mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-26 10:49:33 +00:00
![Martin KaFai Lau](/assets/img/avatar_default.png)
This patch allows a BPF_PROG_TYPE_SK_REUSEPORT bpf prog to select a SO_REUSEPORT sk from a BPF_MAP_TYPE_REUSEPORT_ARRAY introduced in the earlier patch. "bpf_run_sk_reuseport()" will return -ECONNREFUSED when the BPF_PROG_TYPE_SK_REUSEPORT prog returns SK_DROP. The callers, in inet[6]_hashtable.c and ipv[46]/udp.c, are modified to handle this case and return NULL immediately instead of continuing the sk search from its hashtable. It re-uses the existing SO_ATTACH_REUSEPORT_EBPF setsockopt to attach BPF_PROG_TYPE_SK_REUSEPORT. The "sk_reuseport_attach_bpf()" will check if the attaching bpf prog is in the new SK_REUSEPORT or the existing SOCKET_FILTER type and then check different things accordingly. One level of "__reuseport_attach_prog()" call is removed. The "sk_unhashed() && ..." and "sk->sk_reuseport_cb" tests are pushed back to "reuseport_attach_prog()" in sock_reuseport.c. sock_reuseport.c seems to have more knowledge on those test requirements than filter.c. In "reuseport_attach_prog()", after new_prog is attached to reuse->prog, the old_prog (if any) is also directly freed instead of returning the old_prog to the caller and asking the caller to free. The sysctl_optmem_max check is moved back to the "sk_reuseport_attach_filter()" and "sk_reuseport_attach_bpf()". As of other bpf prog types, the new BPF_PROG_TYPE_SK_REUSEPORT is only bounded by the usual "bpf_prog_charge_memlock()" during load time instead of bounded by both bpf_prog_charge_memlock and sysctl_optmem_max. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
40 lines
1.2 KiB
C
40 lines
1.2 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;
|
|
bool bind_inany;
|
|
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);
|
|
int reuseport_get_id(struct sock_reuseport *reuse);
|
|
|
|
#endif /* _SOCK_REUSEPORT_H */
|