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

Pull networking fixes from David Miller:

 1) Fix crash on bpf_prog_load() errors, from Daniel Borkmann.

 2) Fix ATM VCC memory accounting, from David Woodhouse.

 3) fib6_info objects need RCU freeing, from Eric Dumazet.

 4) Fix SO_BINDTODEVICE handling for TCP sockets, from David Ahern.

 5) Fix clobbered error code in enic_open() failure path, from
    Govindarajulu Varadarajan.

 6) Propagate dev_get_valid_name() error returns properly, from Li
    RongQing.

 7) Fix suspend/resume in davinci_emac driver, from Bartosz Golaszewski.

 8) Various act_ife fixes (recursive locking, IDR leaks, etc.) from
    Davide Caratti.

 9) Fix buggy checksum handling in sungem driver, from Eric Dumazet.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (40 commits)
  ip: limit use of gso_size to udp
  stmmac: fix DMA channel hang in half-duplex mode
  net: stmmac: socfpga: add additional ocp reset line for Stratix10
  net: sungem: fix rx checksum support
  bpfilter: ignore binary files
  bpfilter: fix build error
  net/usb/drivers: Remove useless hrtimer_active check
  net/sched: act_ife: preserve the action control in case of error
  net/sched: act_ife: fix recursive lock and idr leak
  net: ethernet: fix suspend/resume in davinci_emac
  net: propagate dev_get_valid_name return code
  enic: do not overwrite error code
  net/tcp: Fix socket lookups with SO_BINDTODEVICE
  ptp: replace getnstimeofday64() with ktime_get_real_ts64()
  net/ipv6: respect rcu grace period before freeing fib6_info
  net: net_failover: fix typo in net_failover_slave_register()
  ipvlan: use ETH_MAX_MTU as max mtu
  net: hamradio: use eth_broadcast_addr
  enic: initialize enic->rfs_h.lock in enic_probe
  MAINTAINERS: Add Sam as the maintainer for NCSI
  ...

MAINTAINERS

@@ -9751,6 +9751,11 @@ L:	linux-scsi@vger.kernel.org
 S:	Maintained
 F:	drivers/scsi/NCR_D700.*
 
+NCSI LIBRARY:
+M:	Samuel Mendoza-Jonas <sam@mendozajonas.com>
+S:	Maintained
+F:	net/ncsi/
+
 NCT6775 HARDWARE MONITOR DRIVER
 M:	Guenter Roeck <linux@roeck-us.net>
 L:	linux-hwmon@vger.kernel.org

drivers/bluetooth/hci_nokia.c

@@ -29,7 +29,7 @@
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/types.h>
-#include <linux/unaligned/le_struct.h>
+#include <asm/unaligned.h>
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
 

drivers/net/ethernet/cisco/enic/enic_clsf.c

@@ -79,7 +79,6 @@ void enic_rfs_flw_tbl_init(struct enic *enic)
 	enic->rfs_h.max = enic->config.num_arfs;
 	enic->rfs_h.free = enic->rfs_h.max;
 	enic->rfs_h.toclean = 0;
-	enic_rfs_timer_start(enic);
 }
 
 void enic_rfs_flw_tbl_free(struct enic *enic)
@@ -88,7 +87,6 @@ void enic_rfs_flw_tbl_free(struct enic *enic)
 
 	enic_rfs_timer_stop(enic);
 	spin_lock_bh(&enic->rfs_h.lock);
-	enic->rfs_h.free = 0;
 	for (i = 0; i < (1 << ENIC_RFS_FLW_BITSHIFT); i++) {
 		struct hlist_head *hhead;
 		struct hlist_node *tmp;
@@ -99,6 +97,7 @@ void enic_rfs_flw_tbl_free(struct enic *enic)
 			enic_delfltr(enic, n->fltr_id);
 			hlist_del(&n->node);
 			kfree(n);
+			enic->rfs_h.free++;
 		}
 	}
 	spin_unlock_bh(&enic->rfs_h.lock);

drivers/net/ethernet/cisco/enic/enic_main.c

@@ -1920,7 +1920,7 @@ static int enic_open(struct net_device *netdev)
 {
 	struct enic *enic = netdev_priv(netdev);
 	unsigned int i;
-	int err;
+	int err, ret;
 
 	err = enic_request_intr(enic);
 	if (err) {
@@ -1971,15 +1971,14 @@ static int enic_open(struct net_device *netdev)
 		vnic_intr_unmask(&enic->intr[i]);
 
 	enic_notify_timer_start(enic);
-	enic_rfs_flw_tbl_init(enic);
+	enic_rfs_timer_start(enic);
 
 	return 0;
 
 err_out_free_rq:
 	for (i = 0; i < enic->rq_count; i++) {
-		err = vnic_rq_disable(&enic->rq[i]);
+		ret = vnic_rq_disable(&enic->rq[i]);
-		if (err)
+		if (!ret)
-			return err;
 			vnic_rq_clean(&enic->rq[i], enic_free_rq_buf);
 	}
 	enic_dev_notify_unset(enic);
@@ -2904,6 +2903,7 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	timer_setup(&enic->notify_timer, enic_notify_timer, 0);
 
+	enic_rfs_flw_tbl_init(enic);
 	enic_set_rx_coal_setting(enic);
 	INIT_WORK(&enic->reset, enic_reset);
 	INIT_WORK(&enic->tx_hang_reset, enic_tx_hang_reset);

drivers/net/ethernet/faraday/ftgmac100.c

@@ -1735,7 +1735,7 @@ static void ftgmac100_ncsi_handler(struct ncsi_dev *nd)
 	if (unlikely(nd->state != ncsi_dev_state_functional))
 		return;
 
-	netdev_info(nd->dev, "NCSI interface %s\n",
+	netdev_dbg(nd->dev, "NCSI interface %s\n",
 		   nd->link_up ? "up" : "down");
 }
 

drivers/net/ethernet/intel/i40e/i40e_txrx.c

@@ -2103,9 +2103,8 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring,
 	unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
 #else
 	unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
-				SKB_DATA_ALIGN(I40E_SKB_PAD +
+				SKB_DATA_ALIGN(xdp->data_end -
-					       (xdp->data_end -
+					       xdp->data_hard_start);
-						xdp->data_hard_start));
 #endif
 	struct sk_buff *skb;
 
@@ -2124,7 +2123,7 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring,
 		return NULL;
 
 	/* update pointers within the skb to store the data */
-	skb_reserve(skb, I40E_SKB_PAD + (xdp->data - xdp->data_hard_start));
+	skb_reserve(skb, xdp->data - xdp->data_hard_start);
 	__skb_put(skb, xdp->data_end - xdp->data);
 	if (metasize)
 		skb_metadata_set(skb, metasize);

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

@@ -255,9 +255,8 @@ qed_dcbx_get_app_protocol_type(struct qed_hwfn *p_hwfn,
 		*type = DCBX_PROTOCOL_ROCE_V2;
 	} else {
 		*type = DCBX_MAX_PROTOCOL_TYPE;
-		DP_ERR(p_hwfn,
+		DP_ERR(p_hwfn, "No action required, App TLV entry = 0x%x\n",
-		       "No action required, App TLV id = 0x%x app_prio_bitmap = 0x%x\n",
+		       app_prio_bitmap);
-		       id, app_prio_bitmap);
 		return false;
 	}
 
@@ -1479,8 +1478,8 @@ static u8 qed_dcbnl_getcap(struct qed_dev *cdev, int capid, u8 *cap)
 		*cap = 0x80;
 		break;
 	case DCB_CAP_ATTR_DCBX:
-		*cap = (DCB_CAP_DCBX_LLD_MANAGED | DCB_CAP_DCBX_VER_CEE |
+		*cap = (DCB_CAP_DCBX_VER_CEE | DCB_CAP_DCBX_VER_IEEE |
-			DCB_CAP_DCBX_VER_IEEE | DCB_CAP_DCBX_STATIC);
+			DCB_CAP_DCBX_STATIC);
 		break;
 	default:
 		*cap = false;
@@ -1548,8 +1547,6 @@ static u8 qed_dcbnl_getdcbx(struct qed_dev *cdev)
 	if (!dcbx_info)
 		return 0;
 
-	if (dcbx_info->operational.enabled)
-		mode |= DCB_CAP_DCBX_LLD_MANAGED;
 	if (dcbx_info->operational.ieee)
 		mode |= DCB_CAP_DCBX_VER_IEEE;
 	if (dcbx_info->operational.cee)

drivers/net/ethernet/qlogic/qed/qed_ll2.c

@@ -201,8 +201,9 @@ void qed_ll2b_complete_rx_packet(void *cxt, struct qed_ll2_comp_rx_data *data)
 
 	skb = build_skb(buffer->data, 0);
 	if (!skb) {
-		rc = -ENOMEM;
+		DP_INFO(cdev, "Failed to build SKB\n");
-		goto out_post;
+		kfree(buffer->data);
+		goto out_post1;
 	}
 
 	data->u.placement_offset += NET_SKB_PAD;
@@ -224,8 +225,14 @@ void qed_ll2b_complete_rx_packet(void *cxt, struct qed_ll2_comp_rx_data *data)
 		cdev->ll2->cbs->rx_cb(cdev->ll2->cb_cookie, skb,
 				      data->opaque_data_0,
 				      data->opaque_data_1);
+	} else {
+		DP_VERBOSE(p_hwfn, (NETIF_MSG_RX_STATUS | NETIF_MSG_PKTDATA |
+				    QED_MSG_LL2 | QED_MSG_STORAGE),
+			   "Dropping the packet\n");
+		kfree(buffer->data);
 	}
 
+out_post1:
 	/* Update Buffer information and update FW producer */
 	buffer->data = new_data;
 	buffer->phys_addr = new_phys_addr;

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

@@ -567,8 +567,16 @@ static irqreturn_t qed_single_int(int irq, void *dev_instance)
 		/* Fastpath interrupts */
 		for (j = 0; j < 64; j++) {
 			if ((0x2ULL << j) & status) {
-				hwfn->simd_proto_handler[j].func(
+				struct qed_simd_fp_handler *p_handler =
-					hwfn->simd_proto_handler[j].token);
+					&hwfn->simd_proto_handler[j];
+
+				if (p_handler->func)
+					p_handler->func(p_handler->token);
+				else
+					DP_NOTICE(hwfn,
+						  "Not calling fastpath handler as it is NULL [handler #%d, status 0x%llx]\n",
+						  j, status);
+
 				status &= ~(0x2ULL << j);
 				rc = IRQ_HANDLED;
 			}

drivers/net/ethernet/stmicro/stmmac/Kconfig

@@ -111,7 +111,7 @@ config DWMAC_ROCKCHIP
 config DWMAC_SOCFPGA
 	tristate "SOCFPGA dwmac support"
 	default ARCH_SOCFPGA
-	depends on OF && (ARCH_SOCFPGA || COMPILE_TEST)
+	depends on OF && (ARCH_SOCFPGA || ARCH_STRATIX10 || COMPILE_TEST)
 	select MFD_SYSCON
 	help
 	  Support for ethernet controller on Altera SOCFPGA

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

@@ -55,6 +55,7 @@ struct socfpga_dwmac {
 	struct	device *dev;
 	struct regmap *sys_mgr_base_addr;
 	struct reset_control *stmmac_rst;
+	struct reset_control *stmmac_ocp_rst;
 	void __iomem *splitter_base;
 	bool f2h_ptp_ref_clk;
 	struct tse_pcs pcs;
@@ -262,7 +263,7 @@ static int socfpga_dwmac_set_phy_mode(struct socfpga_dwmac *dwmac)
 		val = SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_GMII_MII;
 
 	/* Assert reset to the enet controller before changing the phy mode */
-	if (dwmac->stmmac_rst)
+	reset_control_assert(dwmac->stmmac_ocp_rst);
 	reset_control_assert(dwmac->stmmac_rst);
 
 	regmap_read(sys_mgr_base_addr, reg_offset, &ctrl);
@@ -288,7 +289,7 @@ static int socfpga_dwmac_set_phy_mode(struct socfpga_dwmac *dwmac)
 	/* Deassert reset for the phy configuration to be sampled by
 	 * the enet controller, and operation to start in requested mode
 	 */
-	if (dwmac->stmmac_rst)
+	reset_control_deassert(dwmac->stmmac_ocp_rst);
 	reset_control_deassert(dwmac->stmmac_rst);
 	if (phymode == PHY_INTERFACE_MODE_SGMII) {
 		if (tse_pcs_init(dwmac->pcs.tse_pcs_base, &dwmac->pcs) != 0) {
@@ -324,6 +325,15 @@ static int socfpga_dwmac_probe(struct platform_device *pdev)
 		goto err_remove_config_dt;
 	}
 
+	dwmac->stmmac_ocp_rst = devm_reset_control_get_optional(dev, "stmmaceth-ocp");
+	if (IS_ERR(dwmac->stmmac_ocp_rst)) {
+		ret = PTR_ERR(dwmac->stmmac_ocp_rst);
+		dev_err(dev, "error getting reset control of ocp %d\n", ret);
+		goto err_remove_config_dt;
+	}
+
+	reset_control_deassert(dwmac->stmmac_ocp_rst);
+
 	ret = socfpga_dwmac_parse_data(dwmac, dev);
 	if (ret) {
 		dev_err(dev, "Unable to parse OF data\n");

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

@@ -928,6 +928,7 @@ static void stmmac_check_pcs_mode(struct stmmac_priv *priv)
 static int stmmac_init_phy(struct net_device *dev)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 tx_cnt = priv->plat->tx_queues_to_use;
 	struct phy_device *phydev;
 	char phy_id_fmt[MII_BUS_ID_SIZE + 3];
 	char bus_id[MII_BUS_ID_SIZE];
@@ -968,6 +969,15 @@ static int stmmac_init_phy(struct net_device *dev)
 		phydev->advertising &= ~(SUPPORTED_1000baseT_Half |
 					 SUPPORTED_1000baseT_Full);
 
+	/*
+	 * Half-duplex mode not supported with multiqueue
+	 * half-duplex can only works with single queue
+	 */
+	if (tx_cnt > 1)
+		phydev->supported &= ~(SUPPORTED_1000baseT_Half |
+				       SUPPORTED_100baseT_Half |
+				       SUPPORTED_10baseT_Half);
+
 	/*
 	 * Broken HW is sometimes missing the pull-up resistor on the
 	 * MDIO line, which results in reads to non-existent devices returning

drivers/net/ethernet/sun/sungem.c

@@ -60,8 +60,7 @@
 #include <linux/sungem_phy.h>
 #include "sungem.h"
 
-/* Stripping FCS is causing problems, disabled for now */
+#define STRIP_FCS
-#undef STRIP_FCS
 
 #define DEFAULT_MSG	(NETIF_MSG_DRV		| \
 			 NETIF_MSG_PROBE	| \
@@ -435,7 +434,7 @@ static int gem_rxmac_reset(struct gem *gp)
 	writel(desc_dma & 0xffffffff, gp->regs + RXDMA_DBLOW);
 	writel(RX_RING_SIZE - 4, gp->regs + RXDMA_KICK);
 	val = (RXDMA_CFG_BASE | (RX_OFFSET << 10) |
-	       ((14 / 2) << 13) | RXDMA_CFG_FTHRESH_128);
+	       (ETH_HLEN << 13) | RXDMA_CFG_FTHRESH_128);
 	writel(val, gp->regs + RXDMA_CFG);
 	if (readl(gp->regs + GREG_BIFCFG) & GREG_BIFCFG_M66EN)
 		writel(((5 & RXDMA_BLANK_IPKTS) |
@@ -760,7 +759,6 @@ static int gem_rx(struct gem *gp, int work_to_do)
 	struct net_device *dev = gp->dev;
 	int entry, drops, work_done = 0;
 	u32 done;
-	__sum16 csum;
 
 	if (netif_msg_rx_status(gp))
 		printk(KERN_DEBUG "%s: rx interrupt, done: %d, rx_new: %d\n",
@@ -855,9 +853,13 @@ static int gem_rx(struct gem *gp, int work_to_do)
 			skb = copy_skb;
 		}
 
+		if (likely(dev->features & NETIF_F_RXCSUM)) {
+			__sum16 csum;
+
 			csum = (__force __sum16)htons((status & RXDCTRL_TCPCSUM) ^ 0xffff);
 			skb->csum = csum_unfold(csum);
 			skb->ip_summed = CHECKSUM_COMPLETE;
+		}
 		skb->protocol = eth_type_trans(skb, gp->dev);
 
 		napi_gro_receive(&gp->napi, skb);
@@ -1761,7 +1763,7 @@ static void gem_init_dma(struct gem *gp)
 	writel(0, gp->regs + TXDMA_KICK);
 
 	val = (RXDMA_CFG_BASE | (RX_OFFSET << 10) |
-	       ((14 / 2) << 13) | RXDMA_CFG_FTHRESH_128);
+	       (ETH_HLEN << 13) | RXDMA_CFG_FTHRESH_128);
 	writel(val, gp->regs + RXDMA_CFG);
 
 	writel(desc_dma >> 32, gp->regs + RXDMA_DBHI);
@@ -2985,8 +2987,8 @@ static int gem_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	pci_set_drvdata(pdev, dev);
 
 	/* We can do scatter/gather and HW checksum */
-	dev->hw_features = NETIF_F_SG | NETIF_F_HW_CSUM;
+	dev->hw_features = NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM;
-	dev->features |= dev->hw_features | NETIF_F_RXCSUM;
+	dev->features = dev->hw_features;
 	if (pci_using_dac)
 		dev->features |= NETIF_F_HIGHDMA;
 

drivers/net/ethernet/ti/davinci_emac.c

@@ -1385,6 +1385,11 @@ static int emac_devioctl(struct net_device *ndev, struct ifreq *ifrq, int cmd)
 		return -EOPNOTSUPP;
 }
 
+static int match_first_device(struct device *dev, void *data)
+{
+	return !strncmp(dev_name(dev), "davinci_mdio", 12);
+}
+
 /**
  * emac_dev_open - EMAC device open
  * @ndev: The DaVinci EMAC network adapter
@@ -1484,8 +1489,14 @@ static int emac_dev_open(struct net_device *ndev)
 
 	/* use the first phy on the bus if pdata did not give us a phy id */
 	if (!phydev && !priv->phy_id) {
-		phy = bus_find_device_by_name(&mdio_bus_type, NULL,
+		/* NOTE: we can't use bus_find_device_by_name() here because
-					      "davinci_mdio");
+		 * the device name is not guaranteed to be 'davinci_mdio'. On
+		 * some systems it can be 'davinci_mdio.0' so we need to use
+		 * strncmp() against the first part of the string to correctly
+		 * match it.
+		 */
+		phy = bus_find_device(&mdio_bus_type, NULL, NULL,
+				      match_first_device);
 		if (phy) {
 			priv->phy_id = dev_name(phy);
 			if (!priv->phy_id || !*priv->phy_id)

drivers/net/hamradio/bpqether.c

@@ -89,10 +89,6 @@
 static const char banner[] __initconst = KERN_INFO \
 	"AX.25: bpqether driver version 004\n";
 
-static char bcast_addr[6]={0xFF,0xFF,0xFF,0xFF,0xFF,0xFF};
-
-static char bpq_eth_addr[6];
-
 static int bpq_rcv(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *);
 static int bpq_device_event(struct notifier_block *, unsigned long, void *);
 
@@ -501,8 +497,8 @@ static int bpq_new_device(struct net_device *edev)
 	bpq->ethdev = edev;
 	bpq->axdev = ndev;
 
-	memcpy(bpq->dest_addr, bcast_addr, sizeof(bpq_eth_addr));
+	eth_broadcast_addr(bpq->dest_addr);
-	memcpy(bpq->acpt_addr, bcast_addr, sizeof(bpq_eth_addr));
+	eth_broadcast_addr(bpq->acpt_addr);
 
 	err = register_netdevice(ndev);
 	if (err)

drivers/net/ipvlan/ipvlan_main.c

@@ -693,6 +693,7 @@ void ipvlan_link_setup(struct net_device *dev)
 {
 	ether_setup(dev);
 
+	dev->max_mtu = ETH_MAX_MTU;
 	dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING);
 	dev->priv_flags |= IFF_UNICAST_FLT | IFF_NO_QUEUE;
 	dev->netdev_ops = &ipvlan_netdev_ops;

drivers/net/net_failover.c

@@ -527,7 +527,7 @@ static int net_failover_slave_register(struct net_device *slave_dev,
 
 	netif_addr_lock_bh(failover_dev);
 	dev_uc_sync_multiple(slave_dev, failover_dev);
-	dev_uc_sync_multiple(slave_dev, failover_dev);
+	dev_mc_sync_multiple(slave_dev, failover_dev);
 	netif_addr_unlock_bh(failover_dev);
 
 	err = vlan_vids_add_by_dev(slave_dev, failover_dev);

drivers/net/usb/cdc_ncm.c

@@ -967,7 +967,6 @@ void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf)
 
 	atomic_set(&ctx->stop, 1);
 
-	if (hrtimer_active(&ctx->tx_timer))
 	hrtimer_cancel(&ctx->tx_timer);
 
 	tasklet_kill(&ctx->bh);

drivers/ptp/ptp_chardev.c

@@ -221,7 +221,7 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg)
 		}
 		pct = &sysoff->ts[0];
 		for (i = 0; i < sysoff->n_samples; i++) {
-			getnstimeofday64(&ts);
+			ktime_get_real_ts64(&ts);
 			pct->sec = ts.tv_sec;
 			pct->nsec = ts.tv_nsec;
 			pct++;
@@ -230,7 +230,7 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg)
 			pct->nsec = ts.tv_nsec;
 			pct++;
 		}
-		getnstimeofday64(&ts);
+		ktime_get_real_ts64(&ts);
 		pct->sec = ts.tv_sec;
 		pct->nsec = ts.tv_nsec;
 		if (copy_to_user((void __user *)arg, sysoff, sizeof(*sysoff)))

drivers/ptp/ptp_qoriq.c

@@ -374,7 +374,7 @@ static int qoriq_ptp_probe(struct platform_device *dev)
 		pr_err("ioremap ptp registers failed\n");
 		goto no_ioremap;
 	}
-	getnstimeofday64(&now);
+	ktime_get_real_ts64(&now);
 	ptp_qoriq_settime(&qoriq_ptp->caps, &now);
 
 	tmr_ctrl =

include/linux/atmdev.h

@@ -214,6 +214,7 @@ struct atmphy_ops {
 struct atm_skb_data {
 	struct atm_vcc	*vcc;		/* ATM VCC */
 	unsigned long	atm_options;	/* ATM layer options */
+	unsigned int	acct_truesize;  /* truesize accounted to vcc */
 };
 
 #define VCC_HTABLE_SIZE 32
@@ -241,6 +242,20 @@ void vcc_insert_socket(struct sock *sk);
 
 void atm_dev_release_vccs(struct atm_dev *dev);
 
+static inline void atm_account_tx(struct atm_vcc *vcc, struct sk_buff *skb)
+{
+	/*
+	 * Because ATM skbs may not belong to a sock (and we don't
+	 * necessarily want to), skb->truesize may be adjusted,
+	 * escaping the hack in pskb_expand_head() which avoids
+	 * doing so for some cases. So stash the value of truesize
+	 * at the time we accounted it, and atm_pop_raw() can use
+	 * that value later, in case it changes.
+	 */
+	refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc);
+	ATM_SKB(skb)->acct_truesize = skb->truesize;
+	ATM_SKB(skb)->atm_options = vcc->atm_options;
+}
 
 static inline void atm_force_charge(struct atm_vcc *vcc,int truesize)
 {

include/linux/bpf.h

@@ -488,12 +488,15 @@ void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth);
 
 /* Map specifics */
 struct xdp_buff;
+struct sk_buff;
 
 struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key);
 void __dev_map_insert_ctx(struct bpf_map *map, u32 index);
 void __dev_map_flush(struct bpf_map *map);
 int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
 		    struct net_device *dev_rx);
+int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
+			     struct bpf_prog *xdp_prog);
 
 struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key);
 void __cpu_map_insert_ctx(struct bpf_map *map, u32 index);
@@ -586,6 +589,15 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
 	return 0;
 }
 
+struct sk_buff;
+
+static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst,
+					   struct sk_buff *skb,
+					   struct bpf_prog *xdp_prog)
+{
+	return 0;
+}
+
 static inline
 struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
 {

include/linux/filter.h

@@ -19,6 +19,7 @@
 #include <linux/cryptohash.h>
 #include <linux/set_memory.h>
 #include <linux/kallsyms.h>
+#include <linux/if_vlan.h>
 
 #include <net/sch_generic.h>
 
@@ -469,7 +470,8 @@ struct sock_fprog_kern {
 };
 
 struct bpf_binary_header {
-	unsigned int pages;
+	u16 pages;
+	u16 locked:1;
 	u8 image[];
 };
 
@@ -671,15 +673,18 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default)
 
 #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0]))
 
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
 static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
 {
+#ifdef CONFIG_ARCH_HAS_SET_MEMORY
 	fp->locked = 1;
-	WARN_ON_ONCE(set_memory_ro((unsigned long)fp, fp->pages));
+	if (set_memory_ro((unsigned long)fp, fp->pages))
+		fp->locked = 0;
+#endif
 }
 
 static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
 {
+#ifdef CONFIG_ARCH_HAS_SET_MEMORY
 	if (fp->locked) {
 		WARN_ON_ONCE(set_memory_rw((unsigned long)fp, fp->pages));
 		/* In case set_memory_rw() fails, we want to be the first
@@ -687,34 +692,30 @@ static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
 		 */
 		fp->locked = 0;
 	}
+#endif
 }
 
 static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
 {
-	WARN_ON_ONCE(set_memory_ro((unsigned long)hdr, hdr->pages));
+#ifdef CONFIG_ARCH_HAS_SET_MEMORY
+	hdr->locked = 1;
+	if (set_memory_ro((unsigned long)hdr, hdr->pages))
+		hdr->locked = 0;
+#endif
 }
 
 static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr)
 {
+#ifdef CONFIG_ARCH_HAS_SET_MEMORY
+	if (hdr->locked) {
 		WARN_ON_ONCE(set_memory_rw((unsigned long)hdr, hdr->pages));
+		/* In case set_memory_rw() fails, we want to be the first
+		 * to crash here instead of some random place later on.
+		 */
+		hdr->locked = 0;
+	}
+#endif
 }
-#else
-static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
-{
-}
-
-static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
-{
-}
-
-static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
-{
-}
-
-static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr)
-{
-}
-#endif /* CONFIG_ARCH_HAS_SET_MEMORY */
 
 static inline struct bpf_binary_header *
 bpf_jit_binary_hdr(const struct bpf_prog *fp)
@@ -725,6 +726,22 @@ bpf_jit_binary_hdr(const struct bpf_prog *fp)
 	return (void *)addr;
 }
 
+#ifdef CONFIG_ARCH_HAS_SET_MEMORY
+static inline int bpf_prog_check_pages_ro_single(const struct bpf_prog *fp)
+{
+	if (!fp->locked)
+		return -ENOLCK;
+	if (fp->jited) {
+		const struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp);
+
+		if (!hdr->locked)
+			return -ENOLCK;
+	}
+
+	return 0;
+}
+#endif
+
 int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap);
 static inline int sk_filter(struct sock *sk, struct sk_buff *skb)
 {
@@ -786,6 +803,21 @@ static inline bool bpf_dump_raw_ok(void)
 struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 				       const struct bpf_insn *patch, u32 len);
 
+static inline int __xdp_generic_ok_fwd_dev(struct sk_buff *skb,
+					   struct net_device *fwd)
+{
+	unsigned int len;
+
+	if (unlikely(!(fwd->flags & IFF_UP)))
+		return -ENETDOWN;
+
+	len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN;
+	if (skb->len > len)
+		return -EMSGSIZE;
+
+	return 0;
+}
+
 /* The pair of xdp_do_redirect and xdp_do_flush_map MUST be called in the
  * same cpu context. Further for best results no more than a single map
  * for the do_redirect/do_flush pair should be used. This limitation is
@@ -961,6 +993,9 @@ static inline void bpf_prog_kallsyms_del(struct bpf_prog *fp)
 }
 #endif /* CONFIG_BPF_JIT */
 
+void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp);
+void bpf_prog_kallsyms_del_all(struct bpf_prog *fp);
+
 #define BPF_ANC		BIT(15)
 
 static inline bool bpf_needs_clear_a(const struct sock_filter *first)

include/net/ip6_fib.h

@@ -170,6 +170,7 @@ struct fib6_info {
 					unused:3;
 
 	struct fib6_nh			fib6_nh;
+	struct rcu_head			rcu;
 };
 
 struct rt6_info {
@@ -273,7 +274,7 @@ static inline void ip6_rt_put(struct rt6_info *rt)
 }
 
 struct fib6_info *fib6_info_alloc(gfp_t gfp_flags);
-void fib6_info_destroy(struct fib6_info *f6i);
+void fib6_info_destroy_rcu(struct rcu_head *head);
 
 static inline void fib6_info_hold(struct fib6_info *f6i)
 {
@@ -283,7 +284,7 @@ static inline void fib6_info_hold(struct fib6_info *f6i)
 static inline void fib6_info_release(struct fib6_info *f6i)
 {
 	if (f6i && atomic_dec_and_test(&f6i->fib6_ref))
-		fib6_info_destroy(f6i);
+		call_rcu(&f6i->rcu, fib6_info_destroy_rcu);
 }
 
 enum fib6_walk_state {

kernel/bpf/core.c

@@ -350,6 +350,20 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 	return prog_adj;
 }
 
+void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp)
+{
+	int i;
+
+	for (i = 0; i < fp->aux->func_cnt; i++)
+		bpf_prog_kallsyms_del(fp->aux->func[i]);
+}
+
+void bpf_prog_kallsyms_del_all(struct bpf_prog *fp)
+{
+	bpf_prog_kallsyms_del_subprogs(fp);
+	bpf_prog_kallsyms_del(fp);
+}
+
 #ifdef CONFIG_BPF_JIT
 /* All BPF JIT sysctl knobs here. */
 int bpf_jit_enable   __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON);
@@ -584,6 +598,8 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
 	bpf_fill_ill_insns(hdr, size);
 
 	hdr->pages = size / PAGE_SIZE;
+	hdr->locked = 0;
+
 	hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)),
 		     PAGE_SIZE - sizeof(*hdr));
 	start = (get_random_int() % hole) & ~(alignment - 1);
@@ -1434,6 +1450,33 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
 	return 0;
 }
 
+static int bpf_prog_check_pages_ro_locked(const struct bpf_prog *fp)
+{
+#ifdef CONFIG_ARCH_HAS_SET_MEMORY
+	int i, err;
+
+	for (i = 0; i < fp->aux->func_cnt; i++) {
+		err = bpf_prog_check_pages_ro_single(fp->aux->func[i]);
+		if (err)
+			return err;
+	}
+
+	return bpf_prog_check_pages_ro_single(fp);
+#endif
+	return 0;
+}
+
+static void bpf_prog_select_func(struct bpf_prog *fp)
+{
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
+	u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1);
+
+	fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1];
+#else
+	fp->bpf_func = __bpf_prog_ret0_warn;
+#endif
+}
+
 /**
  *	bpf_prog_select_runtime - select exec runtime for BPF program
  *	@fp: bpf_prog populated with internal BPF program
@@ -1444,13 +1487,13 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
  */
 struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 {
-#ifndef CONFIG_BPF_JIT_ALWAYS_ON
+	/* In case of BPF to BPF calls, verifier did all the prep
-	u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1);
+	 * work with regards to JITing, etc.
+	 */
+	if (fp->bpf_func)
+		goto finalize;
 
-	fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1];
+	bpf_prog_select_func(fp);
-#else
-	fp->bpf_func = __bpf_prog_ret0_warn;
-#endif
 
 	/* eBPF JITs can rewrite the program in case constant
 	 * blinding is active. However, in case of error during
@@ -1471,6 +1514,8 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 		if (*err)
 			return fp;
 	}
+
+finalize:
 	bpf_prog_lock_ro(fp);
 
 	/* The tail call compatibility check can only be done at
@@ -1479,7 +1524,17 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 	 * all eBPF JITs might immediately support all features.
 	 */
 	*err = bpf_check_tail_call(fp);
+	if (*err)
+		return fp;
 
+	/* Checkpoint: at this point onwards any cBPF -> eBPF or
+	 * native eBPF program is read-only. If we failed to change
+	 * the page attributes (e.g. allocation failure from
+	 * splitting large pages), then reject the whole program
+	 * in order to guarantee not ending up with any W+X pages
+	 * from BPF side in kernel.
+	 */
+	*err = bpf_prog_check_pages_ro_locked(fp);
 	return fp;
 }
 EXPORT_SYMBOL_GPL(bpf_prog_select_runtime);

kernel/bpf/devmap.c

@@ -345,6 +345,20 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
 	return bq_enqueue(dst, xdpf, dev_rx);
 }
 
+int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
+			     struct bpf_prog *xdp_prog)
+{
+	int err;
+
+	err = __xdp_generic_ok_fwd_dev(skb, dst->dev);
+	if (unlikely(err))
+		return err;
+	skb->dev = dst->dev;
+	generic_xdp_tx(skb, xdp_prog);
+
+	return 0;
+}
+
 static void *dev_map_lookup_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key);

kernel/bpf/syscall.c

@@ -1034,14 +1034,9 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu)
 static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
 {
 	if (atomic_dec_and_test(&prog->aux->refcnt)) {
-		int i;
-
 		/* bpf_prog_free_id() must be called first */
 		bpf_prog_free_id(prog, do_idr_lock);
-
+		bpf_prog_kallsyms_del_all(prog);
-		for (i = 0; i < prog->aux->func_cnt; i++)
-			bpf_prog_kallsyms_del(prog->aux->func[i]);
-		bpf_prog_kallsyms_del(prog);
 
 		call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
 	}
@@ -1358,8 +1353,6 @@ static int bpf_prog_load(union bpf_attr *attr)
 	if (err < 0)
 		goto free_used_maps;
 
-	/* eBPF program is ready to be JITed */
-	if (!prog->bpf_func)
 	prog = bpf_prog_select_runtime(prog, &err);
 	if (err < 0)
 		goto free_used_maps;
@@ -1384,6 +1377,7 @@ static int bpf_prog_load(union bpf_attr *attr)
 	return err;
 
 free_used_maps:
+	bpf_prog_kallsyms_del_subprogs(prog);
 	free_used_maps(prog->aux);
 free_prog:
 	bpf_prog_uncharge_memlock(prog);

net/atm/br2684.c

@@ -252,8 +252,7 @@ static int br2684_xmit_vcc(struct sk_buff *skb, struct net_device *dev,
 
 	ATM_SKB(skb)->vcc = atmvcc = brvcc->atmvcc;
 	pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, atmvcc, atmvcc->dev);
-	refcount_add(skb->truesize, &sk_atm(atmvcc)->sk_wmem_alloc);
+	atm_account_tx(atmvcc, skb);
-	ATM_SKB(skb)->atm_options = atmvcc->atm_options;
 	dev->stats.tx_packets++;
 	dev->stats.tx_bytes += skb->len;
 

net/atm/clip.c

@@ -381,8 +381,7 @@ static netdev_tx_t clip_start_xmit(struct sk_buff *skb,
 		memcpy(here, llc_oui, sizeof(llc_oui));
 		((__be16 *) here)[3] = skb->protocol;
 	}
-	refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc);
+	atm_account_tx(vcc, skb);
-	ATM_SKB(skb)->atm_options = vcc->atm_options;
 	entry->vccs->last_use = jiffies;
 	pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, vcc, vcc->dev);
 	old = xchg(&entry->vccs->xoff, 1);	/* assume XOFF ... */

net/atm/common.c

@@ -630,10 +630,9 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size)
 		goto out;
 	}
 	pr_debug("%d += %d\n", sk_wmem_alloc_get(sk), skb->truesize);
-	refcount_add(skb->truesize, &sk->sk_wmem_alloc);
+	atm_account_tx(vcc, skb);
 
 	skb->dev = NULL; /* for paths shared with net_device interfaces */
-	ATM_SKB(skb)->atm_options = vcc->atm_options;
 	if (!copy_from_iter_full(skb_put(skb, size), size, &m->msg_iter)) {
 		kfree_skb(skb);
 		error = -EFAULT;

net/atm/lec.c

@@ -182,9 +182,8 @@ lec_send(struct atm_vcc *vcc, struct sk_buff *skb)
 	struct net_device *dev = skb->dev;
 
 	ATM_SKB(skb)->vcc = vcc;
-	ATM_SKB(skb)->atm_options = vcc->atm_options;
+	atm_account_tx(vcc, skb);
 
-	refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc);
 	if (vcc->send(vcc, skb) < 0) {
 		dev->stats.tx_dropped++;
 		return;

net/atm/mpc.c

@@ -555,8 +555,7 @@ static int send_via_shortcut(struct sk_buff *skb, struct mpoa_client *mpc)
 					sizeof(struct llc_snap_hdr));
 	}
 
-	refcount_add(skb->truesize, &sk_atm(entry->shortcut)->sk_wmem_alloc);
+	atm_account_tx(entry->shortcut, skb);
-	ATM_SKB(skb)->atm_options = entry->shortcut->atm_options;
 	entry->shortcut->send(entry->shortcut, skb);
 	entry->packets_fwded++;
 	mpc->in_ops->put(entry);

net/atm/pppoatm.c

@@ -350,8 +350,7 @@ static int pppoatm_send(struct ppp_channel *chan, struct sk_buff *skb)
 		return 1;
 	}
 
-	refcount_add(skb->truesize, &sk_atm(ATM_SKB(skb)->vcc)->sk_wmem_alloc);
+	atm_account_tx(vcc, skb);
-	ATM_SKB(skb)->atm_options = ATM_SKB(skb)->vcc->atm_options;
 	pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n",
 		 skb, ATM_SKB(skb)->vcc, ATM_SKB(skb)->vcc->dev);
 	ret = ATM_SKB(skb)->vcc->send(ATM_SKB(skb)->vcc, skb)

net/atm/raw.c

@@ -35,8 +35,8 @@ static void atm_pop_raw(struct atm_vcc *vcc, struct sk_buff *skb)
 	struct sock *sk = sk_atm(vcc);
 
 	pr_debug("(%d) %d -= %d\n",
-		 vcc->vci, sk_wmem_alloc_get(sk), skb->truesize);
+		 vcc->vci, sk_wmem_alloc_get(sk), ATM_SKB(skb)->acct_truesize);
-	WARN_ON(refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc));
+	WARN_ON(refcount_sub_and_test(ATM_SKB(skb)->acct_truesize, &sk->sk_wmem_alloc));
 	dev_kfree_skb_any(skb);
 	sk->sk_write_space(sk);
 }

net/bpfilter/.gitignore

@@ -0,0 +1 @@
+bpfilter_umh

net/bpfilter/Makefile

@@ -21,8 +21,10 @@ endif
 # which bpfilter_kern.c passes further into umh blob loader at run-time
 quiet_cmd_copy_umh = GEN $@
       cmd_copy_umh = echo ':' > $(obj)/.bpfilter_umh.o.cmd; \
-      $(OBJCOPY) -I binary -O `$(OBJDUMP) -f $<|grep format|cut -d' ' -f8` \
+      $(OBJCOPY) -I binary \
-      -B `$(OBJDUMP) -f $<|grep architecture|cut -d, -f1|cut -d' ' -f2` \
+          `LC_ALL=C objdump -f net/bpfilter/bpfilter_umh \
+          |awk -F' |,' '/file format/{print "-O",$$NF} \
+          /^architecture:/{print "-B",$$2}'` \
       --rename-section .data=.init.rodata $< $@
 
 $(obj)/bpfilter_umh.o: $(obj)/bpfilter_umh

net/core/dev.c

@@ -8643,7 +8643,8 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
 		/* We get here if we can't use the current device name */
 		if (!pat)
 			goto out;
-		if (dev_get_valid_name(net, dev, pat) < 0)
+		err = dev_get_valid_name(net, dev, pat);
+		if (err < 0)
 			goto out;
 	}
 
@@ -8655,7 +8656,6 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
 	dev_close(dev);
 
 	/* And unlink it from device chain */
-	err = -ENODEV;
 	unlist_netdevice(dev);
 
 	synchronize_net();

net/core/filter.c

@@ -3214,20 +3214,6 @@ err:
 }
 EXPORT_SYMBOL_GPL(xdp_do_redirect);
 
-static int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, struct net_device *fwd)
-{
-	unsigned int len;
-
-	if (unlikely(!(fwd->flags & IFF_UP)))
-		return -ENETDOWN;
-
-	len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN;
-	if (skb->len > len)
-		return -EMSGSIZE;
-
-	return 0;
-}
-
 static int xdp_do_generic_redirect_map(struct net_device *dev,
 				       struct sk_buff *skb,
 				       struct xdp_buff *xdp,
@@ -3256,10 +3242,11 @@ static int xdp_do_generic_redirect_map(struct net_device *dev,
 	}
 
 	if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
-		if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd))))
+		struct bpf_dtab_netdev *dst = fwd;
+
+		err = dev_map_generic_redirect(dst, skb, xdp_prog);
+		if (unlikely(err))
 			goto err;
-		skb->dev = fwd;
-		generic_xdp_tx(skb, xdp_prog);
 	} else if (map->map_type == BPF_MAP_TYPE_XSKMAP) {
 		struct xdp_sock *xs = fwd;
 

net/ipv4/inet_hashtables.c

@@ -243,9 +243,9 @@ static inline int compute_score(struct sock *sk, struct net *net,
 			bool dev_match = (sk->sk_bound_dev_if == dif ||
 					  sk->sk_bound_dev_if == sdif);
 
-			if (exact_dif && !dev_match)
+			if (!dev_match)
 				return -1;
-			if (sk->sk_bound_dev_if && dev_match)
+			if (sk->sk_bound_dev_if)
 				score += 4;
 		}
 		if (sk->sk_incoming_cpu == raw_smp_processor_id())

net/ipv4/ip_output.c

@@ -1145,7 +1145,8 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 	cork->fragsize = ip_sk_use_pmtu(sk) ?
 			 dst_mtu(&rt->dst) : rt->dst.dev->mtu;
 
-	cork->gso_size = sk->sk_type == SOCK_DGRAM ? ipc->gso_size : 0;
+	cork->gso_size = sk->sk_type == SOCK_DGRAM &&
+			 sk->sk_protocol == IPPROTO_UDP ? ipc->gso_size : 0;
 	cork->dst = &rt->dst;
 	cork->length = 0;
 	cork->ttl = ipc->ttl;

net/ipv6/inet6_hashtables.c

@@ -113,9 +113,9 @@ static inline int compute_score(struct sock *sk, struct net *net,
 			bool dev_match = (sk->sk_bound_dev_if == dif ||
 					  sk->sk_bound_dev_if == sdif);
 
-			if (exact_dif && !dev_match)
+			if (!dev_match)
 				return -1;
-			if (sk->sk_bound_dev_if && dev_match)
+			if (sk->sk_bound_dev_if)
 				score++;
 		}
 		if (sk->sk_incoming_cpu == raw_smp_processor_id())

net/ipv6/ip6_fib.c

@@ -167,8 +167,9 @@ struct fib6_info *fib6_info_alloc(gfp_t gfp_flags)
 	return f6i;
 }
 
-void fib6_info_destroy(struct fib6_info *f6i)
+void fib6_info_destroy_rcu(struct rcu_head *head)
 {
+	struct fib6_info *f6i = container_of(head, struct fib6_info, rcu);
 	struct rt6_exception_bucket *bucket;
 	struct dst_metrics *m;
 
@@ -206,7 +207,7 @@ void fib6_info_destroy(struct fib6_info *f6i)
 
 	kfree(f6i);
 }
-EXPORT_SYMBOL_GPL(fib6_info_destroy);
+EXPORT_SYMBOL_GPL(fib6_info_destroy_rcu);
 
 static struct fib6_node *node_alloc(struct net *net)
 {

net/ipv6/ip6_output.c

@@ -1219,7 +1219,8 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
 	if (mtu < IPV6_MIN_MTU)
 		return -EINVAL;
 	cork->base.fragsize = mtu;
-	cork->base.gso_size = sk->sk_type == SOCK_DGRAM ? ipc6->gso_size : 0;
+	cork->base.gso_size = sk->sk_type == SOCK_DGRAM &&
+			      sk->sk_protocol == IPPROTO_UDP ? ipc6->gso_size : 0;
 
 	if (dst_allfrag(xfrm_dst_path(&rt->dst)))
 		cork->base.flags |= IPCORK_ALLFRAG;

net/ncsi/ncsi-aen.c

@@ -73,7 +73,7 @@ static int ncsi_aen_handler_lsc(struct ncsi_dev_priv *ndp,
 	ncm->data[2] = data;
 	ncm->data[4] = ntohl(lsc->oem_status);
 
-	netdev_info(ndp->ndev.dev, "NCSI: LSC AEN - channel %u state %s\n",
+	netdev_dbg(ndp->ndev.dev, "NCSI: LSC AEN - channel %u state %s\n",
 		   nc->id, data & 0x1 ? "up" : "down");
 
 	chained = !list_empty(&nc->link);
@@ -148,7 +148,7 @@ static int ncsi_aen_handler_hncdsc(struct ncsi_dev_priv *ndp,
 	hncdsc = (struct ncsi_aen_hncdsc_pkt *)h;
 	ncm->data[3] = ntohl(hncdsc->status);
 	spin_unlock_irqrestore(&nc->lock, flags);
-	netdev_printk(KERN_DEBUG, ndp->ndev.dev,
+	netdev_dbg(ndp->ndev.dev,
 		   "NCSI: host driver %srunning on channel %u\n",
 		   ncm->data[3] & 0x1 ? "" : "not ", nc->id);
 

net/ncsi/ncsi-manage.c

@@ -788,8 +788,8 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp)
 		}
 		break;
 	case ncsi_dev_state_config_done:
-		netdev_printk(KERN_DEBUG, ndp->ndev.dev,
+		netdev_dbg(ndp->ndev.dev, "NCSI: channel %u config done\n",
-			      "NCSI: channel %u config done\n", nc->id);
+			   nc->id);
 		spin_lock_irqsave(&nc->lock, flags);
 		if (nc->reconfigure_needed) {
 			/* This channel's configuration has been updated
@@ -804,8 +804,7 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp)
 			list_add_tail_rcu(&nc->link, &ndp->channel_queue);
 			spin_unlock_irqrestore(&ndp->lock, flags);
 
-			netdev_printk(KERN_DEBUG, dev,
+			netdev_dbg(dev, "Dirty NCSI channel state reset\n");
-				      "Dirty NCSI channel state reset\n");
 			ncsi_process_next_channel(ndp);
 			break;
 		}
@@ -816,7 +815,7 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp)
 		} else {
 			hot_nc = NULL;
 			nc->state = NCSI_CHANNEL_INACTIVE;
-			netdev_warn(ndp->ndev.dev,
+			netdev_dbg(ndp->ndev.dev,
 				   "NCSI: channel %u link down after config\n",
 				   nc->id);
 		}
@@ -908,7 +907,7 @@ static int ncsi_choose_active_channel(struct ncsi_dev_priv *ndp)
 	}
 
 	ncm = &found->modes[NCSI_MODE_LINK];
-	netdev_printk(KERN_DEBUG, ndp->ndev.dev,
+	netdev_dbg(ndp->ndev.dev,
 		   "NCSI: Channel %u added to queue (link %s)\n",
 		   found->id, ncm->data[2] & 0x1 ? "up" : "down");
 
@@ -1199,13 +1198,13 @@ int ncsi_process_next_channel(struct ncsi_dev_priv *ndp)
 	switch (old_state) {
 	case NCSI_CHANNEL_INACTIVE:
 		ndp->ndev.state = ncsi_dev_state_config;
-		netdev_info(ndp->ndev.dev, "NCSI: configuring channel %u\n",
+		netdev_dbg(ndp->ndev.dev, "NCSI: configuring channel %u\n",
 	                   nc->id);
 		ncsi_configure_channel(ndp);
 		break;
 	case NCSI_CHANNEL_ACTIVE:
 		ndp->ndev.state = ncsi_dev_state_suspend;
-		netdev_info(ndp->ndev.dev, "NCSI: suspending channel %u\n",
+		netdev_dbg(ndp->ndev.dev, "NCSI: suspending channel %u\n",
 			   nc->id);
 		ncsi_suspend_channel(ndp);
 		break;
@@ -1226,8 +1225,6 @@ out:
 		return ncsi_choose_active_channel(ndp);
 	}
 
-	netdev_printk(KERN_DEBUG, ndp->ndev.dev,
-		      "NCSI: No more channels to process\n");
 	ncsi_report_link(ndp, false);
 	return -ENODEV;
 }
@@ -1318,7 +1315,7 @@ static int ncsi_kick_channels(struct ncsi_dev_priv *ndp)
 				if ((ndp->ndev.state & 0xff00) ==
 						ncsi_dev_state_config ||
 						!list_empty(&nc->link)) {
-					netdev_printk(KERN_DEBUG, nd->dev,
+					netdev_dbg(nd->dev,
 						   "NCSI: channel %p marked dirty\n",
 						   nc);
 					nc->reconfigure_needed = true;
@@ -1338,8 +1335,7 @@ static int ncsi_kick_channels(struct ncsi_dev_priv *ndp)
 			list_add_tail_rcu(&nc->link, &ndp->channel_queue);
 			spin_unlock_irqrestore(&ndp->lock, flags);
 
-			netdev_printk(KERN_DEBUG, nd->dev,
+			netdev_dbg(nd->dev, "NCSI: kicked channel %p\n", nc);
-				      "NCSI: kicked channel %p\n", nc);
 			n++;
 		}
 	}
@@ -1370,8 +1366,8 @@ int ncsi_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid)
 	list_for_each_entry_rcu(vlan, &ndp->vlan_vids, list) {
 		n_vids++;
 		if (vlan->vid == vid) {
-			netdev_printk(KERN_DEBUG, dev,
+			netdev_dbg(dev, "NCSI: vid %u already registered\n",
-				      "NCSI: vid %u already registered\n", vid);
+				   vid);
 			return 0;
 		}
 	}
@@ -1390,7 +1386,7 @@ int ncsi_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid)
 	vlan->vid = vid;
 	list_add_rcu(&vlan->list, &ndp->vlan_vids);
 
-	netdev_printk(KERN_DEBUG, dev, "NCSI: Added new vid %u\n", vid);
+	netdev_dbg(dev, "NCSI: Added new vid %u\n", vid);
 
 	found = ncsi_kick_channels(ndp) != 0;
 
@@ -1419,8 +1415,7 @@ int ncsi_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid)
 	/* Remove the VLAN id from our internal list */
 	list_for_each_entry_safe(vlan, tmp, &ndp->vlan_vids, list)
 		if (vlan->vid == vid) {
-			netdev_printk(KERN_DEBUG, dev,
+			netdev_dbg(dev, "NCSI: vid %u found, removing\n", vid);
-				      "NCSI: vid %u found, removing\n", vid);
 			list_del_rcu(&vlan->list);
 			found = true;
 			kfree(vlan);
@@ -1547,7 +1542,7 @@ void ncsi_stop_dev(struct ncsi_dev *nd)
 		}
 	}
 
-	netdev_printk(KERN_DEBUG, ndp->ndev.dev, "NCSI: Stopping device\n");
+	netdev_dbg(ndp->ndev.dev, "NCSI: Stopping device\n");
 	ncsi_report_link(ndp, true);
 }
 EXPORT_SYMBOL_GPL(ncsi_stop_dev);

net/sched/act_ife.c

@@ -415,6 +415,7 @@ static void tcf_ife_cleanup(struct tc_action *a)
 	spin_unlock_bh(&ife->tcf_lock);
 
 	p = rcu_dereference_protected(ife->params, 1);
+	if (p)
 		kfree_rcu(p, rcu);
 }
 
@@ -516,8 +517,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 			saddr = nla_data(tb[TCA_IFE_SMAC]);
 	}
 
-	ife->tcf_action = parm->action;
-
 	if (parm->flags & IFE_ENCODE) {
 		if (daddr)
 			ether_addr_copy(p->eth_dst, daddr);
@@ -543,10 +542,8 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 				       NULL, NULL);
 		if (err) {
 metadata_parse_err:
-			if (exists)
-				tcf_idr_release(*a, bind);
 			if (ret == ACT_P_CREATED)
-				_tcf_ife_cleanup(*a);
+				tcf_idr_release(*a, bind);
 
 			if (exists)
 				spin_unlock_bh(&ife->tcf_lock);
@@ -567,7 +564,7 @@ metadata_parse_err:
 		err = use_all_metadata(ife);
 		if (err) {
 			if (ret == ACT_P_CREATED)
-				_tcf_ife_cleanup(*a);
+				tcf_idr_release(*a, bind);
 
 			if (exists)
 				spin_unlock_bh(&ife->tcf_lock);
@@ -576,6 +573,7 @@ metadata_parse_err:
 		}
 	}
 
+	ife->tcf_action = parm->action;
 	if (exists)
 		spin_unlock_bh(&ife->tcf_lock);
 

net/sched/sch_blackhole.c

@@ -21,7 +21,7 @@ static int blackhole_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			     struct sk_buff **to_free)
 {
 	qdisc_drop(skb, sch, to_free);
-	return NET_XMIT_SUCCESS;
+	return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
 }
 
 static struct sk_buff *blackhole_dequeue(struct Qdisc *sch)

net/xdp/xsk.c

@@ -118,6 +118,9 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 	u64 addr;
 	int err;
 
+	if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)
+		return -EINVAL;
+
 	if (!xskq_peek_addr(xs->umem->fq, &addr) ||
 	    len > xs->umem->chunk_size_nohr) {
 		xs->rx_dropped++;

tools/bpf/bpftool/perf.c

@@ -29,9 +29,10 @@ static bool has_perf_query_support(void)
 	if (perf_query_supported)
 		goto out;
 
-	fd = open(bin_name, O_RDONLY);
+	fd = open("/", O_RDONLY);
 	if (fd < 0) {
-		p_err("perf_query_support: %s", strerror(errno));
+		p_err("perf_query_support: cannot open directory \"/\" (%s)",
+		      strerror(errno));
 		goto out;
 	}
 

tools/bpf/bpftool/prog.c

@@ -90,7 +90,9 @@ static void print_boot_time(__u64 nsecs, char *buf, unsigned int size)
 	}
 
 	wallclock_secs = (real_time_ts.tv_sec - boot_time_ts.tv_sec) +
-		nsecs / 1000000000;
+		(real_time_ts.tv_nsec - boot_time_ts.tv_nsec + nsecs) /
+		1000000000;
+
 
 	if (!localtime_r(&wallclock_secs, &load_tm)) {
 		snprintf(buf, size, "%llu", nsecs / 1000000000);

tools/testing/selftests/bpf/config

@@ -7,3 +7,13 @@ CONFIG_CGROUP_BPF=y
 CONFIG_NETDEVSIM=m
 CONFIG_NET_CLS_ACT=y
 CONFIG_NET_SCH_INGRESS=y
+CONFIG_NET_IPIP=y
+CONFIG_IPV6=y
+CONFIG_NET_IPGRE_DEMUX=y
+CONFIG_NET_IPGRE=y
+CONFIG_IPV6_GRE=y
+CONFIG_CRYPTO_USER_API_HASH=m
+CONFIG_CRYPTO_HMAC=m
+CONFIG_CRYPTO_SHA256=m
+CONFIG_VXLAN=y
+CONFIG_GENEVE=y

tools/testing/selftests/bpf/test_offload.py

@@ -163,6 +163,10 @@ def bpftool(args, JSON=True, ns="", fail=True):
 
 def bpftool_prog_list(expected=None, ns=""):
     _, progs = bpftool("prog show", JSON=True, ns=ns, fail=True)
+    # Remove the base progs
+    for p in base_progs:
+        if p in progs:
+            progs.remove(p)
     if expected is not None:
         if len(progs) != expected:
             fail(True, "%d BPF programs loaded, expected %d" %
@@ -171,6 +175,10 @@ def bpftool_prog_list(expected=None, ns=""):
 
 def bpftool_map_list(expected=None, ns=""):
     _, maps = bpftool("map show", JSON=True, ns=ns, fail=True)
+    # Remove the base maps
+    for m in base_maps:
+        if m in maps:
+            maps.remove(m)
     if expected is not None:
         if len(maps) != expected:
             fail(True, "%d BPF maps loaded, expected %d" %
@@ -585,8 +593,8 @@ skip(os.getuid() != 0, "test must be run as root")
 # Check tools
 ret, progs = bpftool("prog", fail=False)
 skip(ret != 0, "bpftool not installed")
-# Check no BPF programs are loaded
+base_progs = progs
-skip(len(progs) != 0, "BPF programs already loaded on the system")
+_, base_maps = bpftool("map")
 
 # Check netdevsim
 ret, out = cmd("modprobe netdevsim", fail=False)

tools/testing/selftests/bpf/test_tunnel.sh

@@ -608,20 +608,18 @@ setup_xfrm_tunnel()
 test_xfrm_tunnel()
 {
 	config_device
-        #tcpdump -nei veth1 ip &
+	> /sys/kernel/debug/tracing/trace
-	output=$(mktemp)
-	cat /sys/kernel/debug/tracing/trace_pipe | tee $output &
 	setup_xfrm_tunnel
 	tc qdisc add dev veth1 clsact
 	tc filter add dev veth1 proto ip ingress bpf da obj test_tunnel_kern.o \
 		sec xfrm_get_state
 	ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
 	sleep 1
-	grep "reqid 1" $output
+	grep "reqid 1" /sys/kernel/debug/tracing/trace
 	check_err $?
-	grep "spi 0x1" $output
+	grep "spi 0x1" /sys/kernel/debug/tracing/trace
 	check_err $?
-	grep "remote ip 0xac100164" $output
+	grep "remote ip 0xac100164" /sys/kernel/debug/tracing/trace
 	check_err $?
 	cleanup
 
@@ -657,6 +655,10 @@ cleanup()
 	ip link del ip6geneve11 2> /dev/null
 	ip link del erspan11 2> /dev/null
 	ip link del ip6erspan11 2> /dev/null
+	ip xfrm policy delete dir out src 10.1.1.200/32 dst 10.1.1.100/32 2> /dev/null
+	ip xfrm policy delete dir in src 10.1.1.100/32 dst 10.1.1.200/32 2> /dev/null
+	ip xfrm state delete src 172.16.1.100 dst 172.16.1.200 proto esp spi 0x1 2> /dev/null
+	ip xfrm state delete src 172.16.1.200 dst 172.16.1.100 proto esp spi 0x2 2> /dev/null
 }
 
 cleanup_exit()
@@ -668,7 +670,7 @@ cleanup_exit()
 
 check()
 {
-	ip link help $1 2>&1 | grep -q "^Usage:"
+	ip link help 2>&1 | grep -q "\s$1\s"
 	if [ $? -ne 0 ];then
 		echo "SKIP $1: iproute2 not support"
 	cleanup