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

Pull networking fixes from David Miller:
 "Lots of fixes, here goes:

   1) NULL deref in qtnfmac, from Gustavo A. R. Silva.

   2) Kernel oops when fw download fails in rtlwifi, from Ping-Ke Shih.

   3) Lost completion messages in AF_XDP, from Magnus Karlsson.

   4) Correct bogus self-assignment in rhashtable, from Rishabh
      Bhatnagar.

   5) Fix regression in ipv6 route append handling, from David Ahern.

   6) Fix masking in __set_phy_supported(), from Heiner Kallweit.

   7) Missing module owner set in x_tables icmp, from Florian Westphal.

   8) liquidio's timeouts are HZ dependent, fix from Nicholas Mc Guire.

   9) Link setting fixes for sh_eth and ravb, from Vladimir Zapolskiy.

  10) Fix NULL deref when using chains in act_csum, from Davide Caratti.

  11) XDP_REDIRECT needs to check if the interface is up and whether the
      MTU is sufficient. From Toshiaki Makita.

  12) Net diag can do a double free when killing TCP_NEW_SYN_RECV
      connections, from Lorenzo Colitti.

  13) nf_defrag in ipv6 can unnecessarily hold onto dst entries for a
      full minute, delaying device unregister. From Eric Dumazet.

  14) Update MAC entries in the correct order in ixgbe, from Alexander
      Duyck.

  15) Don't leave partial mangles bpf program in jit_subprogs, from
      Daniel Borkmann.

  16) Fix pfmemalloc SKB state propagation, from Stefano Brivio.

  17) Fix ACK handling in DCTCP congestion control, from Yuchung Cheng.

  18) Use after free in tun XDP_TX, from Toshiaki Makita.

  19) Stale ipv6 header pointer in ipv6 gre code, from Prashant Bhole.

  20) Don't reuse remainder of RX page when XDP is set in mlx4, from
      Saeed Mahameed.

  21) Fix window probe handling of TCP rapair sockets, from Stefan
      Baranoff.

  22) Missing socket locking in smc_ioctl(), from Ursula Braun.

  23) IPV6_ILA needs DST_CACHE, from Arnd Bergmann.

  24) Spectre v1 fix in cxgb3, from Gustavo A. R. Silva.

  25) Two spots in ipv6 do a rol32() on a hash value but ignore the
      result. Fixes from Colin Ian King"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (176 commits)
  tcp: identify cryptic messages as TCP seq # bugs
  ptp: fix missing break in switch
  hv_netvsc: Fix napi reschedule while receive completion is busy
  MAINTAINERS: Drop inactive Vitaly Bordug's email
  net: cavium: Add fine-granular dependencies on PCI
  net: qca_spi: Fix log level if probe fails
  net: qca_spi: Make sure the QCA7000 reset is triggered
  net: qca_spi: Avoid packet drop during initial sync
  ipv6: fix useless rol32 call on hash
  ipv6: sr: fix useless rol32 call on hash
  net: sched: Using NULL instead of plain integer
  net: usb: asix: replace mii_nway_restart in resume path
  net: cxgb3_main: fix potential Spectre v1
  lib/rhashtable: consider param->min_size when setting initial table size
  net/smc: reset recv timeout after clc handshake
  net/smc: add error handling for get_user()
  net/smc: optimize consumer cursor updates
  net/nfc: Avoid stalls when nfc_alloc_send_skb() returned NULL.
  ipv6: ila: select CONFIG_DST_CACHE
  net: usb: rtl8150: demote allmulti message to dev_dbg()
  ...

6 files changed, 69 insertions, 42 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 2d49d18b793a..e016ac3afa24 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -991,16 +991,13 @@ static void btf_int_bits_seq_show(const struct btf *btf,
 				  void *data, u8 bits_offset,
 				  struct seq_file *m)
 {
+	u16 left_shift_bits, right_shift_bits;
 	u32 int_data = btf_type_int(t);
 	u16 nr_bits = BTF_INT_BITS(int_data);
 	u16 total_bits_offset;
 	u16 nr_copy_bytes;
 	u16 nr_copy_bits;
-	u8 nr_upper_bits;
-	union {
-		u64 u64_num;
-		u8  u8_nums[8];
-	} print_num;
+	u64 print_num;
 
 	total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data);
 	data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
@@ -1008,21 +1005,20 @@ static void btf_int_bits_seq_show(const struct btf *btf,
 	nr_copy_bits = nr_bits + bits_offset;
 	nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits);
 
-	print_num.u64_num = 0;
-	memcpy(&print_num.u64_num, data, nr_copy_bytes);
+	print_num = 0;
+	memcpy(&print_num, data, nr_copy_bytes);
 
-	/* Ditch the higher order bits */
-	nr_upper_bits = BITS_PER_BYTE_MASKED(nr_copy_bits);
-	if (nr_upper_bits) {
-		/* We need to mask out some bits of the upper byte. */
-		u8 mask = (1 << nr_upper_bits) - 1;
+#ifdef __BIG_ENDIAN_BITFIELD
+	left_shift_bits = bits_offset;
+#else
+	left_shift_bits = BITS_PER_U64 - nr_copy_bits;
+#endif
+	right_shift_bits = BITS_PER_U64 - nr_bits;
 
-		print_num.u8_nums[nr_copy_bytes - 1] &= mask;
-	}
-
-	print_num.u64_num >>= bits_offset;
+	print_num <<= left_shift_bits;
+	print_num >>= right_shift_bits;
 
-	seq_printf(m, "0x%llx", print_num.u64_num);
+	seq_printf(m, "0x%llx", print_num);
 }
 
 static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 642c97f6d1b8..d361fc1e3bf3 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -334,10 +334,15 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
 {
 	struct net_device *dev = dst->dev;
 	struct xdp_frame *xdpf;
+	int err;
 
 	if (!dev->netdev_ops->ndo_xdp_xmit)
 		return -EOPNOTSUPP;
 
+	err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
+	if (unlikely(err))
+		return err;
+
 	xdpf = convert_to_xdp_frame(xdp);
 	if (unlikely(!xdpf))
 		return -EOVERFLOW;
@@ -350,7 +355,7 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
 {
 	int err;
 
-	err = __xdp_generic_ok_fwd_dev(skb, dst->dev);
+	err = xdp_ok_fwd_dev(dst->dev, skb->len);
 	if (unlikely(err))
 		return err;
 	skb->dev = dst->dev;
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 3ca2198a6d22..513d9dfcf4ee 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -747,13 +747,15 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 				 * old element will be freed immediately.
 				 * Otherwise return an error
 				 */
-				atomic_dec(&htab->count);
-				return ERR_PTR(-E2BIG);
+				l_new = ERR_PTR(-E2BIG);
+				goto dec_count;
 			}
 		l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN,
 				     htab->map.numa_node);
-		if (!l_new)
-			return ERR_PTR(-ENOMEM);
+		if (!l_new) {
+			l_new = ERR_PTR(-ENOMEM);
+			goto dec_count;
+		}
 	}
 
 	memcpy(l_new->key, key, key_size);
@@ -766,7 +768,8 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 						  GFP_ATOMIC | __GFP_NOWARN);
 			if (!pptr) {
 				kfree(l_new);
-				return ERR_PTR(-ENOMEM);
+				l_new = ERR_PTR(-ENOMEM);
+				goto dec_count;
 			}
 		}
 
@@ -780,6 +783,9 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 
 	l_new->hash = hash;
 	return l_new;
+dec_count:
+	atomic_dec(&htab->count);
+	return l_new;
 }
 
 static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old,
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index cf7b6a6dbd1f..98fb7938beea 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -312,10 +312,12 @@ static void bpf_tcp_close(struct sock *sk, long timeout)
 	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);
 	}
 
@@ -371,6 +373,7 @@ static void bpf_tcp_close(struct sock *sk, long timeout)
 		e = psock_map_pop(sk, psock);
 	}
 	rcu_read_unlock();
+	release_sock(sk);
 	close_fun(sk, timeout);
 }
 
@@ -568,7 +571,8 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md)
 	while (sg[i].length) {
 		free += sg[i].length;
 		sk_mem_uncharge(sk, sg[i].length);
-		put_page(sg_page(&sg[i]));
+		if (!md->skb)
+			put_page(sg_page(&sg[i]));
 		sg[i].length = 0;
 		sg[i].page_link = 0;
 		sg[i].offset = 0;
@@ -577,6 +581,8 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md)
 		if (i == MAX_SKB_FRAGS)
 			i = 0;
 	}
+	if (md->skb)
+		consume_skb(md->skb);
 
 	return free;
 }
@@ -1230,7 +1236,7 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb)
 	 */
 	TCP_SKB_CB(skb)->bpf.sk_redir = NULL;
 	skb->sk = psock->sock;
-	bpf_compute_data_pointers(skb);
+	bpf_compute_data_end_sk_skb(skb);
 	preempt_disable();
 	rc = (*prog->bpf_func)(skb, prog->insnsi);
 	preempt_enable();
@@ -1485,7 +1491,7 @@ static int smap_parse_func_strparser(struct strparser *strp,
 	 * any socket yet.
 	 */
 	skb->sk = psock->sock;
-	bpf_compute_data_pointers(skb);
+	bpf_compute_data_end_sk_skb(skb);
 	rc = (*prog->bpf_func)(skb, prog->insnsi);
 	skb->sk = NULL;
 	rcu_read_unlock();
@@ -1896,7 +1902,7 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
 		e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN);
 		if (!e) {
 			err = -ENOMEM;
-			goto out_progs;
+			goto out_free;
 		}
 	}
 
@@ -2069,7 +2075,13 @@ static int sock_map_update_elem(struct bpf_map *map,
 		return -EOPNOTSUPP;
 	}
 
+	lock_sock(skops.sk);
+	preempt_disable();
+	rcu_read_lock();
 	err = sock_map_ctx_update_elem(&skops, map, key, flags);
+	rcu_read_unlock();
+	preempt_enable();
+	release_sock(skops.sk);
 	fput(socket->file);
 	return err;
 }
@@ -2342,7 +2354,10 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 	if (err)
 		goto err;
 
-	/* bpf_map_update_elem() can be called in_irq() */
+	/* psock is valid here because otherwise above *ctx_update_elem would
+	 * have thrown an error. It is safe to skip error check.
+	 */
+	psock = smap_psock_sk(sock);
 	raw_spin_lock_bh(&b->lock);
 	l_old = lookup_elem_raw(head, hash, key, key_size);
 	if (l_old && map_flags == BPF_NOEXIST) {
@@ -2360,12 +2375,6 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 		goto bucket_err;
 	}
 
-	psock = smap_psock_sk(sock);
-	if (unlikely(!psock)) {
-		err = -EINVAL;
-		goto bucket_err;
-	}
-
 	rcu_assign_pointer(e->hash_link, l_new);
 	rcu_assign_pointer(e->htab,
 			   container_of(map, struct bpf_htab, map));
@@ -2388,12 +2397,10 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 	raw_spin_unlock_bh(&b->lock);
 	return 0;
 bucket_err:
+	smap_release_sock(psock, sock);
 	raw_spin_unlock_bh(&b->lock);
 err:
 	kfree(e);
-	psock = smap_psock_sk(sock);
-	if (psock)
-		smap_release_sock(psock, sock);
 	return err;
 }
 
@@ -2415,7 +2422,13 @@ static int sock_hash_update_elem(struct bpf_map *map,
 		return -EINVAL;
 	}
 
+	lock_sock(skops.sk);
+	preempt_disable();
+	rcu_read_lock();
 	err = sock_hash_ctx_update_elem(&skops, map, key, flags);
+	rcu_read_unlock();
+	preempt_enable();
+	release_sock(skops.sk);
 	fput(socket->file);
 	return err;
 }
@@ -2472,10 +2485,8 @@ struct sock  *__sock_hash_lookup_elem(struct bpf_map *map, void *key)
 	b = __select_bucket(htab, hash);
 	head = &b->head;
 
-	raw_spin_lock_bh(&b->lock);
 	l = lookup_elem_raw(head, hash, key, key_size);
 	sk = l ? l->sk : NULL;
-	raw_spin_unlock_bh(&b->lock);
 	return sk;
 }
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index d10ecd78105f..a31a1ba0f8ea 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -735,7 +735,9 @@ static int map_update_elem(union bpf_attr *attr)
 	if (bpf_map_is_dev_bound(map)) {
 		err = bpf_map_offload_update_elem(map, key, value, attr->flags);
 		goto out;
-	} else if (map->map_type == BPF_MAP_TYPE_CPUMAP) {
+	} else if (map->map_type == BPF_MAP_TYPE_CPUMAP ||
+		   map->map_type == BPF_MAP_TYPE_SOCKHASH ||
+		   map->map_type == BPF_MAP_TYPE_SOCKMAP) {
 		err = map->ops->map_update_elem(map, key, value, attr->flags);
 		goto out;
 	}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9e2bf834f13a..63aaac52a265 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5430,6 +5430,10 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		if (insn->code != (BPF_JMP | BPF_CALL) ||
 		    insn->src_reg != BPF_PSEUDO_CALL)
 			continue;
+		/* Upon error here we cannot fall back to interpreter but
+		 * need a hard reject of the program. Thus -EFAULT is
+		 * propagated in any case.
+		 */
 		subprog = find_subprog(env, i + insn->imm + 1);
 		if (subprog < 0) {
 			WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
@@ -5450,7 +5454,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 
 	func = kcalloc(env->subprog_cnt, sizeof(prog), GFP_KERNEL);
 	if (!func)
-		return -ENOMEM;
+		goto out_undo_insn;
 
 	for (i = 0; i < env->subprog_cnt; i++) {
 		subprog_start = subprog_end;
@@ -5515,7 +5519,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		tmp = bpf_int_jit_compile(func[i]);
 		if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) {
 			verbose(env, "JIT doesn't support bpf-to-bpf calls\n");
-			err = -EFAULT;
+			err = -ENOTSUPP;
 			goto out_free;
 		}
 		cond_resched();
@@ -5552,6 +5556,7 @@ out_free:
 		if (func[i])
 			bpf_jit_free(func[i]);
 	kfree(func);
+out_undo_insn:
 	/* cleanup main prog to be interpreted */
 	prog->jit_requested = 0;
 	for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
@@ -5578,6 +5583,8 @@ static int fixup_call_args(struct bpf_verifier_env *env)
 		err = jit_subprogs(env);
 		if (err == 0)
 			return 0;
+		if (err == -EFAULT)
+			return err;
 	}
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
 	for (i = 0; i < prog->len; i++, insn++) {