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

Pull networking fixes from David Miller:

 1) BPF tail call handling bug fixes from Daniel Borkmann.

 2) Fix allowance of too many rx queues in sfc driver, from Bert
    Kenward.

 3) Non-loopback ipv6 packets claiming src of ::1 should be dropped,
    from Florian Westphal.

 4) Statistics requests on KSZ9031 can crash, fix from Grygorii
    Strashko.

 5) TX ring handling fixes in mediatek driver, from Sean Wang.

 6) ip_ra_control can deadlock, fix lock acquisition ordering to fix,
    from Cong WANG.

 7) Fix use after free in ip_recv_error(), from Willem de Buijn.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net:
  bpf: fix checking xdp_adjust_head on tail calls
  bpf: fix cb access in socket filter programs on tail calls
  ipv6: drop non loopback packets claiming to originate from ::1
  net: ethernet: mediatek: fix inconsistency of port number carried in TXD
  net: ethernet: mediatek: fix inconsistency between TXD and the used buffer
  net: phy: micrel: fix crash when statistic requested for KSZ9031 phy
  net: vrf: Fix setting NLM_F_EXCL flag when adding l3mdev rule
  net: thunderx: Fix set_max_bgx_per_node for 81xx rgx
  net-timestamp: avoid use-after-free in ip_recv_error
  ipv4: fix a deadlock in ip_ra_control
  sfc: limit the number of receive queues

drivers/net/ethernet/cavium/thunder/thunder_bgx.c

@@ -134,6 +134,7 @@ static void set_max_bgx_per_node(struct pci_dev *pdev)
 	pci_read_config_word(pdev, PCI_SUBSYSTEM_ID, &sdevid);
 	switch (sdevid) {
 	case PCI_SUBSYS_DEVID_81XX_BGX:
+	case PCI_SUBSYS_DEVID_81XX_RGX:
 		max_bgx_per_node = MAX_BGX_PER_CN81XX;
 		break;
 	case PCI_SUBSYS_DEVID_83XX_BGX:

drivers/net/ethernet/cavium/thunder/thunder_bgx.h

@@ -16,6 +16,7 @@
 /* Subsystem device IDs */
 #define PCI_SUBSYS_DEVID_88XX_BGX		0xA126
 #define PCI_SUBSYS_DEVID_81XX_BGX		0xA226
+#define PCI_SUBSYS_DEVID_81XX_RGX		0xA254
 #define PCI_SUBSYS_DEVID_83XX_BGX		0xA326
 
 #define    MAX_BGX_THUNDER			8 /* Max 2 nodes, 4 per node */

drivers/net/ethernet/mediatek/mtk_eth_soc.c

@@ -613,7 +613,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev,
 	struct mtk_mac *mac = netdev_priv(dev);
 	struct mtk_eth *eth = mac->hw;
 	struct mtk_tx_dma *itxd, *txd;
-	struct mtk_tx_buf *tx_buf;
+	struct mtk_tx_buf *itx_buf, *tx_buf;
 	dma_addr_t mapped_addr;
 	unsigned int nr_frags;
 	int i, n_desc = 1;
@@ -627,8 +627,8 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev,
 	fport = (mac->id + 1) << TX_DMA_FPORT_SHIFT;
 	txd4 |= fport;
 
-	tx_buf = mtk_desc_to_tx_buf(ring, itxd);
-	memset(tx_buf, 0, sizeof(*tx_buf));
+	itx_buf = mtk_desc_to_tx_buf(ring, itxd);
+	memset(itx_buf, 0, sizeof(*itx_buf));
 
 	if (gso)
 		txd4 |= TX_DMA_TSO;
@@ -647,9 +647,11 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev,
 		return -ENOMEM;
 
 	WRITE_ONCE(itxd->txd1, mapped_addr);
-	tx_buf->flags |= MTK_TX_FLAGS_SINGLE0;
-	dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr);
-	dma_unmap_len_set(tx_buf, dma_len0, skb_headlen(skb));
+	itx_buf->flags |= MTK_TX_FLAGS_SINGLE0;
+	itx_buf->flags |= (!mac->id) ? MTK_TX_FLAGS_FPORT0 :
+			  MTK_TX_FLAGS_FPORT1;
+	dma_unmap_addr_set(itx_buf, dma_addr0, mapped_addr);
+	dma_unmap_len_set(itx_buf, dma_len0, skb_headlen(skb));
 
 	/* TX SG offload */
 	txd = itxd;
@@ -685,11 +687,13 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev,
 					       last_frag * TX_DMA_LS0));
 			WRITE_ONCE(txd->txd4, fport);
 
-			tx_buf->skb = (struct sk_buff *)MTK_DMA_DUMMY_DESC;
 			tx_buf = mtk_desc_to_tx_buf(ring, txd);
 			memset(tx_buf, 0, sizeof(*tx_buf));
-
+			tx_buf->skb = (struct sk_buff *)MTK_DMA_DUMMY_DESC;
 			tx_buf->flags |= MTK_TX_FLAGS_PAGE0;
+			tx_buf->flags |= (!mac->id) ? MTK_TX_FLAGS_FPORT0 :
+					 MTK_TX_FLAGS_FPORT1;
+
 			dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr);
 			dma_unmap_len_set(tx_buf, dma_len0, frag_map_size);
 			frag_size -= frag_map_size;
@@ -698,7 +702,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	/* store skb to cleanup */
-	tx_buf->skb = skb;
+	itx_buf->skb = skb;
 
 	WRITE_ONCE(itxd->txd4, txd4);
 	WRITE_ONCE(itxd->txd3, (TX_DMA_SWC | TX_DMA_PLEN0(skb_headlen(skb)) |
@@ -1012,17 +1016,16 @@ static int mtk_poll_tx(struct mtk_eth *eth, int budget)
 
 	while ((cpu != dma) && budget) {
 		u32 next_cpu = desc->txd2;
-		int mac;
+		int mac = 0;
 
 		desc = mtk_qdma_phys_to_virt(ring, desc->txd2);
 		if ((desc->txd3 & TX_DMA_OWNER_CPU) == 0)
 			break;
 
-		mac = (desc->txd4 >> TX_DMA_FPORT_SHIFT) &
-		       TX_DMA_FPORT_MASK;
-		mac--;
-
 		tx_buf = mtk_desc_to_tx_buf(ring, desc);
+		if (tx_buf->flags & MTK_TX_FLAGS_FPORT1)
+			mac = 1;
+
 		skb = tx_buf->skb;
 		if (!skb) {
 			condition = 1;

drivers/net/ethernet/mediatek/mtk_eth_soc.h

@@ -406,12 +406,18 @@ struct mtk_hw_stats {
 	struct u64_stats_sync	syncp;
 };
 
-/* PDMA descriptor can point at 1-2 segments. This enum allows us to track how
- * memory was allocated so that it can be freed properly
- */
 enum mtk_tx_flags {
+	/* PDMA descriptor can point at 1-2 segments. This enum allows us to
+	 * track how memory was allocated so that it can be freed properly.
+	 */
 	MTK_TX_FLAGS_SINGLE0	= 0x01,
 	MTK_TX_FLAGS_PAGE0	= 0x02,
+
+	/* MTK_TX_FLAGS_FPORTx allows tracking which port the transmitted
+	 * SKB out instead of looking up through hardware TX descriptor.
+	 */
+	MTK_TX_FLAGS_FPORT0	= 0x04,
+	MTK_TX_FLAGS_FPORT1	= 0x08,
 };
 
 /* This enum allows us to identify how the clock is defined on the array of the

drivers/net/ethernet/sfc/efx.c

@@ -1371,6 +1371,13 @@ static unsigned int efx_wanted_parallelism(struct efx_nic *efx)
 		free_cpumask_var(thread_mask);
 	}
 
+	if (count > EFX_MAX_RX_QUEUES) {
+		netif_cond_dbg(efx, probe, efx->net_dev, !rss_cpus, warn,
+			       "Reducing number of rx queues from %u to %u.\n",
+			       count, EFX_MAX_RX_QUEUES);
+		count = EFX_MAX_RX_QUEUES;
+	}
+
 	/* If RSS is requested for the PF *and* VFs then we can't write RSS
 	 * table entries that are inaccessible to VFs
 	 */

drivers/net/ethernet/sfc/falcon/efx.c

@@ -1354,6 +1354,13 @@ static unsigned int ef4_wanted_parallelism(struct ef4_nic *efx)
 		free_cpumask_var(thread_mask);
 	}
 
+	if (count > EF4_MAX_RX_QUEUES) {
+		netif_cond_dbg(efx, probe, efx->net_dev, !rss_cpus, warn,
+			       "Reducing number of rx queues from %u to %u.\n",
+			       count, EF4_MAX_RX_QUEUES);
+		count = EF4_MAX_RX_QUEUES;
+	}
+
 	return count;
 }
 

drivers/net/phy/micrel.c

@@ -798,9 +798,6 @@ static struct phy_driver ksphy_driver[] = {
 	.read_status	= genphy_read_status,
 	.ack_interrupt	= kszphy_ack_interrupt,
 	.config_intr	= kszphy_config_intr,
-	.get_sset_count = kszphy_get_sset_count,
-	.get_strings	= kszphy_get_strings,
-	.get_stats	= kszphy_get_stats,
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
 }, {
@@ -940,9 +937,6 @@ static struct phy_driver ksphy_driver[] = {
 	.read_status	= genphy_read_status,
 	.ack_interrupt	= kszphy_ack_interrupt,
 	.config_intr	= kszphy_config_intr,
-	.get_sset_count = kszphy_get_sset_count,
-	.get_strings	= kszphy_get_strings,
-	.get_stats	= kszphy_get_stats,
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
 }, {
@@ -952,6 +946,7 @@ static struct phy_driver ksphy_driver[] = {
 	.features	= PHY_GBIT_FEATURES,
 	.flags		= PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT,
 	.driver_data	= &ksz9021_type,
+	.probe		= kszphy_probe,
 	.config_init	= ksz9021_config_init,
 	.config_aneg	= genphy_config_aneg,
 	.read_status	= genphy_read_status,
@@ -971,6 +966,7 @@ static struct phy_driver ksphy_driver[] = {
 	.features	= PHY_GBIT_FEATURES,
 	.flags		= PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT,
 	.driver_data	= &ksz9021_type,
+	.probe		= kszphy_probe,
 	.config_init	= ksz9031_config_init,
 	.config_aneg	= genphy_config_aneg,
 	.read_status	= ksz9031_read_status,
@@ -989,9 +985,6 @@ static struct phy_driver ksphy_driver[] = {
 	.config_init	= kszphy_config_init,
 	.config_aneg	= ksz8873mll_config_aneg,
 	.read_status	= ksz8873mll_read_status,
-	.get_sset_count = kszphy_get_sset_count,
-	.get_strings	= kszphy_get_strings,
-	.get_stats	= kszphy_get_stats,
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
 }, {
@@ -1003,9 +996,6 @@ static struct phy_driver ksphy_driver[] = {
 	.config_init	= kszphy_config_init,
 	.config_aneg	= genphy_config_aneg,
 	.read_status	= genphy_read_status,
-	.get_sset_count = kszphy_get_sset_count,
-	.get_strings	= kszphy_get_strings,
-	.get_stats	= kszphy_get_stats,
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
 }, {
@@ -1017,9 +1007,6 @@ static struct phy_driver ksphy_driver[] = {
 	.config_init	= kszphy_config_init,
 	.config_aneg	= ksz8873mll_config_aneg,
 	.read_status	= ksz8873mll_read_status,
-	.get_sset_count = kszphy_get_sset_count,
-	.get_strings	= kszphy_get_strings,
-	.get_stats	= kszphy_get_stats,
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
 } };

drivers/net/vrf.c

@@ -1128,7 +1128,7 @@ static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it)
 		goto nla_put_failure;
 
 	/* rule only needs to appear once */
-	nlh->nlmsg_flags &= NLM_F_EXCL;
+	nlh->nlmsg_flags |= NLM_F_EXCL;
 
 	frh = nlmsg_data(nlh);
 	memset(frh, 0, sizeof(*frh));

kernel/bpf/syscall.c

@@ -617,6 +617,14 @@ static void fixup_bpf_calls(struct bpf_prog *prog)
 			if (insn->imm == BPF_FUNC_xdp_adjust_head)
 				prog->xdp_adjust_head = 1;
 			if (insn->imm == BPF_FUNC_tail_call) {
+				/* If we tail call into other programs, we
+				 * cannot make any assumptions since they
+				 * can be replaced dynamically during runtime
+				 * in the program array.
+				 */
+				prog->cb_access = 1;
+				prog->xdp_adjust_head = 1;
+
 				/* mark bpf_tail_call as different opcode
 				 * to avoid conditional branch in
 				 * interpeter for every normal call

net/core/skbuff.c

@@ -3807,6 +3807,7 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb,
 	serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING;
 	serr->ee.ee_info = tstype;
 	serr->opt_stats = opt_stats;
+	serr->header.h4.iif = skb->dev ? skb->dev->ifindex : 0;
 	if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) {
 		serr->ee.ee_data = skb_shinfo(skb)->tskey;
 		if (sk->sk_protocol == IPPROTO_TCP &&

net/ipv4/ip_sockglue.c

@@ -488,16 +488,15 @@ static bool ipv4_datagram_support_cmsg(const struct sock *sk,
 		return false;
 
 	/* Support IP_PKTINFO on tstamp packets if requested, to correlate
-	 * timestamp with egress dev. Not possible for packets without dev
+	 * timestamp with egress dev. Not possible for packets without iif
 	 * or without payload (SOF_TIMESTAMPING_OPT_TSONLY).
 	 */
-	if ((!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG)) ||
-	    (!skb->dev))
+	info = PKTINFO_SKB_CB(skb);
+	if (!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG) ||
+	    !info->ipi_ifindex)
 		return false;
 
-	info = PKTINFO_SKB_CB(skb);
 	info->ipi_spec_dst.s_addr = ip_hdr(skb)->saddr;
-	info->ipi_ifindex = skb->dev->ifindex;
 	return true;
 }
 
@@ -591,6 +590,7 @@ static bool setsockopt_needs_rtnl(int optname)
 	case MCAST_LEAVE_GROUP:
 	case MCAST_LEAVE_SOURCE_GROUP:
 	case MCAST_UNBLOCK_SOURCE:
+	case IP_ROUTER_ALERT:
 		return true;
 	}
 	return false;

net/ipv4/ipmr.c

@@ -1278,7 +1278,7 @@ static void mrtsock_destruct(struct sock *sk)
 	struct net *net = sock_net(sk);
 	struct mr_table *mrt;
 
-	rtnl_lock();
+	ASSERT_RTNL();
 	ipmr_for_each_table(mrt, net) {
 		if (sk == rtnl_dereference(mrt->mroute_sk)) {
 			IPV4_DEVCONF_ALL(net, MC_FORWARDING)--;
@@ -1289,7 +1289,6 @@ static void mrtsock_destruct(struct sock *sk)
 			mroute_clean_tables(mrt, false);
 		}
 	}
-	rtnl_unlock();
 }
 
 /* Socket options and virtual interface manipulation. The whole
@@ -1353,13 +1352,8 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval,
 		if (sk != rcu_access_pointer(mrt->mroute_sk)) {
 			ret = -EACCES;
 		} else {
-			/* We need to unlock here because mrtsock_destruct takes
-			 * care of rtnl itself and we can't change that due to
-			 * the IP_ROUTER_ALERT setsockopt which runs without it.
-			 */
-			rtnl_unlock();
 			ret = ip_ra_control(sk, 0, NULL);
-			goto out;
+			goto out_unlock;
 		}
 		break;
 	case MRT_ADD_VIF:
@@ -1470,7 +1464,6 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval,
 	}
 out_unlock:
 	rtnl_unlock();
-out:
 	return ret;
 }
 

net/ipv4/raw.c

@@ -682,7 +682,9 @@ static void raw_close(struct sock *sk, long timeout)
 	/*
 	 * Raw sockets may have direct kernel references. Kill them.
 	 */
+	rtnl_lock();
 	ip_ra_control(sk, 0, NULL);
+	rtnl_unlock();
 
 	sk_common_release(sk);
 }

net/ipv6/datagram.c

@@ -405,9 +405,6 @@ static inline bool ipv6_datagram_support_addr(struct sock_exterr_skb *serr)
  * At one point, excluding local errors was a quick test to identify icmp/icmp6
  * errors. This is no longer true, but the test remained, so the v6 stack,
  * unlike v4, also honors cmsg requests on all wifi and timestamp errors.
- *
- * Timestamp code paths do not initialize the fields expected by cmsg:
- * the PKTINFO fields in skb->cb[]. Fill those in here.
  */
 static bool ip6_datagram_support_cmsg(struct sk_buff *skb,
 				      struct sock_exterr_skb *serr)
@@ -419,14 +416,9 @@ static bool ip6_datagram_support_cmsg(struct sk_buff *skb,
 	if (serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL)
 		return false;
 
-	if (!skb->dev)
+	if (!IP6CB(skb)->iif)
 		return false;
 
-	if (skb->protocol == htons(ETH_P_IPV6))
-		IP6CB(skb)->iif = skb->dev->ifindex;
-	else
-		PKTINFO_SKB_CB(skb)->ipi_ifindex = skb->dev->ifindex;
-
 	return true;
 }
 

net/ipv6/ip6_input.c

@@ -122,11 +122,14 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt
 			max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs));
 	/*
 	 * RFC4291 2.5.3
+	 * The loopback address must not be used as the source address in IPv6
+	 * packets that are sent outside of a single node. [..]
 	 * A packet received on an interface with a destination address
 	 * of loopback must be dropped.
 	 */
-	if (!(dev->flags & IFF_LOOPBACK) &&
-	    ipv6_addr_loopback(&hdr->daddr))
+	if ((ipv6_addr_loopback(&hdr->saddr) ||
+	     ipv6_addr_loopback(&hdr->daddr)) &&
+	     !(dev->flags & IFF_LOOPBACK))
 		goto err;
 
 	/* RFC4291 Errata ID: 3480