whiterose

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

commit 8f49a658b4ea1d0205068da76b7c8c844817dc44
parent ffd602eb4693bbb49b301fa059b109bbdebf9524
Author: Linus Torvalds <torvalds@linux-foundation.org>
Date:   Mon, 11 Mar 2019 08:54:01 -0700

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

Pull networking fixes from David Miller:
 "First batch of fixes in the new merge window:

   1) Double dst_cache free in act_tunnel_key, from Wenxu.

   2) Avoid NULL deref in IN_DEV_MFORWARD() by failing early in the
      ip_route_input_rcu() path, from Paolo Abeni.

   3) Fix appletalk compile regression, from Arnd Bergmann.

   4) If SLAB objects reach the TCP sendpage method we are in serious
      trouble, so put a debugging check there. From Vasily Averin.

   5) Memory leak in hsr layer, from Mao Wenan.

   6) Only test GSO type on GSO packets, from Willem de Bruijn.

   7) Fix crash in xsk_diag_put_umem(), from Eric Dumazet.

   8) Fix VNIC mailbox length in nfp, from Dirk van der Merwe.

   9) Fix race in ipv4 route exception handling, from Xin Long.

  10) Missing DMA memory barrier in hns3 driver, from Jian Shen.

  11) Use after free in __tcf_chain_put(), from Vlad Buslov.

  12) Handle inet_csk_reqsk_queue_add() failures, from Guillaume Nault.

  13) Return value correction when ip_mc_may_pull() fails, from Eric
      Dumazet.

  14) Use after free in x25_device_event(), also from Eric"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (72 commits)
  gro_cells: make sure device is up in gro_cells_receive()
  vxlan: test dev->flags & IFF_UP before calling gro_cells_receive()
  net/x25: fix use-after-free in x25_device_event()
  isdn: mISDNinfineon: fix potential NULL pointer dereference
  net: hns3: fix to stop multiple HNS reset due to the AER changes
  ip: fix ip_mc_may_pull() return value
  net: keep refcount warning in reqsk_free()
  net: stmmac: Avoid one more sometimes uninitialized Clang warning
  net: dsa: mv88e6xxx: Set correct interface mode for CPU/DSA ports
  rxrpc: Fix client call queueing, waiting for channel
  tcp: handle inet_csk_reqsk_queue_add() failures
  net: ethernet: sun: Zero initialize class in default case in niu_add_ethtool_tcam_entry
  8139too : Add support for U.S. Robotics USR997901A 10/100 Cardbus NIC
  fou, fou6: avoid uninit-value in gue_err() and gue6_err()
  net: sched: fix potential use-after-free in __tcf_chain_put()
  vhost: silence an unused-variable warning
  vsock/virtio: fix kernel panic from virtio_transport_reset_no_sock
  connector: fix unsafe usage of ->real_parent
  vxlan: do not need BH again in vxlan_cleanup()
  net: hns3: add dma_rmb() for rx description
  ...

Diffstat:
MDocumentation/devicetree/bindings/net/stm32-dwmac.txt | 9++++-----
MMAINTAINERS | 2++
March/arm/boot/dts/stm32h743-pinctrl.dtsi | 15+++++++++++++++
March/arm/boot/dts/stm32h743.dtsi | 13+++++++++++++
March/arm/boot/dts/stm32h743i-disco.dts | 17+++++++++++++++++
March/arm/boot/dts/stm32h743i-eval.dts | 17+++++++++++++++++
Mdrivers/connector/cn_proc.c | 22++++++++++++++++++----
Mdrivers/isdn/hardware/mISDN/mISDNinfineon.c | 5++++-
Mdrivers/isdn/isdnloop/isdnloop.c | 2+-
Mdrivers/net/can/usb/peak_usb/pcan_usb_pro.c | 2+-
Mdrivers/net/dsa/mv88e6xxx/chip.c | 11+++++++++++
Mdrivers/net/dsa/mv88e6xxx/chip.h | 3+++
Mdrivers/net/dsa/mv88e6xxx/port.c | 24++++++++++++++++++++++++
Mdrivers/net/dsa/mv88e6xxx/port.h | 4++++
Mdrivers/net/ethernet/cisco/enic/enic_main.c | 6+++---
Mdrivers/net/ethernet/hisilicon/hns3/hnae3.h | 1+
Mdrivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 10+++++++---
Mdrivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c | 9+++++++--
Mdrivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h | 2+-
Mdrivers/net/ethernet/qlogic/qede/qede_ethtool.c | 7+++++--
Mdrivers/net/ethernet/realtek/8139too.c | 1+
Mdrivers/net/ethernet/renesas/ravb_main.c | 2+-
Mdrivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c | 135++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-------------
Mdrivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 6+++---
Mdrivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 3+++
Mdrivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c | 2+-
Mdrivers/net/ethernet/sun/niu.c | 1+
Mdrivers/net/ethernet/ti/davinci_emac.c | 4+---
Mdrivers/net/vxlan.c | 18+++++++++++++++---
Minclude/linux/atalk.h | 18++++++++++++++----
Minclude/linux/bpf-cgroup.h | 2+-
Minclude/linux/igmp.h | 2+-
Minclude/linux/skbuff.h | 68+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-------
Minclude/net/request_sock.h | 1-
Minclude/trace/events/rxrpc.h | 2++
Mkernel/bpf/verifier.c | 10+++++-----
Mkernel/sysctl.c | 2+-
Mnet/atm/resources.c | 10+++-------
Mnet/bpf/test_run.c | 2+-
Mnet/core/ethtool.c | 16+++++++++-------
Mnet/core/filter.c | 8++++----
Mnet/core/gro_cells.c | 22++++++++++++++++++----
Mnet/core/lwt_bpf.c | 2++
Mnet/core/skmsg.c | 1+
Mnet/hsr/hsr_device.c | 18+++++++++---------
Mnet/hsr/hsr_framereg.c | 12++++++++++++
Mnet/hsr/hsr_framereg.h | 1+
Mnet/ipv4/fou.c | 4++--
Mnet/ipv4/ip_tunnel.c | 9++++++---
Mnet/ipv4/route.c | 13+++++++++----
Mnet/ipv4/syncookies.c | 7++++++-
Mnet/ipv4/tcp.c | 9+++++++++
Mnet/ipv4/tcp_input.c | 8+++++++-
Mnet/ipv6/fou6.c | 4++--
Mnet/rxrpc/conn_client.c | 24+++++++++++++++++-------
Mnet/sched/act_tunnel_key.c | 22++++++----------------
Mnet/sched/cls_api.c | 17+++++++----------
Mnet/sched/cls_flower.c | 43++++++++++++++++++++++---------------------
Mnet/sctp/auth.c | 6------
Mnet/sctp/endpointola.c | 18++++++++++--------
Mnet/sctp/socket.c | 44++++++++++++++++++++++++++++++++++----------
Mnet/sctp/stream.c | 2--
Mnet/tipc/socket.c | 2+-
Mnet/vmw_vsock/virtio_transport_common.c | 22+++++++++++++++-------
Mnet/x25/af_x25.c | 6+++++-
Mnet/xdp/xsk.c | 5++++-
Mnet/xdp/xsk_diag.c | 4++--
Mnet/xdp/xsk_queue.h | 4++--
Msamples/bpf/hbm.c | 4++--
Mtools/lib/bpf/Makefile | 3++-
Mtools/lib/bpf/libbpf.c | 2++
Mtools/testing/selftests/bpf/Makefile | 33+++++++++++++++++++++++----------
Mtools/testing/selftests/bpf/prog_tests/signal_pending.c | 2+-
Mtools/testing/selftests/bpf/test_lwt_ip_encap.sh | 54++++++++++++++++++++++++++++++++++++++++++++++++++++--
Mtools/testing/selftests/bpf/verifier/ld_imm64.c | 15++++++++++++++-
75 files changed, 705 insertions(+), 231 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/stm32-dwmac.txt b/Documentation/devicetree/bindings/net/stm32-dwmac.txt @@ -14,8 +14,7 @@ Required properties: - clock-names: Should be "stmmaceth" for the host clock. Should be "mac-clk-tx" for the MAC TX clock. Should be "mac-clk-rx" for the MAC RX clock. - For MPU family need to add also "ethstp" for power mode clock and, - "syscfg-clk" for SYSCFG clock. + For MPU family need to add also "ethstp" for power mode clock - interrupt-names: Should contain a list of interrupt names corresponding to the interrupts in the interrupts property, if available. Should be "macirq" for the main MAC IRQ @@ -24,9 +23,9 @@ Required properties: encompases the glue register, and the offset of the control register. Optional properties: -- clock-names: For MPU family "mac-clk-ck" for PHY without quartz -- st,int-phyclk (boolean) : valid only where PHY do not have quartz and need to be clock - by RCC +- clock-names: For MPU family "eth-ck" for PHY without quartz +- st,eth-clk-sel (boolean) : set this property in RGMII PHY when you want to select RCC clock instead of ETH_CLK125. +- st,eth-ref-clk-sel (boolean) : set this property in RMII mode when you have PHY without crystal 50MHz and want to select RCC clock instead of ETH_REF_CLK. Example: diff --git a/MAINTAINERS b/MAINTAINERS @@ -1059,6 +1059,8 @@ L: netdev@vger.kernel.org S: Odd fixes F: drivers/net/appletalk/ F: net/appletalk/ +F: include/linux/atalk.h +F: include/uapi/linux/atalk.h APPLIED MICRO (APM) X-GENE DEVICE TREE SUPPORT M: Khuong Dinh <khuong@os.amperecomputing.com> diff --git a/arch/arm/boot/dts/stm32h743-pinctrl.dtsi b/arch/arm/boot/dts/stm32h743-pinctrl.dtsi @@ -173,6 +173,21 @@ }; }; + ethernet_rmii: rmii@0 { + pins { + pinmux = <STM32_PINMUX('G', 11, AF11)>, + <STM32_PINMUX('G', 13, AF11)>, + <STM32_PINMUX('G', 12, AF11)>, + <STM32_PINMUX('C', 4, AF11)>, + <STM32_PINMUX('C', 5, AF11)>, + <STM32_PINMUX('A', 7, AF11)>, + <STM32_PINMUX('C', 1, AF11)>, + <STM32_PINMUX('A', 2, AF11)>, + <STM32_PINMUX('A', 1, AF11)>; + slew-rate = <2>; + }; + }; + usart1_pins: usart1@0 { pins1 { pinmux = <STM32_PINMUX('B', 14, AF4)>; /* USART1_TX */ diff --git a/arch/arm/boot/dts/stm32h743.dtsi b/arch/arm/boot/dts/stm32h743.dtsi @@ -513,6 +513,19 @@ status = "disabled"; }; }; + + mac: ethernet@40028000 { + compatible = "st,stm32-dwmac", "snps,dwmac-4.10a"; + reg = <0x40028000 0x8000>; + reg-names = "stmmaceth"; + interrupts = <61>; + interrupt-names = "macirq"; + clock-names = "stmmaceth", "mac-clk-tx", "mac-clk-rx"; + clocks = <&rcc ETH1MAC_CK>, <&rcc ETH1TX_CK>, <&rcc ETH1RX_CK>; + st,syscon = <&syscfg 0x4>; + snps,pbl = <8>; + status = "disabled"; + }; }; }; diff --git a/arch/arm/boot/dts/stm32h743i-disco.dts b/arch/arm/boot/dts/stm32h743i-disco.dts @@ -67,6 +67,23 @@ clock-frequency = <25000000>; }; +&mac { + status = "disabled"; + pinctrl-0 = <&ethernet_rmii>; + pinctrl-names = "default"; + phy-mode = "rmii"; + phy-handle = <&phy0>; + + mdio0 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,dwmac-mdio"; + phy0: ethernet-phy@0 { + reg = <0>; + }; + }; +}; + &usart2 { pinctrl-0 = <&usart2_pins>; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/stm32h743i-eval.dts b/arch/arm/boot/dts/stm32h743i-eval.dts @@ -105,6 +105,23 @@ status = "okay"; }; +&mac { + status = "disabled"; + pinctrl-0 = <&ethernet_rmii>; + pinctrl-names = "default"; + phy-mode = "rmii"; + phy-handle = <&phy0>; + + mdio0 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,dwmac-mdio"; + phy0: ethernet-phy@0 { + reg = <0>; + }; + }; +}; + &usart1 { pinctrl-0 = <&usart1_pins>; pinctrl-names = "default"; diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c @@ -250,6 +250,7 @@ void proc_coredump_connector(struct task_struct *task) { struct cn_msg *msg; struct proc_event *ev; + struct task_struct *parent; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) @@ -262,8 +263,14 @@ void proc_coredump_connector(struct task_struct *task) ev->what = PROC_EVENT_COREDUMP; ev->event_data.coredump.process_pid = task->pid; ev->event_data.coredump.process_tgid = task->tgid; - ev->event_data.coredump.parent_pid = task->real_parent->pid; - ev->event_data.coredump.parent_tgid = task->real_parent->tgid; + + rcu_read_lock(); + if (pid_alive(task)) { + parent = rcu_dereference(task->real_parent); + ev->event_data.coredump.parent_pid = parent->pid; + ev->event_data.coredump.parent_tgid = parent->tgid; + } + rcu_read_unlock(); memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ @@ -276,6 +283,7 @@ void proc_exit_connector(struct task_struct *task) { struct cn_msg *msg; struct proc_event *ev; + struct task_struct *parent; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) @@ -290,8 +298,14 @@ void proc_exit_connector(struct task_struct *task) ev->event_data.exit.process_tgid = task->tgid; ev->event_data.exit.exit_code = task->exit_code; ev->event_data.exit.exit_signal = task->exit_signal; - ev->event_data.exit.parent_pid = task->real_parent->pid; - ev->event_data.exit.parent_tgid = task->real_parent->tgid; + + rcu_read_lock(); + if (pid_alive(task)) { + parent = rcu_dereference(task->real_parent); + ev->event_data.exit.parent_pid = parent->pid; + ev->event_data.exit.parent_tgid = parent->tgid; + } + rcu_read_unlock(); memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ diff --git a/drivers/isdn/hardware/mISDN/mISDNinfineon.c b/drivers/isdn/hardware/mISDN/mISDNinfineon.c @@ -712,8 +712,11 @@ setup_io(struct inf_hw *hw) (ulong)hw->addr.start, (ulong)hw->addr.size); return err; } - if (hw->ci->addr_mode == AM_MEMIO) + if (hw->ci->addr_mode == AM_MEMIO) { hw->addr.p = ioremap(hw->addr.start, hw->addr.size); + if (unlikely(!hw->addr.p)) + return -ENOMEM; + } hw->addr.mode = hw->ci->addr_mode; if (debug & DEBUG_HW) pr_notice("%s: IO addr %lx (%lu bytes) mode%d\n", diff --git a/drivers/isdn/isdnloop/isdnloop.c b/drivers/isdn/isdnloop/isdnloop.c @@ -570,7 +570,7 @@ isdnloop_atimeout(isdnloop_card *card, int ch) char buf[60]; spin_lock_irqsave(&card->isdnloop_lock, flags); - if (card->rcard) { + if (card->rcard[ch]) { isdnloop_fake(card->rcard[ch], "DDIS_I", card->rch[ch] + 1); card->rcard[ch]->rcard[card->rch[ch]] = NULL; card->rcard[ch] = NULL; diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c @@ -127,7 +127,7 @@ static u8 *pcan_msg_init_empty(struct pcan_usb_pro_msg *pm, /* * add one record to a message being built */ -static int pcan_msg_add_rec(struct pcan_usb_pro_msg *pm, u8 id, ...) +static int pcan_msg_add_rec(struct pcan_usb_pro_msg *pm, int id, ...) { int len, i; u8 *pc; diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c @@ -569,6 +569,9 @@ int mv88e6xxx_port_setup_mac(struct mv88e6xxx_chip *chip, int port, int link, goto restore_link; } + if (speed == SPEED_MAX && chip->info->ops->port_max_speed_mode) + mode = chip->info->ops->port_max_speed_mode(port); + if (chip->info->ops->port_set_pause) { err = chip->info->ops->port_set_pause(chip, port, pause); if (err) @@ -3067,6 +3070,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .port_set_duplex = mv88e6xxx_port_set_duplex, .port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay, .port_set_speed = mv88e6341_port_set_speed, + .port_max_speed_mode = mv88e6341_port_max_speed_mode, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, .port_set_egress_floods = mv88e6352_port_set_egress_floods, @@ -3385,6 +3389,7 @@ static const struct mv88e6xxx_ops mv88e6190_ops = { .port_set_duplex = mv88e6xxx_port_set_duplex, .port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay, .port_set_speed = mv88e6390_port_set_speed, + .port_max_speed_mode = mv88e6390_port_max_speed_mode, .port_tag_remap = mv88e6390_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, .port_set_egress_floods = mv88e6352_port_set_egress_floods, @@ -3429,6 +3434,7 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = { .port_set_duplex = mv88e6xxx_port_set_duplex, .port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay, .port_set_speed = mv88e6390x_port_set_speed, + .port_max_speed_mode = mv88e6390x_port_max_speed_mode, .port_tag_remap = mv88e6390_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, .port_set_egress_floods = mv88e6352_port_set_egress_floods, @@ -3473,6 +3479,7 @@ static const struct mv88e6xxx_ops mv88e6191_ops = { .port_set_duplex = mv88e6xxx_port_set_duplex, .port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay, .port_set_speed = mv88e6390_port_set_speed, + .port_max_speed_mode = mv88e6390_port_max_speed_mode, .port_tag_remap = mv88e6390_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, .port_set_egress_floods = mv88e6352_port_set_egress_floods, @@ -3566,6 +3573,7 @@ static const struct mv88e6xxx_ops mv88e6290_ops = { .port_set_duplex = mv88e6xxx_port_set_duplex, .port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay, .port_set_speed = mv88e6390_port_set_speed, + .port_max_speed_mode = mv88e6390_port_max_speed_mode, .port_tag_remap = mv88e6390_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, .port_set_egress_floods = mv88e6352_port_set_egress_floods, @@ -3697,6 +3705,7 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .port_set_duplex = mv88e6xxx_port_set_duplex, .port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay, .port_set_speed = mv88e6341_port_set_speed, + .port_max_speed_mode = mv88e6341_port_max_speed_mode, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, .port_set_egress_floods = mv88e6352_port_set_egress_floods, @@ -3872,6 +3881,7 @@ static const struct mv88e6xxx_ops mv88e6390_ops = { .port_set_duplex = mv88e6xxx_port_set_duplex, .port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay, .port_set_speed = mv88e6390_port_set_speed, + .port_max_speed_mode = mv88e6390_port_max_speed_mode, .port_tag_remap = mv88e6390_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, .port_set_egress_floods = mv88e6352_port_set_egress_floods, @@ -3920,6 +3930,7 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = { .port_set_duplex = mv88e6xxx_port_set_duplex, .port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay, .port_set_speed = mv88e6390x_port_set_speed, + .port_max_speed_mode = mv88e6390x_port_max_speed_mode, .port_tag_remap = mv88e6390_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, .port_set_egress_floods = mv88e6352_port_set_egress_floods, diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h @@ -377,6 +377,9 @@ struct mv88e6xxx_ops { */ int (*port_set_speed)(struct mv88e6xxx_chip *chip, int port, int speed); + /* What interface mode should be used for maximum speed? */ + phy_interface_t (*port_max_speed_mode)(int port); + int (*port_tag_remap)(struct mv88e6xxx_chip *chip, int port); int (*port_set_frame_mode)(struct mv88e6xxx_chip *chip, int port, diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c @@ -312,6 +312,14 @@ int mv88e6341_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed) return mv88e6xxx_port_set_speed(chip, port, speed, !port, true); } +phy_interface_t mv88e6341_port_max_speed_mode(int port) +{ + if (port == 5) + return PHY_INTERFACE_MODE_2500BASEX; + + return PHY_INTERFACE_MODE_NA; +} + /* Support 10, 100, 200, 1000 Mbps (e.g. 88E6352 family) */ int mv88e6352_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed) { @@ -345,6 +353,14 @@ int mv88e6390_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed) return mv88e6xxx_port_set_speed(chip, port, speed, true, true); } +phy_interface_t mv88e6390_port_max_speed_mode(int port) +{ + if (port == 9 || port == 10) + return PHY_INTERFACE_MODE_2500BASEX; + + return PHY_INTERFACE_MODE_NA; +} + /* Support 10, 100, 200, 1000, 2500, 10000 Mbps (e.g. 88E6190X) */ int mv88e6390x_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed) { @@ -360,6 +376,14 @@ int mv88e6390x_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed) return mv88e6xxx_port_set_speed(chip, port, speed, true, true); } +phy_interface_t mv88e6390x_port_max_speed_mode(int port) +{ + if (port == 9 || port == 10) + return PHY_INTERFACE_MODE_XAUI; + + return PHY_INTERFACE_MODE_NA; +} + int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port, phy_interface_t mode) { diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h @@ -285,6 +285,10 @@ int mv88e6352_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed); int mv88e6390_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed); int mv88e6390x_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed); +phy_interface_t mv88e6341_port_max_speed_mode(int port); +phy_interface_t mv88e6390_port_max_speed_mode(int port); +phy_interface_t mv88e6390x_port_max_speed_mode(int port); + int mv88e6xxx_port_set_state(struct mv88e6xxx_chip *chip, int port, u8 state); int mv88e6xxx_port_set_vlan_map(struct mv88e6xxx_chip *chip, int port, u16 map); diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -119,7 +119,7 @@ static void enic_init_affinity_hint(struct enic *enic) for (i = 0; i < enic->intr_count; i++) { if (enic_is_err_intr(enic, i) || enic_is_notify_intr(enic, i) || - (enic->msix[i].affinity_mask && + (cpumask_available(enic->msix[i].affinity_mask) && !cpumask_empty(enic->msix[i].affinity_mask))) continue; if (zalloc_cpumask_var(&enic->msix[i].affinity_mask, @@ -148,7 +148,7 @@ static void enic_set_affinity_hint(struct enic *enic) for (i = 0; i < enic->intr_count; i++) { if (enic_is_err_intr(enic, i) || enic_is_notify_intr(enic, i) || - !enic->msix[i].affinity_mask || + !cpumask_available(enic->msix[i].affinity_mask) || cpumask_empty(enic->msix[i].affinity_mask)) continue; err = irq_set_affinity_hint(enic->msix_entry[i].vector, @@ -161,7 +161,7 @@ static void enic_set_affinity_hint(struct enic *enic) for (i = 0; i < enic->wq_count; i++) { int wq_intr = enic_msix_wq_intr(enic, i); - if (enic->msix[wq_intr].affinity_mask && + if (cpumask_available(enic->msix[wq_intr].affinity_mask) && !cpumask_empty(enic->msix[wq_intr].affinity_mask)) netif_set_xps_queue(enic->netdev, enic->msix[wq_intr].affinity_mask, diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -194,6 +194,7 @@ struct hnae3_ae_dev { const struct hnae3_ae_ops *ops; struct list_head node; u32 flag; + u8 override_pci_need_reset; /* fix to stop multiple reset happening */ enum hnae3_dev_type dev_type; enum hnae3_reset_type reset_type; void *priv; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -1850,7 +1850,9 @@ static pci_ers_result_t hns3_slot_reset(struct pci_dev *pdev) /* request the reset */ if (ae_dev->ops->reset_event) { - ae_dev->ops->reset_event(pdev, NULL); + if (!ae_dev->override_pci_need_reset) + ae_dev->ops->reset_event(pdev, NULL); + return PCI_ERS_RESULT_RECOVERED; } @@ -2321,8 +2323,8 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb, if (!(bd_base_info & BIT(HNS3_RXD_L3L4P_B))) return; - if (unlikely(l234info & (BIT(HNS3_RXD_L3E_B) | BIT(HNS3_RXD_L4E_B) || - BIT(HNS3_RXD_OL3E_B) || + if (unlikely(l234info & (BIT(HNS3_RXD_L3E_B) | BIT(HNS3_RXD_L4E_B) | + BIT(HNS3_RXD_OL3E_B) | BIT(HNS3_RXD_OL4E_B)))) { u64_stats_update_begin(&ring->syncp); ring->stats.l3l4_csum_err++; @@ -2472,6 +2474,8 @@ static int hns3_add_frag(struct hns3_enet_ring *ring, struct hns3_desc *desc, desc = &ring->desc[ring->next_to_clean]; desc_cb = &ring->desc_cb[ring->next_to_clean]; bd_base_info = le32_to_cpu(desc->rx.bd_base_info); + /* make sure HW write desc complete */ + dma_rmb(); if (!(bd_base_info & BIT(HNS3_RXD_VLD_B))) return -ENXIO; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c @@ -1317,8 +1317,10 @@ pci_ers_result_t hclge_handle_hw_ras_error(struct hnae3_ae_dev *ae_dev) hclge_handle_all_ras_errors(hdev); } else { if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) || - hdev->pdev->revision < 0x21) + hdev->pdev->revision < 0x21) { + ae_dev->override_pci_need_reset = 1; return PCI_ERS_RESULT_RECOVERED; + } } if (status & HCLGE_RAS_REG_ROCEE_ERR_MASK) { @@ -1327,8 +1329,11 @@ pci_ers_result_t hclge_handle_hw_ras_error(struct hnae3_ae_dev *ae_dev) } if (status & HCLGE_RAS_REG_NFE_MASK || - status & HCLGE_RAS_REG_ROCEE_ERR_MASK) + status & HCLGE_RAS_REG_ROCEE_ERR_MASK) { + ae_dev->override_pci_need_reset = 0; return PCI_ERS_RESULT_NEED_RESET; + } + ae_dev->override_pci_need_reset = 1; return PCI_ERS_RESULT_RECOVERED; } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h @@ -392,7 +392,7 @@ #define NFP_NET_CFG_MBOX_SIMPLE_CMD 0x0 #define NFP_NET_CFG_MBOX_SIMPLE_RET 0x4 #define NFP_NET_CFG_MBOX_SIMPLE_VAL 0x8 -#define NFP_NET_CFG_MBOX_SIMPLE_LEN 0x12 +#define NFP_NET_CFG_MBOX_SIMPLE_LEN 12 #define NFP_NET_CFG_MBOX_CMD_CTAG_FILTER_ADD 1 #define NFP_NET_CFG_MBOX_CMD_CTAG_FILTER_KILL 2 diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -1663,8 +1663,11 @@ static int qede_selftest_run_loopback(struct qede_dev *edev, u32 loopback_mode) /* Wait for loopback configuration to apply */ msleep_interruptible(500); - /* prepare the loopback packet */ - pkt_size = edev->ndev->mtu + ETH_HLEN; + /* Setting max packet size to 1.5K to avoid data being split over + * multiple BDs in cases where MTU > PAGE_SIZE. + */ + pkt_size = (((edev->ndev->mtu < ETH_DATA_LEN) ? + edev->ndev->mtu : ETH_DATA_LEN) + ETH_HLEN); skb = netdev_alloc_skb(edev->ndev, pkt_size); if (!skb) { diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c @@ -258,6 +258,7 @@ static const struct pci_device_id rtl8139_pci_tbl[] = { {0x126c, 0x1211, PCI_ANY_ID, PCI_ANY_ID, 0, 0, RTL8139 }, {0x1743, 0x8139, PCI_ANY_ID, PCI_ANY_ID, 0, 0, RTL8139 }, {0x021b, 0x8139, PCI_ANY_ID, PCI_ANY_ID, 0, 0, RTL8139 }, + {0x16ec, 0xab06, PCI_ANY_ID, PCI_ANY_ID, 0, 0, RTL8139 }, #ifdef CONFIG_SH_SECUREEDGE5410 /* Bogus 8139 silicon reports 8129 without external PROM :-( */ diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c @@ -458,7 +458,7 @@ static int ravb_dmac_init(struct net_device *ndev) RCR_EFFS | RCR_ENCF | RCR_ETS0 | RCR_ESF | 0x18000000, RCR); /* Set FIFO size */ - ravb_write(ndev, TGC_TQP_AVBMODE1 | 0x00222200, TGC); + ravb_write(ndev, TGC_TQP_AVBMODE1 | 0x00112200, TGC); /* Timestamp enable */ ravb_write(ndev, TCCR_TFEN, TCCR); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c @@ -25,9 +25,24 @@ #define SYSCFG_MCU_ETH_MASK BIT(23) #define SYSCFG_MP1_ETH_MASK GENMASK(23, 16) +#define SYSCFG_PMCCLRR_OFFSET 0x40 #define SYSCFG_PMCR_ETH_CLK_SEL BIT(16) #define SYSCFG_PMCR_ETH_REF_CLK_SEL BIT(17) + +/* Ethernet PHY interface selection in register SYSCFG Configuration + *------------------------------------------ + * src |BIT(23)| BIT(22)| BIT(21)|BIT(20)| + *------------------------------------------ + * MII | 0 | 0 | 0 | 1 | + *------------------------------------------ + * GMII | 0 | 0 | 0 | 0 | + *------------------------------------------ + * RGMII | 0 | 0 | 1 | n/a | + *------------------------------------------ + * RMII | 1 | 0 | 0 | n/a | + *------------------------------------------ + */ #define SYSCFG_PMCR_ETH_SEL_MII BIT(20) #define SYSCFG_PMCR_ETH_SEL_RGMII BIT(21) #define SYSCFG_PMCR_ETH_SEL_RMII BIT(23) @@ -35,14 +50,54 @@ #define SYSCFG_MCU_ETH_SEL_MII 0 #define SYSCFG_MCU_ETH_SEL_RMII 1 +/* STM32MP1 register definitions + * + * Below table summarizes the clock requirement and clock sources for + * supported phy interface modes. + * __________________________________________________________________________ + *|PHY_MODE | Normal | PHY wo crystal| PHY wo crystal |No 125Mhz from PHY| + *| | | 25MHz | 50MHz | | + * --------------------------------------------------------------------------- + *| MII | - | eth-ck | n/a | n/a | + *| | | | | | + * --------------------------------------------------------------------------- + *| GMII | - | eth-ck | n/a | n/a | + *| | | | | | + * --------------------------------------------------------------------------- + *| RGMII | - | eth-ck | n/a | eth-ck (no pin) | + *| | | | | st,eth-clk-sel | + * --------------------------------------------------------------------------- + *| RMII | - | eth-ck | eth-ck | n/a | + *| | | | st,eth-ref-clk-sel | | + * --------------------------------------------------------------------------- + * + * BIT(17) : set this bit in RMII mode when you have PHY without crystal 50MHz + * BIT(16) : set this bit in GMII/RGMII PHY when you do not want use 125Mhz + * from PHY + *----------------------------------------------------- + * src | BIT(17) | BIT(16) | + *----------------------------------------------------- + * MII | n/a | n/a | + *----------------------------------------------------- + * GMII | n/a | st,eth-clk-sel | + *----------------------------------------------------- + * RGMII | n/a | st,eth-clk-sel | + *----------------------------------------------------- + * RMII | st,eth-ref-clk-sel | n/a | + *----------------------------------------------------- + * + */ + struct stm32_dwmac { struct clk *clk_tx; struct clk *clk_rx; struct clk *clk_eth_ck; struct clk *clk_ethstp; struct clk *syscfg_clk; - bool int_phyclk; /* Clock from RCC to drive PHY */ - u32 mode_reg; /* MAC glue-logic mode register */ + int eth_clk_sel_reg; + int eth_ref_clk_sel_reg; + int irq_pwr_wakeup; + u32 mode_reg; /* MAC glue-logic mode register */ struct regmap *regmap; u32 speed; const struct stm32_ops *ops; @@ -102,7 +157,7 @@ static int stm32mp1_clk_prepare(struct stm32_dwmac *dwmac, bool prepare) if (ret) return ret; - if (dwmac->int_phyclk) { + if (dwmac->clk_eth_ck) { ret = clk_prepare_enable(dwmac->clk_eth_ck); if (ret) { clk_disable_unprepare(dwmac->syscfg_clk); @@ -111,7 +166,7 @@ static int stm32mp1_clk_prepare(struct stm32_dwmac *dwmac, bool prepare) } } else { clk_disable_unprepare(dwmac->syscfg_clk); - if (dwmac->int_phyclk) + if (dwmac->clk_eth_ck) clk_disable_unprepare(dwmac->clk_eth_ck); } return ret; @@ -121,7 +176,7 @@ static int stm32mp1_set_mode(struct plat_stmmacenet_data *plat_dat) { struct stm32_dwmac *dwmac = plat_dat->bsp_priv; u32 reg = dwmac->mode_reg; - int val; + int val, ret; switch (plat_dat->interface) { case PHY_INTERFACE_MODE_MII: @@ -130,19 +185,22 @@ static int stm32mp1_set_mode(struct plat_stmmacenet_data *plat_dat) break; case PHY_INTERFACE_MODE_GMII: val = SYSCFG_PMCR_ETH_SEL_GMII; - if (dwmac->int_phyclk) + if (dwmac->eth_clk_sel_reg) val |= SYSCFG_PMCR_ETH_CLK_SEL; pr_debug("SYSCFG init : PHY_INTERFACE_MODE_GMII\n"); break; case PHY_INTERFACE_MODE_RMII: val = SYSCFG_PMCR_ETH_SEL_RMII; - if (dwmac->int_phyclk) + if (dwmac->eth_ref_clk_sel_reg) val |= SYSCFG_PMCR_ETH_REF_CLK_SEL; pr_debug("SYSCFG init : PHY_INTERFACE_MODE_RMII\n"); break; case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: val = SYSCFG_PMCR_ETH_SEL_RGMII; - if (dwmac->int_phyclk) + if (dwmac->eth_clk_sel_reg) val |= SYSCFG_PMCR_ETH_CLK_SEL; pr_debug("SYSCFG init : PHY_INTERFACE_MODE_RGMII\n"); break; @@ -153,6 +211,11 @@ static int stm32mp1_set_mode(struct plat_stmmacenet_data *plat_dat) return -EINVAL; } + /* Need to update PMCCLRR (clear register) */ + ret = regmap_write(dwmac->regmap, reg + SYSCFG_PMCCLRR_OFFSET, + dwmac->ops->syscfg_eth_mask); + + /* Update PMCSETR (set register) */ return regmap_update_bits(dwmac->regmap, reg, dwmac->ops->syscfg_eth_mask, val); } @@ -180,7 +243,7 @@ static int stm32mcu_set_mode(struct plat_stmmacenet_data *plat_dat) } return regmap_update_bits(dwmac->regmap, reg, - dwmac->ops->syscfg_eth_mask, val); + dwmac->ops->syscfg_eth_mask, val << 23); } static void stm32_dwmac_clk_disable(struct stm32_dwmac *dwmac) @@ -232,24 +295,29 @@ static int stm32_dwmac_parse_data(struct stm32_dwmac *dwmac, static int stm32mp1_parse_data(struct stm32_dwmac *dwmac, struct device *dev) { + struct platform_device *pdev = to_platform_device(dev); struct device_node *np = dev->of_node; + int err = 0; - dwmac->int_phyclk = of_property_read_bool(np, "st,int-phyclk"); + /* Gigabit Ethernet 125MHz clock selection. */ + dwmac->eth_clk_sel_reg = of_property_read_bool(np, "st,eth-clk-sel"); - /* Check if internal clk from RCC selected */ - if (dwmac->int_phyclk) { - /* Get ETH_CLK clocks */ - dwmac->clk_eth_ck = devm_clk_get(dev, "eth-ck"); - if (IS_ERR(dwmac->clk_eth_ck)) { - dev_err(dev, "No ETH CK clock provided...\n"); - return PTR_ERR(dwmac->clk_eth_ck); - } + /* Ethernet 50Mhz RMII clock selection */ + dwmac->eth_ref_clk_sel_reg = + of_property_read_bool(np, "st,eth-ref-clk-sel"); + + /* Get ETH_CLK clocks */ + dwmac->clk_eth_ck = devm_clk_get(dev, "eth-ck"); + if (IS_ERR(dwmac->clk_eth_ck)) { + dev_warn(dev, "No phy clock provided...\n"); + dwmac->clk_eth_ck = NULL; } /* Clock used for low power mode */ dwmac->clk_ethstp = devm_clk_get(dev, "ethstp"); if (IS_ERR(dwmac->clk_ethstp)) { - dev_err(dev, "No ETH peripheral clock provided for CStop mode ...\n"); + dev_err(dev, + "No ETH peripheral clock provided for CStop mode ...\n"); return PTR_ERR(dwmac->clk_ethstp); } @@ -260,7 +328,26 @@ static int stm32mp1_parse_data(struct stm32_dwmac *dwmac, return PTR_ERR(dwmac->syscfg_clk); } - return 0; + /* Get IRQ information early to have an ability to ask for deferred + * probe if needed before we went too far with resource allocation. + */ + dwmac->irq_pwr_wakeup = platform_get_irq_byname(pdev, + "stm32_pwr_wakeup"); + if (!dwmac->clk_eth_ck && dwmac->irq_pwr_wakeup >= 0) { + err = device_init_wakeup(&pdev->dev, true); + if (err) { + dev_err(&pdev->dev, "Failed to init wake up irq\n"); + return err; + } + err = dev_pm_set_dedicated_wake_irq(&pdev->dev, + dwmac->irq_pwr_wakeup); + if (err) { + dev_err(&pdev->dev, "Failed to set wake up irq\n"); + device_init_wakeup(&pdev->dev, false); + } + device_set_wakeup_enable(&pdev->dev, false); + } + return err; } static int stm32_dwmac_probe(struct platform_device *pdev) @@ -326,9 +413,15 @@ static int stm32_dwmac_remove(struct platform_device *pdev) struct net_device *ndev = platform_get_drvdata(pdev); struct stmmac_priv *priv = netdev_priv(ndev); int ret = stmmac_dvr_remove(&pdev->dev); + struct stm32_dwmac *dwmac = priv->plat->bsp_priv; stm32_dwmac_clk_disable(priv->plat->bsp_priv); + if (dwmac->irq_pwr_wakeup >= 0) { + dev_pm_clear_wake_irq(&pdev->dev); + device_init_wakeup(&pdev->dev, false); + } + return ret; } @@ -342,7 +435,7 @@ static int stm32mp1_suspend(struct stm32_dwmac *dwmac) clk_disable_unprepare(dwmac->clk_tx); clk_disable_unprepare(dwmac->syscfg_clk); - if (dwmac->int_phyclk) + if (dwmac->clk_eth_ck) clk_disable_unprepare(dwmac->clk_eth_ck); return ret; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -480,7 +480,7 @@ static void stmmac_get_tx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p, struct sk_buff *skb) { struct skb_shared_hwtstamps shhwtstamp; - u64 ns; + u64 ns = 0; if (!priv->hwts_tx_en) return; @@ -519,7 +519,7 @@ static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p, { struct skb_shared_hwtstamps *shhwtstamp = NULL; struct dma_desc *desc = p; - u64 ns; + u64 ns = 0; if (!priv->hwts_rx_en) return; @@ -564,8 +564,8 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) u32 snap_type_sel = 0; u32 ts_master_en = 0; u32 ts_event_en = 0; + u32 sec_inc = 0; u32 value = 0; - u32 sec_inc; bool xmac; xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -408,6 +408,9 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) /* Default to phy auto-detection */ plat->phy_addr = -1; + /* Get clk_csr from device tree */ + of_property_read_u32(np, "clk_csr", &plat->clk_csr); + /* "snps,phy-addr" is not a standard property. Mark it as deprecated * and warn of its use. Remove this when phy node support is added. */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -105,7 +105,7 @@ static int stmmac_get_time(struct ptp_clock_info *ptp, struct timespec64 *ts) struct stmmac_priv *priv = container_of(ptp, struct stmmac_priv, ptp_clock_ops); unsigned long flags; - u64 ns; + u64 ns = 0; spin_lock_irqsave(&priv->ptp_lock, flags); stmmac_get_systime(priv, priv->ptpaddr, &ns); diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c @@ -7464,6 +7464,7 @@ static int niu_add_ethtool_tcam_entry(struct niu *np, class = CLASS_CODE_USER_PROG4; break; default: + class = CLASS_CODE_UNRECOG; break; } ret = tcam_user_ip_class_set(np, class, 0, diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c @@ -2029,7 +2029,6 @@ static const struct dev_pm_ops davinci_emac_pm_ops = { .resume = davinci_emac_resume, }; -#if IS_ENABLED(CONFIG_OF) static const struct emac_platform_data am3517_emac_data = { .version = EMAC_VERSION_2, .hw_ram_addr = 0x01e20000, @@ -2046,14 +2045,13 @@ static const struct of_device_id davinci_emac_of_match[] = { {}, }; MODULE_DEVICE_TABLE(of, davinci_emac_of_match); -#endif /* davinci_emac_driver: EMAC platform driver structure */ static struct platform_driver davinci_emac_driver = { .driver = { .name = "davinci_emac", .pm = &davinci_emac_pm_ops, - .of_match_table = of_match_ptr(davinci_emac_of_match), + .of_match_table = davinci_emac_of_match, }, .probe = davinci_emac_probe, .remove = davinci_emac_remove, diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c @@ -1731,6 +1731,14 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) goto drop; } + rcu_read_lock(); + + if (unlikely(!(vxlan->dev->flags & IFF_UP))) { + rcu_read_unlock(); + atomic_long_inc(&vxlan->dev->rx_dropped); + goto drop; + } + stats = this_cpu_ptr(vxlan->dev->tstats); u64_stats_update_begin(&stats->syncp); stats->rx_packets++; @@ -1738,6 +1746,9 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) u64_stats_update_end(&stats->syncp); gro_cells_receive(&vxlan->gro_cells, skb); + + rcu_read_unlock(); + return 0; drop: @@ -2690,7 +2701,7 @@ static void vxlan_cleanup(struct timer_list *t) for (h = 0; h < FDB_HASH_SIZE; ++h) { struct hlist_node *p, *n; - spin_lock_bh(&vxlan->hash_lock); + spin_lock(&vxlan->hash_lock); hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) { struct vxlan_fdb *f = container_of(p, struct vxlan_fdb, hlist); @@ -2712,7 +2723,7 @@ static void vxlan_cleanup(struct timer_list *t) } else if (time_before(timeout, next_timer)) next_timer = timeout; } - spin_unlock_bh(&vxlan->hash_lock); + spin_unlock(&vxlan->hash_lock); } mod_timer(&vxlan->age_timer, next_timer); @@ -2767,6 +2778,8 @@ static void vxlan_uninit(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); + gro_cells_destroy(&vxlan->gro_cells); + vxlan_fdb_delete_default(vxlan, vxlan->cfg.vni); free_percpu(dev->tstats); @@ -3942,7 +3955,6 @@ static void vxlan_dellink(struct net_device *dev, struct list_head *head) vxlan_flush(vxlan, true); - gro_cells_destroy(&vxlan->gro_cells); list_del(&vxlan->next); unregister_netdevice_queue(dev, head); } diff --git a/include/linux/atalk.h b/include/linux/atalk.h @@ -161,16 +161,26 @@ extern int sysctl_aarp_resolve_time; extern int atalk_register_sysctl(void); extern void atalk_unregister_sysctl(void); #else -#define atalk_register_sysctl() do { } while(0) -#define atalk_unregister_sysctl() do { } while(0) +static inline int atalk_register_sysctl(void) +{ + return 0; +} +static inline void atalk_unregister_sysctl(void) +{ +} #endif #ifdef CONFIG_PROC_FS extern int atalk_proc_init(void); extern void atalk_proc_exit(void); #else -#define atalk_proc_init() ({ 0; }) -#define atalk_proc_exit() do { } while(0) +static inline int atalk_proc_init(void) +{ + return 0; +} +static inline void atalk_proc_exit(void) +{ +} #endif /* CONFIG_PROC_FS */ #endif /* __LINUX_ATALK_H__ */ diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h @@ -292,7 +292,7 @@ static inline int bpf_cgroup_storage_assign(struct bpf_prog *prog, static inline void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *map) {} static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( - struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { return 0; } + struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { return NULL; } static inline void bpf_cgroup_storage_free( struct bpf_cgroup_storage *storage) {} static inline int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, diff --git a/include/linux/igmp.h b/include/linux/igmp.h @@ -110,7 +110,7 @@ struct ip_mc_list { static inline int ip_mc_may_pull(struct sk_buff *skb, unsigned int len) { if (skb_transport_offset(skb) + ip_transport_len(skb) < len) - return -EINVAL; + return 0; return pskb_may_pull(skb, len); } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h @@ -327,26 +327,49 @@ struct skb_frag_struct { #endif }; +/** + * skb_frag_size - Returns the size of a skb fragment + * @frag: skb fragment + */ static inline unsigned int skb_frag_size(const skb_frag_t *frag) { return frag->size; } +/** + * skb_frag_size_set - Sets the size of a skb fragment + * @frag: skb fragment + * @size: size of fragment + */ static inline void skb_frag_size_set(skb_frag_t *frag, unsigned int size) { frag->size = size; } +/** + * skb_frag_size_add - Incrementes the size of a skb fragment by %delta + * @frag: skb fragment + * @delta: value to add + */ static inline void skb_frag_size_add(skb_frag_t *frag, int delta) { frag->size += delta; } +/** + * skb_frag_size_sub - Decrements the size of a skb fragment by %delta + * @frag: skb fragment + * @delta: value to subtract + */ static inline void skb_frag_size_sub(skb_frag_t *frag, int delta) { frag->size -= delta; } +/** + * skb_frag_must_loop - Test if %p is a high memory page + * @p: fragment's page + */ static inline bool skb_frag_must_loop(struct page *p) { #if defined(CONFIG_HIGHMEM) @@ -590,7 +613,7 @@ typedef unsigned int sk_buff_data_t; typedef unsigned char *sk_buff_data_t; #endif -/** +/** * struct sk_buff - socket buffer * @next: Next buffer in list * @prev: Previous buffer in list @@ -648,7 +671,7 @@ typedef unsigned char *sk_buff_data_t; * @csum_not_inet: use CRC32c to resolve CHECKSUM_PARTIAL * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB - * @napi_id: id of the NAPI struct this skb came from + * @napi_id: id of the NAPI struct this skb came from * @secmark: security marking * @mark: Generic packet mark * @vlan_proto: vlan encapsulation protocol @@ -883,7 +906,10 @@ struct sk_buff { #define SKB_ALLOC_RX 0x02 #define SKB_ALLOC_NAPI 0x04 -/* Returns true if the skb was allocated from PFMEMALLOC reserves */ +/** + * skb_pfmemalloc - Test if the skb was allocated from PFMEMALLOC reserves + * @skb: buffer + */ static inline bool skb_pfmemalloc(const struct sk_buff *skb) { return unlikely(skb->pfmemalloc); @@ -905,7 +931,7 @@ static inline bool skb_pfmemalloc(const struct sk_buff *skb) */ static inline struct dst_entry *skb_dst(const struct sk_buff *skb) { - /* If refdst was not refcounted, check we still are in a + /* If refdst was not refcounted, check we still are in a * rcu_read_lock section */ WARN_ON((skb->_skb_refdst & SKB_DST_NOREF) && @@ -952,6 +978,10 @@ static inline bool skb_dst_is_noref(const struct sk_buff *skb) return (skb->_skb_refdst & SKB_DST_NOREF) && skb_dst(skb); } +/** + * skb_rtable - Returns the skb &rtable + * @skb: buffer + */ static inline struct rtable *skb_rtable(const struct sk_buff *skb) { return (struct rtable *)skb_dst(skb); @@ -966,6 +996,10 @@ static inline bool skb_pkt_type_ok(u32 ptype) return ptype <= PACKET_OTHERHOST; } +/** + * skb_napi_id - Returns the skb's NAPI id + * @skb: buffer + */ static inline unsigned int skb_napi_id(const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL @@ -975,7 +1009,12 @@ static inline unsigned int skb_napi_id(const struct sk_buff *skb) #endif } -/* decrement the reference count and return true if we can free the skb */ +/** + * skb_unref - decrement the skb's reference count + * @skb: buffer + * + * Returns true if we can free the skb. + */ static inline bool skb_unref(struct sk_buff *skb) { if (unlikely(!skb)) @@ -1005,6 +1044,14 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags, int node); struct sk_buff *__build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb(void *data, unsigned int frag_size); + +/** + * alloc_skb - allocate a network buffer + * @size: size to allocate + * @priority: allocation mask + * + * This function is a convenient wrapper around __alloc_skb(). + */ static inline struct sk_buff *alloc_skb(unsigned int size, gfp_t priority) { @@ -1047,6 +1094,13 @@ static inline bool skb_fclone_busy(const struct sock *sk, fclones->skb2.sk == sk; } +/** + * alloc_skb_fclone - allocate a network buffer from fclone cache + * @size: size to allocate + * @priority: allocation mask + * + * This function is a convenient wrapper around __alloc_skb(). + */ static inline struct sk_buff *alloc_skb_fclone(unsigned int size, gfp_t priority) { @@ -4232,10 +4286,10 @@ static inline bool skb_is_gso_sctp(const struct sk_buff *skb) return skb_shinfo(skb)->gso_type & SKB_GSO_SCTP; } +/* Note: Should be called only if skb_is_gso(skb) is true */ static inline bool skb_is_gso_tcp(const struct sk_buff *skb) { - return skb_is_gso(skb) && - skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6); + return skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6); } static inline void skb_gso_reset(struct sk_buff *skb) diff --git a/include/net/request_sock.h b/include/net/request_sock.h @@ -108,7 +108,6 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener, static inline void reqsk_free(struct request_sock *req) { - /* temporary debugging */ WARN_ON_ONCE(refcount_read(&req->rsk_refcnt) != 0); req->rsk_ops->destructor(req); diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h @@ -76,6 +76,7 @@ enum rxrpc_client_trace { rxrpc_client_chan_disconnect, rxrpc_client_chan_pass, rxrpc_client_chan_unstarted, + rxrpc_client_chan_wait_failed, rxrpc_client_cleanup, rxrpc_client_count, rxrpc_client_discard, @@ -276,6 +277,7 @@ enum rxrpc_tx_point { EM(rxrpc_client_chan_disconnect, "ChDisc") \ EM(rxrpc_client_chan_pass, "ChPass") \ EM(rxrpc_client_chan_unstarted, "ChUnst") \ + EM(rxrpc_client_chan_wait_failed, "ChWtFl") \ EM(rxrpc_client_cleanup, "Clean ") \ EM(rxrpc_client_count, "Count ") \ EM(rxrpc_client_discard, "Discar") \ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c @@ -6678,17 +6678,17 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) /* valid generic load 64-bit imm */ goto next_insn; - if (insn->src_reg != BPF_PSEUDO_MAP_FD) { - verbose(env, - "unrecognized bpf_ld_imm64 insn\n"); + if (insn[0].src_reg != BPF_PSEUDO_MAP_FD || + insn[1].imm != 0) { + verbose(env, "unrecognized bpf_ld_imm64 insn\n"); return -EINVAL; } - f = fdget(insn->imm); + f = fdget(insn[0].imm); map = __bpf_map_get(f); if (IS_ERR(map)) { verbose(env, "fd %d is not pointing to valid bpf_map\n", - insn->imm); + insn[0].imm); return PTR_ERR(map); } diff --git a/kernel/sysctl.c b/kernel/sysctl.c @@ -3326,7 +3326,7 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write, #endif /* CONFIG_PROC_SYSCTL */ -#ifdef CONFIG_BPF_SYSCALL +#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_SYSCTL) static int proc_dointvec_minmax_bpf_stats(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) diff --git a/net/atm/resources.c b/net/atm/resources.c @@ -203,13 +203,9 @@ int atm_dev_ioctl(unsigned int cmd, void __user *arg, int compat) int __user *sioc_len; int __user *iobuf_len; -#ifndef CONFIG_COMPAT - compat = 0; /* Just so the compiler _knows_ */ -#endif - switch (cmd) { case ATM_GETNAMES: - if (compat) { + if (IS_ENABLED(CONFIG_COMPAT) && compat) { #ifdef CONFIG_COMPAT struct compat_atm_iobuf __user *ciobuf = arg; compat_uptr_t cbuf; @@ -253,7 +249,7 @@ int atm_dev_ioctl(unsigned int cmd, void __user *arg, int compat) break; } - if (compat) { + if (IS_ENABLED(CONFIG_COMPAT) && compat) { #ifdef CONFIG_COMPAT struct compat_atmif_sioc __user *csioc = arg; compat_uptr_t carg; @@ -417,7 +413,7 @@ int atm_dev_ioctl(unsigned int cmd, void __user *arg, int compat) } /* fall through */ default: - if (compat) { + if (IS_ENABLED(CONFIG_COMPAT) && compat) { #ifdef CONFIG_COMPAT if (!dev->ops->compat_ioctl) { error = -EINVAL; diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c @@ -16,7 +16,7 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *retval, u32 *time) { - struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = { 0 }; + struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = { NULL }; enum bpf_cgroup_storage_type stype; u64 time_start, time_spent = 0; int ret = 0; diff --git a/net/core/ethtool.c b/net/core/ethtool.c @@ -2319,9 +2319,10 @@ static int ethtool_set_tunable(struct net_device *dev, void __user *useraddr) return ret; } -static int ethtool_get_per_queue_coalesce(struct net_device *dev, - void __user *useraddr, - struct ethtool_per_queue_op *per_queue_opt) +static noinline_for_stack int +ethtool_get_per_queue_coalesce(struct net_device *dev, + void __user *useraddr, + struct ethtool_per_queue_op *per_queue_opt) { u32 bit; int ret; @@ -2349,9 +2350,10 @@ static int ethtool_get_per_queue_coalesce(struct net_device *dev, return 0; } -static int ethtool_set_per_queue_coalesce(struct net_device *dev, - void __user *useraddr, - struct ethtool_per_queue_op *per_queue_opt) +static noinline_for_stack int +ethtool_set_per_queue_coalesce(struct net_device *dev, + void __user *useraddr, + struct ethtool_per_queue_op *per_queue_opt) { u32 bit; int i, ret = 0; @@ -2405,7 +2407,7 @@ roll_back: return ret; } -static int ethtool_set_per_queue(struct net_device *dev, +static int noinline_for_stack ethtool_set_per_queue(struct net_device *dev, void __user *useraddr, u32 sub_cmd) { struct ethtool_per_queue_op per_queue_opt; diff --git a/net/core/filter.c b/net/core/filter.c @@ -2804,7 +2804,7 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) u32 off = skb_mac_header_len(skb); int ret; - if (!skb_is_gso_tcp(skb)) + if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) return -ENOTSUPP; ret = skb_cow(skb, len_diff); @@ -2845,7 +2845,7 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) u32 off = skb_mac_header_len(skb); int ret; - if (!skb_is_gso_tcp(skb)) + if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) return -ENOTSUPP; ret = skb_unclone(skb, GFP_ATOMIC); @@ -2970,7 +2970,7 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 len_diff) u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb); int ret; - if (!skb_is_gso_tcp(skb)) + if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) return -ENOTSUPP; ret = skb_cow(skb, len_diff); @@ -2999,7 +2999,7 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff) u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb); int ret; - if (!skb_is_gso_tcp(skb)) + if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) return -ENOTSUPP; ret = skb_unclone(skb, GFP_ATOMIC); diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c @@ -13,22 +13,36 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb) { struct net_device *dev = skb->dev; struct gro_cell *cell; + int res; - if (!gcells->cells || skb_cloned(skb) || netif_elide_gro(dev)) - return netif_rx(skb); + rcu_read_lock(); + if (unlikely(!(dev->flags & IFF_UP))) + goto drop; + + if (!gcells->cells || skb_cloned(skb) || netif_elide_gro(dev)) { + res = netif_rx(skb); + goto unlock; + } cell = this_cpu_ptr(gcells->cells); if (skb_queue_len(&cell->napi_skbs) > netdev_max_backlog) { +drop: atomic_long_inc(&dev->rx_dropped); kfree_skb(skb); - return NET_RX_DROP; + res = NET_RX_DROP; + goto unlock; } __skb_queue_tail(&cell->napi_skbs, skb); if (skb_queue_len(&cell->napi_skbs) == 1) napi_schedule(&cell->napi); - return NET_RX_SUCCESS; + + res = NET_RX_SUCCESS; + +unlock: + rcu_read_unlock(); + return res; } EXPORT_SYMBOL(gro_cells_receive); diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c @@ -625,6 +625,8 @@ int bpf_lwt_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len, bool ingress) /* push the encap headers and fix pointers */ skb_reset_inner_headers(skb); + skb_reset_inner_mac_header(skb); /* mac header is not yet set */ + skb_set_inner_protocol(skb, skb->protocol); skb->encapsulation = 1; skb_push(skb, len); if (ingress) diff --git a/net/core/skmsg.c b/net/core/skmsg.c @@ -554,6 +554,7 @@ static void sk_psock_destroy_deferred(struct work_struct *gc) struct sk_psock *psock = container_of(gc, struct sk_psock, gc); /* No sk_callback_lock since already detached. */ + strp_stop(&psock->parser.strp); strp_done(&psock->parser.strp); cancel_work_sync(&psock->work); diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c @@ -94,9 +94,8 @@ static void hsr_check_announce(struct net_device *hsr_dev, && (old_operstate != IF_OPER_UP)) { /* Went up */ hsr->announce_count = 0; - hsr->announce_timer.expires = jiffies + - msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); - add_timer(&hsr->announce_timer); + mod_timer(&hsr->announce_timer, + jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL)); } if ((hsr_dev->operstate != IF_OPER_UP) && (old_operstate == IF_OPER_UP)) @@ -332,6 +331,7 @@ static void hsr_announce(struct timer_list *t) { struct hsr_priv *hsr; struct hsr_port *master; + unsigned long interval; hsr = from_timer(hsr, t, announce_timer); @@ -343,18 +343,16 @@ static void hsr_announce(struct timer_list *t) hsr->protVersion); hsr->announce_count++; - hsr->announce_timer.expires = jiffies + - msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); + interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); } else { send_hsr_supervision_frame(master, HSR_TLV_LIFE_CHECK, hsr->protVersion); - hsr->announce_timer.expires = jiffies + - msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); + interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); } if (is_admin_up(master->dev)) - add_timer(&hsr->announce_timer); + mod_timer(&hsr->announce_timer, jiffies + interval); rcu_read_unlock(); } @@ -486,7 +484,7 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], res = hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER); if (res) - return res; + goto err_add_port; res = register_netdevice(hsr_dev); if (res) @@ -506,6 +504,8 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], fail: hsr_for_each_port(hsr, port) hsr_del_port(port); +err_add_port: + hsr_del_node(&hsr->self_node_db); return res; } diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c @@ -124,6 +124,18 @@ int hsr_create_self_node(struct list_head *self_node_db, return 0; } +void hsr_del_node(struct list_head *self_node_db) +{ + struct hsr_node *node; + + rcu_read_lock(); + node = list_first_or_null_rcu(self_node_db, struct hsr_node, mac_list); + rcu_read_unlock(); + if (node) { + list_del_rcu(&node->mac_list); + kfree(node); + } +} /* Allocate an hsr_node and add it to node_db. 'addr' is the node's AddressA; * seq_out is used to initialize filtering of outgoing duplicate frames diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h @@ -16,6 +16,7 @@ struct hsr_node; +void hsr_del_node(struct list_head *self_node_db); struct hsr_node *hsr_add_node(struct list_head *node_db, unsigned char addr[], u16 seq_out); struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb, diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c @@ -1024,7 +1024,7 @@ static int gue_err(struct sk_buff *skb, u32 info) int ret; len = sizeof(struct udphdr) + sizeof(struct guehdr); - if (!pskb_may_pull(skb, len)) + if (!pskb_may_pull(skb, transport_offset + len)) return -EINVAL; guehdr = (struct guehdr *)&udp_hdr(skb)[1]; @@ -1059,7 +1059,7 @@ static int gue_err(struct sk_buff *skb, u32 info) optlen = guehdr->hlen << 2; - if (!pskb_may_pull(skb, len + optlen)) + if (!pskb_may_pull(skb, transport_offset + len + optlen)) return -EINVAL; guehdr = (struct guehdr *)&udp_hdr(skb)[1]; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c @@ -515,9 +515,10 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, mtu = dst_mtu(&rt->dst) - dev->hard_header_len - sizeof(struct iphdr) - tunnel_hlen; else - mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; + mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; - skb_dst_update_pmtu(skb, mtu); + if (skb_valid_dst(skb)) + skb_dst_update_pmtu(skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { if (!skb_is_gso(skb) && @@ -530,9 +531,11 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, } #if IS_ENABLED(CONFIG_IPV6) else if (skb->protocol == htons(ETH_P_IPV6)) { - struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb); + struct rt6_info *rt6; __be32 daddr; + rt6 = skb_valid_dst(skb) ? (struct rt6_info *)skb_dst(skb) : + NULL; daddr = md ? dst : tunnel->parms.iph.daddr; if (rt6 && mtu < dst_mtu(skb_dst(skb)) && diff --git a/net/ipv4/route.c b/net/ipv4/route.c @@ -1303,6 +1303,10 @@ static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr) if (fnhe->fnhe_daddr == daddr) { rcu_assign_pointer(*fnhe_p, rcu_dereference_protected( fnhe->fnhe_next, lockdep_is_held(&fnhe_lock))); + /* set fnhe_daddr to 0 to ensure it won't bind with + * new dsts in rt_bind_exception(). + */ + fnhe->fnhe_daddr = 0; fnhe_flush_routes(fnhe); kfree_rcu(fnhe, rcu); break; @@ -2149,12 +2153,13 @@ int ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr, int our = 0; int err = -EINVAL; - if (in_dev) - our = ip_check_mc_rcu(in_dev, daddr, saddr, - ip_hdr(skb)->protocol); + if (!in_dev) + return err; + our = ip_check_mc_rcu(in_dev, daddr, saddr, + ip_hdr(skb)->protocol); /* check l3 master if no match yet */ - if ((!in_dev || !our) && netif_is_l3_slave(dev)) { + if (!our && netif_is_l3_slave(dev)) { struct in_device *l3_in_dev; l3_in_dev = __in_dev_get_rcu(skb->dev); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c @@ -216,7 +216,12 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, refcount_set(&req->rsk_refcnt, 1); tcp_sk(child)->tsoffset = tsoff; sock_rps_save_rxhash(child, skb); - inet_csk_reqsk_queue_add(sk, req, child); + if (!inet_csk_reqsk_queue_add(sk, req, child)) { + bh_unlock_sock(child); + sock_put(child); + child = NULL; + reqsk_put(req); + } } else { reqsk_free(req); } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c @@ -943,6 +943,10 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, ssize_t copied; long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); + if (IS_ENABLED(CONFIG_DEBUG_VM) && + WARN_ONCE(PageSlab(page), "page must not be a Slab one")) + return -EINVAL; + /* Wait for a connection to finish. One exception is TCP Fast Open * (passive side) where data is allowed to be sent before a connection * is fully established. @@ -1933,6 +1937,11 @@ static int tcp_inq_hint(struct sock *sk) inq = tp->rcv_nxt - tp->copied_seq; release_sock(sk); } + /* After receiving a FIN, tell the user-space to continue reading + * by returning a non-zero inq. + */ + if (inq == 0 && sock_flag(sk, SOCK_DONE)) + inq = 1; return inq; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c @@ -6498,7 +6498,13 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, af_ops->send_synack(fastopen_sk, dst, &fl, req, &foc, TCP_SYNACK_FASTOPEN); /* Add the child socket directly into the accept queue */ - inet_csk_reqsk_queue_add(sk, req, fastopen_sk); + if (!inet_csk_reqsk_queue_add(sk, req, fastopen_sk)) { + reqsk_fastopen_remove(fastopen_sk, req, false); + bh_unlock_sock(fastopen_sk); + sock_put(fastopen_sk); + reqsk_put(req); + goto drop; + } sk->sk_data_ready(sk); bh_unlock_sock(fastopen_sk); sock_put(fastopen_sk); diff --git a/net/ipv6/fou6.c b/net/ipv6/fou6.c @@ -94,7 +94,7 @@ static int gue6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, int ret; len = sizeof(struct udphdr) + sizeof(struct guehdr); - if (!pskb_may_pull(skb, len)) + if (!pskb_may_pull(skb, transport_offset + len)) return -EINVAL; guehdr = (struct guehdr *)&udp_hdr(skb)[1]; @@ -129,7 +129,7 @@ static int gue6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, optlen = guehdr->hlen << 2; - if (!pskb_may_pull(skb, len + optlen)) + if (!pskb_may_pull(skb, transport_offset + len + optlen)) return -EINVAL; guehdr = (struct guehdr *)&udp_hdr(skb)[1]; diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c @@ -353,7 +353,7 @@ static int rxrpc_get_client_conn(struct rxrpc_sock *rx, * normally have to take channel_lock but we do this before anyone else * can see the connection. */ - list_add_tail(&call->chan_wait_link, &candidate->waiting_calls); + list_add(&call->chan_wait_link, &candidate->waiting_calls); if (cp->exclusive) { call->conn = candidate; @@ -432,7 +432,7 @@ found_extant_conn: call->conn = conn; call->security_ix = conn->security_ix; call->service_id = conn->service_id; - list_add(&call->chan_wait_link, &conn->waiting_calls); + list_add_tail(&call->chan_wait_link, &conn->waiting_calls); spin_unlock(&conn->channel_lock); _leave(" = 0 [extant %d]", conn->debug_id); return 0; @@ -704,6 +704,7 @@ int rxrpc_connect_call(struct rxrpc_sock *rx, ret = rxrpc_wait_for_channel(call, gfp); if (ret < 0) { + trace_rxrpc_client(call->conn, ret, rxrpc_client_chan_wait_failed); rxrpc_disconnect_client_call(call); goto out; } @@ -774,16 +775,22 @@ static void rxrpc_set_client_reap_timer(struct rxrpc_net *rxnet) */ void rxrpc_disconnect_client_call(struct rxrpc_call *call) { - unsigned int channel = call->cid & RXRPC_CHANNELMASK; struct rxrpc_connection *conn = call->conn; - struct rxrpc_channel *chan = &conn->channels[channel]; + struct rxrpc_channel *chan = NULL; struct rxrpc_net *rxnet = conn->params.local->rxnet; + unsigned int channel = -1; + u32 cid; + spin_lock(&conn->channel_lock); + + cid = call->cid; + if (cid) { + channel = cid & RXRPC_CHANNELMASK; + chan = &conn->channels[channel]; + } trace_rxrpc_client(conn, channel, rxrpc_client_chan_disconnect); call->conn = NULL; - spin_lock(&conn->channel_lock); - /* Calls that have never actually been assigned a channel can simply be * discarded. If the conn didn't get used either, it will follow * immediately unless someone else grabs it in the meantime. @@ -807,7 +814,10 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call) goto out; } - ASSERTCMP(rcu_access_pointer(chan->call), ==, call); + if (rcu_access_pointer(chan->call) != call) { + spin_unlock(&conn->channel_lock); + BUG(); + } /* If a client call was exposed to the world, we save the result for * retransmission. diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c @@ -201,14 +201,9 @@ static void tunnel_key_release_params(struct tcf_tunnel_key_params *p) { if (!p) return; - if (p->tcft_action == TCA_TUNNEL_KEY_ACT_SET) { -#ifdef CONFIG_DST_CACHE - struct ip_tunnel_info *info = &p->tcft_enc_metadata->u.tun_info; - - dst_cache_destroy(&info->dst_cache); -#endif + if (p->tcft_action == TCA_TUNNEL_KEY_ACT_SET) dst_release(&p->tcft_enc_metadata->dst); - } + kfree_rcu(p, rcu); } @@ -338,7 +333,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, &metadata->u.tun_info, opts_len, extack); if (ret < 0) - goto release_dst_cache; + goto release_tun_meta; } metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX; @@ -354,14 +349,14 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, &act_tunnel_key_ops, bind, true); if (ret) { NL_SET_ERR_MSG(extack, "Cannot create TC IDR"); - goto release_dst_cache; + goto release_tun_meta; } ret = ACT_P_CREATED; } else if (!ovr) { NL_SET_ERR_MSG(extack, "TC IDR already exists"); ret = -EEXIST; - goto release_dst_cache; + goto release_tun_meta; } t = to_tunnel_key(*a); @@ -371,7 +366,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, NL_SET_ERR_MSG(extack, "Cannot allocate tunnel key parameters"); ret = -ENOMEM; exists = true; - goto release_dst_cache; + goto release_tun_meta; } params_new->tcft_action = parm->t_action; params_new->tcft_enc_metadata = metadata; @@ -388,12 +383,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, return ret; -release_dst_cache: -#ifdef CONFIG_DST_CACHE - if (metadata) - dst_cache_destroy(&metadata->u.tun_info.dst_cache); release_tun_meta: -#endif if (metadata) dst_release(&metadata->dst); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c @@ -470,10 +470,9 @@ static void __tcf_chain_put(struct tcf_chain *chain, bool by_act, { struct tcf_block *block = chain->block; const struct tcf_proto_ops *tmplt_ops; - bool is_last, free_block = false; + bool free_block = false; unsigned int refcnt; void *tmplt_priv; - u32 chain_index; mutex_lock(&block->lock); if (explicitly_created) { @@ -492,23 +491,21 @@ static void __tcf_chain_put(struct tcf_chain *chain, bool by_act, * save these to temporary variables. */ refcnt = --chain->refcnt; - is_last = refcnt - chain->action_refcnt == 0; tmplt_ops = chain->tmplt_ops; tmplt_priv = chain->tmplt_priv; - chain_index = chain->index; - - if (refcnt == 0) - free_block = tcf_chain_detach(chain); - mutex_unlock(&block->lock); /* The last dropped non-action reference will trigger notification. */ - if (is_last && !by_act) { - tc_chain_notify_delete(tmplt_ops, tmplt_priv, chain_index, + if (refcnt - chain->action_refcnt == 0 && !by_act) { + tc_chain_notify_delete(tmplt_ops, tmplt_priv, chain->index, block, NULL, 0, 0, false); /* Last reference to chain, no need to lock. */ chain->flushing = false; } + if (refcnt == 0) + free_block = tcf_chain_detach(chain); + mutex_unlock(&block->lock); + if (refcnt == 0) { tc_chain_tmplt_del(tmplt_ops, tmplt_priv); tcf_chain_destroy(chain, free_block); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c @@ -1348,46 +1348,46 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, if (err < 0) goto errout; - if (!handle) { - handle = 1; - err = idr_alloc_u32(&head->handle_idr, fnew, &handle, - INT_MAX, GFP_KERNEL); - } else if (!fold) { - /* user specifies a handle and it doesn't exist */ - err = idr_alloc_u32(&head->handle_idr, fnew, &handle, - handle, GFP_KERNEL); - } - if (err) - goto errout; - fnew->handle = handle; - if (tb[TCA_FLOWER_FLAGS]) { fnew->flags = nla_get_u32(tb[TCA_FLOWER_FLAGS]); if (!tc_flags_valid(fnew->flags)) { err = -EINVAL; - goto errout_idr; + goto errout; } } err = fl_set_parms(net, tp, fnew, mask, base, tb, tca[TCA_RATE], ovr, tp->chain->tmplt_priv, extack); if (err) - goto errout_idr; + goto errout; err = fl_check_assign_mask(head, fnew, fold, mask); if (err) - goto errout_idr; + goto errout; + + if (!handle) { + handle = 1; + err = idr_alloc_u32(&head->handle_idr, fnew, &handle, + INT_MAX, GFP_KERNEL); + } else if (!fold) { + /* user specifies a handle and it doesn't exist */ + err = idr_alloc_u32(&head->handle_idr, fnew, &handle, + handle, GFP_KERNEL); + } + if (err) + goto errout_mask; + fnew->handle = handle; if (!fold && __fl_lookup(fnew->mask, &fnew->mkey)) { err = -EEXIST; - goto errout_mask; + goto errout_idr; } err = rhashtable_insert_fast(&fnew->mask->ht, &fnew->ht_node, fnew->mask->filter_ht_params); if (err) - goto errout_mask; + goto errout_idr; if (!tc_skip_hw(fnew->flags)) { err = fl_hw_replace_filter(tp, fnew, extack); @@ -1426,12 +1426,13 @@ errout_mask_ht: rhashtable_remove_fast(&fnew->mask->ht, &fnew->ht_node, fnew->mask->filter_ht_params); -errout_mask: - fl_mask_put(head, fnew->mask, false); - errout_idr: if (!fold) idr_remove(&head->handle_idr, fnew->handle); + +errout_mask: + fl_mask_put(head, fnew->mask, false); + errout: tcf_exts_destroy(&fnew->exts); kfree(fnew); diff --git a/net/sctp/auth.c b/net/sctp/auth.c @@ -471,12 +471,6 @@ int sctp_auth_init_hmacs(struct sctp_endpoint *ep, gfp_t gfp) struct crypto_shash *tfm = NULL; __u16 id; - /* If AUTH extension is disabled, we are done */ - if (!ep->auth_enable) { - ep->auth_hmacs = NULL; - return 0; - } - /* If the transforms are already allocated, we are done */ if (ep->auth_hmacs) return 0; diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c @@ -107,6 +107,13 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, auth_chunks->param_hdr.length = htons(sizeof(struct sctp_paramhdr) + 2); } + + /* Allocate and initialize transorms arrays for supported + * HMACs. + */ + err = sctp_auth_init_hmacs(ep, gfp); + if (err) + goto nomem; } /* Initialize the base structure. */ @@ -150,15 +157,10 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, INIT_LIST_HEAD(&ep->endpoint_shared_keys); null_key = sctp_auth_shkey_create(0, gfp); if (!null_key) - goto nomem; + goto nomem_shkey; list_add(&null_key->key_list, &ep->endpoint_shared_keys); - /* Allocate and initialize transorms arrays for supported HMACs. */ - err = sctp_auth_init_hmacs(ep, gfp); - if (err) - goto nomem_hmacs; - /* Add the null key to the endpoint shared keys list and * set the hmcas and chunks pointers. */ @@ -169,8 +171,8 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, return ep; -nomem_hmacs: - sctp_auth_destroy_keys(&ep->endpoint_shared_keys); +nomem_shkey: + sctp_auth_destroy_hmacs(ep->auth_hmacs); nomem: /* Free all allocations */ kfree(auth_hmacs); diff --git a/net/sctp/socket.c b/net/sctp/socket.c @@ -102,9 +102,9 @@ static int sctp_send_asconf(struct sctp_association *asoc, struct sctp_chunk *chunk); static int sctp_do_bind(struct sock *, union sctp_addr *, int); static int sctp_autobind(struct sock *sk); -static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, - struct sctp_association *assoc, - enum sctp_socket_type type); +static int sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, + struct sctp_association *assoc, + enum sctp_socket_type type); static unsigned long sctp_memory_pressure; static atomic_long_t sctp_memory_allocated; @@ -4891,7 +4891,11 @@ static struct sock *sctp_accept(struct sock *sk, int flags, int *err, bool kern) /* Populate the fields of the newsk from the oldsk and migrate the * asoc to the newsk. */ - sctp_sock_migrate(sk, newsk, asoc, SCTP_SOCKET_TCP); + error = sctp_sock_migrate(sk, newsk, asoc, SCTP_SOCKET_TCP); + if (error) { + sk_common_release(newsk); + newsk = NULL; + } out: release_sock(sk); @@ -5639,7 +5643,12 @@ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp) /* Populate the fields of the newsk from the oldsk and migrate the * asoc to the newsk. */ - sctp_sock_migrate(sk, sock->sk, asoc, SCTP_SOCKET_UDP_HIGH_BANDWIDTH); + err = sctp_sock_migrate(sk, sock->sk, asoc, + SCTP_SOCKET_UDP_HIGH_BANDWIDTH); + if (err) { + sock_release(sock); + sock = NULL; + } *sockp = sock; @@ -9171,9 +9180,9 @@ static inline void sctp_copy_descendant(struct sock *sk_to, /* Populate the fields of the newsk from the oldsk and migrate the assoc * and its messages to the newsk. */ -static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, - struct sctp_association *assoc, - enum sctp_socket_type type) +static int sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, + struct sctp_association *assoc, + enum sctp_socket_type type) { struct sctp_sock *oldsp = sctp_sk(oldsk); struct sctp_sock *newsp = sctp_sk(newsk); @@ -9182,6 +9191,7 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, struct sk_buff *skb, *tmp; struct sctp_ulpevent *event; struct sctp_bind_hashbucket *head; + int err; /* Migrate socket buffer sizes and all the socket level options to the * new socket. @@ -9210,8 +9220,20 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, /* Copy the bind_addr list from the original endpoint to the new * endpoint so that we can handle restarts properly */ - sctp_bind_addr_dup(&newsp->ep->base.bind_addr, - &oldsp->ep->base.bind_addr, GFP_KERNEL); + err = sctp_bind_addr_dup(&newsp->ep->base.bind_addr, + &oldsp->ep->base.bind_addr, GFP_KERNEL); + if (err) + return err; + + /* New ep's auth_hmacs should be set if old ep's is set, in case + * that net->sctp.auth_enable has been changed to 0 by users and + * new ep's auth_hmacs couldn't be set in sctp_endpoint_init(). + */ + if (oldsp->ep->auth_hmacs) { + err = sctp_auth_init_hmacs(newsp->ep, GFP_KERNEL); + if (err) + return err; + } /* Move any messages in the old socket's receive queue that are for the * peeled off association to the new socket's receive queue. @@ -9296,6 +9318,8 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, } release_sock(newsk); + + return 0; } diff --git a/net/sctp/stream.c b/net/sctp/stream.c @@ -230,8 +230,6 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, for (i = 0; i < stream->outcnt; i++) SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN; - sched->init(stream); - in: sctp_stream_interleave_init(stream); if (!incnt) diff --git a/net/tipc/socket.c b/net/tipc/socket.c @@ -1333,7 +1333,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) if (unlikely(!dest)) { dest = &tsk->peer; - if (!syn || dest->family != AF_TIPC) + if (!syn && dest->family != AF_TIPC) return -EDESTADDRREQ; } diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c @@ -662,6 +662,8 @@ static int virtio_transport_reset(struct vsock_sock *vsk, */ static int virtio_transport_reset_no_sock(struct virtio_vsock_pkt *pkt) { + const struct virtio_transport *t; + struct virtio_vsock_pkt *reply; struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_RST, .type = le16_to_cpu(pkt->hdr.type), @@ -672,15 +674,21 @@ static int virtio_transport_reset_no_sock(struct virtio_vsock_pkt *pkt) if (le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST) return 0; - pkt = virtio_transport_alloc_pkt(&info, 0, - le64_to_cpu(pkt->hdr.dst_cid), - le32_to_cpu(pkt->hdr.dst_port), - le64_to_cpu(pkt->hdr.src_cid), - le32_to_cpu(pkt->hdr.src_port)); - if (!pkt) + reply = virtio_transport_alloc_pkt(&info, 0, + le64_to_cpu(pkt->hdr.dst_cid), + le32_to_cpu(pkt->hdr.dst_port), + le64_to_cpu(pkt->hdr.src_cid), + le32_to_cpu(pkt->hdr.src_port)); + if (!reply) return -ENOMEM; - return virtio_transport_get_ops()->send_pkt(pkt); + t = virtio_transport_get_ops(); + if (!t) { + virtio_transport_free_pkt(reply); + return -ENOTCONN; + } + + return t->send_pkt(reply); } static void virtio_transport_wait_close(struct sock *sk, long timeout) diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c @@ -820,8 +820,12 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr, sock->state = SS_CONNECTED; rc = 0; out_put_neigh: - if (rc) + if (rc) { + read_lock_bh(&x25_list_lock); x25_neigh_put(x25->neighbour); + x25->neighbour = NULL; + read_unlock_bh(&x25_list_lock); + } out_put_route: x25_route_put(rt); out: diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c @@ -407,6 +407,10 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) if (sxdp->sxdp_family != AF_XDP) return -EINVAL; + flags = sxdp->sxdp_flags; + if (flags & ~(XDP_SHARED_UMEM | XDP_COPY | XDP_ZEROCOPY)) + return -EINVAL; + mutex_lock(&xs->mutex); if (xs->dev) { err = -EBUSY; @@ -425,7 +429,6 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) } qid = sxdp->sxdp_queue_id; - flags = sxdp->sxdp_flags; if (flags & XDP_SHARED_UMEM) { struct xdp_sock *umem_xs; diff --git a/net/xdp/xsk_diag.c b/net/xdp/xsk_diag.c @@ -68,9 +68,9 @@ static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb) err = nla_put(nlskb, XDP_DIAG_UMEM, sizeof(du), &du); if (!err && umem->fq) - err = xsk_diag_put_ring(xs->tx, XDP_DIAG_UMEM_FILL_RING, nlskb); + err = xsk_diag_put_ring(umem->fq, XDP_DIAG_UMEM_FILL_RING, nlskb); if (!err && umem->cq) { - err = xsk_diag_put_ring(xs->tx, XDP_DIAG_UMEM_COMPLETION_RING, + err = xsk_diag_put_ring(umem->cq, XDP_DIAG_UMEM_COMPLETION_RING, nlskb); } return err; diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h @@ -174,8 +174,8 @@ static inline bool xskq_is_valid_desc(struct xsk_queue *q, struct xdp_desc *d) if (!xskq_is_valid_addr(q, d->addr)) return false; - if (((d->addr + d->len) & q->chunk_mask) != - (d->addr & q->chunk_mask)) { + if (((d->addr + d->len) & q->chunk_mask) != (d->addr & q->chunk_mask) || + d->options) { q->invalid_descs++; return false; } diff --git a/samples/bpf/hbm.c b/samples/bpf/hbm.c @@ -18,7 +18,7 @@ * Default is /hbm1 * -r <rate> Rate limit in Mbps * -s Get HBM stats (marked, dropped, etc.) - * -t <time> Exit after specified seconds (deault is 0) + * -t <time> Exit after specified seconds (default is 0) * -w Work conserving flag. cgroup can increase its bandwidth * beyond the rate limit specified while there is available * bandwidth. Current implementation assumes there is only @@ -376,7 +376,7 @@ static void Usage(void) " Default is /hbm1\n" " -r <rate> Rate in Mbps\n" " -s Update HBM stats\n" - " -t <time> Exit after specified seconds (deault is 0)\n" + " -t <time> Exit after specified seconds (default is 0)\n" " -w Work conserving flag. cgroup can increase\n" " bandwidth beyond the rate limit specified\n" " while there is available bandwidth. Current\n" diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile @@ -147,7 +147,8 @@ endif TARGETS = $(CMD_TARGETS) -all: fixdep all_cmd +all: fixdep + $(Q)$(MAKE) all_cmd all_cmd: $(CMD_TARGETS) check diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c @@ -838,6 +838,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) if (IS_ERR(obj->btf) || btf__load(obj->btf)) { pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n", BTF_ELF_SEC, PTR_ERR(obj->btf)); + if (!IS_ERR(obj->btf)) + btf__free(obj->btf); obj->btf = NULL; } } else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) { diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile @@ -153,6 +153,9 @@ endif endif endif +TEST_PROGS_CFLAGS := -I. -I$(OUTPUT) +TEST_VERIFIER_CFLAGS := -I. -I$(OUTPUT) -Iverifier + ifneq ($(SUBREG_CODEGEN),) ALU32_BUILD_DIR = $(OUTPUT)/alu32 TEST_CUSTOM_PROGS += $(ALU32_BUILD_DIR)/test_progs_32 @@ -162,13 +165,15 @@ $(ALU32_BUILD_DIR): $(ALU32_BUILD_DIR)/urandom_read: $(OUTPUT)/urandom_read cp $< $@ -$(ALU32_BUILD_DIR)/test_progs_32: test_progs.c $(ALU32_BUILD_DIR) \ +$(ALU32_BUILD_DIR)/test_progs_32: test_progs.c $(OUTPUT)/libbpf.a\ + $(ALU32_BUILD_DIR) \ $(ALU32_BUILD_DIR)/urandom_read - $(CC) $(CFLAGS) -o $(ALU32_BUILD_DIR)/test_progs_32 $< \ - trace_helpers.c prog_tests/*.c $(OUTPUT)/libbpf.a $(LDLIBS) + $(CC) $(TEST_PROGS_CFLAGS) $(CFLAGS) \ + -o $(ALU32_BUILD_DIR)/test_progs_32 \ + test_progs.c trace_helpers.c prog_tests/*.c \ + $(OUTPUT)/libbpf.a $(LDLIBS) $(ALU32_BUILD_DIR)/test_progs_32: $(PROG_TESTS_H) -$(ALU32_BUILD_DIR)/test_progs_32: CFLAGS += -I$(OUTPUT) $(ALU32_BUILD_DIR)/test_progs_32: prog_tests/*.c $(ALU32_BUILD_DIR)/%.o: progs/%.c $(ALU32_BUILD_DIR) \ @@ -202,12 +207,16 @@ endif PROG_TESTS_H := $(OUTPUT)/prog_tests/tests.h $(OUTPUT)/test_progs: $(PROG_TESTS_H) -$(OUTPUT)/test_progs: CFLAGS += -I$(OUTPUT) +$(OUTPUT)/test_progs: CFLAGS += $(TEST_PROGS_CFLAGS) $(OUTPUT)/test_progs: prog_tests/*.c +PROG_TESTS_DIR = $(OUTPUT)/prog_tests +$(PROG_TESTS_DIR): + mkdir -p $@ + PROG_TESTS_FILES := $(wildcard prog_tests/*.c) -$(PROG_TESTS_H): $(PROG_TESTS_FILES) - $(shell ( cd prog_tests/ +$(PROG_TESTS_H): $(PROG_TESTS_DIR) $(PROG_TESTS_FILES) + $(shell ( cd prog_tests/; \ echo '/* Generated header, do not edit */'; \ echo '#ifdef DECLARE'; \ ls *.c 2> /dev/null | \ @@ -221,11 +230,15 @@ $(PROG_TESTS_H): $(PROG_TESTS_FILES) VERIFIER_TESTS_H := $(OUTPUT)/verifier/tests.h $(OUTPUT)/test_verifier: $(VERIFIER_TESTS_H) -$(OUTPUT)/test_verifier: CFLAGS += -I$(OUTPUT) +$(OUTPUT)/test_verifier: CFLAGS += $(TEST_VERIFIER_CFLAGS) + +VERIFIER_TESTS_DIR = $(OUTPUT)/verifier +$(VERIFIER_TESTS_DIR): + mkdir -p $@ VERIFIER_TEST_FILES := $(wildcard verifier/*.c) -$(OUTPUT)/verifier/tests.h: $(VERIFIER_TEST_FILES) - $(shell ( cd verifier/ +$(OUTPUT)/verifier/tests.h: $(VERIFIER_TESTS_DIR) $(VERIFIER_TEST_FILES) + $(shell ( cd verifier/; \ echo '/* Generated header, do not edit */'; \ echo '#ifdef FILL_ARRAY'; \ ls *.c 2> /dev/null | \ diff --git a/tools/testing/selftests/bpf/prog_tests/signal_pending.c b/tools/testing/selftests/bpf/prog_tests/signal_pending.c @@ -12,7 +12,7 @@ static void test_signal_pending_by_type(enum bpf_prog_type prog_type) struct itimerval timeo = { .it_value.tv_usec = 100000, /* 100ms */ }; - __u32 duration, retval; + __u32 duration = 0, retval; int prog_fd; int err; int i; diff --git a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh @@ -78,6 +78,8 @@ TEST_STATUS=0 TESTS_SUCCEEDED=0 TESTS_FAILED=0 +TMPFILE="" + process_test_results() { if [[ "${TEST_STATUS}" -eq 0 ]] ; then @@ -147,7 +149,6 @@ setup() ip -netns ${NS2} -6 addr add ${IPv6_7}/128 nodad dev veth7 ip -netns ${NS3} -6 addr add ${IPv6_8}/128 nodad dev veth8 - ip -netns ${NS1} link set dev veth1 up ip -netns ${NS2} link set dev veth2 up ip -netns ${NS2} link set dev veth3 up @@ -205,7 +206,7 @@ setup() # configure IPv4 GRE device in NS3, and a route to it via the "bottom" route ip -netns ${NS3} tunnel add gre_dev mode gre remote ${IPv4_1} local ${IPv4_GRE} ttl 255 ip -netns ${NS3} link set gre_dev up - ip -netns ${NS3} addr add ${IPv4_GRE} nodad dev gre_dev + ip -netns ${NS3} addr add ${IPv4_GRE} dev gre_dev ip -netns ${NS1} route add ${IPv4_GRE}/32 dev veth5 via ${IPv4_6} ip -netns ${NS2} route add ${IPv4_GRE}/32 dev veth7 via ${IPv4_8} @@ -222,12 +223,18 @@ setup() ip netns exec ${NS2} sysctl -wq net.ipv4.conf.all.rp_filter=0 ip netns exec ${NS3} sysctl -wq net.ipv4.conf.all.rp_filter=0 + TMPFILE=$(mktemp /tmp/test_lwt_ip_encap.XXXXXX) + sleep 1 # reduce flakiness set +e } cleanup() { + if [ -f ${TMPFILE} ] ; then + rm ${TMPFILE} + fi + ip netns del ${NS1} 2> /dev/null ip netns del ${NS2} 2> /dev/null ip netns del ${NS3} 2> /dev/null @@ -278,6 +285,46 @@ test_ping() fi } +test_gso() +{ + local readonly PROTO=$1 + local readonly PKT_SZ=5000 + local IP_DST="" + : > ${TMPFILE} # trim the capture file + + # check that nc is present + command -v nc >/dev/null 2>&1 || \ + { echo >&2 "nc is not available: skipping TSO tests"; return; } + + # listen on IPv*_DST, capture TCP into $TMPFILE + if [ "${PROTO}" == "IPv4" ] ; then + IP_DST=${IPv4_DST} + ip netns exec ${NS3} bash -c \ + "nc -4 -l -s ${IPv4_DST} -p 9000 > ${TMPFILE} &" + elif [ "${PROTO}" == "IPv6" ] ; then + IP_DST=${IPv6_DST} + ip netns exec ${NS3} bash -c \ + "nc -6 -l -s ${IPv6_DST} -p 9000 > ${TMPFILE} &" + RET=$? + else + echo " test_gso: unknown PROTO: ${PROTO}" + TEST_STATUS=1 + fi + sleep 1 # let nc start listening + + # send a packet larger than MTU + ip netns exec ${NS1} bash -c \ + "dd if=/dev/zero bs=$PKT_SZ count=1 > /dev/tcp/${IP_DST}/9000 2>/dev/null" + sleep 2 # let the packet get delivered + + # verify we received all expected bytes + SZ=$(stat -c %s ${TMPFILE}) + if [ "$SZ" != "$PKT_SZ" ] ; then + echo " test_gso failed: ${PROTO}" + TEST_STATUS=1 + fi +} + test_egress() { local readonly ENCAP=$1 @@ -307,6 +354,8 @@ test_egress() fi test_ping IPv4 0 test_ping IPv6 0 + test_gso IPv4 + test_gso IPv6 # a negative test: remove routes to GRE devices: ping fails remove_routes_to_gredev @@ -350,6 +399,7 @@ test_ingress() ip -netns ${NS2} -6 route add ${IPv6_DST} encap bpf in obj test_lwt_ip_encap.o sec encap_gre6 dev veth2 else echo "FAIL: unknown encap ${ENCAP}" + TEST_STATUS=1 fi test_ping IPv4 0 test_ping IPv6 0 diff --git a/tools/testing/selftests/bpf/verifier/ld_imm64.c b/tools/testing/selftests/bpf/verifier/ld_imm64.c @@ -122,7 +122,7 @@ .insns = { BPF_MOV64_IMM(BPF_REG_1, 0), BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, BPF_REG_1, 0, 1), - BPF_RAW_INSN(0, 0, 0, 0, 1), + BPF_RAW_INSN(0, 0, 0, 0, 0), BPF_EXIT_INSN(), }, .errstr = "not pointing to valid bpf_map", @@ -139,3 +139,16 @@ .errstr = "invalid bpf_ld_imm64 insn", .result = REJECT, }, +{ + "test14 ld_imm64: reject 2nd imm != 0", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, BPF_REG_1, + BPF_PSEUDO_MAP_FD, 0, 0), + BPF_RAW_INSN(0, 0, 0, 0, 0xfefefe), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_48b = { 1 }, + .errstr = "unrecognized bpf_ld_imm64 insn", + .result = REJECT, +},