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

Pull networking fixes from David Miller:
 "Several fixes here. Basically split down the line between newly
  introduced regressions and long existing problems:

   1) Double free in tipc_enable_bearer(), from Cong Wang.

   2) Many fixes to nf_conncount, from Florian Westphal.

   3) op->get_regs_len() can throw an error, check it, from Yunsheng
      Lin.

   4) Need to use GFP_ATOMIC in *_add_hash_mac_address() of fsl/fman
      driver, from Scott Wood.

   5) Inifnite loop in fib_empty_table(), from Yue Haibing.

   6) Use after free in ax25_fillin_cb(), from Cong Wang.

   7) Fix socket locking in nr_find_socket(), also from Cong Wang.

   8) Fix WoL wakeup enable in r8169, from Heiner Kallweit.

   9) On 32-bit sock->sk_stamp is not thread-safe, from Deepa Dinamani.

  10) Fix ptr_ring wrap during queue swap, from Cong Wang.

  11) Missing shutdown callback in hinic driver, from Xue Chaojing.

  12) Need to return NULL on error from ip6_neigh_lookup(), from Stefano
      Brivio.

  13) BPF out of bounds speculation fixes from Daniel Borkmann"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (57 commits)
  ipv6: Consider sk_bound_dev_if when binding a socket to an address
  ipv6: Fix dump of specific table with strict checking
  bpf: add various test cases to selftests
  bpf: prevent out of bounds speculation on pointer arithmetic
  bpf: fix check_map_access smin_value test when pointer contains offset
  bpf: restrict unknown scalars of mixed signed bounds for unprivileged
  bpf: restrict stack pointer arithmetic for unprivileged
  bpf: restrict map value pointer arithmetic for unprivileged
  bpf: enable access to ax register also from verifier rewrite
  bpf: move tmp variable into ax register in interpreter
  bpf: move {prev_,}insn_idx into verifier env
  isdn: fix kernel-infoleak in capi_unlocked_ioctl
  ipv6: route: Fix return value of ip6_neigh_lookup() on neigh_create() error
  net/hamradio/6pack: use mod_timer() to rearm timers
  net-next/hinic:add shutdown callback
  net: hns3: call hns3_nic_net_open() while doing HNAE3_UP_CLIENT
  ip: validate header length on virtual device xmit
  tap: call skb_probe_transport_header after setting skb->dev
  ptr_ring: wrap back ->producer in __ptr_ring_swap_queue()
  net: rds: remove unnecessary NULL check
  ...

Documentation/networking/snmp_counter.rst

@@ -571,7 +571,97 @@ duplicate packet is received.
 
 * TcpExtTCPDSACKOfoRecv
 The TCP stack receives a DSACK, which indicate an out of order
-duplciate packet is received.
+duplicate packet is received.
+
+TCP out of order
+===============
+* TcpExtTCPOFOQueue
+The TCP layer receives an out of order packet and has enough memory
+to queue it.
+
+* TcpExtTCPOFODrop
+The TCP layer receives an out of order packet but doesn't have enough
+memory, so drops it. Such packets won't be counted into
+TcpExtTCPOFOQueue.
+
+* TcpExtTCPOFOMerge
+The received out of order packet has an overlay with the previous
+packet. the overlay part will be dropped. All of TcpExtTCPOFOMerge
+packets will also be counted into TcpExtTCPOFOQueue.
+
+TCP PAWS
+=======
+PAWS (Protection Against Wrapped Sequence numbers) is an algorithm
+which is used to drop old packets. It depends on the TCP
+timestamps. For detail information, please refer the `timestamp wiki`_
+and the `RFC of PAWS`_.
+
+.. _RFC of PAWS: https://tools.ietf.org/html/rfc1323#page-17
+.. _timestamp wiki: https://en.wikipedia.org/wiki/Transmission_Control_Protocol#TCP_timestamps
+
+* TcpExtPAWSActive
+Packets are dropped by PAWS in Syn-Sent status.
+
+* TcpExtPAWSEstab
+Packets are dropped by PAWS in any status other than Syn-Sent.
+
+TCP ACK skip
+===========
+In some scenarios, kernel would avoid sending duplicate ACKs too
+frequently. Please find more details in the tcp_invalid_ratelimit
+section of the `sysctl document`_. When kernel decides to skip an ACK
+due to tcp_invalid_ratelimit, kernel would update one of below
+counters to indicate the ACK is skipped in which scenario. The ACK
+would only be skipped if the received packet is either a SYN packet or
+it has no data.
+
+.. _sysctl document: https://www.kernel.org/doc/Documentation/networking/ip-sysctl.txt
+
+* TcpExtTCPACKSkippedSynRecv
+The ACK is skipped in Syn-Recv status. The Syn-Recv status means the
+TCP stack receives a SYN and replies SYN+ACK. Now the TCP stack is
+waiting for an ACK. Generally, the TCP stack doesn't need to send ACK
+in the Syn-Recv status. But in several scenarios, the TCP stack need
+to send an ACK. E.g., the TCP stack receives the same SYN packet
+repeately, the received packet does not pass the PAWS check, or the
+received packet sequence number is out of window. In these scenarios,
+the TCP stack needs to send ACK. If the ACk sending frequency is higher than
+tcp_invalid_ratelimit allows, the TCP stack will skip sending ACK and
+increase TcpExtTCPACKSkippedSynRecv.
+
+
+* TcpExtTCPACKSkippedPAWS
+The ACK is skipped due to PAWS (Protect Against Wrapped Sequence
+numbers) check fails. If the PAWS check fails in Syn-Recv, Fin-Wait-2
+or Time-Wait statuses, the skipped ACK would be counted to
+TcpExtTCPACKSkippedSynRecv, TcpExtTCPACKSkippedFinWait2 or
+TcpExtTCPACKSkippedTimeWait. In all other statuses, the skipped ACK
+would be counted to TcpExtTCPACKSkippedPAWS.
+
+* TcpExtTCPACKSkippedSeq
+The sequence number is out of window and the timestamp passes the PAWS
+check and the TCP status is not Syn-Recv, Fin-Wait-2, and Time-Wait.
+
+* TcpExtTCPACKSkippedFinWait2
+The ACK is skipped in Fin-Wait-2 status, the reason would be either
+PAWS check fails or the received sequence number is out of window.
+
+* TcpExtTCPACKSkippedTimeWait
+Tha ACK is skipped in Time-Wait status, the reason would be either
+PAWS check failed or the received sequence number is out of window.
+
+* TcpExtTCPACKSkippedChallenge
+The ACK is skipped if the ACK is a challenge ACK. The RFC 5961 defines
+3 kind of challenge ACK, please refer `RFC 5961 section 3.2`_,
+`RFC 5961 section 4.2`_ and `RFC 5961 section 5.2`_. Besides these
+three scenarios, In some TCP status, the linux TCP stack would also
+send challenge ACKs if the ACK number is before the first
+unacknowledged number (more strict than `RFC 5961 section 5.2`_).
+
+.. _RFC 5961 section 3.2: https://tools.ietf.org/html/rfc5961#page-7
+.. _RFC 5961 section 4.2: https://tools.ietf.org/html/rfc5961#page-9
+.. _RFC 5961 section 5.2: https://tools.ietf.org/html/rfc5961#page-11
+
 
 examples
 =======
@@ -1188,3 +1278,151 @@ Run nstat on server B::
 We have deleted the default route on server B. Server B couldn't find
 a route for the 8.8.8.8 IP address, so server B increased
 IpOutNoRoutes.
+
+TcpExtTCPACKSkippedSynRecv
+------------------------
+In this test, we send 3 same SYN packets from client to server. The
+first SYN will let server create a socket, set it to Syn-Recv status,
+and reply a SYN/ACK. The second SYN will let server reply the SYN/ACK
+again, and record the reply time (the duplicate ACK reply time). The
+third SYN will let server check the previous duplicate ACK reply time,
+and decide to skip the duplicate ACK, then increase the
+TcpExtTCPACKSkippedSynRecv counter.
+
+Run tcpdump to capture a SYN packet::
+
+  nstatuser@nstat-a:~$ sudo tcpdump -c 1 -w /tmp/syn.pcap port 9000
+  tcpdump: listening on ens3, link-type EN10MB (Ethernet), capture size 262144 bytes
+
+Open another terminal, run nc command::
+
+  nstatuser@nstat-a:~$ nc nstat-b 9000
+
+As the nstat-b didn't listen on port 9000, it should reply a RST, and
+the nc command exited immediately. It was enough for the tcpdump
+command to capture a SYN packet. A linux server might use hardware
+offload for the TCP checksum, so the checksum in the /tmp/syn.pcap
+might be not correct. We call tcprewrite to fix it::
+
+  nstatuser@nstat-a:~$ tcprewrite --infile=/tmp/syn.pcap --outfile=/tmp/syn_fixcsum.pcap --fixcsum
+
+On nstat-b, we run nc to listen on port 9000::
+
+  nstatuser@nstat-b:~$ nc -lkv 9000
+  Listening on [0.0.0.0] (family 0, port 9000)
+
+On nstat-a, we blocked the packet from port 9000, or nstat-a would send
+RST to nstat-b::
+
+  nstatuser@nstat-a:~$ sudo iptables -A INPUT -p tcp --sport 9000 -j DROP
+
+Send 3 SYN repeatly to nstat-b::
+
+  nstatuser@nstat-a:~$ for i in {1..3}; do sudo tcpreplay -i ens3 /tmp/syn_fixcsum.pcap; done
+
+Check snmp cunter on nstat-b::
+
+  nstatuser@nstat-b:~$ nstat | grep -i skip
+  TcpExtTCPACKSkippedSynRecv      1                  0.0
+
+As we expected, TcpExtTCPACKSkippedSynRecv is 1.
+
+TcpExtTCPACKSkippedPAWS
+----------------------
+To trigger PAWS, we could send an old SYN.
+
+On nstat-b, let nc listen on port 9000::
+
+  nstatuser@nstat-b:~$ nc -lkv 9000
+  Listening on [0.0.0.0] (family 0, port 9000)
+
+On nstat-a, run tcpdump to capture a SYN::
+
+  nstatuser@nstat-a:~$ sudo tcpdump -w /tmp/paws_pre.pcap -c 1 port 9000
+  tcpdump: listening on ens3, link-type EN10MB (Ethernet), capture size 262144 bytes
+
+On nstat-a, run nc as a client to connect nstat-b::
+
+  nstatuser@nstat-a:~$ nc -v nstat-b 9000
+  Connection to nstat-b 9000 port [tcp/*] succeeded!
+
+Now the tcpdump has captured the SYN and exit. We should fix the
+checksum::
+
+  nstatuser@nstat-a:~$ tcprewrite --infile /tmp/paws_pre.pcap --outfile /tmp/paws.pcap --fixcsum
+
+Send the SYN packet twice::
+
+  nstatuser@nstat-a:~$ for i in {1..2}; do sudo tcpreplay -i ens3 /tmp/paws.pcap; done
+
+On nstat-b, check the snmp counter::
+
+  nstatuser@nstat-b:~$ nstat | grep -i skip
+  TcpExtTCPACKSkippedPAWS         1                  0.0
+
+We sent two SYN via tcpreplay, both of them would let PAWS check
+failed, the nstat-b replied an ACK for the first SYN, skipped the ACK
+for the second SYN, and updated TcpExtTCPACKSkippedPAWS.
+
+TcpExtTCPACKSkippedSeq
+--------------------
+To trigger TcpExtTCPACKSkippedSeq, we send packets which have valid
+timestamp (to pass PAWS check) but the sequence number is out of
+window. The linux TCP stack would avoid to skip if the packet has
+data, so we need a pure ACK packet. To generate such a packet, we
+could create two sockets: one on port 9000, another on port 9001. Then
+we capture an ACK on port 9001, change the source/destination port
+numbers to match the port 9000 socket. Then we could trigger
+TcpExtTCPACKSkippedSeq via this packet.
+
+On nstat-b, open two terminals, run two nc commands to listen on both
+port 9000 and port 9001::
+
+  nstatuser@nstat-b:~$ nc -lkv 9000
+  Listening on [0.0.0.0] (family 0, port 9000)
+
+  nstatuser@nstat-b:~$ nc -lkv 9001
+  Listening on [0.0.0.0] (family 0, port 9001)
+
+On nstat-a, run two nc clients::
+
+  nstatuser@nstat-a:~$ nc -v nstat-b 9000
+  Connection to nstat-b 9000 port [tcp/*] succeeded!
+
+  nstatuser@nstat-a:~$ nc -v nstat-b 9001
+  Connection to nstat-b 9001 port [tcp/*] succeeded!
+
+On nstat-a, run tcpdump to capture an ACK::
+
+  nstatuser@nstat-a:~$ sudo tcpdump -w /tmp/seq_pre.pcap -c 1 dst port 9001
+  tcpdump: listening on ens3, link-type EN10MB (Ethernet), capture size 262144 bytes
+
+On nstat-b, send a packet via the port 9001 socket. E.g. we sent a
+string 'foo' in our example::
+
+  nstatuser@nstat-b:~$ nc -lkv 9001
+  Listening on [0.0.0.0] (family 0, port 9001)
+  Connection from nstat-a 42132 received!
+  foo
+
+On nstat-a, the tcpdump should have caputred the ACK. We should check
+the source port numbers of the two nc clients::
+
+  nstatuser@nstat-a:~$ ss -ta '( dport = :9000 || dport = :9001 )' | tee
+  State  Recv-Q   Send-Q         Local Address:Port           Peer Address:Port
+  ESTAB  0        0            192.168.122.250:50208       192.168.122.251:9000
+  ESTAB  0        0            192.168.122.250:42132       192.168.122.251:9001
+
+Run tcprewrite, change port 9001 to port 9000, chagne port 42132 to
+port 50208::
+
+  nstatuser@nstat-a:~$ tcprewrite --infile /tmp/seq_pre.pcap --outfile /tmp/seq.pcap -r 9001:9000 -r 42132:50208 --fixcsum
+
+Now the /tmp/seq.pcap is the packet we need. Send it to nstat-b::
+
+  nstatuser@nstat-a:~$ for i in {1..2}; do sudo tcpreplay -i ens3 /tmp/seq.pcap; done
+
+Check TcpExtTCPACKSkippedSeq on nstat-b::
+
+  nstatuser@nstat-b:~$ nstat | grep -i skip
+  TcpExtTCPACKSkippedSeq          1                  0.0

drivers/isdn/capi/kcapi.c

@@ -852,7 +852,7 @@ u16 capi20_get_manufacturer(u32 contr, u8 *buf)
 	u16 ret;
 
 	if (contr == 0) {
-		strlcpy(buf, capi_manufakturer, CAPI_MANUFACTURER_LEN);
+		strncpy(buf, capi_manufakturer, CAPI_MANUFACTURER_LEN);
 		return CAPI_NOERROR;
 	}
 
@@ -860,7 +860,7 @@ u16 capi20_get_manufacturer(u32 contr, u8 *buf)
 
 	ctr = get_capi_ctr_by_nr(contr);
 	if (ctr && ctr->state == CAPI_CTR_RUNNING) {
-		strlcpy(buf, ctr->manu, CAPI_MANUFACTURER_LEN);
+		strncpy(buf, ctr->manu, CAPI_MANUFACTURER_LEN);
 		ret = CAPI_NOERROR;
 	} else
 		ret = CAPI_REGNOTINSTALLED;

drivers/isdn/hisax/hfc_pci.c

@@ -1169,11 +1169,13 @@ HFCPCI_l1hw(struct PStack *st, int pr, void *arg)
 		if (cs->debug & L1_DEB_LAPD)
 			debugl1(cs, "-> PH_REQUEST_PULL");
 #endif
+		spin_lock_irqsave(&cs->lock, flags);
 		if (!cs->tx_skb) {
 			test_and_clear_bit(FLG_L1_PULL_REQ, &st->l1.Flags);
 			st->l1.l1l2(st, PH_PULL | CONFIRM, NULL);
 		} else
 			test_and_set_bit(FLG_L1_PULL_REQ, &st->l1.Flags);
+		spin_unlock_irqrestore(&cs->lock, flags);
 		break;
 	case (HW_RESET | REQUEST):
 		spin_lock_irqsave(&cs->lock, flags);

drivers/net/dsa/bcm_sf2.c

@@ -303,11 +303,10 @@ static int bcm_sf2_sw_mdio_write(struct mii_bus *bus, int addr, int regnum,
 	 * send them to our master MDIO bus controller
 	 */
 	if (addr == BRCM_PSEUDO_PHY_ADDR && priv->indir_phy_mask & BIT(addr))
-		bcm_sf2_sw_indir_rw(priv, 0, addr, regnum, val);
+		return bcm_sf2_sw_indir_rw(priv, 0, addr, regnum, val);
 	else
-		mdiobus_write_nested(priv->master_mii_bus, addr, regnum, val);
+		return mdiobus_write_nested(priv->master_mii_bus, addr,
-
+				regnum, val);
-	return 0;
 }
 
 static irqreturn_t bcm_sf2_switch_0_isr(int irq, void *dev_id)

drivers/net/ethernet/atheros/atl1e/atl1e_main.c

@@ -473,7 +473,9 @@ static void atl1e_mdio_write(struct net_device *netdev, int phy_id,
 {
 	struct atl1e_adapter *adapter = netdev_priv(netdev);
 
-	atl1e_write_phy_reg(&adapter->hw, reg_num & MDIO_REG_ADDR_MASK, val);
+	if (atl1e_write_phy_reg(&adapter->hw,
+				reg_num & MDIO_REG_ADDR_MASK, val))
+		netdev_err(netdev, "write phy register failed\n");
 }
 
 static int atl1e_mii_ioctl(struct net_device *netdev,

drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c

@@ -1229,6 +1229,10 @@ int cudbg_collect_hw_sched(struct cudbg_init *pdbg_init,
 
 	rc = cudbg_get_buff(pdbg_init, dbg_buff, sizeof(struct cudbg_hw_sched),
 			    &temp_buff);
+
+	if (rc)
+		return rc;
+
 	hw_sched_buff = (struct cudbg_hw_sched *)temp_buff.data;
 	hw_sched_buff->map = t4_read_reg(padap, TP_TX_MOD_QUEUE_REQ_MAP_A);
 	hw_sched_buff->mode = TIMERMODE_G(t4_read_reg(padap, TP_MOD_CONFIG_A));

drivers/net/ethernet/freescale/fman/fman_memac.c

@@ -928,7 +928,7 @@ int memac_add_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr)
 	hash = get_mac_addr_hash_code(addr) & HASH_CTRL_ADDR_MASK;
 
 	/* Create element to be added to the driver hash table */
-	hash_entry = kmalloc(sizeof(*hash_entry), GFP_KERNEL);
+	hash_entry = kmalloc(sizeof(*hash_entry), GFP_ATOMIC);
 	if (!hash_entry)
 		return -ENOMEM;
 	hash_entry->addr = addr;

drivers/net/ethernet/freescale/fman/fman_tgec.c

@@ -553,7 +553,7 @@ int tgec_add_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr)
 	hash = (crc >> TGEC_HASH_MCAST_SHIFT) & TGEC_HASH_ADR_MSK;
 
 	/* Create element to be added to the driver hash table */
-	hash_entry = kmalloc(sizeof(*hash_entry), GFP_KERNEL);
+	hash_entry = kmalloc(sizeof(*hash_entry), GFP_ATOMIC);
 	if (!hash_entry)
 		return -ENOMEM;
 	hash_entry->addr = addr;

drivers/net/ethernet/hisilicon/hns3/hns3_enet.c

@@ -3995,17 +3995,18 @@ static int hns3_reset_notify_up_enet(struct hnae3_handle *handle)
 	struct hns3_nic_priv *priv = netdev_priv(kinfo->netdev);
 	int ret = 0;
 
+	clear_bit(HNS3_NIC_STATE_RESETTING, &priv->state);
+
 	if (netif_running(kinfo->netdev)) {
-		ret = hns3_nic_net_up(kinfo->netdev);
+		ret = hns3_nic_net_open(kinfo->netdev);
 		if (ret) {
+			set_bit(HNS3_NIC_STATE_RESETTING, &priv->state);
 			netdev_err(kinfo->netdev,
 				   "hns net up fail, ret=%d!\n", ret);
 			return ret;
 		}
 	}
 
-	clear_bit(HNS3_NIC_STATE_RESETTING, &priv->state);
-
 	return ret;
 }
 

drivers/net/ethernet/huawei/hinic/hinic_main.c

@@ -1106,6 +1106,11 @@ static void hinic_remove(struct pci_dev *pdev)
 	dev_info(&pdev->dev, "HiNIC driver - removed\n");
 }
 
+static void hinic_shutdown(struct pci_dev *pdev)
+{
+	pci_disable_device(pdev);
+}
+
 static const struct pci_device_id hinic_pci_table[] = {
 	{ PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_QUAD_PORT_25GE), 0},
 	{ PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_DUAL_PORT_25GE), 0},
@@ -1119,6 +1124,7 @@ static struct pci_driver hinic_driver = {
 	.id_table       = hinic_pci_table,
 	.probe          = hinic_probe,
 	.remove         = hinic_remove,
+	.shutdown       = hinic_shutdown,
 };
 
 module_pci_driver(hinic_driver);

drivers/net/ethernet/ibm/ibmveth.c

@@ -1171,11 +1171,15 @@ static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb,
 
 map_failed_frags:
 	last = i+1;
-	for (i = 0; i < last; i++)
+	for (i = 1; i < last; i++)
 		dma_unmap_page(&adapter->vdev->dev, descs[i].fields.address,
 			       descs[i].fields.flags_len & IBMVETH_BUF_LEN_MASK,
 			       DMA_TO_DEVICE);
 
+	dma_unmap_single(&adapter->vdev->dev,
+			 descs[0].fields.address,
+			 descs[0].fields.flags_len & IBMVETH_BUF_LEN_MASK,
+			 DMA_TO_DEVICE);
 map_failed:
 	if (!firmware_has_feature(FW_FEATURE_CMO))
 		netdev_err(netdev, "tx: unable to map xmit buffer\n");

drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c

@@ -5240,6 +5240,8 @@ static int mvpp2_probe(struct platform_device *pdev)
 	if (has_acpi_companion(&pdev->dev)) {
 		acpi_id = acpi_match_device(pdev->dev.driver->acpi_match_table,
 					    &pdev->dev);
+		if (!acpi_id)
+			return -EINVAL;
 		priv->hw_version = (unsigned long)acpi_id->driver_data;
 	} else {
 		priv->hw_version =

drivers/net/ethernet/realtek/r8169.c

@@ -1477,6 +1477,8 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts)
 	}
 
 	RTL_W8(tp, Cfg9346, Cfg9346_Lock);
+
+	device_set_wakeup_enable(tp_to_dev(tp), wolopts);
 }
 
 static int rtl8169_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
@@ -1498,8 +1500,6 @@ static int rtl8169_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 
 	rtl_unlock_work(tp);
 
-	device_set_wakeup_enable(d, tp->saved_wolopts);
-
 	pm_runtime_put_noidle(d);
 
 	return 0;

drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c

@@ -59,7 +59,9 @@ static int sun7i_gmac_init(struct platform_device *pdev, void *priv)
 		gmac->clk_enabled = 1;
 	} else {
 		clk_set_rate(gmac->tx_clk, SUN7I_GMAC_MII_RATE);
-		clk_prepare(gmac->tx_clk);
+		ret = clk_prepare(gmac->tx_clk);
+		if (ret)
+			return ret;
 	}
 
 	return 0;

drivers/net/ethernet/sun/niu.c

@@ -8100,6 +8100,8 @@ static int niu_pci_vpd_scan_props(struct niu *np, u32 start, u32 end)
 		start += 3;
 
 		prop_len = niu_pci_eeprom_read(np, start + 4);
+		if (prop_len < 0)
+			return prop_len;
 		err = niu_pci_vpd_get_propname(np, start + 5, namebuf, 64);
 		if (err < 0)
 			return err;
@@ -8144,8 +8146,12 @@ static int niu_pci_vpd_scan_props(struct niu *np, u32 start, u32 end)
 			netif_printk(np, probe, KERN_DEBUG, np->dev,
 				     "VPD_SCAN: Reading in property [%s] len[%d]\n",
 				     namebuf, prop_len);
-			for (i = 0; i < prop_len; i++)
+			for (i = 0; i < prop_len; i++) {
-				*prop_buf++ = niu_pci_eeprom_read(np, off + i);
+				err = niu_pci_eeprom_read(np, off + i);
+				if (err >= 0)
+					*prop_buf = err;
+				++prop_buf;
+			}
 		}
 
 		start += len;

drivers/net/ethernet/ti/cpts.c

@@ -590,7 +590,9 @@ struct cpts *cpts_create(struct device *dev, void __iomem *regs,
 		return ERR_CAST(cpts->refclk);
 	}
 
-	clk_prepare(cpts->refclk);
+	ret = clk_prepare(cpts->refclk);
+	if (ret)
+		return ERR_PTR(ret);
 
 	cpts->cc.read = cpts_systim_read;
 	cpts->cc.mask = CLOCKSOURCE_MASK(32);

drivers/net/hamradio/6pack.c

@@ -523,10 +523,7 @@ static void resync_tnc(struct timer_list *t)
 
 
 	/* Start resync timer again -- the TNC might be still absent */
-
+	mod_timer(&sp->resync_t, jiffies + SIXP_RESYNC_TIMEOUT);
-	del_timer(&sp->resync_t);
-	sp->resync_t.expires	= jiffies + SIXP_RESYNC_TIMEOUT;
-	add_timer(&sp->resync_t);
 }
 
 static inline int tnc_init(struct sixpack *sp)
@@ -537,9 +534,7 @@ static inline int tnc_init(struct sixpack *sp)
 
 	sp->tty->ops->write(sp->tty, &inbyte, 1);
 
-	del_timer(&sp->resync_t);
+	mod_timer(&sp->resync_t, jiffies + SIXP_RESYNC_TIMEOUT);
-	sp->resync_t.expires = jiffies + SIXP_RESYNC_TIMEOUT;
-	add_timer(&sp->resync_t);
 
 	return 0;
 }
@@ -897,11 +892,8 @@ static void decode_prio_command(struct sixpack *sp, unsigned char cmd)
         /* if the state byte has been received, the TNC is present,
            so the resync timer can be reset. */
 
-	if (sp->tnc_state == TNC_IN_SYNC) {
+	if (sp->tnc_state == TNC_IN_SYNC)
-		del_timer(&sp->resync_t);
+		mod_timer(&sp->resync_t, jiffies + SIXP_INIT_RESYNC_TIMEOUT);
-		sp->resync_t.expires	= jiffies + SIXP_INIT_RESYNC_TIMEOUT;
-		add_timer(&sp->resync_t);
-	}
 
 	sp->status1 = cmd & SIXP_PRIO_DATA_MASK;
 }

drivers/net/tap.c

@@ -1177,8 +1177,6 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp)
 			goto err_kfree;
 	}
 
-	skb_probe_transport_header(skb, ETH_HLEN);
-
 	/* Move network header to the right position for VLAN tagged packets */
 	if ((skb->protocol == htons(ETH_P_8021Q) ||
 	     skb->protocol == htons(ETH_P_8021AD)) &&
@@ -1189,6 +1187,7 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp)
 	tap = rcu_dereference(q->tap);
 	if (tap) {
 		skb->dev = tap->dev;
+		skb_probe_transport_header(skb, ETH_HLEN);
 		dev_queue_xmit(skb);
 	} else {
 		kfree_skb(skb);

drivers/net/wan/fsl_ucc_hdlc.c

@@ -1180,7 +1180,6 @@ static int ucc_hdlc_probe(struct platform_device *pdev)
 	if (register_hdlc_device(dev)) {
 		ret = -ENOBUFS;
 		pr_err("ucc_hdlc: unable to register hdlc device\n");
-		free_netdev(dev);
 		goto free_dev;
 	}
 

drivers/net/wan/x25_asy.c

@@ -485,8 +485,10 @@ static int x25_asy_open(struct net_device *dev)
 
 	/* Cleanup */
 	kfree(sl->xbuff);
+	sl->xbuff = NULL;
 noxbuff:
 	kfree(sl->rbuff);
+	sl->rbuff = NULL;
 norbuff:
 	return -ENOMEM;
 }

include/linux/bpf_verifier.h

@@ -148,6 +148,7 @@ struct bpf_verifier_state {
 	/* call stack tracking */
 	struct bpf_func_state *frame[MAX_CALL_FRAMES];
 	u32 curframe;
+	bool speculative;
 };
 
 #define bpf_get_spilled_reg(slot, frame)				\
@@ -167,15 +168,24 @@ struct bpf_verifier_state_list {
 	struct bpf_verifier_state_list *next;
 };
 
+/* Possible states for alu_state member. */
+#define BPF_ALU_SANITIZE_SRC		1U
+#define BPF_ALU_SANITIZE_DST		2U
+#define BPF_ALU_NEG_VALUE		(1U << 2)
+#define BPF_ALU_SANITIZE		(BPF_ALU_SANITIZE_SRC | \
+					 BPF_ALU_SANITIZE_DST)
+
 struct bpf_insn_aux_data {
 	union {
 		enum bpf_reg_type ptr_type;	/* pointer type for load/store insns */
 		unsigned long map_state;	/* pointer/poison value for maps */
 		s32 call_imm;			/* saved imm field of call insn */
+		u32 alu_limit;			/* limit for add/sub register with pointer */
 	};
 	int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
 	int sanitize_stack_off; /* stack slot to be cleared */
 	bool seen; /* this insn was processed by the verifier */
+	u8 alu_state; /* used in combination with alu_limit */
 };
 
 #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */
@@ -212,6 +222,8 @@ struct bpf_subprog_info {
  * one verifier_env per bpf_check() call
  */
 struct bpf_verifier_env {
+	u32 insn_idx;
+	u32 prev_insn_idx;
 	struct bpf_prog *prog;		/* eBPF program being verified */
 	const struct bpf_verifier_ops *ops;
 	struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */

include/linux/filter.h

@@ -53,14 +53,10 @@ struct sock_reuseport;
 #define BPF_REG_D	BPF_REG_8	/* data, callee-saved */
 #define BPF_REG_H	BPF_REG_9	/* hlen, callee-saved */
 
-/* Kernel hidden auxiliary/helper register for hardening step.
+/* Kernel hidden auxiliary/helper register. */
- * Only used by eBPF JITs. It's nothing more than a temporary
- * register that JITs use internally, only that here it's part
- * of eBPF instructions that have been rewritten for blinding
- * constants. See JIT pre-step in bpf_jit_blind_constants().
- */
 #define BPF_REG_AX		MAX_BPF_REG
-#define MAX_BPF_JIT_REG		(MAX_BPF_REG + 1)
+#define MAX_BPF_EXT_REG		(MAX_BPF_REG + 1)
+#define MAX_BPF_JIT_REG		MAX_BPF_EXT_REG
 
 /* unused opcode to mark special call to bpf_tail_call() helper */
 #define BPF_TAIL_CALL	0xf0

include/linux/phy.h

@@ -1,6 +1,6 @@
 /*
  * Framework and drivers for configuring and reading different PHYs
- * Based on code in sungem_phy.c and gianfar_phy.c
+ * Based on code in sungem_phy.c and (long-removed) gianfar_phy.c
  *
  * Author: Andy Fleming
  *
@@ -110,9 +110,9 @@ typedef enum {
  * @speeds: buffer to store supported speeds in.
  * @size: size of speeds buffer.
  *
- * Description: Returns the number of supported speeds, and
+ * Description: Returns the number of supported speeds, and fills
- * fills the speeds * buffer with the supported speeds. If speeds buffer is
+ * the speeds buffer with the supported speeds. If speeds buffer is
- * too small to contain * all currently supported speeds, will return as
+ * too small to contain all currently supported speeds, will return as
  * many speeds as can fit.
  */
 unsigned int phy_supported_speeds(struct phy_device *phy,
@@ -120,7 +120,10 @@ unsigned int phy_supported_speeds(struct phy_device *phy,
 				      unsigned int size);
 
 /**
- * It maps 'enum phy_interface_t' found in include/linux/phy.h
+ * phy_modes - map phy_interface_t enum to device tree binding of phy-mode
+ * @interface: enum phy_interface_t value
+ *
+ * Description: maps 'enum phy_interface_t' defined in this file
  * into the device tree binding of 'phy-mode', so that Ethernet
  * device driver can get phy interface from device tree.
  */

include/linux/phy/phy.h

@@ -110,6 +110,7 @@ struct phy_ops {
 /**
  * struct phy_attrs - represents phy attributes
  * @bus_width: Data path width implemented by PHY
+ * @mode: PHY mode
  */
 struct phy_attrs {
 	u32			bus_width;
@@ -121,7 +122,6 @@ struct phy_attrs {
  * @dev: phy device
  * @id: id of the phy device
  * @ops: function pointers for performing phy operations
- * @init_data: list of PHY consumers (non-dt only)
  * @mutex: mutex to protect phy_ops
  * @init_count: used to protect when the PHY is used by multiple consumers
  * @power_count: used to protect when the PHY is used by multiple consumers

include/linux/ptr_ring.h

@@ -573,6 +573,8 @@ static inline void **__ptr_ring_swap_queue(struct ptr_ring *r, void **queue,
 		else if (destroy)
 			destroy(ptr);
 
+	if (producer >= size)
+		producer = 0;
 	__ptr_ring_set_size(r, size);
 	r->producer = producer;
 	r->consumer_head = 0;

include/net/ip_tunnels.h

@@ -308,6 +308,26 @@ int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op,
 int ip_tunnel_encap_setup(struct ip_tunnel *t,
 			  struct ip_tunnel_encap *ipencap);
 
+static inline bool pskb_inet_may_pull(struct sk_buff *skb)
+{
+	int nhlen;
+
+	switch (skb->protocol) {
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6):
+		nhlen = sizeof(struct ipv6hdr);
+		break;
+#endif
+	case htons(ETH_P_IP):
+		nhlen = sizeof(struct iphdr);
+		break;
+	default:
+		nhlen = 0;
+	}
+
+	return pskb_network_may_pull(skb, nhlen);
+}
+
 static inline int ip_encap_hlen(struct ip_tunnel_encap *e)
 {
 	const struct ip_tunnel_encap_ops *ops;

include/net/netfilter/nf_conntrack_count.h

@@ -5,17 +5,10 @@
 
 struct nf_conncount_data;
 
-enum nf_conncount_list_add {
-	NF_CONNCOUNT_ADDED, 	/* list add was ok */
-	NF_CONNCOUNT_ERR,	/* -ENOMEM, must drop skb */
-	NF_CONNCOUNT_SKIP,	/* list is already reclaimed by gc */
-};
-
 struct nf_conncount_list {
 	spinlock_t list_lock;
 	struct list_head head;	/* connections with the same filtering key */
 	unsigned int count;	/* length of list */
-	bool dead;
 };
 
 struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family,
@@ -29,18 +22,12 @@ unsigned int nf_conncount_count(struct net *net,
 				const struct nf_conntrack_tuple *tuple,
 				const struct nf_conntrack_zone *zone);
 
-void nf_conncount_lookup(struct net *net, struct nf_conncount_list *list,
+int nf_conncount_add(struct net *net, struct nf_conncount_list *list,
-			 const struct nf_conntrack_tuple *tuple,
+		     const struct nf_conntrack_tuple *tuple,
-			 const struct nf_conntrack_zone *zone,
+		     const struct nf_conntrack_zone *zone);
-			 bool *addit);
 
 void nf_conncount_list_init(struct nf_conncount_list *list);
 
-enum nf_conncount_list_add
-nf_conncount_add(struct nf_conncount_list *list,
-		 const struct nf_conntrack_tuple *tuple,
-		 const struct nf_conntrack_zone *zone);
-
 bool nf_conncount_gc_list(struct net *net,
 			  struct nf_conncount_list *list);
 

include/net/sock.h

@@ -298,6 +298,7 @@ struct sock_common {
   *	@sk_filter: socket filtering instructions
   *	@sk_timer: sock cleanup timer
   *	@sk_stamp: time stamp of last packet received
+  *	@sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only
   *	@sk_tsflags: SO_TIMESTAMPING socket options
   *	@sk_tskey: counter to disambiguate concurrent tstamp requests
   *	@sk_zckey: counter to order MSG_ZEROCOPY notifications
@@ -474,6 +475,9 @@ struct sock {
 	const struct cred	*sk_peer_cred;
 	long			sk_rcvtimeo;
 	ktime_t			sk_stamp;
+#if BITS_PER_LONG==32
+	seqlock_t		sk_stamp_seq;
+#endif
 	u16			sk_tsflags;
 	u8			sk_shutdown;
 	u32			sk_tskey;
@@ -2297,6 +2301,34 @@ static inline void sk_drops_add(struct sock *sk, const struct sk_buff *skb)
 	atomic_add(segs, &sk->sk_drops);
 }
 
+static inline ktime_t sock_read_timestamp(struct sock *sk)
+{
+#if BITS_PER_LONG==32
+	unsigned int seq;
+	ktime_t kt;
+
+	do {
+		seq = read_seqbegin(&sk->sk_stamp_seq);
+		kt = sk->sk_stamp;
+	} while (read_seqretry(&sk->sk_stamp_seq, seq));
+
+	return kt;
+#else
+	return sk->sk_stamp;
+#endif
+}
+
+static inline void sock_write_timestamp(struct sock *sk, ktime_t kt)
+{
+#if BITS_PER_LONG==32
+	write_seqlock(&sk->sk_stamp_seq);
+	sk->sk_stamp = kt;
+	write_sequnlock(&sk->sk_stamp_seq);
+#else
+	sk->sk_stamp = kt;
+#endif
+}
+
 void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 			   struct sk_buff *skb);
 void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk,
@@ -2321,7 +2353,7 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
 	     (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE)))
 		__sock_recv_timestamp(msg, sk, skb);
 	else
-		sk->sk_stamp = kt;
+		sock_write_timestamp(sk, kt);
 
 	if (sock_flag(sk, SOCK_WIFI_STATUS) && skb->wifi_acked_valid)
 		__sock_recv_wifi_status(msg, sk, skb);
@@ -2342,9 +2374,9 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
 	if (sk->sk_flags & FLAGS_TS_OR_DROPS || sk->sk_tsflags & TSFLAGS_ANY)
 		__sock_recv_ts_and_drops(msg, sk, skb);
 	else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP)))
-		sk->sk_stamp = skb->tstamp;
+		sock_write_timestamp(sk, skb->tstamp);
 	else if (unlikely(sk->sk_stamp == SK_DEFAULT_STAMP))
-		sk->sk_stamp = 0;
+		sock_write_timestamp(sk, 0);
 }
 
 void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags);

kernel/bpf/core.c

@@ -54,6 +54,7 @@
 #define DST	regs[insn->dst_reg]
 #define SRC	regs[insn->src_reg]
 #define FP	regs[BPF_REG_FP]
+#define AX	regs[BPF_REG_AX]
 #define ARG1	regs[BPF_REG_ARG1]
 #define CTX	regs[BPF_REG_CTX]
 #define IMM	insn->imm
@@ -857,6 +858,26 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from,
 	BUILD_BUG_ON(BPF_REG_AX  + 1 != MAX_BPF_JIT_REG);
 	BUILD_BUG_ON(MAX_BPF_REG + 1 != MAX_BPF_JIT_REG);
 
+	/* Constraints on AX register:
+	 *
+	 * AX register is inaccessible from user space. It is mapped in
+	 * all JITs, and used here for constant blinding rewrites. It is
+	 * typically "stateless" meaning its contents are only valid within
+	 * the executed instruction, but not across several instructions.
+	 * There are a few exceptions however which are further detailed
+	 * below.
+	 *
+	 * Constant blinding is only used by JITs, not in the interpreter.
+	 * The interpreter uses AX in some occasions as a local temporary
+	 * register e.g. in DIV or MOD instructions.
+	 *
+	 * In restricted circumstances, the verifier can also use the AX
+	 * register for rewrites as long as they do not interfere with
+	 * the above cases!
+	 */
+	if (from->dst_reg == BPF_REG_AX || from->src_reg == BPF_REG_AX)
+		goto out;
+
 	if (from->imm == 0 &&
 	    (from->code == (BPF_ALU   | BPF_MOV | BPF_K) ||
 	     from->code == (BPF_ALU64 | BPF_MOV | BPF_K))) {
@@ -1188,7 +1209,6 @@ bool bpf_opcode_in_insntable(u8 code)
  */
 static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
 {
-	u64 tmp;
 #define BPF_INSN_2_LBL(x, y)    [BPF_##x | BPF_##y] = &&x##_##y
 #define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z
 	static const void *jumptable[256] = {
@@ -1268,36 +1288,36 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
 		(*(s64 *) &DST) >>= IMM;
 		CONT;
 	ALU64_MOD_X:
-		div64_u64_rem(DST, SRC, &tmp);
+		div64_u64_rem(DST, SRC, &AX);
-		DST = tmp;
+		DST = AX;
 		CONT;
 	ALU_MOD_X:
-		tmp = (u32) DST;
+		AX = (u32) DST;
-		DST = do_div(tmp, (u32) SRC);
+		DST = do_div(AX, (u32) SRC);
 		CONT;
 	ALU64_MOD_K:
-		div64_u64_rem(DST, IMM, &tmp);
+		div64_u64_rem(DST, IMM, &AX);
-		DST = tmp;
+		DST = AX;
 		CONT;
 	ALU_MOD_K:
-		tmp = (u32) DST;
+		AX = (u32) DST;
-		DST = do_div(tmp, (u32) IMM);
+		DST = do_div(AX, (u32) IMM);
 		CONT;
 	ALU64_DIV_X:
 		DST = div64_u64(DST, SRC);
 		CONT;
 	ALU_DIV_X:
-		tmp = (u32) DST;
+		AX = (u32) DST;
-		do_div(tmp, (u32) SRC);
+		do_div(AX, (u32) SRC);
-		DST = (u32) tmp;
+		DST = (u32) AX;
 		CONT;
 	ALU64_DIV_K:
 		DST = div64_u64(DST, IMM);
 		CONT;
 	ALU_DIV_K:
-		tmp = (u32) DST;
+		AX = (u32) DST;
-		do_div(tmp, (u32) IMM);
+		do_div(AX, (u32) IMM);
-		DST = (u32) tmp;
+		DST = (u32) AX;
 		CONT;
 	ALU_END_TO_BE:
 		switch (IMM) {
@@ -1553,7 +1573,7 @@ STACK_FRAME_NON_STANDARD(___bpf_prog_run); /* jump table */
 static unsigned int PROG_NAME(stack_size)(const void *ctx, const struct bpf_insn *insn) \
 { \
 	u64 stack[stack_size / sizeof(u64)]; \
-	u64 regs[MAX_BPF_REG]; \
+	u64 regs[MAX_BPF_EXT_REG]; \
 \
 	FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \
 	ARG1 = (u64) (unsigned long) ctx; \
@@ -1566,7 +1586,7 @@ static u64 PROG_NAME_ARGS(stack_size)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5, \
 				      const struct bpf_insn *insn) \
 { \
 	u64 stack[stack_size / sizeof(u64)]; \
-	u64 regs[MAX_BPF_REG]; \
+	u64 regs[MAX_BPF_EXT_REG]; \
 \
 	FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \
 	BPF_R1 = r1; \

kernel/bpf/verifier.c

@@ -710,6 +710,7 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
 		free_func_state(dst_state->frame[i]);
 		dst_state->frame[i] = NULL;
 	}
+	dst_state->speculative = src->speculative;
 	dst_state->curframe = src->curframe;
 	for (i = 0; i <= src->curframe; i++) {
 		dst = dst_state->frame[i];
@@ -754,7 +755,8 @@ static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx,
 }
 
 static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env,
-					     int insn_idx, int prev_insn_idx)
+					     int insn_idx, int prev_insn_idx,
+					     bool speculative)
 {
 	struct bpf_verifier_state *cur = env->cur_state;
 	struct bpf_verifier_stack_elem *elem;
@@ -772,6 +774,7 @@ static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env,
 	err = copy_verifier_state(&elem->st, cur);
 	if (err)
 		goto err;
+	elem->st.speculative |= speculative;
 	if (env->stack_size > BPF_COMPLEXITY_LIMIT_STACK) {
 		verbose(env, "BPF program is too complex\n");
 		goto err;
@@ -1387,6 +1390,31 @@ static int check_stack_read(struct bpf_verifier_env *env,
 	}
 }
 
+static int check_stack_access(struct bpf_verifier_env *env,
+			      const struct bpf_reg_state *reg,
+			      int off, int size)
+{
+	/* Stack accesses must be at a fixed offset, so that we
+	 * can determine what type of data were returned. See
+	 * check_stack_read().
+	 */
+	if (!tnum_is_const(reg->var_off)) {
+		char tn_buf[48];
+
+		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+		verbose(env, "variable stack access var_off=%s off=%d size=%d",
+			tn_buf, off, size);
+		return -EACCES;
+	}
+
+	if (off >= 0 || off < -MAX_BPF_STACK) {
+		verbose(env, "invalid stack off=%d size=%d\n", off, size);
+		return -EACCES;
+	}
+
+	return 0;
+}
+
 /* check read/write into map element returned by bpf_map_lookup_elem() */
 static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off,
 			      int size, bool zero_size_allowed)
@@ -1418,13 +1446,17 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
 	 */
 	if (env->log.level)
 		print_verifier_state(env, state);
+
 	/* The minimum value is only important with signed
 	 * comparisons where we can't assume the floor of a
 	 * value is 0.  If we are using signed variables for our
 	 * index'es we need to make sure that whatever we use
 	 * will have a set floor within our range.
 	 */
-	if (reg->smin_value < 0) {
+	if (reg->smin_value < 0 &&
+	    (reg->smin_value == S64_MIN ||
+	     (off + reg->smin_value != (s64)(s32)(off + reg->smin_value)) ||
+	      reg->smin_value + off < 0)) {
 		verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
 			regno);
 		return -EACCES;
@@ -1954,24 +1986,10 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		}
 
 	} else if (reg->type == PTR_TO_STACK) {
-		/* stack accesses must be at a fixed offset, so that we can
-		 * determine what type of data were returned.
-		 * See check_stack_read().
-		 */
-		if (!tnum_is_const(reg->var_off)) {
-			char tn_buf[48];
-
-			tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
-			verbose(env, "variable stack access var_off=%s off=%d size=%d",
-				tn_buf, off, size);
-			return -EACCES;
-		}
 		off += reg->var_off.value;
-		if (off >= 0 || off < -MAX_BPF_STACK) {
+		err = check_stack_access(env, reg, off, size);
-			verbose(env, "invalid stack off=%d size=%d\n", off,
+		if (err)
-				size);
+			return err;
-			return -EACCES;
-		}
 
 		state = func(env, reg);
 		err = update_stack_depth(env, state, off);
@@ -3052,6 +3070,102 @@ static bool check_reg_sane_offset(struct bpf_verifier_env *env,
 	return true;
 }
 
+static struct bpf_insn_aux_data *cur_aux(struct bpf_verifier_env *env)
+{
+	return &env->insn_aux_data[env->insn_idx];
+}
+
+static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
+			      u32 *ptr_limit, u8 opcode, bool off_is_neg)
+{
+	bool mask_to_left = (opcode == BPF_ADD &&  off_is_neg) ||
+			    (opcode == BPF_SUB && !off_is_neg);
+	u32 off;
+
+	switch (ptr_reg->type) {
+	case PTR_TO_STACK:
+		off = ptr_reg->off + ptr_reg->var_off.value;
+		if (mask_to_left)
+			*ptr_limit = MAX_BPF_STACK + off;
+		else
+			*ptr_limit = -off;
+		return 0;
+	case PTR_TO_MAP_VALUE:
+		if (mask_to_left) {
+			*ptr_limit = ptr_reg->umax_value + ptr_reg->off;
+		} else {
+			off = ptr_reg->smin_value + ptr_reg->off;
+			*ptr_limit = ptr_reg->map_ptr->value_size - off;
+		}
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int sanitize_ptr_alu(struct bpf_verifier_env *env,
+			    struct bpf_insn *insn,
+			    const struct bpf_reg_state *ptr_reg,
+			    struct bpf_reg_state *dst_reg,
+			    bool off_is_neg)
+{
+	struct bpf_verifier_state *vstate = env->cur_state;
+	struct bpf_insn_aux_data *aux = cur_aux(env);
+	bool ptr_is_dst_reg = ptr_reg == dst_reg;
+	u8 opcode = BPF_OP(insn->code);
+	u32 alu_state, alu_limit;
+	struct bpf_reg_state tmp;
+	bool ret;
+
+	if (env->allow_ptr_leaks || BPF_SRC(insn->code) == BPF_K)
+		return 0;
+
+	/* We already marked aux for masking from non-speculative
+	 * paths, thus we got here in the first place. We only care
+	 * to explore bad access from here.
+	 */
+	if (vstate->speculative)
+		goto do_sim;
+
+	alu_state  = off_is_neg ? BPF_ALU_NEG_VALUE : 0;
+	alu_state |= ptr_is_dst_reg ?
+		     BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST;
+
+	if (retrieve_ptr_limit(ptr_reg, &alu_limit, opcode, off_is_neg))
+		return 0;
+
+	/* If we arrived here from different branches with different
+	 * limits to sanitize, then this won't work.
+	 */
+	if (aux->alu_state &&
+	    (aux->alu_state != alu_state ||
+	     aux->alu_limit != alu_limit))
+		return -EACCES;
+
+	/* Corresponding fixup done in fixup_bpf_calls(). */
+	aux->alu_state = alu_state;
+	aux->alu_limit = alu_limit;
+
+do_sim:
+	/* Simulate and find potential out-of-bounds access under
+	 * speculative execution from truncation as a result of
+	 * masking when off was not within expected range. If off
+	 * sits in dst, then we temporarily need to move ptr there
+	 * to simulate dst (== 0) +/-= ptr. Needed, for example,
+	 * for cases where we use K-based arithmetic in one direction
+	 * and truncated reg-based in the other in order to explore
+	 * bad access.
+	 */
+	if (!ptr_is_dst_reg) {
+		tmp = *dst_reg;
+		*dst_reg = *ptr_reg;
+	}
+	ret = push_stack(env, env->insn_idx + 1, env->insn_idx, true);
+	if (!ptr_is_dst_reg)
+		*dst_reg = tmp;
+	return !ret ? -EFAULT : 0;
+}
+
 /* Handles arithmetic on a pointer and a scalar: computes new min/max and var_off.
  * Caller should also handle BPF_MOV case separately.
  * If we return -EACCES, caller may want to try again treating pointer as a
@@ -3070,8 +3184,9 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	    smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value;
 	u64 umin_val = off_reg->umin_value, umax_val = off_reg->umax_value,
 	    umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value;
+	u32 dst = insn->dst_reg, src = insn->src_reg;
 	u8 opcode = BPF_OP(insn->code);
-	u32 dst = insn->dst_reg;
+	int ret;
 
 	dst_reg = &regs[dst];
 
@@ -3104,6 +3219,13 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 		verbose(env, "R%d pointer arithmetic on %s prohibited\n",
 			dst, reg_type_str[ptr_reg->type]);
 		return -EACCES;
+	case PTR_TO_MAP_VALUE:
+		if (!env->allow_ptr_leaks && !known && (smin_val < 0) != (smax_val < 0)) {
+			verbose(env, "R%d has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root\n",
+				off_reg == dst_reg ? dst : src);
+			return -EACCES;
+		}
+		/* fall-through */
 	default:
 		break;
 	}
@@ -3120,6 +3242,11 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 
 	switch (opcode) {
 	case BPF_ADD:
+		ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0);
+		if (ret < 0) {
+			verbose(env, "R%d tried to add from different maps or paths\n", dst);
+			return ret;
+		}
 		/* We can take a fixed offset as long as it doesn't overflow
 		 * the s32 'off' field
 		 */
@@ -3170,6 +3297,11 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 		}
 		break;
 	case BPF_SUB:
+		ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0);
+		if (ret < 0) {
+			verbose(env, "R%d tried to sub from different maps or paths\n", dst);
+			return ret;
+		}
 		if (dst_reg == off_reg) {
 			/* scalar -= pointer.  Creates an unknown scalar */
 			verbose(env, "R%d tried to subtract pointer from scalar\n",
@@ -3249,6 +3381,25 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	__update_reg_bounds(dst_reg);
 	__reg_deduce_bounds(dst_reg);
 	__reg_bound_offset(dst_reg);
+
+	/* For unprivileged we require that resulting offset must be in bounds
+	 * in order to be able to sanitize access later on.
+	 */
+	if (!env->allow_ptr_leaks) {
+		if (dst_reg->type == PTR_TO_MAP_VALUE &&
+		    check_map_access(env, dst, dst_reg->off, 1, false)) {
+			verbose(env, "R%d pointer arithmetic of map value goes out of range, "
+				"prohibited for !root\n", dst);
+			return -EACCES;
+		} else if (dst_reg->type == PTR_TO_STACK &&
+			   check_stack_access(env, dst_reg, dst_reg->off +
+					      dst_reg->var_off.value, 1)) {
+			verbose(env, "R%d stack pointer arithmetic goes out of range, "
+				"prohibited for !root\n", dst);
+			return -EACCES;
+		}
+	}
+
 	return 0;
 }
 
@@ -4348,7 +4499,8 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 		}
 	}
 
-	other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx);
+	other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx,
+				  false);
 	if (!other_branch)
 		return -EFAULT;
 	other_branch_regs = other_branch->frame[other_branch->curframe]->regs;
@@ -5458,6 +5610,12 @@ static bool states_equal(struct bpf_verifier_env *env,
 	if (old->curframe != cur->curframe)
 		return false;
 
+	/* Verification state from speculative execution simulation
+	 * must never prune a non-speculative execution one.
+	 */
+	if (old->speculative && !cur->speculative)
+		return false;
+
 	/* for states to be equal callsites have to be the same
 	 * and all frame states need to be equivalent
 	 */
@@ -5650,7 +5808,6 @@ static int do_check(struct bpf_verifier_env *env)
 	struct bpf_insn *insns = env->prog->insnsi;
 	struct bpf_reg_state *regs;
 	int insn_cnt = env->prog->len, i;
-	int insn_idx, prev_insn_idx = 0;
 	int insn_processed = 0;
 	bool do_print_state = false;
 
@@ -5660,6 +5817,7 @@ static int do_check(struct bpf_verifier_env *env)
 	if (!state)
 		return -ENOMEM;
 	state->curframe = 0;
+	state->speculative = false;
 	state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL);
 	if (!state->frame[0]) {
 		kfree(state);
@@ -5670,19 +5828,19 @@ static int do_check(struct bpf_verifier_env *env)
 			BPF_MAIN_FUNC /* callsite */,
 			0 /* frameno */,
 			0 /* subprogno, zero == main subprog */);
-	insn_idx = 0;
+
 	for (;;) {
 		struct bpf_insn *insn;
 		u8 class;
 		int err;
 
-		if (insn_idx >= insn_cnt) {
+		if (env->insn_idx >= insn_cnt) {
 			verbose(env, "invalid insn idx %d insn_cnt %d\n",
-				insn_idx, insn_cnt);
+				env->insn_idx, insn_cnt);
 			return -EFAULT;
 		}
 
-		insn = &insns[insn_idx];
+		insn = &insns[env->insn_idx];
 		class = BPF_CLASS(insn->code);
 
 		if (++insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) {
@@ -5692,17 +5850,19 @@ static int do_check(struct bpf_verifier_env *env)
 			return -E2BIG;
 		}
 
-		err = is_state_visited(env, insn_idx);
+		err = is_state_visited(env, env->insn_idx);
 		if (err < 0)
 			return err;
 		if (err == 1) {
 			/* found equivalent state, can prune the search */
 			if (env->log.level) {
 				if (do_print_state)
-					verbose(env, "\nfrom %d to %d: safe\n",
+					verbose(env, "\nfrom %d to %d%s: safe\n",
-						prev_insn_idx, insn_idx);
+						env->prev_insn_idx, env->insn_idx,
+						env->cur_state->speculative ?
+						" (speculative execution)" : "");
 				else
-					verbose(env, "%d: safe\n", insn_idx);
+					verbose(env, "%d: safe\n", env->insn_idx);
 			}
 			goto process_bpf_exit;
 		}
@@ -5715,10 +5875,12 @@ static int do_check(struct bpf_verifier_env *env)
 
 		if (env->log.level > 1 || (env->log.level && do_print_state)) {
 			if (env->log.level > 1)
-				verbose(env, "%d:", insn_idx);
+				verbose(env, "%d:", env->insn_idx);
 			else
-				verbose(env, "\nfrom %d to %d:",
+				verbose(env, "\nfrom %d to %d%s:",
-					prev_insn_idx, insn_idx);
+					env->prev_insn_idx, env->insn_idx,
+					env->cur_state->speculative ?
+					" (speculative execution)" : "");
 			print_verifier_state(env, state->frame[state->curframe]);
 			do_print_state = false;
 		}
@@ -5729,20 +5891,20 @@ static int do_check(struct bpf_verifier_env *env)
 				.private_data	= env,
 			};
 
-			verbose_linfo(env, insn_idx, "; ");
+			verbose_linfo(env, env->insn_idx, "; ");
-			verbose(env, "%d: ", insn_idx);
+			verbose(env, "%d: ", env->insn_idx);
 			print_bpf_insn(&cbs, insn, env->allow_ptr_leaks);
 		}
 
 		if (bpf_prog_is_dev_bound(env->prog->aux)) {
-			err = bpf_prog_offload_verify_insn(env, insn_idx,
+			err = bpf_prog_offload_verify_insn(env, env->insn_idx,
-							   prev_insn_idx);
+							   env->prev_insn_idx);
 			if (err)
 				return err;
 		}
 
 		regs = cur_regs(env);
-		env->insn_aux_data[insn_idx].seen = true;
+		env->insn_aux_data[env->insn_idx].seen = true;
 
 		if (class == BPF_ALU || class == BPF_ALU64) {
 			err = check_alu_op(env, insn);
@@ -5768,13 +5930,13 @@ static int do_check(struct bpf_verifier_env *env)
 			/* check that memory (src_reg + off) is readable,
 			 * the state of dst_reg will be updated by this func
 			 */
-			err = check_mem_access(env, insn_idx, insn->src_reg, insn->off,
+			err = check_mem_access(env, env->insn_idx, insn->src_reg,
-					       BPF_SIZE(insn->code), BPF_READ,
+					       insn->off, BPF_SIZE(insn->code),
-					       insn->dst_reg, false);
+					       BPF_READ, insn->dst_reg, false);
 			if (err)
 				return err;
 
-			prev_src_type = &env->insn_aux_data[insn_idx].ptr_type;
+			prev_src_type = &env->insn_aux_data[env->insn_idx].ptr_type;
 
 			if (*prev_src_type == NOT_INIT) {
 				/* saw a valid insn
@@ -5799,10 +5961,10 @@ static int do_check(struct bpf_verifier_env *env)
 			enum bpf_reg_type *prev_dst_type, dst_reg_type;
 
 			if (BPF_MODE(insn->code) == BPF_XADD) {
-				err = check_xadd(env, insn_idx, insn);
+				err = check_xadd(env, env->insn_idx, insn);
 				if (err)
 					return err;
-				insn_idx++;
+				env->insn_idx++;
 				continue;
 			}
 
@@ -5818,13 +5980,13 @@ static int do_check(struct bpf_verifier_env *env)
 			dst_reg_type = regs[insn->dst_reg].type;
 
 			/* check that memory (dst_reg + off) is writeable */
-			err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
+			err = check_mem_access(env, env->insn_idx, insn->dst_reg,
-					       BPF_SIZE(insn->code), BPF_WRITE,
+					       insn->off, BPF_SIZE(insn->code),
-					       insn->src_reg, false);
+					       BPF_WRITE, insn->src_reg, false);
 			if (err)
 				return err;
 
-			prev_dst_type = &env->insn_aux_data[insn_idx].ptr_type;
+			prev_dst_type = &env->insn_aux_data[env->insn_idx].ptr_type;
 
 			if (*prev_dst_type == NOT_INIT) {
 				*prev_dst_type = dst_reg_type;
@@ -5852,9 +6014,9 @@ static int do_check(struct bpf_verifier_env *env)
 			}
 
 			/* check that memory (dst_reg + off) is writeable */
-			err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
+			err = check_mem_access(env, env->insn_idx, insn->dst_reg,
-					       BPF_SIZE(insn->code), BPF_WRITE,
+					       insn->off, BPF_SIZE(insn->code),
-					       -1, false);
+					       BPF_WRITE, -1, false);
 			if (err)
 				return err;
 
@@ -5872,9 +6034,9 @@ static int do_check(struct bpf_verifier_env *env)
 				}
 
 				if (insn->src_reg == BPF_PSEUDO_CALL)
-					err = check_func_call(env, insn, &insn_idx);
+					err = check_func_call(env, insn, &env->insn_idx);
 				else
-					err = check_helper_call(env, insn->imm, insn_idx);
+					err = check_helper_call(env, insn->imm, env->insn_idx);
 				if (err)
 					return err;
 
@@ -5887,7 +6049,7 @@ static int do_check(struct bpf_verifier_env *env)
 					return -EINVAL;
 				}
 
-				insn_idx += insn->off + 1;
+				env->insn_idx += insn->off + 1;
 				continue;
 
 			} else if (opcode == BPF_EXIT) {
@@ -5901,8 +6063,8 @@ static int do_check(struct bpf_verifier_env *env)
 
 				if (state->curframe) {
 					/* exit from nested function */
-					prev_insn_idx = insn_idx;
+					env->prev_insn_idx = env->insn_idx;
-					err = prepare_func_exit(env, &insn_idx);
+					err = prepare_func_exit(env, &env->insn_idx);
 					if (err)
 						return err;
 					do_print_state = true;
@@ -5932,7 +6094,8 @@ static int do_check(struct bpf_verifier_env *env)
 				if (err)
 					return err;
 process_bpf_exit:
-				err = pop_stack(env, &prev_insn_idx, &insn_idx);
+				err = pop_stack(env, &env->prev_insn_idx,
+						&env->insn_idx);
 				if (err < 0) {
 					if (err != -ENOENT)
 						return err;
@@ -5942,7 +6105,7 @@ static int do_check(struct bpf_verifier_env *env)
 					continue;
 				}
 			} else {
-				err = check_cond_jmp_op(env, insn, &insn_idx);
+				err = check_cond_jmp_op(env, insn, &env->insn_idx);
 				if (err)
 					return err;
 			}
@@ -5959,8 +6122,8 @@ static int do_check(struct bpf_verifier_env *env)
 				if (err)
 					return err;
 
-				insn_idx++;
+				env->insn_idx++;
-				env->insn_aux_data[insn_idx].seen = true;
+				env->insn_aux_data[env->insn_idx].seen = true;
 			} else {
 				verbose(env, "invalid BPF_LD mode\n");
 				return -EINVAL;
@@ -5970,7 +6133,7 @@ static int do_check(struct bpf_verifier_env *env)
 			return -EINVAL;
 		}
 
-		insn_idx++;
+		env->insn_idx++;
 	}
 
 	verbose(env, "processed %d insns (limit %d), stack depth ",
@@ -6709,6 +6872,57 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 			continue;
 		}
 
+		if (insn->code == (BPF_ALU64 | BPF_ADD | BPF_X) ||
+		    insn->code == (BPF_ALU64 | BPF_SUB | BPF_X)) {
+			const u8 code_add = BPF_ALU64 | BPF_ADD | BPF_X;
+			const u8 code_sub = BPF_ALU64 | BPF_SUB | BPF_X;
+			struct bpf_insn insn_buf[16];
+			struct bpf_insn *patch = &insn_buf[0];
+			bool issrc, isneg;
+			u32 off_reg;
+
+			aux = &env->insn_aux_data[i + delta];
+			if (!aux->alu_state)
+				continue;
+
+			isneg = aux->alu_state & BPF_ALU_NEG_VALUE;
+			issrc = (aux->alu_state & BPF_ALU_SANITIZE) ==
+				BPF_ALU_SANITIZE_SRC;
+
+			off_reg = issrc ? insn->src_reg : insn->dst_reg;
+			if (isneg)
+				*patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1);
+			*patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit - 1);
+			*patch++ = BPF_ALU64_REG(BPF_SUB, BPF_REG_AX, off_reg);
+			*patch++ = BPF_ALU64_REG(BPF_OR, BPF_REG_AX, off_reg);
+			*patch++ = BPF_ALU64_IMM(BPF_NEG, BPF_REG_AX, 0);
+			*patch++ = BPF_ALU64_IMM(BPF_ARSH, BPF_REG_AX, 63);
+			if (issrc) {
+				*patch++ = BPF_ALU64_REG(BPF_AND, BPF_REG_AX,
+							 off_reg);
+				insn->src_reg = BPF_REG_AX;
+			} else {
+				*patch++ = BPF_ALU64_REG(BPF_AND, off_reg,
+							 BPF_REG_AX);
+			}
+			if (isneg)
+				insn->code = insn->code == code_add ?
+					     code_sub : code_add;
+			*patch++ = *insn;
+			if (issrc && isneg)
+				*patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1);
+			cnt = patch - insn_buf;
+
+			new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+			if (!new_prog)
+				return -ENOMEM;
+
+			delta    += cnt - 1;
+			env->prog = prog = new_prog;
+			insn      = new_prog->insnsi + i + delta;
+			continue;
+		}
+
 		if (insn->code != (BPF_JMP | BPF_CALL))
 			continue;
 		if (insn->src_reg == BPF_PSEUDO_CALL)

net/ax25/af_ax25.c

@@ -653,15 +653,22 @@ static int ax25_setsockopt(struct socket *sock, int level, int optname,
 			break;
 		}
 
-		dev = dev_get_by_name(&init_net, devname);
+		rtnl_lock();
+		dev = __dev_get_by_name(&init_net, devname);
 		if (!dev) {
+			rtnl_unlock();
 			res = -ENODEV;
 			break;
 		}
 
 		ax25->ax25_dev = ax25_dev_ax25dev(dev);
+		if (!ax25->ax25_dev) {
+			rtnl_unlock();
+			res = -ENODEV;
+			break;
+		}
 		ax25_fillin_cb(ax25, ax25->ax25_dev);
-		dev_put(dev);
+		rtnl_unlock();
 		break;
 
 	default:

net/ax25/ax25_dev.c

@@ -116,6 +116,7 @@ void ax25_dev_device_down(struct net_device *dev)
 	if ((s = ax25_dev_list) == ax25_dev) {
 		ax25_dev_list = s->next;
 		spin_unlock_bh(&ax25_dev_lock);
+		dev->ax25_ptr = NULL;
 		dev_put(dev);
 		kfree(ax25_dev);
 		return;
@@ -125,6 +126,7 @@ void ax25_dev_device_down(struct net_device *dev)
 		if (s->next == ax25_dev) {
 			s->next = ax25_dev->next;
 			spin_unlock_bh(&ax25_dev_lock);
+			dev->ax25_ptr = NULL;
 			dev_put(dev);
 			kfree(ax25_dev);
 			return;

net/compat.c

@@ -467,12 +467,14 @@ int compat_sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp)
 	ctv = (struct compat_timeval __user *) userstamp;
 	err = -ENOENT;
 	sock_enable_timestamp(sk, SOCK_TIMESTAMP);
-	tv = ktime_to_timeval(sk->sk_stamp);
+	tv = ktime_to_timeval(sock_read_timestamp(sk));
+
 	if (tv.tv_sec == -1)
 		return err;
 	if (tv.tv_sec == 0) {
-		sk->sk_stamp = ktime_get_real();
+		ktime_t kt = ktime_get_real();
-		tv = ktime_to_timeval(sk->sk_stamp);
+		sock_write_timestamp(sk, kt);
+		tv = ktime_to_timeval(kt);
 	}
 	err = 0;
 	if (put_user(tv.tv_sec, &ctv->tv_sec) ||
@@ -494,12 +496,13 @@ int compat_sock_get_timestampns(struct sock *sk, struct timespec __user *usersta
 	ctv = (struct compat_timespec __user *) userstamp;
 	err = -ENOENT;
 	sock_enable_timestamp(sk, SOCK_TIMESTAMP);
-	ts = ktime_to_timespec(sk->sk_stamp);
+	ts = ktime_to_timespec(sock_read_timestamp(sk));
 	if (ts.tv_sec == -1)
 		return err;
 	if (ts.tv_sec == 0) {
-		sk->sk_stamp = ktime_get_real();
+		ktime_t kt = ktime_get_real();
-		ts = ktime_to_timespec(sk->sk_stamp);
+		sock_write_timestamp(sk, kt);
+		ts = ktime_to_timespec(kt);
 	}
 	err = 0;
 	if (put_user(ts.tv_sec, &ctv->tv_sec) ||

net/core/ethtool.c

@@ -793,8 +793,13 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev,
 		if (rc >= 0)
 			info.n_priv_flags = rc;
 	}
-	if (ops->get_regs_len)
+	if (ops->get_regs_len) {
-		info.regdump_len = ops->get_regs_len(dev);
+		int ret = ops->get_regs_len(dev);
+
+		if (ret > 0)
+			info.regdump_len = ret;
+	}
+
 	if (ops->get_eeprom_len)
 		info.eedump_len = ops->get_eeprom_len(dev);
 
@@ -1337,6 +1342,9 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr)
 		return -EFAULT;
 
 	reglen = ops->get_regs_len(dev);
+	if (reglen <= 0)
+		return reglen;
+
 	if (regs.len > reglen)
 		regs.len = reglen;
 

net/core/rtnetlink.c

@@ -4104,6 +4104,11 @@ static int rtnl_fdb_get(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	if (err < 0)
 		return err;
 
+	if (!addr) {
+		NL_SET_ERR_MSG(extack, "Missing lookup address for fdb get request");
+		return -EINVAL;
+	}
+
 	if (brport_idx) {
 		dev = __dev_get_by_index(net, brport_idx);
 		if (!dev) {

net/core/sock.c

@@ -2751,6 +2751,9 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 	sk->sk_sndtimeo		=	MAX_SCHEDULE_TIMEOUT;
 
 	sk->sk_stamp = SK_DEFAULT_STAMP;
+#if BITS_PER_LONG==32
+	seqlock_init(&sk->sk_stamp_seq);
+#endif
 	atomic_set(&sk->sk_zckey, 0);
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
@@ -2850,12 +2853,13 @@ int sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp)
 	struct timeval tv;
 
 	sock_enable_timestamp(sk, SOCK_TIMESTAMP);
-	tv = ktime_to_timeval(sk->sk_stamp);
+	tv = ktime_to_timeval(sock_read_timestamp(sk));
 	if (tv.tv_sec == -1)
 		return -ENOENT;
 	if (tv.tv_sec == 0) {
-		sk->sk_stamp = ktime_get_real();
+		ktime_t kt = ktime_get_real();
-		tv = ktime_to_timeval(sk->sk_stamp);
+		sock_write_timestamp(sk, kt);
+		tv = ktime_to_timeval(kt);
 	}
 	return copy_to_user(userstamp, &tv, sizeof(tv)) ? -EFAULT : 0;
 }
@@ -2866,11 +2870,12 @@ int sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp)
 	struct timespec ts;
 
 	sock_enable_timestamp(sk, SOCK_TIMESTAMP);
-	ts = ktime_to_timespec(sk->sk_stamp);
+	ts = ktime_to_timespec(sock_read_timestamp(sk));
 	if (ts.tv_sec == -1)
 		return -ENOENT;
 	if (ts.tv_sec == 0) {
-		sk->sk_stamp = ktime_get_real();
+		ktime_t kt = ktime_get_real();
+		sock_write_timestamp(sk, kt);
 		ts = ktime_to_timespec(sk->sk_stamp);
 	}
 	return copy_to_user(userstamp, &ts, sizeof(ts)) ? -EFAULT : 0;

net/ipv4/fib_rules.c

@@ -198,11 +198,15 @@ static int fib4_rule_match(struct fib_rule *rule, struct flowi *fl, int flags)
 
 static struct fib_table *fib_empty_table(struct net *net)
 {
-	u32 id;
+	u32 id = 1;
 
-	for (id = 1; id <= RT_TABLE_MAX; id++)
+	while (1) {
 		if (!fib_get_table(net, id))
 			return fib_new_table(net, id);
+
+		if (id++ == RT_TABLE_MAX)
+			break;
+	}
 	return NULL;
 }
 

net/ipv4/ip_gre.c

@@ -676,6 +676,9 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	const struct iphdr *tnl_params;
 
+	if (!pskb_inet_may_pull(skb))
+		goto free_skb;
+
 	if (tunnel->collect_md) {
 		gre_fb_xmit(skb, dev, skb->protocol);
 		return NETDEV_TX_OK;
@@ -719,6 +722,9 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb,
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	bool truncate = false;
 
+	if (!pskb_inet_may_pull(skb))
+		goto free_skb;
+
 	if (tunnel->collect_md) {
 		erspan_fb_xmit(skb, dev, skb->protocol);
 		return NETDEV_TX_OK;
@@ -762,6 +768,9 @@ static netdev_tx_t gre_tap_xmit(struct sk_buff *skb,
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 
+	if (!pskb_inet_may_pull(skb))
+		goto free_skb;
+
 	if (tunnel->collect_md) {
 		gre_fb_xmit(skb, dev, htons(ETH_P_TEB));
 		return NETDEV_TX_OK;

net/ipv4/ip_tunnel.c

@@ -627,7 +627,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		    const struct iphdr *tnl_params, u8 protocol)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
-	unsigned int inner_nhdr_len = 0;
 	const struct iphdr *inner_iph;
 	struct flowi4 fl4;
 	u8     tos, ttl;
@@ -637,14 +636,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	__be32 dst;
 	bool connected;
 
-	/* ensure we can access the inner net header, for several users below */
-	if (skb->protocol == htons(ETH_P_IP))
-		inner_nhdr_len = sizeof(struct iphdr);
-	else if (skb->protocol == htons(ETH_P_IPV6))
-		inner_nhdr_len = sizeof(struct ipv6hdr);
-	if (unlikely(!pskb_may_pull(skb, inner_nhdr_len)))
-		goto tx_error;
-
 	inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
 	connected = (tunnel->parms.iph.daddr != 0);
 

net/ipv4/ip_vti.c

@@ -241,6 +241,9 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	struct flowi fl;
 
+	if (!pskb_inet_may_pull(skb))
+		goto tx_err;
+
 	memset(&fl, 0, sizeof(fl));
 
 	switch (skb->protocol) {
@@ -253,15 +256,18 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 		memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
 		break;
 	default:
-		dev->stats.tx_errors++;
+		goto tx_err;
-		dev_kfree_skb(skb);
-		return NETDEV_TX_OK;
 	}
 
 	/* override mark with tunnel output key */
 	fl.flowi_mark = be32_to_cpu(tunnel->parms.o_key);
 
 	return vti_xmit(skb, dev, &fl);
+
+tx_err:
+	dev->stats.tx_errors++;
+	kfree_skb(skb);
+	return NETDEV_TX_OK;
 }
 
 static int vti4_err(struct sk_buff *skb, u32 info)

net/ipv6/addrconf.c

@@ -4736,8 +4736,8 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
 			 IFA_F_MCAUTOJOIN | IFA_F_OPTIMISTIC;
 
 	idev = ipv6_find_idev(dev);
-	if (IS_ERR(idev))
+	if (!idev)
-		return PTR_ERR(idev);
+		return -ENOBUFS;
 
 	if (!ipv6_allow_optimistic_dad(net, idev))
 		cfg.ifa_flags &= ~IFA_F_OPTIMISTIC;

net/ipv6/af_inet6.c

@@ -350,6 +350,9 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
 					err = -EINVAL;
 					goto out_unlock;
 				}
+			}
+
+			if (sk->sk_bound_dev_if) {
 				dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if);
 				if (!dev) {
 					err = -ENODEV;

net/ipv6/ip6_fib.c

@@ -627,7 +627,11 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 			return -ENOENT;
 		}
 
-		res = fib6_dump_table(tb, skb, cb);
+		if (!cb->args[0]) {
+			res = fib6_dump_table(tb, skb, cb);
+			if (!res)
+				cb->args[0] = 1;
+		}
 		goto out;
 	}
 

net/ipv6/ip6_gre.c

@@ -881,6 +881,9 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb,
 	struct net_device_stats *stats = &t->dev->stats;
 	int ret;
 
+	if (!pskb_inet_may_pull(skb))
+		goto tx_err;
+
 	if (!ip6_tnl_xmit_ctl(t, &t->parms.laddr, &t->parms.raddr))
 		goto tx_err;
 
@@ -923,6 +926,9 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 	int nhoff;
 	int thoff;
 
+	if (!pskb_inet_may_pull(skb))
+		goto tx_err;
+
 	if (!ip6_tnl_xmit_ctl(t, &t->parms.laddr, &t->parms.raddr))
 		goto tx_err;
 
@@ -995,8 +1001,6 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 			goto tx_err;
 		}
 	} else {
-		struct ipv6hdr *ipv6h = ipv6_hdr(skb);
-
 		switch (skb->protocol) {
 		case htons(ETH_P_IP):
 			memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
@@ -1004,7 +1008,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 						 &dsfield, &encap_limit);
 			break;
 		case htons(ETH_P_IPV6):
-			if (ipv6_addr_equal(&t->parms.raddr, &ipv6h->saddr))
+			if (ipv6_addr_equal(&t->parms.raddr, &ipv6_hdr(skb)->saddr))
 				goto tx_err;
 			if (prepare_ip6gre_xmit_ipv6(skb, dev, &fl6,
 						     &dsfield, &encap_limit))

net/ipv6/ip6_tunnel.c

@@ -1243,10 +1243,6 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	u8 tproto;
 	int err;
 
-	/* ensure we can access the full inner ip header */
-	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
-		return -1;
-
 	iph = ip_hdr(skb);
 	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
 
@@ -1321,9 +1317,6 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	u8 tproto;
 	int err;
 
-	if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
-		return -1;
-
 	ipv6h = ipv6_hdr(skb);
 	tproto = READ_ONCE(t->parms.proto);
 	if ((tproto != IPPROTO_IPV6 && tproto != 0) ||
@@ -1405,6 +1398,9 @@ ip6_tnl_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct net_device_stats *stats = &t->dev->stats;
 	int ret;
 
+	if (!pskb_inet_may_pull(skb))
+		goto tx_err;
+
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
 		ret = ip4ip6_tnl_xmit(skb, dev);

net/ipv6/ip6_vti.c

@@ -522,18 +522,18 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
 	struct net_device_stats *stats = &t->dev->stats;
-	struct ipv6hdr *ipv6h;
 	struct flowi fl;
 	int ret;
 
+	if (!pskb_inet_may_pull(skb))
+		goto tx_err;
+
 	memset(&fl, 0, sizeof(fl));
 
 	switch (skb->protocol) {
 	case htons(ETH_P_IPV6):
-		ipv6h = ipv6_hdr(skb);
-
 		if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) ||
-		    vti6_addr_conflict(t, ipv6h))
+		    vti6_addr_conflict(t, ipv6_hdr(skb)))
 			goto tx_err;
 
 		xfrm_decode_session(skb, &fl, AF_INET6);

net/ipv6/ip6mr.c

@@ -51,6 +51,7 @@
 #include <linux/export.h>
 #include <net/ip6_checksum.h>
 #include <linux/netconf.h>
+#include <net/ip_tunnels.h>
 
 #include <linux/nospec.h>
 
@@ -599,13 +600,12 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb,
 		.flowi6_iif	= skb->skb_iif ? : LOOPBACK_IFINDEX,
 		.flowi6_mark	= skb->mark,
 	};
-	int err;
 
-	err = ip6mr_fib_lookup(net, &fl6, &mrt);
+	if (!pskb_inet_may_pull(skb))
-	if (err < 0) {
+		goto tx_err;
-		kfree_skb(skb);
+
-		return err;
+	if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0)
-	}
+		goto tx_err;
 
 	read_lock(&mrt_lock);
 	dev->stats.tx_bytes += skb->len;
@@ -614,6 +614,11 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb,
 	read_unlock(&mrt_lock);
 	kfree_skb(skb);
 	return NETDEV_TX_OK;
+
+tx_err:
+	dev->stats.tx_errors++;
+	kfree_skb(skb);
+	return NETDEV_TX_OK;
 }
 
 static int reg_vif_get_iflink(const struct net_device *dev)

net/ipv6/reassembly.c

@@ -210,7 +210,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
 	if (next && next->ip_defrag_offset < end)
 		goto discard_fq;
 
-	/* Note : skb->ip_defrag_offset and skb->dev share the same location */
+	/* Note : skb->ip_defrag_offset and skb->sk share the same location */
 	dev = skb->dev;
 	if (dev)
 		fq->iif = dev->ifindex;

net/ipv6/route.c

@@ -210,7 +210,9 @@ struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw,
 	n = __ipv6_neigh_lookup(dev, daddr);
 	if (n)
 		return n;
-	return neigh_create(&nd_tbl, daddr, dev);
+
+	n = neigh_create(&nd_tbl, daddr, dev);
+	return IS_ERR(n) ? NULL : n;
 }
 
 static struct neighbour *ip6_dst_neigh_lookup(const struct dst_entry *dst,
@@ -5054,12 +5056,16 @@ int ipv6_sysctl_rtcache_flush(struct ctl_table *ctl, int write,
 {
 	struct net *net;
 	int delay;
+	int ret;
 	if (!write)
 		return -EINVAL;
 
 	net = (struct net *)ctl->extra1;
 	delay = net->ipv6.sysctl.flush_delay;
-	proc_dointvec(ctl, write, buffer, lenp, ppos);
+	ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
+	if (ret)
+		return ret;
+
 	fib6_run_gc(delay <= 0 ? 0 : (unsigned long)delay, net, delay > 0);
 	return 0;
 }

net/ipv6/sit.c

@@ -1021,6 +1021,9 @@ static netdev_tx_t sit_tunnel_xmit__(struct sk_buff *skb,
 static netdev_tx_t sit_tunnel_xmit(struct sk_buff *skb,
 				   struct net_device *dev)
 {
+	if (!pskb_inet_may_pull(skb))
+		goto tx_err;
+
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
 		sit_tunnel_xmit__(skb, dev, IPPROTO_IPIP);

net/netfilter/nf_conncount.c

@@ -33,12 +33,6 @@
 
 #define CONNCOUNT_SLOTS		256U
 
-#ifdef CONFIG_LOCKDEP
-#define CONNCOUNT_LOCK_SLOTS	8U
-#else
-#define CONNCOUNT_LOCK_SLOTS	256U
-#endif
-
 #define CONNCOUNT_GC_MAX_NODES	8
 #define MAX_KEYLEN		5
 
@@ -49,8 +43,6 @@ struct nf_conncount_tuple {
 	struct nf_conntrack_zone	zone;
 	int				cpu;
 	u32				jiffies32;
-	bool				dead;
-	struct rcu_head			rcu_head;
 };
 
 struct nf_conncount_rb {
@@ -60,7 +52,7 @@ struct nf_conncount_rb {
 	struct rcu_head rcu_head;
 };
 
-static spinlock_t nf_conncount_locks[CONNCOUNT_LOCK_SLOTS] __cacheline_aligned_in_smp;
+static spinlock_t nf_conncount_locks[CONNCOUNT_SLOTS] __cacheline_aligned_in_smp;
 
 struct nf_conncount_data {
 	unsigned int keylen;
@@ -89,79 +81,25 @@ static int key_diff(const u32 *a, const u32 *b, unsigned int klen)
 	return memcmp(a, b, klen * sizeof(u32));
 }
 
-enum nf_conncount_list_add
+static void conn_free(struct nf_conncount_list *list,
-nf_conncount_add(struct nf_conncount_list *list,
-		 const struct nf_conntrack_tuple *tuple,
-		 const struct nf_conntrack_zone *zone)
-{
-	struct nf_conncount_tuple *conn;
-
-	if (WARN_ON_ONCE(list->count > INT_MAX))
-		return NF_CONNCOUNT_ERR;
-
-	conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC);
-	if (conn == NULL)
-		return NF_CONNCOUNT_ERR;
-
-	conn->tuple = *tuple;
-	conn->zone = *zone;
-	conn->cpu = raw_smp_processor_id();
-	conn->jiffies32 = (u32)jiffies;
-	conn->dead = false;
-	spin_lock_bh(&list->list_lock);
-	if (list->dead == true) {
-		kmem_cache_free(conncount_conn_cachep, conn);
-		spin_unlock_bh(&list->list_lock);
-		return NF_CONNCOUNT_SKIP;
-	}
-	list_add_tail(&conn->node, &list->head);
-	list->count++;
-	spin_unlock_bh(&list->list_lock);
-	return NF_CONNCOUNT_ADDED;
-}
-EXPORT_SYMBOL_GPL(nf_conncount_add);
-
-static void __conn_free(struct rcu_head *h)
-{
-	struct nf_conncount_tuple *conn;
-
-	conn = container_of(h, struct nf_conncount_tuple, rcu_head);
-	kmem_cache_free(conncount_conn_cachep, conn);
-}
-
-static bool conn_free(struct nf_conncount_list *list,
 		      struct nf_conncount_tuple *conn)
 {
-	bool free_entry = false;
+	lockdep_assert_held(&list->list_lock);
-
-	spin_lock_bh(&list->list_lock);
-
-	if (conn->dead) {
-		spin_unlock_bh(&list->list_lock);
-		return free_entry;
-	}
 
 	list->count--;
-	conn->dead = true;
+	list_del(&conn->node);
-	list_del_rcu(&conn->node);
-	if (list->count == 0) {
-		list->dead = true;
-		free_entry = true;
-	}
 
-	spin_unlock_bh(&list->list_lock);
+	kmem_cache_free(conncount_conn_cachep, conn);
-	call_rcu(&conn->rcu_head, __conn_free);
-	return free_entry;
 }
 
 static const struct nf_conntrack_tuple_hash *
 find_or_evict(struct net *net, struct nf_conncount_list *list,
-	      struct nf_conncount_tuple *conn, bool *free_entry)
+	      struct nf_conncount_tuple *conn)
 {
 	const struct nf_conntrack_tuple_hash *found;
 	unsigned long a, b;
 	int cpu = raw_smp_processor_id();
-	__s32 age;
+	u32 age;
 
 	found = nf_conntrack_find_get(net, &conn->zone, &conn->tuple);
 	if (found)
@@ -176,52 +114,45 @@ find_or_evict(struct net *net, struct nf_conncount_list *list,
 	 */
 	age = a - b;
 	if (conn->cpu == cpu || age >= 2) {
-		*free_entry = conn_free(list, conn);
+		conn_free(list, conn);
 		return ERR_PTR(-ENOENT);
 	}
 
 	return ERR_PTR(-EAGAIN);
 }
 
-void nf_conncount_lookup(struct net *net,
+static int __nf_conncount_add(struct net *net,
-			 struct nf_conncount_list *list,
+			      struct nf_conncount_list *list,
-			 const struct nf_conntrack_tuple *tuple,
+			      const struct nf_conntrack_tuple *tuple,
-			 const struct nf_conntrack_zone *zone,
+			      const struct nf_conntrack_zone *zone)
-			 bool *addit)
 {
 	const struct nf_conntrack_tuple_hash *found;
 	struct nf_conncount_tuple *conn, *conn_n;
 	struct nf_conn *found_ct;
 	unsigned int collect = 0;
-	bool free_entry = false;
-
-	/* best effort only */
-	*addit = tuple ? true : false;
 
 	/* check the saved connections */
 	list_for_each_entry_safe(conn, conn_n, &list->head, node) {
 		if (collect > CONNCOUNT_GC_MAX_NODES)
 			break;
 
-		found = find_or_evict(net, list, conn, &free_entry);
+		found = find_or_evict(net, list, conn);
 		if (IS_ERR(found)) {
 			/* Not found, but might be about to be confirmed */
 			if (PTR_ERR(found) == -EAGAIN) {
-				if (!tuple)
-					continue;
-
 				if (nf_ct_tuple_equal(&conn->tuple, tuple) &&
 				    nf_ct_zone_id(&conn->zone, conn->zone.dir) ==
 				    nf_ct_zone_id(zone, zone->dir))
-					*addit = false;
+					return 0; /* already exists */
-			} else if (PTR_ERR(found) == -ENOENT)
+			} else {
 				collect++;
+			}
 			continue;
 		}
 
 		found_ct = nf_ct_tuplehash_to_ctrack(found);
 
-		if (tuple && nf_ct_tuple_equal(&conn->tuple, tuple) &&
+		if (nf_ct_tuple_equal(&conn->tuple, tuple) &&
 		    nf_ct_zone_equal(found_ct, zone, zone->dir)) {
 			/*
 			 * We should not see tuples twice unless someone hooks
@@ -229,7 +160,8 @@ void nf_conncount_lookup(struct net *net,
 			 *
 			 * Attempt to avoid a re-add in this case.
 			 */
-			*addit = false;
+			nf_ct_put(found_ct);
+			return 0;
 		} else if (already_closed(found_ct)) {
 			/*
 			 * we do not care about connections which are
@@ -243,19 +175,48 @@ void nf_conncount_lookup(struct net *net,
 
 		nf_ct_put(found_ct);
 	}
+
+	if (WARN_ON_ONCE(list->count > INT_MAX))
+		return -EOVERFLOW;
+
+	conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC);
+	if (conn == NULL)
+		return -ENOMEM;
+
+	conn->tuple = *tuple;
+	conn->zone = *zone;
+	conn->cpu = raw_smp_processor_id();
+	conn->jiffies32 = (u32)jiffies;
+	list_add_tail(&conn->node, &list->head);
+	list->count++;
+	return 0;
 }
-EXPORT_SYMBOL_GPL(nf_conncount_lookup);
+
+int nf_conncount_add(struct net *net,
+		     struct nf_conncount_list *list,
+		     const struct nf_conntrack_tuple *tuple,
+		     const struct nf_conntrack_zone *zone)
+{
+	int ret;
+
+	/* check the saved connections */
+	spin_lock_bh(&list->list_lock);
+	ret = __nf_conncount_add(net, list, tuple, zone);
+	spin_unlock_bh(&list->list_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nf_conncount_add);
 
 void nf_conncount_list_init(struct nf_conncount_list *list)
 {
 	spin_lock_init(&list->list_lock);
 	INIT_LIST_HEAD(&list->head);
 	list->count = 0;
-	list->dead = false;
 }
 EXPORT_SYMBOL_GPL(nf_conncount_list_init);
 
-/* Return true if the list is empty */
+/* Return true if the list is empty. Must be called with BH disabled. */
 bool nf_conncount_gc_list(struct net *net,
 			  struct nf_conncount_list *list)
 {
@@ -263,17 +224,17 @@ bool nf_conncount_gc_list(struct net *net,
 	struct nf_conncount_tuple *conn, *conn_n;
 	struct nf_conn *found_ct;
 	unsigned int collected = 0;
-	bool free_entry = false;
 	bool ret = false;
 
+	/* don't bother if other cpu is already doing GC */
+	if (!spin_trylock(&list->list_lock))
+		return false;
+
 	list_for_each_entry_safe(conn, conn_n, &list->head, node) {
-		found = find_or_evict(net, list, conn, &free_entry);
+		found = find_or_evict(net, list, conn);
 		if (IS_ERR(found)) {
-			if (PTR_ERR(found) == -ENOENT)  {
+			if (PTR_ERR(found) == -ENOENT)
-				if (free_entry)
-					return true;
 				collected++;
-			}
 			continue;
 		}
 
@@ -284,23 +245,19 @@ bool nf_conncount_gc_list(struct net *net,
 			 * closed already -> ditch it
 			 */
 			nf_ct_put(found_ct);
-			if (conn_free(list, conn))
+			conn_free(list, conn);
-				return true;
 			collected++;
 			continue;
 		}
 
 		nf_ct_put(found_ct);
 		if (collected > CONNCOUNT_GC_MAX_NODES)
-			return false;
+			break;
 	}
 
-	spin_lock_bh(&list->list_lock);
+	if (!list->count)
-	if (!list->count) {
-		list->dead = true;
 		ret = true;
-	}
+	spin_unlock(&list->list_lock);
-	spin_unlock_bh(&list->list_lock);
 
 	return ret;
 }
@@ -314,6 +271,7 @@ static void __tree_nodes_free(struct rcu_head *h)
 	kmem_cache_free(conncount_rb_cachep, rbconn);
 }
 
+/* caller must hold tree nf_conncount_locks[] lock */
 static void tree_nodes_free(struct rb_root *root,
 			    struct nf_conncount_rb *gc_nodes[],
 			    unsigned int gc_count)
@@ -323,8 +281,10 @@ static void tree_nodes_free(struct rb_root *root,
 	while (gc_count) {
 		rbconn = gc_nodes[--gc_count];
 		spin_lock(&rbconn->list.list_lock);
-		rb_erase(&rbconn->node, root);
+		if (!rbconn->list.count) {
-		call_rcu(&rbconn->rcu_head, __tree_nodes_free);
+			rb_erase(&rbconn->node, root);
+			call_rcu(&rbconn->rcu_head, __tree_nodes_free);
+		}
 		spin_unlock(&rbconn->list.list_lock);
 	}
 }
@@ -341,20 +301,19 @@ insert_tree(struct net *net,
 	    struct rb_root *root,
 	    unsigned int hash,
 	    const u32 *key,
-	    u8 keylen,
 	    const struct nf_conntrack_tuple *tuple,
 	    const struct nf_conntrack_zone *zone)
 {
-	enum nf_conncount_list_add ret;
 	struct nf_conncount_rb *gc_nodes[CONNCOUNT_GC_MAX_NODES];
 	struct rb_node **rbnode, *parent;
 	struct nf_conncount_rb *rbconn;
 	struct nf_conncount_tuple *conn;
 	unsigned int count = 0, gc_count = 0;
-	bool node_found = false;
+	u8 keylen = data->keylen;
-
+	bool do_gc = true;
-	spin_lock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
 
+	spin_lock_bh(&nf_conncount_locks[hash]);
+restart:
 	parent = NULL;
 	rbnode = &(root->rb_node);
 	while (*rbnode) {
@@ -368,45 +327,32 @@ insert_tree(struct net *net,
 		} else if (diff > 0) {
 			rbnode = &((*rbnode)->rb_right);
 		} else {
-			/* unlikely: other cpu added node already */
+			int ret;
-			node_found = true;
+
-			ret = nf_conncount_add(&rbconn->list, tuple, zone);
+			ret = nf_conncount_add(net, &rbconn->list, tuple, zone);
-			if (ret == NF_CONNCOUNT_ERR) {
+			if (ret)
 				count = 0; /* hotdrop */
-			} else if (ret == NF_CONNCOUNT_ADDED) {
+			else
 				count = rbconn->list.count;
-			} else {
+			tree_nodes_free(root, gc_nodes, gc_count);
-				/* NF_CONNCOUNT_SKIP, rbconn is already
+			goto out_unlock;
-				 * reclaimed by gc, insert a new tree node
-				 */
-				node_found = false;
-			}
-			break;
 		}
 
 		if (gc_count >= ARRAY_SIZE(gc_nodes))
 			continue;
 
-		if (nf_conncount_gc_list(net, &rbconn->list))
+		if (do_gc && nf_conncount_gc_list(net, &rbconn->list))
 			gc_nodes[gc_count++] = rbconn;
 	}
 
 	if (gc_count) {
 		tree_nodes_free(root, gc_nodes, gc_count);
-		/* tree_node_free before new allocation permits
+		schedule_gc_worker(data, hash);
-		 * allocator to re-use newly free'd object.
+		gc_count = 0;
-		 *
+		do_gc = false;
-		 * This is a rare event; in most cases we will find
+		goto restart;
-		 * existing node to re-use. (or gc_count is 0).
-		 */
-
-		if (gc_count >= ARRAY_SIZE(gc_nodes))
-			schedule_gc_worker(data, hash);
 	}
 
-	if (node_found)
-		goto out_unlock;
-
 	/* expected case: match, insert new node */
 	rbconn = kmem_cache_alloc(conncount_rb_cachep, GFP_ATOMIC);
 	if (rbconn == NULL)
@@ -430,7 +376,7 @@ insert_tree(struct net *net,
 	rb_link_node_rcu(&rbconn->node, parent, rbnode);
 	rb_insert_color(&rbconn->node, root);
 out_unlock:
-	spin_unlock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
+	spin_unlock_bh(&nf_conncount_locks[hash]);
 	return count;
 }
 
@@ -441,7 +387,6 @@ count_tree(struct net *net,
 	   const struct nf_conntrack_tuple *tuple,
 	   const struct nf_conntrack_zone *zone)
 {
-	enum nf_conncount_list_add ret;
 	struct rb_root *root;
 	struct rb_node *parent;
 	struct nf_conncount_rb *rbconn;
@@ -454,7 +399,6 @@ count_tree(struct net *net,
 	parent = rcu_dereference_raw(root->rb_node);
 	while (parent) {
 		int diff;
-		bool addit;
 
 		rbconn = rb_entry(parent, struct nf_conncount_rb, node);
 
@@ -464,31 +408,36 @@ count_tree(struct net *net,
 		} else if (diff > 0) {
 			parent = rcu_dereference_raw(parent->rb_right);
 		} else {
-			/* same source network -> be counted! */
+			int ret;
-			nf_conncount_lookup(net, &rbconn->list, tuple, zone,
-					    &addit);
 
-			if (!addit)
+			if (!tuple) {
+				nf_conncount_gc_list(net, &rbconn->list);
 				return rbconn->list.count;
+			}
 
-			ret = nf_conncount_add(&rbconn->list, tuple, zone);
+			spin_lock_bh(&rbconn->list.list_lock);
-			if (ret == NF_CONNCOUNT_ERR) {
+			/* Node might be about to be free'd.
-				return 0; /* hotdrop */
+			 * We need to defer to insert_tree() in this case.
-			} else if (ret == NF_CONNCOUNT_ADDED) {
+			 */
-				return rbconn->list.count;
+			if (rbconn->list.count == 0) {
-			} else {
+				spin_unlock_bh(&rbconn->list.list_lock);
-				/* NF_CONNCOUNT_SKIP, rbconn is already
-				 * reclaimed by gc, insert a new tree node
-				 */
 				break;
 			}
+
+			/* same source network -> be counted! */
+			ret = __nf_conncount_add(net, &rbconn->list, tuple, zone);
+			spin_unlock_bh(&rbconn->list.list_lock);
+			if (ret)
+				return 0; /* hotdrop */
+			else
+				return rbconn->list.count;
 		}
 	}
 
 	if (!tuple)
 		return 0;
 
-	return insert_tree(net, data, root, hash, key, keylen, tuple, zone);
+	return insert_tree(net, data, root, hash, key, tuple, zone);
 }
 
 static void tree_gc_worker(struct work_struct *work)
@@ -499,27 +448,47 @@ static void tree_gc_worker(struct work_struct *work)
 	struct rb_node *node;
 	unsigned int tree, next_tree, gc_count = 0;
 
-	tree = data->gc_tree % CONNCOUNT_LOCK_SLOTS;
+	tree = data->gc_tree % CONNCOUNT_SLOTS;
 	root = &data->root[tree];
 
+	local_bh_disable();
 	rcu_read_lock();
 	for (node = rb_first(root); node != NULL; node = rb_next(node)) {
 		rbconn = rb_entry(node, struct nf_conncount_rb, node);
 		if (nf_conncount_gc_list(data->net, &rbconn->list))
-			gc_nodes[gc_count++] = rbconn;
+			gc_count++;
 	}
 	rcu_read_unlock();
+	local_bh_enable();
+
+	cond_resched();
 
 	spin_lock_bh(&nf_conncount_locks[tree]);
+	if (gc_count < ARRAY_SIZE(gc_nodes))
+		goto next; /* do not bother */
 
-	if (gc_count) {
+	gc_count = 0;
-		tree_nodes_free(root, gc_nodes, gc_count);
+	node = rb_first(root);
+	while (node != NULL) {
+		rbconn = rb_entry(node, struct nf_conncount_rb, node);
+		node = rb_next(node);
+
+		if (rbconn->list.count > 0)
+			continue;
+
+		gc_nodes[gc_count++] = rbconn;
+		if (gc_count >= ARRAY_SIZE(gc_nodes)) {
+			tree_nodes_free(root, gc_nodes, gc_count);
+			gc_count = 0;
+		}
 	}
 
+	tree_nodes_free(root, gc_nodes, gc_count);
+next:
 	clear_bit(tree, data->pending_trees);
 
 	next_tree = (tree + 1) % CONNCOUNT_SLOTS;
-	next_tree = find_next_bit(data->pending_trees, next_tree, CONNCOUNT_SLOTS);
+	next_tree = find_next_bit(data->pending_trees, CONNCOUNT_SLOTS, next_tree);
 
 	if (next_tree < CONNCOUNT_SLOTS) {
 		data->gc_tree = next_tree;
@@ -621,10 +590,7 @@ static int __init nf_conncount_modinit(void)
 {
 	int i;
 
-	BUILD_BUG_ON(CONNCOUNT_LOCK_SLOTS > CONNCOUNT_SLOTS);
+	for (i = 0; i < CONNCOUNT_SLOTS; ++i)
-	BUILD_BUG_ON((CONNCOUNT_SLOTS % CONNCOUNT_LOCK_SLOTS) != 0);
-
-	for (i = 0; i < CONNCOUNT_LOCK_SLOTS; ++i)
 		spin_lock_init(&nf_conncount_locks[i]);
 
 	conncount_conn_cachep = kmem_cache_create("nf_conncount_tuple",

net/netfilter/nf_tables_api.c

@@ -5727,6 +5727,8 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net,
 		goto nla_put_failure;
 
 	nest = nla_nest_start(skb, NFTA_FLOWTABLE_HOOK);
+	if (!nest)
+		goto nla_put_failure;
 	if (nla_put_be32(skb, NFTA_FLOWTABLE_HOOK_NUM, htonl(flowtable->hooknum)) ||
 	    nla_put_be32(skb, NFTA_FLOWTABLE_HOOK_PRIORITY, htonl(flowtable->priority)))
 		goto nla_put_failure;

net/netfilter/nft_connlimit.c

@@ -30,7 +30,6 @@ static inline void nft_connlimit_do_eval(struct nft_connlimit *priv,
 	enum ip_conntrack_info ctinfo;
 	const struct nf_conn *ct;
 	unsigned int count;
-	bool addit;
 
 	tuple_ptr = &tuple;
 
@@ -44,19 +43,12 @@ static inline void nft_connlimit_do_eval(struct nft_connlimit *priv,
 		return;
 	}
 
-	nf_conncount_lookup(nft_net(pkt), &priv->list, tuple_ptr, zone,
+	if (nf_conncount_add(nft_net(pkt), &priv->list, tuple_ptr, zone)) {
-			    &addit);
-	count = priv->list.count;
-
-	if (!addit)
-		goto out;
-
-	if (nf_conncount_add(&priv->list, tuple_ptr, zone) == NF_CONNCOUNT_ERR) {
 		regs->verdict.code = NF_DROP;
 		return;
 	}
-	count++;
+
-out:
+	count = priv->list.count;
 
 	if ((count > priv->limit) ^ priv->invert) {
 		regs->verdict.code = NFT_BREAK;

net/netrom/af_netrom.c

@@ -153,7 +153,7 @@ static struct sock *nr_find_listener(ax25_address *addr)
 	sk_for_each(s, &nr_list)
 		if (!ax25cmp(&nr_sk(s)->source_addr, addr) &&
 		    s->sk_state == TCP_LISTEN) {
-			bh_lock_sock(s);
+			sock_hold(s);
 			goto found;
 		}
 	s = NULL;
@@ -174,7 +174,7 @@ static struct sock *nr_find_socket(unsigned char index, unsigned char id)
 		struct nr_sock *nr = nr_sk(s);
 
 		if (nr->my_index == index && nr->my_id == id) {
-			bh_lock_sock(s);
+			sock_hold(s);
 			goto found;
 		}
 	}
@@ -198,7 +198,7 @@ static struct sock *nr_find_peer(unsigned char index, unsigned char id,
 
 		if (nr->your_index == index && nr->your_id == id &&
 		    !ax25cmp(&nr->dest_addr, dest)) {
-			bh_lock_sock(s);
+			sock_hold(s);
 			goto found;
 		}
 	}
@@ -224,7 +224,7 @@ static unsigned short nr_find_next_circuit(void)
 		if (i != 0 && j != 0) {
 			if ((sk=nr_find_socket(i, j)) == NULL)
 				break;
-			bh_unlock_sock(sk);
+			sock_put(sk);
 		}
 
 		id++;
@@ -920,6 +920,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	if (sk != NULL) {
+		bh_lock_sock(sk);
 		skb_reset_transport_header(skb);
 
 		if (frametype == NR_CONNACK && skb->len == 22)
@@ -929,6 +930,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
 
 		ret = nr_process_rx_frame(sk, skb);
 		bh_unlock_sock(sk);
+		sock_put(sk);
 		return ret;
 	}
 
@@ -960,10 +962,12 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
 	    (make = nr_make_new(sk)) == NULL) {
 		nr_transmit_refusal(skb, 0);
 		if (sk)
-			bh_unlock_sock(sk);
+			sock_put(sk);
 		return 0;
 	}
 
+	bh_lock_sock(sk);
+
 	window = skb->data[20];
 
 	skb->sk             = make;
@@ -1016,6 +1020,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
 		sk->sk_data_ready(sk);
 
 	bh_unlock_sock(sk);
+	sock_put(sk);
 
 	nr_insert_socket(make);
 

net/rds/tcp.c

@@ -623,7 +623,7 @@ static void __net_exit rds_tcp_exit_net(struct net *net)
 	if (rtn->rds_tcp_sysctl)
 		unregister_net_sysctl_table(rtn->rds_tcp_sysctl);
 
-	if (net != &init_net && rtn->ctl_table)
+	if (net != &init_net)
 		kfree(rtn->ctl_table);
 }
 

net/sunrpc/svcsock.c

@@ -542,7 +542,7 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp)
 		/* Don't enable netstamp, sunrpc doesn't
 		   need that much accuracy */
 	}
-	svsk->sk_sk->sk_stamp = skb->tstamp;
+	sock_write_timestamp(svsk->sk_sk, skb->tstamp);
 	set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); /* there may be more data... */
 
 	len  = skb->len;

net/tipc/bearer.c

@@ -319,7 +319,6 @@ static int tipc_enable_bearer(struct net *net, const char *name,
 	res = tipc_disc_create(net, b, &b->bcast_addr, &skb);
 	if (res) {
 		bearer_disable(net, b);
-		kfree(b);
 		errstr = "failed to create discoverer";
 		goto rejected;
 	}

net/tipc/netlink_compat.c

@@ -904,6 +904,8 @@ static int tipc_nl_compat_publ_dump(struct tipc_nl_compat_msg *msg, u32 sock)
 
 	hdr = genlmsg_put(args, 0, 0, &tipc_genl_family, NLM_F_MULTI,
 			  TIPC_NL_PUBL_GET);
+	if (!hdr)
+		return -EMSGSIZE;
 
 	nest = nla_nest_start(args, TIPC_NLA_SOCK);
 	if (!nest) {

tools/testing/selftests/bpf/test_maps.c

@@ -510,7 +510,7 @@ static void test_devmap(int task, void *data)
 	fd = bpf_create_map(BPF_MAP_TYPE_DEVMAP, sizeof(key), sizeof(value),
 			    2, 0);
 	if (fd < 0) {
-		printf("Failed to create arraymap '%s'!\n", strerror(errno));
+		printf("Failed to create devmap '%s'!\n", strerror(errno));
 		exit(1);
 	}