ path && d_unlinked(path->dentry))
+ return 0;
+
+ /* Check interest of this mark in case event was sent with two marks */
+ if (!(mask & inode_mark->mask & ALL_FSNOTIFY_EVENTS))
+ return 0;
+
+ return ops->handle_inode_event(inode_mark, mask, inode, dir, name, cookie);
+}
+
+static int fsnotify_handle_event(struct fsnotify_group *group, __u32 mask,
+ const void *data, int data_type,
+ struct inode *dir, const struct qstr *name,
+ u32 cookie, struct fsnotify_iter_info *iter_info)
+{
+ struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info);
+ struct fsnotify_mark *parent_mark = fsnotify_iter_parent_mark(iter_info);
+ int ret;
+
+ if (WARN_ON_ONCE(fsnotify_iter_sb_mark(iter_info)) ||
+ WARN_ON_ONCE(fsnotify_iter_vfsmount_mark(iter_info)))
+ return 0;
+
+ /*
+ * For FS_RENAME, 'dir' is old dir and 'data' is new dentry.
+ * The only ->handle_inode_event() backend that supports FS_RENAME is
+ * dnotify, where it means file was renamed within same parent.
+ */
+ if (mask & FS_RENAME) {
+ struct dentry *moved = fsnotify_data_dentry(data, data_type);
+
+ if (dir != moved->d_parent->d_inode)
+ return 0;
+ }
+
+ if (parent_mark) {
+ ret = fsnotify_handle_inode_event(group, parent_mark, mask,
+ data, data_type, dir, name, 0);
+ if (ret)
+ return ret;
+ }
+
+ if (!inode_mark)
+ return 0;
+
+ if (mask & FS_EVENT_ON_CHILD) {
+ /*
+ * Some events can be sent on both parent dir and child marks
+ * (e.g. FS_ATTRIB). If both parent dir and child are
+ * watching, report the event once to parent dir with name (if
+ * interested) and once to child without name (if interested).
+ * The child watcher is expecting an event without a file name
+ * and without the FS_EVENT_ON_CHILD flag.
+ */
+ mask &= ~FS_EVENT_ON_CHILD;
+ dir = NULL;
+ name = NULL;
+ }
+
+ return fsnotify_handle_inode_event(group, inode_mark, mask, data, data_type,
+ dir, name, cookie);
+}
+
+static int send_to_group(__u32 mask, const void *data, int data_type,
+ struct inode *dir, const struct qstr *file_name,
+ u32 cookie, struct fsnotify_iter_info *iter_info)
+{
+ struct fsnotify_group *group = NULL;
+ __u32 test_mask = (mask & ALL_FSNOTIFY_EVENTS);
+ __u32 marks_mask = 0;
+ __u32 marks_ignore_mask = 0;
+ bool is_dir = mask & FS_ISDIR;
+ struct fsnotify_mark *mark;
+ int type;
+
+ if (!iter_info->report_mask)
+ return 0;
+
+ /* clear ignored on inode modification */
+ if (mask & FS_MODIFY) {
+ fsnotify_foreach_iter_mark_type(iter_info, mark, type) {
+ if (!(mark->flags &
+ FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY))
+ mark->ignore_mask = 0;
+ }
+ }
+
+ /* Are any of the group marks interested in this event? */
+ fsnotify_foreach_iter_mark_type(iter_info, mark, type) {
+ group = mark->group;
+ marks_mask |= mark->mask;
+ marks_ignore_mask |=
+ fsnotify_effective_ignore_mask(mark, is_dir, type);
+ }
+
+ pr_debug("%s: group=%p mask=%x marks_mask=%x marks_ignore_mask=%x data=%p data_type=%d dir=%p cookie=%d\n",
+ __func__, group, mask, marks_mask, marks_ignore_mask,
+ data, data_type, dir, cookie);
+
+ if (!(test_mask & marks_mask & ~marks_ignore_mask))
+ return 0;
+
+ if (group->ops->handle_event) {
+ return group->ops->handle_event(group, mask, data, data_type, dir,
+ file_name, cookie, iter_info);
+ }
+
+ return fsnotify_handle_event(group, mask, data, data_type, dir,
+ 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 to a subset of the selected marks.
+ * Returns false if there are no more groups to iterate.
+ */
+static bool 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_iter_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 false;
+
+ /* Set the report mask for marks from same group as max prio group */
+ iter_info->current_group = max_prio_group;
+ iter_info->report_mask = 0;
+ fsnotify_foreach_iter_type(type) {
+ mark = iter_info->marks[type];
+ if (mark && mark->group == iter_info->current_group) {
+ /*
+ * FSNOTIFY_ITER_TYPE_PARENT indicates that this inode
+ * is watching children and interested in this event,
+ * which is an event possible on child.
+ * But is *this mark* watching children?
+ */
+ if (type == FSNOTIFY_ITER_TYPE_PARENT &&
+ !(mark->mask & FS_EVENT_ON_CHILD) &&
+ !(fsnotify_ignore_mask(mark) & FS_EVENT_ON_CHILD))
+ continue;
+
+ fsnotify_iter_set_report_type(iter_info, type);
+ }
+ }
+
+ return true;
+}
+
+/*
+ * Pop from iter_info multi head queue, the marks that belong to the group of
+ * current iteration step.
+ */
+static void fsnotify_iter_next(struct fsnotify_iter_info *iter_info)
+{
+ struct fsnotify_mark *mark;
+ int type;
+
+ /*
+ * We cannot use fsnotify_foreach_iter_mark_type() here because we
+ * may need to advance a mark of type X that belongs to current_group
+ * but was not selected for reporting.
+ */
+ fsnotify_foreach_iter_type(type) {
+ mark = iter_info->marks[type];
+ if (mark && mark->group == iter_info->current_group)
+ iter_info->marks[type] =
+ fsnotify_next_mark(iter_info->marks[type]);
+ }
+}
+
+/*
+ * fsnotify - 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.
+ *
+ * @mask: event type and flags
+ * @data: object that event happened on
+ * @data_type: type of object for fanotify_data_XXX() accessors
+ * @dir: optional directory associated with event -
+ * if @file_name is not NULL, this is the directory that
+ * @file_name is relative to
+ * @file_name: optional file name associated with event
+ * @inode: optional inode associated with event -
+ * If @dir and @inode are both non-NULL, event may be
+ * reported to both.
+ * @cookie: inotify rename cookie
+ */
+int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
+ const struct qstr *file_name, struct inode *inode, u32 cookie)
+{
+ const struct path *path = fsnotify_data_path(data, data_type);
+ struct super_block *sb = fsnotify_data_sb(data, data_type);
+ struct fsnotify_iter_info iter_info = {};
+ struct mount *mnt = NULL;
+ struct inode *inode2 = NULL;
+ struct dentry *moved;
+ int inode2_type;
+ int ret = 0;
+ __u32 test_mask, marks_mask;
+
+ if (path)
+ mnt = real_mount(path->mnt);
+
+ if (!inode) {
+ /* Dirent event - report on TYPE_INODE to dir */
+ inode = dir;
+ /* For FS_RENAME, inode is old_dir and inode2 is new_dir */
+ if (mask & FS_RENAME) {
+ moved = fsnotify_data_dentry(data, data_type);
+ inode2 = moved->d_parent->d_inode;
+ inode2_type = FSNOTIFY_ITER_TYPE_INODE2;
+ }
+ } else if (mask & FS_EVENT_ON_CHILD) {
+ /*
+ * Event on child - report on TYPE_PARENT to dir if it is
+ * watching children and on TYPE_INODE to child.
+ */
+ inode2 = dir;
+ inode2_type = FSNOTIFY_ITER_TYPE_PARENT;
+ }
+
+ /*
+ * 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 (!sb->s_fsnotify_marks &&
+ (!mnt || !mnt->mnt_fsnotify_marks) &&
+ (!inode || !inode->i_fsnotify_marks) &&
+ (!inode2 || !inode2->i_fsnotify_marks))
+ return 0;
+
+ marks_mask = sb->s_fsnotify_mask;
+ if (mnt)
+ marks_mask |= mnt->mnt_fsnotify_mask;
+ if (inode)
+ marks_mask |= inode->i_fsnotify_mask;
+ if (inode2)
+ marks_mask |= inode2->i_fsnotify_mask;
+
+
+ /*
+ * If this is a modify event we may need to clear some ignore masks.
+ * In that case, the object with ignore masks will have the FS_MODIFY
+ * event in its mask.
+ * Otherwise, return if none of the marks care about this type of event.
+ */
+ test_mask = (mask & ALL_FSNOTIFY_EVENTS);
+ if (!(test_mask & marks_mask))
+ return 0;
+
+ iter_info.srcu_idx = srcu_read_lock(&fsnotify_mark_srcu);
+
+ iter_info.marks[FSNOTIFY_ITER_TYPE_SB] =
+ fsnotify_first_mark(&sb->s_fsnotify_marks);
+ if (mnt) {
+ iter_info.marks[FSNOTIFY_ITER_TYPE_VFSMOUNT] =
+ fsnotify_first_mark(&mnt->mnt_fsnotify_marks);
+ }
+ if (inode) {
+ iter_info.marks[FSNOTIFY_ITER_TYPE_INODE] =
+ fsnotify_first_mark(&inode->i_fsnotify_marks);
+ }
+ if (inode2) {
+ iter_info.marks[inode2_type] =
+ fsnotify_first_mark(&inode2->i_fsnotify_marks);
+ }
+
+ /*
+ * We need to merge inode/vfsmount/sb mark lists so that e.g. inode mark
+ * ignore masks are properly reflected for mount/sb mark notifications.
+ * That's why this traversal is so complicated...
+ */
+ while (fsnotify_iter_select_report_types(&iter_info)) {
+ ret = send_to_group(mask, data, data_type, dir, file_name,
+ cookie, &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);
+
+static __init int fsnotify_init(void)
+{
+ int ret;
+
+ BUILD_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 000000000..fde74eb33
--- /dev/null
+++ b/fs/notify/fsnotify.h
@@ -0,0 +1,81 @@
+/* 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);
+}
+
+static inline struct super_block *fsnotify_conn_sb(
+ struct fsnotify_mark_connector *conn)
+{
+ return container_of(conn->obj, struct super_block, s_fsnotify_marks);
+}
+
+static inline struct super_block *fsnotify_connector_sb(
+ struct fsnotify_mark_connector *conn)
+{
+ switch (conn->type) {
+ case FSNOTIFY_OBJ_TYPE_INODE:
+ return fsnotify_conn_inode(conn)->i_sb;
+ case FSNOTIFY_OBJ_TYPE_VFSMOUNT:
+ return fsnotify_conn_mount(conn)->mnt.mnt_sb;
+ case FSNOTIFY_OBJ_TYPE_SB:
+ return fsnotify_conn_sb(conn);
+ default:
+ return NULL;
+ }
+}
+
+/* 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);
+}
+/* run the list of all marks associated with sb and destroy them */
+static inline void fsnotify_clear_marks_by_sb(struct super_block *sb)
+{
+ fsnotify_destroy_marks(&sb->s_fsnotify_marks);
+}
+
+/*
+ * 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);
+
+extern struct kmem_cache *fsnotify_mark_connector_cachep;
+
+#endif /* __FS_NOTIFY_FSNOTIFY_H_ */
diff --git a/fs/notify/group.c b/fs/notify/group.c
new file mode 100644
index 000000000..1de6631a3
--- /dev/null
+++ b/fs/notify/group.c
@@ -0,0 +1,171 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
+ */
+
+#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);
+ mutex_destroy(&group->mark_mutex);
+
+ 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_TYPE_ANY);
+
+ /*
+ * 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, 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);
+}
+EXPORT_SYMBOL_GPL(fsnotify_put_group);
+
+static struct fsnotify_group *__fsnotify_alloc_group(
+ const struct fsnotify_ops *ops,
+ int flags, gfp_t gfp)
+{
+ static struct lock_class_key nofs_marks_lock;
+ struct fsnotify_group *group;
+
+ group = kzalloc(sizeof(struct fsnotify_group), gfp);
+ 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->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;
+ group->flags = flags;
+ /*
+ * For most backends, eviction of inode with a mark is not expected,
+ * because marks hold a refcount on the inode against eviction.
+ *
+ * Use a different lockdep class for groups that support evictable
+ * inode marks, because with evictable marks, mark_mutex is NOT
+ * fs-reclaim safe - the mutex is taken when evicting inodes.
+ */
+ if (flags & FSNOTIFY_GROUP_NOFS)
+ lockdep_set_class(&group->mark_mutex, &nofs_marks_lock);
+
+ return 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,
+ int flags)
+{
+ gfp_t gfp = (flags & FSNOTIFY_GROUP_USER) ? GFP_KERNEL_ACCOUNT :
+ GFP_KERNEL;
+
+ return __fsnotify_alloc_group(ops, flags, gfp);
+}
+EXPORT_SYMBOL_GPL(fsnotify_alloc_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 000000000..1cc8be25d
--- /dev/null
+++ b/fs/notify/inotify/Kconfig
@@ -0,0 +1,17 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config INOTIFY_USER
+ bool "Inotify support for userspace"
+ 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.rst>
+
+ If unsure, say Y.
diff --git a/fs/notify/inotify/Makefile b/fs/notify/inotify/Makefile
new file mode 100644
index 000000000..812237eec
--- /dev/null
+++ b/fs/notify/inotify/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+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 000000000..7d5df7a21
--- /dev/null
+++ b/fs/notify/inotify/inotify.h
@@ -0,0 +1,69 @@
+/* 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;
+ u32 mask;
+ 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);
+}
+
+/*
+ * INOTIFY_USER_FLAGS 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.
+ */
+#define INOTIFY_USER_MASK (IN_ALL_EVENTS)
+
+static inline __u32 inotify_mark_user_mask(struct fsnotify_mark *fsn_mark)
+{
+ __u32 mask = fsn_mark->mask & INOTIFY_USER_MASK;
+
+ if (fsn_mark->flags & FSNOTIFY_MARK_FLAG_EXCL_UNLINK)
+ mask |= IN_EXCL_UNLINK;
+ if (fsn_mark->flags & FSNOTIFY_MARK_FLAG_IN_ONESHOT)
+ mask |= IN_ONESHOT;
+
+ return mask;
+}
+
+extern void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark,
+ struct fsnotify_group *group);
+extern int inotify_handle_inode_event(struct fsnotify_mark *inode_mark,
+ u32 mask, struct inode *inode,
+ struct inode *dir,
+ const struct qstr *name, u32 cookie);
+
+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 000000000..993375f0d
--- /dev/null
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -0,0 +1,209 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * 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
+ */
+
+#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;
+
+ old = INOTIFY_E(old_fsn);
+ new = INOTIFY_E(new_fsn);
+ if (old->mask & FS_IN_IGNORED)
+ return false;
+ if ((old->mask == new->mask) &&
+ (old->wd == new->wd) &&
+ (old->name_len == new->name_len) &&
+ (!old->name_len || !strcmp(old->name, new->name)))
+ return true;
+ return false;
+}
+
+static int inotify_merge(struct fsnotify_group *group,
+ struct fsnotify_event *event)
+{
+ struct list_head *list = &group->notification_list;
+ struct fsnotify_event *last_event;
+
+ last_event = list_entry(list->prev, struct fsnotify_event, list);
+ return event_compare(last_event, event);
+}
+
+int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask,
+ struct inode *inode, struct inode *dir,
+ const struct qstr *name, u32 cookie)
+{
+ struct inotify_inode_mark *i_mark;
+ struct inotify_event_info *event;
+ struct fsnotify_event *fsn_event;
+ struct fsnotify_group *group = inode_mark->group;
+ int ret;
+ int len = 0, wd;
+ int alloc_len = sizeof(struct inotify_event_info);
+ struct mem_cgroup *old_memcg;
+
+ if (name) {
+ len = name->len;
+ alloc_len += len + 1;
+ }
+
+ pr_debug("%s: group=%p mark=%p mask=%x\n", __func__, group, inode_mark,
+ mask);
+
+ i_mark = container_of(inode_mark, struct inotify_inode_mark,
+ fsn_mark);
+
+ /*
+ * We can be racing with mark being detached. Don't report event with
+ * invalid wd.
+ */
+ wd = READ_ONCE(i_mark->wd);
+ if (wd == -1)
+ return 0;
+ /*
+ * Whoever is interested in the event, pays for the allocation. Do not
+ * trigger OOM killer in the target monitoring memcg as it may have
+ * security repercussion.
+ */
+ old_memcg = set_active_memcg(group->memcg);
+ event = kmalloc(alloc_len, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL);
+ set_active_memcg(old_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;
+ }
+
+ /*
+ * We now report FS_ISDIR flag with MOVE_SELF and DELETE_SELF events
+ * for fanotify. inotify never reported IN_ISDIR with those events.
+ * It looks like an oversight, but to avoid the risk of breaking
+ * existing inotify programs, mask the flag out from those events.
+ */
+ if (mask & (IN_MOVE_SELF | IN_DELETE_SELF))
+ mask &= ~IN_ISDIR;
+
+ fsn_event = &event->fse;
+ fsnotify_init_event(fsn_event);
+ event->mask = mask;
+ event->wd = wd;
+ event->sync_cookie = cookie;
+ event->name_len = len;
+ if (len)
+ strcpy(event->name, name->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->flags & FSNOTIFY_MARK_FLAG_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_group *group,
+ 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_inode_event = inotify_handle_inode_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 000000000..1c4bfdab0
--- /dev/null
+++ b/fs/notify/inotify/inotify_user.c
@@ -0,0 +1,875 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * 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
+ */
+
+#include <linux/file.h>
+#include <linux/fs.h> /* struct inode */
+#include <linux/fsnotify_backend.h>
+#include <linux/idr.h>
+#include <linux/init.h> /* fs_initcall */
+#include <linux/inotify.h>
+#include <linux/kernel.h> /* roundup() */
+#include <linux/namei.h> /* LOOKUP_FOLLOW */
+#include <linux/sched/signal.h>
+#include <linux/slab.h> /* struct kmem_cache */
+#include <linux/syscalls.h>
+#include <linux/types.h>
+#include <linux/anon_inodes.h>
+#include <linux/uaccess.h>
+#include <linux/poll.h>
+#include <linux/wait.h>
+#include <linux/memcontrol.h>
+#include <linux/security.h>
+
+#include "inotify.h"
+#include "../fdinfo.h"
+
+#include <asm/ioctls.h>
+
+/*
+ * An inotify watch requires allocating an inotify_inode_mark structure as
+ * well as pinning the watched inode. Doubling the size of a VFS inode
+ * should be more than enough to cover the additional filesystem inode
+ * size increase.
+ */
+#define INOTIFY_WATCH_COST (sizeof(struct inotify_inode_mark) + \
+ 2 * sizeof(struct inode))
+
+/* 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 long it_zero = 0;
+static long it_int_max = INT_MAX;
+
+static struct ctl_table inotify_table[] = {
+ {
+ .procname = "max_user_instances",
+ .data = &init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES],
+ .maxlen = sizeof(long),
+ .mode = 0644,
+ .proc_handler = proc_doulongvec_minmax,
+ .extra1 = &it_zero,
+ .extra2 = &it_int_max,
+ },
+ {
+ .procname = "max_user_watches",
+ .data = &init_user_ns.ucount_max[UCOUNT_INOTIFY_WATCHES],
+ .maxlen = sizeof(long),
+ .mode = 0644,
+ .proc_handler = proc_doulongvec_minmax,
+ .extra1 = &it_zero,
+ .extra2 = &it_int_max,
+ },
+ {
+ .procname = "max_queued_events",
+ .data = &inotify_max_queued_events,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO
+ },
+ { }
+};
+
+static void __init inotify_sysctls_init(void)
+{
+ register_sysctl("fs/inotify", inotify_table);
+}
+
+#else
+#define inotify_sysctls_init() do { } while (0)
+#endif /* CONFIG_SYSCTL */
+
+static inline __u32 inotify_arg_to_mask(struct inode *inode, u32 arg)
+{
+ __u32 mask;
+
+ /*
+ * Everything should receive events when the inode is unmounted.
+ * All directories care about children.
+ */
+ mask = (FS_UNMOUNT);
+ if (S_ISDIR(inode->i_mode))
+ mask |= FS_EVENT_ON_CHILD;
+
+ /* mask off the flags used to open the fd */
+ mask |= (arg & INOTIFY_USER_MASK);
+
+ return mask;
+}
+
+#define INOTIFY_MARK_FLAGS \
+ (FSNOTIFY_MARK_FLAG_EXCL_UNLINK | FSNOTIFY_MARK_FLAG_IN_ONESHOT)
+
+static inline unsigned int inotify_arg_to_flags(u32 arg)
+{
+ unsigned int flags = 0;
+
+ if (arg & IN_EXCL_UNLINK)
+ flags |= FSNOTIFY_MARK_FLAG_EXCL_UNLINK;
+ if (arg & IN_ONESHOT)
+ flags |= FSNOTIFY_MARK_FLAG_IN_ONESHOT;
+
+ return flags;
+}
+
+static inline u32 inotify_mask_to_arg(__u32 mask)
+{
+ return mask & (IN_ALL_EVENTS | IN_ISDIR | IN_UNMOUNT | IN_IGNORED |
+ IN_Q_OVERFLOW);
+}
+
+/* inotify 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;
+
+ event = fsnotify_peek_first_event(group);
+ if (!event)
+ return NULL;
+
+ pr_debug("%s: group=%p event=%p\n", __func__, group, event);
+
+ event_size += round_event_name_len(event);
+ if (event_size > count)
+ return ERR_PTR(-EINVAL);
+
+ /* 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(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 int flags, __u64 mask)
+{
+ 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 = path_permission(path, MAY_READ);
+ if (error) {
+ path_put(path);
+ return error;
+ }
+ error = security_path_notify(path, mask,
+ FSNOTIFY_OBJ_TYPE_INODE);
+ if (error)
+ path_put(path);
+
+ return error;
+}
+
+static int inotify_add_to_idr(struct idr *idr, spinlock_t *idr_lock,
+ struct inotify_inode_mark *i_mark)
+{
+ int ret;
+
+ idr_preload(GFP_KERNEL);
+ spin_lock(idr_lock);
+
+ ret = idr_alloc_cyclic(idr, i_mark, 1, 0, GFP_NOWAIT);
+ if (ret >= 0) {
+ /* 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;
+
+ /* Queue ignore event for the watch */
+ inotify_handle_inode_event(fsn_mark, FS_IN_IGNORED, NULL, NULL, NULL,
+ 0);
+
+ i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
+ /* 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;
+ int replace = !(arg & IN_MASK_ADD);
+ int create = (arg & IN_MASK_CREATE);
+ int ret;
+
+ fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, group);
+ if (!fsn_mark)
+ return -ENOENT;
+ else if (create) {
+ ret = -EEXIST;
+ goto out;
+ }
+
+ i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
+
+ spin_lock(&fsn_mark->lock);
+ old_mask = fsn_mark->mask;
+ if (replace) {
+ fsn_mark->mask = 0;
+ fsn_mark->flags &= ~INOTIFY_MARK_FLAGS;
+ }
+ fsn_mark->mask |= inotify_arg_to_mask(inode, arg);
+ fsn_mark->flags |= inotify_arg_to_flags(arg);
+ new_mask = fsn_mark->mask;
+ spin_unlock(&fsn_mark->lock);
+
+ if (old_mask != new_mask) {
+ /* 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;
+
+out:
+ /* 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;
+ int ret;
+ struct idr *idr = &group->inotify_data.idr;
+ spinlock_t *idr_lock = &group->inotify_data.idr_lock;
+
+ tmp_i_mark = kmem_cache_alloc(inotify_inode_mark_cachep, GFP_KERNEL);
+ if (unlikely(!tmp_i_mark))
+ return -ENOMEM;
+
+ fsnotify_init_mark(&tmp_i_mark->fsn_mark, group);
+ tmp_i_mark->fsn_mark.mask = inotify_arg_to_mask(inode, arg);
+ tmp_i_mark->fsn_mark.flags = inotify_arg_to_flags(arg);
+ tmp_i_mark->wd = -1;
+
+ ret = inotify_add_to_idr(idr, idr_lock, tmp_i_mark);
+ if (ret)
+ goto out_err;
+
+ /* 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;
+
+ fsnotify_group_lock(group);
+ /* 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);
+ fsnotify_group_unlock(group);
+
+ return ret;
+}
+
+static struct fsnotify_group *inotify_new_group(unsigned int max_events)
+{
+ struct fsnotify_group *group;
+ struct inotify_event_info *oevent;
+
+ group = fsnotify_alloc_group(&inotify_fsnotify_ops,
+ FSNOTIFY_GROUP_USER);
+ if (IS_ERR(group))
+ return group;
+
+ oevent = kmalloc(sizeof(struct inotify_event_info), GFP_KERNEL_ACCOUNT);
+ if (unlikely(!oevent)) {
+ fsnotify_destroy_group(group);
+ return ERR_PTR(-ENOMEM);
+ }
+ group->overflow_event = &oevent->fse;
+ fsnotify_init_event(group->overflow_event);
+ oevent->mask = FS_Q_OVERFLOW;
+ oevent->wd = -1;
+ oevent->sync_cookie = 0;
+ oevent->name_len = 0;
+
+ group->max_events = max_events;
+ group->memcg = get_mem_cgroup_from_mm(current->mm);
+
+ spin_lock_init(&group->inotify_data.idr_lock);
+ idr_init(&group->inotify_data.idr);
+ group->inotify_data.ucounts = inc_ucount(current_user_ns(),
+ current_euid(),
+ UCOUNT_INOTIFY_INSTANCES);
+
+ if (!group->inotify_data.ucounts) {
+ fsnotify_destroy_group(group);
+ return ERR_PTR(-EMFILE);
+ }
+
+ return group;
+}
+
+
+/* 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))) {
+ ret = -EINVAL;
+ goto fput_and_out;
+ }
+
+ /* 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,
+ (mask & IN_ALL_EVENTS));
+ 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 = -EINVAL;
+
+ f = fdget(fd);
+ if (unlikely(!f.file))
+ return -EBADF;
+
+ /* verify that this is indeed an inotify instance */
+ if (unlikely(f.file->f_op != &inotify_fops))
+ goto out;
+
+ group = f.file->private_data;
+
+ i_mark = inotify_idr_find(group, wd);
+ if (unlikely(!i_mark))
+ goto out;
+
+ ret = 0;
+
+ fsnotify_destroy_mark(&i_mark->fsn_mark, group);
+
+ /* 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)
+{
+ unsigned long watches_max;
+ struct sysinfo si;
+
+ si_meminfo(&si);
+ /*
+ * Allow up to 1% of addressable memory to be allocated for inotify
+ * watches (per user) limited to the range [8192, 1048576].
+ */
+ watches_max = (((si.totalram - si.totalhigh) / 100) << PAGE_SHIFT) /
+ INOTIFY_WATCH_COST;
+ watches_max = clamp(watches_max, 8192UL, 1048576UL);
+
+ BUILD_BUG_ON(IN_ACCESS != FS_ACCESS);
+ BUILD_BUG_ON(IN_MODIFY != FS_MODIFY);
+ BUILD_BUG_ON(IN_ATTRIB != FS_ATTRIB);
+ BUILD_BUG_ON(IN_CLOSE_WRITE != FS_CLOSE_WRITE);
+ BUILD_BUG_ON(IN_CLOSE_NOWRITE != FS_CLOSE_NOWRITE);
+ BUILD_BUG_ON(IN_OPEN != FS_OPEN);
+ BUILD_BUG_ON(IN_MOVED_FROM != FS_MOVED_FROM);
+ BUILD_BUG_ON(IN_MOVED_TO != FS_MOVED_TO);
+ BUILD_BUG_ON(IN_CREATE != FS_CREATE);
+ BUILD_BUG_ON(IN_DELETE != FS_DELETE);
+ BUILD_BUG_ON(IN_DELETE_SELF != FS_DELETE_SELF);
+ BUILD_BUG_ON(IN_MOVE_SELF != FS_MOVE_SELF);
+ BUILD_BUG_ON(IN_UNMOUNT != FS_UNMOUNT);
+ BUILD_BUG_ON(IN_Q_OVERFLOW != FS_Q_OVERFLOW);
+ BUILD_BUG_ON(IN_IGNORED != FS_IN_IGNORED);
+ BUILD_BUG_ON(IN_ISDIR != FS_ISDIR);
+
+ BUILD_BUG_ON(HWEIGHT32(ALL_INOTIFY_BITS) != 22);
+
+ inotify_inode_mark_cachep = KMEM_CACHE(inotify_inode_mark,
+ SLAB_PANIC|SLAB_ACCOUNT);
+
+ inotify_max_queued_events = 16384;
+ init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES] = 128;
+ init_user_ns.ucount_max[UCOUNT_INOTIFY_WATCHES] = watches_max;
+ inotify_sysctls_init();
+
+ return 0;
+}
+fs_initcall(inotify_user_setup);
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
new file mode 100644
index 000000000..c74ef9474
--- /dev/null
+++ b/fs/notify/mark.c
@@ -0,0 +1,911 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
+ */
+
+/*
+ * 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/ratelimit.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;
+ else if (conn->type == FSNOTIFY_OBJ_TYPE_SB)
+ return &fsnotify_conn_sb(conn)->s_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_get_inode_ref(struct inode *inode)
+{
+ ihold(inode);
+ atomic_long_inc(&inode->i_sb->s_fsnotify_connectors);
+}
+
+/*
+ * Grab or drop inode reference for the connector if needed.
+ *
+ * When it's time to drop the reference, we only clear the HAS_IREF flag and
+ * return the inode object. fsnotify_drop_object() will be resonsible for doing
+ * iput() outside of spinlocks. This happens when last mark that wanted iref is
+ * detached.
+ */
+static struct inode *fsnotify_update_iref(struct fsnotify_mark_connector *conn,
+ bool want_iref)
+{
+ bool has_iref = conn->flags & FSNOTIFY_CONN_FLAG_HAS_IREF;
+ struct inode *inode = NULL;
+
+ if (conn->type != FSNOTIFY_OBJ_TYPE_INODE ||
+ want_iref == has_iref)
+ return NULL;
+
+ if (want_iref) {
+ /* Pin inode if any mark wants inode refcount held */
+ fsnotify_get_inode_ref(fsnotify_conn_inode(conn));
+ conn->flags |= FSNOTIFY_CONN_FLAG_HAS_IREF;
+ } else {
+ /* Unpin inode after detach of last mark that wanted iref */
+ inode = fsnotify_conn_inode(conn);
+ conn->flags &= ~FSNOTIFY_CONN_FLAG_HAS_IREF;
+ }
+
+ return inode;
+}
+
+static void *__fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
+{
+ u32 new_mask = 0;
+ bool want_iref = false;
+ 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 NULL;
+ hlist_for_each_entry(mark, &conn->list, obj_list) {
+ if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED))
+ continue;
+ new_mask |= fsnotify_calc_mask(mark);
+ if (conn->type == FSNOTIFY_OBJ_TYPE_INODE &&
+ !(mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF))
+ want_iref = true;
+ }
+ *fsnotify_conn_mask_p(conn) = new_mask;
+
+ return fsnotify_update_iref(conn, want_iref);
+}
+
+/*
+ * 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_put_inode_ref(struct inode *inode)
+{
+ struct super_block *sb = inode->i_sb;
+
+ iput(inode);
+ if (atomic_long_dec_and_test(&sb->s_fsnotify_connectors))
+ wake_up_var(&sb->s_fsnotify_connectors);
+}
+
+static void fsnotify_get_sb_connectors(struct fsnotify_mark_connector *conn)
+{
+ struct super_block *sb = fsnotify_connector_sb(conn);
+
+ if (sb)
+ atomic_long_inc(&sb->s_fsnotify_connectors);
+}
+
+static void fsnotify_put_sb_connectors(struct fsnotify_mark_connector *conn)
+{
+ struct super_block *sb = fsnotify_connector_sb(conn);
+
+ if (sb && atomic_long_dec_and_test(&sb->s_fsnotify_connectors))
+ wake_up_var(&sb->s_fsnotify_connectors);
+}
+
+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;
+
+ /* Unpin inode when detaching from connector */
+ if (!(conn->flags & FSNOTIFY_CONN_FLAG_HAS_IREF))
+ inode = NULL;
+ } else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) {
+ fsnotify_conn_mount(conn)->mnt_fsnotify_mask = 0;
+ } else if (conn->type == FSNOTIFY_OBJ_TYPE_SB) {
+ fsnotify_conn_sb(conn)->s_fsnotify_mask = 0;
+ }
+
+ fsnotify_put_sb_connectors(conn);
+ 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)
+{
+ if (!objp)
+ return;
+ /* Currently only inode references are passed to be dropped */
+ if (WARN_ON_ONCE(type != FSNOTIFY_OBJ_TYPE_INODE))
+ return;
+ fsnotify_put_inode_ref(objp);
+}
+
+void fsnotify_put_mark(struct fsnotify_mark *mark)
+{
+ struct fsnotify_mark_connector *conn = READ_ONCE(mark->connector);
+ void *objp = NULL;
+ unsigned int type = FSNOTIFY_OBJ_TYPE_DETACHED;
+ bool free_conn = false;
+
+ /* Catch marks that were actually never attached to object */
+ if (!conn) {
+ 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, &conn->lock))
+ return;
+
+ hlist_del_init_rcu(&mark->obj_list);
+ if (hlist_empty(&conn->list)) {
+ objp = fsnotify_detach_connector_from_object(conn, &type);
+ free_conn = true;
+ } else {
+ objp = __fsnotify_recalc_mask(conn);
+ type = conn->type;
+ }
+ WRITE_ONCE(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);
+}
+EXPORT_SYMBOL_GPL(fsnotify_put_mark);
+
+/*
+ * 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)
+ __releases(&fsnotify_mark_srcu)
+{
+ int type;
+
+ fsnotify_foreach_iter_type(type) {
+ /* This can fail if mark is being removed */
+ if (!fsnotify_get_mark_safe(iter_info->marks[type])) {
+ __release(&fsnotify_mark_srcu);
+ 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)
+ __acquires(&fsnotify_mark_srcu)
+{
+ int type;
+
+ iter_info->srcu_idx = srcu_read_lock(&fsnotify_mark_srcu);
+ fsnotify_foreach_iter_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)
+{
+ fsnotify_group_assert_locked(mark->group);
+ 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);
+
+ /* 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)
+{
+ fsnotify_group_lock(group);
+ fsnotify_detach_mark(mark);
+ fsnotify_group_unlock(group);
+ fsnotify_free_mark(mark);
+}
+EXPORT_SYMBOL_GPL(fsnotify_destroy_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 obj_type,
+ __kernel_fsid_t *fsid)
+{
+ 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->flags = 0;
+ conn->type = obj_type;
+ conn->obj = connp;
+ /* Cache fsid of filesystem containing the object */
+ if (fsid) {
+ conn->fsid = *fsid;
+ conn->flags = FSNOTIFY_CONN_FLAG_HAS_FSID;
+ } else {
+ conn->fsid.val[0] = conn->fsid.val[1] = 0;
+ conn->flags = 0;
+ }
+ fsnotify_get_sb_connectors(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 */
+ fsnotify_put_sb_connectors(conn);
+ 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 obj_type,
+ int add_flags, __kernel_fsid_t *fsid)
+{
+ struct fsnotify_mark *lmark, *last = NULL;
+ struct fsnotify_mark_connector *conn;
+ int cmp;
+ int err = 0;
+
+ if (WARN_ON(!fsnotify_valid_obj_type(obj_type)))
+ return -EINVAL;
+
+ /* Backend is expected to check for zero fsid (e.g. tmpfs) */
+ if (fsid && WARN_ON_ONCE(!fsid->val[0] && !fsid->val[1]))
+ return -ENODEV;
+
+restart:
+ spin_lock(&mark->lock);
+ conn = fsnotify_grab_connector(connp);
+ if (!conn) {
+ spin_unlock(&mark->lock);
+ err = fsnotify_attach_connector_to_object(connp, obj_type,
+ fsid);
+ if (err)
+ return err;
+ goto restart;
+ } else if (fsid && !(conn->flags & FSNOTIFY_CONN_FLAG_HAS_FSID)) {
+ conn->fsid = *fsid;
+ /* Pairs with smp_rmb() in fanotify_get_fsid() */
+ smp_wmb();
+ conn->flags |= FSNOTIFY_CONN_FLAG_HAS_FSID;
+ } else if (fsid && (conn->flags & FSNOTIFY_CONN_FLAG_HAS_FSID) &&
+ (fsid->val[0] != conn->fsid.val[0] ||
+ fsid->val[1] != conn->fsid.val[1])) {
+ /*
+ * Backend is expected to check for non uniform fsid
+ * (e.g. btrfs), but maybe we missed something?
+ * Only allow setting conn->fsid once to non zero fsid.
+ * inotify and non-fid fanotify groups do not set nor test
+ * conn->fsid.
+ */
+ pr_warn_ratelimited("%s: fsid mismatch on object of type %u: "
+ "%x.%x != %x.%x\n", __func__, conn->type,
+ fsid->val[0], fsid->val[1],
+ conn->fsid.val[0], conn->fsid.val[1]);
+ err = -EXDEV;
+ goto out_err;
+ }
+
+ /* 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) &&
+ !(mark->group->flags & FSNOTIFY_GROUP_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:
+ /*
+ * Since connector is attached to object using cmpxchg() we are
+ * guaranteed that connector initialization is fully visible by anyone
+ * seeing mark->connector set.
+ */
+ WRITE_ONCE(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 obj_type,
+ int add_flags, __kernel_fsid_t *fsid)
+{
+ struct fsnotify_group *group = mark->group;
+ int ret = 0;
+
+ fsnotify_group_assert_locked(group);
+
+ /*
+ * 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);
+ fsnotify_get_mark(mark); /* for g_list */
+ spin_unlock(&mark->lock);
+
+ ret = fsnotify_add_mark_list(mark, connp, obj_type, add_flags, fsid);
+ if (ret)
+ goto err;
+
+ 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);
+
+ fsnotify_put_mark(mark);
+ return ret;
+}
+
+int fsnotify_add_mark(struct fsnotify_mark *mark, fsnotify_connp_t *connp,
+ unsigned int obj_type, int add_flags,
+ __kernel_fsid_t *fsid)
+{
+ int ret;
+ struct fsnotify_group *group = mark->group;
+
+ fsnotify_group_lock(group);
+ ret = fsnotify_add_mark_locked(mark, connp, obj_type, add_flags, fsid);
+ fsnotify_group_unlock(group);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(fsnotify_add_mark);
+
+/*
+ * 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;
+}
+EXPORT_SYMBOL_GPL(fsnotify_find_mark);
+
+/* Clear any marks in a group with given type mask */
+void fsnotify_clear_marks_by_group(struct fsnotify_group *group,
+ unsigned int obj_type)
+{
+ 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 (obj_type == FSNOTIFY_OBJ_TYPE_ANY) {
+ 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.
+ */
+ fsnotify_group_lock(group);
+ list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) {
+ if (mark->connector->type == obj_type)
+ list_move(&mark->g_list, &to_free);
+ }
+ fsnotify_group_unlock(group);
+
+clear:
+ while (1) {
+ fsnotify_group_lock(group);
+ if (list_empty(head)) {
+ fsnotify_group_unlock(group);
+ break;
+ }
+ mark = list_first_entry(head, struct fsnotify_mark, g_list);
+ fsnotify_get_mark(mark);
+ fsnotify_detach_mark(mark);
+ fsnotify_group_unlock(group);
+ 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;
+ WRITE_ONCE(mark->connector, NULL);
+}
+EXPORT_SYMBOL_GPL(fsnotify_init_mark);
+
+/*
+ * 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);
+}
+EXPORT_SYMBOL_GPL(fsnotify_wait_marks_destroyed);
diff --git a/fs/notify/notification.c b/fs/notify/notification.c
new file mode 100644
index 000000000..9022ae650
--- /dev/null
+++ b/fs/notify/notification.c
@@ -0,0 +1,193 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
+ */
+
+/*
+ * 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);
+
+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 == group->overflow_event)
+ 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(group, event);
+}
+
+/*
+ * Try to add an event to the notification queue.
+ * The group can later pull this event off the queue to deal with.
+ * The group can use the @merge hook to merge the event with a queued event.
+ * The group can use the @insert hook to insert the event into hash table.
+ * The function returns:
+ * 0 if the event was added to a 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_insert_event(struct fsnotify_group *group,
+ struct fsnotify_event *event,
+ int (*merge)(struct fsnotify_group *,
+ struct fsnotify_event *),
+ void (*insert)(struct fsnotify_group *,
+ 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(group, event);
+ if (ret) {
+ spin_unlock(&group->notification_lock);
+ return ret;
+ }
+ }
+
+queue:
+ group->q_len++;
+ list_add_tail(&event->list, list);
+ if (insert)
+ insert(group, event);
+ spin_unlock(&group->notification_lock);
+
+ wake_up(&group->notification_waitq);
+ kill_fasync(&group->fsn_fa, SIGIO, POLL_IN);
+ return ret;
+}
+
+void fsnotify_remove_queued_event(struct fsnotify_group *group,
+ struct fsnotify_event *event)
+{
+ assert_spin_locked(&group->notification_lock);
+ /*
+ * 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 the first event on the notification list without removing it.
+ * Returns NULL if the list is empty.
+ */
+struct fsnotify_event *fsnotify_peek_first_event(struct fsnotify_group *group)
+{
+ assert_spin_locked(&group->notification_lock);
+
+ if (fsnotify_notify_queue_is_empty(group))
+ return NULL;
+
+ return list_first_entry(&group->notification_list,
+ struct fsnotify_event, list);
+}
+
+/*
+ * 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 = fsnotify_peek_first_event(group);
+
+ if (!event)
+ return NULL;
+
+ pr_debug("%s: group=%p event=%p\n", __func__, group, event);
+
+ fsnotify_remove_queued_event(group, event);
+
+ return event;
+}
+
+/*
+ * 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);
+}