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

Dave writes:
  "Networking fixes:

  1) Fix multiqueue handling of coalesce timer in stmmac, from Jose
     Abreu.

   2) Fix memory corruption in NFC, from Suren Baghdasaryan.

   3) Don't write reserved bits in ravb driver, from Kazuya Mizuguchi.

   4) SMC bug fixes from Karsten Graul, YueHaibing, and Ursula Braun.

   5) Fix TX done race in mvpp2, from Antoine Tenart.

   6) ipv6 metrics leak, from Wei Wang.

   7) Adjust firmware version requirements in mlxsw, from Petr Machata.

   8) Fix autonegotiation on resume in r8169, from Heiner Kallweit.

   9) Fixed missing entries when dumping /proc/net/if_inet6, from Jeff
      Barnhill.

   10) Fix double free in devlink, from Dan Carpenter.

   11) Fix ethtool regression from UFO feature removal, from Maciej
       Żenczykowski.

   12) Fix drivers that have a ndo_poll_controller() that captures the
       cpu entirely on loaded hosts by trying to drain all rx and tx
       queues, from Eric Dumazet.

   13) Fix memory corruption with jumbo frames in aquantia driver, from
       Friedemann Gerold."

* gitolite.kernel.org:/pub/scm/linux/kernel/git/davem/net: (79 commits)
  net: mvneta: fix the remaining Rx descriptor unmapping issues
  ip_tunnel: be careful when accessing the inner header
  mpls: allow routes on ip6gre devices
  net: aquantia: memory corruption on jumbo frames
  tun: remove ndo_poll_controller
  nfp: remove ndo_poll_controller
  bnxt: remove ndo_poll_controller
  bnx2x: remove ndo_poll_controller
  mlx5: remove ndo_poll_controller
  mlx4: remove ndo_poll_controller
  i40evf: remove ndo_poll_controller
  ice: remove ndo_poll_controller
  igb: remove ndo_poll_controller
  ixgb: remove ndo_poll_controller
  fm10k: remove ndo_poll_controller
  ixgbevf: remove ndo_poll_controller
  ixgbe: remove ndo_poll_controller
  bonding: use netpoll_poll_dev() helper
  netpoll: make ndo_poll_controller() optional
  rds: Fix build regression.
  ...

1 files changed, 71 insertions, 20 deletions

diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index 488ef96..0a0f2ec 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -132,6 +132,7 @@ struct smap_psock {
 	struct work_struct gc_work;
 
 	struct proto *sk_proto;
+	void (*save_unhash)(struct sock *sk);
 	void (*save_close)(struct sock *sk, long timeout);
 	void (*save_data_ready)(struct sock *sk);
 	void (*save_write_space)(struct sock *sk);
@@ -143,6 +144,7 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
 static int bpf_tcp_sendpage(struct sock *sk, struct page *page,
 			    int offset, size_t size, int flags);
+static void bpf_tcp_unhash(struct sock *sk);
 static void bpf_tcp_close(struct sock *sk, long timeout);
 
 static inline struct smap_psock *smap_psock_sk(const struct sock *sk)
@@ -184,6 +186,7 @@ static void build_protos(struct proto prot[SOCKMAP_NUM_CONFIGS],
 			 struct proto *base)
 {
 	prot[SOCKMAP_BASE]			= *base;
+	prot[SOCKMAP_BASE].unhash		= bpf_tcp_unhash;
 	prot[SOCKMAP_BASE].close		= bpf_tcp_close;
 	prot[SOCKMAP_BASE].recvmsg		= bpf_tcp_recvmsg;
 	prot[SOCKMAP_BASE].stream_memory_read	= bpf_tcp_stream_read;
@@ -217,6 +220,7 @@ static int bpf_tcp_init(struct sock *sk)
 		return -EBUSY;
 	}
 
+	psock->save_unhash = sk->sk_prot->unhash;
 	psock->save_close = sk->sk_prot->close;
 	psock->sk_proto = sk->sk_prot;
 
@@ -305,30 +309,12 @@ static struct smap_psock_map_entry *psock_map_pop(struct sock *sk,
 	return e;
 }
 
-static void bpf_tcp_close(struct sock *sk, long timeout)
+static void bpf_tcp_remove(struct sock *sk, struct smap_psock *psock)
 {
-	void (*close_fun)(struct sock *sk, long timeout);
 	struct smap_psock_map_entry *e;
 	struct sk_msg_buff *md, *mtmp;
-	struct smap_psock *psock;
 	struct sock *osk;
 
-	lock_sock(sk);
-	rcu_read_lock();
-	psock = smap_psock_sk(sk);
-	if (unlikely(!psock)) {
-		rcu_read_unlock();
-		release_sock(sk);
-		return sk->sk_prot->close(sk, timeout);
-	}
-
-	/* The psock may be destroyed anytime after exiting the RCU critial
-	 * section so by the time we use close_fun the psock may no longer
-	 * be valid. However, bpf_tcp_close is called with the sock lock
-	 * held so the close hook and sk are still valid.
-	 */
-	close_fun = psock->save_close;
-
 	if (psock->cork) {
 		free_start_sg(psock->sock, psock->cork, true);
 		kfree(psock->cork);
@@ -379,6 +365,42 @@ static void bpf_tcp_close(struct sock *sk, long timeout)
 		kfree(e);
 		e = psock_map_pop(sk, psock);
 	}
+}
+
+static void bpf_tcp_unhash(struct sock *sk)
+{
+	void (*unhash_fun)(struct sock *sk);
+	struct smap_psock *psock;
+
+	rcu_read_lock();
+	psock = smap_psock_sk(sk);
+	if (unlikely(!psock)) {
+		rcu_read_unlock();
+		if (sk->sk_prot->unhash)
+			sk->sk_prot->unhash(sk);
+		return;
+	}
+	unhash_fun = psock->save_unhash;
+	bpf_tcp_remove(sk, psock);
+	rcu_read_unlock();
+	unhash_fun(sk);
+}
+
+static void bpf_tcp_close(struct sock *sk, long timeout)
+{
+	void (*close_fun)(struct sock *sk, long timeout);
+	struct smap_psock *psock;
+
+	lock_sock(sk);
+	rcu_read_lock();
+	psock = smap_psock_sk(sk);
+	if (unlikely(!psock)) {
+		rcu_read_unlock();
+		release_sock(sk);
+		return sk->sk_prot->close(sk, timeout);
+	}
+	close_fun = psock->save_close;
+	bpf_tcp_remove(sk, psock);
 	rcu_read_unlock();
 	release_sock(sk);
 	close_fun(sk, timeout);
@@ -2097,8 +2119,12 @@ static int sock_map_update_elem(struct bpf_map *map,
 		return -EINVAL;
 	}
 
+	/* ULPs are currently supported only for TCP sockets in ESTABLISHED
+	 * state.
+	 */
 	if (skops.sk->sk_type != SOCK_STREAM ||
-	    skops.sk->sk_protocol != IPPROTO_TCP) {
+	    skops.sk->sk_protocol != IPPROTO_TCP ||
+	    skops.sk->sk_state != TCP_ESTABLISHED) {
 		fput(socket->file);
 		return -EOPNOTSUPP;
 	}
@@ -2453,6 +2479,16 @@ static int sock_hash_update_elem(struct bpf_map *map,
 		return -EINVAL;
 	}
 
+	/* ULPs are currently supported only for TCP sockets in ESTABLISHED
+	 * state.
+	 */
+	if (skops.sk->sk_type != SOCK_STREAM ||
+	    skops.sk->sk_protocol != IPPROTO_TCP ||
+	    skops.sk->sk_state != TCP_ESTABLISHED) {
+		fput(socket->file);
+		return -EOPNOTSUPP;
+	}
+
 	lock_sock(skops.sk);
 	preempt_disable();
 	rcu_read_lock();
@@ -2543,10 +2579,22 @@ const struct bpf_map_ops sock_hash_ops = {
 	.map_check_btf = map_check_no_btf,
 };
 
+static bool bpf_is_valid_sock_op(struct bpf_sock_ops_kern *ops)
+{
+	return ops->op == BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB ||
+	       ops->op == BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB;
+}
 BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock,
 	   struct bpf_map *, map, void *, key, u64, flags)
 {
 	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	/* ULPs are currently supported only for TCP sockets in ESTABLISHED
+	 * state. This checks that the sock ops triggering the update is
+	 * one indicating we are (or will be soon) in an ESTABLISHED state.
+	 */
+	if (!bpf_is_valid_sock_op(bpf_sock))
+		return -EOPNOTSUPP;
 	return sock_map_ctx_update_elem(bpf_sock, map, key, flags);
 }
 
@@ -2565,6 +2613,9 @@ BPF_CALL_4(bpf_sock_hash_update, struct bpf_sock_ops_kern *, bpf_sock,
 	   struct bpf_map *, map, void *, key, u64, flags)
 {
 	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	if (!bpf_is_valid_sock_op(bpf_sock))
+		return -EOPNOTSUPP;
 	return sock_hash_ctx_update_elem(bpf_sock, map, key, flags);
 }