Files
linux/include/net/inet6_hashtables.h
Kuniyuki Iwashima d4d8c6e6fd tcp: Initialise ehash secrets during connect() and listen().
inet_ehashfn() and inet6_ehashfn() initialise random secrets
on the first call by net_get_random_once().

While the init part is patched out using static keys, with
CONFIG_STACKPROTECTOR_STRONG=y, this causes a compiler to
generate a stack canary due to an automatic variable,
unsigned long ___flags, in the DO_ONCE() macro being passed
to __do_once_start().

With FDO, this is visible in __inet_lookup_established() and
__inet6_lookup_established() too.

Let's initialise the secrets by get_random_sleepable_once()
in the slow paths: inet_hash() for listen(), and
inet_hash_connect() and inet6_hash_connect() for connect().

Note that IPv6 listener will initialise both IPv4 & IPv6 secrets
in inet_hash() for IPv4-mapped IPv6 address.

With the patch, the stack size is reduced by 16 bytes (___flags
 + a stack canary) and NOPs for the static key go away.

Before: __inet6_lookup_established()

       ...
       push   %rbx
       sub    $0x38,%rsp                # stack is 56 bytes
       mov    %edx,%ebx                 # sport
       mov    %gs:0x299419f(%rip),%rax  # load stack canary
       mov    %rax,0x30(%rsp)              and store it onto stack
       mov    0x440(%rdi),%r15          # net->ipv4.tcp_death_row.hashinfo
       nop
 32:   mov    %r8d,%ebp                 # hnum
       shl    $0x10,%ebp                # hnum << 16
       nop
 3d:   mov    0x70(%rsp),%r14d          # sdif
       or     %ebx,%ebp                 # INET_COMBINED_PORTS(sport, hnum)
       mov    0x11a8382(%rip),%eax      # inet6_ehashfn() ...

After: __inet6_lookup_established()

       ...
       push   %rbx
       sub    $0x28,%rsp                # stack is 40 bytes
       mov    0x60(%rsp),%ebp           # sdif
       mov    %r8d,%r14d                # hnum
       shl    $0x10,%r14d               # hnum << 16
       or     %edx,%r14d                # INET_COMBINED_PORTS(sport, hnum)
       mov    0x440(%rdi),%rax          # net->ipv4.tcp_death_row.hashinfo
       mov    0x1194f09(%rip),%r10d     # inet6_ehashfn() ...

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260303235424.3877267-1-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-03-05 18:50:05 -08:00

192 lines
5.4 KiB
C

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Authors: Lotsa people, from code originally in tcp
*/
#ifndef _INET6_HASHTABLES_H
#define _INET6_HASHTABLES_H
#if IS_ENABLED(CONFIG_IPV6)
#include <linux/in6.h>
#include <linux/ipv6.h>
#include <linux/types.h>
#include <linux/jhash.h>
#include <net/inet_sock.h>
#include <net/ipv6.h>
#include <net/netns/hash.h>
struct inet_hashinfo;
void inet6_init_ehash_secret(void);
static inline unsigned int __inet6_ehashfn(const u32 lhash,
const u16 lport,
const u32 fhash,
const __be16 fport,
const u32 initval)
{
const u32 ports = (((u32)lport) << 16) | (__force u32)fport;
return jhash_3words(lhash, fhash, ports, initval);
}
/*
* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so
* we need not check it for TCP lookups anymore, thanks Alexey. -DaveM
*
* The sockhash lock must be held as a reader here.
*/
struct sock *__inet6_lookup_established(const struct net *net,
const struct in6_addr *saddr,
const __be16 sport,
const struct in6_addr *daddr,
const u16 hnum, const int dif,
const int sdif);
typedef u32 (inet6_ehashfn_t)(const struct net *net,
const struct in6_addr *laddr, const u16 lport,
const struct in6_addr *faddr, const __be16 fport);
inet6_ehashfn_t inet6_ehashfn;
INDIRECT_CALLABLE_DECLARE(inet6_ehashfn_t udp6_ehashfn);
struct sock *inet6_lookup_reuseport(const struct net *net, struct sock *sk,
struct sk_buff *skb, int doff,
const struct in6_addr *saddr,
__be16 sport,
const struct in6_addr *daddr,
unsigned short hnum,
inet6_ehashfn_t *ehashfn);
struct sock *inet6_lookup_listener(const struct net *net,
struct sk_buff *skb, int doff,
const struct in6_addr *saddr,
const __be16 sport,
const struct in6_addr *daddr,
const unsigned short hnum,
const int dif, const int sdif);
struct sock *inet6_lookup_run_sk_lookup(const struct net *net,
int protocol,
struct sk_buff *skb, int doff,
const struct in6_addr *saddr,
const __be16 sport,
const struct in6_addr *daddr,
const u16 hnum, const int dif,
inet6_ehashfn_t *ehashfn);
static inline struct sock *__inet6_lookup(const struct net *net,
struct sk_buff *skb, int doff,
const struct in6_addr *saddr,
const __be16 sport,
const struct in6_addr *daddr,
const u16 hnum,
const int dif, const int sdif,
bool *refcounted)
{
struct sock *sk = __inet6_lookup_established(net, saddr, sport,
daddr, hnum,
dif, sdif);
*refcounted = true;
if (sk)
return sk;
*refcounted = false;
return inet6_lookup_listener(net, skb, doff, saddr, sport,
daddr, hnum, dif, sdif);
}
static inline
struct sock *inet6_steal_sock(struct net *net, struct sk_buff *skb, int doff,
const struct in6_addr *saddr, const __be16 sport,
const struct in6_addr *daddr, const __be16 dport,
bool *refcounted, inet6_ehashfn_t *ehashfn)
{
struct sock *sk, *reuse_sk;
bool prefetched;
sk = skb_steal_sock(skb, refcounted, &prefetched);
if (!sk)
return NULL;
if (!prefetched || !sk_fullsock(sk))
return sk;
if (sk->sk_protocol == IPPROTO_TCP) {
if (sk->sk_state != TCP_LISTEN)
return sk;
} else if (sk->sk_protocol == IPPROTO_UDP) {
if (sk->sk_state != TCP_CLOSE)
return sk;
} else {
return sk;
}
reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff,
saddr, sport, daddr, ntohs(dport),
ehashfn);
if (!reuse_sk)
return sk;
/* We've chosen a new reuseport sock which is never refcounted. This
* implies that sk also isn't refcounted.
*/
WARN_ON_ONCE(*refcounted);
return reuse_sk;
}
static inline struct sock *__inet6_lookup_skb(struct sk_buff *skb, int doff,
const __be16 sport,
const __be16 dport,
int iif, int sdif,
bool *refcounted)
{
struct net *net = skb_dst_dev_net_rcu(skb);
const struct ipv6hdr *ip6h = ipv6_hdr(skb);
struct sock *sk;
sk = inet6_steal_sock(net, skb, doff, &ip6h->saddr, sport, &ip6h->daddr, dport,
refcounted, inet6_ehashfn);
if (IS_ERR(sk))
return NULL;
if (sk)
return sk;
return __inet6_lookup(net, skb, doff, &ip6h->saddr, sport,
&ip6h->daddr, ntohs(dport),
iif, sdif, refcounted);
}
struct sock *inet6_lookup(const struct net *net, struct sk_buff *skb, int doff,
const struct in6_addr *saddr, const __be16 sport,
const struct in6_addr *daddr, const __be16 dport,
const int dif);
static inline bool inet6_match(const struct net *net, const struct sock *sk,
const struct in6_addr *saddr,
const struct in6_addr *daddr,
const __portpair ports,
const int dif, const int sdif)
{
if (!net_eq(sock_net(sk), net) ||
sk->sk_family != AF_INET6 ||
READ_ONCE(sk->sk_portpair) != ports ||
!ipv6_addr_equal(&sk->sk_v6_daddr, saddr) ||
!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
return false;
/* READ_ONCE() paired with WRITE_ONCE() in sock_bindtoindex_locked() */
return inet_sk_bound_dev_eq(net, READ_ONCE(sk->sk_bound_dev_if), dif,
sdif);
}
#endif /* IS_ENABLED(CONFIG_IPV6) */
#endif /* _INET6_HASHTABLES_H */