whiterose

linux unikernel
Log | Files | Refs | README | LICENSE | git clone https://git.ne02ptzero.me/git/whiterose

commit 5211da9ca526a5adddee1ccd078e6e33a583ab36
parent 3918c21eacb06e3d9d43f718354cbce6703f4812
Author: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date:   Tue, 18 Sep 2018 09:31:53 +0200

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

Dave writes:
  "Various fixes, all over the place:

   1) OOB data generation fix in bluetooth, from Matias Karhumaa.

   2) BPF BTF boundary calculation fix, from Martin KaFai Lau.

   3) Don't bug on excessive frags, to be compatible in situations mixing
      older and newer kernels on each end.  From Juergen Gross.

   4) Scheduling in RCU fix in hv_netvsc, from Stephen Hemminger.

   5) Zero keying information in TLS layer before freeing copies
      of them, from Sabrina Dubroca.

   6) Fix NULL deref in act_sample, from Davide Caratti.

   7) Orphan SKB before GRO in veth to prevent crashes with XDP,
      from Toshiaki Makita.

   8) Fix use after free in ip6_xmit, from Eric Dumazet.

   9) Fix VF mac address regression in bnxt_en, from Micahel Chan.

   10) Fix MSG_PEEK behavior in TLS layer, from Daniel Borkmann.

   11) Programming adjustments to r8169 which fix not being to enter deep
       sleep states on some machines, from Kai-Heng Feng and Hans de
       Goede.

   12) Fix DST_NOCOUNT flag handling for ipv6 routes, from Peter
       Oskolkov."

* gitolite.kernel.org:/pub/scm/linux/kernel/git/davem/net: (45 commits)
  net/ipv6: do not copy dst flags on rt init
  qmi_wwan: set DTR for modems in forced USB2 mode
  clk: x86: Stop marking clocks as CLK_IS_CRITICAL
  r8169: Get and enable optional ether_clk clock
  clk: x86: add "ether_clk" alias for Bay Trail / Cherry Trail
  r8169: enable ASPM on RTL8106E
  r8169: Align ASPM/CLKREQ setting function with vendor driver
  Revert "kcm: remove any offset before parsing messages"
  kcm: remove any offset before parsing messages
  net: ethernet: Fix a unused function warning.
  net: dsa: mv88e6xxx: Fix ATU Miss Violation
  tls: fix currently broken MSG_PEEK behavior
  hv_netvsc: pair VF based on serial number
  PCI: hv: support reporting serial number as slot information
  bnxt_en: Fix VF mac address regression.
  ipv6: fix possible use-after-free in ip6_xmit()
  net: hp100: fix always-true check for link up state
  ARM: dts: at91: add new compatibility string for macb on sama5d3
  net: macb: disable scatter-gather for macb on sama5d3
  net: mvpp2: let phylink manage the carrier state
  ...

Diffstat:
MDocumentation/devicetree/bindings/net/macb.txt | 1+
March/arm/boot/dts/sama5d3_emac.dtsi | 2+-
Mdrivers/bluetooth/hci_ldisc.c | 2++
Mdrivers/clk/x86/clk-pmc-atom.c | 18+++++++++++-------
Mdrivers/net/appletalk/ipddp.c | 8++++++--
Mdrivers/net/dsa/mv88e6xxx/global1.h | 2+-
Mdrivers/net/dsa/mv88e6xxx/global1_atu.c | 2+-
Mdrivers/net/ethernet/broadcom/bnxt/bnxt.c | 9+++++++--
Mdrivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c | 9+++++----
Mdrivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h | 2+-
Mdrivers/net/ethernet/cadence/macb_main.c | 8++++++++
Mdrivers/net/ethernet/hp/hp100.c | 2+-
Mdrivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 21++++++---------------
Mdrivers/net/ethernet/microchip/lan743x_main.c | 6+++---
Mdrivers/net/ethernet/realtek/r8169.c | 40+++++++++++++++++++++++++++++++++++++++-
Mdrivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 5++---
Mdrivers/net/ethernet/ti/Kconfig | 1+
Mdrivers/net/hyperv/netvsc.c | 3+++
Mdrivers/net/hyperv/netvsc_drv.c | 67++++++++++++++++++++++++++++++++++++-------------------------------
Mdrivers/net/ppp/pppoe.c | 3+++
Mdrivers/net/usb/qmi_wwan.c | 14+++++++-------
Mdrivers/net/veth.c | 4++--
Mdrivers/net/xen-netfront.c | 8+++++++-
Mdrivers/pci/controller/pci-hyperv.c | 37+++++++++++++++++++++++++++++++++++++
Minclude/net/tls.h | 19+++++++++----------
Mkernel/bpf/btf.c | 2+-
Mkernel/bpf/verifier.c | 2+-
Mnet/bluetooth/smp.c | 16+++++++++++++---
Mnet/core/filter.c | 3++-
Mnet/core/neighbour.c | 13++++++++-----
Mnet/core/rtnetlink.c | 2+-
Mnet/ipv4/af_inet.c | 1+
Mnet/ipv4/udp.c | 49++++++++++++++++++++++++++-----------------------
Mnet/ipv6/ip6_offload.c | 1+
Mnet/ipv6/ip6_output.c | 6++----
Mnet/ipv6/route.c | 44++++++++++++++++++++++++++++++--------------
Mnet/ipv6/udp.c | 65+++++++++++++++++++++++++++++++++++++----------------------------
Mnet/sched/act_sample.c | 2+-
Mnet/sched/cls_api.c | 2++
Mnet/socket.c | 22++++++++++++++--------
Mnet/tls/tls_device.c | 6+++---
Mnet/tls/tls_device_fallback.c | 2+-
Mnet/tls/tls_main.c | 22++++++++++++++++------
Mnet/tls/tls_sw.c | 21+++++++++++++--------
Mtools/testing/selftests/net/tls.c | 49+++++++++++++++++++++++++++++++++++++++++++++++++
45 files changed, 422 insertions(+), 201 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/macb.txt b/Documentation/devicetree/bindings/net/macb.txt @@ -10,6 +10,7 @@ Required properties: Use "cdns,pc302-gem" for Picochip picoXcell pc302 and later devices based on the Cadence GEM, or the generic form: "cdns,gem". Use "atmel,sama5d2-gem" for the GEM IP (10/100) available on Atmel sama5d2 SoCs. + Use "atmel,sama5d3-macb" for the 10/100Mbit IP available on Atmel sama5d3 SoCs. Use "atmel,sama5d3-gem" for the Gigabit IP available on Atmel sama5d3 SoCs. Use "atmel,sama5d4-gem" for the GEM IP (10/100) available on Atmel sama5d4 SoCs. Use "cdns,zynq-gem" Xilinx Zynq-7xxx SoC. diff --git a/arch/arm/boot/dts/sama5d3_emac.dtsi b/arch/arm/boot/dts/sama5d3_emac.dtsi @@ -41,7 +41,7 @@ }; macb1: ethernet@f802c000 { - compatible = "cdns,at91sam9260-macb", "cdns,macb"; + compatible = "atmel,sama5d3-macb", "cdns,at91sam9260-macb", "cdns,macb"; reg = <0xf802c000 0x100>; interrupts = <35 IRQ_TYPE_LEVEL_HIGH 3>; pinctrl-names = "default"; diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c @@ -543,6 +543,8 @@ static void hci_uart_tty_close(struct tty_struct *tty) } clear_bit(HCI_UART_PROTO_SET, &hu->flags); + percpu_free_rwsem(&hu->proto_lock); + kfree(hu); } diff --git a/drivers/clk/x86/clk-pmc-atom.c b/drivers/clk/x86/clk-pmc-atom.c @@ -55,6 +55,7 @@ struct clk_plt_data { u8 nparents; struct clk_plt *clks[PMC_CLK_NUM]; struct clk_lookup *mclk_lookup; + struct clk_lookup *ether_clk_lookup; }; /* Return an index in parent table */ @@ -186,13 +187,6 @@ static struct clk_plt *plt_clk_register(struct platform_device *pdev, int id, pclk->reg = base + PMC_CLK_CTL_OFFSET + id * PMC_CLK_CTL_SIZE; spin_lock_init(&pclk->lock); - /* - * If the clock was already enabled by the firmware mark it as critical - * to avoid it being gated by the clock framework if no driver owns it. - */ - if (plt_clk_is_enabled(&pclk->hw)) - init.flags |= CLK_IS_CRITICAL; - ret = devm_clk_hw_register(&pdev->dev, &pclk->hw); if (ret) { pclk = ERR_PTR(ret); @@ -351,11 +345,20 @@ static int plt_clk_probe(struct platform_device *pdev) goto err_unreg_clk_plt; } + data->ether_clk_lookup = clkdev_hw_create(&data->clks[4]->hw, + "ether_clk", NULL); + if (!data->ether_clk_lookup) { + err = -ENOMEM; + goto err_drop_mclk; + } + plt_clk_free_parent_names_loop(parent_names, data->nparents); platform_set_drvdata(pdev, data); return 0; +err_drop_mclk: + clkdev_drop(data->mclk_lookup); err_unreg_clk_plt: plt_clk_unregister_loop(data, i); plt_clk_unregister_parents(data); @@ -369,6 +372,7 @@ static int plt_clk_remove(struct platform_device *pdev) data = platform_get_drvdata(pdev); + clkdev_drop(data->ether_clk_lookup); clkdev_drop(data->mclk_lookup); plt_clk_unregister_loop(data, PMC_CLK_NUM); plt_clk_unregister_parents(data); diff --git a/drivers/net/appletalk/ipddp.c b/drivers/net/appletalk/ipddp.c @@ -283,8 +283,12 @@ static int ipddp_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCFINDIPDDPRT: spin_lock_bh(&ipddp_route_lock); rp = __ipddp_find_route(&rcp); - if (rp) - memcpy(&rcp2, rp, sizeof(rcp2)); + if (rp) { + memset(&rcp2, 0, sizeof(rcp2)); + rcp2.ip = rp->ip; + rcp2.at = rp->at; + rcp2.flags = rp->flags; + } spin_unlock_bh(&ipddp_route_lock); if (rp) { diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h @@ -128,7 +128,7 @@ #define MV88E6XXX_G1_ATU_OP_GET_CLR_VIOLATION 0x7000 #define MV88E6XXX_G1_ATU_OP_AGE_OUT_VIOLATION BIT(7) #define MV88E6XXX_G1_ATU_OP_MEMBER_VIOLATION BIT(6) -#define MV88E6XXX_G1_ATU_OP_MISS_VIOLTATION BIT(5) +#define MV88E6XXX_G1_ATU_OP_MISS_VIOLATION BIT(5) #define MV88E6XXX_G1_ATU_OP_FULL_VIOLATION BIT(4) /* Offset 0x0C: ATU Data Register */ diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c @@ -349,7 +349,7 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id) chip->ports[entry.portvec].atu_member_violation++; } - if (val & MV88E6XXX_G1_ATU_OP_MEMBER_VIOLATION) { + if (val & MV88E6XXX_G1_ATU_OP_MISS_VIOLATION) { dev_err_ratelimited(chip->dev, "ATU miss violation for %pM portvec %x\n", entry.mac, entry.portvec); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -8027,7 +8027,7 @@ static int bnxt_change_mac_addr(struct net_device *dev, void *p) if (ether_addr_equal(addr->sa_data, dev->dev_addr)) return 0; - rc = bnxt_approve_mac(bp, addr->sa_data); + rc = bnxt_approve_mac(bp, addr->sa_data, true); if (rc) return rc; @@ -8827,14 +8827,19 @@ static int bnxt_init_mac_addr(struct bnxt *bp) } else { #ifdef CONFIG_BNXT_SRIOV struct bnxt_vf_info *vf = &bp->vf; + bool strict_approval = true; if (is_valid_ether_addr(vf->mac_addr)) { /* overwrite netdev dev_addr with admin VF MAC */ memcpy(bp->dev->dev_addr, vf->mac_addr, ETH_ALEN); + /* Older PF driver or firmware may not approve this + * correctly. + */ + strict_approval = false; } else { eth_hw_addr_random(bp->dev); } - rc = bnxt_approve_mac(bp, bp->dev->dev_addr); + rc = bnxt_approve_mac(bp, bp->dev->dev_addr, strict_approval); #endif } return rc; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -1104,7 +1104,7 @@ update_vf_mac_exit: mutex_unlock(&bp->hwrm_cmd_lock); } -int bnxt_approve_mac(struct bnxt *bp, u8 *mac) +int bnxt_approve_mac(struct bnxt *bp, u8 *mac, bool strict) { struct hwrm_func_vf_cfg_input req = {0}; int rc = 0; @@ -1122,12 +1122,13 @@ int bnxt_approve_mac(struct bnxt *bp, u8 *mac) memcpy(req.dflt_mac_addr, mac, ETH_ALEN); rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); mac_done: - if (rc) { + if (rc && strict) { rc = -EADDRNOTAVAIL; netdev_warn(bp->dev, "VF MAC address %pM not approved by the PF\n", mac); + return rc; } - return rc; + return 0; } #else @@ -1144,7 +1145,7 @@ void bnxt_update_vf_mac(struct bnxt *bp) { } -int bnxt_approve_mac(struct bnxt *bp, u8 *mac) +int bnxt_approve_mac(struct bnxt *bp, u8 *mac, bool strict) { return 0; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h @@ -39,5 +39,5 @@ int bnxt_sriov_configure(struct pci_dev *pdev, int num_vfs); void bnxt_sriov_disable(struct bnxt *); void bnxt_hwrm_exec_fwd_req(struct bnxt *); void bnxt_update_vf_mac(struct bnxt *); -int bnxt_approve_mac(struct bnxt *, u8 *); +int bnxt_approve_mac(struct bnxt *, u8 *, bool); #endif diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c @@ -3837,6 +3837,13 @@ static const struct macb_config at91sam9260_config = { .init = macb_init, }; +static const struct macb_config sama5d3macb_config = { + .caps = MACB_CAPS_SG_DISABLED + | MACB_CAPS_USRIO_HAS_CLKEN | MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII, + .clk_init = macb_clk_init, + .init = macb_init, +}; + static const struct macb_config pc302gem_config = { .caps = MACB_CAPS_SG_DISABLED | MACB_CAPS_GIGABIT_MODE_AVAILABLE, .dma_burst_length = 16, @@ -3904,6 +3911,7 @@ static const struct of_device_id macb_dt_ids[] = { { .compatible = "cdns,gem", .data = &pc302gem_config }, { .compatible = "atmel,sama5d2-gem", .data = &sama5d2_config }, { .compatible = "atmel,sama5d3-gem", .data = &sama5d3_config }, + { .compatible = "atmel,sama5d3-macb", .data = &sama5d3macb_config }, { .compatible = "atmel,sama5d4-gem", .data = &sama5d4_config }, { .compatible = "cdns,at91rm9200-emac", .data = &emac_config }, { .compatible = "cdns,emac", .data = &emac_config }, diff --git a/drivers/net/ethernet/hp/hp100.c b/drivers/net/ethernet/hp/hp100.c @@ -2634,7 +2634,7 @@ static int hp100_login_to_vg_hub(struct net_device *dev, u_short force_relogin) /* Wait for link to drop */ time = jiffies + (HZ / 10); do { - if (~(hp100_inb(VG_LAN_CFG_1) & HP100_LINK_UP_ST)) + if (!(hp100_inb(VG_LAN_CFG_1) & HP100_LINK_UP_ST)) break; if (!in_interrupt()) schedule_timeout_interruptible(1); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -58,6 +58,8 @@ static struct { */ static void mvpp2_mac_config(struct net_device *dev, unsigned int mode, const struct phylink_link_state *state); +static void mvpp2_mac_link_up(struct net_device *dev, unsigned int mode, + phy_interface_t interface, struct phy_device *phy); /* Queue modes */ #define MVPP2_QDIST_SINGLE_MODE 0 @@ -3142,6 +3144,7 @@ static void mvpp2_start_dev(struct mvpp2_port *port) mvpp22_mode_reconfigure(port); if (port->phylink) { + netif_carrier_off(port->dev); phylink_start(port->phylink); } else { /* Phylink isn't used as of now for ACPI, so the MAC has to be @@ -3150,9 +3153,10 @@ static void mvpp2_start_dev(struct mvpp2_port *port) */ struct phylink_link_state state = { .interface = port->phy_interface, - .link = 1, }; mvpp2_mac_config(port->dev, MLO_AN_INBAND, &state); + mvpp2_mac_link_up(port->dev, MLO_AN_INBAND, port->phy_interface, + NULL); } netif_tx_start_all_queues(port->dev); @@ -4495,10 +4499,6 @@ static void mvpp2_mac_config(struct net_device *dev, unsigned int mode, return; } - netif_tx_stop_all_queues(port->dev); - if (!port->has_phy) - netif_carrier_off(port->dev); - /* Make sure the port is disabled when reconfiguring the mode */ mvpp2_port_disable(port); @@ -4523,16 +4523,7 @@ static void mvpp2_mac_config(struct net_device *dev, unsigned int mode, if (port->priv->hw_version == MVPP21 && port->flags & MVPP2_F_LOOPBACK) mvpp2_port_loopback_set(port, state); - /* If the port already was up, make sure it's still in the same state */ - if (state->link || !port->has_phy) { - mvpp2_port_enable(port); - - mvpp2_egress_enable(port); - mvpp2_ingress_enable(port); - if (!port->has_phy) - netif_carrier_on(dev); - netif_tx_wake_all_queues(dev); - } + mvpp2_port_enable(port); } static void mvpp2_mac_link_up(struct net_device *dev, unsigned int mode, diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c @@ -2850,7 +2850,7 @@ static void lan743x_pcidev_shutdown(struct pci_dev *pdev) lan743x_hardware_cleanup(adapter); } -#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP static u16 lan743x_pm_wakeframe_crc16(const u8 *buf, int len) { return bitrev16(crc16(0xFFFF, buf, len)); @@ -3016,7 +3016,7 @@ static int lan743x_pm_resume(struct device *dev) static const struct dev_pm_ops lan743x_pm_ops = { SET_SYSTEM_SLEEP_PM_OPS(lan743x_pm_suspend, lan743x_pm_resume) }; -#endif /*CONFIG_PM */ +#endif /* CONFIG_PM_SLEEP */ static const struct pci_device_id lan743x_pcidev_tbl[] = { { PCI_DEVICE(PCI_VENDOR_ID_SMSC, PCI_DEVICE_ID_SMSC_LAN7430) }, @@ -3028,7 +3028,7 @@ static struct pci_driver lan743x_pcidev_driver = { .id_table = lan743x_pcidev_tbl, .probe = lan743x_pcidev_probe, .remove = lan743x_pcidev_remove, -#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP .driver.pm = &lan743x_pm_ops, #endif .shutdown = lan743x_pcidev_shutdown, diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c @@ -13,6 +13,7 @@ #include <linux/pci.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> +#include <linux/clk.h> #include <linux/delay.h> #include <linux/ethtool.h> #include <linux/phy.h> @@ -665,6 +666,7 @@ struct rtl8169_private { u16 event_slow; const struct rtl_coalesce_info *coalesce_info; + struct clk *clk; struct mdio_ops { void (*write)(struct rtl8169_private *, int, int); @@ -4775,12 +4777,14 @@ static void rtl_pcie_state_l2l3_enable(struct rtl8169_private *tp, bool enable) static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable) { if (enable) { - RTL_W8(tp, Config2, RTL_R8(tp, Config2) | ClkReqEn); RTL_W8(tp, Config5, RTL_R8(tp, Config5) | ASPM_en); + RTL_W8(tp, Config2, RTL_R8(tp, Config2) | ClkReqEn); } else { RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn); RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en); } + + udelay(10); } static void rtl_hw_start_8168bb(struct rtl8169_private *tp) @@ -5625,6 +5629,8 @@ static void rtl_hw_start_8402(struct rtl8169_private *tp) static void rtl_hw_start_8106(struct rtl8169_private *tp) { + rtl_hw_aspm_clkreq_enable(tp, false); + /* Force LAN exit from ASPM if Rx/Tx are not idle */ RTL_W32(tp, FuncEvent, RTL_R32(tp, FuncEvent) | 0x002800); @@ -5633,6 +5639,7 @@ static void rtl_hw_start_8106(struct rtl8169_private *tp) RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN); rtl_pcie_state_l2l3_enable(tp, false); + rtl_hw_aspm_clkreq_enable(tp, true); } static void rtl_hw_start_8101(struct rtl8169_private *tp) @@ -7257,6 +7264,11 @@ static int rtl_jumbo_max(struct rtl8169_private *tp) } } +static void rtl_disable_clk(void *data) +{ + clk_disable_unprepare(data); +} + static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) { const struct rtl_cfg_info *cfg = rtl_cfg_infos + ent->driver_data; @@ -7277,6 +7289,32 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) tp->msg_enable = netif_msg_init(debug.msg_enable, R8169_MSG_DEFAULT); tp->supports_gmii = cfg->has_gmii; + /* Get the *optional* external "ether_clk" used on some boards */ + tp->clk = devm_clk_get(&pdev->dev, "ether_clk"); + if (IS_ERR(tp->clk)) { + rc = PTR_ERR(tp->clk); + if (rc == -ENOENT) { + /* clk-core allows NULL (for suspend / resume) */ + tp->clk = NULL; + } else if (rc == -EPROBE_DEFER) { + return rc; + } else { + dev_err(&pdev->dev, "failed to get clk: %d\n", rc); + return rc; + } + } else { + rc = clk_prepare_enable(tp->clk); + if (rc) { + dev_err(&pdev->dev, "failed to enable clk: %d\n", rc); + return rc; + } + + rc = devm_add_action_or_reset(&pdev->dev, rtl_disable_clk, + tp->clk); + if (rc) + return rc; + } + /* enable device (incl. PCI PM wakeup and hotplug setup) */ rc = pcim_enable_device(pdev); if (rc < 0) { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -67,7 +67,7 @@ static int dwmac1000_validate_mcast_bins(int mcast_bins) * Description: * This function validates the number of Unicast address entries supported * by a particular Synopsys 10/100/1000 controller. The Synopsys controller - * supports 1, 32, 64, or 128 Unicast filter entries for it's Unicast filter + * supports 1..32, 64, or 128 Unicast filter entries for it's Unicast filter * logic. This function validates a valid, supported configuration is * selected, and defaults to 1 Unicast address if an unsupported * configuration is selected. @@ -77,8 +77,7 @@ static int dwmac1000_validate_ucast_entries(int ucast_entries) int x = ucast_entries; switch (x) { - case 1: - case 32: + case 1 ... 32: case 64: case 128: break; diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig @@ -41,6 +41,7 @@ config TI_DAVINCI_MDIO config TI_DAVINCI_CPDMA tristate "TI DaVinci CPDMA Support" depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || COMPILE_TEST + select GENERIC_ALLOCATOR ---help--- This driver supports TI's DaVinci CPDMA dma engine. diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c @@ -1203,6 +1203,9 @@ static void netvsc_send_vf(struct net_device *ndev, net_device_ctx->vf_alloc = nvmsg->msg.v4_msg.vf_assoc.allocated; net_device_ctx->vf_serial = nvmsg->msg.v4_msg.vf_assoc.serial; + netdev_info(ndev, "VF slot %u %s\n", + net_device_ctx->vf_serial, + net_device_ctx->vf_alloc ? "added" : "removed"); } static void netvsc_receive_inband(struct net_device *ndev, diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c @@ -1894,20 +1894,6 @@ out_unlock: rtnl_unlock(); } -static struct net_device *get_netvsc_bymac(const u8 *mac) -{ - struct net_device_context *ndev_ctx; - - list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) { - struct net_device *dev = hv_get_drvdata(ndev_ctx->device_ctx); - - if (ether_addr_equal(mac, dev->perm_addr)) - return dev; - } - - return NULL; -} - static struct net_device *get_netvsc_byref(struct net_device *vf_netdev) { struct net_device_context *net_device_ctx; @@ -2036,26 +2022,48 @@ static void netvsc_vf_setup(struct work_struct *w) rtnl_unlock(); } +/* Find netvsc by VMBus serial number. + * The PCI hyperv controller records the serial number as the slot. + */ +static struct net_device *get_netvsc_byslot(const struct net_device *vf_netdev) +{ + struct device *parent = vf_netdev->dev.parent; + struct net_device_context *ndev_ctx; + struct pci_dev *pdev; + + if (!parent || !dev_is_pci(parent)) + return NULL; /* not a PCI device */ + + pdev = to_pci_dev(parent); + if (!pdev->slot) { + netdev_notice(vf_netdev, "no PCI slot information\n"); + return NULL; + } + + list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) { + if (!ndev_ctx->vf_alloc) + continue; + + if (ndev_ctx->vf_serial == pdev->slot->number) + return hv_get_drvdata(ndev_ctx->device_ctx); + } + + netdev_notice(vf_netdev, + "no netdev found for slot %u\n", pdev->slot->number); + return NULL; +} + static int netvsc_register_vf(struct net_device *vf_netdev) { - struct net_device *ndev; struct net_device_context *net_device_ctx; - struct device *pdev = vf_netdev->dev.parent; struct netvsc_device *netvsc_dev; + struct net_device *ndev; int ret; if (vf_netdev->addr_len != ETH_ALEN) return NOTIFY_DONE; - if (!pdev || !dev_is_pci(pdev) || dev_is_pf(pdev)) - return NOTIFY_DONE; - - /* - * We will use the MAC address to locate the synthetic interface to - * associate with the VF interface. If we don't find a matching - * synthetic interface, move on. - */ - ndev = get_netvsc_bymac(vf_netdev->perm_addr); + ndev = get_netvsc_byslot(vf_netdev); if (!ndev) return NOTIFY_DONE; @@ -2272,17 +2280,15 @@ static int netvsc_remove(struct hv_device *dev) cancel_delayed_work_sync(&ndev_ctx->dwork); - rcu_read_lock(); - nvdev = rcu_dereference(ndev_ctx->nvdev); - - if (nvdev) + rtnl_lock(); + nvdev = rtnl_dereference(ndev_ctx->nvdev); + if (nvdev) cancel_work_sync(&nvdev->subchan_work); /* * Call to the vsc driver to let it know that the device is being * removed. Also blocks mtu and channel changes. */ - rtnl_lock(); vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev); if (vf_netdev) netvsc_unregister_vf(vf_netdev); @@ -2294,7 +2300,6 @@ static int netvsc_remove(struct hv_device *dev) list_del(&ndev_ctx->list); rtnl_unlock(); - rcu_read_unlock(); hv_set_drvdata(dev, NULL); diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c @@ -429,6 +429,9 @@ static int pppoe_rcv(struct sk_buff *skb, struct net_device *dev, if (!skb) goto out; + if (skb_mac_header_len(skb) < ETH_HLEN) + goto drop; + if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr))) goto drop; diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c @@ -1213,13 +1213,13 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1199, 0x9061, 8)}, /* Sierra Wireless Modem */ {QMI_FIXED_INTF(0x1199, 0x9063, 8)}, /* Sierra Wireless EM7305 */ {QMI_FIXED_INTF(0x1199, 0x9063, 10)}, /* Sierra Wireless EM7305 */ - {QMI_FIXED_INTF(0x1199, 0x9071, 8)}, /* Sierra Wireless MC74xx */ - {QMI_FIXED_INTF(0x1199, 0x9071, 10)}, /* Sierra Wireless MC74xx */ - {QMI_FIXED_INTF(0x1199, 0x9079, 8)}, /* Sierra Wireless EM74xx */ - {QMI_FIXED_INTF(0x1199, 0x9079, 10)}, /* Sierra Wireless EM74xx */ - {QMI_FIXED_INTF(0x1199, 0x907b, 8)}, /* Sierra Wireless EM74xx */ - {QMI_FIXED_INTF(0x1199, 0x907b, 10)}, /* Sierra Wireless EM74xx */ - {QMI_FIXED_INTF(0x1199, 0x9091, 8)}, /* Sierra Wireless EM7565 */ + {QMI_QUIRK_SET_DTR(0x1199, 0x9071, 8)}, /* Sierra Wireless MC74xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x9071, 10)},/* Sierra Wireless MC74xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x9079, 8)}, /* Sierra Wireless EM74xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x9079, 10)},/* Sierra Wireless EM74xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x907b, 8)}, /* Sierra Wireless EM74xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x907b, 10)},/* Sierra Wireless EM74xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x9091, 8)}, /* Sierra Wireless EM7565 */ {QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */ {QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */ {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ diff --git a/drivers/net/veth.c b/drivers/net/veth.c @@ -463,6 +463,8 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq, struct sk_buff *skb, int mac_len, delta, off; struct xdp_buff xdp; + skb_orphan(skb); + rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); if (unlikely(!xdp_prog)) { @@ -508,8 +510,6 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq, struct sk_buff *skb, skb_copy_header(nskb, skb); head_off = skb_headroom(nskb) - skb_headroom(skb); skb_headers_offset_update(nskb, head_off); - if (skb->sk) - skb_set_owner_w(nskb, skb->sk); consume_skb(skb); skb = nskb; } diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c @@ -908,7 +908,11 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue, BUG_ON(pull_to <= skb_headlen(skb)); __pskb_pull_tail(skb, pull_to - skb_headlen(skb)); } - BUG_ON(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS); + if (unlikely(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS)) { + queue->rx.rsp_cons = ++cons; + kfree_skb(nskb); + return ~0U; + } skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, skb_frag_page(nfrag), @@ -1045,6 +1049,8 @@ err: skb->len += rx->status; i = xennet_fill_frags(queue, skb, &tmpq); + if (unlikely(i == ~0U)) + goto err; if (rx->flags & XEN_NETRXF_csum_blank) skb->ip_summed = CHECKSUM_PARTIAL; diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c @@ -89,6 +89,9 @@ static enum pci_protocol_version_t pci_protocol_version; #define STATUS_REVISION_MISMATCH 0xC0000059 +/* space for 32bit serial number as string */ +#define SLOT_NAME_SIZE 11 + /* * Message Types */ @@ -494,6 +497,7 @@ struct hv_pci_dev { struct list_head list_entry; refcount_t refs; enum hv_pcichild_state state; + struct pci_slot *pci_slot; struct pci_function_description desc; bool reported_missing; struct hv_pcibus_device *hbus; @@ -1457,6 +1461,34 @@ static void prepopulate_bars(struct hv_pcibus_device *hbus) spin_unlock_irqrestore(&hbus->device_list_lock, flags); } +/* + * Assign entries in sysfs pci slot directory. + * + * Note that this function does not need to lock the children list + * because it is called from pci_devices_present_work which + * is serialized with hv_eject_device_work because they are on the + * same ordered workqueue. Therefore hbus->children list will not change + * even when pci_create_slot sleeps. + */ +static void hv_pci_assign_slots(struct hv_pcibus_device *hbus) +{ + struct hv_pci_dev *hpdev; + char name[SLOT_NAME_SIZE]; + int slot_nr; + + list_for_each_entry(hpdev, &hbus->children, list_entry) { + if (hpdev->pci_slot) + continue; + + slot_nr = PCI_SLOT(wslot_to_devfn(hpdev->desc.win_slot.slot)); + snprintf(name, SLOT_NAME_SIZE, "%u", hpdev->desc.ser); + hpdev->pci_slot = pci_create_slot(hbus->pci_bus, slot_nr, + name, NULL); + if (!hpdev->pci_slot) + pr_warn("pci_create slot %s failed\n", name); + } +} + /** * create_root_hv_pci_bus() - Expose a new root PCI bus * @hbus: Root PCI bus, as understood by this driver @@ -1480,6 +1512,7 @@ static int create_root_hv_pci_bus(struct hv_pcibus_device *hbus) pci_lock_rescan_remove(); pci_scan_child_bus(hbus->pci_bus); pci_bus_assign_resources(hbus->pci_bus); + hv_pci_assign_slots(hbus); pci_bus_add_devices(hbus->pci_bus); pci_unlock_rescan_remove(); hbus->state = hv_pcibus_installed; @@ -1742,6 +1775,7 @@ static void pci_devices_present_work(struct work_struct *work) */ pci_lock_rescan_remove(); pci_scan_child_bus(hbus->pci_bus); + hv_pci_assign_slots(hbus); pci_unlock_rescan_remove(); break; @@ -1858,6 +1892,9 @@ static void hv_eject_device_work(struct work_struct *work) list_del(&hpdev->list_entry); spin_unlock_irqrestore(&hpdev->hbus->device_list_lock, flags); + if (hpdev->pci_slot) + pci_destroy_slot(hpdev->pci_slot); + memset(&ctxt, 0, sizeof(ctxt)); ejct_pkt = (struct pci_eject_response *)&ctxt.pkt.message; ejct_pkt->message_type.type = PCI_EJECTION_COMPLETE; diff --git a/include/net/tls.h b/include/net/tls.h @@ -171,15 +171,14 @@ struct cipher_context { char *rec_seq; }; +union tls_crypto_context { + struct tls_crypto_info info; + struct tls12_crypto_info_aes_gcm_128 aes_gcm_128; +}; + struct tls_context { - union { - struct tls_crypto_info crypto_send; - struct tls12_crypto_info_aes_gcm_128 crypto_send_aes_gcm_128; - }; - union { - struct tls_crypto_info crypto_recv; - struct tls12_crypto_info_aes_gcm_128 crypto_recv_aes_gcm_128; - }; + union tls_crypto_context crypto_send; + union tls_crypto_context crypto_recv; struct list_head list; struct net_device *netdev; @@ -367,8 +366,8 @@ static inline void tls_fill_prepend(struct tls_context *ctx, * size KTLS_DTLS_HEADER_SIZE + KTLS_DTLS_NONCE_EXPLICIT_SIZE */ buf[0] = record_type; - buf[1] = TLS_VERSION_MINOR(ctx->crypto_send.version); - buf[2] = TLS_VERSION_MAJOR(ctx->crypto_send.version); + buf[1] = TLS_VERSION_MINOR(ctx->crypto_send.info.version); + buf[2] = TLS_VERSION_MAJOR(ctx->crypto_send.info.version); /* we can use IV for nonce explicit according to spec */ buf[3] = pkt_len >> 8; buf[4] = pkt_len & 0xFF; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c @@ -1844,7 +1844,7 @@ static int btf_check_all_metas(struct btf_verifier_env *env) hdr = &btf->hdr; cur = btf->nohdr_data + hdr->type_off; - end = btf->nohdr_data + hdr->type_len; + end = cur + hdr->type_len; env->log_type_id = 1; while (cur < end) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c @@ -3163,7 +3163,7 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, * an arbitrary scalar. Disallow all math except * pointer subtraction */ - if (opcode == BPF_SUB){ + if (opcode == BPF_SUB && env->allow_ptr_leaks) { mark_reg_unknown(env, regs, insn->dst_reg); return 0; } diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c @@ -83,6 +83,7 @@ enum { struct smp_dev { /* Secure Connections OOB data */ + bool local_oob; u8 local_pk[64]; u8 local_rand[16]; bool debug_key; @@ -599,6 +600,8 @@ int smp_generate_oob(struct hci_dev *hdev, u8 hash[16], u8 rand[16]) memcpy(rand, smp->local_rand, 16); + smp->local_oob = true; + return 0; } @@ -1785,7 +1788,7 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) * successfully received our local OOB data - therefore set the * flag to indicate that local OOB is in use. */ - if (req->oob_flag == SMP_OOB_PRESENT) + if (req->oob_flag == SMP_OOB_PRESENT && SMP_DEV(hdev)->local_oob) set_bit(SMP_FLAG_LOCAL_OOB, &smp->flags); /* SMP over BR/EDR requires special treatment */ @@ -1967,7 +1970,7 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb) * successfully received our local OOB data - therefore set the * flag to indicate that local OOB is in use. */ - if (rsp->oob_flag == SMP_OOB_PRESENT) + if (rsp->oob_flag == SMP_OOB_PRESENT && SMP_DEV(hdev)->local_oob) set_bit(SMP_FLAG_LOCAL_OOB, &smp->flags); smp->prsp[0] = SMP_CMD_PAIRING_RSP; @@ -2697,7 +2700,13 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) * key was set/generated. */ if (test_bit(SMP_FLAG_LOCAL_OOB, &smp->flags)) { - struct smp_dev *smp_dev = chan->data; + struct l2cap_chan *hchan = hdev->smp_data; + struct smp_dev *smp_dev; + + if (!hchan || !hchan->data) + return SMP_UNSPECIFIED; + + smp_dev = hchan->data; tfm_ecdh = smp_dev->tfm_ecdh; } else { @@ -3230,6 +3239,7 @@ static struct l2cap_chan *smp_add_cid(struct hci_dev *hdev, u16 cid) return ERR_CAST(tfm_ecdh); } + smp->local_oob = false; smp->tfm_aes = tfm_aes; smp->tfm_cmac = tfm_cmac; smp->tfm_ecdh = tfm_ecdh; diff --git a/net/core/filter.c b/net/core/filter.c @@ -2344,7 +2344,8 @@ BPF_CALL_4(bpf_msg_pull_data, if (unlikely(bytes_sg_total > copy)) return -EINVAL; - page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC, get_order(copy)); + page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC | __GFP_COMP, + get_order(copy)); if (unlikely(!page)) return -ENOMEM; p = page_address(page); diff --git a/net/core/neighbour.c b/net/core/neighbour.c @@ -1180,6 +1180,12 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, lladdr = neigh->ha; } + /* Update confirmed timestamp for neighbour entry after we + * received ARP packet even if it doesn't change IP to MAC binding. + */ + if (new & NUD_CONNECTED) + neigh->confirmed = jiffies; + /* If entry was valid and address is not changed, do not change entry state, if new one is STALE. */ @@ -1201,15 +1207,12 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, } } - /* Update timestamps only once we know we will make a change to the + /* Update timestamp only once we know we will make a change to the * neighbour entry. Otherwise we risk to move the locktime window with * noop updates and ignore relevant ARP updates. */ - if (new != old || lladdr != neigh->ha) { - if (new & NUD_CONNECTED) - neigh->confirmed = jiffies; + if (new != old || lladdr != neigh->ha) neigh->updated = jiffies; - } if (new != old) { neigh_del_timer(neigh); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c @@ -2810,7 +2810,7 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm) } if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) { - __dev_notify_flags(dev, old_flags, 0U); + __dev_notify_flags(dev, old_flags, (old_flags ^ dev->flags)); } else { dev->rtnl_link_state = RTNL_LINK_INITIALIZED; __dev_notify_flags(dev, old_flags, ~0U); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c @@ -1377,6 +1377,7 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb, if (encap) skb_reset_inner_headers(skb); skb->network_header = (u8 *)iph - skb->head; + skb_reset_mac_len(skb); } while ((skb = skb->next)); out: diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c @@ -2124,6 +2124,28 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh, inet_compute_pseudo); } +/* wrapper for udp_queue_rcv_skb tacking care of csum conversion and + * return code conversion for ip layer consumption + */ +static int udp_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb, + struct udphdr *uh) +{ + int ret; + + if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) + skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check, + inet_compute_pseudo); + + ret = udp_queue_rcv_skb(sk, skb); + + /* a return value > 0 means to resubmit the input, but + * it wants the return to be -protocol, or 0 + */ + if (ret > 0) + return -ret; + return 0; +} + /* * All we need to do is get the socket, and then do a checksum. */ @@ -2170,14 +2192,9 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (unlikely(sk->sk_rx_dst != dst)) udp_sk_rx_dst_set(sk, dst); - ret = udp_queue_rcv_skb(sk, skb); + ret = udp_unicast_rcv_skb(sk, skb, uh); sock_put(sk); - /* a return value > 0 means to resubmit the input, but - * it wants the return to be -protocol, or 0 - */ - if (ret > 0) - return -ret; - return 0; + return ret; } if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST)) @@ -2185,22 +2202,8 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, saddr, daddr, udptable, proto); sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable); - if (sk) { - int ret; - - if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) - skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check, - inet_compute_pseudo); - - ret = udp_queue_rcv_skb(sk, skb); - - /* a return value > 0 means to resubmit the input, but - * it wants the return to be -protocol, or 0 - */ - if (ret > 0) - return -ret; - return 0; - } + if (sk) + return udp_unicast_rcv_skb(sk, skb, uh); if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c @@ -115,6 +115,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, payload_len = skb->len - nhoff - sizeof(*ipv6h); ipv6h->payload_len = htons(payload_len); skb->network_header = (u8 *)ipv6h - skb->head; + skb_reset_mac_len(skb); if (udpfrag) { int err = ip6_find_1stfragopt(skb, &prevhdr); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c @@ -219,12 +219,10 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, kfree_skb(skb); return -ENOBUFS; } + if (skb->sk) + skb_set_owner_w(skb2, skb->sk); consume_skb(skb); skb = skb2; - /* skb_set_owner_w() changes sk->sk_wmem_alloc atomically, - * it is safe to call in our context (socket lock not held) - */ - skb_set_owner_w(skb, (struct sock *)sk); } if (opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); diff --git a/net/ipv6/route.c b/net/ipv6/route.c @@ -946,8 +946,6 @@ static void ip6_rt_init_dst_reject(struct rt6_info *rt, struct fib6_info *ort) static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort) { - rt->dst.flags |= fib6_info_dst_flags(ort); - if (ort->fib6_flags & RTF_REJECT) { ip6_rt_init_dst_reject(rt, ort); return; @@ -4670,20 +4668,31 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, int iif, int type, u32 portid, u32 seq, unsigned int flags) { - struct rtmsg *rtm; + struct rt6_info *rt6 = (struct rt6_info *)dst; + struct rt6key *rt6_dst, *rt6_src; + u32 *pmetrics, table, rt6_flags; struct nlmsghdr *nlh; + struct rtmsg *rtm; long expires = 0; - u32 *pmetrics; - u32 table; nlh = nlmsg_put(skb, portid, seq, type, sizeof(*rtm), flags); if (!nlh) return -EMSGSIZE; + if (rt6) { + rt6_dst = &rt6->rt6i_dst; + rt6_src = &rt6->rt6i_src; + rt6_flags = rt6->rt6i_flags; + } else { + rt6_dst = &rt->fib6_dst; + rt6_src = &rt->fib6_src; + rt6_flags = rt->fib6_flags; + } + rtm = nlmsg_data(nlh); rtm->rtm_family = AF_INET6; - rtm->rtm_dst_len = rt->fib6_dst.plen; - rtm->rtm_src_len = rt->fib6_src.plen; + rtm->rtm_dst_len = rt6_dst->plen; + rtm->rtm_src_len = rt6_src->plen; rtm->rtm_tos = 0; if (rt->fib6_table) table = rt->fib6_table->tb6_id; @@ -4698,7 +4707,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, rtm->rtm_scope = RT_SCOPE_UNIVERSE; rtm->rtm_protocol = rt->fib6_protocol; - if (rt->fib6_flags & RTF_CACHE) + if (rt6_flags & RTF_CACHE) rtm->rtm_flags |= RTM_F_CLONED; if (dest) { @@ -4706,7 +4715,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, goto nla_put_failure; rtm->rtm_dst_len = 128; } else if (rtm->rtm_dst_len) - if (nla_put_in6_addr(skb, RTA_DST, &rt->fib6_dst.addr)) + if (nla_put_in6_addr(skb, RTA_DST, &rt6_dst->addr)) goto nla_put_failure; #ifdef CONFIG_IPV6_SUBTREES if (src) { @@ -4714,12 +4723,12 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, goto nla_put_failure; rtm->rtm_src_len = 128; } else if (rtm->rtm_src_len && - nla_put_in6_addr(skb, RTA_SRC, &rt->fib6_src.addr)) + nla_put_in6_addr(skb, RTA_SRC, &rt6_src->addr)) goto nla_put_failure; #endif if (iif) { #ifdef CONFIG_IPV6_MROUTE - if (ipv6_addr_is_multicast(&rt->fib6_dst.addr)) { + if (ipv6_addr_is_multicast(&rt6_dst->addr)) { int err = ip6mr_get_route(net, skb, rtm, portid); if (err == 0) @@ -4754,7 +4763,14 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, /* For multipath routes, walk the siblings list and add * each as a nexthop within RTA_MULTIPATH. */ - if (rt->fib6_nsiblings) { + if (rt6) { + if (rt6_flags & RTF_GATEWAY && + nla_put_in6_addr(skb, RTA_GATEWAY, &rt6->rt6i_gateway)) + goto nla_put_failure; + + if (dst->dev && nla_put_u32(skb, RTA_OIF, dst->dev->ifindex)) + goto nla_put_failure; + } else if (rt->fib6_nsiblings) { struct fib6_info *sibling, *next_sibling; struct nlattr *mp; @@ -4777,7 +4793,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, goto nla_put_failure; } - if (rt->fib6_flags & RTF_EXPIRES) { + if (rt6_flags & RTF_EXPIRES) { expires = dst ? dst->expires : rt->expires; expires -= jiffies; } @@ -4785,7 +4801,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, if (rtnl_put_cacheinfo(skb, dst, 0, expires, dst ? dst->error : 0) < 0) goto nla_put_failure; - if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->fib6_flags))) + if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt6_flags))) goto nla_put_failure; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c @@ -752,6 +752,28 @@ static void udp6_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) } } +/* wrapper for udp_queue_rcv_skb tacking care of csum conversion and + * return code conversion for ip layer consumption + */ +static int udp6_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb, + struct udphdr *uh) +{ + int ret; + + if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) + skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check, + ip6_compute_pseudo); + + ret = udpv6_queue_rcv_skb(sk, skb); + + /* a return value > 0 means to resubmit the input, but + * it wants the return to be -protocol, or 0 + */ + if (ret > 0) + return -ret; + return 0; +} + int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, int proto) { @@ -803,13 +825,14 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (unlikely(sk->sk_rx_dst != dst)) udp6_sk_rx_dst_set(sk, dst); - ret = udpv6_queue_rcv_skb(sk, skb); - sock_put(sk); + if (!uh->check && !udp_sk(sk)->no_check6_rx) { + sock_put(sk); + goto report_csum_error; + } - /* a return value > 0 means to resubmit the input */ - if (ret > 0) - return ret; - return 0; + ret = udp6_unicast_rcv_skb(sk, skb, uh); + sock_put(sk); + return ret; } /* @@ -822,30 +845,13 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, /* Unicast */ sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable); if (sk) { - int ret; - - if (!uh->check && !udp_sk(sk)->no_check6_rx) { - udp6_csum_zero_error(skb); - goto csum_error; - } - - if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) - skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check, - ip6_compute_pseudo); - - ret = udpv6_queue_rcv_skb(sk, skb); - - /* a return value > 0 means to resubmit the input */ - if (ret > 0) - return ret; - - return 0; + if (!uh->check && !udp_sk(sk)->no_check6_rx) + goto report_csum_error; + return udp6_unicast_rcv_skb(sk, skb, uh); } - if (!uh->check) { - udp6_csum_zero_error(skb); - goto csum_error; - } + if (!uh->check) + goto report_csum_error; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard; @@ -866,6 +872,9 @@ short_packet: ulen, skb->len, daddr, ntohs(uh->dest)); goto discard; + +report_csum_error: + udp6_csum_zero_error(skb); csum_error: __UDP6_INC_STATS(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE); discard: diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c @@ -69,7 +69,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, parm->index, est, a, - &act_sample_ops, bind, false); + &act_sample_ops, bind, true); if (ret) { tcf_idr_cleanup(tn, parm->index); return ret; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c @@ -1902,6 +1902,8 @@ replay: RTM_NEWCHAIN, false); break; case RTM_DELCHAIN: + tfilter_notify_chain(net, skb, block, q, parent, n, + chain, RTM_DELTFILTER); /* Flush the chain first as the user requested chain removal. */ tcf_chain_flush(chain); /* In case the chain was successfully deleted, put a reference diff --git a/net/socket.c b/net/socket.c @@ -941,7 +941,8 @@ void dlci_ioctl_set(int (*hook) (unsigned int, void __user *)) EXPORT_SYMBOL(dlci_ioctl_set); static long sock_do_ioctl(struct net *net, struct socket *sock, - unsigned int cmd, unsigned long arg) + unsigned int cmd, unsigned long arg, + unsigned int ifreq_size) { int err; void __user *argp = (void __user *)arg; @@ -967,11 +968,11 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, } else { struct ifreq ifr; bool need_copyout; - if (copy_from_user(&ifr, argp, sizeof(struct ifreq))) + if (copy_from_user(&ifr, argp, ifreq_size)) return -EFAULT; err = dev_ioctl(net, cmd, &ifr, &need_copyout); if (!err && need_copyout) - if (copy_to_user(argp, &ifr, sizeof(struct ifreq))) + if (copy_to_user(argp, &ifr, ifreq_size)) return -EFAULT; } return err; @@ -1070,7 +1071,8 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) err = open_related_ns(&net->ns, get_net_ns); break; default: - err = sock_do_ioctl(net, sock, cmd, arg); + err = sock_do_ioctl(net, sock, cmd, arg, + sizeof(struct ifreq)); break; } return err; @@ -2750,7 +2752,8 @@ static int do_siocgstamp(struct net *net, struct socket *sock, int err; set_fs(KERNEL_DS); - err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv); + err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv, + sizeof(struct compat_ifreq)); set_fs(old_fs); if (!err) err = compat_put_timeval(&ktv, up); @@ -2766,7 +2769,8 @@ static int do_siocgstampns(struct net *net, struct socket *sock, int err; set_fs(KERNEL_DS); - err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts); + err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts, + sizeof(struct compat_ifreq)); set_fs(old_fs); if (!err) err = compat_put_timespec(&kts, up); @@ -3072,7 +3076,8 @@ static int routing_ioctl(struct net *net, struct socket *sock, } set_fs(KERNEL_DS); - ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r); + ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r, + sizeof(struct compat_ifreq)); set_fs(old_fs); out: @@ -3185,7 +3190,8 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCBONDSETHWADDR: case SIOCBONDCHANGEACTIVE: case SIOCGIFNAME: - return sock_do_ioctl(net, sock, cmd, arg); + return sock_do_ioctl(net, sock, cmd, arg, + sizeof(struct compat_ifreq)); } return -ENOIOCTLCMD; diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c @@ -686,7 +686,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) goto free_marker_record; } - crypto_info = &ctx->crypto_send; + crypto_info = &ctx->crypto_send.info; switch (crypto_info->cipher_type) { case TLS_CIPHER_AES_GCM_128: nonce_size = TLS_CIPHER_AES_GCM_128_IV_SIZE; @@ -780,7 +780,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) ctx->priv_ctx_tx = offload_ctx; rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_TX, - &ctx->crypto_send, + &ctx->crypto_send.info, tcp_sk(sk)->write_seq); if (rc) goto release_netdev; @@ -862,7 +862,7 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx) goto release_ctx; rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_RX, - &ctx->crypto_recv, + &ctx->crypto_recv.info, tcp_sk(sk)->copied_seq); if (rc) { pr_err_ratelimited("%s: The netdev has refused to offload this socket\n", diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c @@ -320,7 +320,7 @@ static struct sk_buff *tls_enc_skb(struct tls_context *tls_ctx, goto free_req; iv = buf; - memcpy(iv, tls_ctx->crypto_send_aes_gcm_128.salt, + memcpy(iv, tls_ctx->crypto_send.aes_gcm_128.salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE); aad = buf + TLS_CIPHER_AES_GCM_128_SALT_SIZE + TLS_CIPHER_AES_GCM_128_IV_SIZE; diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c @@ -241,6 +241,16 @@ static void tls_write_space(struct sock *sk) ctx->sk_write_space(sk); } +static void tls_ctx_free(struct tls_context *ctx) +{ + if (!ctx) + return; + + memzero_explicit(&ctx->crypto_send, sizeof(ctx->crypto_send)); + memzero_explicit(&ctx->crypto_recv, sizeof(ctx->crypto_recv)); + kfree(ctx); +} + static void tls_sk_proto_close(struct sock *sk, long timeout) { struct tls_context *ctx = tls_get_ctx(sk); @@ -294,7 +304,7 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) #else { #endif - kfree(ctx); + tls_ctx_free(ctx); ctx = NULL; } @@ -305,7 +315,7 @@ skip_tx_cleanup: * for sk->sk_prot->unhash [tls_hw_unhash] */ if (free_ctx) - kfree(ctx); + tls_ctx_free(ctx); } static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, @@ -330,7 +340,7 @@ static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, } /* get user crypto info */ - crypto_info = &ctx->crypto_send; + crypto_info = &ctx->crypto_send.info; if (!TLS_CRYPTO_INFO_READY(crypto_info)) { rc = -EBUSY; @@ -417,9 +427,9 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, } if (tx) - crypto_info = &ctx->crypto_send; + crypto_info = &ctx->crypto_send.info; else - crypto_info = &ctx->crypto_recv; + crypto_info = &ctx->crypto_recv.info; /* Currently we don't support set crypto info more than one time */ if (TLS_CRYPTO_INFO_READY(crypto_info)) { @@ -499,7 +509,7 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, goto out; err_crypto_info: - memset(crypto_info, 0, sizeof(*crypto_info)); + memzero_explicit(crypto_info, sizeof(union tls_crypto_context)); out: return rc; } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c @@ -931,7 +931,15 @@ int tls_sw_recvmsg(struct sock *sk, if (control != TLS_RECORD_TYPE_DATA) goto recv_end; } + } else { + /* MSG_PEEK right now cannot look beyond current skb + * from strparser, meaning we cannot advance skb here + * and thus unpause strparser since we'd loose original + * one. + */ + break; } + /* If we have a new message from strparser, continue now. */ if (copied >= target && !ctx->recv_pkt) break; @@ -1055,8 +1063,8 @@ static int tls_read_size(struct strparser *strp, struct sk_buff *skb) goto read_failure; } - if (header[1] != TLS_VERSION_MINOR(tls_ctx->crypto_recv.version) || - header[2] != TLS_VERSION_MAJOR(tls_ctx->crypto_recv.version)) { + if (header[1] != TLS_VERSION_MINOR(tls_ctx->crypto_recv.info.version) || + header[2] != TLS_VERSION_MAJOR(tls_ctx->crypto_recv.info.version)) { ret = -EINVAL; goto read_failure; } @@ -1136,7 +1144,6 @@ void tls_sw_free_resources_rx(struct sock *sk) int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) { - char keyval[TLS_CIPHER_AES_GCM_128_KEY_SIZE]; struct tls_crypto_info *crypto_info; struct tls12_crypto_info_aes_gcm_128 *gcm_128_info; struct tls_sw_context_tx *sw_ctx_tx = NULL; @@ -1181,12 +1188,12 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) if (tx) { crypto_init_wait(&sw_ctx_tx->async_wait); - crypto_info = &ctx->crypto_send; + crypto_info = &ctx->crypto_send.info; cctx = &ctx->tx; aead = &sw_ctx_tx->aead_send; } else { crypto_init_wait(&sw_ctx_rx->async_wait); - crypto_info = &ctx->crypto_recv; + crypto_info = &ctx->crypto_recv.info; cctx = &ctx->rx; aead = &sw_ctx_rx->aead_recv; } @@ -1265,9 +1272,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) ctx->push_pending_record = tls_sw_push_pending_record; - memcpy(keyval, gcm_128_info->key, TLS_CIPHER_AES_GCM_128_KEY_SIZE); - - rc = crypto_aead_setkey(*aead, keyval, + rc = crypto_aead_setkey(*aead, gcm_128_info->key, TLS_CIPHER_AES_GCM_128_KEY_SIZE); if (rc) goto free_aead; diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c @@ -502,6 +502,55 @@ TEST_F(tls, recv_peek_multiple) EXPECT_EQ(memcmp(test_str, buf, send_len), 0); } +TEST_F(tls, recv_peek_multiple_records) +{ + char const *test_str = "test_read_peek_mult_recs"; + char const *test_str_first = "test_read_peek"; + char const *test_str_second = "_mult_recs"; + int len; + char buf[64]; + + len = strlen(test_str_first); + EXPECT_EQ(send(self->fd, test_str_first, len, 0), len); + + len = strlen(test_str_second) + 1; + EXPECT_EQ(send(self->fd, test_str_second, len, 0), len); + + len = sizeof(buf); + memset(buf, 0, len); + EXPECT_NE(recv(self->cfd, buf, len, MSG_PEEK), -1); + + /* MSG_PEEK can only peek into the current record. */ + len = strlen(test_str_first) + 1; + EXPECT_EQ(memcmp(test_str_first, buf, len), 0); + + len = sizeof(buf); + memset(buf, 0, len); + EXPECT_NE(recv(self->cfd, buf, len, 0), -1); + + /* Non-MSG_PEEK will advance strparser (and therefore record) + * however. + */ + len = strlen(test_str) + 1; + EXPECT_EQ(memcmp(test_str, buf, len), 0); + + /* MSG_MORE will hold current record open, so later MSG_PEEK + * will see everything. + */ + len = strlen(test_str_first); + EXPECT_EQ(send(self->fd, test_str_first, len, MSG_MORE), len); + + len = strlen(test_str_second) + 1; + EXPECT_EQ(send(self->fd, test_str_second, len, 0), len); + + len = sizeof(buf); + memset(buf, 0, len); + EXPECT_NE(recv(self->cfd, buf, len, MSG_PEEK), -1); + + len = strlen(test_str) + 1; + EXPECT_EQ(memcmp(test_str, buf, len), 0); +} + TEST_F(tls, pollin) { char const *test_str = "test_poll";