mirror of
https://github.com/torvalds/linux
synced 2024-09-16 09:05:45 +00:00
035ff358f2
Commit 736b46027e ("net: Add ID (if needed) to sock_reuseport and expose
reuseport_lock") has introduced lazy generation of reuseport group IDs that
survive group resize.
By comparing the identifier we check if BPF reuseport program is not trying
to select a socket from a BPF map that belongs to a different reuseport
group than the one the packet is for.
Because SOCKARRAY used to be the only BPF map type that can be used with
reuseport BPF, it was possible to delay the generation of reuseport group
ID until a socket from the group was inserted into BPF map for the first
time.
Now that SOCK{MAP,HASH} can be used with reuseport BPF we have two options,
either generate the reuseport ID on map update, like SOCKARRAY does, or
allocate an ID from the start when reuseport group gets created.
This patch takes the latter approach to keep sockmap free of calls into
reuseport code. This streamlines the reuseport_id access as its lifetime
now matches the longevity of reuseport object.
The cost of this simplification, however, is that we allocate reuseport IDs
for all SO_REUSEPORT users. Even those that don't use SOCKARRAY in their
setups. With the way identifiers are currently generated, we can have at
most S32_MAX reuseport groups, which hopefully is sufficient. If we ever
get close to the limit, we can switch an u64 counter like sk_cookie.
Another change is that we now always call into SOCKARRAY logic to unlink
the socket from the map when unhashing or closing the socket. Previously we
did it only when at least one socket from the group was in a BPF map.
It is worth noting that this doesn't conflict with sockmap tear-down in
case a socket is in a SOCK{MAP,HASH} and belongs to a reuseport
group. sockmap tear-down happens first:
prot->unhash
`- tcp_bpf_unhash
|- tcp_bpf_remove
| `- while (sk_psock_link_pop(psock))
| `- sk_psock_unlink
| `- sock_map_delete_from_link
| `- __sock_map_delete
| `- sock_map_unref
| `- sk_psock_put
| `- sk_psock_drop
| `- rcu_assign_sk_user_data(sk, NULL)
`- inet_unhash
`- reuseport_detach_sock
`- bpf_sk_reuseport_detach
`- WRITE_ONCE(sk->sk_user_data, NULL)
Suggested-by: Martin Lau <kafai@fb.com>
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20200218171023.844439-10-jakub@cloudflare.com
59 lines
1.5 KiB
C
59 lines
1.5 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 */
|
|
/* 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[0]; /* 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);
|
|
extern struct sock *reuseport_select_sock(struct sock *sk,
|
|
u32 hash,
|
|
struct sk_buff *skb,
|
|
int hdr_len);
|
|
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, bool set)
|
|
{
|
|
struct sock_reuseport *reuse;
|
|
bool ret = false;
|
|
|
|
rcu_read_lock();
|
|
reuse = rcu_dereference(sk->sk_reuseport_cb);
|
|
if (reuse) {
|
|
if (set)
|
|
reuse->has_conns = 1;
|
|
ret = reuse->has_conns;
|
|
}
|
|
rcu_read_unlock();
|
|
|
|
return ret;
|
|
}
|
|
|
|
#endif /* _SOCK_REUSEPORT_H */
|