Merge tag 'net-5.18-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from xfrm and can.

  Current release - regressions:

   - rxrpc: restore removed timer deletion

  Current release - new code bugs:

   - gre: fix device lookup for l3mdev use-case

   - xfrm: fix egress device lookup for l3mdev use-case

  Previous releases - regressions:

   - sched: cls_u32: fix netns refcount changes in u32_change()

   - smc: fix sock leak when release after smc_shutdown()

   - xfrm: limit skb_page_frag_refill use to a single page

   - eth: atlantic: invert deep par in pm functions, preventing null
     derefs

   - eth: stmmac: use readl_poll_timeout_atomic() in atomic state

  Previous releases - always broken:

   - gre: fix skb_under_panic on xmit

   - openvswitch: fix OOB access in reserve_sfa_size()

   - dsa: hellcreek: calculate checksums in tagger

   - eth: ice: fix crash in switchdev mode

   - eth: igc:
      - fix infinite loop in release_swfw_sync
      - fix scheduling while atomic"

* tag 'net-5.18-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (37 commits)
  drivers: net: hippi: Fix deadlock in rr_close()
  selftests: mlxsw: vxlan_flooding_ipv6: Prevent flooding of unwanted packets
  selftests: mlxsw: vxlan_flooding: Prevent flooding of unwanted packets
  nfc: MAINTAINERS: add Bug entry
  net: stmmac: Use readl_poll_timeout_atomic() in atomic state
  doc/ip-sysctl: add bc_forwarding
  netlink: reset network and mac headers in netlink_dump()
  net: mscc: ocelot: fix broken IP multicast flooding
  net: dsa: hellcreek: Calculate checksums in tagger
  net: atlantic: invert deep par in pm functions, preventing null derefs
  can: isotp: stop timeout monitoring when no first frame was sent
  bonding: do not discard lowest hash bit for non layer3+4 hashing
  net: lan966x: Make sure to release ptp interrupt
  ipv6: make ip6_rt_gc_expire an atomic_t
  net: Handle l3mdev in ip_tunnel_init_flow
  l3mdev: l3mdev_master_upper_ifindex_by_index_rcu should be using netdev_master_upper_dev_get_rcu
  net/sched: cls_u32: fix possible leak in u32_init_knode()
  net/sched: cls_u32: fix netns refcount changes in u32_change()
  powerpc: Update MAINTAINERS for ibmvnic and VAS
  net: restore alpha order to Ethernet devices in config
  ...

Documentation/networking/ip-sysctl.rst

@@ -267,6 +267,13 @@ ipfrag_max_dist - INTEGER
 	from different IP datagrams, which could result in data corruption.
 	Default: 64
 
+bc_forwarding - INTEGER
+	bc_forwarding enables the feature described in rfc1812#section-5.3.5.2
+	and rfc2644. It allows the router to forward directed broadcast.
+	To enable this feature, the 'all' entry and the input interface entry
+	should be set to 1.
+	Default: 0
+
 INET peer storage
 =================
 

MAINTAINERS

@@ -9337,14 +9337,12 @@ F:	drivers/pci/hotplug/rpaphp*
 
 IBM Power SRIOV Virtual NIC Device Driver
 M:	Dany Madden <drt@linux.ibm.com>
-M:	Sukadev Bhattiprolu <sukadev@linux.ibm.com>
 R:	Thomas Falcon <tlfalcon@linux.ibm.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/ibm/ibmvnic.*
 
 IBM Power Virtual Accelerator Switchboard
-M:	Sukadev Bhattiprolu <sukadev@linux.ibm.com>
 L:	linuxppc-dev@lists.ozlabs.org
 S:	Supported
 F:	arch/powerpc/include/asm/vas.h
@@ -13823,6 +13821,7 @@ M:	Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
 L:	linux-nfc@lists.01.org (subscribers-only)
 L:	netdev@vger.kernel.org
 S:	Maintained
+B:	mailto:linux-nfc@lists.01.org
 F:	Documentation/devicetree/bindings/net/nfc/
 F:	drivers/nfc/
 F:	include/linux/platform_data/nfcmrvl.h

drivers/net/bonding/bond_main.c

@@ -4027,14 +4027,19 @@ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, const v
 	return true;
 }
 
-static u32 bond_ip_hash(u32 hash, struct flow_keys *flow)
+static u32 bond_ip_hash(u32 hash, struct flow_keys *flow, int xmit_policy)
 {
 	hash ^= (__force u32)flow_get_u32_dst(flow) ^
 		(__force u32)flow_get_u32_src(flow);
 	hash ^= (hash >> 16);
 	hash ^= (hash >> 8);
+
 	/* discard lowest hash bit to deal with the common even ports pattern */
-	return hash >> 1;
+	if (xmit_policy == BOND_XMIT_POLICY_LAYER34 ||
+		xmit_policy == BOND_XMIT_POLICY_ENCAP34)
+		return hash >> 1;
+
+	return hash;
 }
 
 /* Generate hash based on xmit policy. If @skb is given it is used to linearize
@@ -4064,7 +4069,7 @@ static u32 __bond_xmit_hash(struct bonding *bond, struct sk_buff *skb, const voi
 			memcpy(&hash, &flow.ports.ports, sizeof(hash));
 	}
 
-	return bond_ip_hash(hash, &flow);
+	return bond_ip_hash(hash, &flow, bond->params.xmit_policy);
 }
 
 /**
@@ -5259,7 +5264,7 @@ static u32 bond_sk_hash_l34(struct sock *sk)
 	/* L4 */
 	memcpy(&hash, &flow.ports.ports, sizeof(hash));
 	/* L3 */
-	return bond_ip_hash(hash, &flow);
+	return bond_ip_hash(hash, &flow, BOND_XMIT_POLICY_LAYER34);
 }
 
 static struct net_device *__bond_sk_get_lower_dev(struct bonding *bond,

drivers/net/ethernet/Kconfig

@@ -35,15 +35,6 @@ source "drivers/net/ethernet/aquantia/Kconfig"
 source "drivers/net/ethernet/arc/Kconfig"
 source "drivers/net/ethernet/asix/Kconfig"
 source "drivers/net/ethernet/atheros/Kconfig"
-source "drivers/net/ethernet/broadcom/Kconfig"
-source "drivers/net/ethernet/brocade/Kconfig"
-source "drivers/net/ethernet/cadence/Kconfig"
-source "drivers/net/ethernet/calxeda/Kconfig"
-source "drivers/net/ethernet/cavium/Kconfig"
-source "drivers/net/ethernet/chelsio/Kconfig"
-source "drivers/net/ethernet/cirrus/Kconfig"
-source "drivers/net/ethernet/cisco/Kconfig"
-source "drivers/net/ethernet/cortina/Kconfig"
 
 config CX_ECAT
 	tristate "Beckhoff CX5020 EtherCAT master support"
@@ -57,6 +48,14 @@ config CX_ECAT
 	  To compile this driver as a module, choose M here. The module
 	  will be called ec_bhf.
 
+source "drivers/net/ethernet/broadcom/Kconfig"
+source "drivers/net/ethernet/cadence/Kconfig"
+source "drivers/net/ethernet/calxeda/Kconfig"
+source "drivers/net/ethernet/cavium/Kconfig"
+source "drivers/net/ethernet/chelsio/Kconfig"
+source "drivers/net/ethernet/cirrus/Kconfig"
+source "drivers/net/ethernet/cisco/Kconfig"
+source "drivers/net/ethernet/cortina/Kconfig"
 source "drivers/net/ethernet/davicom/Kconfig"
 
 config DNET
@@ -85,7 +84,6 @@ source "drivers/net/ethernet/huawei/Kconfig"
 source "drivers/net/ethernet/i825xx/Kconfig"
 source "drivers/net/ethernet/ibm/Kconfig"
 source "drivers/net/ethernet/intel/Kconfig"
-source "drivers/net/ethernet/microsoft/Kconfig"
 source "drivers/net/ethernet/xscale/Kconfig"
 
 config JME
@@ -128,8 +126,9 @@ source "drivers/net/ethernet/mediatek/Kconfig"
 source "drivers/net/ethernet/mellanox/Kconfig"
 source "drivers/net/ethernet/micrel/Kconfig"
 source "drivers/net/ethernet/microchip/Kconfig"
-source "drivers/net/ethernet/moxa/Kconfig"
 source "drivers/net/ethernet/mscc/Kconfig"
+source "drivers/net/ethernet/microsoft/Kconfig"
+source "drivers/net/ethernet/moxa/Kconfig"
 source "drivers/net/ethernet/myricom/Kconfig"
 
 config FEALNX
@@ -141,10 +140,10 @@ config FEALNX
 	  Say Y here to support the Myson MTD-800 family of PCI-based Ethernet
 	  cards. <http://www.myson.com.tw/>
 
+source "drivers/net/ethernet/ni/Kconfig"
 source "drivers/net/ethernet/natsemi/Kconfig"
 source "drivers/net/ethernet/neterion/Kconfig"
 source "drivers/net/ethernet/netronome/Kconfig"
-source "drivers/net/ethernet/ni/Kconfig"
 source "drivers/net/ethernet/8390/Kconfig"
 source "drivers/net/ethernet/nvidia/Kconfig"
 source "drivers/net/ethernet/nxp/Kconfig"
@@ -164,6 +163,7 @@ source "drivers/net/ethernet/packetengines/Kconfig"
 source "drivers/net/ethernet/pasemi/Kconfig"
 source "drivers/net/ethernet/pensando/Kconfig"
 source "drivers/net/ethernet/qlogic/Kconfig"
+source "drivers/net/ethernet/brocade/Kconfig"
 source "drivers/net/ethernet/qualcomm/Kconfig"
 source "drivers/net/ethernet/rdc/Kconfig"
 source "drivers/net/ethernet/realtek/Kconfig"
@@ -171,10 +171,10 @@ source "drivers/net/ethernet/renesas/Kconfig"
 source "drivers/net/ethernet/rocker/Kconfig"
 source "drivers/net/ethernet/samsung/Kconfig"
 source "drivers/net/ethernet/seeq/Kconfig"
-source "drivers/net/ethernet/sfc/Kconfig"
 source "drivers/net/ethernet/sgi/Kconfig"
 source "drivers/net/ethernet/silan/Kconfig"
 source "drivers/net/ethernet/sis/Kconfig"
+source "drivers/net/ethernet/sfc/Kconfig"
 source "drivers/net/ethernet/smsc/Kconfig"
 source "drivers/net/ethernet/socionext/Kconfig"
 source "drivers/net/ethernet/stmicro/Kconfig"

drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c

@@ -444,22 +444,22 @@ static int atl_resume_common(struct device *dev, bool deep)
 
 static int aq_pm_freeze(struct device *dev)
 {
-	return aq_suspend_common(dev, false);
+	return aq_suspend_common(dev, true);
 }
 
 static int aq_pm_suspend_poweroff(struct device *dev)
 {
-	return aq_suspend_common(dev, true);
+	return aq_suspend_common(dev, false);
 }
 
 static int aq_pm_thaw(struct device *dev)
 {
-	return atl_resume_common(dev, false);
+	return atl_resume_common(dev, true);
 }
 
 static int aq_pm_resume_restore(struct device *dev)
 {
-	return atl_resume_common(dev, true);
+	return atl_resume_common(dev, false);
 }
 
 static const struct dev_pm_ops aq_pm_ops = {

drivers/net/ethernet/intel/e1000e/ich8lan.c

@@ -1009,8 +1009,8 @@ static s32 e1000_platform_pm_pch_lpt(struct e1000_hw *hw, bool link)
 {
 	u32 reg = link << (E1000_LTRV_REQ_SHIFT + E1000_LTRV_NOSNOOP_SHIFT) |
 	    link << E1000_LTRV_REQ_SHIFT | E1000_LTRV_SEND;
-	u16 max_ltr_enc_d = 0;	/* maximum LTR decoded by platform */
-	u16 lat_enc_d = 0;	/* latency decoded */
+	u32 max_ltr_enc_d = 0;	/* maximum LTR decoded by platform */
+	u32 lat_enc_d = 0;	/* latency decoded */
 	u16 lat_enc = 0;	/* latency encoded */
 
 	if (link) {

drivers/net/ethernet/intel/ice/ice_eswitch.c

@@ -361,7 +361,8 @@ ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 	np = netdev_priv(netdev);
 	vsi = np->vsi;
 
-	if (ice_is_reset_in_progress(vsi->back->state))
+	if (ice_is_reset_in_progress(vsi->back->state) ||
+	    test_bit(ICE_VF_DIS, vsi->back->state))
 		return NETDEV_TX_BUSY;
 
 	repr = ice_netdev_to_repr(netdev);

drivers/net/ethernet/intel/ice/ice_eswitch.h

@@ -52,7 +52,7 @@ static inline void ice_eswitch_update_repr(struct ice_vsi *vsi) { }
 
 static inline int ice_eswitch_configure(struct ice_pf *pf)
 {
-	return -EOPNOTSUPP;
+	return 0;
 }
 
 static inline int ice_eswitch_rebuild(struct ice_pf *pf)

drivers/net/ethernet/intel/ice/ice_nvm.c

@@ -641,6 +641,7 @@ ice_get_orom_civd_data(struct ice_hw *hw, enum ice_bank_select bank,
 	status = ice_read_flash_module(hw, bank, ICE_SR_1ST_OROM_BANK_PTR, 0,
 				       orom_data, hw->flash.banks.orom_size);
 	if (status) {
+		vfree(orom_data);
 		ice_debug(hw, ICE_DBG_NVM, "Unable to read Option ROM data\n");
 		return status;
 	}

drivers/net/ethernet/intel/ice/ice_xsk.c

@@ -415,8 +415,8 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp,
  */
 static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
 {
+	u32 nb_buffs_extra = 0, nb_buffs = 0;
 	union ice_32b_rx_flex_desc *rx_desc;
-	u32 nb_buffs_extra = 0, nb_buffs;
 	u16 ntu = rx_ring->next_to_use;
 	u16 total_count = count;
 	struct xdp_buff **xdp;
@@ -428,6 +428,10 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
 		nb_buffs_extra = ice_fill_rx_descs(rx_ring->xsk_pool, xdp,
 						   rx_desc,
 						   rx_ring->count - ntu);
+		if (nb_buffs_extra != rx_ring->count - ntu) {
+			ntu += nb_buffs_extra;
+			goto exit;
+		}
 		rx_desc = ICE_RX_DESC(rx_ring, 0);
 		xdp = ice_xdp_buf(rx_ring, 0);
 		ntu = 0;
@@ -441,6 +445,7 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
 	if (ntu == rx_ring->count)
 		ntu = 0;
 
+exit:
 	if (rx_ring->next_to_use != ntu)
 		ice_release_rx_desc(rx_ring, ntu);
 

drivers/net/ethernet/intel/igc/igc_i225.c

@@ -156,8 +156,15 @@ void igc_release_swfw_sync_i225(struct igc_hw *hw, u16 mask)
 {
 	u32 swfw_sync;
 
-	while (igc_get_hw_semaphore_i225(hw))
-		; /* Empty */
+	/* Releasing the resource requires first getting the HW semaphore.
+	 * If we fail to get the semaphore, there is nothing we can do,
+	 * except log an error and quit. We are not allowed to hang here
+	 * indefinitely, as it may cause denial of service or system crash.
+	 */
+	if (igc_get_hw_semaphore_i225(hw)) {
+		hw_dbg("Failed to release SW_FW_SYNC.\n");
+		return;
+	}
 
 	swfw_sync = rd32(IGC_SW_FW_SYNC);
 	swfw_sync &= ~mask;

drivers/net/ethernet/intel/igc/igc_phy.c

@@ -581,7 +581,7 @@ static s32 igc_read_phy_reg_mdic(struct igc_hw *hw, u32 offset, u16 *data)
 	 * the lower time out
 	 */
 	for (i = 0; i < IGC_GEN_POLL_TIMEOUT; i++) {
-		usleep_range(500, 1000);
+		udelay(50);
 		mdic = rd32(IGC_MDIC);
 		if (mdic & IGC_MDIC_READY)
 			break;
@@ -638,7 +638,7 @@ static s32 igc_write_phy_reg_mdic(struct igc_hw *hw, u32 offset, u16 data)
 	 * the lower time out
 	 */
 	for (i = 0; i < IGC_GEN_POLL_TIMEOUT; i++) {
-		usleep_range(500, 1000);
+		udelay(50);
 		mdic = rd32(IGC_MDIC);
 		if (mdic & IGC_MDIC_READY)
 			break;

drivers/net/ethernet/intel/igc/igc_ptp.c

@@ -992,6 +992,17 @@ static void igc_ptp_time_restore(struct igc_adapter *adapter)
 	igc_ptp_write_i225(adapter, &ts);
 }
 
+static void igc_ptm_stop(struct igc_adapter *adapter)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u32 ctrl;
+
+	ctrl = rd32(IGC_PTM_CTRL);
+	ctrl &= ~IGC_PTM_CTRL_EN;
+
+	wr32(IGC_PTM_CTRL, ctrl);
+}
+
 /**
  * igc_ptp_suspend - Disable PTP work items and prepare for suspend
  * @adapter: Board private structure
@@ -1009,8 +1020,10 @@ void igc_ptp_suspend(struct igc_adapter *adapter)
 	adapter->ptp_tx_skb = NULL;
 	clear_bit_unlock(__IGC_PTP_TX_IN_PROGRESS, &adapter->state);
 
-	if (pci_device_is_present(adapter->pdev))
+	if (pci_device_is_present(adapter->pdev)) {
 		igc_ptp_time_save(adapter);
+		igc_ptm_stop(adapter);
+	}
 }
 
 /**

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

@@ -423,7 +423,7 @@ mlxsw_sp_span_gretap4_route(const struct net_device *to_dev,
 
 	parms = mlxsw_sp_ipip_netdev_parms4(to_dev);
 	ip_tunnel_init_flow(&fl4, parms.iph.protocol, *daddrp, *saddrp,
-			    0, 0, parms.link, tun->fwmark, 0);
+			    0, 0, dev_net(to_dev), parms.link, tun->fwmark, 0);
 
 	rt = ip_route_output_key(tun->net, &fl4);
 	if (IS_ERR(rt))

drivers/net/ethernet/microchip/lan966x/lan966x_main.c

@@ -671,6 +671,9 @@ static void lan966x_cleanup_ports(struct lan966x *lan966x)
 		disable_irq(lan966x->ana_irq);
 		lan966x->ana_irq = -ENXIO;
 	}
+
+	if (lan966x->ptp_irq)
+		devm_free_irq(lan966x->dev, lan966x->ptp_irq, lan966x);
 }
 
 static int lan966x_probe_port(struct lan966x *lan966x, u32 p,

drivers/net/ethernet/mscc/ocelot.c

@@ -2859,6 +2859,8 @@ static void ocelot_port_set_mcast_flood(struct ocelot *ocelot, int port,
 		val = BIT(port);
 
 	ocelot_rmw_rix(ocelot, val, BIT(port), ANA_PGID_PGID, PGID_MC);
+	ocelot_rmw_rix(ocelot, val, BIT(port), ANA_PGID_PGID, PGID_MCIPV4);
+	ocelot_rmw_rix(ocelot, val, BIT(port), ANA_PGID_PGID, PGID_MCIPV6);
 }
 
 static void ocelot_port_set_bcast_flood(struct ocelot *ocelot, int port,

drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c

@@ -71,9 +71,9 @@ static int init_systime(void __iomem *ioaddr, u32 sec, u32 nsec)
 	writel(value, ioaddr + PTP_TCR);
 
 	/* wait for present system time initialize to complete */
-	return readl_poll_timeout(ioaddr + PTP_TCR, value,
+	return readl_poll_timeout_atomic(ioaddr + PTP_TCR, value,
 				 !(value & PTP_TCR_TSINIT),
-				 10000, 100000);
+				 10, 100000);
 }
 
 static int config_addend(void __iomem *ioaddr, u32 addend)

drivers/net/hippi/rrunner.c

@@ -1355,7 +1355,9 @@ static int rr_close(struct net_device *dev)
 
 	rrpriv->fw_running = 0;
 
+	spin_unlock_irqrestore(&rrpriv->lock, flags);
 	del_timer_sync(&rrpriv->timer);
+	spin_lock_irqsave(&rrpriv->lock, flags);
 
 	writel(0, &regs->TxPi);
 	writel(0, &regs->IpRxPi);

drivers/net/phy/microchip_t1.c

@@ -743,6 +743,7 @@ static struct phy_driver microchip_t1_phy_driver[] = {
 	{
 		PHY_ID_MATCH_MODEL(PHY_ID_LAN937X),
 		.name		= "Microchip LAN937x T1",
+		.flags          = PHY_POLL_CABLE_TEST,
 		.features	= PHY_BASIC_T1_FEATURES,
 		.config_init	= lan87xx_config_init,
 		.suspend	= genphy_suspend,

include/net/esp.h

@@ -4,8 +4,6 @@
 
 #include <linux/skbuff.h>
 
-#define ESP_SKB_FRAG_MAXSIZE (PAGE_SIZE << SKB_FRAG_PAGE_ORDER)
-
 struct ip_esp_hdr;
 
 static inline struct ip_esp_hdr *ip_esp_hdr(const struct sk_buff *skb)

include/net/ip_tunnels.h

@@ -243,11 +243,18 @@ static inline __be32 tunnel_id_to_key32(__be64 tun_id)
 static inline void ip_tunnel_init_flow(struct flowi4 *fl4,
 				       int proto,
 				       __be32 daddr, __be32 saddr,
-				       __be32 key, __u8 tos, int oif,
+				       __be32 key, __u8 tos,
+				       struct net *net, int oif,
 				       __u32 mark, __u32 tun_inner_hash)
 {
 	memset(fl4, 0, sizeof(*fl4));
-	fl4->flowi4_oif = oif;
+
+	if (oif) {
+		fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index_rcu(net, oif);
+		/* Legacy VRF/l3mdev use case */
+		fl4->flowi4_oif = fl4->flowi4_l3mdev ? 0 : oif;
+	}
+
 	fl4->daddr = daddr;
 	fl4->saddr = saddr;
 	fl4->flowi4_tos = tos;

include/net/netns/ipv6.h

@@ -75,8 +75,8 @@ struct netns_ipv6 {
 	struct list_head	fib6_walkers;
 	rwlock_t		fib6_walker_lock;
 	spinlock_t		fib6_gc_lock;
-	unsigned int		 ip6_rt_gc_expire;
-	unsigned long		 ip6_rt_last_gc;
+	atomic_t		ip6_rt_gc_expire;
+	unsigned long		ip6_rt_last_gc;
 	unsigned char		flowlabel_has_excl;
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
 	bool			fib6_has_custom_rules;

net/can/isotp.c

@@ -906,6 +906,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 	struct canfd_frame *cf;
 	int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0;
 	int wait_tx_done = (so->opt.flags & CAN_ISOTP_WAIT_TX_DONE) ? 1 : 0;
+	s64 hrtimer_sec = 0;
 	int off;
 	int err;
 
@@ -1004,7 +1005,9 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 		isotp_create_fframe(cf, so, ae);
 
 		/* start timeout for FC */
-		hrtimer_start(&so->txtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT);
+		hrtimer_sec = 1;
+		hrtimer_start(&so->txtimer, ktime_set(hrtimer_sec, 0),
+			      HRTIMER_MODE_REL_SOFT);
 	}
 
 	/* send the first or only CAN frame */
@@ -1017,6 +1020,11 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 	if (err) {
 		pr_notice_once("can-isotp: %s: can_send_ret %pe\n",
 			       __func__, ERR_PTR(err));
+
+		/* no transmission -> no timeout monitoring */
+		if (hrtimer_sec)
+			hrtimer_cancel(&so->txtimer);
+
 		goto err_out_drop;
 	}
 

net/dsa/tag_hellcreek.c

@@ -21,6 +21,14 @@ static struct sk_buff *hellcreek_xmit(struct sk_buff *skb,
 	struct dsa_port *dp = dsa_slave_to_port(dev);
 	u8 *tag;
 
+	/* Calculate checksums (if required) before adding the trailer tag to
+	 * avoid including it in calculations. That would lead to wrong
+	 * checksums after the switch strips the tag.
+	 */
+	if (skb->ip_summed == CHECKSUM_PARTIAL &&
+	    skb_checksum_help(skb))
+		return NULL;
+
 	/* Tag encoding */
 	tag  = skb_put(skb, HELLCREEK_TAG_LEN);
 	*tag = BIT(dp->index);

net/ipv4/esp4.c

@@ -446,7 +446,6 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 	struct page *page;
 	struct sk_buff *trailer;
 	int tailen = esp->tailen;
-	unsigned int allocsz;
 
 	/* this is non-NULL only with TCP/UDP Encapsulation */
 	if (x->encap) {
@@ -456,8 +455,8 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 			return err;
 	}
 
-	allocsz = ALIGN(skb->data_len + tailen, L1_CACHE_BYTES);
-	if (allocsz > ESP_SKB_FRAG_MAXSIZE)
+	if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE ||
+	    ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE)
 		goto cow;
 
 	if (!skb_cloned(skb)) {

net/ipv4/ip_gre.c

@@ -605,8 +605,8 @@ static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 	key = &info->key;
 	ip_tunnel_init_flow(&fl4, IPPROTO_GRE, key->u.ipv4.dst, key->u.ipv4.src,
 			    tunnel_id_to_key32(key->tun_id),
-			    key->tos & ~INET_ECN_MASK, 0, skb->mark,
-			    skb_get_hash(skb));
+			    key->tos & ~INET_ECN_MASK, dev_net(dev), 0,
+			    skb->mark, skb_get_hash(skb));
 	rt = ip_route_output_key(dev_net(dev), &fl4);
 	if (IS_ERR(rt))
 		return PTR_ERR(rt);

net/ipv4/ip_tunnel.c

@@ -294,8 +294,8 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 
 		ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr,
 				    iph->saddr, tunnel->parms.o_key,
-				    RT_TOS(iph->tos), tunnel->parms.link,
-				    tunnel->fwmark, 0);
+				    RT_TOS(iph->tos), dev_net(dev),
+				    tunnel->parms.link, tunnel->fwmark, 0);
 		rt = ip_route_output_key(tunnel->net, &fl4);
 
 		if (!IS_ERR(rt)) {
@@ -570,7 +570,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	}
 	ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src,
 			    tunnel_id_to_key32(key->tun_id), RT_TOS(tos),
-			    0, skb->mark, skb_get_hash(skb));
+			    dev_net(dev), 0, skb->mark, skb_get_hash(skb));
 	if (tunnel->encap.type != TUNNEL_ENCAP_NONE)
 		goto tx_error;
 
@@ -726,7 +726,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr,
-			    tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link,
+			    tunnel->parms.o_key, RT_TOS(tos),
+			    dev_net(dev), tunnel->parms.link,
 			    tunnel->fwmark, skb_get_hash(skb));
 
 	if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0)

net/ipv6/esp6.c

@@ -482,7 +482,6 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info
 	struct page *page;
 	struct sk_buff *trailer;
 	int tailen = esp->tailen;
-	unsigned int allocsz;
 
 	if (x->encap) {
 		int err = esp6_output_encap(x, skb, esp);
@@ -491,8 +490,8 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info
 			return err;
 	}
 
-	allocsz = ALIGN(skb->data_len + tailen, L1_CACHE_BYTES);
-	if (allocsz > ESP_SKB_FRAG_MAXSIZE)
+	if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE ||
+	    ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE)
 		goto cow;
 
 	if (!skb_cloned(skb)) {

net/ipv6/ip6_gre.c

@@ -733,9 +733,6 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
 	else
 		fl6->daddr = tunnel->parms.raddr;
 
-	if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen))
-		return -ENOMEM;
-
 	/* Push GRE header. */
 	protocol = (dev->type == ARPHRD_ETHER) ? htons(ETH_P_TEB) : proto;
 
@@ -743,6 +740,7 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
 		struct ip_tunnel_info *tun_info;
 		const struct ip_tunnel_key *key;
 		__be16 flags;
+		int tun_hlen;
 
 		tun_info = skb_tunnel_info_txcheck(skb);
 		if (IS_ERR(tun_info) ||
@@ -760,9 +758,12 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
 		dsfield = key->tos;
 		flags = key->tun_flags &
 			(TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ);
-		tunnel->tun_hlen = gre_calc_hlen(flags);
+		tun_hlen = gre_calc_hlen(flags);
 
-		gre_build_header(skb, tunnel->tun_hlen,
+		if (skb_cow_head(skb, dev->needed_headroom ?: tun_hlen + tunnel->encap_hlen))
+			return -ENOMEM;
+
+		gre_build_header(skb, tun_hlen,
 				 flags, protocol,
 				 tunnel_id_to_key32(tun_info->key.tun_id),
 				 (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++)
@@ -772,6 +773,9 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
 		if (tunnel->parms.o_flags & TUNNEL_SEQ)
 			tunnel->o_seqno++;
 
+		if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen))
+			return -ENOMEM;
+
 		gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags,
 				 protocol, tunnel->parms.o_key,
 				 htonl(tunnel->o_seqno));

net/ipv6/route.c

@@ -3292,6 +3292,7 @@ static int ip6_dst_gc(struct dst_ops *ops)
 	int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity;
 	int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout;
 	unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc;
+	unsigned int val;
 	int entries;
 
 	entries = dst_entries_get_fast(ops);
@@ -3302,13 +3303,13 @@ static int ip6_dst_gc(struct dst_ops *ops)
 	    entries <= rt_max_size)
 		goto out;
 
-	net->ipv6.ip6_rt_gc_expire++;
-	fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, true);
+	fib6_run_gc(atomic_inc_return(&net->ipv6.ip6_rt_gc_expire), net, true);
 	entries = dst_entries_get_slow(ops);
 	if (entries < ops->gc_thresh)
-		net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1;
+		atomic_set(&net->ipv6.ip6_rt_gc_expire, rt_gc_timeout >> 1);
 out:
-	net->ipv6.ip6_rt_gc_expire -= net->ipv6.ip6_rt_gc_expire>>rt_elasticity;
+	val = atomic_read(&net->ipv6.ip6_rt_gc_expire);
+	atomic_set(&net->ipv6.ip6_rt_gc_expire, val - (val >> rt_elasticity));
 	return entries > rt_max_size;
 }
 
@@ -6509,7 +6510,7 @@ static int __net_init ip6_route_net_init(struct net *net)
 	net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40;
 	net->ipv6.sysctl.skip_notify_on_dev_down = 0;
 
-	net->ipv6.ip6_rt_gc_expire = 30*HZ;
+	atomic_set(&net->ipv6.ip6_rt_gc_expire, 30*HZ);
 
 	ret = 0;
 out:

net/l3mdev/l3mdev.c

@@ -147,7 +147,7 @@ int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex)
 
 	dev = dev_get_by_index_rcu(net, ifindex);
 	while (dev && !netif_is_l3_master(dev))
-		dev = netdev_master_upper_dev_get(dev);
+		dev = netdev_master_upper_dev_get_rcu(dev);
 
 	return dev ? dev->ifindex : 0;
 }

net/netlink/af_netlink.c

@@ -2263,6 +2263,13 @@ static int netlink_dump(struct sock *sk)
 	 * single netdev. The outcome is MSG_TRUNC error.
 	 */
 	skb_reserve(skb, skb_tailroom(skb) - alloc_size);
+
+	/* Make sure malicious BPF programs can not read unitialized memory
+	 * from skb->head -> skb->data
+	 */
+	skb_reset_network_header(skb);
+	skb_reset_mac_header(skb);
+
 	netlink_skb_set_owner_r(skb, sk);
 
 	if (nlk->dump_done_errno > 0) {

net/openvswitch/flow_netlink.c

@@ -2465,7 +2465,7 @@ static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa,
 	new_acts_size = max(next_offset + req_size, ksize(*sfa) * 2);
 
 	if (new_acts_size > MAX_ACTIONS_BUFSIZE) {
-		if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size) {
+		if ((next_offset + req_size) > MAX_ACTIONS_BUFSIZE) {
 			OVS_NLERR(log, "Flow action size exceeds max %u",
 				  MAX_ACTIONS_BUFSIZE);
 			return ERR_PTR(-EMSGSIZE);

net/packet/af_packet.c

@@ -2858,8 +2858,9 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 
 		status = TP_STATUS_SEND_REQUEST;
 		err = po->xmit(skb);
-		if (unlikely(err > 0)) {
-			err = net_xmit_errno(err);
+		if (unlikely(err != 0)) {
+			if (err > 0)
+				err = net_xmit_errno(err);
 			if (err && __packet_get_status(po, ph) ==
 				   TP_STATUS_AVAILABLE) {
 				/* skb was destructed already */
@@ -3060,8 +3061,12 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		skb->no_fcs = 1;
 
 	err = po->xmit(skb);
-	if (err > 0 && (err = net_xmit_errno(err)) != 0)
-		goto out_unlock;
+	if (unlikely(err != 0)) {
+		if (err > 0)
+			err = net_xmit_errno(err);
+		if (err)
+			goto out_unlock;
+	}
 
 	dev_put(dev);
 

net/rxrpc/net_ns.c

@@ -113,7 +113,9 @@ static __net_exit void rxrpc_exit_net(struct net *net)
 	struct rxrpc_net *rxnet = rxrpc_net(net);
 
 	rxnet->live = false;
+	del_timer_sync(&rxnet->peer_keepalive_timer);
 	cancel_work_sync(&rxnet->peer_keepalive_work);
+	/* Remove the timer again as the worker may have restarted it. */
 	del_timer_sync(&rxnet->peer_keepalive_timer);
 	rxrpc_destroy_all_calls(rxnet);
 	rxrpc_destroy_all_connections(rxnet);

net/sched/cls_u32.c

@@ -386,14 +386,19 @@ static int u32_init(struct tcf_proto *tp)
 	return 0;
 }
 
-static int u32_destroy_key(struct tc_u_knode *n, bool free_pf)
+static void __u32_destroy_key(struct tc_u_knode *n)
 {
 	struct tc_u_hnode *ht = rtnl_dereference(n->ht_down);
 
 	tcf_exts_destroy(&n->exts);
-	tcf_exts_put_net(&n->exts);
 	if (ht && --ht->refcnt == 0)
 		kfree(ht);
+	kfree(n);
+}
+
+static void u32_destroy_key(struct tc_u_knode *n, bool free_pf)
+{
+	tcf_exts_put_net(&n->exts);
 #ifdef CONFIG_CLS_U32_PERF
 	if (free_pf)
 		free_percpu(n->pf);
@@ -402,8 +407,7 @@ static int u32_destroy_key(struct tc_u_knode *n, bool free_pf)
 	if (free_pf)
 		free_percpu(n->pcpu_success);
 #endif
-	kfree(n);
-	return 0;
+	__u32_destroy_key(n);
 }
 
 /* u32_delete_key_rcu should be called when free'ing a copied
@@ -811,10 +815,6 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp,
 	new->flags = n->flags;
 	RCU_INIT_POINTER(new->ht_down, ht);
 
-	/* bump reference count as long as we hold pointer to structure */
-	if (ht)
-		ht->refcnt++;
-
 #ifdef CONFIG_CLS_U32_PERF
 	/* Statistics may be incremented by readers during update
 	 * so we must keep them in tact. When the node is later destroyed
@@ -836,6 +836,10 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp,
 		return NULL;
 	}
 
+	/* bump reference count as long as we hold pointer to structure */
+	if (ht)
+		ht->refcnt++;
+
 	return new;
 }
 
@@ -900,13 +904,13 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 				    extack);
 
 		if (err) {
-			u32_destroy_key(new, false);
+			__u32_destroy_key(new);
 			return err;
 		}
 
 		err = u32_replace_hw_knode(tp, new, flags, extack);
 		if (err) {
-			u32_destroy_key(new, false);
+			__u32_destroy_key(new);
 			return err;
 		}
 

net/smc/af_smc.c

@@ -2674,8 +2674,10 @@ static int smc_shutdown(struct socket *sock, int how)
 	if (smc->use_fallback) {
 		rc = kernel_sock_shutdown(smc->clcsock, how);
 		sk->sk_shutdown = smc->clcsock->sk->sk_shutdown;
-		if (sk->sk_shutdown == SHUTDOWN_MASK)
+		if (sk->sk_shutdown == SHUTDOWN_MASK) {
 			sk->sk_state = SMC_CLOSED;
+			sock_put(sk);
+		}
 		goto out;
 	}
 	switch (how) {

net/xfrm/xfrm_policy.c

@@ -2593,12 +2593,14 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
 
 		if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) {
 			__u32 mark = 0;
+			int oif;
 
 			if (xfrm[i]->props.smark.v || xfrm[i]->props.smark.m)
 				mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]);
 
 			family = xfrm[i]->props.family;
-			dst = xfrm_dst_lookup(xfrm[i], tos, fl->flowi_oif,
+			oif = fl->flowi_oif ? : fl->flowi_l3mdev;
+			dst = xfrm_dst_lookup(xfrm[i], tos, oif,
 					      &saddr, &daddr, family, mark);
 			err = PTR_ERR(dst);
 			if (IS_ERR(dst))

tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh

@@ -159,6 +159,17 @@ flooding_remotes_add()
 	local lsb
 	local i
 
+	# Prevent unwanted packets from entering the bridge and interfering
+	# with the test.
+	tc qdisc add dev br0 clsact
+	tc filter add dev br0 egress protocol all pref 1 handle 1 \
+		matchall skip_hw action drop
+	tc qdisc add dev $h1 clsact
+	tc filter add dev $h1 egress protocol all pref 1 handle 1 \
+		flower skip_hw dst_mac de:ad:be:ef:13:37 action pass
+	tc filter add dev $h1 egress protocol all pref 2 handle 2 \
+		matchall skip_hw action drop
+
 	for i in $(eval echo {1..$num_remotes}); do
 		lsb=$((i + 1))
 
@@ -195,6 +206,12 @@ flooding_filters_del()
 	done
 
 	tc qdisc del dev $rp2 clsact
+
+	tc filter del dev $h1 egress protocol all pref 2 handle 2 matchall
+	tc filter del dev $h1 egress protocol all pref 1 handle 1 flower
+	tc qdisc del dev $h1 clsact
+	tc filter del dev br0 egress protocol all pref 1 handle 1 matchall
+	tc qdisc del dev br0 clsact
 }
 
 flooding_check_packets()

tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh

@@ -172,6 +172,17 @@ flooding_filters_add()
 	local lsb
 	local i
 
+	# Prevent unwanted packets from entering the bridge and interfering
+	# with the test.
+	tc qdisc add dev br0 clsact
+	tc filter add dev br0 egress protocol all pref 1 handle 1 \
+		matchall skip_hw action drop
+	tc qdisc add dev $h1 clsact
+	tc filter add dev $h1 egress protocol all pref 1 handle 1 \
+		flower skip_hw dst_mac de:ad:be:ef:13:37 action pass
+	tc filter add dev $h1 egress protocol all pref 2 handle 2 \
+		matchall skip_hw action drop
+
 	tc qdisc add dev $rp2 clsact
 
 	for i in $(eval echo {1..$num_remotes}); do
@@ -194,6 +205,12 @@ flooding_filters_del()
 	done
 
 	tc qdisc del dev $rp2 clsact
+
+	tc filter del dev $h1 egress protocol all pref 2 handle 2 matchall
+	tc filter del dev $h1 egress protocol all pref 1 handle 1 flower
+	tc qdisc del dev $h1 clsact
+	tc filter del dev br0 egress protocol all pref 1 handle 1 matchall
+	tc qdisc del dev br0 clsact
 }
 
 flooding_check_packets()