linux/include/net/sock_reuseport.h
Kuniyuki Iwashima b261eda84e soreuseport: Fix socket selection for SO_INCOMING_CPU.
Kazuho Oku reported that setsockopt(SO_INCOMING_CPU) does not work
with setsockopt(SO_REUSEPORT) since v4.6.

With the combination of SO_REUSEPORT and SO_INCOMING_CPU, we could
build a highly efficient server application.

setsockopt(SO_INCOMING_CPU) associates a CPU with a TCP listener
or UDP socket, and then incoming packets processed on the CPU will
likely be distributed to the socket.  Technically, a socket could
even receive packets handled on another CPU if no sockets in the
reuseport group have the same CPU receiving the flow.

The logic exists in compute_score() so that a socket will get a higher
score if it has the same CPU with the flow.  However, the score gets
ignored after the blamed two commits, which introduced a faster socket
selection algorithm for SO_REUSEPORT.

This patch introduces a counter of sockets with SO_INCOMING_CPU in
a reuseport group to check if we should iterate all sockets to find
a proper one.  We increment the counter when

  * calling listen() if the socket has SO_INCOMING_CPU and SO_REUSEPORT

  * enabling SO_INCOMING_CPU if the socket is in a reuseport group

Also, we decrement it when

  * detaching a socket out of the group to apply SO_INCOMING_CPU to
    migrated TCP requests

  * disabling SO_INCOMING_CPU if the socket is in a reuseport group

When the counter reaches 0, we can get back to the O(1) selection
algorithm.

The overall changes are negligible for the non-SO_INCOMING_CPU case,
and the only notable thing is that we have to update sk_incomnig_cpu
under reuseport_lock.  Otherwise, the race prevents transitioning to
the O(n) algorithm and results in the wrong socket selection.

 cpu1 (setsockopt)               cpu2 (listen)
+-----------------+             +-------------+

lock_sock(sk1)                  lock_sock(sk2)

reuseport_update_incoming_cpu(sk1, val)
.
|  /* set CPU as 0 */
|- WRITE_ONCE(sk1->incoming_cpu, val)
|
|                               spin_lock_bh(&reuseport_lock)
|                               reuseport_grow(sk2, reuse)
|                               .
|                               |- more_socks_size = reuse->max_socks * 2U;
|                               |- if (more_socks_size > U16_MAX &&
|                               |       reuse->num_closed_socks)
|                               |  .
|                               |  |- RCU_INIT_POINTER(sk1->sk_reuseport_cb, NULL);
|                               |  `- __reuseport_detach_closed_sock(sk1, reuse)
|                               |     .
|                               |     `- reuseport_put_incoming_cpu(sk1, reuse)
|                               |        .
|                               |        |  /* Read shutdown()ed sk1's sk_incoming_cpu
|                               |        |   * without lock_sock().
|                               |        |   */
|                               |        `- if (sk1->sk_incoming_cpu >= 0)
|                               |           .
|                               |           |  /* decrement not-yet-incremented
|                               |           |   * count, which is never incremented.
|                               |           |   */
|                               |           `- __reuseport_put_incoming_cpu(reuse);
|                               |
|                               `- spin_lock_bh(&reuseport_lock)
|
|- spin_lock_bh(&reuseport_lock)
|
|- reuse = rcu_dereference_protected(sk1->sk_reuseport_cb, ...)
|- if (!reuse)
|  .
|  |  /* Cannot increment reuse->incoming_cpu. */
|  `- goto out;
|
`- spin_unlock_bh(&reuseport_lock)

Fixes: e32ea7e747 ("soreuseport: fast reuseport UDP socket selection")
Fixes: c125e80b88 ("soreuseport: fast reuseport TCP socket selection")
Reported-by: Kazuho Oku <kazuhooku@gmail.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-10-25 11:35:16 +02:00

65 lines
1.8 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _SOCK_REUSEPORT_H
#define _SOCK_REUSEPORT_H
#include <linux/filter.h>
#include <linux/skbuff.h>
#include <linux/types.h>
#include <linux/spinlock.h>
#include <net/sock.h>
extern spinlock_t reuseport_lock;
struct sock_reuseport {
struct rcu_head rcu;
u16 max_socks; /* length of socks */
u16 num_socks; /* elements in socks */
u16 num_closed_socks; /* closed elements in socks */
u16 incoming_cpu;
/* The last synq overflow event timestamp of this
* reuse->socks[] group.
*/
unsigned int synq_overflow_ts;
/* ID stays the same even after the size of socks[] grows. */
unsigned int reuseport_id;
unsigned int bind_inany:1;
unsigned int has_conns:1;
struct bpf_prog __rcu *prog; /* optional BPF sock selector */
struct sock *socks[]; /* array of sock pointers */
};
extern int reuseport_alloc(struct sock *sk, bool bind_inany);
extern int reuseport_add_sock(struct sock *sk, struct sock *sk2,
bool bind_inany);
extern void reuseport_detach_sock(struct sock *sk);
void reuseport_stop_listen_sock(struct sock *sk);
extern struct sock *reuseport_select_sock(struct sock *sk,
u32 hash,
struct sk_buff *skb,
int hdr_len);
struct sock *reuseport_migrate_sock(struct sock *sk,
struct sock *migrating_sk,
struct sk_buff *skb);
extern int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog);
extern int reuseport_detach_prog(struct sock *sk);
static inline bool reuseport_has_conns(struct sock *sk)
{
struct sock_reuseport *reuse;
bool ret = false;
rcu_read_lock();
reuse = rcu_dereference(sk->sk_reuseport_cb);
if (reuse && reuse->has_conns)
ret = true;
rcu_read_unlock();
return ret;
}
void reuseport_has_conns_set(struct sock *sk);
void reuseport_update_incoming_cpu(struct sock *sk, int val);
#endif /* _SOCK_REUSEPORT_H */