epoll: take epitem list out of struct file

Move the head of epitem list out of struct file; for epoll ones it's
moved into struct eventpoll (->refs there), for non-epoll - into
the new object (struct epitem_head).  In place of ->f_ep_links we
leave a pointer to the list head (->f_ep).

->f_ep is protected by ->f_lock and it's zeroed as soon as the list
of epitems becomes empty (that can happen only in ep_remove() by
now).

The list of files for reverse path check is *not* going through
struct file now - it's a single-linked list going through epitem_head
instances.  It's terminated by ERR_PTR(-1) (== EP_UNACTIVE_POINTER),
so the elements of list can be distinguished by head->next != NULL.

epitem_head instances are allocated at ep_insert() time (by
attach_epitem()) and freed either by ep_remove() (if it empties
the set of epitems *and* epitem_head does not belong to the
reverse path check list) or by clear_tfile_check_list() when
the list is emptied (if the set of epitems is empty by that
point).  Allocations are done from a separate slab - minimal kmalloc()
size is too large on some architectures.

As the result, we trim struct file _and_ get rid of the games with
temporary file references.

Locking and barriers are interesting (aren't they always); see unlist_file()
and ep_remove() for details.  The non-obvious part is that ep_remove() needs
to decide if it will be the one to free the damn thing *before* actually
storing NULL to head->epitems.first - that's what smp_load_acquire is for
in there.  unlist_file() lockless path is safe, since we hit it only if
we observe NULL in head->epitems.first and whoever had done that store is
guaranteed to have observed non-NULL in head->next.  IOW, their last access
had been the store of NULL into ->epitems.first and we can safely free
the sucker.  OTOH, we are under rcu_read_lock() and both epitem and
epitem->file have their freeing RCU-delayed.  So if we see non-NULL
->epitems.first, we can grab ->f_lock (all epitems in there share the
same struct file) and safely recheck the emptiness of ->epitems; again,
->next is still non-NULL, so ep_remove() couldn't have freed head yet.
->f_lock serializes us wrt ep_remove(); the rest is trivial.

Note that once head->epitems becomes NULL, nothing can get inserted into
it - the only remaining reference to head after that point is from the
reverse path check list.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

2 files changed, 3 insertions, 13 deletions

diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h
index 4e215ccfa792..0350393465d4 100644
--- a/include/linux/eventpoll.h
+++ b/include/linux/eventpoll.h
@@ -22,14 +22,6 @@ struct file;
 struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff);
 #endif
 
-/* Used to initialize the epoll bits inside the "struct file" */
-static inline void eventpoll_init_file(struct file *file)
-{
-	INIT_HLIST_HEAD(&file->f_ep_links);
-	INIT_LIST_HEAD(&file->f_tfile_llink);
-}
-
-
 /* Used to release the epoll bits inside the "struct file" */
 void eventpoll_release_file(struct file *file);
 
@@ -50,7 +42,7 @@ static inline void eventpoll_release(struct file *file)
 	 * because the file in on the way to be removed and nobody ( but
 	 * eventpoll ) has still a reference to this file.
 	 */
-	if (likely(hlist_empty(&file->f_ep_links)))
+	if (likely(!file->f_ep))
 		return;
 
 	/*
@@ -72,7 +64,6 @@ static inline int ep_op_has_event(int op)
 
 #else
 
-static inline void eventpoll_init_file(struct file *file) {}
 static inline void eventpoll_release(struct file *file) {}
 
 #endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b484ba0e474a..993c540e3b77 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -923,7 +923,7 @@ struct file {
 	const struct file_operations	*f_op;
 
 	/*
-	 * Protects f_ep_links, f_flags.
+	 * Protects f_ep, f_flags.
 	 * Must not be taken from IRQ context.
 	 */
 	spinlock_t		f_lock;
@@ -946,8 +946,7 @@ struct file {
 
 #ifdef CONFIG_EPOLL
 	/* Used by fs/eventpoll.c to link all the hooks to this file */
-	struct hlist_head	f_ep_links;
-	struct list_head	f_tfile_llink;
+	struct hlist_head	*f_ep;
 #endif /* #ifdef CONFIG_EPOLL */
 	struct address_space	*f_mapping;
 	errseq_t		f_wb_err;