From 01573e231f18eb2d99162747186f59511f56b64d Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Fri, 08 Dec 2023 10:40:48 +0000
Subject: [PATCH] 移去rt
---
kernel/fs/notify/fanotify/fanotify_user.c | 798 ++++++++++++++++++++++++++++++++++++++++++--------------
1 files changed, 591 insertions(+), 207 deletions(-)
diff --git a/kernel/fs/notify/fanotify/fanotify_user.c b/kernel/fs/notify/fanotify/fanotify_user.c
index 06c5729..18e014f 100644
--- a/kernel/fs/notify/fanotify/fanotify_user.c
+++ b/kernel/fs/notify/fanotify/fanotify_user.c
@@ -17,6 +17,8 @@
#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>
@@ -44,42 +46,90 @@
extern const struct fsnotify_ops fanotify_fsnotify_ops;
struct kmem_cache *fanotify_mark_cache __read_mostly;
-struct kmem_cache *fanotify_event_cachep __read_mostly;
+struct kmem_cache *fanotify_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_INFO_HDR_LEN \
+ (sizeof(struct fanotify_event_info_fid) + sizeof(struct file_handle))
+
+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_INFO_HDR_LEN + info_len, FANOTIFY_EVENT_ALIGN);
+}
+
+static int fanotify_event_info_len(unsigned int fid_mode,
+ struct fanotify_event *event)
+{
+ struct fanotify_info *info = fanotify_event_info(event);
+ int dir_fh_len = fanotify_event_dir_fh_len(event);
+ int fh_len = fanotify_event_object_fh_len(event);
+ int info_len = 0;
+ int dot_len = 0;
+
+ if (dir_fh_len) {
+ info_len += fanotify_fid_info_len(dir_fh_len, info->name_len);
+ } else if ((fid_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 (fh_len)
+ info_len += fanotify_fid_info_len(fh_len, dot_len);
+
+ return info_len;
+}
+
/*
- * Get an fsnotify notification event if one exists and is small
+ * 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.
- *
- * Called with the group->notification_lock held.
+ * is not large enough. When permission event is dequeued, its state is
+ * updated accordingly.
*/
-static struct fsnotify_event *get_one_event(struct fsnotify_group *group,
+static struct fanotify_event *get_one_event(struct fsnotify_group *group,
size_t count)
{
- assert_spin_locked(&group->notification_lock);
+ size_t event_size = FAN_EVENT_METADATA_LEN;
+ struct fanotify_event *event = NULL;
+ unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
pr_debug("%s: group=%p count=%zd\n", __func__, group, count);
+ spin_lock(&group->notification_lock);
if (fsnotify_notify_queue_is_empty(group))
- return NULL;
+ goto out;
- if (FAN_EVENT_METADATA_LEN > count)
- return ERR_PTR(-EINVAL);
+ if (fid_mode) {
+ event_size += fanotify_event_info_len(fid_mode,
+ FANOTIFY_E(fsnotify_peek_first_event(group)));
+ }
- /* held the notification_lock the whole time, so this is the
- * same event we peeked above */
- return fsnotify_remove_first_event(group);
+ if (event_size > count) {
+ event = ERR_PTR(-EINVAL);
+ goto out;
+ }
+ event = FANOTIFY_E(fsnotify_remove_first_event(group));
+ if (fanotify_is_perm_event(event->mask))
+ FANOTIFY_PERM(event)->state = FAN_EVENT_REPORTED;
+out:
+ spin_unlock(&group->notification_lock);
+ return event;
}
-static int create_fd(struct fsnotify_group *group,
- struct fanotify_event_info *event,
+static int create_fd(struct fsnotify_group *group, struct path *path,
struct file **file)
{
int client_fd;
struct file *new_file;
-
- pr_debug("%s: group=%p event=%p\n", __func__, group, event);
client_fd = get_unused_fd_flags(group->fanotify_data.f_flags);
if (client_fd < 0)
@@ -89,14 +139,9 @@
* we need a new file handle for the userspace program so it can read even if it was
* originally opened O_WRONLY.
*/
- /* it's possible this event was an overflow event. in that case dentry and mnt
- * are NULL; That's fine, just don't call dentry open */
- if (event->path.dentry && event->path.mnt)
- new_file = dentry_open(&event->path,
- group->fanotify_data.f_flags | FMODE_NONOTIFY,
- current_cred());
- else
- new_file = ERR_PTR(-EOVERFLOW);
+ 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
@@ -114,62 +159,32 @@
return client_fd;
}
-static int fill_event_metadata(struct fsnotify_group *group,
- struct fanotify_event_metadata *metadata,
- struct fsnotify_event *fsn_event,
- struct file **file)
+/*
+ * 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)
{
- int ret = 0;
- struct fanotify_event_info *event;
+ bool destroy = false;
- pr_debug("%s: group=%p metadata=%p event=%p\n", __func__,
- group, metadata, fsn_event);
-
- *file = NULL;
- event = container_of(fsn_event, struct fanotify_event_info, fse);
- metadata->event_len = FAN_EVENT_METADATA_LEN;
- metadata->metadata_len = FAN_EVENT_METADATA_LEN;
- metadata->vers = FANOTIFY_METADATA_VERSION;
- metadata->reserved = 0;
- metadata->mask = fsn_event->mask & FAN_ALL_OUTGOING_EVENTS;
- metadata->pid = pid_vnr(event->tgid);
- if (unlikely(fsn_event->mask & FAN_Q_OVERFLOW))
- metadata->fd = FAN_NOFD;
- else {
- metadata->fd = create_fd(group, event, file);
- if (metadata->fd < 0)
- ret = metadata->fd;
- }
-
- return ret;
-}
-
-static struct fanotify_perm_event_info *dequeue_event(
- struct fsnotify_group *group, int fd)
-{
- struct fanotify_perm_event_info *event, *return_e = NULL;
-
- spin_lock(&group->notification_lock);
- list_for_each_entry(event, &group->fanotify_data.access_list,
- fae.fse.list) {
- if (event->fd != fd)
- continue;
-
- list_del_init(&event->fae.fse.list);
- return_e = event;
- break;
- }
+ 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);
-
- pr_debug("%s: found return_re=%p\n", __func__, return_e);
-
- return return_e;
+ 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_info *event;
+ struct fanotify_perm_event *event;
int fd = response_struct->fd;
int response = response_struct->response;
@@ -191,45 +206,233 @@
if (fd < 0)
return -EINVAL;
- if ((response & FAN_AUDIT) && !group->fanotify_data.audit)
+ if ((response & FAN_AUDIT) && !FAN_GROUP_FLAG(group, FAN_ENABLE_AUDIT))
return -EINVAL;
- event = dequeue_event(group, fd);
- if (!event)
- return -ENOENT;
+ spin_lock(&group->notification_lock);
+ list_for_each_entry(event, &group->fanotify_data.access_list,
+ fae.fse.list) {
+ if (event->fd != fd)
+ continue;
- event->response = response;
- wake_up(&group->fanotify_data.access_waitq);
+ 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 0;
+ return -ENOENT;
+}
+
+static int copy_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 (!fh_len)
+ return 0;
+
+ 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:
+ 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;
+ 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 ssize_t copy_event_to_user(struct fsnotify_group *group,
- struct fsnotify_event *event,
- char __user *buf)
+ struct fanotify_event *event,
+ char __user *buf, size_t count)
{
- struct fanotify_event_metadata fanotify_event_metadata;
- struct file *f;
- int fd, ret;
+ struct fanotify_event_metadata metadata;
+ struct path *path = fanotify_event_path(event);
+ struct fanotify_info *info = fanotify_event_info(event);
+ unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
+ struct file *f = NULL;
+ int ret, fd = FAN_NOFD;
+ int info_type = 0;
pr_debug("%s: group=%p event=%p\n", __func__, group, event);
- ret = fill_event_metadata(group, &fanotify_event_metadata, event, &f);
- if (ret < 0)
- return ret;
+ metadata.event_len = FAN_EVENT_METADATA_LEN +
+ fanotify_event_info_len(fid_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);
- fd = fanotify_event_metadata.fd;
+ if (path && path->mnt && path->dentry) {
+ fd = create_fd(group, path, &f);
+ if (fd < 0)
+ return fd;
+ }
+ metadata.fd = fd;
+
ret = -EFAULT;
- if (copy_to_user(buf, &fanotify_event_metadata,
- fanotify_event_metadata.event_len))
+ /*
+ * 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 (fanotify_is_perm_event(event->mask))
- FANOTIFY_PE(event)->fd = fd;
+ if (copy_to_user(buf, &metadata, FAN_EVENT_METADATA_LEN))
+ goto out_close_fd;
- if (fd != FAN_NOFD)
+ buf += FAN_EVENT_METADATA_LEN;
+ count -= FAN_EVENT_METADATA_LEN;
+
+ if (fanotify_is_perm_event(event->mask))
+ FANOTIFY_PERM(event)->fd = fd;
+
+ /* Event info records order is: dir fid + name, child fid */
+ if (fanotify_event_dir_fh_len(event)) {
+ info_type = info->name_len ? FAN_EVENT_INFO_TYPE_DFID_NAME :
+ FAN_EVENT_INFO_TYPE_DFID;
+ ret = copy_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)
+ goto out_close_fd;
+
+ buf += ret;
+ count -= ret;
+ }
+
+ if (fanotify_event_object_fh_len(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_info_to_user(fanotify_event_fsid(event),
+ fanotify_event_object_fh(event),
+ info_type, dot, dot_len, buf, count);
+ if (ret < 0)
+ goto out_close_fd;
+
+ buf += ret;
+ count -= ret;
+ }
+
+ if (f)
fd_install(fd, f);
- return fanotify_event_metadata.event_len;
+
+ return metadata.event_len;
out_close_fd:
if (fd != FAN_NOFD) {
@@ -258,7 +461,7 @@
size_t count, loff_t *pos)
{
struct fsnotify_group *group;
- struct fsnotify_event *kevent;
+ struct fanotify_event *event;
char __user *start;
int ret;
DEFINE_WAIT_FUNC(wait, woken_wake_function);
@@ -270,16 +473,18 @@
add_wait_queue(&group->notification_waitq, &wait);
while (1) {
- spin_lock(&group->notification_lock);
- kevent = get_one_event(group, count);
- spin_unlock(&group->notification_lock);
-
- if (IS_ERR(kevent)) {
- ret = PTR_ERR(kevent);
+ /*
+ * 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 (!kevent) {
+ if (!event) {
ret = -EAGAIN;
if (file->f_flags & O_NONBLOCK)
break;
@@ -295,7 +500,7 @@
continue;
}
- ret = copy_event_to_user(group, kevent, buf);
+ ret = copy_event_to_user(group, event, buf, count);
if (unlikely(ret == -EOPENSTALE)) {
/*
* We cannot report events with stale fd so drop it.
@@ -310,15 +515,17 @@
* Permission events get queued to wait for response. Other
* events can be destroyed now.
*/
- if (!fanotify_is_perm_event(kevent->mask)) {
- fsnotify_destroy_event(group, kevent);
+ if (!fanotify_is_perm_event(event->mask)) {
+ fsnotify_destroy_event(group, &event->fse);
} else {
if (ret <= 0) {
- FANOTIFY_PE(kevent)->response = FAN_DENY;
+ 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(&kevent->list,
+ list_add_tail(&event->fse.list,
&group->fanotify_data.access_list);
spin_unlock(&group->notification_lock);
}
@@ -346,8 +553,10 @@
group = file->private_data;
- if (count > sizeof(response))
- count = sizeof(response);
+ if (count < sizeof(response))
+ return -EINVAL;
+
+ count = sizeof(response);
pr_debug("%s: group=%p count=%zu\n", __func__, group, count);
@@ -364,8 +573,6 @@
static int fanotify_release(struct inode *ignored, struct file *file)
{
struct fsnotify_group *group = file->private_data;
- struct fanotify_perm_event_info *event, *next;
- struct fsnotify_event *fsn_event;
/*
* Stop new events from arriving in the notification queue. since
@@ -379,13 +586,14 @@
* and simulate reply from userspace.
*/
spin_lock(&group->notification_lock);
- list_for_each_entry_safe(event, next, &group->fanotify_data.access_list,
- fae.fse.list) {
- pr_debug("%s: found group=%p event=%p\n", __func__, group,
- event);
+ 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);
- event->response = FAN_ALLOW;
+ finish_permission_event(group, event, FAN_ALLOW);
+ spin_lock(&group->notification_lock);
}
/*
@@ -394,14 +602,17 @@
* response is consumed and fanotify_get_response() returns.
*/
while (!fsnotify_notify_queue_is_empty(group)) {
- fsn_event = fsnotify_remove_first_event(group);
- if (!(fsn_event->mask & FAN_ALL_PERM_EVENTS)) {
+ struct fanotify_event *event;
+
+ event = FANOTIFY_E(fsnotify_remove_first_event(group));
+ if (!(event->mask & FANOTIFY_PERM_EVENTS)) {
spin_unlock(&group->notification_lock);
- fsnotify_destroy_event(group, fsn_event);
- spin_lock(&group->notification_lock);
+ fsnotify_destroy_event(group, &event->fse);
} else {
- FANOTIFY_PE(fsn_event)->response = FAN_ALLOW;
+ finish_permission_event(group, FANOTIFY_PERM(event),
+ FAN_ALLOW);
}
+ spin_lock(&group->notification_lock);
}
spin_unlock(&group->notification_lock);
@@ -447,12 +658,13 @@
.fasync = NULL,
.release = fanotify_release,
.unlocked_ioctl = fanotify_ioctl,
- .compat_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)
+ struct path *path, unsigned int flags, __u64 mask,
+ unsigned int obj_type)
{
int ret;
@@ -490,36 +702,42 @@
}
/* you can only watch an inode if you have read permissions on it */
- ret = inode_permission2(path->mnt, path->dentry->d_inode, MAY_READ);
+ ret = inode_permission(path->dentry->d_inode, 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,
- int *destroy)
+ __u32 mask, unsigned int flags,
+ __u32 umask, int *destroy)
{
__u32 oldmask = 0;
+ /* umask bits cannot be removed by user */
+ mask &= ~umask;
spin_lock(&fsn_mark->lock);
if (!(flags & FAN_MARK_IGNORED_MASK)) {
- __u32 tmask = fsn_mark->mask & ~mask;
-
- if (flags & FAN_MARK_ONDIR)
- tmask &= ~FAN_ONDIR;
-
oldmask = fsn_mark->mask;
- fsn_mark->mask = tmask;
+ fsn_mark->mask &= ~mask;
} else {
- __u32 tmask = fsn_mark->ignored_mask & ~mask;
- if (flags & FAN_MARK_ONDIR)
- tmask &= ~FAN_ONDIR;
- fsn_mark->ignored_mask = tmask;
+ fsn_mark->ignored_mask &= ~mask;
}
- *destroy = !(fsn_mark->mask | fsn_mark->ignored_mask);
+ /*
+ * 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->ignored_mask) & ~umask);
spin_unlock(&fsn_mark->lock);
return mask & oldmask;
@@ -527,7 +745,7 @@
static int fanotify_remove_mark(struct fsnotify_group *group,
fsnotify_connp_t *connp, __u32 mask,
- unsigned int flags)
+ unsigned int flags, __u32 umask)
{
struct fsnotify_mark *fsn_mark = NULL;
__u32 removed;
@@ -541,7 +759,7 @@
}
removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags,
- &destroy_mark);
+ umask, &destroy_mark);
if (removed & fsnotify_conn_mask(fsn_mark->connector))
fsnotify_recalc_mask(fsn_mark->connector);
if (destroy_mark)
@@ -557,18 +775,26 @@
static int fanotify_remove_vfsmount_mark(struct fsnotify_group *group,
struct vfsmount *mnt, __u32 mask,
- unsigned int flags)
+ unsigned int flags, __u32 umask)
{
return fanotify_remove_mark(group, &real_mount(mnt)->mnt_fsnotify_marks,
- mask, flags);
+ 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)
+ unsigned int flags, __u32 umask)
{
return fanotify_remove_mark(group, &inode->i_fsnotify_marks, mask,
- flags);
+ flags, umask);
}
static __u32 fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark,
@@ -579,19 +805,10 @@
spin_lock(&fsn_mark->lock);
if (!(flags & FAN_MARK_IGNORED_MASK)) {
- __u32 tmask = fsn_mark->mask | mask;
-
- if (flags & FAN_MARK_ONDIR)
- tmask |= FAN_ONDIR;
-
oldmask = fsn_mark->mask;
- fsn_mark->mask = tmask;
+ fsn_mark->mask |= mask;
} else {
- __u32 tmask = fsn_mark->ignored_mask | mask;
- if (flags & FAN_MARK_ONDIR)
- tmask |= FAN_ONDIR;
-
- fsn_mark->ignored_mask = tmask;
+ fsn_mark->ignored_mask |= mask;
if (flags & FAN_MARK_IGNORED_SURV_MODIFY)
fsn_mark->flags |= FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY;
}
@@ -602,7 +819,8 @@
static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group,
fsnotify_connp_t *connp,
- unsigned int type)
+ unsigned int type,
+ __kernel_fsid_t *fsid)
{
struct fsnotify_mark *mark;
int ret;
@@ -615,7 +833,7 @@
return ERR_PTR(-ENOMEM);
fsnotify_init_mark(mark, group);
- ret = fsnotify_add_mark_locked(mark, connp, type, 0);
+ ret = fsnotify_add_mark_locked(mark, connp, type, 0, fsid);
if (ret) {
fsnotify_put_mark(mark);
return ERR_PTR(ret);
@@ -627,7 +845,8 @@
static int fanotify_add_mark(struct fsnotify_group *group,
fsnotify_connp_t *connp, unsigned int type,
- __u32 mask, unsigned int flags)
+ __u32 mask, unsigned int flags,
+ __kernel_fsid_t *fsid)
{
struct fsnotify_mark *fsn_mark;
__u32 added;
@@ -635,7 +854,7 @@
mutex_lock(&group->mark_mutex);
fsn_mark = fsnotify_find_mark(connp, group);
if (!fsn_mark) {
- fsn_mark = fanotify_add_new_mark(group, connp, type);
+ fsn_mark = fanotify_add_new_mark(group, connp, type, fsid);
if (IS_ERR(fsn_mark)) {
mutex_unlock(&group->mark_mutex);
return PTR_ERR(fsn_mark);
@@ -652,15 +871,23 @@
static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
struct vfsmount *mnt, __u32 mask,
- unsigned int flags)
+ unsigned int flags, __kernel_fsid_t *fsid)
{
return fanotify_add_mark(group, &real_mount(mnt)->mnt_fsnotify_marks,
- FSNOTIFY_OBJ_TYPE_VFSMOUNT, mask, flags);
+ 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)
+ unsigned int flags, __kernel_fsid_t *fsid)
{
pr_debug("%s: group=%p inode=%p\n", __func__, group, inode);
@@ -671,11 +898,25 @@
*/
if ((flags & FAN_MARK_IGNORED_MASK) &&
!(flags & FAN_MARK_IGNORED_SURV_MODIFY) &&
- (atomic_read(&inode->i_writecount) > 0))
+ inode_is_open_for_write(inode))
return 0;
return fanotify_add_mark(group, &inode->i_fsnotify_marks,
- FSNOTIFY_OBJ_TYPE_INODE, mask, flags);
+ 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;
}
/* fanotify syscalls */
@@ -684,18 +925,19 @@
struct fsnotify_group *group;
int f_flags, fd;
struct user_struct *user;
- struct fanotify_event_info *oevent;
+ unsigned int fid_mode = flags & FANOTIFY_FID_BITS;
+ unsigned int class = flags & FANOTIFY_CLASS_BITS;
- pr_debug("%s: flags=%d event_f_flags=%d\n",
- __func__, flags, event_f_flags);
+ pr_debug("%s: flags=%x event_f_flags=%x\n",
+ __func__, flags, event_f_flags);
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
#ifdef CONFIG_AUDITSYSCALL
- if (flags & ~(FAN_ALL_INIT_FLAGS | FAN_ENABLE_AUDIT))
+ if (flags & ~(FANOTIFY_INIT_FLAGS | FAN_ENABLE_AUDIT))
#else
- if (flags & ~FAN_ALL_INIT_FLAGS)
+ if (flags & ~FANOTIFY_INIT_FLAGS)
#endif
return -EINVAL;
@@ -710,6 +952,16 @@
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;
user = get_current_user();
if (atomic_read(&user->fanotify_listeners) > FANOTIFY_DEFAULT_MAX_LISTENERS) {
@@ -731,22 +983,22 @@
}
group->fanotify_data.user = user;
+ group->fanotify_data.flags = flags;
atomic_inc(&user->fanotify_listeners);
group->memcg = get_mem_cgroup_from_mm(current->mm);
- oevent = fanotify_alloc_event(group, NULL, FS_Q_OVERFLOW, NULL);
- if (unlikely(!oevent)) {
+ group->overflow_event = fanotify_alloc_overflow_event();
+ if (unlikely(!group->overflow_event)) {
fd = -ENOMEM;
goto out_destroy_group;
}
- group->overflow_event = &oevent->fse;
if (force_o_largefile())
event_f_flags |= O_LARGEFILE;
group->fanotify_data.f_flags = event_f_flags;
init_waitqueue_head(&group->fanotify_data.access_waitq);
INIT_LIST_HEAD(&group->fanotify_data.access_list);
- switch (flags & FAN_ALL_CLASS_BITS) {
+ switch (class) {
case FAN_CLASS_NOTIF:
group->priority = FS_PRIO_0;
break;
@@ -783,7 +1035,6 @@
fd = -EPERM;
if (!capable(CAP_AUDIT_WRITE))
goto out_destroy_group;
- group->fanotify_data.audit = true;
}
fd = anon_inode_getfd("[fanotify]", &fanotify_fops, group, f_flags);
@@ -797,6 +1048,64 @@
return fd;
}
+/* Check if filesystem can encode a unique fid */
+static int fanotify_test_fid(struct path *path, __kernel_fsid_t *fsid)
+{
+ __kernel_fsid_t root_fsid;
+ int err;
+
+ /*
+ * Make sure path is not in filesystem with zero fsid (e.g. tmpfs).
+ */
+ err = vfs_get_fsid(path->dentry, fsid);
+ if (err)
+ return err;
+
+ if (!fsid->val[0] && !fsid->val[1])
+ return -ENODEV;
+
+ /*
+ * Make sure path is not inside a filesystem subvolume (e.g. btrfs)
+ * which uses a different fsid than sb root.
+ */
+ err = vfs_get_fsid(path->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;
+
+ /*
+ * 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 (!path->dentry->d_sb->s_export_op ||
+ !path->dentry->d_sb->s_export_op->fh_to_dentry)
+ return -EOPNOTSUPP;
+
+ return 0;
+}
+
+static int fanotify_events_supported(struct path *path, __u64 mask)
+{
+ /*
+ * 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;
+ return 0;
+}
+
static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
int dfd, const char __user *pathname)
{
@@ -805,7 +1114,12 @@
struct fsnotify_group *group;
struct fd f;
struct path path;
- u32 valid_mask = FAN_ALL_EVENTS | FAN_EVENT_ON_CHILD;
+ __kernel_fsid_t __fsid, *fsid = NULL;
+ u32 valid_mask = FANOTIFY_EVENTS | FANOTIFY_EVENT_FLAGS;
+ unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS;
+ bool ignored = flags & FAN_MARK_IGNORED_MASK;
+ 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",
@@ -815,32 +1129,46 @@
if (mask & ((__u64)0xffffffff << 32))
return -EINVAL;
- if (flags & ~FAN_ALL_MARK_FLAGS)
+ 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 (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE | FAN_MARK_FLUSH)) {
- case FAN_MARK_ADD: /* fallthrough */
+ case FAN_MARK_ADD:
case FAN_MARK_REMOVE:
if (!mask)
return -EINVAL;
break;
case FAN_MARK_FLUSH:
- if (flags & ~(FAN_MARK_MOUNT | FAN_MARK_FLUSH))
+ if (flags & ~(FANOTIFY_MARK_TYPE_BITS | FAN_MARK_FLUSH))
return -EINVAL;
break;
default:
return -EINVAL;
}
- if (mask & FAN_ONDIR) {
- flags |= FAN_MARK_ONDIR;
- mask &= ~FAN_ONDIR;
- }
-
if (IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS))
- valid_mask |= FAN_ALL_PERM_EVENTS;
+ valid_mask |= FANOTIFY_PERM_EVENTS;
if (mask & ~valid_mask)
return -EINVAL;
+
+ /* Event flags (ONDIR, ON_CHILD) are meaningless in ignored mask */
+ if (ignored)
+ mask &= ~FANOTIFY_EVENT_FLAGS;
f = fdget(fanotify_fd);
if (unlikely(!f.file))
@@ -857,73 +1185,123 @@
* allowed to set permissions events.
*/
ret = -EINVAL;
- if (mask & FAN_ALL_PERM_EVENTS &&
+ if (mask & FANOTIFY_PERM_EVENTS &&
group->priority == FS_PRIO_0)
+ goto fput_and_out;
+
+ /*
+ * Events with data type inode do not carry enough information to report
+ * event->fd, so we do not allow setting a mask for inode events unless
+ * group supports reporting fid.
+ * inode 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_INODE_EVENTS &&
+ (!fid_mode || mark_type == FAN_MARK_MOUNT))
goto fput_and_out;
if (flags & FAN_MARK_FLUSH) {
ret = 0;
- if (flags & FAN_MARK_MOUNT)
+ 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);
+ ret = fanotify_find_path(dfd, pathname, &path, flags,
+ (mask & ALL_FSNOTIFY_EVENTS), obj_type);
if (ret)
goto fput_and_out;
+ if (flags & FAN_MARK_ADD) {
+ ret = fanotify_events_supported(&path, mask);
+ if (ret)
+ goto path_put_and_out;
+ }
+
+ if (fid_mode) {
+ ret = fanotify_test_fid(&path, &__fsid);
+ if (ret)
+ goto path_put_and_out;
+
+ fsid = &__fsid;
+ }
+
/* inode held in place by reference to path; group by fget on fd */
- if (!(flags & FAN_MARK_MOUNT))
+ if (mark_type == FAN_MARK_INODE)
inode = path.dentry->d_inode;
else
mnt = path.mnt;
+ /* 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) && !ignored)
+ mask |= FAN_EVENT_ON_CHILD;
+ }
+
/* create/update an inode mark */
switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE)) {
case FAN_MARK_ADD:
- if (flags & FAN_MARK_MOUNT)
- ret = fanotify_add_vfsmount_mark(group, mnt, mask, flags);
+ 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);
+ ret = fanotify_add_inode_mark(group, inode, mask,
+ flags, fsid);
break;
case FAN_MARK_REMOVE:
- if (flags & FAN_MARK_MOUNT)
- ret = fanotify_remove_vfsmount_mark(group, mnt, mask, flags);
+ 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);
+ 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
-#ifdef CONFIG_COMPAT
-COMPAT_SYSCALL_DEFINE6(fanotify_mark,
+#if defined(CONFIG_ARCH_SPLIT_ARG64) || defined(CONFIG_COMPAT)
+SYSCALL32_DEFINE6(fanotify_mark,
int, fanotify_fd, unsigned int, flags,
- __u32, mask0, __u32, mask1, int, dfd,
+ SC_ARG64(mask), int, dfd,
const char __user *, pathname)
{
- return do_fanotify_mark(fanotify_fd, flags,
-#ifdef __BIG_ENDIAN
- ((__u64)mask0 << 32) | mask1,
-#else
- ((__u64)mask1 << 32) | mask0,
-#endif
- dfd, pathname);
+ return do_fanotify_mark(fanotify_fd, flags, SC_VAL64(__u64, mask),
+ dfd, pathname);
}
#endif
@@ -934,12 +1312,18 @@
*/
static int __init fanotify_user_setup(void)
{
+ BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 10);
+ BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 9);
+
fanotify_mark_cache = KMEM_CACHE(fsnotify_mark,
SLAB_PANIC|SLAB_ACCOUNT);
- fanotify_event_cachep = KMEM_CACHE(fanotify_event_info, SLAB_PANIC);
+ 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_info, SLAB_PANIC);
+ KMEM_CACHE(fanotify_perm_event, SLAB_PANIC);
}
return 0;
--
Gitblit v1.6.2