Commit 4408d55a authored by Kuniyuki Iwashima's avatar Kuniyuki Iwashima Committed by Alexei Starovoitov
Browse files

af_unix: Refactor unix_next_socket(). 



Currently, unix_next_socket() is overloaded depending on the 2nd argument.
If it is NULL, unix_next_socket() returns the first socket in the hash.  If
not NULL, it returns the next socket in the same hash list or the first
socket in the next non-empty hash list.

This patch refactors unix_next_socket() into two functions unix_get_first()
and unix_get_next().  unix_get_first() newly acquires a lock and returns
the first socket in the list.  unix_get_next() returns the next socket in a
list or releases a lock and falls back to unix_get_first().

In the following patch, bpf iter holds entire sockets in a list and always
releases the lock before .show().  It always calls unix_get_first() to
acquire a lock in each iteration.  So, this patch makes the change easier
to follow.

Signed-off-by: default avatarKuniyuki Iwashima <kuniyu@amazon.co.jp>
Link: https://lore.kernel.org/r/20220113002849.4384-2-kuniyu@amazon.co.jp


Signed-off-by: default avatarAlexei Starovoitov <ast@kernel.org>
parent 2a1aff60

net/unix/af_unix.c

+30 −21
Original line number Original line Diff line number Diff line
@@ -3240,49 +3240,58 @@ static struct sock *unix_from_bucket(struct seq_file *seq, loff_t *pos) 
	return sk;

	return sk;

}

}





static struct sock *unix_next_socket(struct seq_file *seq,

static struct sock *unix_get_first(struct seq_file *seq, loff_t *pos)

				     struct sock *sk,

				     loff_t *pos)

{

{

	unsigned long bucket = get_bucket(*pos);

	unsigned long bucket = get_bucket(*pos);

	struct sock *sk;





	while (sk > (struct sock *)SEQ_START_TOKEN) {

	while (bucket < ARRAY_SIZE(unix_socket_table)) {

		sk = sk_next(sk);

		if (!sk)

			goto next_bucket;

		if (sock_net(sk) == seq_file_net(seq))

			return sk;

	}



	do {

		spin_lock(&unix_table_locks[bucket]);

		spin_lock(&unix_table_locks[bucket]);



		sk = unix_from_bucket(seq, pos);

		sk = unix_from_bucket(seq, pos);

		if (sk)

		if (sk)

			return sk;

			return sk;





next_bucket:

		spin_unlock(&unix_table_locks[bucket]);

		spin_unlock(&unix_table_locks[bucket++]);



		*pos = set_bucket_offset(bucket, 1);

		*pos = set_bucket_offset(++bucket, 1);

	} while (bucket < ARRAY_SIZE(unix_socket_table));

	}





	return NULL;

	return NULL;

}

}





static struct sock *unix_get_next(struct seq_file *seq, struct sock *sk,

				  loff_t *pos)

{

	unsigned long bucket = get_bucket(*pos);



	for (sk = sk_next(sk); sk; sk = sk_next(sk))

		if (sock_net(sk) == seq_file_net(seq))

			return sk;



	spin_unlock(&unix_table_locks[bucket]);



	*pos = set_bucket_offset(++bucket, 1);



	return unix_get_first(seq, pos);

}



static void *unix_seq_start(struct seq_file *seq, loff_t *pos)

static void *unix_seq_start(struct seq_file *seq, loff_t *pos)

{

{

	if (!*pos)

	if (!*pos)

		return SEQ_START_TOKEN;

		return SEQ_START_TOKEN;





	if (get_bucket(*pos) >= ARRAY_SIZE(unix_socket_table))

	return unix_get_first(seq, pos);

		return NULL;



	return unix_next_socket(seq, NULL, pos);

}

}





static void *unix_seq_next(struct seq_file *seq, void *v, loff_t *pos)

static void *unix_seq_next(struct seq_file *seq, void *v, loff_t *pos)

{

{

	++*pos;

	++*pos;

	return unix_next_socket(seq, v, pos);



	if (v == SEQ_START_TOKEN)

		return unix_get_first(seq, pos);



	return unix_get_next(seq, v, pos);

}

}





static void unix_seq_stop(struct seq_file *seq, void *v)

static void unix_seq_stop(struct seq_file *seq, void *v)