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

Pull networking fixes from David Miller:

 1) Fix hotplug deadlock in hv_netvsc, from Stephen Hemminger.

 2) Fix double-free in rmnet driver, from Dan Carpenter.

 3) INET connection socket layer can double put request sockets, fix
    from Eric Dumazet.

 4) Don't match collect metadata-mode tunnels if the device is down,
    from Haishuang Yan.

 5) Do not perform TSO6/GSO on ipv6 packets with extensions headers in
    be2net driver, from Suresh Reddy.

 6) Fix scaling error in gen_estimator, from Eric Dumazet.

 7) Fix 64-bit statistics deadlock in systemport driver, from Florian
    Fainelli.

 8) Fix use-after-free in sctp_sock_dump, from Xin Long.

 9) Reject invalid BPF_END instructions in verifier, from Edward Cree.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (43 commits)
  mlxsw: spectrum_router: Only handle IPv4 and IPv6 events
  Documentation: link in networking docs
  tcp: fix data delivery rate
  bpf/verifier: reject BPF_ALU64|BPF_END
  sctp: do not mark sk dumped when inet_sctp_diag_fill returns err
  sctp: fix an use-after-free issue in sctp_sock_dump
  netvsc: increase default receive buffer size
  tcp: update skb->skb_mstamp more carefully
  net: ipv4: fix l3slave check for index returned in IP_PKTINFO
  net: smsc911x: Quieten netif during suspend
  net: systemport: Fix 64-bit stats deadlock
  net: vrf: avoid gcc-4.6 warning
  qed: remove unnecessary call to memset
  tg3: clean up redundant initialization of tnapi
  tls: make tls_sw_free_resources static
  sctp: potential read out of bounds in sctp_ulpevent_type_enabled()
  MAINTAINERS: review Renesas DT bindings as well
  net_sched: gen_estimator: fix scaling error in bytes/packets samples
  nfp: wait for the NSP resource to appear on boot
  nfp: wait for board state before talking to the NSP
  ...

Documentation/networking/filter.txt

@@ -45,7 +45,7 @@ in many more places. There's xt_bpf for netfilter, cls_bpf in the kernel
 qdisc layer, SECCOMP-BPF (SECure COMPuting [1]), and lots of other places
 such as team driver, PTP code, etc where BPF is being used.
 
- [1] Documentation/prctl/seccomp_filter.txt
+ [1] Documentation/userspace-api/seccomp_filter.rst
 
 Original BPF paper:
 

MAINTAINERS

@@ -11435,6 +11435,8 @@ RENESAS ETHERNET DRIVERS
 R:	Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
 L:	netdev@vger.kernel.org
 L:	linux-renesas-soc@vger.kernel.org
+F:	Documentation/devicetree/bindings/net/renesas,*.txt
+F:	Documentation/devicetree/bindings/net/sh_eth.txt
 F:	drivers/net/ethernet/renesas/
 F:	include/linux/sh_eth.h
 

drivers/net/bonding/bond_main.c

@@ -4289,7 +4289,7 @@ static int bond_check_params(struct bond_params *params)
 	int bond_mode	= BOND_MODE_ROUNDROBIN;
 	int xmit_hashtype = BOND_XMIT_POLICY_LAYER2;
 	int lacp_fast = 0;
-	int tlb_dynamic_lb = 0;
+	int tlb_dynamic_lb;
 
 	/* Convert string parameters. */
 	if (mode) {
@@ -4601,16 +4601,13 @@ static int bond_check_params(struct bond_params *params)
 	}
 	ad_user_port_key = valptr->value;
 
-	if ((bond_mode == BOND_MODE_TLB) || (bond_mode == BOND_MODE_ALB)) {
+	bond_opt_initstr(&newval, "default");
-		bond_opt_initstr(&newval, "default");
+	valptr = bond_opt_parse(bond_opt_get(BOND_OPT_TLB_DYNAMIC_LB), &newval);
-		valptr = bond_opt_parse(bond_opt_get(BOND_OPT_TLB_DYNAMIC_LB),
+	if (!valptr) {
-					&newval);
+		pr_err("Error: No tlb_dynamic_lb default value");
-		if (!valptr) {
+		return -EINVAL;
-			pr_err("Error: No tlb_dynamic_lb default value");
-			return -EINVAL;
-		}
-		tlb_dynamic_lb = valptr->value;
 	}
+	tlb_dynamic_lb = valptr->value;
 
 	if (lp_interval == 0) {
 		pr_warn("Warning: ip_interval must be between 1 and %d, so it was reset to %d\n",

drivers/net/bonding/bond_options.c

@@ -754,6 +754,9 @@ static int bond_option_mode_set(struct bonding *bond,
 			   bond->params.miimon);
 	}
 
+	if (newval->value == BOND_MODE_ALB)
+		bond->params.tlb_dynamic_lb = 1;
+
 	/* don't cache arp_validate between modes */
 	bond->params.arp_validate = BOND_ARP_VALIDATE_NONE;
 	bond->params.mode = newval->value;

drivers/net/ethernet/broadcom/bcmsysport.c

@@ -1735,11 +1735,8 @@ static void bcm_sysport_get_stats64(struct net_device *dev,
 		stats->tx_packets += tx_packets;
 	}
 
-	/* lockless update tx_bytes and tx_packets */
-	u64_stats_update_begin(&priv->syncp);
 	stats64->tx_bytes = stats->tx_bytes;
 	stats64->tx_packets = stats->tx_packets;
-	u64_stats_update_end(&priv->syncp);
 
 	do {
 		start = u64_stats_fetch_begin_irq(&priv->syncp);

drivers/net/ethernet/broadcom/tg3.c

@@ -11536,11 +11536,11 @@ static int tg3_start(struct tg3 *tp, bool reset_phy, bool test_irq,
 	tg3_napi_enable(tp);
 
 	for (i = 0; i < tp->irq_cnt; i++) {
-		struct tg3_napi *tnapi = &tp->napi[i];
 		err = tg3_request_irq(tp, i);
 		if (err) {
 			for (i--; i >= 0; i--) {
-				tnapi = &tp->napi[i];
+				struct tg3_napi *tnapi = &tp->napi[i];
+
 				free_irq(tnapi->irq_vec, tnapi);
 			}
 			goto out_napi_fini;

drivers/net/ethernet/emulex/benet/be.h

@@ -930,6 +930,14 @@ static inline bool is_ipv4_pkt(struct sk_buff *skb)
 	return skb->protocol == htons(ETH_P_IP) && ip_hdr(skb)->version == 4;
 }
 
+static inline bool is_ipv6_ext_hdr(struct sk_buff *skb)
+{
+	if (ip_hdr(skb)->version == 6)
+		return ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr);
+	else
+		return false;
+}
+
 #define be_error_recovering(adapter)	\
 		(adapter->flags & BE_FLAGS_TRY_RECOVERY)
 

drivers/net/ethernet/emulex/benet/be_main.c

@@ -5089,6 +5089,20 @@ static netdev_features_t be_features_check(struct sk_buff *skb,
 	struct be_adapter *adapter = netdev_priv(dev);
 	u8 l4_hdr = 0;
 
+	if (skb_is_gso(skb)) {
+		/* IPv6 TSO requests with extension hdrs are a problem
+		 * to Lancer and BE3 HW. Disable TSO6 feature.
+		 */
+		if (!skyhawk_chip(adapter) && is_ipv6_ext_hdr(skb))
+			features &= ~NETIF_F_TSO6;
+
+		/* Lancer cannot handle the packet with MSS less than 256.
+		 * Disable the GSO support in such cases
+		 */
+		if (lancer_chip(adapter) && skb_shinfo(skb)->gso_size < 256)
+			features &= ~NETIF_F_GSO_MASK;
+	}
+
 	/* The code below restricts offload features for some tunneled and
 	 * Q-in-Q packets.
 	 * Offload features for normal (non tunnel) packets are unchanged.

drivers/net/ethernet/mellanox/mlxsw/spectrum.c

@@ -575,15 +575,14 @@ static void mlxsw_sp_span_entry_destroy(struct mlxsw_sp *mlxsw_sp,
 }
 
 static struct mlxsw_sp_span_entry *
-mlxsw_sp_span_entry_find(struct mlxsw_sp_port *port)
+mlxsw_sp_span_entry_find(struct mlxsw_sp *mlxsw_sp, u8 local_port)
 {
-	struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp;
 	int i;
 
 	for (i = 0; i < mlxsw_sp->span.entries_count; i++) {
 		struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i];
 
-		if (curr->used && curr->local_port == port->local_port)
+		if (curr->used && curr->local_port == local_port)
 			return curr;
 	}
 	return NULL;
@@ -594,7 +593,8 @@ static struct mlxsw_sp_span_entry
 {
 	struct mlxsw_sp_span_entry *span_entry;
 
-	span_entry = mlxsw_sp_span_entry_find(port);
+	span_entry = mlxsw_sp_span_entry_find(port->mlxsw_sp,
+					      port->local_port);
 	if (span_entry) {
 		/* Already exists, just take a reference */
 		span_entry->ref_count++;
@@ -783,12 +783,13 @@ err_port_bind:
 }
 
 static void mlxsw_sp_span_mirror_remove(struct mlxsw_sp_port *from,
-					struct mlxsw_sp_port *to,
+					u8 destination_port,
 					enum mlxsw_sp_span_type type)
 {
 	struct mlxsw_sp_span_entry *span_entry;
 
-	span_entry = mlxsw_sp_span_entry_find(to);
+	span_entry = mlxsw_sp_span_entry_find(from->mlxsw_sp,
+					      destination_port);
 	if (!span_entry) {
 		netdev_err(from->dev, "no span entry found\n");
 		return;
@@ -1563,14 +1564,12 @@ static void
 mlxsw_sp_port_del_cls_matchall_mirror(struct mlxsw_sp_port *mlxsw_sp_port,
 				      struct mlxsw_sp_port_mall_mirror_tc_entry *mirror)
 {
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	enum mlxsw_sp_span_type span_type;
-	struct mlxsw_sp_port *to_port;
 
-	to_port = mlxsw_sp->ports[mirror->to_local_port];
 	span_type = mirror->ingress ?
 			MLXSW_SP_SPAN_INGRESS : MLXSW_SP_SPAN_EGRESS;
-	mlxsw_sp_span_mirror_remove(mlxsw_sp_port, to_port, span_type);
+	mlxsw_sp_span_mirror_remove(mlxsw_sp_port, mirror->to_local_port,
+				    span_type);
 }
 
 static int
@@ -2545,7 +2544,9 @@ out:
 	return err;
 }
 
-#define MLXSW_SP_QSFP_I2C_ADDR 0x50
+#define MLXSW_SP_I2C_ADDR_LOW 0x50
+#define MLXSW_SP_I2C_ADDR_HIGH 0x51
+#define MLXSW_SP_EEPROM_PAGE_LENGTH 256
 
 static int mlxsw_sp_query_module_eeprom(struct mlxsw_sp_port *mlxsw_sp_port,
 					u16 offset, u16 size, void *data,
@@ -2554,12 +2555,25 @@ static int mlxsw_sp_query_module_eeprom(struct mlxsw_sp_port *mlxsw_sp_port,
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	char eeprom_tmp[MLXSW_SP_REG_MCIA_EEPROM_SIZE];
 	char mcia_pl[MLXSW_REG_MCIA_LEN];
+	u16 i2c_addr;
 	int status;
 	int err;
 
 	size = min_t(u16, size, MLXSW_SP_REG_MCIA_EEPROM_SIZE);
+
+	if (offset < MLXSW_SP_EEPROM_PAGE_LENGTH &&
+	    offset + size > MLXSW_SP_EEPROM_PAGE_LENGTH)
+		/* Cross pages read, read until offset 256 in low page */
+		size = MLXSW_SP_EEPROM_PAGE_LENGTH - offset;
+
+	i2c_addr = MLXSW_SP_I2C_ADDR_LOW;
+	if (offset >= MLXSW_SP_EEPROM_PAGE_LENGTH) {
+		i2c_addr = MLXSW_SP_I2C_ADDR_HIGH;
+		offset -= MLXSW_SP_EEPROM_PAGE_LENGTH;
+	}
+
 	mlxsw_reg_mcia_pack(mcia_pl, mlxsw_sp_port->mapping.module,
-			    0, 0, offset, size, MLXSW_SP_QSFP_I2C_ADDR);
+			    0, 0, offset, size, i2c_addr);
 
 	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(mcia), mcia_pl);
 	if (err)

drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c

@@ -4868,7 +4868,8 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
 	struct fib_notifier_info *info = ptr;
 	struct mlxsw_sp_router *router;
 
-	if (!net_eq(info->net, &init_net))
+	if (!net_eq(info->net, &init_net) ||
+	    (info->family != AF_INET && info->family != AF_INET6))
 		return NOTIFY_DONE;
 
 	fib_work = kzalloc(sizeof(*fib_work), GFP_ATOMIC);

drivers/net/ethernet/netronome/nfp/flower/offload.c

@@ -44,6 +44,16 @@
 #include "../nfp_net.h"
 #include "../nfp_port.h"
 
+#define NFP_FLOWER_WHITELIST_DISSECTOR \
+	(BIT(FLOW_DISSECTOR_KEY_CONTROL) | \
+	 BIT(FLOW_DISSECTOR_KEY_BASIC) | \
+	 BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | \
+	 BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | \
+	 BIT(FLOW_DISSECTOR_KEY_PORTS) | \
+	 BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | \
+	 BIT(FLOW_DISSECTOR_KEY_VLAN) | \
+	 BIT(FLOW_DISSECTOR_KEY_IP))
+
 static int
 nfp_flower_xmit_flow(struct net_device *netdev,
 		     struct nfp_fl_payload *nfp_flow, u8 mtype)
@@ -112,6 +122,9 @@ nfp_flower_calculate_key_layers(struct nfp_fl_key_ls *ret_key_ls,
 	u8 key_layer;
 	int key_size;
 
+	if (flow->dissector->used_keys & ~NFP_FLOWER_WHITELIST_DISSECTOR)
+		return -EOPNOTSUPP;
+
 	if (dissector_uses_key(flow->dissector,
 			       FLOW_DISSECTOR_KEY_ENC_CONTROL)) {
 		struct flow_dissector_key_control *mask_enc_ctl =

drivers/net/ethernet/netronome/nfp/nfp_main.c

@@ -74,6 +74,45 @@ static const struct pci_device_id nfp_pci_device_ids[] = {
 };
 MODULE_DEVICE_TABLE(pci, nfp_pci_device_ids);
 
+static bool nfp_board_ready(struct nfp_pf *pf)
+{
+	const char *cp;
+	long state;
+	int err;
+
+	cp = nfp_hwinfo_lookup(pf->hwinfo, "board.state");
+	if (!cp)
+		return false;
+
+	err = kstrtol(cp, 0, &state);
+	if (err < 0)
+		return false;
+
+	return state == 15;
+}
+
+static int nfp_pf_board_state_wait(struct nfp_pf *pf)
+{
+	const unsigned long wait_until = jiffies + 10 * HZ;
+
+	while (!nfp_board_ready(pf)) {
+		if (time_is_before_eq_jiffies(wait_until)) {
+			nfp_err(pf->cpp, "NFP board initialization timeout\n");
+			return -EINVAL;
+		}
+
+		nfp_info(pf->cpp, "waiting for board initialization\n");
+		if (msleep_interruptible(500))
+			return -ERESTARTSYS;
+
+		/* Refresh cached information */
+		kfree(pf->hwinfo);
+		pf->hwinfo = nfp_hwinfo_read(pf->cpp);
+	}
+
+	return 0;
+}
+
 static int nfp_pcie_sriov_read_nfd_limit(struct nfp_pf *pf)
 {
 	int err;
@@ -312,6 +351,10 @@ static int nfp_nsp_init(struct pci_dev *pdev, struct nfp_pf *pf)
 	struct nfp_nsp *nsp;
 	int err;
 
+	err = nfp_resource_wait(pf->cpp, NFP_RESOURCE_NSP, 30);
+	if (err)
+		return err;
+
 	nsp = nfp_nsp_open(pf->cpp);
 	if (IS_ERR(nsp)) {
 		err = PTR_ERR(nsp);
@@ -425,6 +468,10 @@ static int nfp_pci_probe(struct pci_dev *pdev,
 		 nfp_hwinfo_lookup(pf->hwinfo, "assembly.revision"),
 		 nfp_hwinfo_lookup(pf->hwinfo, "cpld.version"));
 
+	err = nfp_pf_board_state_wait(pf);
+	if (err)
+		goto err_hwinfo_free;
+
 	err = devlink_register(devlink, &pdev->dev);
 	if (err)
 		goto err_hwinfo_free;

drivers/net/ethernet/netronome/nfp/nfp_net_main.c

@@ -64,23 +64,6 @@
 
 #define NFP_PF_CSR_SLICE_SIZE	(32 * 1024)
 
-static int nfp_is_ready(struct nfp_pf *pf)
-{
-	const char *cp;
-	long state;
-	int err;
-
-	cp = nfp_hwinfo_lookup(pf->hwinfo, "board.state");
-	if (!cp)
-		return 0;
-
-	err = kstrtol(cp, 0, &state);
-	if (err < 0)
-		return 0;
-
-	return state == 15;
-}
-
 /**
  * nfp_net_get_mac_addr() - Get the MAC address.
  * @pf:       NFP PF handle
@@ -725,12 +708,6 @@ int nfp_net_pci_probe(struct nfp_pf *pf)
 
 	INIT_WORK(&pf->port_refresh_work, nfp_net_refresh_vnics);
 
-	/* Verify that the board has completed initialization */
-	if (!nfp_is_ready(pf)) {
-		nfp_err(pf->cpp, "NFP is not ready for NIC operation.\n");
-		return -EINVAL;
-	}
-
 	if (!pf->rtbl) {
 		nfp_err(pf->cpp, "No %s, giving up.\n",
 			pf->fw_loaded ? "symbol table" : "firmware found");

drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h

@@ -97,6 +97,8 @@ nfp_resource_acquire(struct nfp_cpp *cpp, const char *name);
 
 void nfp_resource_release(struct nfp_resource *res);
 
+int nfp_resource_wait(struct nfp_cpp *cpp, const char *name, unsigned int secs);
+
 u32 nfp_resource_cpp_id(struct nfp_resource *res);
 
 const char *nfp_resource_name(struct nfp_resource *res);

drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c

@@ -249,6 +249,51 @@ void nfp_resource_release(struct nfp_resource *res)
 	kfree(res);
 }
 
+/**
+ * nfp_resource_wait() - Wait for resource to appear
+ * @cpp:	NFP CPP handle
+ * @name:	Name of the resource
+ * @secs:	Number of seconds to wait
+ *
+ * Wait for resource to appear in the resource table, grab and release
+ * its lock.  The wait is jiffies-based, don't expect fine granularity.
+ *
+ * Return: 0 on success, errno otherwise.
+ */
+int nfp_resource_wait(struct nfp_cpp *cpp, const char *name, unsigned int secs)
+{
+	unsigned long warn_at = jiffies + NFP_MUTEX_WAIT_FIRST_WARN * HZ;
+	unsigned long err_at = jiffies + secs * HZ;
+	struct nfp_resource *res;
+
+	while (true) {
+		res = nfp_resource_acquire(cpp, name);
+		if (!IS_ERR(res)) {
+			nfp_resource_release(res);
+			return 0;
+		}
+
+		if (PTR_ERR(res) != -ENOENT) {
+			nfp_err(cpp, "error waiting for resource %s: %ld\n",
+				name, PTR_ERR(res));
+			return PTR_ERR(res);
+		}
+		if (time_is_before_eq_jiffies(err_at)) {
+			nfp_err(cpp, "timeout waiting for resource %s\n", name);
+			return -ETIMEDOUT;
+		}
+		if (time_is_before_eq_jiffies(warn_at)) {
+			warn_at = jiffies + NFP_MUTEX_WAIT_NEXT_WARN * HZ;
+			nfp_info(cpp, "waiting for NFP resource %s\n", name);
+		}
+		if (msleep_interruptible(10)) {
+			nfp_err(cpp, "wait for resource %s interrupted\n",
+				name);
+			return -ERESTARTSYS;
+		}
+	}
+}
+
 /**
  * nfp_resource_cpp_id() - Return the cpp_id of a resource handle
  * @res:	NFP Resource handle

drivers/net/ethernet/nuvoton/w90p910_ether.c

@@ -11,6 +11,7 @@
 
 #include <linux/module.h>
 #include <linux/init.h>
+#include <linux/interrupt.h>
 #include <linux/mii.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>

drivers/net/ethernet/qlogic/qed/qed_dcbx.c

@@ -1244,7 +1244,6 @@ int qed_dcbx_get_config_params(struct qed_hwfn *p_hwfn,
 	if (!dcbx_info)
 		return -ENOMEM;
 
-	memset(dcbx_info, 0, sizeof(*dcbx_info));
 	rc = qed_dcbx_query_params(p_hwfn, dcbx_info, QED_DCBX_OPERATIONAL_MIB);
 	if (rc) {
 		kfree(dcbx_info);

drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c

@@ -84,6 +84,10 @@ struct sk_buff *rmnet_map_deaggregate(struct sk_buff *skb)
 	if (((int)skb->len - (int)packet_len) < 0)
 		return NULL;
 
+	/* Some hardware can send us empty frames. Catch them */
+	if (ntohs(maph->pkt_len) == 0)
+		return NULL;
+
 	skbn = alloc_skb(packet_len + RMNET_MAP_DEAGGR_SPACING, GFP_ATOMIC);
 	if (!skbn)
 		return NULL;
@@ -94,11 +98,5 @@ struct sk_buff *rmnet_map_deaggregate(struct sk_buff *skb)
 	memcpy(skbn->data, skb->data, packet_len);
 	skb_pull(skb, packet_len);
 
-	/* Some hardware can send us empty frames. Catch them */
-	if (ntohs(maph->pkt_len) == 0) {
-		kfree_skb(skb);
-		return NULL;
-	}
-
 	return skbn;
 }

drivers/net/ethernet/smsc/smsc911x.c

@@ -2595,6 +2595,11 @@ static int smsc911x_suspend(struct device *dev)
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct smsc911x_data *pdata = netdev_priv(ndev);
 
+	if (netif_running(ndev)) {
+		netif_stop_queue(ndev);
+		netif_device_detach(ndev);
+	}
+
 	/* enable wake on LAN, energy detection and the external PME
 	 * signal. */
 	smsc911x_reg_write(pdata, PMT_CTRL,
@@ -2628,7 +2633,15 @@ static int smsc911x_resume(struct device *dev)
 	while (!(smsc911x_reg_read(pdata, PMT_CTRL) & PMT_CTRL_READY_) && --to)
 		udelay(1000);
 
-	return (to == 0) ? -EIO : 0;
+	if (to == 0)
+		return -EIO;
+
+	if (netif_running(ndev)) {
+		netif_device_attach(ndev);
+		netif_start_queue(ndev);
+	}
+
+	return 0;
 }
 
 static const struct dev_pm_ops smsc911x_pm_ops = {

drivers/net/hyperv/hyperv_net.h

@@ -204,6 +204,8 @@ int netvsc_recv_callback(struct net_device *net,
 			 const struct ndis_pkt_8021q_info *vlan);
 void netvsc_channel_cb(void *context);
 int netvsc_poll(struct napi_struct *napi, int budget);
+
+void rndis_set_subchannel(struct work_struct *w);
 bool rndis_filter_opened(const struct netvsc_device *nvdev);
 int rndis_filter_open(struct netvsc_device *nvdev);
 int rndis_filter_close(struct netvsc_device *nvdev);
@@ -782,6 +784,7 @@ struct netvsc_device {
 	u32 num_chn;
 
 	atomic_t open_chn;
+	struct work_struct subchan_work;
 	wait_queue_head_t subchan_open;
 
 	struct rndis_device *extension;

drivers/net/hyperv/netvsc.c

@@ -81,6 +81,7 @@ static struct netvsc_device *alloc_net_device(void)
 
 	init_completion(&net_device->channel_init_wait);
 	init_waitqueue_head(&net_device->subchan_open);
+	INIT_WORK(&net_device->subchan_work, rndis_set_subchannel);
 
 	return net_device;
 }
@@ -557,6 +558,8 @@ void netvsc_device_remove(struct hv_device *device)
 		= rtnl_dereference(net_device_ctx->nvdev);
 	int i;
 
+	cancel_work_sync(&net_device->subchan_work);
+
 	netvsc_disconnect_vsp(device);
 
 	RCU_INIT_POINTER(net_device_ctx->nvdev, NULL);

drivers/net/hyperv/netvsc_drv.c

@@ -49,7 +49,7 @@
 #define NETVSC_MIN_TX_SECTIONS	10
 #define NETVSC_DEFAULT_TX	192	/* ~1M */
 #define NETVSC_MIN_RX_SECTIONS	10	/* ~64K */
-#define NETVSC_DEFAULT_RX	2048	/* ~4M */
+#define NETVSC_DEFAULT_RX	10485   /* Max ~16M */
 
 #define LINKCHANGE_INT (2 * HZ)
 #define VF_TAKEOVER_INT (HZ / 10)
@@ -853,10 +853,7 @@ static int netvsc_set_channels(struct net_device *net,
 	rndis_filter_device_remove(dev, nvdev);
 
 	nvdev = rndis_filter_device_add(dev, &device_info);
-	if (!IS_ERR(nvdev)) {
+	if (IS_ERR(nvdev)) {
-		netif_set_real_num_tx_queues(net, nvdev->num_chn);
-		netif_set_real_num_rx_queues(net, nvdev->num_chn);
-	} else {
 		ret = PTR_ERR(nvdev);
 		device_info.num_chn = orig;
 		nvdev = rndis_filter_device_add(dev, &device_info);
@@ -1954,9 +1951,6 @@ static int netvsc_probe(struct hv_device *dev,
 		NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
 	net->vlan_features = net->features;
 
-	netif_set_real_num_tx_queues(net, nvdev->num_chn);
-	netif_set_real_num_rx_queues(net, nvdev->num_chn);
-
 	netdev_lockdep_set_classes(net);
 
 	/* MTU range: 68 - 1500 or 65521 */
@@ -2012,9 +2006,10 @@ static int netvsc_remove(struct hv_device *dev)
 	if (vf_netdev)
 		netvsc_unregister_vf(vf_netdev);
 
+	unregister_netdevice(net);
+
 	rndis_filter_device_remove(dev,
 				   rtnl_dereference(ndev_ctx->nvdev));
-	unregister_netdevice(net);
 	rtnl_unlock();
 
 	hv_set_drvdata(dev, NULL);

drivers/net/hyperv/rndis_filter.c

@@ -1039,8 +1039,6 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc)
 
 	/* Set the channel before opening.*/
 	nvchan->channel = new_sc;
-	netif_napi_add(ndev, &nvchan->napi,
-		       netvsc_poll, NAPI_POLL_WEIGHT);
 
 	ret = vmbus_open(new_sc, nvscdev->ring_size * PAGE_SIZE,
 			 nvscdev->ring_size * PAGE_SIZE, NULL, 0,
@@ -1048,10 +1046,86 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc)
 	if (ret == 0)
 		napi_enable(&nvchan->napi);
 	else
-		netif_napi_del(&nvchan->napi);
+		netdev_notice(ndev, "sub channel open failed: %d\n", ret);
 
-	atomic_inc(&nvscdev->open_chn);
+	if (atomic_inc_return(&nvscdev->open_chn) == nvscdev->num_chn)
-	wake_up(&nvscdev->subchan_open);
+		wake_up(&nvscdev->subchan_open);
+}
+
+/* Open sub-channels after completing the handling of the device probe.
+ * This breaks overlap of processing the host message for the
+ * new primary channel with the initialization of sub-channels.
+ */
+void rndis_set_subchannel(struct work_struct *w)
+{
+	struct netvsc_device *nvdev
+		= container_of(w, struct netvsc_device, subchan_work);
+	struct nvsp_message *init_packet = &nvdev->channel_init_pkt;
+	struct net_device_context *ndev_ctx;
+	struct rndis_device *rdev;
+	struct net_device *ndev;
+	struct hv_device *hv_dev;
+	int i, ret;
+
+	if (!rtnl_trylock()) {
+		schedule_work(w);
+		return;
+	}
+
+	rdev = nvdev->extension;
+	if (!rdev)
+		goto unlock;	/* device was removed */
+
+	ndev = rdev->ndev;
+	ndev_ctx = netdev_priv(ndev);
+	hv_dev = ndev_ctx->device_ctx;
+
+	memset(init_packet, 0, sizeof(struct nvsp_message));
+	init_packet->hdr.msg_type = NVSP_MSG5_TYPE_SUBCHANNEL;
+	init_packet->msg.v5_msg.subchn_req.op = NVSP_SUBCHANNEL_ALLOCATE;
+	init_packet->msg.v5_msg.subchn_req.num_subchannels =
+						nvdev->num_chn - 1;
+	ret = vmbus_sendpacket(hv_dev->channel, init_packet,
+			       sizeof(struct nvsp_message),
+			       (unsigned long)init_packet,
+			       VM_PKT_DATA_INBAND,
+			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
+	if (ret) {
+		netdev_err(ndev, "sub channel allocate send failed: %d\n", ret);
+		goto failed;
+	}
+
+	wait_for_completion(&nvdev->channel_init_wait);
+	if (init_packet->msg.v5_msg.subchn_comp.status != NVSP_STAT_SUCCESS) {
+		netdev_err(ndev, "sub channel request failed\n");
+		goto failed;
+	}
+
+	nvdev->num_chn = 1 +
+		init_packet->msg.v5_msg.subchn_comp.num_subchannels;
+
+	/* wait for all sub channels to open */
+	wait_event(nvdev->subchan_open,
+		   atomic_read(&nvdev->open_chn) == nvdev->num_chn);
+
+	/* ignore failues from setting rss parameters, still have channels */
+	rndis_filter_set_rss_param(rdev, netvsc_hash_key);
+
+	netif_set_real_num_tx_queues(ndev, nvdev->num_chn);
+	netif_set_real_num_rx_queues(ndev, nvdev->num_chn);
+
+	rtnl_unlock();
+	return;
+
+failed:
+	/* fallback to only primary channel */
+	for (i = 1; i < nvdev->num_chn; i++)
+		netif_napi_del(&nvdev->chan_table[i].napi);
+
+	nvdev->max_chn = 1;
+	nvdev->num_chn = 1;
+unlock:
+	rtnl_unlock();
 }
 
 struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
@@ -1063,7 +1137,6 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
 	struct rndis_device *rndis_device;
 	struct ndis_offload hwcaps;
 	struct ndis_offload_params offloads;
-	struct nvsp_message *init_packet;
 	struct ndis_recv_scale_cap rsscap;
 	u32 rsscap_size = sizeof(struct ndis_recv_scale_cap);
 	unsigned int gso_max_size = GSO_MAX_SIZE;
@@ -1215,9 +1288,7 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
 							net_device->num_chn);
 
 	atomic_set(&net_device->open_chn, 1);
-
+	vmbus_set_sc_create_callback(dev->channel, netvsc_sc_open);
-	if (net_device->num_chn == 1)
-		return net_device;
 
 	for (i = 1; i < net_device->num_chn; i++) {
 		ret = netvsc_alloc_recv_comp_ring(net_device, i);
@@ -1228,38 +1299,15 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
 		}
 	}
 
-	vmbus_set_sc_create_callback(dev->channel, netvsc_sc_open);
+	for (i = 1; i < net_device->num_chn; i++)
+		netif_napi_add(net, &net_device->chan_table[i].napi,
+			       netvsc_poll, NAPI_POLL_WEIGHT);
 
-	init_packet = &net_device->channel_init_pkt;
+	if (net_device->num_chn > 1)
-	memset(init_packet, 0, sizeof(struct nvsp_message));
+		schedule_work(&net_device->subchan_work);
-	init_packet->hdr.msg_type = NVSP_MSG5_TYPE_SUBCHANNEL;
-	init_packet->msg.v5_msg.subchn_req.op = NVSP_SUBCHANNEL_ALLOCATE;
-	init_packet->msg.v5_msg.subchn_req.num_subchannels =
-						net_device->num_chn - 1;
-	ret = vmbus_sendpacket(dev->channel, init_packet,
-			       sizeof(struct nvsp_message),
-			       (unsigned long)init_packet,
-			       VM_PKT_DATA_INBAND,
-			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
-	if (ret)
-		goto out;
 
-	wait_for_completion(&net_device->channel_init_wait);
-	if (init_packet->msg.v5_msg.subchn_comp.status != NVSP_STAT_SUCCESS) {
-		ret = -ENODEV;
-		goto out;
-	}
-
-	net_device->num_chn = 1 +
-		init_packet->msg.v5_msg.subchn_comp.num_subchannels;
-
-	/* wait for all sub channels to open */
-	wait_event(net_device->subchan_open,
-		   atomic_read(&net_device->open_chn) == net_device->num_chn);
-
-	/* ignore failues from setting rss parameters, still have channels */
-	rndis_filter_set_rss_param(rndis_device, netvsc_hash_key);
 out:
+	/* if unavailable, just proceed with one queue */
 	if (ret) {
 		net_device->max_chn = 1;
 		net_device->num_chn = 1;
@@ -1280,10 +1328,10 @@ void rndis_filter_device_remove(struct hv_device *dev,
 	/* Halt and release the rndis device */
 	rndis_filter_halt_device(rndis_dev);
 
-	kfree(rndis_dev);
 	net_dev->extension = NULL;
 
 	netvsc_device_remove(dev);
+	kfree(rndis_dev);
 }
 
 int rndis_filter_open(struct netvsc_device *nvdev)

drivers/net/usb/smsc95xx.c

@@ -526,7 +526,7 @@ static void smsc95xx_set_multicast(struct net_device *netdev)
 static int smsc95xx_phy_update_flowcontrol(struct usbnet *dev, u8 duplex,
 					   u16 lcladv, u16 rmtadv)
 {
-	u32 flow, afc_cfg = 0;
+	u32 flow = 0, afc_cfg;
 
 	int ret = smsc95xx_read_reg(dev, AFC_CFG, &afc_cfg);
 	if (ret < 0)
@@ -537,20 +537,19 @@ static int smsc95xx_phy_update_flowcontrol(struct usbnet *dev, u8 duplex,
 
 		if (cap & FLOW_CTRL_RX)
 			flow = 0xFFFF0002;
-		else
-			flow = 0;
 
-		if (cap & FLOW_CTRL_TX)
+		if (cap & FLOW_CTRL_TX) {
 			afc_cfg |= 0xF;
-		else
+			flow |= 0xFFFF0000;
+		} else {
 			afc_cfg &= ~0xF;
+		}
 
 		netif_dbg(dev, link, dev->net, "rx pause %s, tx pause %s\n",
 				   cap & FLOW_CTRL_RX ? "enabled" : "disabled",
 				   cap & FLOW_CTRL_TX ? "enabled" : "disabled");
 	} else {
 		netif_dbg(dev, link, dev->net, "half duplex\n");
-		flow = 0;
 		afc_cfg |= 0xF;
 	}
 

drivers/net/vrf.c

@@ -957,12 +957,12 @@ static void vrf_ip6_input_dst(struct sk_buff *skb, struct net_device *vrf_dev,
 {
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
 	struct flowi6 fl6 = {
+		.flowi6_iif     = ifindex,
+		.flowi6_mark    = skb->mark,
+		.flowi6_proto   = iph->nexthdr,
 		.daddr          = iph->daddr,
 		.saddr          = iph->saddr,
 		.flowlabel      = ip6_flowinfo(iph),
-		.flowi6_mark    = skb->mark,
-		.flowi6_proto   = iph->nexthdr,
-		.flowi6_iif     = ifindex,
 	};
 	struct net *net = dev_net(vrf_dev);
 	struct rt6_info *rt6;

include/linux/syscalls.h

@@ -200,6 +200,8 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event)
 #define SYSCALL_DEFINE5(name, ...) SYSCALL_DEFINEx(5, _##name, __VA_ARGS__)
 #define SYSCALL_DEFINE6(name, ...) SYSCALL_DEFINEx(6, _##name, __VA_ARGS__)
 
+#define SYSCALL_DEFINE_MAXARGS	6
+
 #define SYSCALL_DEFINEx(x, sname, ...)				\
 	SYSCALL_METADATA(sname, x, __VA_ARGS__)			\
 	__SYSCALL_DEFINEx(x, sname, __VA_ARGS__)

include/net/act_api.h

@@ -34,7 +34,6 @@ struct tc_action {
 	struct gnet_stats_queue		tcfa_qstats;
 	struct net_rate_estimator __rcu *tcfa_rate_est;
 	spinlock_t			tcfa_lock;
-	struct rcu_head			tcfa_rcu;
 	struct gnet_stats_basic_cpu __percpu *cpu_bstats;
 	struct gnet_stats_queue __percpu *cpu_qstats;
 	struct tc_cookie	*act_cookie;
@@ -50,7 +49,6 @@ struct tc_action {
 #define tcf_qstats	common.tcfa_qstats
 #define tcf_rate_est	common.tcfa_rate_est
 #define tcf_lock	common.tcfa_lock
-#define tcf_rcu		common.tcfa_rcu
 
 /* Update lastuse only if needed, to avoid dirtying a cache line.
  * We use a temp variable to avoid fetching jiffies twice.

include/net/sctp/sctp.h

@@ -127,7 +127,8 @@ int sctp_transport_lookup_process(int (*cb)(struct sctp_transport *, void *),
 				  const union sctp_addr *laddr,
 				  const union sctp_addr *paddr, void *p);
 int sctp_for_each_transport(int (*cb)(struct sctp_transport *, void *),
-			    struct net *net, int pos, void *p);
+			    int (*cb_done)(struct sctp_transport *, void *),
+			    struct net *net, int *pos, void *p);
 int sctp_for_each_endpoint(int (*cb)(struct sctp_endpoint *, void *), void *p);
 int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc,
 		       struct sctp_info *info);

include/net/sctp/ulpevent.h

@@ -153,8 +153,12 @@ __u16 sctp_ulpevent_get_notification_type(const struct sctp_ulpevent *event);
 static inline int sctp_ulpevent_type_enabled(__u16 sn_type,
 					     struct sctp_event_subscribe *mask)
 {
+	int offset = sn_type - SCTP_SN_TYPE_BASE;
 	char *amask = (char *) mask;
-	return amask[sn_type - SCTP_SN_TYPE_BASE];
+
+	if (offset >= sizeof(struct sctp_event_subscribe))
+		return 0;
+	return amask[offset];
 }
 
 /* Given an event subscription, is this event enabled? */

include/trace/events/xdp.h

@@ -138,11 +138,11 @@ DEFINE_EVENT_PRINT(xdp_redirect_template, xdp_redirect_map_err,
 
 #define _trace_xdp_redirect_map(dev, xdp, fwd, map, idx)		\
 	 trace_xdp_redirect_map(dev, xdp, fwd ? fwd->ifindex : 0,	\
-				0, map, idx);
+				0, map, idx)
 
 #define _trace_xdp_redirect_map_err(dev, xdp, fwd, map, idx, err)	\
 	 trace_xdp_redirect_map_err(dev, xdp, fwd ? fwd->ifindex : 0,	\
-				    err, map, idx);
+				    err, map, idx)
 
 #endif /* _TRACE_XDP_H */
 

kernel/bpf/verifier.c

@@ -2292,7 +2292,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			}
 		} else {
 			if (insn->src_reg != BPF_REG_0 || insn->off != 0 ||
-			    (insn->imm != 16 && insn->imm != 32 && insn->imm != 64)) {
+			    (insn->imm != 16 && insn->imm != 32 && insn->imm != 64) ||
+			    BPF_CLASS(insn->code) == BPF_ALU64) {
 				verbose("BPF_END uses reserved fields\n");
 				return -EINVAL;
 			}

kernel/trace/trace_syscalls.c

@@ -565,7 +565,7 @@ static int perf_call_bpf_enter(struct bpf_prog *prog, struct pt_regs *regs,
 	struct syscall_tp_t {
 		unsigned long long regs;
 		unsigned long syscall_nr;
-		unsigned long args[sys_data->nb_args];
+		unsigned long args[SYSCALL_DEFINE_MAXARGS];
 	} param;
 	int i;
 

net/core/filter.c

@@ -2506,21 +2506,19 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
 	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
 	const struct bpf_prog *map_owner = ri->map_owner;
 	struct bpf_map *map = ri->map;
+	struct net_device *fwd = NULL;
 	u32 index = ri->ifindex;
-	struct net_device *fwd;
 	int err;
 
 	ri->ifindex = 0;
 	ri->map = NULL;
 	ri->map_owner = NULL;
 
-	/* This is really only caused by a deliberately crappy
+	if (unlikely(map_owner != xdp_prog)) {
-	 * BPF program, normally we would never hit that case,
+		err = -EFAULT;
-	 * so no need to inform someone via tracepoints either,
+		map = NULL;
-	 * just bail out.
+		goto err;
-	 */
+	}
-	if (unlikely(map_owner != xdp_prog))
-		return -EINVAL;
 
 	fwd = __dev_map_lookup_elem(map, index);
 	if (!fwd) {
@@ -2576,13 +2574,27 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
 			    struct bpf_prog *xdp_prog)
 {
 	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+	const struct bpf_prog *map_owner = ri->map_owner;
+	struct bpf_map *map = ri->map;
+	struct net_device *fwd = NULL;
 	u32 index = ri->ifindex;
-	struct net_device *fwd;
 	unsigned int len;
 	int err = 0;
 
-	fwd = dev_get_by_index_rcu(dev_net(dev), index);
 	ri->ifindex = 0;
+	ri->map = NULL;
+	ri->map_owner = NULL;
+
+	if (map) {
+		if (unlikely(map_owner != xdp_prog)) {
+			err = -EFAULT;
+			map = NULL;
+			goto err;
+		}
+		fwd = __dev_map_lookup_elem(map, index);
+	} else {
+		fwd = dev_get_by_index_rcu(dev_net(dev), index);
+	}
 	if (unlikely(!fwd)) {
 		err = -EINVAL;
 		goto err;
@@ -2600,10 +2612,12 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
 	}
 
 	skb->dev = fwd;
-	_trace_xdp_redirect(dev, xdp_prog, index);
+	map ? _trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index)
+		: _trace_xdp_redirect(dev, xdp_prog, index);
 	return 0;
 err:
-	_trace_xdp_redirect_err(dev, xdp_prog, index, err);
+	map ? _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err)
+		: _trace_xdp_redirect_err(dev, xdp_prog, index, err);
 	return err;
 }
 EXPORT_SYMBOL_GPL(xdp_do_generic_redirect);

net/core/gen_estimator.c

@@ -83,10 +83,10 @@ static void est_timer(unsigned long arg)
 	u64 rate, brate;
 
 	est_fetch_counters(est, &b);
-	brate = (b.bytes - est->last_bytes) << (8 - est->ewma_log);
+	brate = (b.bytes - est->last_bytes) << (10 - est->ewma_log - est->intvl_log);
 	brate -= (est->avbps >> est->ewma_log);
 
-	rate = (u64)(b.packets - est->last_packets) << (8 - est->ewma_log);
+	rate = (u64)(b.packets - est->last_packets) << (10 - est->ewma_log - est->intvl_log);
 	rate -= (est->avpps >> est->ewma_log);
 
 	write_seqcount_begin(&est->seq);

net/ipv4/inet_connection_sock.c

@@ -916,7 +916,6 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req,
 		tcp_sk(child)->fastopen_rsk = NULL;
 	}
 	inet_csk_destroy_sock(child);
-	reqsk_put(req);
 }
 
 struct sock *inet_csk_reqsk_queue_add(struct sock *sk,
@@ -987,6 +986,7 @@ void inet_csk_listen_stop(struct sock *sk)
 		sock_hold(child);
 
 		inet_child_forget(sk, req, child);
+		reqsk_put(req);
 		bh_unlock_sock(child);
 		local_bh_enable();
 		sock_put(child);

net/ipv4/ip_sockglue.c

@@ -1207,7 +1207,6 @@ e_inval:
 void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb)
 {
 	struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb);
-	bool l3slave = ipv4_l3mdev_skb(IPCB(skb)->flags);
 	bool prepare = (inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO) ||
 		       ipv6_sk_rxinfo(sk);
 
@@ -1221,8 +1220,13 @@ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb)
 		 * (e.g., process binds socket to eth0 for Tx which is
 		 * redirected to loopback in the rtable/dst).
 		 */
-		if (pktinfo->ipi_ifindex == LOOPBACK_IFINDEX || l3slave)
+		struct rtable *rt = skb_rtable(skb);
+		bool l3slave = ipv4_l3mdev_skb(IPCB(skb)->flags);
+
+		if (pktinfo->ipi_ifindex == LOOPBACK_IFINDEX)
 			pktinfo->ipi_ifindex = inet_iif(skb);
+		else if (l3slave && rt && rt->rt_iif)
+			pktinfo->ipi_ifindex = rt->rt_iif;
 
 		pktinfo->ipi_spec_dst.s_addr = fib_compute_spec_dst(skb);
 	} else {

net/ipv4/ip_tunnel.c

@@ -176,7 +176,7 @@ skip_key_lookup:
 		return cand;
 
 	t = rcu_dereference(itn->collect_md_tun);
-	if (t)
+	if (t && t->dev->flags & IFF_UP)
 		return t;
 
 	if (itn->fb_tunnel_dev && itn->fb_tunnel_dev->flags & IFF_UP)

net/ipv4/tcp_output.c

@@ -991,6 +991,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	struct tcp_skb_cb *tcb;
 	struct tcp_out_options opts;
 	unsigned int tcp_options_size, tcp_header_size;
+	struct sk_buff *oskb = NULL;
 	struct tcp_md5sig_key *md5;
 	struct tcphdr *th;
 	int err;
@@ -998,12 +999,10 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	BUG_ON(!skb || !tcp_skb_pcount(skb));
 	tp = tcp_sk(sk);
 
-	skb->skb_mstamp = tp->tcp_mstamp;
 	if (clone_it) {
 		TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq
 			- tp->snd_una;
-		tcp_rate_skb_sent(sk, skb);
+		oskb = skb;
-
 		if (unlikely(skb_cloned(skb)))
 			skb = pskb_copy(skb, gfp_mask);
 		else
@@ -1011,6 +1010,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 		if (unlikely(!skb))
 			return -ENOBUFS;
 	}
+	skb->skb_mstamp = tp->tcp_mstamp;
 
 	inet = inet_sk(sk);
 	tcb = TCP_SKB_CB(skb);
@@ -1122,12 +1122,15 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 
 	err = icsk->icsk_af_ops->queue_xmit(sk, skb, &inet->cork.fl);
 
-	if (likely(err <= 0))
+	if (unlikely(err > 0)) {
-		return err;
+		tcp_enter_cwr(sk);
-
+		err = net_xmit_eval(err);
-	tcp_enter_cwr(sk);
+	}
-
+	if (!err && oskb) {
-	return net_xmit_eval(err);
+		oskb->skb_mstamp = tp->tcp_mstamp;
+		tcp_rate_skb_sent(sk, oskb);
+	}
+	return err;
 }
 
 /* This routine just queues the buffer for sending.
@@ -2869,10 +2872,11 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 		     skb_headroom(skb) >= 0xFFFF)) {
 		struct sk_buff *nskb;
 
-		skb->skb_mstamp = tp->tcp_mstamp;
 		nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC);
 		err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
 			     -ENOBUFS;
+		if (!err)
+			skb->skb_mstamp = tp->tcp_mstamp;
 	} else {
 		err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
 	}

net/ipv6/ip6_tunnel.c

@@ -171,7 +171,7 @@ ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_
 	}
 
 	t = rcu_dereference(ip6n->collect_md_tun);
-	if (t)
+	if (t && t->dev->flags & IFF_UP)
 		return t;
 
 	t = rcu_dereference(ip6n->tnls_wc[0]);

net/ipv6/seg6_local.c

@@ -72,10 +72,6 @@ static struct ipv6_sr_hdr *get_srh(struct sk_buff *skb)
 
 	srh = (struct ipv6_sr_hdr *)(skb->data + srhoff);
 
-	/* make sure it's a Segment Routing header (Routing Type 4) */
-	if (srh->type != IPV6_SRCRT_TYPE_4)
-		return NULL;
-
 	len = (srh->hdrlen + 1) << 3;
 
 	if (!pskb_may_pull(skb, srhoff + len))

net/openvswitch/datapath.c

@@ -1112,7 +1112,8 @@ static int ovs_nla_init_match_and_action(struct net *net,
 		if (!a[OVS_FLOW_ATTR_KEY]) {
 			OVS_NLERR(log,
 				  "Flow key attribute not present in set flow.");
-			return -EINVAL;
+			error = -EINVAL;
+			goto error;
 		}
 
 		*acts = get_flow_actions(net, a[OVS_FLOW_ATTR_ACTIONS], key,

net/sched/act_api.c

@@ -53,10 +53,13 @@ static void tcf_action_goto_chain_exec(const struct tc_action *a,
 	res->goto_tp = rcu_dereference_bh(chain->filter_chain);
 }
 
-static void free_tcf(struct rcu_head *head)
+/* XXX: For standalone actions, we don't need a RCU grace period either, because
+ * actions are always connected to filters and filters are already destroyed in
+ * RCU callbacks, so after a RCU grace period actions are already disconnected
+ * from filters. Readers later can not find us.
+ */
+static void free_tcf(struct tc_action *p)
 {
-	struct tc_action *p = container_of(head, struct tc_action, tcfa_rcu);
-
 	free_percpu(p->cpu_bstats);
 	free_percpu(p->cpu_qstats);
 
@@ -76,11 +79,7 @@ static void tcf_idr_remove(struct tcf_idrinfo *idrinfo, struct tc_action *p)
 	idr_remove_ext(&idrinfo->action_idr, p->tcfa_index);
 	spin_unlock_bh(&idrinfo->lock);
 	gen_kill_estimator(&p->tcfa_rate_est);
-	/*
+	free_tcf(p);
-	 * gen_estimator est_timer() might access p->tcfa_lock
-	 * or bstats, wait a RCU grace period before freeing p
-	 */
-	call_rcu(&p->tcfa_rcu, free_tcf);
 }
 
 int __tcf_idr_release(struct tc_action *p, bool bind, bool strict)
@@ -181,7 +180,7 @@ static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
 	idr_for_each_entry_ext(idr, p, id) {
 		ret = __tcf_idr_release(p, false, true);
 		if (ret == ACT_P_DELETED) {
-			module_put(p->ops->owner);
+			module_put(ops->owner);
 			n_i++;
 		} else if (ret < 0) {
 			goto nla_put_failure;
@@ -259,7 +258,7 @@ void tcf_idr_cleanup(struct tc_action *a, struct nlattr *est)
 {
 	if (est)
 		gen_kill_estimator(&a->tcfa_rate_est);
-	call_rcu(&a->tcfa_rcu, free_tcf);
+	free_tcf(a);
 }
 EXPORT_SYMBOL(tcf_idr_cleanup);
 
@@ -515,13 +514,15 @@ EXPORT_SYMBOL(tcf_action_exec);
 
 int tcf_action_destroy(struct list_head *actions, int bind)
 {
+	const struct tc_action_ops *ops;
 	struct tc_action *a, *tmp;
 	int ret = 0;
 
 	list_for_each_entry_safe(a, tmp, actions, list) {
+		ops = a->ops;
 		ret = __tcf_idr_release(a, bind, true);
 		if (ret == ACT_P_DELETED)
-			module_put(a->ops->owner);
+			module_put(ops->owner);
 		else if (ret < 0)
 			return ret;
 	}

net/sched/cls_api.c

@@ -182,7 +182,7 @@ static struct tcf_chain *tcf_chain_create(struct tcf_block *block,
 	list_add_tail(&chain->list, &block->chain_list);
 	chain->block = block;
 	chain->index = chain_index;
-	chain->refcnt = 0;
+	chain->refcnt = 1;
 	return chain;
 }
 
@@ -194,21 +194,20 @@ static void tcf_chain_flush(struct tcf_chain *chain)
 		RCU_INIT_POINTER(*chain->p_filter_chain, NULL);
 	while ((tp = rtnl_dereference(chain->filter_chain)) != NULL) {
 		RCU_INIT_POINTER(chain->filter_chain, tp->next);
+		tcf_chain_put(chain);
 		tcf_proto_destroy(tp);
 	}
 }
 
 static void tcf_chain_destroy(struct tcf_chain *chain)
 {
-	/* May be already removed from the list by the previous call. */
+	list_del(&chain->list);
-	if (!list_empty(&chain->list))
+	kfree(chain);
-		list_del_init(&chain->list);
+}
 
-	/* There might still be a reference held when we got here from
+static void tcf_chain_hold(struct tcf_chain *chain)
-	 * tcf_block_put. Wait for the user to drop reference before free.
+{
-	 */
+	++chain->refcnt;
-	if (!chain->refcnt)
-		kfree(chain);
 }
 
 struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index,
@@ -217,24 +216,19 @@ struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index,
 	struct tcf_chain *chain;
 
 	list_for_each_entry(chain, &block->chain_list, list) {
-		if (chain->index == chain_index)
+		if (chain->index == chain_index) {
-			goto incref;
+			tcf_chain_hold(chain);
+			return chain;
+		}
 	}
-	chain = create ? tcf_chain_create(block, chain_index) : NULL;
 
-incref:
+	return create ? tcf_chain_create(block, chain_index) : NULL;
-	if (chain)
-		chain->refcnt++;
-	return chain;
 }
 EXPORT_SYMBOL(tcf_chain_get);
 
 void tcf_chain_put(struct tcf_chain *chain)
 {
-	/* Destroy unused chain, with exception of chain 0, which is the
+	if (--chain->refcnt == 0)
-	 * default one and has to be always present.
-	 */
-	if (--chain->refcnt == 0 && !chain->filter_chain && chain->index != 0)
 		tcf_chain_destroy(chain);
 }
 EXPORT_SYMBOL(tcf_chain_put);
@@ -279,10 +273,31 @@ void tcf_block_put(struct tcf_block *block)
 	if (!block)
 		return;
 
-	list_for_each_entry_safe(chain, tmp, &block->chain_list, list) {
+	/* XXX: Standalone actions are not allowed to jump to any chain, and
+	 * bound actions should be all removed after flushing. However,
+	 * filters are destroyed in RCU callbacks, we have to hold the chains
+	 * first, otherwise we would always race with RCU callbacks on this list
+	 * without proper locking.
+	 */
+
+	/* Wait for existing RCU callbacks to cool down. */
+	rcu_barrier();
+
+	/* Hold a refcnt for all chains, except 0, in case they are gone. */
+	list_for_each_entry(chain, &block->chain_list, list)
+		if (chain->index)
+			tcf_chain_hold(chain);
+
+	/* No race on the list, because no chain could be destroyed. */
+	list_for_each_entry(chain, &block->chain_list, list)
 		tcf_chain_flush(chain);
-		tcf_chain_destroy(chain);
+
-	}
+	/* Wait for RCU callbacks to release the reference count. */
+	rcu_barrier();
+
+	/* At this point, all the chains should have refcnt == 1. */
+	list_for_each_entry_safe(chain, tmp, &block->chain_list, list)
+		tcf_chain_put(chain);
 	kfree(block);
 }
 EXPORT_SYMBOL(tcf_block_put);
@@ -360,6 +375,7 @@ static void tcf_chain_tp_insert(struct tcf_chain *chain,
 		rcu_assign_pointer(*chain->p_filter_chain, tp);
 	RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain_info));
 	rcu_assign_pointer(*chain_info->pprev, tp);
+	tcf_chain_hold(chain);
 }
 
 static void tcf_chain_tp_remove(struct tcf_chain *chain,
@@ -371,6 +387,7 @@ static void tcf_chain_tp_remove(struct tcf_chain *chain,
 	if (chain->p_filter_chain && tp == chain->filter_chain)
 		RCU_INIT_POINTER(*chain->p_filter_chain, next);
 	RCU_INIT_POINTER(*chain_info->pprev, next);
+	tcf_chain_put(chain);
 }
 
 static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain,

net/sched/cls_rsvp.h

@@ -389,7 +389,7 @@ static unsigned int gen_handle(struct tcf_proto *tp, unsigned salt)
 		if ((data->hgenerator += 0x10000) == 0)
 			data->hgenerator = 0x10000;
 		h = data->hgenerator|salt;
-		if (rsvp_get(tp, h) == 0)
+		if (!rsvp_get(tp, h))
 			return h;
 	}
 	return 0;

net/sctp/sctp_diag.c

@@ -279,9 +279,11 @@ out:
 	return err;
 }
 
-static int sctp_sock_dump(struct sock *sk, void *p)
+static int sctp_sock_dump(struct sctp_transport *tsp, void *p)
 {
+	struct sctp_endpoint *ep = tsp->asoc->ep;
 	struct sctp_comm_param *commp = p;
+	struct sock *sk = ep->base.sk;
 	struct sk_buff *skb = commp->skb;
 	struct netlink_callback *cb = commp->cb;
 	const struct inet_diag_req_v2 *r = commp->r;
@@ -289,9 +291,7 @@ static int sctp_sock_dump(struct sock *sk, void *p)
 	int err = 0;
 
 	lock_sock(sk);
-	if (!sctp_sk(sk)->ep)
+	list_for_each_entry(assoc, &ep->asocs, asocs) {
-		goto release;
-	list_for_each_entry(assoc, &sctp_sk(sk)->ep->asocs, asocs) {
 		if (cb->args[4] < cb->args[1])
 			goto next;
 
@@ -309,7 +309,6 @@ static int sctp_sock_dump(struct sock *sk, void *p)
 					cb->nlh->nlmsg_seq,
 					NLM_F_MULTI, cb->nlh,
 					commp->net_admin) < 0) {
-			cb->args[3] = 1;
 			err = 1;
 			goto release;
 		}
@@ -327,40 +326,30 @@ next:
 		cb->args[4]++;
 	}
 	cb->args[1] = 0;
-	cb->args[2]++;
 	cb->args[3] = 0;
 	cb->args[4] = 0;
 release:
 	release_sock(sk);
-	sock_put(sk);
 	return err;
 }
 
-static int sctp_get_sock(struct sctp_transport *tsp, void *p)
+static int sctp_sock_filter(struct sctp_transport *tsp, void *p)
 {
 	struct sctp_endpoint *ep = tsp->asoc->ep;
 	struct sctp_comm_param *commp = p;
 	struct sock *sk = ep->base.sk;
-	struct netlink_callback *cb = commp->cb;
 	const struct inet_diag_req_v2 *r = commp->r;
 	struct sctp_association *assoc =
 		list_entry(ep->asocs.next, struct sctp_association, asocs);
 
 	/* find the ep only once through the transports by this condition */
 	if (tsp->asoc != assoc)
-		goto out;
+		return 0;
 
 	if (r->sdiag_family != AF_UNSPEC && sk->sk_family != r->sdiag_family)
-		goto out;
+		return 0;
-
-	sock_hold(sk);
-	cb->args[5] = (long)sk;
 
 	return 1;
-
-out:
-	cb->args[2]++;
-	return 0;
 }
 
 static int sctp_ep_dump(struct sctp_endpoint *ep, void *p)
@@ -503,12 +492,8 @@ skip:
 	if (!(idiag_states & ~(TCPF_LISTEN | TCPF_CLOSE)))
 		goto done;
 
-next:
+	sctp_for_each_transport(sctp_sock_filter, sctp_sock_dump,
-	cb->args[5] = 0;
+				net, (int *)&cb->args[2], &commp);
-	sctp_for_each_transport(sctp_get_sock, net, cb->args[2], &commp);
-
-	if (cb->args[5] && !sctp_sock_dump((struct sock *)cb->args[5], &commp))
-		goto next;
 
 done:
 	cb->args[1] = cb->args[4];

net/sctp/socket.c

@@ -4658,29 +4658,39 @@ int sctp_transport_lookup_process(int (*cb)(struct sctp_transport *, void *),
 EXPORT_SYMBOL_GPL(sctp_transport_lookup_process);
 
 int sctp_for_each_transport(int (*cb)(struct sctp_transport *, void *),
-			    struct net *net, int pos, void *p) {
+			    int (*cb_done)(struct sctp_transport *, void *),
+			    struct net *net, int *pos, void *p) {
 	struct rhashtable_iter hti;
-	void *obj;
+	struct sctp_transport *tsp;
-	int err;
+	int ret;
 
-	err = sctp_transport_walk_start(&hti);
+again:
-	if (err)
+	ret = sctp_transport_walk_start(&hti);
-		return err;
+	if (ret)
+		return ret;
 
-	obj = sctp_transport_get_idx(net, &hti, pos + 1);
+	tsp = sctp_transport_get_idx(net, &hti, *pos + 1);
-	for (; !IS_ERR_OR_NULL(obj); obj = sctp_transport_get_next(net, &hti)) {
+	for (; !IS_ERR_OR_NULL(tsp); tsp = sctp_transport_get_next(net, &hti)) {
-		struct sctp_transport *transport = obj;
+		if (!sctp_transport_hold(tsp))
-
-		if (!sctp_transport_hold(transport))
 			continue;
-		err = cb(transport, p);
+		ret = cb(tsp, p);
-		sctp_transport_put(transport);
+		if (ret)
-		if (err)
 			break;
+		(*pos)++;
+		sctp_transport_put(tsp);
 	}
 	sctp_transport_walk_stop(&hti);
 
-	return err;
+	if (ret) {
+		if (cb_done && !cb_done(tsp, p)) {
+			(*pos)++;
+			sctp_transport_put(tsp);
+			goto again;
+		}
+		sctp_transport_put(tsp);
+	}
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(sctp_for_each_transport);
 

net/tls/tls_sw.c

@@ -639,7 +639,7 @@ sendpage_end:
 	return ret;
 }
 
-void tls_sw_free_resources(struct sock *sk)
+static void tls_sw_free_resources(struct sock *sk)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);

tools/testing/selftests/bpf/test_verifier.c

@@ -6629,6 +6629,22 @@ static struct bpf_test tests[] = {
 		.result = REJECT,
 		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
+	{
+		"invalid 64-bit BPF_END",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_0, 0),
+			{
+				.code  = BPF_ALU64 | BPF_END | BPF_TO_LE,
+				.dst_reg = BPF_REG_0,
+				.src_reg = 0,
+				.off   = 0,
+				.imm   = 32,
+			},
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "BPF_END uses reserved fields",
+		.result = REJECT,
+	},
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)