[PATCH AUTOSEL 4.19 44/81] ipvs: do not schedule icmp errors from tunnels

[PATCH AUTOSEL 4.19 44/81] ipvs: do not schedule icmp errors from tunnels

[Sasha Levin]

From: Julian Anastasov <ja@ssi.bg>

[ Upstream commit 0261ea1bd1eb0da5c0792a9119b8655cf33c80a3 ]

We can receive ICMP errors from client or from
tunneling real server. While the former can be
scheduled to real server, the latter should
not be scheduled, they are decapsulated only when
existing connection is found.

Fixes: 6044eeffafbe ("ipvs: attempt to schedule icmp packets")
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/netfilter/ipvs/ip_vs_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 3f963ea22277..a42c1bc7c698 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1647,7 +1647,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
 	if (!cp) {
 		int v;
 
-		if (!sysctl_schedule_icmp(ipvs))
+		if (ipip || !sysctl_schedule_icmp(ipvs))
 			return NF_ACCEPT;
 
 		if (!ip_vs_try_to_schedule(ipvs, AF_INET, skb, pd, &v, &cp, &ciph))
-- 
2.20.1

[PATCH AUTOSEL 4.19 45/81] netfilter: ctnetlink: don't use conntrack/expect object addresses as id

[Sasha Levin]

From: Florian Westphal <fw@strlen.de>

[ Upstream commit 3c79107631db1f7fd32cf3f7368e4672004a3010 ]

else, we leak the addresses to userspace via ctnetlink events
and dumps.

Compute an ID on demand based on the immutable parts of nf_conn struct.

Another advantage compared to using an address is that there is no
immediate re-use of the same ID in case the conntrack entry is freed and
reallocated again immediately.

Fixes: 3583240249ef ("[NETFILTER]: nf_conntrack_expect: kill unique ID")
Fixes: 7f85f914721f ("[NETFILTER]: nf_conntrack: kill unique ID")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/net/netfilter/nf_conntrack.h |  2 ++
 net/netfilter/nf_conntrack_core.c    | 35 ++++++++++++++++++++++++++++
 net/netfilter/nf_conntrack_netlink.c | 34 +++++++++++++++++++++++----
 3 files changed, 66 insertions(+), 5 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 7e012312cd61..f45141bdbb83 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -313,6 +313,8 @@ struct nf_conn *nf_ct_tmpl_alloc(struct net *net,
 				 gfp_t flags);
 void nf_ct_tmpl_free(struct nf_conn *tmpl);
 
+u32 nf_ct_get_id(const struct nf_conn *ct);
+
 static inline void
 nf_ct_set(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info info)
 {
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 9a249478abf2..27eff89fad01 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -25,6 +25,7 @@
 #include <linux/slab.h>
 #include <linux/random.h>
 #include <linux/jhash.h>
+#include <linux/siphash.h>
 #include <linux/err.h>
 #include <linux/percpu.h>
 #include <linux/moduleparam.h>
@@ -424,6 +425,40 @@ nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
 }
 EXPORT_SYMBOL_GPL(nf_ct_invert_tuple);
 
+/* Generate a almost-unique pseudo-id for a given conntrack.
+ *
+ * intentionally doesn't re-use any of the seeds used for hash
+ * table location, we assume id gets exposed to userspace.
+ *
+ * Following nf_conn items do not change throughout lifetime
+ * of the nf_conn after it has been committed to main hash table:
+ *
+ * 1. nf_conn address
+ * 2. nf_conn->ext address
+ * 3. nf_conn->master address (normally NULL)
+ * 4. tuple
+ * 5. the associated net namespace
+ */
+u32 nf_ct_get_id(const struct nf_conn *ct)
+{
+	static __read_mostly siphash_key_t ct_id_seed;
+	unsigned long a, b, c, d;
+
+	net_get_random_once(&ct_id_seed, sizeof(ct_id_seed));
+
+	a = (unsigned long)ct;
+	b = (unsigned long)ct->master ^ net_hash_mix(nf_ct_net(ct));
+	c = (unsigned long)ct->ext;
+	d = (unsigned long)siphash(&ct->tuplehash, sizeof(ct->tuplehash),
+				   &ct_id_seed);
+#ifdef CONFIG_64BIT
+	return siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &ct_id_seed);
+#else
+	return siphash_4u32((u32)a, (u32)b, (u32)c, (u32)d, &ct_id_seed);
+#endif
+}
+EXPORT_SYMBOL_GPL(nf_ct_get_id);
+
 static void
 clean_from_lists(struct nf_conn *ct)
 {
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 036207ecaf16..47e5a076522d 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -29,6 +29,7 @@
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
 #include <linux/slab.h>
+#include <linux/siphash.h>
 
 #include <linux/netfilter.h>
 #include <net/netlink.h>
@@ -487,7 +488,9 @@ static int ctnetlink_dump_ct_synproxy(struct sk_buff *skb, struct nf_conn *ct)
 
 static int ctnetlink_dump_id(struct sk_buff *skb, const struct nf_conn *ct)
 {
-	if (nla_put_be32(skb, CTA_ID, htonl((unsigned long)ct)))
+	__be32 id = (__force __be32)nf_ct_get_id(ct);
+
+	if (nla_put_be32(skb, CTA_ID, id))
 		goto nla_put_failure;
 	return 0;
 
@@ -1275,8 +1278,9 @@ static int ctnetlink_del_conntrack(struct net *net, struct sock *ctnl,
 	}
 
 	if (cda[CTA_ID]) {
-		u_int32_t id = ntohl(nla_get_be32(cda[CTA_ID]));
-		if (id != (u32)(unsigned long)ct) {
+		__be32 id = nla_get_be32(cda[CTA_ID]);
+
+		if (id != (__force __be32)nf_ct_get_id(ct)) {
 			nf_ct_put(ct);
 			return -ENOENT;
 		}
@@ -2675,6 +2679,25 @@ static int ctnetlink_exp_dump_mask(struct sk_buff *skb,
 
 static const union nf_inet_addr any_addr;
 
+static __be32 nf_expect_get_id(const struct nf_conntrack_expect *exp)
+{
+	static __read_mostly siphash_key_t exp_id_seed;
+	unsigned long a, b, c, d;
+
+	net_get_random_once(&exp_id_seed, sizeof(exp_id_seed));
+
+	a = (unsigned long)exp;
+	b = (unsigned long)exp->helper;
+	c = (unsigned long)exp->master;
+	d = (unsigned long)siphash(&exp->tuple, sizeof(exp->tuple), &exp_id_seed);
+
+#ifdef CONFIG_64BIT
+	return (__force __be32)siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &exp_id_seed);
+#else
+	return (__force __be32)siphash_4u32((u32)a, (u32)b, (u32)c, (u32)d, &exp_id_seed);
+#endif
+}
+
 static int
 ctnetlink_exp_dump_expect(struct sk_buff *skb,
 			  const struct nf_conntrack_expect *exp)
@@ -2722,7 +2745,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb,
 	}
 #endif
 	if (nla_put_be32(skb, CTA_EXPECT_TIMEOUT, htonl(timeout)) ||
-	    nla_put_be32(skb, CTA_EXPECT_ID, htonl((unsigned long)exp)) ||
+	    nla_put_be32(skb, CTA_EXPECT_ID, nf_expect_get_id(exp)) ||
 	    nla_put_be32(skb, CTA_EXPECT_FLAGS, htonl(exp->flags)) ||
 	    nla_put_be32(skb, CTA_EXPECT_CLASS, htonl(exp->class)))
 		goto nla_put_failure;
@@ -3027,7 +3050,8 @@ static int ctnetlink_get_expect(struct net *net, struct sock *ctnl,
 
 	if (cda[CTA_EXPECT_ID]) {
 		__be32 id = nla_get_be32(cda[CTA_EXPECT_ID]);
-		if (ntohl(id) != (u32)(unsigned long)exp) {
+
+		if (id != nf_expect_get_id(exp)) {
 			nf_ct_expect_put(exp);
 			return -ENOENT;
 		}
-- 
2.20.1

[PATCH AUTOSEL 4.19 46/81] netfilter: nf_tables: prevent shift wrap in nft_chain_parse_hook()

[Sasha Levin]

From: Dan Carpenter <dan.carpenter@oracle.com>

[ Upstream commit 33d1c018179d0a30c39cc5f1682b77867282694b ]

I believe that "hook->num" can be up to UINT_MAX.  Shifting more than
31 bits would is undefined in C but in practice it would lead to shift
wrapping.  That would lead to an array overflow in nf_tables_addchain():

	ops->hook       = hook.type->hooks[ops->hooknum];

Fixes: fe19c04ca137 ("netfilter: nf_tables: remove nhooks field from struct nft_af_info")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/netfilter/nf_tables_api.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 1af54119bafc..f272f9538c44 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1496,7 +1496,7 @@ static int nft_chain_parse_hook(struct net *net,
 		if (IS_ERR(type))
 			return PTR_ERR(type);
 	}
-	if (!(type->hook_mask & (1 << hook->num)))
+	if (hook->num > NF_MAX_HOOKS || !(type->hook_mask & (1 << hook->num)))
 		return -EOPNOTSUPP;
 
 	if (type->type == NFT_CHAIN_T_NAT &&
-- 
2.20.1

[PATCH AUTOSEL 4.19 52/81] netfilter: fix nf_l4proto_log_invalid to log invalid packets

[Sasha Levin]

From: Andrei Vagin <avagin@gmail.com>

[ Upstream commit d48668052b2603b6262459625c86108c493588dd ]

It doesn't log a packet if sysctl_log_invalid isn't equal to protonum
OR sysctl_log_invalid isn't equal to IPPROTO_RAW. This sentence is
always true. I believe we need to replace OR to AND.

Cc: Florian Westphal <fw@strlen.de>
Fixes: c4f3db1595827 ("netfilter: conntrack: add and use nf_l4proto_log_invalid")
Signed-off-by: Andrei Vagin <avagin@gmail.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/netfilter/nf_conntrack_proto.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index 51c5d7eec0a3..e903ef9b96cf 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -86,7 +86,7 @@ void nf_l4proto_log_invalid(const struct sk_buff *skb,
 	struct va_format vaf;
 	va_list args;
 
-	if (net->ct.sysctl_log_invalid != protonum ||
+	if (net->ct.sysctl_log_invalid != protonum &&
 	    net->ct.sysctl_log_invalid != IPPROTO_RAW)
 		return;
 
-- 
2.20.1

[PATCH AUTOSEL 4.19 70/81] netfilter: nf_tables: use-after-free in dynamic operations

[Sasha Levin]

From: Pablo Neira Ayuso <pablo@netfilter.org>

[ Upstream commit 3f3a390dbd59d236f62cff8e8b20355ef7069e3d ]

Smatch reports:

       net/netfilter/nf_tables_api.c:2167 nf_tables_expr_destroy()
        error: dereferencing freed memory 'expr->ops'

net/netfilter/nf_tables_api.c
    2162 static void nf_tables_expr_destroy(const struct nft_ctx *ctx,
    2163                                   struct nft_expr *expr)
    2164 {
    2165        if (expr->ops->destroy)
    2166                expr->ops->destroy(ctx, expr);
                                                ^^^^
--> 2167        module_put(expr->ops->type->owner);
                           ^^^^^^^^^
    2168 }

Smatch says there are three functions which free expr->ops.

Fixes: b8e204006340 ("netfilter: nft_compat: use .release_ops and remove list of extension")
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
---
 net/netfilter/nf_tables_api.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index f272f9538c44..ef7ff13a7b99 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2113,9 +2113,11 @@ static int nf_tables_newexpr(const struct nft_ctx *ctx,
 static void nf_tables_expr_destroy(const struct nft_ctx *ctx,
 				   struct nft_expr *expr)
 {
+	const struct nft_expr_type *type = expr->ops->type;
+
 	if (expr->ops->destroy)
 		expr->ops->destroy(ctx, expr);
-	module_put(expr->ops->type->owner);
+	module_put(type->owner);
 }
 
 struct nft_expr *nft_expr_init(const struct nft_ctx *ctx,
-- 
2.20.1

[PATCH AUTOSEL 4.19 71/81] netfilter: nf_tables: add missing ->release_ops() in error path of newrule()

[Sasha Levin]

From: Taehee Yoo <ap420073@gmail.com>

[ Upstream commit b25a31bf0ca091aa8bdb9ab329b0226257568bbe ]

->release_ops() callback releases resources and this is used in error path.
If nf_tables_newrule() fails after ->select_ops(), it should release
resources. but it can not call ->destroy() because that should be called
after ->init().
At this point, ->release_ops() should be used for releasing resources.

Test commands:
   modprobe -rv xt_tcpudp
   iptables-nft -I INPUT -m tcp   <-- error command
   lsmod

Result:
   Module                  Size  Used by
   xt_tcpudp              20480  2      <-- it should be 0

Fixes: b8e204006340 ("netfilter: nft_compat: use .release_ops and remove list of extension")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
---
 net/netfilter/nf_tables_api.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index ef7ff13a7b99..ebfcfe1dcbdb 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2719,8 +2719,11 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 	nf_tables_rule_release(&ctx, rule);
 err1:
 	for (i = 0; i < n; i++) {
-		if (info[i].ops != NULL)
+		if (info[i].ops) {
 			module_put(info[i].ops->type->owner);
+			if (info[i].ops->type->release_ops)
+				info[i].ops->type->release_ops(info[i].ops);
+		}
 	}
 	kvfree(info);
 	return err;
-- 
2.20.1