Merge tag 'net-5.13-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Networking fixes for 5.13-rc4, including fixes from bpf, netfilter,
  can and wireless trees. Notably including fixes for the recently
  announced "FragAttacks" WiFi vulnerabilities. Rather large batch,
  touching some core parts of the stack, too, but nothing hair-raising.

  Current release - regressions:

   - tipc: make node link identity publish thread safe

   - dsa: felix: re-enable TAS guard band mode

   - stmmac: correct clocks enabled in stmmac_vlan_rx_kill_vid()

   - stmmac: fix system hang if change mac address after interface
     ifdown

  Current release - new code bugs:

   - mptcp: avoid OOB access in setsockopt()

   - bpf: Fix nested bpf_bprintf_prepare with more per-cpu buffers

   - ethtool: stats: fix a copy-paste error - init correct array size

  Previous releases - regressions:

   - sched: fix packet stuck problem for lockless qdisc

   - net: really orphan skbs tied to closing sk

   - mlx4: fix EEPROM dump support

   - bpf: fix alu32 const subreg bound tracking on bitwise operations

   - bpf: fix mask direction swap upon off reg sign change

   - bpf, offload: reorder offload callback 'prepare' in verifier

   - stmmac: Fix MAC WoL not working if PHY does not support WoL

   - packetmmap: fix only tx timestamp on request

   - tipc: skb_linearize the head skb when reassembling msgs

  Previous releases - always broken:

   - mac80211: address recent "FragAttacks" vulnerabilities

   - mac80211: do not accept/forward invalid EAPOL frames

   - mptcp: avoid potential error message floods

   - bpf, ringbuf: deny reserve of buffers larger than ringbuf to
     prevent out of buffer writes

   - bpf: forbid trampoline attach for functions with variable arguments

   - bpf: add deny list of functions to prevent inf recursion of tracing
     programs

   - tls splice: check SPLICE_F_NONBLOCK instead of MSG_DONTWAIT

   - can: isotp: prevent race between isotp_bind() and
     isotp_setsockopt()

   - netfilter: nft_set_pipapo_avx2: Add irq_fpu_usable() check,
     fallback to non-AVX2 version

  Misc:

   - bpf: add kconfig knob for disabling unpriv bpf by default"

* tag 'net-5.13-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (172 commits)
  net: phy: Document phydev::dev_flags bits allocation
  mptcp: validate 'id' when stopping the ADD_ADDR retransmit timer
  mptcp: avoid error message on infinite mapping
  mptcp: drop unconditional pr_warn on bad opt
  mptcp: avoid OOB access in setsockopt()
  nfp: update maintainer and mailing list addresses
  net: mvpp2: add buffer header handling in RX
  bnx2x: Fix missing error code in bnx2x_iov_init_one()
  net: zero-initialize tc skb extension on allocation
  net: hns: Fix kernel-doc
  sctp: fix the proc_handler for sysctl encap_port
  sctp: add the missing setting for asoc encap_port
  bpf, selftests: Adjust few selftest result_unpriv outcomes
  bpf: No need to simulate speculative domain for immediates
  bpf: Fix mask direction swap upon off reg sign change
  bpf: Wrap aux data inside bpf_sanitize_info container
  bpf: Fix BPF_LSM kconfig symbol dependency
  selftests/bpf: Add test for l3 use of bpf_redirect_peer
  bpftool: Add sock_release help info for cgroup attach/prog load command
  net: dsa: microchip: enable phy errata workaround on 9567
  ...

3 files changed, 29 insertions, 9 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 222b1d322c96..ef8cf7619baf 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3853,7 +3853,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 
 	if (q->flags & TCQ_F_NOLOCK) {
 		rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
-		qdisc_run(q);
+		if (likely(!netif_xmit_frozen_or_stopped(txq)))
+			qdisc_run(q);
 
 		if (unlikely(to_free))
 			kfree_skb_list(to_free);
@@ -5025,25 +5026,43 @@ static __latent_entropy void net_tx_action(struct softirq_action *h)
 		sd->output_queue_tailp = &sd->output_queue;
 		local_irq_enable();
 
+		rcu_read_lock();
+
 		while (head) {
 			struct Qdisc *q = head;
 			spinlock_t *root_lock = NULL;
 
 			head = head->next_sched;
 
-			if (!(q->flags & TCQ_F_NOLOCK)) {
-				root_lock = qdisc_lock(q);
-				spin_lock(root_lock);
-			}
 			/* We need to make sure head->next_sched is read
 			 * before clearing __QDISC_STATE_SCHED
 			 */
 			smp_mb__before_atomic();
+
+			if (!(q->flags & TCQ_F_NOLOCK)) {
+				root_lock = qdisc_lock(q);
+				spin_lock(root_lock);
+			} else if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED,
+						     &q->state))) {
+				/* There is a synchronize_net() between
+				 * STATE_DEACTIVATED flag being set and
+				 * qdisc_reset()/some_qdisc_is_busy() in
+				 * dev_deactivate(), so we can safely bail out
+				 * early here to avoid data race between
+				 * qdisc_deactivate() and some_qdisc_is_busy()
+				 * for lockless qdisc.
+				 */
+				clear_bit(__QDISC_STATE_SCHED, &q->state);
+				continue;
+			}
+
 			clear_bit(__QDISC_STATE_SCHED, &q->state);
 			qdisc_run(q);
 			if (root_lock)
 				spin_unlock(root_lock);
 		}
+
+		rcu_read_unlock();
 	}
 
 	xfrm_dev_backlog(sd);
diff --git a/net/core/filter.c b/net/core/filter.c
index cae56d08a670..65ab4e21c087 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3784,6 +3784,7 @@ static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room,
 		__skb_push(skb, head_room);
 		memset(skb->data, 0, head_room);
 		skb_reset_mac_header(skb);
+		skb_reset_mac_len(skb);
 	}
 
 	return ret;
diff --git a/net/core/sock.c b/net/core/sock.c
index c761c4a0b66b..958614ea16ed 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2132,10 +2132,10 @@ void skb_orphan_partial(struct sk_buff *skb)
 	if (skb_is_tcp_pure_ack(skb))
 		return;
 
-	if (can_skb_orphan_partial(skb))
-		skb_set_owner_sk_safe(skb, skb->sk);
-	else
-		skb_orphan(skb);
+	if (can_skb_orphan_partial(skb) && skb_set_owner_sk_safe(skb, skb->sk))
+		return;
+
+	skb_orphan(skb);
 }
 EXPORT_SYMBOL(skb_orphan_partial);