af_unix: Refine wait_for_unix_gc().

unix_tot_inflight is a poor metric, only telling the number of
inflight AF_UNXI sockets, and we should use unix_graph_state instead.

Also, if the receiver is catching up with the passed fds, the
sender does not need to schedule GC.

GC only helps unreferenced cyclic SCM_RIGHTS references, and in
such a situation, the malicious sendmsg() will continue to call
wait_for_unix_gc() and hit the UNIX_INFLIGHT_SANE_USER condition.

Let's make only malicious users schedule GC and wait for it to
finish if a cyclic reference exists during the previous GC run.

Then, sane users will pay almost no cost for wait_for_unix_gc().

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20251115020935.2643121-6-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This commit is contained in:
Kuniyuki Iwashima
2025-11-15 02:08:36 +00:00
committed by Jakub Kicinski
parent 384900542d
commit e29c7a4cec
+8 -13
View File
@@ -543,7 +543,7 @@ static void unix_walk_scc(struct sk_buff_head *hitlist)
list_replace_init(&unix_visited_vertices, &unix_unvisited_vertices);
swap(unix_vertex_unvisited_index, unix_vertex_grouped_index);
unix_graph_cyclic_sccs = cyclic_sccs;
WRITE_ONCE(unix_graph_cyclic_sccs, cyclic_sccs);
WRITE_ONCE(unix_graph_state,
cyclic_sccs ? UNIX_GRAPH_CYCLIC : UNIX_GRAPH_NOT_CYCLIC);
}
@@ -577,7 +577,7 @@ static void unix_walk_scc_fast(struct sk_buff_head *hitlist)
list_replace_init(&unix_visited_vertices, &unix_unvisited_vertices);
unix_graph_cyclic_sccs = cyclic_sccs;
WRITE_ONCE(unix_graph_cyclic_sccs, cyclic_sccs);
WRITE_ONCE(unix_graph_state,
cyclic_sccs ? UNIX_GRAPH_CYCLIC : UNIX_GRAPH_NOT_CYCLIC);
}
@@ -629,19 +629,12 @@ void unix_schedule_gc(void)
queue_work(system_dfl_wq, &unix_gc_work);
}
#define UNIX_INFLIGHT_TRIGGER_GC 16000
#define UNIX_INFLIGHT_SANE_USER (SCM_MAX_FD * 8)
#define UNIX_INFLIGHT_SANE_USER (SCM_MAX_FD * 8)
static void wait_for_unix_gc(struct scm_fp_list *fpl)
{
/* If number of inflight sockets is insane,
* force a garbage collect right now.
*
* Paired with the WRITE_ONCE() in unix_inflight(),
* unix_notinflight(), and __unix_gc().
*/
if (READ_ONCE(unix_tot_inflight) > UNIX_INFLIGHT_TRIGGER_GC)
unix_schedule_gc();
if (READ_ONCE(unix_graph_state) == UNIX_GRAPH_NOT_CYCLIC)
return;
/* Penalise users who want to send AF_UNIX sockets
* but whose sockets have not been received yet.
@@ -649,6 +642,8 @@ static void wait_for_unix_gc(struct scm_fp_list *fpl)
if (READ_ONCE(fpl->user->unix_inflight) < UNIX_INFLIGHT_SANE_USER)
return;
if (READ_ONCE(gc_in_progress))
unix_schedule_gc();
if (READ_ONCE(unix_graph_cyclic_sccs))
flush_work(&unix_gc_work);
}