Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

tools/testing/selftests/net/forwarding/Makefile
  f62c5acc800e ("selftests/net/forwarding: add missing tests to Makefile")
  50fe062c806e ("selftests: forwarding: new test, verify host mdb entries")
https://lore.kernel.org/all/20220502111539.0b7e4621@canb.auug.org.au/

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 33 insertions, 18 deletions

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 1ba8ebc439f3..b65d074d9620 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -2403,9 +2403,10 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct
 			/* decrease mem now to avoid the memleak warning */
 			atomic_sub(struct_size(psl, sl_addr, psl->sl_max),
 				   &sk->sk_omem_alloc);
-			kfree_rcu(psl, rcu);
 		}
 		rcu_assign_pointer(pmc->sflist, newpsl);
+		if (psl)
+			kfree_rcu(psl, rcu);
 		psl = newpsl;
 	}
 	rv = 1;	/* > 0 for insert logic below if sl_count is 0 */
@@ -2507,11 +2508,13 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex)
 		/* decrease mem now to avoid the memleak warning */
 		atomic_sub(struct_size(psl, sl_addr, psl->sl_max),
 			   &sk->sk_omem_alloc);
-		kfree_rcu(psl, rcu);
-	} else
+	} else {
 		(void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode,
 			0, NULL, 0);
+	}
 	rcu_assign_pointer(pmc->sflist, newpsl);
+	if (psl)
+		kfree_rcu(psl, rcu);
 	pmc->sfmode = msf->imsf_fmode;
 	err = 0;
 done:
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 17440840a791..a5d57fa679ca 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -504,7 +504,7 @@ not_unique:
 	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);
 
@@ -726,15 +726,17 @@ EXPORT_SYMBOL_GPL(inet_unhash);
  * 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,
- * we use 256 instead to really give more isolation and
- * privacy, this only consumes 1 KB of kernel memory.
+ * RFC claims using TABLE_LENGTH=10 buckets gives an improvement, though
+ * attacks were since demonstrated, thus we use 65536 instead to really
+ * give more isolation and privacy, at the expense of 256kB of kernel
+ * memory.
  */
-#define INET_TABLE_PERTURB_SHIFT 8
-static u32 table_perturb[1 << INET_TABLE_PERTURB_SHIFT];
+#define INET_TABLE_PERTURB_SHIFT 16
+#define INET_TABLE_PERTURB_SIZE (1 << INET_TABLE_PERTURB_SHIFT)
+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 **))
 {
@@ -774,10 +776,13 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 	if (likely(remaining > 1))
 		remaining &= ~1U;
 
-	net_get_random_once(table_perturb, sizeof(table_perturb));
-	index = hash_32(port_offset, INET_TABLE_PERTURB_SHIFT);
+	net_get_random_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;
 
-	offset = (READ_ONCE(table_perturb[index]) + port_offset) % remaining;
 	/* In first pass we try ports of @low parity.
 	 * inet_csk_get_port() does the opposite choice.
 	 */
@@ -831,11 +836,12 @@ next_port:
 	return -EADDRNOTAVAIL;
 
 ok:
-	/* If our first attempt found a candidate, skip next candidate
-	 * in 1/16 of cases to add some noise.
+	/* 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.
 	 */
-	if (!i && !(prandom_u32() % 16))
-		i = 2;
+	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 */
@@ -859,7 +865,7 @@ ok:
 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);
@@ -909,6 +915,12 @@ void __init inet_hashinfo2_init(struct inet_hashinfo *h, const char *name,
 					    low_limit,
 					    high_limit);
 	init_hashinfo_lhash2(h);
+
+	/* 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)