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

Pull networking fixes from David Miller:

 1) Netlink socket dumping had several missing verifications and checks.

    In particular, address comparisons in the request byte code
    interpreter could access past the end of the address in the
    inet_request_sock.

    Also, address family and address prefix lengths were not validated
    properly at all.

    This means arbitrary applications can read past the end of certain
    kernel data structures.

    Fixes from Neal Cardwell.

 2) ip_check_defrag() operates in contexts where we're in the process
    of, or about to, input the packet into the real protocols
    (specifically macvlan and AF_PACKET snooping).

    Unfortunately, it does a pskb_may_pull() which can modify the
    backing packet data which is not legal if the SKB is shared.  It
    very much can be shared in this context.

    Deal with the possibility that the SKB is segmented by using
    skb_copy_bits().

    Fix from Johannes Berg based upon a report by Eric Leblond.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net:
  ipv4: ip_check_defrag must not modify skb before unsharing
  inet_diag: validate port comparison byte code to prevent unsafe reads
  inet_diag: avoid unsafe and nonsensical prefix matches in inet_diag_bc_run()
  inet_diag: validate byte code to prevent oops in inet_diag_bc_run()
  inet_diag: fix oops for IPv4 AF_INET6 TCP SYN-RECV state

2 files changed, 131 insertions, 42 deletions

diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 0c34bfa..e23e16d 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -44,6 +44,10 @@ struct inet_diag_entry {
 	u16 dport;
 	u16 family;
 	u16 userlocks;
+#if IS_ENABLED(CONFIG_IPV6)
+	struct in6_addr saddr_storage;	/* for IPv4-mapped-IPv6 addresses */
+	struct in6_addr daddr_storage;	/* for IPv4-mapped-IPv6 addresses */
+#endif
 };
 
 static DEFINE_MUTEX(inet_diag_table_mutex);
@@ -428,25 +432,31 @@ static int inet_diag_bc_run(const struct nlattr *_bc,
 				break;
 			}
 
-			if (cond->prefix_len == 0)
-				break;
-
 			if (op->code == INET_DIAG_BC_S_COND)
 				addr = entry->saddr;
 			else
 				addr = entry->daddr;
 
+			if (cond->family != AF_UNSPEC &&
+			    cond->family != entry->family) {
+				if (entry->family == AF_INET6 &&
+				    cond->family == AF_INET) {
+					if (addr[0] == 0 && addr[1] == 0 &&
+					    addr[2] == htonl(0xffff) &&
+					    bitstring_match(addr + 3,
+							    cond->addr,
+							    cond->prefix_len))
+						break;
+				}
+				yes = 0;
+				break;
+			}
+
+			if (cond->prefix_len == 0)
+				break;
 			if (bitstring_match(addr, cond->addr,
 					    cond->prefix_len))
 				break;
-			if (entry->family == AF_INET6 &&
-			    cond->family == AF_INET) {
-				if (addr[0] == 0 && addr[1] == 0 &&
-				    addr[2] == htonl(0xffff) &&
-				    bitstring_match(addr + 3, cond->addr,
-						    cond->prefix_len))
-					break;
-			}
 			yes = 0;
 			break;
 		}
@@ -509,6 +519,55 @@ static int valid_cc(const void *bc, int len, int cc)
 	return 0;
 }
 
+/* Validate an inet_diag_hostcond. */
+static bool valid_hostcond(const struct inet_diag_bc_op *op, int len,
+			   int *min_len)
+{
+	int addr_len;
+	struct inet_diag_hostcond *cond;
+
+	/* Check hostcond space. */
+	*min_len += sizeof(struct inet_diag_hostcond);
+	if (len < *min_len)
+		return false;
+	cond = (struct inet_diag_hostcond *)(op + 1);
+
+	/* Check address family and address length. */
+	switch (cond->family) {
+	case AF_UNSPEC:
+		addr_len = 0;
+		break;
+	case AF_INET:
+		addr_len = sizeof(struct in_addr);
+		break;
+	case AF_INET6:
+		addr_len = sizeof(struct in6_addr);
+		break;
+	default:
+		return false;
+	}
+	*min_len += addr_len;
+	if (len < *min_len)
+		return false;
+
+	/* Check prefix length (in bits) vs address length (in bytes). */
+	if (cond->prefix_len > 8 * addr_len)
+		return false;
+
+	return true;
+}
+
+/* Validate a port comparison operator. */
+static inline bool valid_port_comparison(const struct inet_diag_bc_op *op,
+					 int len, int *min_len)
+{
+	/* Port comparisons put the port in a follow-on inet_diag_bc_op. */
+	*min_len += sizeof(struct inet_diag_bc_op);
+	if (len < *min_len)
+		return false;
+	return true;
+}
+
 static int inet_diag_bc_audit(const void *bytecode, int bytecode_len)
 {
 	const void *bc = bytecode;
@@ -516,29 +575,39 @@ static int inet_diag_bc_audit(const void *bytecode, int bytecode_len)
 
 	while (len > 0) {
 		const struct inet_diag_bc_op *op = bc;
+		int min_len = sizeof(struct inet_diag_bc_op);
 
 //printk("BC: %d %d %d {%d} / %d\n", op->code, op->yes, op->no, op[1].no, len);
 		switch (op->code) {
-		case INET_DIAG_BC_AUTO:
 		case INET_DIAG_BC_S_COND:
 		case INET_DIAG_BC_D_COND:
+			if (!valid_hostcond(bc, len, &min_len))
+				return -EINVAL;
+			break;
 		case INET_DIAG_BC_S_GE:
 		case INET_DIAG_BC_S_LE:
 		case INET_DIAG_BC_D_GE:
 		case INET_DIAG_BC_D_LE:
-		case INET_DIAG_BC_JMP:
-			if (op->no < 4 || op->no > len + 4 || op->no & 3)
-				return -EINVAL;
-			if (op->no < len &&
-			    !valid_cc(bytecode, bytecode_len, len - op->no))
+			if (!valid_port_comparison(bc, len, &min_len))
 				return -EINVAL;
 			break;
+		case INET_DIAG_BC_AUTO:
+		case INET_DIAG_BC_JMP:
 		case INET_DIAG_BC_NOP:
 			break;
 		default:
 			return -EINVAL;
 		}
-		if (op->yes < 4 || op->yes > len + 4 || op->yes & 3)
+
+		if (op->code != INET_DIAG_BC_NOP) {
+			if (op->no < min_len || op->no > len + 4 || op->no & 3)
+				return -EINVAL;
+			if (op->no < len &&
+			    !valid_cc(bytecode, bytecode_len, len - op->no))
+				return -EINVAL;
+		}
+
+		if (op->yes < min_len || op->yes > len + 4 || op->yes & 3)
 			return -EINVAL;
 		bc  += op->yes;
 		len -= op->yes;
@@ -596,6 +665,36 @@ static int inet_twsk_diag_dump(struct inet_timewait_sock *tw,
 				   cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh);
 }
 
+/* Get the IPv4, IPv6, or IPv4-mapped-IPv6 local and remote addresses
+ * from a request_sock. For IPv4-mapped-IPv6 we must map IPv4 to IPv6.
+ */
+static inline void inet_diag_req_addrs(const struct sock *sk,
+				       const struct request_sock *req,
+				       struct inet_diag_entry *entry)
+{
+	struct inet_request_sock *ireq = inet_rsk(req);
+
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sk->sk_family == AF_INET6) {
+		if (req->rsk_ops->family == AF_INET6) {
+			entry->saddr = inet6_rsk(req)->loc_addr.s6_addr32;
+			entry->daddr = inet6_rsk(req)->rmt_addr.s6_addr32;
+		} else if (req->rsk_ops->family == AF_INET) {
+			ipv6_addr_set_v4mapped(ireq->loc_addr,
+					       &entry->saddr_storage);
+			ipv6_addr_set_v4mapped(ireq->rmt_addr,
+					       &entry->daddr_storage);
+			entry->saddr = entry->saddr_storage.s6_addr32;
+			entry->daddr = entry->daddr_storage.s6_addr32;
+		}
+	} else
+#endif
+	{
+		entry->saddr = &ireq->loc_addr;
+		entry->daddr = &ireq->rmt_addr;
+	}
+}
+
 static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk,
 			      struct request_sock *req,
 			      struct user_namespace *user_ns,
@@ -637,8 +736,10 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk,
 	r->idiag_inode = 0;
 #if IS_ENABLED(CONFIG_IPV6)
 	if (r->idiag_family == AF_INET6) {
-		*(struct in6_addr *)r->id.idiag_src = inet6_rsk(req)->loc_addr;
-		*(struct in6_addr *)r->id.idiag_dst = inet6_rsk(req)->rmt_addr;
+		struct inet_diag_entry entry;
+		inet_diag_req_addrs(sk, req, &entry);
+		memcpy(r->id.idiag_src, entry.saddr, sizeof(struct in6_addr));
+		memcpy(r->id.idiag_dst, entry.daddr, sizeof(struct in6_addr));
 	}
 #endif
 
@@ -691,18 +792,7 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk,
 				continue;
 
 			if (bc) {
-				entry.saddr =
-#if IS_ENABLED(CONFIG_IPV6)
-					(entry.family == AF_INET6) ?
-					inet6_rsk(req)->loc_addr.s6_addr32 :
-#endif
-					&ireq->loc_addr;
-				entry.daddr =
-#if IS_ENABLED(CONFIG_IPV6)
-					(entry.family == AF_INET6) ?
-					inet6_rsk(req)->rmt_addr.s6_addr32 :
-#endif
-					&ireq->rmt_addr;
+				inet_diag_req_addrs(sk, req, &entry);
 				entry.dport = ntohs(ireq->rmt_port);
 
 				if (!inet_diag_bc_run(bc, &entry))
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 448e685..8d5cc75 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -707,28 +707,27 @@ EXPORT_SYMBOL(ip_defrag);
 
 struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user)
 {
-	const struct iphdr *iph;
+	struct iphdr iph;
 	u32 len;
 
 	if (skb->protocol != htons(ETH_P_IP))
 		return skb;
 
-	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+	if (!skb_copy_bits(skb, 0, &iph, sizeof(iph)))
 		return skb;
 
-	iph = ip_hdr(skb);
-	if (iph->ihl < 5 || iph->version != 4)
+	if (iph.ihl < 5 || iph.version != 4)
 		return skb;
-	if (!pskb_may_pull(skb, iph->ihl*4))
-		return skb;
-	iph = ip_hdr(skb);
-	len = ntohs(iph->tot_len);
-	if (skb->len < len || len < (iph->ihl * 4))
+
+	len = ntohs(iph.tot_len);
+	if (skb->len < len || len < (iph.ihl * 4))
 		return skb;
 
-	if (ip_is_fragment(ip_hdr(skb))) {
+	if (ip_is_fragment(&iph)) {
 		skb = skb_share_check(skb, GFP_ATOMIC);
 		if (skb) {
+			if (!pskb_may_pull(skb, iph.ihl*4))
+				return skb;
 			if (pskb_trim_rcsum(skb, len))
 				return skb;
 			memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));