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

Pull networking fixes from David Miller:

 1) Must perform TXQ teardown before unregistering interfaces in
    mac80211, from Toke Høiland-Jørgensen.

 2) Don't allow creating mac80211_hwsim with less than one channel, from
    Johannes Berg.

 3) Division by zero in cfg80211, fix from Johannes Berg.

 4) Fix endian issue in tipc, from Haiqing Bai.

 5) BPF sockmap use-after-free fixes from Daniel Borkmann.

 6) Spectre-v1 in mac80211_hwsim, from Jinbum Park.

 7) Missing rhashtable_walk_exit() in tipc, from Cong Wang.

 8) Revert kvzalloc() conversion of AF_PACKET, it breaks mmap() when
    kvzalloc() tries to use kmalloc() pages. From Eric Dumazet.

 9) Fix deadlock in hv_netvsc, from Dexuan Cui.

10) Do not restart timewait timer on RST, from Florian Westphal.

11) Fix double lwstate refcount grab in ipv6, from Alexey Kodanev.

12) Unsolicit report count handling is off-by-one, fix from Hangbin Liu.

13) Sleep-in-atomic in cadence driver, from Jia-Ju Bai.

14) Respect ttl-inherit in ip6 tunnel driver, from Hangbin Liu.

15) Use-after-free in act_ife, fix from Cong Wang.

16) Missing hold to meta module in act_ife, from Vlad Buslov.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (91 commits)
  net: phy: sfp: Handle unimplemented hwmon limits and alarms
  net: sched: action_ife: take reference to meta module
  act_ife: fix a potential use-after-free
  net/mlx5: Fix SQ offset in QPs with small RQ
  tipc: correct spelling errors for tipc_topsrv_queue_evt() comments
  tipc: correct spelling errors for struct tipc_bc_base's comment
  bnxt_en: Do not adjust max_cp_rings by the ones used by RDMA.
  bnxt_en: Clean up unused functions.
  bnxt_en: Fix firmware signaled resource change logic in open.
  sctp: not traverse asoc trans list if non-ipv6 trans exists for ipv6_flowlabel
  sctp: fix invalid reference to the index variable of the iterator
  net/ibm/emac: wrong emac_calc_base call was used by typo
  net: sched: null actions array pointer before releasing action
  vhost: fix VHOST_GET_BACKEND_FEATURES ioctl request definition
  r8169: add support for NCube 8168 network card
  ip6_tunnel: respect ttl inherit for ip6tnl
  mac80211: shorten the IBSS debug messages
  mac80211: don't Tx a deauth frame if the AP forbade Tx
  mac80211: Fix station bandwidth setting after channel switch
  mac80211: fix a race between restart and CSA flows
  ...

1 files changed, 36 insertions, 28 deletions

diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index cf5195c7c331..488ef9663c01 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -236,7 +236,7 @@ static int bpf_tcp_init(struct sock *sk)
 }
 
 static void smap_release_sock(struct smap_psock *psock, struct sock *sock);
-static int free_start_sg(struct sock *sk, struct sk_msg_buff *md);
+static int free_start_sg(struct sock *sk, struct sk_msg_buff *md, bool charge);
 
 static void bpf_tcp_release(struct sock *sk)
 {
@@ -248,7 +248,7 @@ static void bpf_tcp_release(struct sock *sk)
                 goto out;
 
         if (psock->cork) {
-                free_start_sg(psock->sock, psock->cork);
+                free_start_sg(psock->sock, psock->cork, true);
                 kfree(psock->cork);
                 psock->cork = NULL;
         }
@@ -330,14 +330,14 @@ static void bpf_tcp_close(struct sock *sk, long timeout)
         close_fun = psock->save_close;
 
         if (psock->cork) {
-                free_start_sg(psock->sock, psock->cork);
+                free_start_sg(psock->sock, psock->cork, true);
                 kfree(psock->cork);
                 psock->cork = NULL;
         }
 
         list_for_each_entry_safe(md, mtmp, &psock->ingress, list) {
                 list_del(&md->list);
-                free_start_sg(psock->sock, md);
+                free_start_sg(psock->sock, md, true);
                 kfree(md);
         }
 
@@ -369,7 +369,7 @@ static void bpf_tcp_close(struct sock *sk, long timeout)
                         /* If another thread deleted this object skip deletion.
                          * The refcnt on psock may or may not be zero.
                          */
-                        if (l) {
+                        if (l && l == link) {
                                 hlist_del_rcu(&link->hash_node);
                                 smap_release_sock(psock, link->sk);
                                 free_htab_elem(htab, link);
@@ -570,14 +570,16 @@ static void free_bytes_sg(struct sock *sk, int bytes,
         md->sg_start = i;
 }
 
-static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md)
+static int free_sg(struct sock *sk, int start,
+                   struct sk_msg_buff *md, bool charge)
 {
         struct scatterlist *sg = md->sg_data;
         int i = start, free = 0;
 
         while (sg[i].length) {
                 free += sg[i].length;
-                sk_mem_uncharge(sk, sg[i].length);
+                if (charge)
+                        sk_mem_uncharge(sk, sg[i].length);
                 if (!md->skb)
                         put_page(sg_page(&sg[i]));
                 sg[i].length = 0;
@@ -594,9 +596,9 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md)
         return free;
 }
 
-static int free_start_sg(struct sock *sk, struct sk_msg_buff *md)
+static int free_start_sg(struct sock *sk, struct sk_msg_buff *md, bool charge)
 {
-        int free = free_sg(sk, md->sg_start, md);
+        int free = free_sg(sk, md->sg_start, md, charge);
 
         md->sg_start = md->sg_end;
         return free;
@@ -604,7 +606,7 @@ static int free_start_sg(struct sock *sk, struct sk_msg_buff *md)
 
 static int free_curr_sg(struct sock *sk, struct sk_msg_buff *md)
 {
-        return free_sg(sk, md->sg_curr, md);
+        return free_sg(sk, md->sg_curr, md, true);
 }
 
 static int bpf_map_msg_verdict(int _rc, struct sk_msg_buff *md)
@@ -718,7 +720,7 @@ static int bpf_tcp_ingress(struct sock *sk, int apply_bytes,
                 list_add_tail(&r->list, &psock->ingress);
                 sk->sk_data_ready(sk);
         } else {
-                free_start_sg(sk, r);
+                free_start_sg(sk, r, true);
                 kfree(r);
         }
 
@@ -752,14 +754,10 @@ static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send,
                 release_sock(sk);
         }
         smap_release_sock(psock, sk);
-        if (unlikely(err))
-                goto out;
-        return 0;
+        return err;
 out_rcu:
         rcu_read_unlock();
-out:
-        free_bytes_sg(NULL, send, md, false);
-        return err;
+        return 0;
 }
 
 static inline void bpf_md_init(struct smap_psock *psock)
@@ -822,7 +820,7 @@ more_data:
         case __SK_PASS:
                 err = bpf_tcp_push(sk, send, m, flags, true);
                 if (unlikely(err)) {
-                        *copied -= free_start_sg(sk, m);
+                        *copied -= free_start_sg(sk, m, true);
                         break;
                 }
 
@@ -845,16 +843,17 @@ more_data:
                 lock_sock(sk);
 
                 if (unlikely(err < 0)) {
-                        free_start_sg(sk, m);
+                        int free = free_start_sg(sk, m, false);
+
                         psock->sg_size = 0;
                         if (!cork)
-                                *copied -= send;
+                                *copied -= free;
                 } else {
                         psock->sg_size -= send;
                 }
 
                 if (cork) {
-                        free_start_sg(sk, m);
+                        free_start_sg(sk, m, true);
                         psock->sg_size = 0;
                         kfree(m);
                         m = NULL;
@@ -912,6 +911,8 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 
         if (unlikely(flags & MSG_ERRQUEUE))
                 return inet_recv_error(sk, msg, len, addr_len);
+        if (!skb_queue_empty(&sk->sk_receive_queue))
+                return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 
         rcu_read_lock();
         psock = smap_psock_sk(sk);
@@ -922,9 +923,6 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
                 goto out;
         rcu_read_unlock();
 
-        if (!skb_queue_empty(&sk->sk_receive_queue))
-                return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
-
         lock_sock(sk);
 bytes_ready:
         while (copied != len) {
@@ -1122,7 +1120,7 @@ wait_for_memory:
                 err = sk_stream_wait_memory(sk, &timeo);
                 if (err) {
                         if (m && m != psock->cork)
-                                free_start_sg(sk, m);
+                                free_start_sg(sk, m, true);
                         goto out_err;
                 }
         }
@@ -1464,10 +1462,16 @@ static void smap_destroy_psock(struct rcu_head *rcu)
         schedule_work(&psock->gc_work);
 }
 
+static bool psock_is_smap_sk(struct sock *sk)
+{
+        return inet_csk(sk)->icsk_ulp_ops == &bpf_tcp_ulp_ops;
+}
+
 static void smap_release_sock(struct smap_psock *psock, struct sock *sock)
 {
         if (refcount_dec_and_test(&psock->refcnt)) {
-                tcp_cleanup_ulp(sock);
+                if (psock_is_smap_sk(sock))
+                        tcp_cleanup_ulp(sock);
                 write_lock_bh(&sock->sk_callback_lock);
                 smap_stop_sock(psock, sock);
                 write_unlock_bh(&sock->sk_callback_lock);
@@ -1581,13 +1585,13 @@ static void smap_gc_work(struct work_struct *w)
                 bpf_prog_put(psock->bpf_tx_msg);
 
         if (psock->cork) {
-                free_start_sg(psock->sock, psock->cork);
+                free_start_sg(psock->sock, psock->cork, true);
                 kfree(psock->cork);
         }
 
         list_for_each_entry_safe(md, mtmp, &psock->ingress, list) {
                 list_del(&md->list);
-                free_start_sg(psock->sock, md);
+                free_start_sg(psock->sock, md, true);
                 kfree(md);
         }
 
@@ -1894,6 +1898,10 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
          * doesn't update user data.
          */
         if (psock) {
+                if (!psock_is_smap_sk(sock)) {
+                        err = -EBUSY;
+                        goto out_progs;
+                }
                 if (READ_ONCE(psock->bpf_parse) && parse) {
                         err = -EBUSY;
                         goto out_progs;