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

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

14 files changed, 65 insertions, 28 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 55f66e108059..9e7f071b846c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -145,6 +145,7 @@
 #include <linux/indirect_call_wrapper.h>
 #include <net/devlink.h>
 #include <linux/pm_runtime.h>
+#include <linux/prandom.h>
 
 #include "net-sysfs.h"
 
@@ -3558,6 +3559,7 @@ static int xmit_one(struct sk_buff *skb, struct net_device *dev,
 		dev_queue_xmit_nit(skb, dev);
 
 	len = skb->len;
+	PRANDOM_ADD_NOISE(skb, dev, txq, len + jiffies);
 	trace_net_dev_start_xmit(skb, dev);
 	rc = netdev_start_xmit(skb, dev, txq, more);
 	trace_net_dev_xmit(skb, rc, dev, len);
@@ -4130,6 +4132,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 			if (!skb)
 				goto out;
 
+			PRANDOM_ADD_NOISE(skb, dev, txq, jiffies);
 			HARD_TX_LOCK(dev, txq, cpu);
 
 			if (!netif_xmit_stopped(txq)) {
@@ -4195,6 +4198,7 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
 
 	skb_set_queue_mapping(skb, queue_id);
 	txq = skb_get_tx_queue(dev, skb);
+	PRANDOM_ADD_NOISE(skb, dev, txq, jiffies);
 
 	local_bh_disable();
 
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/rds/ib_cm.c b/net/rds/ib_cm.c
index 06603dd1c8aa..b36b60668b1d 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -956,9 +956,10 @@ int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id, bool isv6)
 	rds_ib_cm_fill_conn_param(conn, &conn_param, &dp,
 				  conn->c_proposed_version,
 				  UINT_MAX, UINT_MAX, isv6);
-	ret = rdma_connect(cm_id, &conn_param);
+	ret = rdma_connect_locked(cm_id, &conn_param);
 	if (ret)
-		rds_ib_conn_error(conn, "rdma_connect failed (%d)\n", ret);
+		rds_ib_conn_error(conn, "rdma_connect_locked failed (%d)\n",
+				  ret);
 
 out:
 	/* Beware - returning non-zero tells the rdma_cm to destroy
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/crypto.c b/net/tipc/crypto.c
index 40c44101fe8e..740ab9ae41a6 100644
--- a/net/tipc/crypto.c
+++ b/net/tipc/crypto.c
@@ -418,7 +418,7 @@ static void tipc_aead_free(struct rcu_head *rp)
 		kfree(head);
 	}
 	free_percpu(aead->tfm_entry);
-	kzfree(aead->key);
+	kfree_sensitive(aead->key);
 	kfree(aead);
 }
 
@@ -2452,7 +2452,7 @@ static void tipc_crypto_work_tx(struct work_struct *work)
 		     tipc_crypto_key_init(tx, skey, PER_NODE_KEY, false);
 		if (likely(rc > 0))
 			rc = tipc_crypto_key_distr(tx, rc, NULL);
-		kzfree(skey);
+		kfree_sensitive(skey);
 	}
 
 	if (unlikely(rc))
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;