From: Eric Dumazet edumazet@google.com
commit 190cc82489f46f9d88e73c81a47e14f80a791e1a upstream
RFC 6056 (Recommendations for Transport-Protocol Port Randomization) provides good summary of why source selection needs extra care.
David Dworken reminded us that linux implements Algorithm 3 as described in RFC 6056 3.3.3
Quoting David : In the context of the web, this creates an interesting info leak where websites can count how many TCP connections a user's computer is establishing over time. For example, this allows a website to count exactly how many subresources a third party website loaded. This also allows: - Distinguishing between different users behind a VPN based on distinct source port ranges. - Tracking users over time across multiple networks. - Covert communication channels between different browsers/browser profiles running on the same computer - Tracking what applications are running on a computer based on the pattern of how fast source ports are getting incremented.
Section 3.3.4 describes an enhancement, that reduces attackers ability to use the basic information currently stored into the shared 'u32 hint'.
This change also decreases collision rate when multiple applications need to connect() to different destinations.
Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: David Dworken ddworken@google.com Cc: Willem de Bruijn willemb@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Stefan Ghinea stefan.ghinea@windriver.com --- net/ipv4/inet_hashtables.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-)
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index cbbeb0eea0c3..dbfcefc264d6 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -671,6 +671,17 @@ void inet_unhash(struct sock *sk) } 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, + * we use 256 instead to really give more isolation and + * privacy, this only consumes 1 KB of kernel memory. + */ +#define INET_TABLE_PERTURB_SHIFT 8 +static u32 table_perturb[1 << INET_TABLE_PERTURB_SHIFT]; + int __inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk, u32 port_offset, int (*check_established)(struct inet_timewait_death_row *, @@ -684,8 +695,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, 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, @@ -712,7 +723,10 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, if (likely(remaining > 1)) remaining &= ~1U;
- offset = (hint + port_offset) % remaining; + net_get_random_once(table_perturb, sizeof(table_perturb)); + index = hash_32(port_offset, INET_TABLE_PERTURB_SHIFT); + + 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. */ @@ -766,7 +780,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, return -EADDRNOTAVAIL;
ok: - hint += i + 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);
From: Willy Tarreau w@1wt.eu
commit b2d057560b8107c633b39aabe517ff9d93f285e3 upstream
SipHash replaced MD5 in secure_ipv{4,6}_port_ephemeral() via commit 7cd23e5300c1 ("secure_seq: use SipHash in place of MD5"), but the output remained truncated to 32-bit only. In order to exploit more bits from the hash, let's make the functions return the full 64-bit of siphash_3u32(). We also make sure the port offset calculation in __inet_hash_connect() remains done on 32-bit to avoid the need for div_u64_rem() and an extra cost on 32-bit systems.
Cc: Jason A. Donenfeld Jason@zx2c4.com Cc: Moshe Kol moshe.kol@mail.huji.ac.il Cc: Yossi Gilad yossi.gilad@mail.huji.ac.il Cc: Amit Klein aksecurity@gmail.com Reviewed-by: Eric Dumazet edumazet@google.com Signed-off-by: Willy Tarreau w@1wt.eu Signed-off-by: Jakub Kicinski kuba@kernel.org [SG: Adjusted context] Signed-off-by: Stefan Ghinea stefan.ghinea@windriver.com --- include/net/inet_hashtables.h | 2 +- include/net/secure_seq.h | 4 ++-- net/core/secure_seq.c | 4 ++-- net/ipv4/inet_hashtables.c | 10 ++++++---- net/ipv6/inet6_hashtables.c | 4 ++-- 5 files changed, 13 insertions(+), 11 deletions(-)
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index a1869a678944..a186c245a6f4 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -420,7 +420,7 @@ static inline void sk_rcv_saddr_set(struct sock *sk, __be32 addr) }
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 **)); diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h index d7d2495f83c2..dac91aa38c5a 100644 --- a/include/net/secure_seq.h +++ b/include/net/secure_seq.h @@ -4,8 +4,8 @@
#include <linux/types.h>
-u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); -u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, +u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); +u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport); u32 secure_tcp_seq(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport); diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 2f9796a1a63f..a1867c65ac63 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -97,7 +97,7 @@ u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, } EXPORT_SYMBOL(secure_tcpv6_seq);
-u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, +u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport) { const struct { @@ -147,7 +147,7 @@ u32 secure_tcp_seq(__be32 saddr, __be32 daddr, } EXPORT_SYMBOL_GPL(secure_tcp_seq);
-u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) +u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) { net_secret_init(); return siphash_4u32((__force u32)saddr, (__force u32)daddr, diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index dbfcefc264d6..959f4f0c8546 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -464,7 +464,7 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, 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);
@@ -683,7 +683,7 @@ EXPORT_SYMBOL_GPL(inet_unhash); static u32 table_perturb[1 << INET_TABLE_PERTURB_SHIFT];
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 **)) { @@ -726,7 +726,9 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, net_get_random_once(table_perturb, sizeof(table_perturb)); index = hash_32(port_offset, INET_TABLE_PERTURB_SHIFT);
- offset = (READ_ONCE(table_perturb[index]) + port_offset) % remaining; + offset = READ_ONCE(table_perturb[index]) + port_offset; + offset %= remaining; + /* In first pass we try ports of @low parity. * inet_csk_get_port() does the opposite choice. */ @@ -803,7 +805,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, 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); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index ab12e00f6bff..528c78bc920e 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -262,7 +262,7 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, return -EADDRNOTAVAIL; }
-static u32 inet6_sk_port_offset(const struct sock *sk) +static u64 inet6_sk_port_offset(const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk);
@@ -274,7 +274,7 @@ static u32 inet6_sk_port_offset(const struct sock *sk) int inet6_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 = inet6_sk_port_offset(sk);
linux-stable-mirror@lists.linaro.org