[PATCH net-next v2 0/3] af_unix: Fix priority inversion issue

[PATCH net-next v2 0/3] af_unix: Fix priority inversion issue

[Nam Cao]

Hi,

While auditing AF_UNIX sockets, I noticed that the sendmsg() code paths may
block on the garbage collector running as workqueue. This can cause
priority inversion and latency for real-time users.

The implementation does kindly avoid blocking "sane users". However, it is
impossible to tell whether the kernel's definition of "sane users"
accurately describes all users out there.

Digging into history and figuring out the reasons why sendmsg() needs to
wait for garbage collector, it is determined that those reasons no longer
apply.

The first patch resolves another issue reported by Sashiko in v1, paves the
way for the second patch to remove the block. The last one is a simple
post-cleanup.

v2:
  - Add patch [1/3]
  - Rebase the other two patches onto the new patch
  - Change commit message to be more precise

Nam Cao (3):
  af_unix: Schedule the garbage collector at task exit
  af_unix: Do not wait for garbage collector in sendmsg()
  af_unix: Clean up unix_schedule_gc()

 include/net/af_unix.h |  5 +++++
 kernel/exit.c         |  2 ++
 net/unix/af_unix.c    |  2 +-
 net/unix/af_unix.h    |  1 -
 net/unix/garbage.c    | 16 +---------------
 5 files changed, 9 insertions(+), 17 deletions(-)

-- 
2.47.3

[PATCH net-next v2 1/3] af_unix: Schedule the garbage collector at task exit

[Nam Cao]

When a task exits while still having dead cyclic reference AF_UNIX sockets,
those sockets stay behind indefinitely until the garbage collector gets
scheduled by an unrelated reason. This can be observed with the program
below.

Resolve this issue by scheduling the garbage collector during task exit,
after the task's file descriptors have been closed.

static int send_fd(int unix_fd, int fd)
{
        struct msghdr msgh;
        struct cmsghdr *cmsg;
        char buf[CMSG_SPACE(sizeof(fd))];

        memset(&msgh, 0, sizeof(msgh));

        memset(buf, 0, sizeof(buf));
        msgh.msg_control = buf;
        msgh.msg_controllen = sizeof(buf);

        cmsg = CMSG_FIRSTHDR(&msgh);
        cmsg->cmsg_len = CMSG_LEN(sizeof(fd));
        cmsg->cmsg_level = SOL_SOCKET;
        cmsg->cmsg_type = SCM_RIGHTS;

        msgh.msg_controllen = cmsg->cmsg_len;

        memcpy(CMSG_DATA(cmsg), &fd, sizeof(fd));
        return sendmsg(unix_fd, &msgh, 0);
}

int main(int argc, char *argv[])
{
	int fd[2];
	int i;

	for (int n = 0; n < 100; ++n) {
		if (socketpair(PF_UNIX, SOCK_SEQPACKET, 0, fd) == -1)
			goto out_error;

		for (i = 0; i < 100; ++i) {
			if (send_fd(fd[0], fd[0]) == -1)
				goto out_error;

			if (send_fd(fd[1], fd[1]) == -1)
				goto out_error;
		}
	}

	return 0;

out_error:
	fprintf(stderr, "error: %s\n", strerror(errno));
}

Signed-off-by: Nam Cao <namcao@linutronix.de>
---
 include/net/af_unix.h | 5 +++++
 kernel/exit.c         | 2 ++
 net/unix/af_unix.h    | 1 -
 3 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 34f53dde65ce..686f6f1d1c21 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -14,11 +14,16 @@
 
 #if IS_ENABLED(CONFIG_UNIX)
 struct unix_sock *unix_get_socket(struct file *filp);
+void unix_schedule_gc(struct user_struct *user);
 #else
 static inline struct unix_sock *unix_get_socket(struct file *filp)
 {
 	return NULL;
 }
+
+static inline void unix_schedule_gc(struct user_struct *user)
+{
+}
 #endif
 
 struct unix_address {
diff --git a/kernel/exit.c b/kernel/exit.c
index 2c0b1c02920f..ba9404844523 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -71,6 +71,7 @@
 #include <linux/unwind_deferred.h>
 #include <linux/uaccess.h>
 #include <linux/pidfs.h>
+#include <net/af_unix.h>
 
 #include <uapi/linux/wait.h>
 
@@ -1002,6 +1003,7 @@ void __noreturn do_exit(long code)
 	exit_sem(tsk);
 	exit_shm(tsk);
 	exit_files(tsk);
+	unix_schedule_gc(NULL); /* Must be after exit_files() */
 	exit_fs(tsk);
 	if (group_dead)
 		disassociate_ctty(1);
diff --git a/net/unix/af_unix.h b/net/unix/af_unix.h
index 8119dbeef3a3..fc4c59893124 100644
--- a/net/unix/af_unix.h
+++ b/net/unix/af_unix.h
@@ -30,7 +30,6 @@ void unix_update_edges(struct unix_sock *receiver);
 int unix_prepare_fpl(struct scm_fp_list *fpl);
 void unix_destroy_fpl(struct scm_fp_list *fpl);
 void unix_peek_fpl(struct scm_fp_list *fpl);
-void unix_schedule_gc(struct user_struct *user);
 
 /* SOCK_DIAG */
 long unix_inq_len(struct sock *sk);
-- 
2.47.3

Re: [PATCH net-next v2 1/3] af_unix: Schedule the garbage collector at task exit

[Nam Cao]

Nam Cao <namcao@linutronix.de> writes:
> @@ -1002,6 +1003,7 @@ void __noreturn do_exit(long code)
>  	exit_sem(tsk);
>  	exit_shm(tsk);
>  	exit_files(tsk);
> +	unix_schedule_gc(NULL); /* Must be after exit_files() */

Argh, I just realized that exit_files() is deferred to task work, so
this must be after exit_task_work().

I will send v3 in a few days, if there is no other comment.

Nam

[PATCH net-next v2 2/3] af_unix: Do not wait for garbage collector in sendmsg()

[Nam Cao]

AF_UNIX sockets' sendmsg() schedules and blocks on the garbage collector if
user has too many inflight unix sockets and there is cyclic reference in
the system. This causes real-time issues, as cyclic reference can be
created by any task in the system, and high priority tasks who do need to
send lots of AF_UNIX sockets get blocked by the garbage collector which
runs as workqueue, causing a priority inversion scenario.

The reason for blocking on garbage collector goes back to 2008, when
it was reported that "Local/unprivileged users can cause soft lockups
and take out system processes by triggering the OOM killer":
https://bugzilla.redhat.com/show_bug.cgi?id=470201

The soft lockup was because a process can keep queueing AF_UNIX sockets to
another process that is exiting. Back in 2008, the garbage collector was
run synchronously by the exiting process, therefore keep queueing AF_UNIX
sockets blocks that process from exiting.

The solution to that issue was forcing sendmsg() to wait for ongoing
garbage collector.

The OOM killer issue was brought up again in 2010:
https://lore.kernel.org/lkml/AANLkTi=Q967xpX0KLMwX-=_4_1AKO5wjHEuJ1TrNjCj9@mail.gmail.com/

To resolve that report, beside blocking on the garbage collector, sendmsg()
also schedules the garbage collector if the number of inflight AF_UNIX
sockets in the system is too high.

Then in 2015, once again, the OOM killer problem was brought up:
https://lore.kernel.org/lkml/20151228141435.GA13351@1wt.eu/

That time, the issue was resolved by disallowing a user from having more
inflight AF_UNIX sockets than their RLIMIT_NOFILE. That was done by commit
712f4aad406b ("unix: properly account for FDs passed over unix sockets")
and commit 415e3d3e90ce ("unix: correctly track in-flight fds in sending
process user_struct").

Now, sendmsg() does not have to block on the garbage collector anymore,
because:

  - The OOM killer issue has already been addressed by checking
    RLIMIT_NOFILE.

  - The soft lockup issue is no longer relevant, because the garbage
    collector now runs asynchronously since commit d9f21b361333 ("af_unix:
    Try to run GC async.")

Therefore, remove that to prevent priority inversion. Running all the
reproducers from the mentioned bug reports after this patch, no problem is
observed.

Signed-off-by: Nam Cao <namcao@linutronix.de>
---
 net/unix/garbage.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 0783555e2526..f180c59b3da9 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -300,8 +300,6 @@ int unix_prepare_fpl(struct scm_fp_list *fpl)
 	if (!fpl->edges)
 		goto err;
 
-	unix_schedule_gc(fpl->user);
-
 	return 0;
 
 err:
-- 
2.47.3

[PATCH net-next v2 3/3] af_unix: Clean up unix_schedule_gc()

[Nam Cao]

unix_schedule_gc() is only called with NULL as an argument.

Simplify by deleting the parameter.

Signed-off-by: Nam Cao <namcao@linutronix.de>
---
 include/net/af_unix.h |  4 ++--
 kernel/exit.c         |  2 +-
 net/unix/af_unix.c    |  2 +-
 net/unix/garbage.c    | 14 +-------------
 4 files changed, 5 insertions(+), 17 deletions(-)

diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 686f6f1d1c21..1dfdc0720052 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -14,14 +14,14 @@
 
 #if IS_ENABLED(CONFIG_UNIX)
 struct unix_sock *unix_get_socket(struct file *filp);
-void unix_schedule_gc(struct user_struct *user);
+void unix_schedule_gc(void);
 #else
 static inline struct unix_sock *unix_get_socket(struct file *filp)
 {
 	return NULL;
 }
 
-static inline void unix_schedule_gc(struct user_struct *user)
+static inline void unix_schedule_gc(void)
 {
 }
 #endif
diff --git a/kernel/exit.c b/kernel/exit.c
index ba9404844523..764a911f111e 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1003,7 +1003,7 @@ void __noreturn do_exit(long code)
 	exit_sem(tsk);
 	exit_shm(tsk);
 	exit_files(tsk);
-	unix_schedule_gc(NULL); /* Must be after exit_files() */
+	unix_schedule_gc(); /* Must be after exit_files() */
 	exit_fs(tsk);
 	if (group_dead)
 		disassociate_ctty(1);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index f7a9d55eee8a..759db734a866 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -733,7 +733,7 @@ static void unix_release_sock(struct sock *sk, int embrion)
 
 	/* ---- Socket is dead now and most probably destroyed ---- */
 
-	unix_schedule_gc(NULL);
+	unix_schedule_gc();
 }
 
 struct unix_peercred {
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index f180c59b3da9..d46aeb9d2051 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -635,23 +635,11 @@ static void unix_gc(struct work_struct *work)
 
 static DECLARE_WORK(unix_gc_work, unix_gc);
 
-#define UNIX_INFLIGHT_SANE_USER		(SCM_MAX_FD * 8)
-
-void unix_schedule_gc(struct user_struct *user)
+void unix_schedule_gc(void)
 {
 	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.
-	 */
-	if (user &&
-	    READ_ONCE(user->unix_inflight) < UNIX_INFLIGHT_SANE_USER)
-		return;
-
 	if (!READ_ONCE(gc_in_progress))
 		queue_work(system_dfl_wq, &unix_gc_work);
-
-	if (user && READ_ONCE(unix_graph_cyclic_sccs))
-		flush_work(&unix_gc_work);
 }
-- 
2.47.3