Merge tag 'net-5.10-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Current release regressions:

   - r8169: fix forced threading conflicting with other shared
     interrupts; we tried to fix the use of raise_softirq_irqoff from an
     IRQ handler on RT by forcing hard irqs, but this driver shares
     legacy PCI IRQs so drop the _irqoff() instead

   - tipc: fix memory leak caused by a recent syzbot report fix to
     tipc_buf_append()

  Current release - bugs in new features:

   - devlink: Unlock on error in dumpit() and fix some error codes

   - net/smc: fix null pointer dereference in smc_listen_decline()

  Previous release - regressions:

   - tcp: Prevent low rmem stalls with SO_RCVLOWAT.

   - net: protect tcf_block_unbind with block lock

   - ibmveth: Fix use of ibmveth in a bridge; the self-imposed filtering
     to only send legal frames to the hypervisor was too strict

   - net: hns3: Clear the CMDQ registers before unmapping BAR region;
     incorrect cleanup order was leading to a crash

   - bnxt_en - handful of fixes to fixes:
      - Send HWRM_FUNC_RESET fw command unconditionally, even if there
        are PCIe errors being reported
      - Check abort error state in bnxt_open_nic().
      - Invoke cancel_delayed_work_sync() for PFs also.
      - Fix regression in workqueue cleanup logic in bnxt_remove_one().

   - mlxsw: Only advertise link modes supported by both driver and
     device, after removal of 56G support from the driver 56G was not
     cleared from advertised modes

   - net/smc: fix suppressed return code

  Previous release - always broken:

   - netem: fix zero division in tabledist, caused by integer overflow

   - bnxt_en: Re-write PCI BARs after PCI fatal error.

   - cxgb4: set up filter action after rewrites

   - net: ipa: command payloads already mapped

  Misc:

   - s390/ism: fix incorrect system EID, it's okay to change since it
     was added in current release

   - vsock: use ns_capable_noaudit() on socket create to suppress false
     positive audit messages"

* tag 'net-5.10-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (36 commits)
  r8169: fix issue with forced threading in combination with shared interrupts
  netem: fix zero division in tabledist
  ibmvnic: fix ibmvnic_set_mac
  mptcp: add missing memory scheduling in the rx path
  tipc: fix memory leak caused by tipc_buf_append()
  gtp: fix an use-before-init in gtp_newlink()
  net: protect tcf_block_unbind with block lock
  ibmveth: Fix use of ibmveth in a bridge.
  net/sched: act_mpls: Add softdep on mpls_gso.ko
  ravb: Fix bit fields checking in ravb_hwtstamp_get()
  devlink: Unlock on error in dumpit()
  devlink: Fix some error codes
  chelsio/chtls: fix memory leaks in CPL handlers
  chelsio/chtls: fix deadlock issue
  net: hns3: Clear the CMDQ registers before unmapping BAR region
  bnxt_en: Send HWRM_FUNC_RESET fw command unconditionally.
  bnxt_en: Check abort error state in bnxt_open_nic().
  bnxt_en: Re-write PCI BARs after PCI fatal error.
  bnxt_en: Invoke cancel_delayed_work_sync() for PFs also.
  bnxt_en: Fix regression in workqueue cleanup logic in bnxt_remove_one().
  ...

11 files changed, 56 insertions, 24 deletions

diff --git a/net/core/devlink.c b/net/core/devlink.c
index a578634052a3..a932d95be798 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -4213,10 +4213,12 @@ static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink,
 	if (err)
 		goto nla_put_failure;
 
-	if (region->port)
-		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
-				region->port->index))
+	if (region->port) {
+		err = nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
+				  region->port->index);
+		if (err)
 			goto nla_put_failure;
+	}
 
 	err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, region->ops->name);
 	if (err)
@@ -4265,10 +4267,12 @@ devlink_nl_region_notify_build(struct devlink_region *region,
 	if (err)
 		goto out_cancel_msg;
 
-	if (region->port)
-		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
-				region->port->index))
+	if (region->port) {
+		err = nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
+				  region->port->index);
+		if (err)
 			goto out_cancel_msg;
+	}
 
 	err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME,
 			     region->ops->name);
@@ -4915,8 +4919,10 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
 		index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
 
 		port = devlink_port_get_by_index(devlink, index);
-		if (!port)
-			return -ENODEV;
+		if (!port) {
+			err = -ENODEV;
+			goto out_unlock;
+		}
 	}
 
 	region_name = nla_data(attrs[DEVLINK_ATTR_REGION_NAME]);
@@ -4962,10 +4968,12 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
 	if (err)
 		goto nla_put_failure;
 
-	if (region->port)
-		if (nla_put_u32(skb, DEVLINK_ATTR_PORT_INDEX,
-				region->port->index))
+	if (region->port) {
+		err = nla_put_u32(skb, DEVLINK_ATTR_PORT_INDEX,
+				  region->port->index);
+		if (err)
 			goto nla_put_failure;
+	}
 
 	err = nla_put_string(skb, DEVLINK_ATTR_REGION_NAME, region_name);
 	if (err)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index bae4284bf542..b2bc3d7fe9e8 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -485,6 +485,8 @@ static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,
 			return true;
 		if (tcp_rmem_pressure(sk))
 			return true;
+		if (tcp_receive_window(tp) <= inet_csk(sk)->icsk_ack.rcv_mss)
+			return true;
 	}
 	if (sk->sk_prot->stream_memory_read)
 		return sk->sk_prot->stream_memory_read(sk);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index fc445833b5e5..389d1b340248 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4908,7 +4908,8 @@ void tcp_data_ready(struct sock *sk)
 	int avail = tp->rcv_nxt - tp->copied_seq;
 
 	if (avail < sk->sk_rcvlowat && !tcp_rmem_pressure(sk) &&
-	    !sock_flag(sk, SOCK_DONE))
+	    !sock_flag(sk, SOCK_DONE) &&
+	    tcp_receive_window(tp) > inet_csk(sk)->icsk_ack.rcv_mss)
 		return;
 
 	sk->sk_data_ready(sk);
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 185dacb39781..e7419fd15d84 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -274,6 +274,15 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
 	skb_ext_reset(skb);
 	skb_orphan(skb);
 
+	/* try to fetch required memory from subflow */
+	if (!sk_rmem_schedule(sk, skb, skb->truesize)) {
+		if (ssk->sk_forward_alloc < skb->truesize)
+			goto drop;
+		__sk_mem_reclaim(ssk, skb->truesize);
+		if (!sk_rmem_schedule(sk, skb, skb->truesize))
+			goto drop;
+	}
+
 	/* the skb map_seq accounts for the skb offset:
 	 * mptcp_subflow_get_mapped_dsn() is based on the current tp->copied_seq
 	 * value
@@ -301,6 +310,7 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
 	 * will retransmit as needed, if needed.
 	 */
 	MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
+drop:
 	mptcp_drop(sk, skb);
 	return false;
 }
diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c
index f40bf9771cb9..5c7456e5b5cf 100644
--- a/net/sched/act_mpls.c
+++ b/net/sched/act_mpls.c
@@ -426,6 +426,7 @@ static void __exit mpls_cleanup_module(void)
 module_init(mpls_init_module);
 module_exit(mpls_cleanup_module);
 
+MODULE_SOFTDEP("post: mpls_gso");
 MODULE_AUTHOR("Netronome Systems <oss-drivers@netronome.com>");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("MPLS manipulation actions");
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index faeabff283a2..838b3fd94d77 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -652,12 +652,12 @@ static void tc_block_indr_cleanup(struct flow_block_cb *block_cb)
 			       block_cb->indr.binder_type,
 			       &block->flow_block, tcf_block_shared(block),
 			       &extack);
+	rtnl_lock();
 	down_write(&block->cb_lock);
 	list_del(&block_cb->driver_list);
 	list_move(&block_cb->list, &bo.cb_list);
-	up_write(&block->cb_lock);
-	rtnl_lock();
 	tcf_block_unbind(block, &bo);
+	up_write(&block->cb_lock);
 	rtnl_unlock();
 }
 
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 84f82771cdf5..0c345e43a09a 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -330,7 +330,7 @@ static s64 tabledist(s64 mu, s32 sigma,
 
 	/* default uniform distribution */
 	if (dist == NULL)
-		return ((rnd % (2 * sigma)) + mu) - sigma;
+		return ((rnd % (2 * (u32)sigma)) + mu) - sigma;
 
 	t = dist->table[rnd % dist->size];
 	x = (sigma % NETEM_DIST_SCALE) * t;
@@ -812,6 +812,10 @@ static void get_slot(struct netem_sched_data *q, const struct nlattr *attr)
 		q->slot_config.max_packets = INT_MAX;
 	if (q->slot_config.max_bytes == 0)
 		q->slot_config.max_bytes = INT_MAX;
+
+	/* capping dist_jitter to the range acceptable by tabledist() */
+	q->slot_config.dist_jitter = min_t(__s64, INT_MAX, abs(q->slot_config.dist_jitter));
+
 	q->slot.packets_left = q->slot_config.max_packets;
 	q->slot.bytes_left = q->slot_config.max_bytes;
 	if (q->slot_config.min_delay | q->slot_config.max_delay |
@@ -1037,6 +1041,9 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
 	if (tb[TCA_NETEM_SLOT])
 		get_slot(q, tb[TCA_NETEM_SLOT]);
 
+	/* capping jitter to the range acceptable by tabledist() */
+	q->jitter = min_t(s64, abs(q->jitter), INT_MAX);
+
 	return ret;
 
 get_table_failure:
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 82be0bd0f6e8..e9f487c8c6d5 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1317,10 +1317,10 @@ static void smc_listen_out_err(struct smc_sock *new_smc)
 
 /* listen worker: decline and fall back if possible */
 static void smc_listen_decline(struct smc_sock *new_smc, int reason_code,
-			       struct smc_init_info *ini, u8 version)
+			       int local_first, u8 version)
 {
 	/* RDMA setup failed, switch back to TCP */
-	if (ini->first_contact_local)
+	if (local_first)
 		smc_lgr_cleanup_early(&new_smc->conn);
 	else
 		smc_conn_free(&new_smc->conn);
@@ -1768,7 +1768,8 @@ static void smc_listen_work(struct work_struct *work)
 out_unlock:
 	mutex_unlock(&smc_server_lgr_pending);
 out_decl:
-	smc_listen_decline(new_smc, rc, ini, version);
+	smc_listen_decline(new_smc, rc, ini ? ini->first_contact_local : 0,
+			   version);
 out_free:
 	kfree(ini);
 	kfree(buf);
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index d790c43c473f..2b19863f7171 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -1615,8 +1615,11 @@ static struct smc_buf_desc *smcd_new_buf_create(struct smc_link_group *lgr,
 		rc = smc_ism_register_dmb(lgr, bufsize, buf_desc);
 		if (rc) {
 			kfree(buf_desc);
-			return (rc == -ENOMEM) ? ERR_PTR(-EAGAIN) :
-						 ERR_PTR(-EIO);
+			if (rc == -ENOMEM)
+				return ERR_PTR(-EAGAIN);
+			if (rc == -ENOSPC)
+				return ERR_PTR(-ENOSPC);
+			return ERR_PTR(-EIO);
 		}
 		buf_desc->pages = virt_to_page(buf_desc->cpu_addr);
 		/* CDC header stored in buf. So, pretend it was smaller */
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 2a78aa701572..32c79c59052b 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -150,12 +150,11 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf)
 	if (fragid == FIRST_FRAGMENT) {
 		if (unlikely(head))
 			goto err;
-		if (skb_cloned(frag))
-			frag = skb_copy(frag, GFP_ATOMIC);
+		*buf = NULL;
+		frag = skb_unshare(frag, GFP_ATOMIC);
 		if (unlikely(!frag))
 			goto err;
 		head = *headbuf = frag;
-		*buf = NULL;
 		TIPC_SKB_CB(head)->tail = NULL;
 		if (skb_is_nonlinear(head)) {
 			skb_walk_frags(head, tail) {
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 9e93bc201cc0..b4d7b8aba003 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -739,7 +739,7 @@ static struct sock *__vsock_create(struct net *net,
 		vsk->buffer_min_size = psk->buffer_min_size;
 		vsk->buffer_max_size = psk->buffer_max_size;
 	} else {
-		vsk->trusted = capable(CAP_NET_ADMIN);
+		vsk->trusted = ns_capable_noaudit(&init_user_ns, CAP_NET_ADMIN);
 		vsk->owner = get_current_cred();
 		vsk->connect_timeout = VSOCK_DEFAULT_CONNECT_TIMEOUT;
 		vsk->buffer_size = VSOCK_DEFAULT_BUFFER_SIZE;