io_uring/af_unix: defer registered files gc to io_uring release
[ upstream commit 0091bfc81741b8d3aeb3b7ab8636f911b2de6e80 ]
Instead of putting io_uring's registered files in unix_gc() we want it
to be done by io_uring itself. The trick here is to consider io_uring
registered files for cycle detection but not actually putting them down.
Because io_uring can't register other ring instances, this will remove
all refs to the ring file triggering the ->release path and clean up
with io_ring_ctx_free().
Cc: stable@vger.kernel.org
Fixes: 6b06314c47e1 ("io_uring: add file set registration")
Reported-and-tested-by: David Bouman <dbouman03@gmail.com>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com>
[axboe: add kerneldoc comment to skb, fold in skb leak fix]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
BUG=b/254721300
TEST=presubmit
RELEASE_NOTE=Fixed CVE-2022-2602 in the Linux kernel.
cos-patch: security-high
Change-Id: I627aa666fe0f4686202b8a4f4bfec26e131c3134
Reviewed-on: https://cos-review.googlesource.com/c/third_party/kernel/+/37851
Reviewed-by: Oleksandr Tymoshenko <ovt@google.com>
Tested-by: Cusky Presubmit Bot <presubmit@cos-infra-prod.iam.gserviceaccount.com>
Main-Branch-Verified: Cusky Presubmit Bot <presubmit@cos-infra-prod.iam.gserviceaccount.com>
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 501c7e1..e8df634 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -3172,6 +3172,7 @@
}
skb->sk = sk;
+ skb->scm_io_uring = 1;
skb->destructor = io_destruct_skb;
fpl->user = get_uid(ctx->user);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 680f71e..eab3a4d 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -659,6 +659,7 @@
* @wifi_acked: whether frame was acked on wifi or not
* @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS
* @csum_not_inet: use CRC32c to resolve CHECKSUM_PARTIAL
+ * @scm_io_uring: SKB holds io_uring registered files
* @dst_pending_confirm: need to confirm neighbour
* @decrypted: Decrypted SKB
* @napi_id: id of the NAPI struct this skb came from
@@ -824,6 +825,7 @@
#ifdef CONFIG_TLS_DEVICE
__u8 decrypted:1;
#endif
+ __u8 scm_io_uring:1;
#ifdef CONFIG_NET_SCHED
__u16 tc_index; /* traffic control index */
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index d45d536..dc27635 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -204,6 +204,7 @@
/* The external entry point: unix_gc() */
void unix_gc(void)
{
+ struct sk_buff *next_skb, *skb;
struct unix_sock *u;
struct unix_sock *next;
struct sk_buff_head hitlist;
@@ -297,11 +298,30 @@
spin_unlock(&unix_gc_lock);
+ /* We need io_uring to clean its registered files, ignore all io_uring
+ * originated skbs. It's fine as io_uring doesn't keep references to
+ * other io_uring instances and so killing all other files in the cycle
+ * will put all io_uring references forcing it to go through normal
+ * release.path eventually putting registered files.
+ */
+ skb_queue_walk_safe(&hitlist, skb, next_skb) {
+ if (skb->scm_io_uring) {
+ __skb_unlink(skb, &hitlist);
+ skb_queue_tail(&skb->sk->sk_receive_queue, skb);
+ }
+ }
+
/* Here we are. Hitlist is filled. Die. */
__skb_queue_purge(&hitlist);
spin_lock(&unix_gc_lock);
+ /* There could be io_uring registered files, just push them back to
+ * the inflight list
+ */
+ list_for_each_entry_safe(u, next, &gc_candidates, link)
+ list_move_tail(&u->link, &gc_inflight_list);
+
/* All candidates should have been detached by now. */
BUG_ON(!list_empty(&gc_candidates));