Use pid in inotify events.

Hi.

Attached patch puts pid into unused cookie field in inotify events. Cookie from move command were not changed.

Having pid of the event origin is very useful for the notification daemons which have to differentiate 'local' and 'remote' users, i.e. those which have different policies. One of the examples is libionotify (an IO notiication library) and POHMELFS server.

Also fixed several whitespace issues.

1. libionotify
http://www.ioremap.net/projects/libionotify

2. POHMELFS
http://www.ioremap.net/projects/pohmelfs

Signed-off-by Evgeniy Polyakov <[email protected]>

include/linux/fsnotify.h +33 -24

index d4b7c4a..4a10dff 100644
@@ -55,7 +55,7 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir,
 
       if (isdir)
               isdir = IN_ISDIR;
-       inotify_inode_queue_event(old_dir, IN_MOVED_FROM|isdir,cookie,old_name,
+       inotify_inode_queue_event(old_dir, IN_MOVED_FROM|isdir,cookie, old_name,
                                 source);
       inotify_inode_queue_event(new_dir, IN_MOVED_TO|isdir, cookie, new_name,
                                 source);

@@ -79,7 +79,8 @@ static inline void fsnotify_nameremove(struct dentry *dentry, int isdir)
       if (isdir)
               isdir = IN_ISDIR;
       dnotify_parent(dentry, DN_DELETE);
-       inotify_dentry_parent_queue_event(dentry, IN_DELETE|isdir, 0, dentry->d_name.name);
+       inotify_dentry_parent_queue_event(dentry, IN_DELETE|isdir,
+                       task_tgid_vnr(current), dentry->d_name.name);
 }
 
 /*

@@ -87,7 +88,8 @@ static inline void fsnotify_nameremove(struct dentry *dentry, int isdir)
 */
 static inline void fsnotify_inoderemove(struct inode *inode)
 {
-       inotify_inode_queue_event(inode, IN_DELETE_SELF, 0, NULL, NULL);
+       inotify_inode_queue_event(inode, IN_DELETE_SELF,
+                       task_tgid_vnr(current), NULL, NULL);
       inotify_inode_is_dead(inode);
 }
 

@@ -96,7 +98,8 @@ static inline void fsnotify_inoderemove(struct inode *inode)
 */
 static inline void fsnotify_link_count(struct inode *inode)
 {
-       inotify_inode_queue_event(inode, IN_ATTRIB, 0, NULL, NULL);
+       inotify_inode_queue_event(inode, IN_ATTRIB,
+                       task_tgid_vnr(current), NULL, NULL);
 }
 
 /*

@@ -105,8 +108,8 @@ static inline void fsnotify_link_count(struct inode *inode)
 static inline void fsnotify_create(struct inode *inode, struct dentry *dentry)
 {
       inode_dir_notify(inode, DN_CREATE);
-       inotify_inode_queue_event(inode, IN_CREATE, 0, dentry->d_name.name,
-                                 dentry->d_inode);
+       inotify_inode_queue_event(inode, IN_CREATE, task_tgid_vnr(current),
+                       dentry->d_name.name, dentry->d_inode);
       audit_inode_child(dentry->d_name.name, dentry, inode);
 }
 

@@ -118,8 +121,8 @@ static inline void fsnotify_create(struct inode *inode, struct dentry *dentry)
 static inline void fsnotify_link(struct inode *dir, struct inode *inode, struct dentry *new_dentry)
 {
       inode_dir_notify(dir, DN_CREATE);
-       inotify_inode_queue_event(dir, IN_CREATE, 0, new_dentry->d_name.name,
-                                 inode);
+       inotify_inode_queue_event(dir, IN_CREATE, task_tgid_vnr(current),
+                       new_dentry->d_name.name, inode);
       fsnotify_link_count(inode);
       audit_inode_child(new_dentry->d_name.name, new_dentry, dir);
 }

@@ -130,8 +133,8 @@ static inline void fsnotify_link(struct inode *dir, struct inode *inode, struct
 static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry)
 {
       inode_dir_notify(inode, DN_CREATE);
-       inotify_inode_queue_event(inode, IN_CREATE | IN_ISDIR, 0,
-                                 dentry->d_name.name, dentry->d_inode);
+       inotify_inode_queue_event(inode, IN_CREATE | IN_ISDIR,
+               task_tgid_vnr(current), dentry->d_name.name, dentry->d_inode);
       audit_inode_child(dentry->d_name.name, dentry, inode);
 }
 

@@ -147,8 +150,9 @@ static inline void fsnotify_access(struct dentry *dentry)
               mask |= IN_ISDIR;
 
       dnotify_parent(dentry, DN_ACCESS);
-       inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
-       inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
+       inotify_dentry_parent_queue_event(dentry, mask,
+                       task_tgid_vnr(current), dentry->d_name.name);
+       inotify_inode_queue_event(inode, mask, task_tgid_vnr(current), NULL, NULL);
 }
 
 /*

@@ -163,8 +167,9 @@ static inline void fsnotify_modify(struct dentry *dentry)
               mask |= IN_ISDIR;
 
       dnotify_parent(dentry, DN_MODIFY);
-       inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
-       inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
+       inotify_dentry_parent_queue_event(dentry, mask,
+                       task_tgid_vnr(current), dentry->d_name.name);
+       inotify_inode_queue_event(inode, mask, task_tgid_vnr(current), NULL, NULL);
 }
 
 /*

@@ -178,8 +183,10 @@ static inline void fsnotify_open(struct dentry *dentry)
       if (S_ISDIR(inode->i_mode))
               mask |= IN_ISDIR;
 
-       inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
-       inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
+       inotify_dentry_parent_queue_event(dentry, mask,
+               task_tgid_vnr(current), dentry->d_name.name);
+       inotify_inode_queue_event(inode, mask,
+               task_tgid_vnr(current), NULL, NULL);
 }
 
 /*

@@ -196,8 +203,8 @@ static inline void fsnotify_close(struct file *file)
       if (S_ISDIR(inode->i_mode))
               mask |= IN_ISDIR;
 
-       inotify_dentry_parent_queue_event(dentry, mask, 0, name);
-       inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
+       inotify_dentry_parent_queue_event(dentry, mask, task_tgid_vnr(current), name);
+       inotify_inode_queue_event(inode, mask, task_tgid_vnr(current), NULL, NULL);
 }
 
 /*

@@ -211,8 +218,10 @@ static inline void fsnotify_xattr(struct dentry *dentry)
       if (S_ISDIR(inode->i_mode))
               mask |= IN_ISDIR;
 
-       inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
-       inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
+       inotify_dentry_parent_queue_event(dentry, mask,
+                       task_tgid_vnr(current), dentry->d_name.name);
+       inotify_inode_queue_event(inode, mask,
+                       task_tgid_vnr(current), NULL, NULL);
 }
 
 /*

@@ -259,9 +268,10 @@ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid)
       if (in_mask) {
               if (S_ISDIR(inode->i_mode))
                       in_mask |= IN_ISDIR;
-               inotify_inode_queue_event(inode, in_mask, 0, NULL, NULL);
-               inotify_dentry_parent_queue_event(dentry, in_mask, 0,
-                                                 dentry->d_name.name);
+               inotify_inode_queue_event(inode, in_mask,
+                               task_tgid_vnr(current), NULL, NULL);
+               inotify_dentry_parent_queue_event(dentry, in_mask,
+                               task_tgid_vnr(current), dentry->d_name.name);
       }
 }
 
 
 
--
       Evgeniy Polyakov

I've not looked closely at the patch, but a quick question. The ookied field is unused for _most_ events, but is used for rename events. Are you saying that with this patch, that the cookie will be used as before for rename events, but for other events it will be the PID of the triggering process? If so, that seems a bit ugly -- why wouldn't we also be intersted in the PID for rename events?

Hi Michael.

Quoted 6 lines · Michael Kerrisk

I've not looked closely at the patch, but a quick question. The ookied field is unused for _most_ events, but is used for rename events. Are you saying that with this patch, that the cookie will be used as before for rename events, but for other events it will be the PID of the triggering process? If so, that seems a bit ugly -- why wouldn't we also be intersted in the PID for rename events?

Yes, rename events actually consist of at least two: move from and move to, and they carry the same cookie, so that userspace could combine them into single transaction. All others use zero, so I decided to put PID of the caller there. This does not look perfect of course, but we can not change the structure layout, so rename events can not be changed to carry additional PID field.

[CC += "John McCutchan" <ttb-/[email protected]>, who was one of the inotify developers, as I recall]

Hi Evgeniy,

Quoted 10 lines · Evgeniy Polyakov

Hi Michael.

Quoted 6 lines · Michael Kerrisk

I've not looked closely at the patch, but a quick question. The ookied field is unused for _most_ events, but is used for rename events. Are you saying that with this patch, that the cookie will be used as before for rename events, but for other events it will be the PID of the triggering process? If so, that seems a bit ugly -- why wouldn't we also be intersted in the PID for rename events?

Quoted 6 lines

Yes, rename events actually consist of at least two: move from and move to, and they carry the same cookie, so that userspace could combine them into single transaction. All others use zero, so I decided to put PID of the caller there. This does not look perfect of course, but we can not change the structure layout, so rename events can not be changed to carry additional PID field.

It's perhaps unfortunate that the structure wasn't padded out with a few additional fields "for future use". But -- maybe it is not really true that we can't change things. Two things to consider:

a) We now (since 2.6.27) have an inotify_init1() which has a flags argument.
b) There are spare bits in the mask argument of inotify_add_watch()

We could use a flag in either of these to say that we want a different structure returned on read() from the inotify descriptor. In the first case, this would be a global setting for all inotify events on that descriptor. In the second, we could do it on a per-watch basis (I'm not so sure that that is a nice idea). Since we are in any case extending the ABI, and new applications would need to be taught about the extension, it seems we could consider either of the alternative extensions I mentioned, which woul also allow the PID to be obtained for rename() events. What do you think?

Cheers,

Michael

--
Michael Kerrisk
Linux man-pages maintainer; http://www.kernel.org/doc/man-pages/
git://git.kernel.org/pub/scm/docs/man-pages/man-pages.git
man-pages online: http://www.kernel.org/doc/man-pages/online_pages.html
Found a bug? http://www.kernel.org/doc/man-pages/reporting_bugs.html

The reason John & I did not add a pid field -- and we discussed it and really wanted it -- is security. It is an information leak to know what an unrelated process is doing.

Trust me that the rest of the kernel developers are even harder on this subject than I.

I suppose you could fill out the pid field only if the uid's match, but that is extra work for less utility.

It's perhaps unfortunate that the structure wasn't padded out with a few additional fields "for future use". But -- maybe it is not really true that we can't change things. Two things to consider:

a) We now (since 2.6.27) have an inotify_init1() which has a flags argument.
b) There are spare bits in the mask argument of inotify_add_watch()

We could use a flag in either of these to say that we want a different structure returned on read() from the inotify descriptor. In the first case, this would be a global setting for all inotify events on that descriptor. In the second, we could do it on a per-watch basis (I'm not so sure that that is a nice idea). Since we are in any case extending the ABI, and new applications would need to be taught about the extension, it seems we could consider either of the alternative extensions I mentioned, which woul also allow the PID to be obtained for rename() events. What do you think?

Hi Michael.

Quoted 7 lines · Michael Kerrisk

It's perhaps unfortunate that the structure wasn't padded out with a few additional fields "for future use". But -- maybe it is not really true that we can't change things. Two things to consider:

a) We now (since 2.6.27) have an inotify_init1() which has a flags argument.
b) There are spare bits in the mask argument of inotify_add_watch()

Quoted 9 lines

We could use a flag in either of these to say that we want a different structure returned on read() from the inotify descriptor. In the first case, this would be a global setting for all inotify events on that descriptor. In the second, we could do it on a per-watch basis (I'm not so sure that that is a nice idea). Since we are in any case extending the ABI, and new applications would need to be taught about the extension, it seems we could consider either of the alternative extensions I mentioned, which woul also allow the PID to be obtained for rename() events. What do you think?

This may be a good idea for some serious ABI change. I think we could extend it even more to include IO offset/size into events and attribute changes.

Quoted 3 lines

This may be a good idea for some serious ABI change. I think we could extend it even more to include IO offset/size into events and attribute changes.

Are you going to revise your patch to use this idea?