Merge tag 'net-5.14-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski.
 "Including fixes from bpf and netfilter.

  Current release - regressions:

   - sock: fix parameter order in sock_setsockopt()

  Current release - new code bugs:

   - netfilter: nft_last:
       - fix incorrect arithmetic when restoring last used
       - honor NFTA_LAST_SET on restoration

  Previous releases - regressions:

   - udp: properly flush normal packet at GRO time

   - sfc: ensure correct number of XDP queues; don't allow enabling the
     feature if there isn't sufficient resources to Tx from any CPU

   - dsa: sja1105: fix address learning getting disabled on the CPU port

   - mptcp: addresses a rmem accounting issue that could keep packets in
     subflow receive buffers longer than necessary, delaying MPTCP-level
     ACKs

   - ip_tunnel: fix mtu calculation for ETHER tunnel devices

   - do not reuse skbs allocated from skbuff_fclone_cache in the napi
     skb cache, we'd try to return them to the wrong slab cache

   - tcp: consistently disable header prediction for mptcp

  Previous releases - always broken:

   - bpf: fix subprog poke descriptor tracking use-after-free

   - ipv6:
       - allocate enough headroom in ip6_finish_output2() in case
         iptables TEE is used
       - tcp: drop silly ICMPv6 packet too big messages to avoid
         expensive and pointless lookups (which may serve as a DDOS
         vector)
       - make sure fwmark is copied in SYNACK packets
       - fix 'disable_policy' for forwarded packets (align with IPv4)

   - netfilter: conntrack:
       - do not renew entry stuck in tcp SYN_SENT state
       - do not mark RST in the reply direction coming after SYN packet
         for an out-of-sync entry

   - mptcp: cleanly handle error conditions with MP_JOIN and syncookies

   - mptcp: fix double free when rejecting a join due to port mismatch

   - validate lwtstate->data before returning from skb_tunnel_info()

   - tcp: call sk_wmem_schedule before sk_mem_charge in zerocopy path

   - mt76: mt7921: continue to probe driver when fw already downloaded

   - bonding: fix multiple issues with offloading IPsec to (thru?) bond

   - stmmac: ptp: fix issues around Qbv support and setting time back

   - bcmgenet: always clear wake-up based on energy detection

  Misc:

   - sctp: move 198 addresses from unusable to private scope

   - ptp: support virtual clocks and timestamping

   - openvswitch: optimize operation for key comparison"

* tag 'net-5.14-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (158 commits)
  net: dsa: properly check for the bridge_leave methods in dsa_switch_bridge_leave()
  sfc: add logs explaining XDP_TX/REDIRECT is not available
  sfc: ensure correct number of XDP queues
  sfc: fix lack of XDP TX queues - error XDP TX failed (-22)
  net: fddi: fix UAF in fza_probe
  net: dsa: sja1105: fix address learning getting disabled on the CPU port
  net: ocelot: fix switchdev objects synced for wrong netdev with LAG offload
  net: Use nlmsg_unicast() instead of netlink_unicast()
  octeontx2-pf: Fix uninitialized boolean variable pps
  ipv6: allocate enough headroom in ip6_finish_output2()
  net: hdlc: rename 'mod_init' & 'mod_exit' functions to be module-specific
  net: bridge: multicast: fix MRD advertisement router port marking race
  net: bridge: multicast: fix PIM hello router port marking race
  net: phy: marvell10g: fix differentiation of 88X3310 from 88X3340
  dsa: fix for_each_child.cocci warnings
  virtio_net: check virtqueue_add_sgs() return value
  mptcp: properly account bulk freed memory
  selftests: mptcp: fix case multiple subflows limited by server
  mptcp: avoid processing packet if a subflow reset
  mptcp: fix syncookie process if mptcp can not_accept new subflow
  ...

3 files changed, 32 insertions, 42 deletions

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 034ad93a1ad7..9b1577498373 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2236,8 +2236,14 @@ static void bpf_prog_free_deferred(struct work_struct *work)
 #endif
 	if (aux->dst_trampoline)
 		bpf_trampoline_put(aux->dst_trampoline);
-	for (i = 0; i < aux->func_cnt; i++)
+	for (i = 0; i < aux->func_cnt; i++) {
+		/* We can just unlink the subprog poke descriptor table as
+		 * it was originally linked to the main program and is also
+		 * released along with it.
+		 */
+		aux->func[i]->aux->poke_tab = NULL;
 		bpf_jit_free(aux->func[i]);
+	}
 	if (aux->func_cnt) {
 		kfree(aux->func);
 		bpf_prog_unlock_free(aux->prog);
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 2546dafd6672..fdc20892837c 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -558,7 +558,8 @@ int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
 
 	if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
 		for (i = 0; i < map->max_entries; i++) {
-			dst = READ_ONCE(dtab->netdev_map[i]);
+			dst = rcu_dereference_check(dtab->netdev_map[i],
+						    rcu_read_lock_bh_held());
 			if (!is_valid_dst(dst, xdp, exclude_ifindex))
 				continue;
 
@@ -654,7 +655,8 @@ int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
 
 	if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
 		for (i = 0; i < map->max_entries; i++) {
-			dst = READ_ONCE(dtab->netdev_map[i]);
+			dst = rcu_dereference_check(dtab->netdev_map[i],
+						    rcu_read_lock_bh_held());
 			if (!dst || dst->dev->ifindex == exclude_ifindex)
 				continue;
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index be38bb930bf1..42a4063de7cd 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -12121,33 +12121,19 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 			goto out_free;
 		func[i]->is_func = 1;
 		func[i]->aux->func_idx = i;
-		/* the btf and func_info will be freed only at prog->aux */
+		/* Below members will be freed only at prog->aux */
 		func[i]->aux->btf = prog->aux->btf;
 		func[i]->aux->func_info = prog->aux->func_info;
+		func[i]->aux->poke_tab = prog->aux->poke_tab;
+		func[i]->aux->size_poke_tab = prog->aux->size_poke_tab;
 
 		for (j = 0; j < prog->aux->size_poke_tab; j++) {
-			u32 insn_idx = prog->aux->poke_tab[j].insn_idx;
-			int ret;
+			struct bpf_jit_poke_descriptor *poke;
 
-			if (!(insn_idx >= subprog_start &&
-			      insn_idx <= subprog_end))
-				continue;
-
-			ret = bpf_jit_add_poke_descriptor(func[i],
-							  &prog->aux->poke_tab[j]);
-			if (ret < 0) {
-				verbose(env, "adding tail call poke descriptor failed\n");
-				goto out_free;
-			}
-
-			func[i]->insnsi[insn_idx - subprog_start].imm = ret + 1;
-
-			map_ptr = func[i]->aux->poke_tab[ret].tail_call.map;
-			ret = map_ptr->ops->map_poke_track(map_ptr, func[i]->aux);
-			if (ret < 0) {
-				verbose(env, "tracking tail call prog failed\n");
-				goto out_free;
-			}
+			poke = &prog->aux->poke_tab[j];
+			if (poke->insn_idx < subprog_end &&
+			    poke->insn_idx >= subprog_start)
+				poke->aux = func[i]->aux;
 		}
 
 		/* Use bpf_prog_F_tag to indicate functions in stack traces.
@@ -12178,18 +12164,6 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		cond_resched();
 	}
 
-	/* Untrack main program's aux structs so that during map_poke_run()
-	 * we will not stumble upon the unfilled poke descriptors; each
-	 * of the main program's poke descs got distributed across subprogs
-	 * and got tracked onto map, so we are sure that none of them will
-	 * be missed after the operation below
-	 */
-	for (i = 0; i < prog->aux->size_poke_tab; i++) {
-		map_ptr = prog->aux->poke_tab[i].tail_call.map;
-
-		map_ptr->ops->map_poke_untrack(map_ptr, prog->aux);
-	}
-
 	/* at this point all bpf functions were successfully JITed
 	 * now populate all bpf_calls with correct addresses and
 	 * run last pass of JIT
@@ -12267,14 +12241,22 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 	bpf_prog_jit_attempt_done(prog);
 	return 0;
 out_free:
+	/* We failed JIT'ing, so at this point we need to unregister poke
+	 * descriptors from subprogs, so that kernel is not attempting to
+	 * patch it anymore as we're freeing the subprog JIT memory.
+	 */
+	for (i = 0; i < prog->aux->size_poke_tab; i++) {
+		map_ptr = prog->aux->poke_tab[i].tail_call.map;
+		map_ptr->ops->map_poke_untrack(map_ptr, prog->aux);
+	}
+	/* At this point we're guaranteed that poke descriptors are not
+	 * live anymore. We can just unlink its descriptor table as it's
+	 * released with the main prog.
+	 */
 	for (i = 0; i < env->subprog_cnt; i++) {
 		if (!func[i])
 			continue;
-
-		for (j = 0; j < func[i]->aux->size_poke_tab; j++) {
-			map_ptr = func[i]->aux->poke_tab[j].tail_call.map;
-			map_ptr->ops->map_poke_untrack(map_ptr, func[i]->aux);
-		}
+		func[i]->aux->poke_tab = NULL;
 		bpf_jit_free(func[i]);
 	}
 	kfree(func);