[Devel] [PATCH vz9 3/3] eventpoll: fix ep_remove struct eventpoll / struct file UAF

[Eva Kurchatova]

[ Upstream commit a6dc643c69311677c574a0f17a3f4d66a5f3744b ]

ep_remove() (via ep_remove_file()) cleared file->f_ep under
file->f_lock but then kept using @file inside the critical section
(is_file_epoll(), hlist_del_rcu() through the head, spin_unlock).
A concurrent __fput() taking the eventpoll_release() fastpath in
that window observed the transient NULL, skipped
eventpoll_release_file() and ran to f_op->release / file_free().

For the epoll-watches-epoll case, f_op->release is
ep_eventpoll_release() -> ep_clear_and_put() -> ep_free(), which
kfree()s the watched struct eventpoll. Its embedded ->refs
hlist_head is exactly where epi->fllink.pprev points, so the
subsequent hlist_del_rcu()'s "*pprev = next" scribbles into freed
kmalloc-192 memory.

In addition, struct file is SLAB_TYPESAFE_BY_RCU, so the slot
backing @file could be recycled by alloc_empty_file() --
reinitializing f_lock and f_ep -- while ep_remove() is still
nominally inside that lock. The upshot is an attacker-controllable
kmem_cache_free() against the wrong slab cache.

Pin @file via epi_fget() at the top of ep_remove() and gate the
critical section on the pin succeeding. With the pin held @file
cannot reach refcount zero, which holds __fput() off and
transitively keeps the watched struct eventpoll alive across the
hlist_del_rcu() and the f_lock use, closing both UAFs.

If the pin fails @file has already reached refcount zero and its
__fput() is in flight. Because we bailed before clearing f_ep,
that path takes the eventpoll_release() slow path into
eventpoll_release_file() and blocks on ep->mtx until the waiter
side's ep_clear_and_put() drops it. The bailed epi's share of
ep->refcount stays intact, so the trailing ep_refcount_dec_and_test()
in ep_clear_and_put() cannot free the eventpoll out from under
eventpoll_release_file(); the orphaned epi is then cleaned up
there.

A successful pin also proves we are not racing
eventpoll_release_file() on this epi, so drop the now-redundant
re-check of epi->dying under f_lock. The cheap lockless
READ_ONCE(epi->dying) fast-path bailout stays.

Fixes: 58c9b016e128 ("epoll: use refcount to reduce ep_mutex contention")
Reported-by: Jaeyoung Chung <jjy600901 at snu.ac.kr>
Link: https://patch.msgid.link/20260423-work-epoll-uaf-v1-6-2470f9eec0f5@kernel.org
Signed-off-by: Christian Brauner (Amutable) <brauner at kernel.org>
Signed-off-by: Quentin Schulz <quentin.schulz at cherry.de>
Signed-off-by: Sasha Levin <sashal at kernel.org>
(cherry picked from commit 9324de74a3a59b9fde9b62ee45ebaa71458ba2e5)

Signed-off-by: Eva Kurchatova <eva.kurchatova at virtuozzo.com>

https://virtuozzo.atlassian.net/browse/VSTOR-137490
Feature: fix epoll cve
---
 fs/eventpoll.c | 36 +++++++++++++++++++++++++++++-------
 1 file changed, 29 insertions(+), 7 deletions(-)

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 7ac22aadaf8b..c937325c614b 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -715,6 +715,8 @@ static void ep_free(struct eventpoll *ep)
 	kfree_rcu(ep, rcu);
 }
 
+static struct file *epi_fget(const struct epitem *epi);
+
 /*
  * Removes a "struct epitem" from the eventpoll RB tree and deallocates
  * all the associated resources. Must be called with "mtx" held.
@@ -725,7 +727,7 @@ static void ep_free(struct eventpoll *ep)
  */
 static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force)
 {
-	struct file *file = epi->ffd.file;
+	struct file *file = NULL;
 	struct epitems_head *to_free;
 	struct hlist_head *head;
 
@@ -736,13 +738,29 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force)
 	 */
 	ep_unregister_pollwait(ep, epi);
 
-	/* Remove the current item from the list of epoll hooks */
-	spin_lock(&file->f_lock);
-	if (epi->dying && !force) {
-		spin_unlock(&file->f_lock);
-		return false;
+	if (!force) {
+		/* cheap sync with eventpoll_release_file() */
+		if (unlikely(READ_ONCE(epi->dying)))
+			return false;
+
+		/*
+		 * If we manage to grab a reference it means we're not in
+		 * eventpoll_release_file() and aren't going to be.
+		 */
+		file = epi_fget(epi);
+		if (!file)
+			return false;
+	} else {
+		/*
+		 * For force (eventpoll_release_file()), the caller already owns
+		 * the file and set epi->dying; the file is safe to access
+		 * directly but its refcount is zero so epi_fget() would fail.
+		 */
+		file = epi->ffd.file;
 	}
 
+	/* Remove the current item from the list of epoll hooks */
+	spin_lock(&file->f_lock);
 	to_free = NULL;
 	head = file->f_ep;
 	if (head->first == &epi->fllink && !epi->fllink.next) {
@@ -776,6 +794,10 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force)
 	call_rcu(&epi->rcu, epi_rcu_free);
 
 	percpu_counter_dec(&ep->user->epoll_watches);
+	if (!force) {
+		/* Put down the pinned file reference */
+		fput(file);
+	}
 	return true;
 }
 
@@ -993,7 +1015,7 @@ void eventpoll_release_file(struct file *file)
 	spin_lock(&file->f_lock);
 	if (file->f_ep && file->f_ep->first) {
 		epi = hlist_entry(file->f_ep->first, struct epitem, fllink);
-		epi->dying = true;
+		WRITE_ONCE(epi->dying, true);
 		spin_unlock(&file->f_lock);
 
 		/*
-- 
2.55.0