From 37f49e37ab4cb5d0bc4c60eb5c6d4dd57db767bb Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Fri, 10 May 2024 07:44:59 +0000
Subject: [PATCH] gmac get mac form eeprom
---
kernel/net/ipv4/inet_hashtables.c | 377 ++++++++++++++++++++++++++++++++++-------------------
1 files changed, 238 insertions(+), 139 deletions(-)
diff --git a/kernel/net/ipv4/inet_hashtables.c b/kernel/net/ipv4/inet_hashtables.c
index 3a5f12f..5650565 100644
--- a/kernel/net/ipv4/inet_hashtables.c
+++ b/kernel/net/ipv4/inet_hashtables.c
@@ -1,3 +1,4 @@
+// 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
@@ -6,11 +7,6 @@
* Generic INET transport hashtables
*
* Authors: Lotsa people, from code originally in tcp
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
*/
#include <linux/module.h>
@@ -19,11 +15,14 @@
#include <linux/slab.h>
#include <linux/wait.h>
#include <linux/vmalloc.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <net/addrconf.h>
#include <net/inet_connection_sock.h>
#include <net/inet_hashtables.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/inet6_hashtables.h>
+#endif
#include <net/secure_seq.h>
#include <net/ip.h>
#include <net/tcp.h>
@@ -65,12 +64,14 @@
struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep,
struct net *net,
struct inet_bind_hashbucket *head,
- const unsigned short snum)
+ const unsigned short snum,
+ int l3mdev)
{
struct inet_bind_bucket *tb = kmem_cache_alloc(cachep, GFP_ATOMIC);
if (tb) {
write_pnet(&tb->ib_net, net);
+ tb->l3mdev = l3mdev;
tb->port = snum;
tb->fastreuse = 0;
tb->fastreuseport = 0;
@@ -135,6 +136,7 @@
table->bhash_size);
struct inet_bind_hashbucket *head = &table->bhash[bhash];
struct inet_bind_bucket *tb;
+ int l3mdev;
spin_lock(&head->lock);
tb = inet_csk(sk)->icsk_bind_hash;
@@ -143,6 +145,8 @@
return -ENOENT;
}
if (tb->port != port) {
+ l3mdev = inet_sk_bound_l3mdev(sk);
+
/* NOTE: using tproxy and redirecting skbs to a proxy
* on a different listener port breaks the assumption
* that the listener socket's icsk_bind_hash is the same
@@ -150,12 +154,13 @@
* create a new bind bucket for the child here. */
inet_bind_bucket_for_each(tb, &head->chain) {
if (net_eq(ib_net(tb), sock_net(sk)) &&
- tb->port == port)
+ tb->l3mdev == l3mdev && tb->port == port)
break;
}
if (!tb) {
tb = inet_bind_bucket_create(table->bind_bucket_cachep,
- sock_net(sk), head, port);
+ sock_net(sk), head, port,
+ l3mdev);
if (!tb) {
spin_unlock(&head->lock);
return -ENOMEM;
@@ -226,33 +231,40 @@
static inline int compute_score(struct sock *sk, struct net *net,
const unsigned short hnum, const __be32 daddr,
- const int dif, const int sdif, bool exact_dif)
+ const int dif, const int sdif)
{
int score = -1;
- struct inet_sock *inet = inet_sk(sk);
- if (net_eq(sock_net(sk), net) && inet->inet_num == hnum &&
+ if (net_eq(sock_net(sk), net) && sk->sk_num == hnum &&
!ipv6_only_sock(sk)) {
- __be32 rcv_saddr = inet->inet_rcv_saddr;
- score = sk->sk_family == PF_INET ? 2 : 1;
- if (rcv_saddr) {
- if (rcv_saddr != daddr)
- return -1;
- score += 4;
- }
- if (sk->sk_bound_dev_if || exact_dif) {
- bool dev_match = (sk->sk_bound_dev_if == dif ||
- sk->sk_bound_dev_if == sdif);
+ if (sk->sk_rcv_saddr != daddr)
+ return -1;
- if (!dev_match)
- return -1;
- if (sk->sk_bound_dev_if)
- score += 4;
- }
+ if (!inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif))
+ return -1;
+ score = sk->sk_bound_dev_if ? 2 : 1;
+
+ if (sk->sk_family == PF_INET)
+ score++;
if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
score++;
}
return score;
+}
+
+static inline struct sock *lookup_reuseport(struct net *net, struct sock *sk,
+ struct sk_buff *skb, int doff,
+ __be32 saddr, __be16 sport,
+ __be32 daddr, unsigned short hnum)
+{
+ struct sock *reuse_sk = NULL;
+ u32 phash;
+
+ if (sk->sk_reuseport) {
+ phash = inet_ehashfn(net, daddr, hnum, saddr, sport);
+ reuse_sk = reuseport_select_sock(sk, phash, skb, doff);
+ }
+ return reuse_sk;
}
/*
@@ -270,31 +282,48 @@
const __be32 daddr, const unsigned short hnum,
const int dif, const int sdif)
{
- bool exact_dif = inet_exact_dif_match(net, skb);
struct inet_connection_sock *icsk;
struct sock *sk, *result = NULL;
int score, hiscore = 0;
- u32 phash = 0;
inet_lhash2_for_each_icsk_rcu(icsk, &ilb2->head) {
sk = (struct sock *)icsk;
- score = compute_score(sk, net, hnum, daddr,
- dif, sdif, exact_dif);
+ score = compute_score(sk, net, hnum, daddr, dif, sdif);
if (score > hiscore) {
- if (sk->sk_reuseport) {
- phash = inet_ehashfn(net, daddr, hnum,
- saddr, sport);
- result = reuseport_select_sock(sk, phash,
- skb, doff);
- if (result)
- return result;
- }
+ result = lookup_reuseport(net, sk, skb, doff,
+ saddr, sport, daddr, hnum);
+ if (result)
+ return result;
+
result = sk;
hiscore = score;
}
}
return result;
+}
+
+static inline struct sock *inet_lookup_run_bpf(struct net *net,
+ struct inet_hashinfo *hashinfo,
+ struct sk_buff *skb, int doff,
+ __be32 saddr, __be16 sport,
+ __be32 daddr, u16 hnum)
+{
+ struct sock *sk, *reuse_sk;
+ bool no_reuseport;
+
+ if (hashinfo != &tcp_hashinfo)
+ return NULL; /* only TCP is supported */
+
+ no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_TCP,
+ saddr, sport, daddr, hnum, &sk);
+ if (no_reuseport || IS_ERR_OR_NULL(sk))
+ return sk;
+
+ reuse_sk = lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum);
+ if (reuse_sk)
+ sk = reuse_sk;
+ return sk;
}
struct sock *__inet_lookup_listener(struct net *net,
@@ -304,27 +333,20 @@
const __be32 daddr, const unsigned short hnum,
const int dif, const int sdif)
{
- unsigned int hash = inet_lhashfn(net, hnum);
- struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash];
- bool exact_dif = inet_exact_dif_match(net, skb);
struct inet_listen_hashbucket *ilb2;
- struct sock *sk, *result = NULL;
- struct hlist_nulls_node *node;
- int score, hiscore = 0;
+ struct sock *result = NULL;
unsigned int hash2;
- u32 phash = 0;
- if (ilb->count <= 10 || !hashinfo->lhash2)
- goto port_lookup;
-
- /* Too many sk in the ilb bucket (which is hashed by port alone).
- * Try lhash2 (which is hashed by port and addr) instead.
- */
+ /* Lookup redirect from BPF */
+ if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
+ result = inet_lookup_run_bpf(net, hashinfo, skb, doff,
+ saddr, sport, daddr, hnum);
+ if (result)
+ goto done;
+ }
hash2 = ipv4_portaddr_hash(net, daddr, hnum);
ilb2 = inet_lhash2_bucket(hashinfo, hash2);
- if (ilb2->count > ilb->count)
- goto port_lookup;
result = inet_lhash2_lookup(net, ilb2, skb, doff,
saddr, sport, daddr, hnum,
@@ -333,36 +355,14 @@
goto done;
/* Lookup lhash2 with INADDR_ANY */
-
hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum);
ilb2 = inet_lhash2_bucket(hashinfo, hash2);
- if (ilb2->count > ilb->count)
- goto port_lookup;
result = inet_lhash2_lookup(net, ilb2, skb, doff,
- saddr, sport, daddr, hnum,
+ saddr, sport, htonl(INADDR_ANY), hnum,
dif, sdif);
- goto done;
-
-port_lookup:
- sk_nulls_for_each_rcu(sk, node, &ilb->nulls_head) {
- score = compute_score(sk, net, hnum, daddr,
- dif, sdif, exact_dif);
- if (score > hiscore) {
- if (sk->sk_reuseport) {
- phash = inet_ehashfn(net, daddr, hnum,
- saddr, sport);
- result = reuseport_select_sock(sk, phash,
- skb, doff);
- if (result)
- goto done;
- }
- result = sk;
- hiscore = score;
- }
- }
done:
- if (unlikely(IS_ERR(result)))
+ if (IS_ERR(result))
return NULL;
return result;
}
@@ -410,13 +410,11 @@
sk_nulls_for_each_rcu(sk, node, &head->chain) {
if (sk->sk_hash != hash)
continue;
- if (likely(INET_MATCH(sk, net, acookie,
- saddr, daddr, ports, dif, sdif))) {
+ if (likely(INET_MATCH(net, sk, acookie, ports, dif, sdif))) {
if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
goto out;
- if (unlikely(!INET_MATCH(sk, net, acookie,
- saddr, daddr, ports,
- dif, sdif))) {
+ if (unlikely(!INET_MATCH(net, sk, acookie,
+ ports, dif, sdif))) {
sock_gen_put(sk);
goto begin;
}
@@ -465,8 +463,7 @@
if (sk2->sk_hash != hash)
continue;
- if (likely(INET_MATCH(sk2, net, acookie,
- saddr, daddr, ports, dif, sdif))) {
+ if (likely(INET_MATCH(net, sk2, acookie, ports, dif, sdif))) {
if (sk2->sk_state == TCP_TIME_WAIT) {
tw = inet_twsk(sk2);
if (twsk_unique(sk, sk2, twp))
@@ -504,7 +501,7 @@
return -EADDRNOTAVAIL;
}
-static u32 inet_sk_port_offset(const struct sock *sk)
+static u64 inet_sk_port_offset(const struct sock *sk)
{
const struct inet_sock *inet = inet_sk(sk);
@@ -513,10 +510,50 @@
inet->inet_dport);
}
-/* insert a socket into ehash, and eventually remove another one
- * (The another one can be a SYN_RECV or TIMEWAIT
+/* Searches for an exsiting socket in the ehash bucket list.
+ * Returns true if found, false otherwise.
*/
-bool inet_ehash_insert(struct sock *sk, struct sock *osk)
+static bool inet_ehash_lookup_by_sk(struct sock *sk,
+ struct hlist_nulls_head *list)
+{
+ const __portpair ports = INET_COMBINED_PORTS(sk->sk_dport, sk->sk_num);
+ const int sdif = sk->sk_bound_dev_if;
+ const int dif = sk->sk_bound_dev_if;
+ const struct hlist_nulls_node *node;
+ struct net *net = sock_net(sk);
+ struct sock *esk;
+
+ INET_ADDR_COOKIE(acookie, sk->sk_daddr, sk->sk_rcv_saddr);
+
+ sk_nulls_for_each_rcu(esk, node, list) {
+ if (esk->sk_hash != sk->sk_hash)
+ continue;
+ if (sk->sk_family == AF_INET) {
+ if (unlikely(INET_MATCH(net, esk, acookie,
+ ports, dif, sdif))) {
+ return true;
+ }
+ }
+#if IS_ENABLED(CONFIG_IPV6)
+ else if (sk->sk_family == AF_INET6) {
+ if (unlikely(inet6_match(net, esk,
+ &sk->sk_v6_daddr,
+ &sk->sk_v6_rcv_saddr,
+ ports, dif, sdif))) {
+ return true;
+ }
+ }
+#endif
+ }
+ return false;
+}
+
+/* Insert a socket into ehash, and eventually remove another one
+ * (The another one can be a SYN_RECV or TIMEWAIT)
+ * If an existing socket already exists, socket sk is not inserted,
+ * and sets found_dup_sk parameter to true.
+ */
+bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk)
{
struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
struct hlist_nulls_head *list;
@@ -535,16 +572,23 @@
if (osk) {
WARN_ON_ONCE(sk->sk_hash != osk->sk_hash);
ret = sk_nulls_del_node_init_rcu(osk);
+ } else if (found_dup_sk) {
+ *found_dup_sk = inet_ehash_lookup_by_sk(sk, list);
+ if (*found_dup_sk)
+ ret = false;
}
+
if (ret)
__sk_nulls_add_node_rcu(sk, list);
+
spin_unlock(lock);
+
return ret;
}
-bool inet_ehash_nolisten(struct sock *sk, struct sock *osk)
+bool inet_ehash_nolisten(struct sock *sk, struct sock *osk, bool *found_dup_sk)
{
- bool ok = inet_ehash_insert(sk, osk);
+ bool ok = inet_ehash_insert(sk, osk, found_dup_sk);
if (ok) {
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
@@ -588,7 +632,9 @@
int err = 0;
if (sk->sk_state != TCP_LISTEN) {
- inet_ehash_nolisten(sk, osk);
+ local_bh_disable();
+ inet_ehash_nolisten(sk, osk, NULL);
+ local_bh_enable();
return 0;
}
WARN_ON(!sk_unhashed(sk));
@@ -620,50 +666,72 @@
{
int err = 0;
- if (sk->sk_state != TCP_CLOSE) {
- local_bh_disable();
+ if (sk->sk_state != TCP_CLOSE)
err = __inet_hash(sk, NULL);
- local_bh_enable();
- }
return err;
}
EXPORT_SYMBOL_GPL(inet_hash);
-void inet_unhash(struct sock *sk)
+static void __inet_unhash(struct sock *sk, struct inet_listen_hashbucket *ilb)
{
- struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
- struct inet_listen_hashbucket *ilb = NULL;
- spinlock_t *lock;
-
if (sk_unhashed(sk))
return;
-
- if (sk->sk_state == TCP_LISTEN) {
- ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)];
- lock = &ilb->lock;
- } else {
- lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
- }
- spin_lock_bh(lock);
- if (sk_unhashed(sk))
- goto unlock;
if (rcu_access_pointer(sk->sk_reuseport_cb))
reuseport_detach_sock(sk);
if (ilb) {
+ struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
+
inet_unhash2(hashinfo, sk);
ilb->count--;
}
__sk_nulls_del_node_init_rcu(sk);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
-unlock:
- spin_unlock_bh(lock);
+}
+
+void inet_unhash(struct sock *sk)
+{
+ struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
+
+ if (sk_unhashed(sk))
+ return;
+
+ if (sk->sk_state == TCP_LISTEN) {
+ struct inet_listen_hashbucket *ilb;
+
+ ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)];
+ /* Don't disable bottom halves while acquiring the lock to
+ * avoid circular locking dependency on PREEMPT_RT.
+ */
+ spin_lock(&ilb->lock);
+ __inet_unhash(sk, ilb);
+ spin_unlock(&ilb->lock);
+ } else {
+ spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
+
+ spin_lock_bh(lock);
+ __inet_unhash(sk, NULL);
+ spin_unlock_bh(lock);
+ }
}
EXPORT_SYMBOL_GPL(inet_unhash);
+/* RFC 6056 3.3.4. Algorithm 4: Double-Hash Port Selection Algorithm
+ * Note that we use 32bit integers (vs RFC 'short integers')
+ * because 2^16 is not a multiple of num_ephemeral and this
+ * property might be used by clever attacker.
+ *
+ * RFC claims using TABLE_LENGTH=10 buckets gives an improvement, though
+ * attacks were since demonstrated, thus we use 65536 by default instead
+ * to really give more isolation and privacy, at the expense of 256kB
+ * of kernel memory.
+ */
+#define INET_TABLE_PERTURB_SIZE (1 << CONFIG_INET_TABLE_PERTURB_ORDER)
+static u32 *table_perturb;
+
int __inet_hash_connect(struct inet_timewait_death_row *death_row,
- struct sock *sk, u32 port_offset,
+ struct sock *sk, u64 port_offset,
int (*check_established)(struct inet_timewait_death_row *,
struct sock *, __u16, struct inet_timewait_sock **))
{
@@ -675,24 +743,17 @@
struct inet_bind_bucket *tb;
u32 remaining, offset;
int ret, i, low, high;
- static u32 hint;
+ int l3mdev;
+ u32 index;
if (port) {
- head = &hinfo->bhash[inet_bhashfn(net, port,
- hinfo->bhash_size)];
- tb = inet_csk(sk)->icsk_bind_hash;
- spin_lock_bh(&head->lock);
- if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) {
- inet_ehash_nolisten(sk, NULL);
- spin_unlock_bh(&head->lock);
- return 0;
- }
- spin_unlock(&head->lock);
- /* No definite answer... Walk to established hash table */
+ local_bh_disable();
ret = check_established(death_row, sk, port, NULL);
local_bh_enable();
return ret;
}
+
+ l3mdev = inet_sk_bound_l3mdev(sk);
inet_get_local_port_range(net, &low, &high);
high++; /* [32768, 60999] -> [32768, 61000[ */
@@ -700,7 +761,13 @@
if (likely(remaining > 1))
remaining &= ~1U;
- offset = (hint + port_offset) % remaining;
+ get_random_slow_once(table_perturb,
+ INET_TABLE_PERTURB_SIZE * sizeof(*table_perturb));
+ index = port_offset & (INET_TABLE_PERTURB_SIZE - 1);
+
+ offset = READ_ONCE(table_perturb[index]) + (port_offset >> 32);
+ offset %= remaining;
+
/* In first pass we try ports of @low parity.
* inet_csk_get_port() does the opposite choice.
*/
@@ -720,7 +787,8 @@
* the established check is already unique enough.
*/
inet_bind_bucket_for_each(tb, &head->chain) {
- if (net_eq(ib_net(tb), net) && tb->port == port) {
+ if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev &&
+ tb->port == port) {
if (tb->fastreuse >= 0 ||
tb->fastreuseport >= 0)
goto next_port;
@@ -733,7 +801,7 @@
}
tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep,
- net, head, port);
+ net, head, port, l3mdev);
if (!tb) {
spin_unlock_bh(&head->lock);
return -ENOMEM;
@@ -753,13 +821,19 @@
return -EADDRNOTAVAIL;
ok:
- hint += i + 2;
+ /* Here we want to add a little bit of randomness to the next source
+ * port that will be chosen. We use a max() with a random here so that
+ * on low contention the randomness is maximal and on high contention
+ * it may be inexistent.
+ */
+ i = max_t(int, i, (prandom_u32() & 7) * 2);
+ WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + 2);
/* Head lock still held and bh's disabled */
inet_bind_hash(sk, tb, port);
if (sk_unhashed(sk)) {
inet_sk(sk)->inet_sport = htons(port);
- inet_ehash_nolisten(sk, (struct sock *)tw);
+ inet_ehash_nolisten(sk, (struct sock *)tw, NULL);
}
if (tw)
inet_twsk_bind_unhash(tw, hinfo);
@@ -776,7 +850,7 @@
int inet_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk)
{
- u32 port_offset = 0;
+ u64 port_offset = 0;
if (!inet_sk(sk)->inet_num)
port_offset = inet_sk_port_offset(sk);
@@ -800,13 +874,22 @@
}
EXPORT_SYMBOL_GPL(inet_hashinfo_init);
+static void init_hashinfo_lhash2(struct inet_hashinfo *h)
+{
+ int i;
+
+ for (i = 0; i <= h->lhash2_mask; i++) {
+ spin_lock_init(&h->lhash2[i].lock);
+ INIT_HLIST_HEAD(&h->lhash2[i].head);
+ h->lhash2[i].count = 0;
+ }
+}
+
void __init inet_hashinfo2_init(struct inet_hashinfo *h, const char *name,
unsigned long numentries, int scale,
unsigned long low_limit,
unsigned long high_limit)
{
- unsigned int i;
-
h->lhash2 = alloc_large_system_hash(name,
sizeof(*h->lhash2),
numentries,
@@ -816,14 +899,30 @@
&h->lhash2_mask,
low_limit,
high_limit);
+ init_hashinfo_lhash2(h);
- for (i = 0; i <= h->lhash2_mask; i++) {
- spin_lock_init(&h->lhash2[i].lock);
- INIT_HLIST_HEAD(&h->lhash2[i].head);
- h->lhash2[i].count = 0;
- }
+ /* this one is used for source ports of outgoing connections */
+ table_perturb = kmalloc_array(INET_TABLE_PERTURB_SIZE,
+ sizeof(*table_perturb), GFP_KERNEL);
+ if (!table_perturb)
+ panic("TCP: failed to alloc table_perturb");
}
+int inet_hashinfo2_init_mod(struct inet_hashinfo *h)
+{
+ h->lhash2 = kmalloc_array(INET_LHTABLE_SIZE, sizeof(*h->lhash2), GFP_KERNEL);
+ if (!h->lhash2)
+ return -ENOMEM;
+
+ h->lhash2_mask = INET_LHTABLE_SIZE - 1;
+ /* INET_LHTABLE_SIZE must be a power of 2 */
+ BUG_ON(INET_LHTABLE_SIZE & h->lhash2_mask);
+
+ init_hashinfo_lhash2(h);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(inet_hashinfo2_init_mod);
+
int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo)
{
unsigned int locksz = sizeof(spinlock_t);
--
Gitblit v1.6.2