diff options
121 files changed, 1932 insertions, 1023 deletions
diff --git a/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml b/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml index f197d9b516bb..97dd1a7c5ed2 100644 --- a/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml +++ b/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml @@ -17,6 +17,7 @@ properties: compatible: oneOf: - enum: + - fsl,imx95-flexcan - fsl,imx93-flexcan - fsl,imx8qm-flexcan - fsl,imx8mp-flexcan @@ -39,9 +40,6 @@ properties: - fsl,imx6sx-flexcan - const: fsl,imx6q-flexcan - items: - - const: fsl,imx95-flexcan - - const: fsl,imx93-flexcan - - items: - enum: - fsl,ls1028ar1-flexcan - const: fsl,lx2160ar1-flexcan @@ -80,6 +78,10 @@ properties: node then controller is assumed to be little endian. If this property is present then controller is assumed to be big endian. + can-transceiver: + $ref: can-transceiver.yaml# + unevaluatedProperties: false + fsl,stop-mode: description: | Register bits of stop mode control. diff --git a/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml b/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml index 7e405ad96eb2..ea979bcae1d6 100644 --- a/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml +++ b/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml @@ -92,6 +92,10 @@ properties: Built-in switch of the MT7988 SoC const: mediatek,mt7988-switch + - description: + Built-in switch of the Airoha EN7581 SoC + const: airoha,en7581-switch + reg: maxItems: 1 @@ -284,7 +288,9 @@ allOf: - if: properties: compatible: - const: mediatek,mt7988-switch + enum: + - mediatek,mt7988-switch + - airoha,en7581-switch then: $ref: "#/$defs/mt7530-dsa-port" properties: diff --git a/Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.yaml b/Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.yaml index b99d7a694b70..51cf574249be 100644 --- a/Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.yaml +++ b/Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.yaml @@ -52,6 +52,25 @@ properties: allOf: - $ref: dsa.yaml#/$defs/ethernet-ports +patternProperties: + "^(ethernet-)?ports$": + additionalProperties: true + patternProperties: + "^(ethernet-)?port@6$": + allOf: + - if: + properties: + phy-mode: + contains: + enum: + - rgmii + then: + properties: + rx-internal-delay-ps: + $ref: "#/$defs/internal-delay-ps" + tx-internal-delay-ps: + $ref: "#/$defs/internal-delay-ps" + # This checks if reg is a chipselect so the device is on an SPI # bus, the if-clause will fail if reg is a tuple such as for a # platform device. @@ -67,6 +86,15 @@ required: - compatible - reg +$defs: + internal-delay-ps: + description: + Disable tunable delay lines using 0 ps, or enable them and select + the phase between 1400 ps and 2000 ps in increments of 300 ps. + default: 2000 + enum: + [0, 1400, 1700, 2000] + unevaluatedProperties: false examples: @@ -108,6 +136,8 @@ examples: reg = <6>; ethernet = <&gmac1>; phy-mode = "rgmii"; + rx-internal-delay-ps = <0>; + tx-internal-delay-ps = <0>; fixed-link { speed = <1000>; full-duplex; @@ -150,6 +180,8 @@ examples: ethernet-port@6 { reg = <6>; ethernet = <&enet0>; + rx-internal-delay-ps = <0>; + tx-internal-delay-ps = <0>; phy-mode = "rgmii"; fixed-link { speed = <1000>; diff --git a/Documentation/netlink/specs/rt_link.yaml b/Documentation/netlink/specs/rt_link.yaml index de08c12fd56f..0c4d5d40cae9 100644 --- a/Documentation/netlink/specs/rt_link.yaml +++ b/Documentation/netlink/specs/rt_link.yaml @@ -903,6 +903,22 @@ definitions: - cfm-config - cfm-status - mst + - + name: netkit-policy + type: enum + entries: + - + name: forward + value: 0 + - + name: blackhole + value: 2 + - + name: netkit-mode + type: enum + entries: + - name: l2 + - name: l3 attribute-sets: - @@ -2109,6 +2125,28 @@ attribute-sets: - name: id type: u32 + - + name: linkinfo-netkit-attrs + name-prefix: ifla-netkit- + attributes: + - + name: peer-info + type: binary + - + name: primary + type: u8 + - + name: policy + type: u32 + enum: netkit-policy + - + name: peer-policy + type: u32 + enum: netkit-policy + - + name: mode + type: u32 + enum: netkit-mode sub-messages: - @@ -2147,6 +2185,9 @@ sub-messages: - value: vrf attribute-set: linkinfo-vrf-attrs + - + value: netkit + attribute-set: linkinfo-netkit-attrs - name: linkinfo-member-data-msg formats: diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 3616389c8c2d..eacf8983e230 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -2362,6 +2362,20 @@ ra_honor_pio_life - BOOLEAN Default: 0 (disabled) +ra_honor_pio_pflag - BOOLEAN + The Prefix Information Option P-flag indicates the network can + allocate a unique IPv6 prefix per client using DHCPv6-PD. + This sysctl can be enabled when a userspace DHCPv6-PD client + is running to cause the P-flag to take effect: i.e. the + P-flag suppresses any effects of the A-flag within the same + PIO. For a given PIO, P=1 and A=1 is treated as A=0. + + - If disabled, the P-flag is ignored. + - If enabled, the P-flag will disable SLAAC autoconfiguration + for the given Prefix Information Option. + + Default: 0 (disabled) + accept_ra_rt_info_min_plen - INTEGER Minimum prefix length of Route Information in RA. diff --git a/MAINTAINERS b/MAINTAINERS index 82f19f0f0752..1a7ea5c7c710 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14491,7 +14491,7 @@ MELLANOX ETHERNET DRIVER (mlx4_en) M: Tariq Toukan <tariqt@nvidia.com> L: netdev@vger.kernel.org S: Supported -W: http://www.mellanox.com +W: https://www.nvidia.com/networking/ Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx4/en_* @@ -14500,7 +14500,7 @@ M: Saeed Mahameed <saeedm@nvidia.com> M: Tariq Toukan <tariqt@nvidia.com> L: netdev@vger.kernel.org S: Supported -W: http://www.mellanox.com +W: https://www.nvidia.com/networking/ Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx5/core/en_* @@ -14508,7 +14508,7 @@ MELLANOX ETHERNET INNOVA DRIVERS R: Boris Pismenny <borisp@nvidia.com> L: netdev@vger.kernel.org S: Supported -W: http://www.mellanox.com +W: https://www.nvidia.com/networking/ Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx5/core/en_accel/* F: drivers/net/ethernet/mellanox/mlx5/core/fpga/* @@ -14519,7 +14519,7 @@ M: Ido Schimmel <idosch@nvidia.com> M: Petr Machata <petrm@nvidia.com> L: netdev@vger.kernel.org S: Supported -W: http://www.mellanox.com +W: https://www.nvidia.com/networking/ Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlxsw/ F: tools/testing/selftests/drivers/net/mlxsw/ @@ -14528,7 +14528,7 @@ MELLANOX FIRMWARE FLASH LIBRARY (mlxfw) M: mlxsw@nvidia.com L: netdev@vger.kernel.org S: Supported -W: http://www.mellanox.com +W: https://www.nvidia.com/networking/ Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlxfw/ @@ -14547,7 +14547,7 @@ M: Tariq Toukan <tariqt@nvidia.com> L: netdev@vger.kernel.org L: linux-rdma@vger.kernel.org S: Supported -W: http://www.mellanox.com +W: https://www.nvidia.com/networking/ Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx4/ F: include/linux/mlx4/ @@ -14556,7 +14556,7 @@ MELLANOX MLX4 IB driver M: Yishai Hadas <yishaih@nvidia.com> L: linux-rdma@vger.kernel.org S: Supported -W: http://www.mellanox.com +W: https://www.nvidia.com/networking/ Q: http://patchwork.kernel.org/project/linux-rdma/list/ F: drivers/infiniband/hw/mlx4/ F: include/linux/mlx4/ @@ -14569,7 +14569,7 @@ M: Tariq Toukan <tariqt@nvidia.com> L: netdev@vger.kernel.org L: linux-rdma@vger.kernel.org S: Supported -W: http://www.mellanox.com +W: https://www.nvidia.com/networking/ Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: Documentation/networking/device_drivers/ethernet/mellanox/ F: drivers/net/ethernet/mellanox/mlx5/core/ @@ -14579,7 +14579,7 @@ MELLANOX MLX5 IB driver M: Leon Romanovsky <leonro@nvidia.com> L: linux-rdma@vger.kernel.org S: Supported -W: http://www.mellanox.com +W: https://www.nvidia.com/networking/ Q: http://patchwork.kernel.org/project/linux-rdma/list/ F: drivers/infiniband/hw/mlx5/ F: include/linux/mlx5/ diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 1cd92c12e782..f9633a6f8571 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -6338,7 +6338,8 @@ static int bond_init(struct net_device *bond_dev) netdev_dbg(bond_dev, "Begin bond_init\n"); - bond->wq = alloc_ordered_workqueue(bond_dev->name, WQ_MEM_RECLAIM); + bond->wq = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, + bond_dev->name); if (!bond->wq) return -ENOMEM; diff --git a/drivers/net/can/esd/esd_402_pci-core.c b/drivers/net/can/esd/esd_402_pci-core.c index b7cdcffd0e45..5d6d2828cd04 100644 --- a/drivers/net/can/esd/esd_402_pci-core.c +++ b/drivers/net/can/esd/esd_402_pci-core.c @@ -369,12 +369,13 @@ static int pci402_init_cores(struct pci_dev *pdev) SET_NETDEV_DEV(netdev, &pdev->dev); priv = netdev_priv(netdev); + priv->can.clock.freq = card->ov.core_frequency; priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK | CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_BERR_REPORTING | CAN_CTRLMODE_CC_LEN8_DLC; - - priv->can.clock.freq = card->ov.core_frequency; + if (card->ov.features & ACC_OV_REG_FEAT_MASK_DAR) + priv->can.ctrlmode_supported |= CAN_CTRLMODE_ONE_SHOT; if (card->ov.features & ACC_OV_REG_FEAT_MASK_CANFD) priv->can.bittiming_const = &pci402_bittiming_const_canfd; else diff --git a/drivers/net/can/esd/esdacc.c b/drivers/net/can/esd/esdacc.c index 121cbbf81458..c80032bc1a52 100644 --- a/drivers/net/can/esd/esdacc.c +++ b/drivers/net/can/esd/esdacc.c @@ -17,6 +17,9 @@ /* esdACC DLC register layout */ #define ACC_DLC_DLC_MASK GENMASK(3, 0) #define ACC_DLC_RTR_FLAG BIT(4) +#define ACC_DLC_SSTX_FLAG BIT(24) /* Single Shot TX */ + +/* esdACC DLC in struct acc_bmmsg_rxtxdone::acc_dlc.len only! */ #define ACC_DLC_TXD_FLAG BIT(5) /* ecc value of esdACC equals SJA1000's ECC register */ @@ -43,8 +46,8 @@ static void acc_resetmode_enter(struct acc_core *core) { - acc_set_bits(core, ACC_CORE_OF_CTRL_MODE, - ACC_REG_CONTROL_MASK_MODE_RESETMODE); + acc_set_bits(core, ACC_CORE_OF_CTRL, + ACC_REG_CTRL_MASK_RESETMODE); /* Read back reset mode bit to flush PCI write posting */ acc_resetmode_entered(core); @@ -52,14 +55,14 @@ static void acc_resetmode_enter(struct acc_core *core) static void acc_resetmode_leave(struct acc_core *core) { - acc_clear_bits(core, ACC_CORE_OF_CTRL_MODE, - ACC_REG_CONTROL_MASK_MODE_RESETMODE); + acc_clear_bits(core, ACC_CORE_OF_CTRL, + ACC_REG_CTRL_MASK_RESETMODE); /* Read back reset mode bit to flush PCI write posting */ acc_resetmode_entered(core); } -static void acc_txq_put(struct acc_core *core, u32 acc_id, u8 acc_dlc, +static void acc_txq_put(struct acc_core *core, u32 acc_id, u32 acc_dlc, const void *data) { acc_write32_noswap(core, ACC_CORE_OF_TXFIFO_DATA_1, @@ -172,7 +175,7 @@ int acc_open(struct net_device *netdev) struct acc_net_priv *priv = netdev_priv(netdev); struct acc_core *core = priv->core; u32 tx_fifo_status; - u32 ctrl_mode; + u32 ctrl; int err; /* Retry to enter RESET mode if out of sync. */ @@ -187,19 +190,19 @@ int acc_open(struct net_device *netdev) if (err) return err; - ctrl_mode = ACC_REG_CONTROL_MASK_IE_RXTX | - ACC_REG_CONTROL_MASK_IE_TXERROR | - ACC_REG_CONTROL_MASK_IE_ERRWARN | - ACC_REG_CONTROL_MASK_IE_OVERRUN | - ACC_REG_CONTROL_MASK_IE_ERRPASS; + ctrl = ACC_REG_CTRL_MASK_IE_RXTX | + ACC_REG_CTRL_MASK_IE_TXERROR | + ACC_REG_CTRL_MASK_IE_ERRWARN | + ACC_REG_CTRL_MASK_IE_OVERRUN | + ACC_REG_CTRL_MASK_IE_ERRPASS; if (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) - ctrl_mode |= ACC_REG_CONTROL_MASK_IE_BUSERR; + ctrl |= ACC_REG_CTRL_MASK_IE_BUSERR; if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) - ctrl_mode |= ACC_REG_CONTROL_MASK_MODE_LOM; + ctrl |= ACC_REG_CTRL_MASK_LOM; - acc_set_bits(core, ACC_CORE_OF_CTRL_MODE, ctrl_mode); + acc_set_bits(core, ACC_CORE_OF_CTRL, ctrl); acc_resetmode_leave(core); priv->can.state = CAN_STATE_ERROR_ACTIVE; @@ -218,13 +221,13 @@ int acc_close(struct net_device *netdev) struct acc_net_priv *priv = netdev_priv(netdev); struct acc_core *core = priv->core; - acc_clear_bits(core, ACC_CORE_OF_CTRL_MODE, - ACC_REG_CONTROL_MASK_IE_RXTX | - ACC_REG_CONTROL_MASK_IE_TXERROR | - ACC_REG_CONTROL_MASK_IE_ERRWARN | - ACC_REG_CONTROL_MASK_IE_OVERRUN | - ACC_REG_CONTROL_MASK_IE_ERRPASS | - ACC_REG_CONTROL_MASK_IE_BUSERR); + acc_clear_bits(core, ACC_CORE_OF_CTRL, + ACC_REG_CTRL_MASK_IE_RXTX | + ACC_REG_CTRL_MASK_IE_TXERROR | + ACC_REG_CTRL_MASK_IE_ERRWARN | + ACC_REG_CTRL_MASK_IE_OVERRUN | + ACC_REG_CTRL_MASK_IE_ERRPASS | + ACC_REG_CTRL_MASK_IE_BUSERR); netif_stop_queue(netdev); acc_resetmode_enter(core); @@ -233,9 +236,9 @@ int acc_close(struct net_device *netdev) /* Mark pending TX requests to be aborted after controller restart. */ acc_write32(core, ACC_CORE_OF_TX_ABORT_MASK, 0xffff); - /* ACC_REG_CONTROL_MASK_MODE_LOM is only accessible in RESET mode */ - acc_clear_bits(core, ACC_CORE_OF_CTRL_MODE, - ACC_REG_CONTROL_MASK_MODE_LOM); + /* ACC_REG_CTRL_MASK_LOM is only accessible in RESET mode */ + acc_clear_bits(core, ACC_CORE_OF_CTRL, + ACC_REG_CTRL_MASK_LOM); close_candev(netdev); return 0; @@ -249,7 +252,7 @@ netdev_tx_t acc_start_xmit(struct sk_buff *skb, struct net_device *netdev) u8 tx_fifo_head = core->tx_fifo_head; int fifo_usage; u32 acc_id; - u8 acc_dlc; + u32 acc_dlc; if (can_dropped_invalid_skb(netdev, skb)) return NETDEV_TX_OK; @@ -274,6 +277,8 @@ netdev_tx_t acc_start_xmit(struct sk_buff *skb, struct net_device *netdev) acc_dlc = can_get_cc_dlc(cf, priv->can.ctrlmode); if (cf->can_id & CAN_RTR_FLAG) acc_dlc |= ACC_DLC_RTR_FLAG; + if (priv->can.ctrlmode & CAN_CTRLMODE_ONE_SHOT) + acc_dlc |= ACC_DLC_SSTX_FLAG; if (cf->can_id & CAN_EFF_FLAG) { acc_id = cf->can_id & CAN_EFF_MASK; diff --git a/drivers/net/can/esd/esdacc.h b/drivers/net/can/esd/esdacc.h index a70488b25d39..6b7ebd8c91b2 100644 --- a/drivers/net/can/esd/esdacc.h +++ b/drivers/net/can/esd/esdacc.h @@ -35,6 +35,7 @@ */ #define ACC_OV_REG_FEAT_MASK_CANFD BIT(27 - 16) #define ACC_OV_REG_FEAT_MASK_NEW_PSC BIT(28 - 16) +#define ACC_OV_REG_FEAT_MASK_DAR BIT(30 - 16) #define ACC_OV_REG_MODE_MASK_ENDIAN_LITTLE BIT(0) #define ACC_OV_REG_MODE_MASK_BM_ENABLE BIT(1) @@ -50,7 +51,7 @@ #define ACC_OV_REG_MODE_MASK_FPGA_RESET BIT(31) /* esdACC CAN Core Module */ -#define ACC_CORE_OF_CTRL_MODE 0x0000 +#define ACC_CORE_OF_CTRL 0x0000 #define ACC_CORE_OF_STATUS_IRQ 0x0008 #define ACC_CORE_OF_BRP 0x000c #define ACC_CORE_OF_BTR 0x0010 @@ -66,21 +67,22 @@ #define ACC_CORE_OF_TXFIFO_DATA_0 0x00c8 #define ACC_CORE_OF_TXFIFO_DATA_1 0x00cc -#define ACC_REG_CONTROL_MASK_MODE_RESETMODE BIT(0) -#define ACC_REG_CONTROL_MASK_MODE_LOM BIT(1) -#define ACC_REG_CONTROL_MASK_MODE_STM BIT(2) -#define ACC_REG_CONTROL_MASK_MODE_TRANSEN BIT(5) -#define ACC_REG_CONTROL_MASK_MODE_TS BIT(6) -#define ACC_REG_CONTROL_MASK_MODE_SCHEDULE BIT(7) - -#define ACC_REG_CONTROL_MASK_IE_RXTX BIT(8) -#define ACC_REG_CONTROL_MASK_IE_TXERROR BIT(9) -#define ACC_REG_CONTROL_MASK_IE_ERRWARN BIT(10) -#define ACC_REG_CONTROL_MASK_IE_OVERRUN BIT(11) -#define ACC_REG_CONTROL_MASK_IE_TSI BIT(12) -#define ACC_REG_CONTROL_MASK_IE_ERRPASS BIT(13) -#define ACC_REG_CONTROL_MASK_IE_ALI BIT(14) -#define ACC_REG_CONTROL_MASK_IE_BUSERR BIT(15) +/* CTRL register layout */ +#define ACC_REG_CTRL_MASK_RESETMODE BIT(0) +#define ACC_REG_CTRL_MASK_LOM BIT(1) +#define ACC_REG_CTRL_MASK_STM BIT(2) +#define ACC_REG_CTRL_MASK_TRANSEN BIT(5) +#define ACC_REG_CTRL_MASK_TS BIT(6) +#define ACC_REG_CTRL_MASK_SCHEDULE BIT(7) + +#define ACC_REG_CTRL_MASK_IE_RXTX BIT(8) +#define ACC_REG_CTRL_MASK_IE_TXERROR BIT(9) +#define ACC_REG_CTRL_MASK_IE_ERRWARN BIT(10) +#define ACC_REG_CTRL_MASK_IE_OVERRUN BIT(11) +#define ACC_REG_CTRL_MASK_IE_TSI BIT(12) +#define ACC_REG_CTRL_MASK_IE_ERRPASS BIT(13) +#define ACC_REG_CTRL_MASK_IE_ALI BIT(14) +#define ACC_REG_CTRL_MASK_IE_BUSERR BIT(15) /* BRP and BTR register layout for CAN-Classic version */ #define ACC_REG_BRP_CL_MASK_BRP GENMASK(8, 0) @@ -300,9 +302,9 @@ static inline void acc_clear_bits(struct acc_core *core, static inline int acc_resetmode_entered(struct acc_core *core) { - u32 ctrl = acc_read32(core, ACC_CORE_OF_CTRL_MODE); + u32 ctrl = acc_read32(core, ACC_CORE_OF_CTRL); - return (ctrl & ACC_REG_CONTROL_MASK_MODE_RESETMODE) != 0; + return (ctrl & ACC_REG_CTRL_MASK_RESETMODE) != 0; } static inline u32 acc_ov_read32(struct acc_ov *ov, unsigned short offs) diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c index 8ea7f2795551..d11411029330 100644 --- a/drivers/net/can/flexcan/flexcan-core.c +++ b/drivers/net/can/flexcan/flexcan-core.c @@ -354,6 +354,14 @@ static struct flexcan_devtype_data fsl_imx93_devtype_data = { FLEXCAN_QUIRK_SUPPORT_RX_MAILBOX_RTR, }; +static const struct flexcan_devtype_data fsl_imx95_devtype_data = { + .quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS | + FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_USE_RX_MAILBOX | + FLEXCAN_QUIRK_BROKEN_PERR_STATE | FLEXCAN_QUIRK_SUPPORT_FD | + FLEXCAN_QUIRK_SUPPORT_ECC | FLEXCAN_QUIRK_SUPPORT_RX_MAILBOX | + FLEXCAN_QUIRK_SUPPORT_RX_MAILBOX_RTR | FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI, +}; + static const struct flexcan_devtype_data fsl_vf610_devtype_data = { .quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS | FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_USE_RX_MAILBOX | @@ -544,6 +552,13 @@ static inline int flexcan_enter_stop_mode(struct flexcan_priv *priv) } else if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SETUP_STOP_MODE_GPR) { regmap_update_bits(priv->stm.gpr, priv->stm.req_gpr, 1 << priv->stm.req_bit, 1 << priv->stm.req_bit); + } else if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI) { + /* For the SCMI mode, driver do nothing, ATF will send request to + * SM(system manager, M33 core) through SCMI protocol after linux + * suspend. Once SM get this request, it will send IPG_STOP signal + * to Flex_CAN, let CAN in STOP mode. + */ + return 0; } return flexcan_low_power_enter_ack(priv); @@ -555,7 +570,11 @@ static inline int flexcan_exit_stop_mode(struct flexcan_priv *priv) u32 reg_mcr; int ret; - /* remove stop request */ + /* Remove stop request, for FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI, + * do nothing here, because ATF already send request to SM before + * linux resume. Once SM get this request, it will deassert the + * IPG_STOP signal to Flex_CAN. + */ if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SETUP_STOP_MODE_SCFW) { ret = flexcan_stop_mode_enable_scfw(priv, false); if (ret < 0) @@ -1983,6 +2002,9 @@ static int flexcan_setup_stop_mode(struct platform_device *pdev) ret = flexcan_setup_stop_mode_scfw(pdev); else if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SETUP_STOP_MODE_GPR) ret = flexcan_setup_stop_mode_gpr(pdev); + else if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI) + /* ATF will handle all STOP_IPG related work */ + ret = 0; else /* return 0 directly if doesn't support stop mode feature */ return 0; @@ -2009,6 +2031,7 @@ static const struct of_device_id flexcan_of_match[] = { { .compatible = "fsl,imx8qm-flexcan", .data = &fsl_imx8qm_devtype_data, }, { .compatible = "fsl,imx8mp-flexcan", .data = &fsl_imx8mp_devtype_data, }, { .compatible = "fsl,imx93-flexcan", .data = &fsl_imx93_devtype_data, }, + { .compatible = "fsl,imx95-flexcan", .data = &fsl_imx95_devtype_data, }, { .compatible = "fsl,imx6q-flexcan", .data = &fsl_imx6q_devtype_data, }, { .compatible = "fsl,imx28-flexcan", .data = &fsl_imx28_devtype_data, }, { .compatible = "fsl,imx53-flexcan", .data = &fsl_imx25_devtype_data, }, @@ -2309,9 +2332,19 @@ static int __maybe_unused flexcan_noirq_suspend(struct device *device) if (device_may_wakeup(device)) flexcan_enable_wakeup_irq(priv, true); - err = pm_runtime_force_suspend(device); - if (err) - return err; + /* For FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI, it need ATF to send + * to SM through SCMI protocol, SM will assert the IPG_STOP + * signal. But all this works need the CAN clocks keep on. + * After the CAN module get the IPG_STOP mode, and switch to + * STOP mode, whether still keep the CAN clocks on or gate them + * off depend on the Hardware design. + */ + if (!(device_may_wakeup(device) && + priv->devtype_data.quirks & FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI)) { + err = pm_runtime_force_suspend(device); + if (err) + return err; + } } return 0; @@ -2325,9 +2358,12 @@ static int __maybe_unused flexcan_noirq_resume(struct device *device) if (netif_running(dev)) { int err; - err = pm_runtime_force_resume(device); - if (err) - return err; + if (!(device_may_wakeup(device) && + priv->devtype_data.quirks & FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI)) { + err = pm_runtime_force_resume(device); + if (err) + return err; + } if (device_may_wakeup(device)) flexcan_enable_wakeup_irq(priv, false); diff --git a/drivers/net/can/flexcan/flexcan.h b/drivers/net/can/flexcan/flexcan.h index 025c3417031f..4933d8c7439e 100644 --- a/drivers/net/can/flexcan/flexcan.h +++ b/drivers/net/can/flexcan/flexcan.h @@ -68,6 +68,8 @@ #define FLEXCAN_QUIRK_SUPPORT_RX_MAILBOX_RTR BIT(15) /* Device supports RX via FIFO */ #define FLEXCAN_QUIRK_SUPPORT_RX_FIFO BIT(16) +/* Setup stop mode with ATF SCMI protocol to support wakeup */ +#define FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI BIT(17) struct flexcan_devtype_data { u32 quirks; /* quirks needed for different IP cores */ diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h index ff10b3790d84..078496d9b7ba 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h @@ -22,6 +22,8 @@ */ #include <linux/completion.h> +#include <linux/ktime.h> +#include <linux/math64.h> #include <linux/spinlock.h> #include <linux/types.h> #include <linux/usb.h> @@ -39,7 +41,6 @@ #define KVASER_USB_QUIRK_HAS_SILENT_MODE BIT(0) #define KVASER_USB_QUIRK_HAS_TXRX_ERRORS BIT(1) #define KVASER_USB_QUIRK_IGNORE_CLK_FREQ BIT(2) -#define KVASER_USB_QUIRK_HAS_HARDWARE_TIMESTAMP BIT(3) /* Device capabilities */ #define KVASER_USB_CAP_BERR_CAP 0x01 @@ -68,6 +69,7 @@ struct kvaser_usb_dev_card_data { u32 ctrlmode_supported; u32 capabilities; struct kvaser_usb_dev_card_data_hydra hydra; + u32 usbcan_timestamp_msb; }; /* Context for an outstanding, not yet ACKed, transmission */ @@ -216,4 +218,26 @@ int kvaser_usb_can_rx_over_error(struct net_device *netdev); extern const struct can_bittiming_const kvaser_usb_flexc_bittiming_const; +static inline ktime_t kvaser_usb_ticks_to_ktime(const struct kvaser_usb_dev_cfg *cfg, + u64 ticks) +{ + return ns_to_ktime(div_u64(ticks * 1000, cfg->timestamp_freq)); +} + +static inline ktime_t kvaser_usb_timestamp48_to_ktime(const struct kvaser_usb_dev_cfg *cfg, + const __le16 *timestamp) +{ + u64 ticks = le16_to_cpu(timestamp[0]) | + (u64)(le16_to_cpu(timestamp[1])) << 16 | + (u64)(le16_to_cpu(timestamp[2])) << 32; + + return kvaser_usb_ticks_to_ktime(cfg, ticks); +} + +static inline ktime_t kvaser_usb_timestamp64_to_ktime(const struct kvaser_usb_dev_cfg *cfg, + __le64 timestamp) +{ + return kvaser_usb_ticks_to_ktime(cfg, le64_to_cpu(timestamp)); +} + #endif /* KVASER_USB_H */ diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c index daa34b532aa8..35b4132b0639 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c @@ -94,7 +94,7 @@ #define USB_MINI_PCIE_1XCAN_PRODUCT_ID 0x011B static const struct kvaser_usb_driver_info kvaser_usb_driver_info_hydra = { - .quirks = KVASER_USB_QUIRK_HAS_HARDWARE_TIMESTAMP, + .quirks = 0, .ops = &kvaser_usb_hydra_dev_ops, }; @@ -756,23 +756,12 @@ freeurb: static const struct net_device_ops kvaser_usb_netdev_ops = { .ndo_open = kvaser_usb_open, .ndo_stop = kvaser_usb_close, - .ndo_start_xmit = kvaser_usb_start_xmit, - .ndo_change_mtu = can_change_mtu, -}; - -static const struct net_device_ops kvaser_usb_netdev_ops_hwts = { - .ndo_open = kvaser_usb_open, - .ndo_stop = kvaser_usb_close, .ndo_eth_ioctl = can_eth_ioctl_hwts, .ndo_start_xmit = kvaser_usb_start_xmit, .ndo_change_mtu = can_change_mtu, }; static const struct ethtool_ops kvaser_usb_ethtool_ops = { - .get_ts_info = ethtool_op_get_ts_info, -}; - -static const struct ethtool_ops kvaser_usb_ethtool_ops_hwts = { .get_ts_info = can_ethtool_op_get_ts_info_hwts, }; @@ -859,13 +848,7 @@ static int kvaser_usb_init_one(struct kvaser_usb *dev, int channel) netdev->flags |= IFF_ECHO; netdev->netdev_ops = &kvaser_usb_netdev_ops; - if (driver_info->quirks & KVASER_USB_QUIRK_HAS_HARDWARE_TIMESTAMP) { - netdev->netdev_ops = &kvaser_usb_netdev_ops_hwts; - netdev->ethtool_ops = &kvaser_usb_ethtool_ops_hwts; - } else { - netdev->netdev_ops = &kvaser_usb_netdev_ops; - netdev->ethtool_ops = &kvaser_usb_ethtool_ops; - } + netdev->ethtool_ops = &kvaser_usb_ethtool_ops; SET_NETDEV_DEV(netdev, &dev->intf->dev); netdev->dev_id = channel; diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c index c7ba768dfe17..3764b263add3 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c @@ -10,7 +10,6 @@ * - Transition from CAN_STATE_ERROR_WARNING to CAN_STATE_ERROR_ACTIVE is only * reported after a call to do_get_berr_counter(), since firmware does not * distinguish between ERROR_WARNING and ERROR_ACTIVE. - * - Hardware timestamps are not set for CAN Tx frames. */ #include <linux/completion.h> @@ -261,6 +260,15 @@ struct kvaser_cmd_tx_can { u8 reserved[11]; } __packed; +struct kvaser_cmd_tx_ack { + __le32 id; + u8 data[8]; + u8 dlc; + u8 flags; + __le16 timestamp[3]; + u8 reserved0[8]; +} __packed; + struct kvaser_cmd_header { u8 cmd_no; /* The destination HE address is stored in 0..5 of he_addr. @@ -297,6 +305,7 @@ struct kvaser_cmd { struct kvaser_cmd_rx_can rx_can; struct kvaser_cmd_tx_can tx_can; + struct kvaser_cmd_tx_ack tx_ack; } __packed; } __packed; @@ -522,23 +531,25 @@ kvaser_usb_hydra_net_priv_from_cmd(const struct kvaser_usb *dev, return priv; } -static ktime_t -kvaser_usb_hydra_ktime_from_rx_cmd(const struct kvaser_usb_dev_cfg *cfg, - const struct kvaser_cmd *cmd) +static ktime_t kvaser_usb_hydra_ktime_from_cmd(const struct kvaser_usb_dev_cfg *cfg, + const struct kvaser_cmd *cmd) { - u64 ticks; + ktime_t hwtstamp = 0; if (cmd->header.cmd_no == CMD_EXTENDED) { struct kvaser_cmd_ext *cmd_ext = (struct kvaser_cmd_ext *)cmd; - ticks = le64_to_cpu(cmd_ext->rx_can.timestamp); - } else { - ticks = le16_to_cpu(cmd->rx_can.timestamp[0]); - ticks += (u64)(le16_to_cpu(cmd->rx_can.timestamp[1])) << 16; - ticks += (u64)(le16_to_cpu(cmd->rx_can.timestamp[2])) << 32; + if (cmd_ext->cmd_no_ext == CMD_RX_MESSAGE_FD) + hwtstamp = kvaser_usb_timestamp64_to_ktime(cfg, cmd_ext->rx_can.timestamp); + else if (cmd_ext->cmd_no_ext == CMD_TX_ACKNOWLEDGE_FD) + hwtstamp = kvaser_usb_timestamp64_to_ktime(cfg, cmd_ext->tx_ack.timestamp); + } else if (cmd->header.cmd_no == CMD_RX_MESSAGE) { + hwtstamp = kvaser_usb_timestamp48_to_ktime(cfg, cmd->rx_can.timestamp); + } else if (cmd->header.cmd_no == CMD_TX_ACKNOWLEDGE) { + hwtstamp = kvaser_usb_timestamp48_to_ktime(cfg, cmd->tx_ack.timestamp); } - return ns_to_ktime(div_u64(ticks * 1000, cfg->timestamp_freq)); + return hwtstamp; } static int kvaser_usb_hydra_send_simple_cmd(struct kvaser_usb *dev, @@ -1175,6 +1186,7 @@ static void kvaser_usb_hydra_tx_acknowledge(const struct kvaser_usb *dev, bool one_shot_fail = false; bool is_err_frame = false; u16 transid = kvaser_usb_hydra_get_cmd_transid(cmd); + struct sk_buff *skb; priv = kvaser_usb_hydra_net_priv_from_cmd(dev, cmd); if (!priv) @@ -1201,6 +1213,9 @@ static void kvaser_usb_hydra_tx_acknowledge(const struct kvaser_usb *dev, spin_lock_irqsave(&priv->tx_contexts_lock, irq_flags); + skb = priv->can.echo_skb[context->echo_index]; + if (skb) + skb_hwtstamps(skb)->hwtstamp = kvaser_usb_hydra_ktime_from_cmd(dev->cfg, cmd); len = can_get_echo_skb(priv->netdev, context->echo_index, NULL); context->echo_index = dev->max_tx_urbs; --priv->active_tx_contexts; @@ -1234,7 +1249,7 @@ static void kvaser_usb_hydra_rx_msg_std(const struct kvaser_usb *dev, stats = &priv->netdev->stats; flags = cmd->rx_can.flags; - hwtstamp = kvaser_usb_hydra_ktime_from_rx_cmd(dev->cfg, cmd); + hwtstamp = kvaser_usb_hydra_ktime_from_cmd(dev->cfg, cmd); if (flags & KVASER_USB_HYDRA_CF_FLAG_ERROR_FRAME) { kvaser_usb_hydra_error_frame(priv, &cmd->rx_can.err_frame_data, @@ -1302,7 +1317,7 @@ static void kvaser_usb_hydra_rx_msg_ext(const struct kvaser_usb *dev, KVASER_USB_KCAN_DATA_DLC_SHIFT; flags = le32_to_cpu(cmd->rx_can.flags); - hwtstamp = kvaser_usb_hydra_ktime_from_rx_cmd(dev->cfg, std_cmd); + hwtstamp = kvaser_usb_hydra_ktime_from_cmd(dev->cfg, std_cmd); if (flags & KVASER_USB_HYDRA_CF_FLAG_ERROR_FRAME) { kvaser_usb_hydra_error_frame(priv, &cmd->rx_can.err_frame_data, diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c index 23bd7574b1c7..6b9122ab1464 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c @@ -119,6 +119,10 @@ /* Extended CAN identifier flag */ #define KVASER_EXTENDED_FRAME BIT(31) +/* USBCanII timestamp */ +#define KVASER_USB_USBCAN_CLK_OVERFLOW_MASK GENMASK(31, 16) +#define KVASER_USB_USBCAN_TIMESTAMP_FACTOR 10 + struct kvaser_cmd_simple { u8 tid; u8 channel; @@ -235,6 +239,20 @@ struct kvaser_cmd_tx_acknowledge_header { u8 tid; } __packed; +struct leaf_cmd_tx_acknowledge { + u8 channel; + u8 tid; + __le16 time[3]; + u8 padding[2]; +} __packed; + +struct usbcan_cmd_tx_acknowledge { + u8 channel; + u8 tid; + __le16 time; + u8 padding[2]; +} __packed; + struct leaf_cmd_can_error_event { u8 tid; u8 flags; @@ -281,6 +299,12 @@ struct usbcan_cmd_error_event { __le16 padding; } __packed; +struct usbcan_cmd_clk_overflow_event { + u8 tid; + u8 padding; + __le32 time; +} __packed; + struct kvaser_cmd_ctrl_mode { u8 tid; u8 channel; @@ -347,6 +371,7 @@ struct kvaser_cmd { struct leaf_cmd_error_event error_event; struct kvaser_cmd_cap_req cap_req; struct kvaser_cmd_cap_res cap_res; + struct leaf_cmd_tx_acknowledge tx_ack; } __packed leaf; union { @@ -355,6 +380,8 @@ struct kvaser_cmd { struct usbcan_cmd_chip_state_event chip_state_event; struct usbcan_cmd_can_error_event can_error_event; struct usbcan_cmd_error_event error_event; + struct usbcan_cmd_tx_acknowledge tx_ack; + struct usbcan_cmd_clk_overflow_event clk_overflow_event; } __packed usbcan; struct kvaser_cmd_tx_can tx_can; @@ -370,7 +397,7 @@ static const u8 kvaser_usb_leaf_cmd_sizes_leaf[] = { [CMD_START_CHIP_REPLY] = kvaser_fsize(u.simple), [CMD_STOP_CHIP_REPLY] = kvaser_fsize(u.simple), [CMD_GET_CARD_INFO_REPLY] = kvaser_fsize(u.cardinfo), - [CMD_TX_ACKNOWLEDGE] = kvaser_fsize(u.tx_acknowledge_header), + [CMD_TX_ACKNOWLEDGE] = kvaser_fsize(u.leaf.tx_ack), [CMD_GET_SOFTWARE_INFO_REPLY] = kvaser_fsize(u.leaf.softinfo), [CMD_RX_STD_MESSAGE] = kvaser_fsize(u.leaf.rx_can), [CMD_RX_EXT_MESSAGE] = kvaser_fsize(u.leaf.rx_can), @@ -388,15 +415,14 @@ static const u8 kvaser_usb_leaf_cmd_sizes_usbcan[] = { [CMD_START_CHIP_REPLY] = kvaser_fsize(u.simple), [CMD_STOP_CHIP_REPLY] = kvaser_fsize(u.simple), [CMD_GET_CARD_INFO_REPLY] = kvaser_fsize(u.cardinfo), - [CMD_TX_ACKNOWLEDGE] = kvaser_fsize(u.tx_acknowledge_header), + [CMD_TX_ACKNOWLEDGE] = kvaser_fsize(u.usbcan.tx_ack), [CMD_GET_SOFTWARE_INFO_REPLY] = kvaser_fsize(u.usbcan.softinfo), [CMD_RX_STD_MESSAGE] = kvaser_fsize(u.usbcan.rx_can), [CMD_RX_EXT_MESSAGE] = kvaser_fsize(u.usbcan.rx_can), [CMD_CHIP_STATE_EVENT] = kvaser_fsize(u.usbcan.chip_state_event), [CMD_CAN_ERROR_EVENT] = kvaser_fsize(u.usbcan.can_error_event), [CMD_ERROR_EVENT] = kvaser_fsize(u.usbcan.error_event), - /* ignored events: */ - [CMD_USBCAN_CLOCK_OVERFLOW_EVENT] = CMD_SIZE_ANY, + [CMD_USBCAN_CLOCK_OVERFLOW_EVENT] = kvaser_fsize(u.usbcan.clk_overflow_event), }; /* Summary of a kvaser error event, for a unified Leaf/Usbcan error @@ -463,11 +489,27 @@ static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_usbcan_dev_cfg = { .bittiming_const = &kvaser_usb_leaf_m16c_bittiming_const, }; -static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_m32c_dev_cfg = { +static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_m32c_dev_cfg_16mhz = { .clock = { .freq = 16 * MEGA /* Hz */, }, - .timestamp_freq = 1, + .timestamp_freq = 16, + .bittiming_const = &kvaser_usb_leaf_m32c_bittiming_const, +}; + +static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_m32c_dev_cfg_24mhz = { + .clock = { + .freq = 16 * MEGA /* Hz */, + }, + .timestamp_freq = 24, + .bittiming_const = &kvaser_usb_leaf_m32c_bittiming_const, +}; + +static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_m32c_dev_cfg_32mhz = { + .clock = { + .freq = 16 * MEGA /* Hz */, + }, + .timestamp_freq = 32, .bittiming_const = &kvaser_usb_leaf_m32c_bittiming_const, }; @@ -475,7 +517,7 @@ static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_imx_dev_cfg_16mhz = { .clock = { .freq = 16 * MEGA /* Hz */, }, - .timestamp_freq = 1, + .timestamp_freq = 16, .bittiming_const = &kvaser_usb_flexc_bittiming_const, }; @@ -483,7 +525,7 @@ static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_imx_dev_cfg_24mhz = { .clock = { .freq = 24 * MEGA /* Hz */, }, - .timestamp_freq = 1, + .timestamp_freq = 24, .bittiming_const = &kvaser_usb_flexc_bittiming_const, }; @@ -491,10 +533,19 @@ static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_imx_dev_cfg_32mhz = { .clock = { .freq = 32 * MEGA /* Hz */, }, - .timestamp_freq = 1, + .timestamp_freq = 32, .bittiming_const = &kvaser_usb_flexc_bittiming_const, }; +static inline ktime_t kvaser_usb_usbcan_timestamp_to_ktime(const struct kvaser_usb *dev, + __le16 timestamp) +{ + u64 ticks = le16_to_cpu(timestamp) | + dev->card_data.usbcan_timestamp_msb; + + return kvaser_usb_ticks_to_ktime(dev->cfg, ticks * KVASER_USB_USBCAN_TIMESTAMP_FACTOR); +} + static int kvaser_usb_leaf_verify_size(const struct kvaser_usb *dev, const struct kvaser_cmd *cmd) { @@ -678,8 +729,19 @@ static void kvaser_usb_leaf_get_software_info_leaf(struct kvaser_usb *dev, if (dev->driver_info->quirks & KVASER_USB_QUIRK_IGNORE_CLK_FREQ) { /* Firmware expects bittiming parameters calculated for 16MHz * clock, regardless of the actual clock + * Though, the reported freq is used for timestamps */ - dev->cfg = &kvaser_usb_leaf_m32c_dev_cfg; + switch (sw_options & KVASER_USB_LEAF_SWOPTION_FREQ_MASK) { + case KVASER_USB_LEAF_SWOPTION_FREQ_16_MHZ_CLK: + dev->cfg = &kvaser_usb_leaf_m32c_dev_cfg_16mhz; + break; + case KVASER_USB_LEAF_SWOPTION_FREQ_24_MHZ_CLK: + dev->cfg = &kvaser_usb_leaf_m32c_dev_cfg_24mhz; + break; + case KVASER_USB_LEAF_SWOPTION_FREQ_32_MHZ_CLK: + dev->cfg = &kvaser_usb_leaf_m32c_dev_cfg_32mhz; + break; + } } else { switch (sw_options & KVASER_USB_LEAF_SWOPTION_FREQ_MASK) { case KVASER_USB_LEAF_SWOPTION_FREQ_16_MHZ_CLK: @@ -880,6 +942,8 @@ static void kvaser_usb_leaf_tx_acknowledge(const struct kvaser_usb *dev, struct kvaser_usb_net_priv *priv; unsigned long flags; u8 channel, tid; + struct sk_buff *skb; + ktime_t hwtstamp = 0; channel = cmd->u.tx_acknowledge_header.channel; tid = cmd->u.tx_acknowledge_header.tid; @@ -901,14 +965,14 @@ static void kvaser_usb_leaf_tx_acknowledge(const struct kvaser_usb *dev, /* Sometimes the state change doesn't come after a bus-off event */ if (priv->can.restart_ms && priv->can.state == CAN_STATE_BUS_OFF) { - struct sk_buff *skb; + struct sk_buff *err_skb; struct can_frame *cf; - skb = alloc_can_err_skb(priv->netdev, &cf); - if (skb) { + err_skb = alloc_can_err_skb(priv->netdev, &cf); + if (err_skb) { cf->can_id |= CAN_ERR_RESTARTED; - netif_rx(skb); + netif_rx(err_skb); } else { netdev_err(priv->netdev, "No memory left for err_skb\n"); @@ -919,9 +983,20 @@ static void kvaser_usb_leaf_tx_acknowledge(const struct kvaser_usb *dev, priv->can.state = CAN_STATE_ERROR_ACTIVE; } + switch (dev->driver_info->family) { + case KVASER_LEAF: + hwtstamp = kvaser_usb_timestamp48_to_ktime(dev->cfg, cmd->u.leaf.tx_ack.time); + break; + case KVASER_USBCAN: + hwtstamp = kvaser_usb_usbcan_timestamp_to_ktime(dev, cmd->u.usbcan.tx_ack.time); + break; + } spin_lock_irqsave(&priv->tx_contexts_lock, flags); + skb = priv->can.echo_skb[context->echo_index]; + if (skb) + skb_hwtstamps(skb)->hwtstamp = hwtstamp; stats->tx_packets++; stats->tx_bytes += can_get_echo_skb(priv->netdev, context->echo_index, NULL); @@ -1299,6 +1374,7 @@ static void kvaser_usb_leaf_rx_can_msg(const struct kvaser_usb *dev, struct net_device_stats *stats; u8 channel = cmd->u.rx_can_header.channel; const u8 *rx_data = NULL; /* GCC */ + ktime_t hwtstamp = 0; if (channel >= dev->nchannels) { dev_err(&dev->intf->dev, @@ -1329,9 +1405,11 @@ static void kvaser_usb_leaf_rx_can_msg(const struct kvaser_usb *dev, switch (dev->driver_info->family) { case KVASER_LEAF: rx_data = cmd->u.leaf.rx_can.data; + hwtstamp = kvaser_usb_timestamp48_to_ktime(dev->cfg, cmd->u.leaf.rx_can.time); break; case KVASER_USBCAN: rx_data = cmd->u.usbcan.rx_can.data; + hwtstamp = kvaser_usb_usbcan_timestamp_to_ktime(dev, cmd->u.usbcan.rx_can.time); break; } @@ -1375,6 +1453,7 @@ static void kvaser_usb_leaf_rx_can_msg(const struct kvaser_usb *dev, memcpy(cf->data, &rx_data[6], cf->len); } + skb_hwtstamps(skb)->hwtstamp = hwtstamp; stats->rx_packets++; if (!(cf->can_id & CAN_RTR_FLAG)) stats->rx_bytes += cf->len; @@ -1508,7 +1587,7 @@ static void kvaser_usb_leaf_get_busparams_reply(const struct kvaser_usb *dev, complete(&priv->get_busparams_comp); } -static void kvaser_usb_leaf_handle_command(const struct kvaser_usb *dev, +static void kvaser_usb_leaf_handle_command(struct kvaser_usb *dev, const struct kvaser_cmd *cmd) { if (kvaser_usb_leaf_verify_size(dev, cmd) < 0) @@ -1554,12 +1633,15 @@ static void kvaser_usb_leaf_handle_command(const struct kvaser_usb *dev, kvaser_usb_leaf_get_busparams_reply(dev, cmd); break; - /* Ignored commands */ case CMD_USBCAN_CLOCK_OVERFLOW_EVENT: if (dev->driver_info->family != KVASER_USBCAN) goto warn; + dev->card_data.usbcan_timestamp_msb = + le32_to_cpu(cmd->u.usbcan.clk_overflow_event.time) & + KVASER_USB_USBCAN_CLK_OVERFLOW_MASK; break; + /* Ignored commands */ case CMD_FLUSH_QUEUE_REPLY: if (dev->driver_info->family != KVASER_LEAF) goto warn; diff --git a/drivers/net/dsa/mt7530-mmio.c b/drivers/net/dsa/mt7530-mmio.c index b74a230a3f13..10dc49961f15 100644 --- a/drivers/net/dsa/mt7530-mmio.c +++ b/drivers/net/dsa/mt7530-mmio.c @@ -11,6 +11,7 @@ #include "mt7530.h" static const struct of_device_id mt7988_of_match[] = { + { .compatible = "airoha,en7581-switch", .data = &mt753x_table[ID_EN7581], }, { .compatible = "mediatek,mt7988-switch", .data = &mt753x_table[ID_MT7988], }, { /* sentinel */ }, }; diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index ec18e68bf3a8..d84ee1b419a6 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1152,7 +1152,8 @@ mt753x_cpu_port_enable(struct dsa_switch *ds, int port) * the MT7988 SoC. Trapped frames will be forwarded to the CPU port that * is affine to the inbound user port. */ - if (priv->id == ID_MT7531 || priv->id == ID_MT7988) + if (priv->id == ID_MT7531 || priv->id == ID_MT7988 || + priv->id == ID_EN7581) mt7530_set(priv, MT7531_CFC, MT7531_CPU_PMAP(BIT(port))); /* CPU port gets connected to all user ports of @@ -2207,7 +2208,7 @@ mt7530_setup_irq(struct mt7530_priv *priv) return priv->irq ? : -EINVAL; } - if (priv->id == ID_MT7988) + if (priv->id == ID_MT7988 || priv->id == ID_EN7581) priv->irq_domain = irq_domain_add_linear(np, MT7530_NUM_PHYS, &mt7988_irq_domain_ops, priv); @@ -2438,8 +2439,10 @@ mt7530_setup(struct dsa_switch *ds) /* Clear link settings and enable force mode to force link down * on all ports until they're enabled later. */ - mt7530_rmw(priv, MT753X_PMCR_P(i), PMCR_LINK_SETTINGS_MASK | - MT7530_FORCE_MODE, MT7530_FORCE_MODE); + mt7530_rmw(priv, MT753X_PMCR_P(i), + PMCR_LINK_SETTINGS_MASK | + MT753X_FORCE_MODE(priv->id), + MT753X_FORCE_MODE(priv->id)); /* Disable forwarding by default on all ports */ mt7530_rmw(priv, MT7530_PCR_P(i), PCR_MATRIX_MASK, @@ -2550,8 +2553,10 @@ mt7531_setup_common(struct dsa_switch *ds) /* Clear link settings and enable force mode to force link down * on all ports until they're enabled later. */ - mt7530_rmw(priv, MT753X_PMCR_P(i), PMCR_LINK_SETTINGS_MASK | - MT7531_FORCE_MODE_MASK, MT7531_FORCE_MODE_MASK); + mt7530_rmw(priv, MT753X_PMCR_P(i), + PMCR_LINK_SETTINGS_MASK | + MT753X_FORCE_MODE(priv->id), + MT753X_FORCE_MODE(priv->id)); /* Disable forwarding by default on all ports */ mt7530_rmw(priv, MT7530_PCR_P(i), PCR_MATRIX_MASK, @@ -2783,6 +2788,28 @@ static void mt7988_mac_port_get_caps(struct dsa_switch *ds, int port, } } +static void en7581_mac_port_get_caps(struct dsa_switch *ds, int port, + struct phylink_config *config) +{ + switch (port) { + /* Ports which are connected to switch PHYs. There is no MII pinout. */ + case 0 ... 4: + __set_bit(PHY_INTERFACE_MODE_INTERNAL, + config->supported_interfaces); + + config->mac_capabilities |= MAC_10 | MAC_100 | MAC_1000FD; + break; + + /* Port 6 is connected to SoC's XGMII MAC. There is no MII pinout. */ + case 6: + __set_bit(PHY_INTERFACE_MODE_INTERNAL, + config->supported_interfaces); + + config->mac_capabilities |= MAC_10000FD; + break; + } +} + static void mt7530_mac_config(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface) @@ -3220,6 +3247,16 @@ const struct mt753x_info mt753x_table[] = { .phy_write_c45 = mt7531_ind_c45_phy_write, .mac_port_get_caps = mt7988_mac_port_get_caps, }, + [ID_EN7581] = { + .id = ID_EN7581, + .pcs_ops = &mt7530_pcs_ops, + .sw_setup = mt7988_setup, + .phy_read_c22 = mt7531_ind_c22_phy_read, + .phy_write_c22 = mt7531_ind_c22_phy_write, + .phy_read_c45 = mt7531_ind_c45_phy_read, + .phy_write_c45 = mt7531_ind_c45_phy_write, + .mac_port_get_caps = en7581_mac_port_get_caps, + }, }; EXPORT_SYMBOL_GPL(mt753x_table); diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index 28592123070b..6ad33a9f6b1d 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -19,6 +19,7 @@ enum mt753x_id { ID_MT7621 = 1, ID_MT7531 = 2, ID_MT7988 = 3, + ID_EN7581 = 4, }; #define NUM_TRGMII_CTRL 5 @@ -64,25 +65,30 @@ enum mt753x_id { #define MT7531_CPU_PMAP(x) FIELD_PREP(MT7531_CPU_PMAP_MASK, x) #define MT753X_MIRROR_REG(id) ((id == ID_MT7531 || \ - id == ID_MT7988) ? \ + id == ID_MT7988 || \ + id == ID_EN7581) ? \ MT7531_CFC : MT753X_MFC) #define MT753X_MIRROR_EN(id) ((id == ID_MT7531 || \ - id == ID_MT7988) ? \ + id == ID_MT7988 || \ + id == ID_EN7581) ? \ MT7531_MIRROR_EN : MT7530_MIRROR_EN) #define MT753X_MIRROR_PORT_MASK(id) ((id == ID_MT7531 || \ - id == ID_MT7988) ? \ + id == ID_MT7988 || \ + id == ID_EN7581) ? \ MT7531_MIRROR_PORT_MASK : \ MT7530_MIRROR_PORT_MASK) #define MT753X_MIRROR_PORT_GET(id, val) ((id == ID_MT7531 || \ - id == ID_MT7988) ? \ + id == ID_MT7988 || \ + id == ID_EN7581) ? \ MT7531_MIRROR_PORT_GET(val) : \ MT7530_MIRROR_PORT_GET(val)) #define MT753X_MIRROR_PORT_SET(id, val) ((id == ID_MT7531 || \ - id == ID_MT7988) ? \ + id == ID_MT7988 || \ + id == ID_EN7581) ? \ MT7531_MIRROR_PORT_SET(val) : \ MT7530_MIRROR_PORT_SET(val)) @@ -355,6 +361,10 @@ enum mt7530_vlan_port_acc_frm { MT7531_FORCE_MODE_TX_FC | \ MT7531_FORCE_MODE_EEE100 | \ MT7531_FORCE_MODE_EEE1G) +#define MT753X_FORCE_MODE(id) ((id == ID_MT7531 || \ + id == ID_MT7988) ? \ + MT7531_FORCE_MODE_MASK : \ + MT7530_FORCE_MODE) #define PMCR_LINK_SETTINGS_MASK (PMCR_MAC_TX_EN | PMCR_MAC_RX_EN | \ PMCR_FORCE_EEE1G | \ PMCR_FORCE_EEE100 | \ diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c index d9d3e30fd47a..1711e780e65b 100644 --- a/drivers/net/dsa/vitesse-vsc73xx-core.c +++ b/drivers/net/dsa/vitesse-vsc73xx-core.c @@ -40,6 +40,9 @@ #define VSC73XX_BLOCK_ARBITER 0x5 /* Only subblock 0 */ #define VSC73XX_BLOCK_SYSTEM 0x7 /* Only subblock 0 */ +/* MII Block subblock */ +#define VSC73XX_BLOCK_MII_INTERNAL 0x0 /* Internal MDIO subblock */ + #define CPU_PORT 6 /* CPU port */ /* MAC Block registers */ @@ -224,6 +227,11 @@ #define VSC73XX_MII_STAT 0x0 #define VSC73XX_MII_CMD 0x1 #define VSC73XX_MII_DATA 0x2 +#define VSC73XX_MII_MPRES 0x3 + +#define VSC73XX_MII_MPRES_NOPREAMBLE BIT(6) +#define VSC73XX_MII_MPRES_PRESCALEVAL GENMASK(5, 0) +#define VSC73XX_MII_PRESCALEVAL_MIN 3 /* min allowed mdio clock prescaler */ /* Arbiter block 5 registers */ #define VSC73XX_ARBEMPTY 0x0c @@ -684,10 +692,71 @@ vsc73xx_update_vlan_table(struct vsc73xx *vsc, int port, u16 vid, bool set) return vsc73xx_write_vlan_table_entry(vsc, vid, portmap); } +static int vsc73xx_configure_rgmii_port_delay(struct dsa_switch *ds) +{ + /* Keep 2.0 ns delay for backward complatibility */ + u32 tx_delay = VSC73XX_GMIIDELAY_GMII0_GTXDELAY_2_0_NS; + u32 rx_delay = VSC73XX_GMIIDELAY_GMII0_RXDELAY_2_0_NS; + struct dsa_port *dp = dsa_to_port(ds, CPU_PORT); + struct device_node *port_dn = dp->dn; + struct vsc73xx *vsc = ds->priv; + u32 delay; + + if (!of_property_read_u32(port_dn, "tx-internal-delay-ps", &delay)) { + switch (delay) { + case 0: + tx_delay = VSC73XX_GMIIDELAY_GMII0_GTXDELAY_NONE; + break; + case 1400: + tx_delay = VSC73XX_GMIIDELAY_GMII0_GTXDELAY_1_4_NS; + break; + case 1700: + tx_delay = VSC73XX_GMIIDELAY_GMII0_GTXDELAY_1_7_NS; + break; + case 2000: + break; + default: + dev_err(vsc->dev, + "Unsupported RGMII Transmit Clock Delay\n"); + return -EINVAL; + } + } else { + dev_dbg(vsc->dev, + "RGMII Transmit Clock Delay isn't configured, set to 2.0 ns\n"); + } + + if (!of_property_read_u32(port_dn, "rx-internal-delay-ps", &delay)) { + switch (delay) { + case 0: + rx_delay = VSC73XX_GMIIDELAY_GMII0_RXDELAY_NONE; + break; + case 1400: + rx_delay = VSC73XX_GMIIDELAY_GMII0_RXDELAY_1_4_NS; + break; + case 1700: + rx_delay = VSC73XX_GMIIDELAY_GMII0_RXDELAY_1_7_NS; + break; + case 2000: + break; + default: + dev_err(vsc->dev, + "Unsupported RGMII Receive Clock Delay value\n"); + return -EINVAL; + } + } else { + dev_dbg(vsc->dev, + "RGMII Receive Clock Delay isn't configured, set to 2.0 ns\n"); + } + + /* MII delay, set both GTX and RX delay */ + return vsc73xx_write(vsc, VSC73XX_BLOCK_SYSTEM, 0, VSC73XX_GMIIDELAY, + tx_delay | rx_delay); +} + static int vsc73xx_setup(struct dsa_switch *ds) { struct vsc73xx *vsc = ds->priv; - int i, ret; + int i, ret, val; dev_info(vsc->dev, "set up the switch\n"); @@ -746,10 +815,11 @@ static int vsc73xx_setup(struct dsa_switch *ds) VSC73XX_MAC_CFG, VSC73XX_MAC_CFG_RESET); } - /* MII delay, set both GTX and RX delay to 2 ns */ - vsc73xx_write(vsc, VSC73XX_BLOCK_SYSTEM, 0, VSC73XX_GMIIDELAY, - VSC73XX_GMIIDELAY_GMII0_GTXDELAY_2_0_NS | - VSC73XX_GMIIDELAY_GMII0_RXDELAY_2_0_NS); + /* Configure RGMII delay */ + ret = vsc73xx_configure_rgmii_port_delay(ds); + if (ret) + return ret; + /* Ingess VLAN reception mask (table 145) */ vsc73xx_write(vsc, VSC73XX_BLOCK_ANALYZER, 0, VSC73XX_VLANMASK, 0xff); @@ -759,6 +829,15 @@ static int vsc73xx_setup(struct dsa_switch *ds) mdelay(50); + /* Disable preamble and use maximum allowed clock for the internal + * mdio bus, used for communication with internal PHYs only. + */ + val = VSC73XX_MII_MPRES_NOPREAMBLE | + FIELD_PREP(VSC73XX_MII_MPRES_PRESCALEVAL, + VSC73XX_MII_PRESCALEVAL_MIN); + vsc73xx_write(vsc, VSC73XX_BLOCK_MII, VSC73XX_BLOCK_MII_INTERNAL, + VSC73XX_MII_MPRES, val); + /* Release reset from the internal PHYs */ vsc73xx_write(vsc, VSC73XX_BLOCK_SYSTEM, 0, VSC73XX_GLORESET, VSC73XX_GLORESET_PHY_RESET); diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c index 3d8ac63132fb..9e6f91df2ba0 100644 --- a/drivers/net/ethernet/alteon/acenic.c +++ b/drivers/net/ethernet/alteon/acenic.c @@ -1560,9 +1560,9 @@ static void ace_watchdog(struct net_device *data, unsigned int txqueue) } -static void ace_tasklet(struct tasklet_struct *t) +static void ace_bh_work(struct work_struct *work) { - struct ace_private *ap = from_tasklet(ap, t, ace_tasklet); + struct ace_private *ap = from_work(ap, work, ace_bh_work); struct net_device *dev = ap->ndev; int cur_size; @@ -1595,7 +1595,7 @@ static void ace_tasklet(struct tasklet_struct *t) #endif ace_load_jumbo_rx_ring(dev, RX_JUMBO_SIZE - cur_size); } - ap->tasklet_pending = 0; + ap->bh_work_pending = 0; } @@ -1617,7 +1617,7 @@ static void ace_dump_trace(struct ace_private *ap) * * Loading rings is safe without holding the spin lock since this is * done only before the device is enabled, thus no interrupts are - * generated and by the interrupt handler/tasklet handler. + * generated and by the interrupt handler/bh handler. */ static void ace_load_std_rx_ring(struct net_device *dev, int nr_bufs) { @@ -2160,7 +2160,7 @@ static irqreturn_t ace_interrupt(int irq, void *dev_id) */ if (netif_running(dev)) { int cur_size; - int run_tasklet = 0; + int run_bh_work = 0; cur_size = atomic_read(&ap->cur_rx_bufs); if (cur_size < RX_LOW_STD_THRES) { @@ -2172,7 +2172,7 @@ static irqreturn_t ace_interrupt(int irq, void *dev_id) ace_load_std_rx_ring(dev, RX_RING_SIZE - cur_size); } else - run_tasklet = 1; + run_bh_work = 1; } if (!ACE_IS_TIGON_I(ap)) { @@ -2188,7 +2188,7 @@ static irqreturn_t ace_interrupt(int irq, void *dev_id) ace_load_mini_rx_ring(dev, RX_MINI_SIZE - cur_size); } else - run_tasklet = 1; + run_bh_work = 1; } } @@ -2205,12 +2205,12 @@ static irqreturn_t ace_interrupt(int irq, void *dev_id) ace_load_jumbo_rx_ring(dev, RX_JUMBO_SIZE - cur_size); } else - run_tasklet = 1; + run_bh_work = 1; } } - if (run_tasklet && !ap->tasklet_pending) { - ap->tasklet_pending = 1; - tasklet_schedule(&ap->ace_tasklet); + if (run_bh_work && !ap->bh_work_pending) { + ap->bh_work_pending = 1; + queue_work(system_bh_wq, &ap->ace_bh_work); } } @@ -2267,7 +2267,7 @@ static int ace_open(struct net_device *dev) /* * Setup the bottom half rx ring refill handler */ - tasklet_setup(&ap->ace_tasklet, ace_tasklet); + INIT_WORK(&ap->ace_bh_work, ace_bh_work); return 0; } @@ -2301,7 +2301,7 @@ static int ace_close(struct net_device *dev) cmd.idx = 0; ace_issue_cmd(regs, &cmd); - tasklet_kill(&ap->ace_tasklet); + cancel_work_sync(&ap->ace_bh_work); /* * Make sure one CPU is not processing packets while diff --git a/drivers/net/ethernet/alteon/acenic.h b/drivers/net/ethernet/alteon/acenic.h index ca5ce0cbbad1..0e45a97b9c9b 100644 --- a/drivers/net/ethernet/alteon/acenic.h +++ b/drivers/net/ethernet/alteon/acenic.h @@ -2,7 +2,7 @@ #ifndef _ACENIC_H_ #define _ACENIC_H_ #include <linux/interrupt.h> - +#include <linux/workqueue.h> /* * Generate TX index update each time, when TX ring is closed. @@ -667,8 +667,8 @@ struct ace_private struct rx_desc *rx_mini_ring; struct rx_desc *rx_return_ring; - int tasklet_pending, jumbo; - struct tasklet_struct ace_tasklet; + int bh_work_pending, jumbo; + struct work_struct ace_bh_work; struct event *evt_ring; @@ -776,7 +776,7 @@ static int ace_open(struct net_device *dev); static netdev_tx_t ace_start_xmit(struct sk_buff *skb, struct net_device *dev); static int ace_close(struct net_device *dev); -static void ace_tasklet(struct tasklet_struct *t); +static void ace_bh_work(struct work_struct *work); static void ace_dump_trace(struct ace_private *ap); static void ace_set_multicast_list(struct net_device *dev); static int ace_change_mtu(struct net_device *dev, int new_mtu); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index c4a4e316683f..5475867708f4 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -403,9 +403,9 @@ static bool xgbe_ecc_ded(struct xgbe_prv_data *pdata, unsigned long *period, return false; } -static void xgbe_ecc_isr_task(struct tasklet_struct *t) +static void xgbe_ecc_isr_bh_work(struct work_struct *work) { - struct xgbe_prv_data *pdata = from_tasklet(pdata, t, tasklet_ecc); + struct xgbe_prv_data *pdata = from_work(pdata, work, ecc_bh_work); unsigned int ecc_isr; bool stop = false; @@ -465,17 +465,17 @@ static irqreturn_t xgbe_ecc_isr(int irq, void *data) { struct xgbe_prv_data *pdata = data; - if (pdata->isr_as_tasklet) - tasklet_schedule(&pdata->tasklet_ecc); + if (pdata->isr_as_bh_work) + queue_work(system_bh_wq, &pdata->ecc_bh_work); else - xgbe_ecc_isr_task(&pdata->tasklet_ecc); + xgbe_ecc_isr_bh_work(&pdata->ecc_bh_work); return IRQ_HANDLED; } -static void xgbe_isr_task(struct tasklet_struct *t) +static void xgbe_isr_bh_work(struct work_struct *work) { - struct xgbe_prv_data *pdata = from_tasklet(pdata, t, tasklet_dev); + struct xgbe_prv_data *pdata = from_work(pdata, work, dev_bh_work); struct xgbe_hw_if *hw_if = &pdata->hw_if; struct xgbe_channel *channel; unsigned int dma_isr, dma_ch_isr; @@ -582,7 +582,7 @@ isr_done: /* If there is not a separate ECC irq, handle it here */ if (pdata->vdata->ecc_support && (pdata->dev_irq == pdata->ecc_irq)) - xgbe_ecc_isr_task(&pdata->tasklet_ecc); + xgbe_ecc_isr_bh_work(&pdata->ecc_bh_work); /* If there is not a separate I2C irq, handle it here */ if (pdata->vdata->i2c_support && (pdata->dev_irq == pdata->i2c_irq)) @@ -604,10 +604,10 @@ static irqreturn_t xgbe_isr(int irq, void *data) { struct xgbe_prv_data *pdata = data; - if (pdata->isr_as_tasklet) - tasklet_schedule(&pdata->tasklet_dev); + if (pdata->isr_as_bh_work) + queue_work(system_bh_wq, &pdata->dev_bh_work); else - xgbe_isr_task(&pdata->tasklet_dev); + xgbe_isr_bh_work(&pdata->dev_bh_work); return IRQ_HANDLED; } @@ -1007,8 +1007,8 @@ static int xgbe_request_irqs(struct xgbe_prv_data *pdata) unsigned int i; int ret; - tasklet_setup(&pdata->tasklet_dev, xgbe_isr_task); - tasklet_setup(&pdata->tasklet_ecc, xgbe_ecc_isr_task); + INIT_WORK(&pdata->dev_bh_work, xgbe_isr_bh_work); + INIT_WORK(&pdata->ecc_bh_work, xgbe_ecc_isr_bh_work); ret = devm_request_irq(pdata->dev, pdata->dev_irq, xgbe_isr, 0, netdev_name(netdev), pdata); @@ -1078,8 +1078,8 @@ static void xgbe_free_irqs(struct xgbe_prv_data *pdata) devm_free_irq(pdata->dev, pdata->dev_irq, pdata); - tasklet_kill(&pdata->tasklet_dev); - tasklet_kill(&pdata->tasklet_ecc); + cancel_work_sync(&pdata->dev_bh_work); + cancel_work_sync(&pdata->ecc_bh_work); if (pdata->vdata->ecc_support && (pdata->dev_irq != pdata->ecc_irq)) devm_free_irq(pdata->dev, pdata->ecc_irq, pdata); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c b/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c index a9ccc4258ee5..7a833894f52a 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c @@ -274,9 +274,9 @@ static void xgbe_i2c_clear_isr_interrupts(struct xgbe_prv_data *pdata, XI2C_IOREAD(pdata, IC_CLR_STOP_DET); } -static void xgbe_i2c_isr_task(struct tasklet_struct *t) +static void xgbe_i2c_isr_bh_work(struct work_struct *work) { - struct xgbe_prv_data *pdata = from_tasklet(pdata, t, tasklet_i2c); + struct xgbe_prv_data *pdata = from_work(pdata, work, i2c_bh_work); struct xgbe_i2c_op_state *state = &pdata->i2c.op_state; unsigned int isr; @@ -321,10 +321,10 @@ static irqreturn_t xgbe_i2c_isr(int irq, void *data) { struct xgbe_prv_data *pdata = (struct xgbe_prv_data *)data; - if (pdata->isr_as_tasklet) - tasklet_schedule(&pdata->tasklet_i2c); + if (pdata->isr_as_bh_work) + queue_work(system_bh_wq, &pdata->i2c_bh_work); else - xgbe_i2c_isr_task(&pdata->tasklet_i2c); + xgbe_i2c_isr_bh_work(&pdata->i2c_bh_work); return IRQ_HANDLED; } @@ -369,7 +369,7 @@ static void xgbe_i2c_set_target(struct xgbe_prv_data *pdata, unsigned int addr) static irqreturn_t xgbe_i2c_combined_isr(struct xgbe_prv_data *pdata) { - xgbe_i2c_isr_task(&pdata->tasklet_i2c); + xgbe_i2c_isr_bh_work(&pdata->i2c_bh_work); return IRQ_HANDLED; } @@ -449,7 +449,7 @@ static void xgbe_i2c_stop(struct xgbe_prv_data *pdata) if (pdata->dev_irq != pdata->i2c_irq) { devm_free_irq(pdata->dev, pdata->i2c_irq, pdata); - tasklet_kill(&pdata->tasklet_i2c); + cancel_work_sync(&pdata->i2c_bh_work); } } @@ -464,7 +464,7 @@ static int xgbe_i2c_start(struct xgbe_prv_data *pdata) /* If we have a separate I2C irq, enable it */ if (pdata->dev_irq != pdata->i2c_irq) { - tasklet_setup(&pdata->tasklet_i2c, xgbe_i2c_isr_task); + INIT_WORK(&pdata->i2c_bh_work, xgbe_i2c_isr_bh_work); ret = devm_request_irq(pdata->dev, pdata->i2c_irq, xgbe_i2c_isr, 0, pdata->i2c_name, diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c index 4a2dc705b528..07f4f3418d01 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c @@ -703,9 +703,9 @@ static void xgbe_an73_isr(struct xgbe_prv_data *pdata) } } -static void xgbe_an_isr_task(struct tasklet_struct *t) +static void xgbe_an_isr_bh_work(struct work_struct *work) { - struct xgbe_prv_data *pdata = from_tasklet(pdata, t, tasklet_an); + struct xgbe_prv_data *pdata = from_work(pdata, work, an_bh_work); netif_dbg(pdata, intr, pdata->netdev, "AN interrupt received\n"); @@ -727,17 +727,17 @@ static irqreturn_t xgbe_an_isr(int irq, void *data) { struct xgbe_prv_data *pdata = (struct xgbe_prv_data *)data; - if (pdata->isr_as_tasklet) - tasklet_schedule(&pdata->tasklet_an); + if (pdata->isr_as_bh_work) + queue_work(system_bh_wq, &pdata->an_bh_work); else - xgbe_an_isr_task(&pdata->tasklet_an); + xgbe_an_isr_bh_work(&pdata->an_bh_work); return IRQ_HANDLED; } static irqreturn_t xgbe_an_combined_isr(struct xgbe_prv_data *pdata) { - xgbe_an_isr_task(&pdata->tasklet_an); + xgbe_an_isr_bh_work(&pdata->an_bh_work); return IRQ_HANDLED; } @@ -1454,7 +1454,7 @@ static void xgbe_phy_stop(struct xgbe_prv_data *pdata) if (pdata->dev_irq != pdata->an_irq) { devm_free_irq(pdata->dev, pdata->an_irq, pdata); - tasklet_kill(&pdata->tasklet_an); + cancel_work_sync(&pdata->an_bh_work); } pdata->phy_if.phy_impl.stop(pdata); @@ -1477,7 +1477,7 @@ static int xgbe_phy_start(struct xgbe_prv_data *pdata) /* If we have a separate AN irq, enable it */ if (pdata->dev_irq != pdata->an_irq) { - tasklet_setup(&pdata->tasklet_an, xgbe_an_isr_task); + INIT_WORK(&pdata->an_bh_work, xgbe_an_isr_bh_work); ret = devm_request_irq(pdata->dev, pdata->an_irq, xgbe_an_isr, 0, pdata->an_name, diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c index c5e5fac49779..c636999a6a84 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c @@ -139,7 +139,7 @@ static int xgbe_config_multi_msi(struct xgbe_prv_data *pdata) return ret; } - pdata->isr_as_tasklet = 1; + pdata->isr_as_bh_work = 1; pdata->irq_count = ret; pdata->dev_irq = pci_irq_vector(pdata->pcidev, 0); @@ -176,7 +176,7 @@ static int xgbe_config_irqs(struct xgbe_prv_data *pdata) return ret; } - pdata->isr_as_tasklet = pdata->pcidev->msi_enabled ? 1 : 0; + pdata->isr_as_bh_work = pdata->pcidev->msi_enabled ? 1 : 0; pdata->irq_count = 1; pdata->channel_irq_count = 1; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index f01a1e566da6..d85386cac8d1 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -1298,11 +1298,11 @@ struct xgbe_prv_data { unsigned int lpm_ctrl; /* CTRL1 for resume */ - unsigned int isr_as_tasklet; - struct tasklet_struct tasklet_dev; - struct tasklet_struct tasklet_ecc; - struct tasklet_struct tasklet_i2c; - struct tasklet_struct tasklet_an; + unsigned int isr_as_bh_work; + struct work_struct dev_bh_work; + struct work_struct ecc_bh_work; + struct work_struct i2c_bh_work; + struct work_struct an_bh_work; struct dentry *xgbe_debugfs; diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index c2b4188a1ef1..a9040c42d2ff 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -31,6 +31,7 @@ #include <linux/if_vlan.h> #include <linux/prefetch.h> #include <linux/random.h> +#include <linux/workqueue.h> #if IS_ENABLED(CONFIG_VLAN_8021Q) #define BCM_VLAN 1 #endif @@ -3015,9 +3016,9 @@ static int cnic_service_bnx2(void *data, void *status_blk) return cnic_service_bnx2_queues(dev); } -static void cnic_service_bnx2_msix(struct tasklet_struct *t) +static void cnic_service_bnx2_msix(struct work_struct *work) { - struct cnic_local *cp = from_tasklet(cp, t, cnic_irq_task); + struct cnic_local *cp = from_work(cp, work, cnic_irq_bh_work); struct cnic_dev *dev = cp->dev; cp->last_status_idx = cnic_service_bnx2_queues(dev); @@ -3036,7 +3037,7 @@ static void cnic_doirq(struct cnic_dev *dev) prefetch(cp->status_blk.gen); prefetch(&cp->kcq1.kcq[KCQ_PG(prod)][KCQ_IDX(prod)]); - tasklet_schedule(&cp->cnic_irq_task); + queue_work(system_bh_wq, &cp->cnic_irq_bh_work); } } @@ -3140,9 +3141,9 @@ static u32 cnic_service_bnx2x_kcq(struct cnic_dev *dev, struct kcq_info *info) return last_status; } -static void cnic_service_bnx2x_bh(struct tasklet_struct *t) +static void cnic_service_bnx2x_bh_work(struct work_struct *work) { - struct cnic_local *cp = from_tasklet(cp, t, cnic_irq_task); + struct cnic_local *cp = from_work(cp, work, cnic_irq_bh_work); struct cnic_dev *dev = cp->dev; struct bnx2x *bp = netdev_priv(dev->netdev); u32 status_idx, new_status_idx; @@ -4428,7 +4429,7 @@ static void cnic_free_irq(struct cnic_dev *dev) if (ethdev->drv_state & CNIC_DRV_STATE_USING_MSIX) { cp->disable_int_sync(dev); - tasklet_kill(&cp->cnic_irq_task); + cancel_work_sync(&cp->cnic_irq_bh_work); free_irq(ethdev->irq_arr[0].vector, dev); } } @@ -4441,7 +4442,7 @@ static int cnic_request_irq(struct cnic_dev *dev) err = request_irq(ethdev->irq_arr[0].vector, cnic_irq, 0, "cnic", dev); if (err) - tasklet_disable(&cp->cnic_irq_task); + disable_work_sync(&cp->cnic_irq_bh_work); return err; } @@ -4464,7 +4465,7 @@ static int cnic_init_bnx2_irq(struct cnic_dev *dev) CNIC_WR(dev, base + BNX2_HC_CMD_TICKS_OFF, (64 << 16) | 220); cp->last_status_idx = cp->status_blk.bnx2->status_idx; - tasklet_setup(&cp->cnic_irq_task, cnic_service_bnx2_msix); + INIT_WORK(&cp->cnic_irq_bh_work, cnic_service_bnx2_msix); err = cnic_request_irq(dev); if (err) return err; @@ -4873,7 +4874,7 @@ static int cnic_init_bnx2x_irq(struct cnic_dev *dev) struct cnic_eth_dev *ethdev = cp->ethdev; int err = 0; - tasklet_setup(&cp->cnic_irq_task, cnic_service_bnx2x_bh); + INIT_WORK(&cp->cnic_irq_bh_work, cnic_service_bnx2x_bh_work); if (ethdev->drv_state & CNIC_DRV_STATE_USING_MSIX) err = cnic_request_irq(dev); diff --git a/drivers/net/ethernet/broadcom/cnic.h b/drivers/net/ethernet/broadcom/cnic.h index fedc84ada937..1a314a75d2d2 100644 --- a/drivers/net/ethernet/broadcom/cnic.h +++ b/drivers/net/ethernet/broadcom/cnic.h @@ -268,7 +268,7 @@ struct cnic_local { u32 bnx2x_igu_sb_id; u32 int_num; u32 last_status_idx; - struct tasklet_struct cnic_irq_task; + struct work_struct cnic_irq_bh_work; struct kcqe *completed_kcq[MAX_COMPLETED_KCQE]; diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index ea71612f6b36..5740c98d8c9f 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -13,6 +13,7 @@ #include <linux/net_tstamp.h> #include <linux/interrupt.h> #include <linux/phy/phy.h> +#include <linux/workqueue.h> #if defined(CONFIG_ARCH_DMA_ADDR_T_64BIT) || defined(CONFIG_MACB_USE_HWSTAMP) #define MACB_EXT_DESC @@ -1330,7 +1331,7 @@ struct macb { spinlock_t rx_fs_lock; unsigned int max_tuples; - struct tasklet_struct hresp_err_tasklet; + struct work_struct hresp_err_bh_work; int rx_bd_rd_prefetch; int tx_bd_rd_prefetch; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 11665be3a22c..95e8742dce1d 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1792,9 +1792,9 @@ static int macb_tx_poll(struct napi_struct *napi, int budget) return work_done; } -static void macb_hresp_error_task(struct tasklet_struct *t) +static void macb_hresp_error_task(struct work_struct *work) { - struct macb *bp = from_tasklet(bp, t, hresp_err_tasklet); + struct macb *bp = from_work(bp, work, hresp_err_bh_work); struct net_device *dev = bp->dev; struct macb_queue *queue; unsigned int q; @@ -1994,7 +1994,7 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id) } if (status & MACB_BIT(HRESP)) { - tasklet_schedule(&bp->hresp_err_tasklet); + queue_work(system_bh_wq, &bp->hresp_err_bh_work); netdev_err(dev, "DMA bus error: HRESP not OK\n"); if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE) @@ -5172,7 +5172,7 @@ static int macb_probe(struct platform_device *pdev) goto err_out_unregister_mdio; } - tasklet_setup(&bp->hresp_err_tasklet, macb_hresp_error_task); + INIT_WORK(&bp->hresp_err_bh_work, macb_hresp_error_task); netdev_info(dev, "Cadence %s rev 0x%08x at 0x%08lx irq %d (%pM)\n", macb_is_gem(bp) ? "GEM" : "MACB", macb_readl(bp, MID), @@ -5216,7 +5216,7 @@ static void macb_remove(struct platform_device *pdev) mdiobus_free(bp->mii_bus); unregister_netdev(dev); - tasklet_kill(&bp->hresp_err_tasklet); + cancel_work_sync(&bp->hresp_err_bh_work); pm_runtime_disable(&pdev->dev); pm_runtime_dont_use_autosuspend(&pdev->dev); if (!pm_runtime_suspended(&pdev->dev)) { diff --git a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c index 854d87e1125c..2e3973a32d9d 100644 --- a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c +++ b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c @@ -342,10 +342,10 @@ int cxgbi_ppm_release(struct cxgbi_ppm *ppm) } EXPORT_SYMBOL(cxgbi_ppm_release); -static struct cxgbi_ppm_pool *ppm_alloc_cpu_pool(unsigned int *total, - unsigned int *pcpu_ppmax) +static struct cxgbi_ppm_pool __percpu * +ppm_alloc_cpu_pool(unsigned int *total, unsigned int *pcpu_ppmax) { - struct cxgbi_ppm_pool *pools; + struct cxgbi_ppm_pool __percpu *pools; unsigned int ppmax = (*total) / num_possible_cpus(); unsigned int max = (PCPU_MIN_UNIT_SIZE - sizeof(*pools)) << 3; unsigned int bmap; @@ -392,7 +392,7 @@ int cxgbi_ppm_init(void **ppm_pp, struct net_device *ndev, unsigned int iscsi_edram_size) { struct cxgbi_ppm *ppm = (struct cxgbi_ppm *)(*ppm_pp); - struct cxgbi_ppm_pool *pool = NULL; + struct cxgbi_ppm_pool __percpu *pool = NULL; unsigned int pool_index_max = 0; unsigned int ppmax_pool = 0; unsigned int ppod_bmap_size; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index a923cb95cdc6..8c3bf0faba63 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -4606,7 +4606,7 @@ fec_drv_remove(struct platform_device *pdev) free_netdev(ndev); } -static int __maybe_unused fec_suspend(struct device *dev) +static int fec_suspend(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); struct fec_enet_private *fep = netdev_priv(ndev); @@ -4659,7 +4659,7 @@ static int __maybe_unused fec_suspend(struct device *dev) return 0; } -static int __maybe_unused fec_resume(struct device *dev) +static int fec_resume(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); struct fec_enet_private *fep = netdev_priv(ndev); @@ -4714,7 +4714,7 @@ failed_clk: return ret; } -static int __maybe_unused fec_runtime_suspend(struct device *dev) +static int fec_runtime_suspend(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); struct fec_enet_private *fep = netdev_priv(ndev); @@ -4725,7 +4725,7 @@ static int __maybe_unused fec_runtime_suspend(struct device *dev) return 0; } -static int __maybe_unused fec_runtime_resume(struct device *dev) +static int fec_runtime_resume(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); struct fec_enet_private *fep = netdev_priv(ndev); @@ -4746,14 +4746,14 @@ failed_clk_ipg: } static const struct dev_pm_ops fec_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(fec_suspend, fec_resume) - SET_RUNTIME_PM_OPS(fec_runtime_suspend, fec_runtime_resume, NULL) + SYSTEM_SLEEP_PM_OPS(fec_suspend, fec_resume) + RUNTIME_PM_OPS(fec_runtime_suspend, fec_runtime_resume, NULL) }; static struct platform_driver fec_driver = { .driver = { .name = DRIVER_NAME, - .pm = &fec_pm_ops, + .pm = pm_ptr(&fec_pm_ops), .of_match_table = fec_dt_ids, .suppress_bind_attrs = true, }, diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c index 406e75e9e5ea..f17a4e511510 100644 --- a/drivers/net/ethernet/freescale/fman/fman_port.c +++ b/drivers/net/ethernet/freescale/fman/fman_port.c @@ -1748,7 +1748,7 @@ static int fman_port_probe(struct platform_device *of_dev) struct resource res; struct resource *dev_res; u32 val; - int err = 0, lenp; + int err = 0; enum fman_port_type port_type; u16 port_speed; u8 port_id; @@ -1795,7 +1795,7 @@ static int fman_port_probe(struct platform_device *of_dev) if (of_device_is_compatible(port_node, "fsl,fman-v3-port-tx")) { port_type = FMAN_PORT_TYPE_TX; port_speed = 1000; - if (of_find_property(port_node, "fsl,fman-10g-port", &lenp)) + if (of_property_read_bool(port_node, "fsl,fman-10g-port")) port_speed = 10000; } else if (of_device_is_compatible(port_node, "fsl,fman-v2-port-tx")) { @@ -1808,7 +1808,7 @@ static int fman_port_probe(struct platform_device *of_dev) } else if (of_device_is_compatible(port_node, "fsl,fman-v3-port-rx")) { port_type = FMAN_PORT_TYPE_RX; port_speed = 1000; - if (of_find_property(port_node, "fsl,fman-10g-port", &lenp)) + if (of_property_read_bool(port_node, "fsl,fman-10g-port")) port_speed = 10000; } else if (of_device_is_compatible(port_node, "fsl,fman-v2-port-rx")) { diff --git a/drivers/net/ethernet/fungible/funcore/fun_dev.c b/drivers/net/ethernet/fungible/funcore/fun_dev.c index a7fbd4cd560a..ce97b76f9ae0 100644 --- a/drivers/net/ethernet/fungible/funcore/fun_dev.c +++ b/drivers/net/ethernet/fungible/funcore/fun_dev.c @@ -546,17 +546,14 @@ int fun_bind(struct fun_dev *fdev, enum fun_admin_bind_type type0, unsigned int id0, enum fun_admin_bind_type type1, unsigned int id1) { - struct { - struct fun_admin_bind_req req; - struct fun_admin_bind_entry entry[2]; - } cmd = { - .req.common = FUN_ADMIN_REQ_COMMON_INIT2(FUN_ADMIN_OP_BIND, - sizeof(cmd)), - .entry[0] = FUN_ADMIN_BIND_ENTRY_INIT(type0, id0), - .entry[1] = FUN_ADMIN_BIND_ENTRY_INIT(type1, id1), - }; + DEFINE_RAW_FLEX(struct fun_admin_bind_req, cmd, entry, 2); + + cmd->common = FUN_ADMIN_REQ_COMMON_INIT2(FUN_ADMIN_OP_BIND, + __struct_size(cmd)); + cmd->entry[0] = FUN_ADMIN_BIND_ENTRY_INIT(type0, id0); + cmd->entry[1] = FUN_ADMIN_BIND_ENTRY_INIT(type1, id1); - return fun_submit_admin_sync_cmd(fdev, &cmd.req.common, NULL, 0, 0); + return fun_submit_admin_sync_cmd(fdev, &cmd->common, NULL, 0, 0); } EXPORT_SYMBOL_GPL(fun_bind); diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 4c9d9badd698..b619a3ec245b 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -39,7 +39,8 @@ #include "ibmveth.h" static irqreturn_t ibmveth_interrupt(int irq, void *dev_instance); -static void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter); +static void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter, + bool reuse); static unsigned long ibmveth_get_desired_dma(struct vio_dev *vdev); static struct kobj_type ktype_veth_pool; @@ -226,6 +227,16 @@ static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter, for (i = 0; i < count; ++i) { union ibmveth_buf_desc desc; + free_index = pool->consumer_index; + index = pool->free_map[free_index]; + skb = NULL; + + BUG_ON(index == IBM_VETH_INVALID_MAP); + + /* are we allocating a new buffer or recycling an old one */ + if (pool->skbuff[index]) + goto reuse; + skb = netdev_alloc_skb(adapter->netdev, pool->buff_size); if (!skb) { @@ -235,46 +246,46 @@ static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter, break; } - free_index = pool->consumer_index; - pool->consumer_index++; - if (pool->consumer_index >= pool->size) - pool->consumer_index = 0; - index = pool->free_map[free_index]; - - BUG_ON(index == IBM_VETH_INVALID_MAP); - BUG_ON(pool->skbuff[index] != NULL); - dma_addr = dma_map_single(&adapter->vdev->dev, skb->data, pool->buff_size, DMA_FROM_DEVICE); if (dma_mapping_error(&adapter->vdev->dev, dma_addr)) goto failure; - pool->free_map[free_index] = IBM_VETH_INVALID_MAP; pool->dma_addr[index] = dma_addr; pool->skbuff[index] = skb; - correlator = ((u64)pool->index << 32) | index; - *(u64 *)skb->data = correlator; - - desc.fields.flags_len = IBMVETH_BUF_VALID | pool->buff_size; - desc.fields.address = dma_addr; - if (rx_flush) { unsigned int len = min(pool->buff_size, - adapter->netdev->mtu + - IBMVETH_BUFF_OH); + adapter->netdev->mtu + + IBMVETH_BUFF_OH); ibmveth_flush_buffer(skb->data, len); } +reuse: + dma_addr = pool->dma_addr[index]; + desc.fields.flags_len = IBMVETH_BUF_VALID | pool->buff_size; + desc.fields.address = dma_addr; + + correlator = ((u64)pool->index << 32) | index; + *(u64 *)pool->skbuff[index]->data = correlator; + lpar_rc = h_add_logical_lan_buffer(adapter->vdev->unit_address, desc.desc); if (lpar_rc != H_SUCCESS) { + netdev_warn(adapter->netdev, + "%sadd_logical_lan failed %lu\n", + skb ? "" : "When recycling: ", lpar_rc); goto failure; - } else { - buffers_added++; - adapter->replenish_add_buff_success++; } + + pool->free_map[free_index] = IBM_VETH_INVALID_MAP; + pool->consumer_index++; + if (pool->consumer_index >= pool->size) + pool->consumer_index = 0; + + buffers_added++; + adapter->replenish_add_buff_success++; } mb(); @@ -282,17 +293,13 @@ static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter, return; failure: - pool->free_map[free_index] = index; - pool->skbuff[index] = NULL; - if (pool->consumer_index == 0) - pool->consumer_index = pool->size - 1; - else - pool->consumer_index--; - if (!dma_mapping_error(&adapter->vdev->dev, dma_addr)) + + if (dma_addr && !dma_mapping_error(&adapter->vdev->dev, dma_addr)) dma_unmap_single(&adapter->vdev->dev, pool->dma_addr[index], pool->buff_size, DMA_FROM_DEVICE); - dev_kfree_skb_any(skb); + dev_kfree_skb_any(pool->skbuff[index]); + pool->skbuff[index] = NULL; adapter->replenish_add_buff_failure++; mb(); @@ -365,7 +372,7 @@ static void ibmveth_free_buffer_pool(struct ibmveth_adapter *adapter, /* remove a buffer from a pool */ static void ibmveth_remove_buffer_from_pool(struct ibmveth_adapter *adapter, - u64 correlator) + u64 correlator, bool reuse) { unsigned int pool = correlator >> 32; unsigned int index = correlator & 0xffffffffUL; @@ -376,15 +383,23 @@ static void ibmveth_remove_buffer_from_pool(struct ibmveth_adapter *adapter, BUG_ON(index >= adapter->rx_buff_pool[pool].size); skb = adapter->rx_buff_pool[pool].skbuff[index]; - BUG_ON(skb == NULL); - adapter->rx_buff_pool[pool].skbuff[index] = NULL; + /* if we are going to reuse the buffer then keep the pointers around + * but mark index as available. replenish will see the skb pointer and + * assume it is to be recycled. + */ + if (!reuse) { + /* remove the skb pointer to mark free. actual freeing is done + * by upper level networking after gro_recieve + */ + adapter->rx_buff_pool[pool].skbuff[index] = NULL; - dma_unmap_single(&adapter->vdev->dev, - adapter->rx_buff_pool[pool].dma_addr[index], - adapter->rx_buff_pool[pool].buff_size, - DMA_FROM_DEVICE); + dma_unmap_single(&adapter->vdev->dev, + adapter->rx_buff_pool[pool].dma_addr[index], + adapter->rx_buff_pool[pool].buff_size, + DMA_FROM_DEVICE); + } free_index = adapter->rx_buff_pool[pool].producer_index; adapter->rx_buff_pool[pool].producer_index++; @@ -411,51 +426,13 @@ static inline struct sk_buff *ibmveth_rxq_get_buffer(struct ibmveth_adapter *ada return adapter->rx_buff_pool[pool].skbuff[index]; } -/* recycle the current buffer on the rx queue */ -static int ibmveth_rxq_recycle_buffer(struct ibmveth_adapter *adapter) +static void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter, + bool reuse) { - u32 q_index = adapter->rx_queue.index; - u64 correlator = adapter->rx_queue.queue_addr[q_index].correlator; - unsigned int pool = correlator >> 32; - unsigned int index = correlator & 0xffffffffUL; - union ibmveth_buf_desc desc; - unsigned long lpar_rc; - int ret = 1; - - BUG_ON(pool >= IBMVETH_NUM_BUFF_POOLS); - BUG_ON(index >= adapter->rx_buff_pool[pool].size); - - if (!adapter->rx_buff_pool[pool].active) { - ibmveth_rxq_harvest_buffer(adapter); - ibmveth_free_buffer_pool(adapter, &adapter->rx_buff_pool[pool]); - goto out; - } - - desc.fields.flags_len = IBMVETH_BUF_VALID | - adapter->rx_buff_pool[pool].buff_size; - desc.fields.address = adapter->rx_buff_pool[pool].dma_addr[index]; - - lpar_rc = h_add_logical_lan_buffer(adapter->vdev->unit_address, desc.desc); - - if (lpar_rc != H_SUCCESS) { - netdev_dbg(adapter->netdev, "h_add_logical_lan_buffer failed " - "during recycle rc=%ld", lpar_rc); - ibmveth_remove_buffer_from_pool(adapter, adapter->rx_queue.queue_addr[adapter->rx_queue.index].correlator); - ret = 0; - } - - if (++adapter->rx_queue.index == adapter->rx_queue.num_slots) { - adapter->rx_queue.index = 0; - adapter->rx_queue.toggle = !adapter->rx_queue.toggle; - } - -out: - return ret; -} + u64 cor; -static void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter) -{ - ibmveth_remove_buffer_from_pool(adapter, adapter->rx_queue.queue_addr[adapter->rx_queue.index].correlator); + cor = adapter->rx_queue.queue_addr[adapter->rx_queue.index].correlator; + ibmveth_remove_buffer_from_pool(adapter, cor, reuse); if (++adapter->rx_queue.index == adapter->rx_queue.num_slots) { adapter->rx_queue.index = 0; @@ -1337,6 +1314,7 @@ static int ibmveth_poll(struct napi_struct *napi, int budget) unsigned long lpar_rc; u16 mss = 0; +restart_poll: while (frames_processed < budget) { if (!ibmveth_rxq_pending_buffer(adapter)) break; @@ -1346,7 +1324,7 @@ static int ibmveth_poll(struct napi_struct *napi, int budget) wmb(); /* suggested by larson1 */ adapter->rx_invalid_buffer++; netdev_dbg(netdev, "recycling invalid buffer\n"); - ibmveth_rxq_recycle_buffer(adapter); + ibmveth_rxq_harvest_buffer(adapter, true); } else { struct sk_buff *skb, *new_skb; int length = ibmveth_rxq_frame_length(adapter); @@ -1379,11 +1357,10 @@ static int ibmveth_poll(struct napi_struct *napi, int budget) if (rx_flush) ibmveth_flush_buffer(skb->data, length + offset); - if (!ibmveth_rxq_recycle_buffer(adapter)) - kfree_skb(skb); + ibmveth_rxq_harvest_buffer(adapter, true); skb = new_skb; } else { - ibmveth_rxq_harvest_buffer(adapter); + ibmveth_rxq_harvest_buffer(adapter, false); skb_reserve(skb, offset); } @@ -1420,24 +1397,25 @@ static int ibmveth_poll(struct napi_struct *napi, int budget) ibmveth_replenish_task(adapter); - if (frames_processed < budget) { - napi_complete_done(napi, frames_processed); + if (frames_processed == budget) + goto out; - /* We think we are done - reenable interrupts, - * then check once more to make sure we are done. - */ - lpar_rc = h_vio_signal(adapter->vdev->unit_address, - VIO_IRQ_ENABLE); + if (!napi_complete_done(napi, frames_processed)) + goto out; - BUG_ON(lpar_rc != H_SUCCESS); + /* We think we are done - reenable interrupts, + * then check once more to make sure we are done. + */ + lpar_rc = h_vio_signal(adapter->vdev->unit_address, VIO_IRQ_ENABLE); + BUG_ON(lpar_rc != H_SUCCESS); - if (ibmveth_rxq_pending_buffer(adapter) && - napi_schedule(napi)) { - lpar_rc = h_vio_signal(adapter->vdev->unit_address, - VIO_IRQ_DISABLE); - } + if (ibmveth_rxq_pending_buffer(adapter) && napi_schedule(napi)) { + lpar_rc = h_vio_signal(adapter->vdev->unit_address, + VIO_IRQ_DISABLE); + goto restart_poll; } +out: return frames_processed; } diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h index e809f91c08fb..9e02e4367bec 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h @@ -1088,7 +1088,7 @@ struct mvpp2 { unsigned int max_port_rxqs; /* Workqueue to gather hardware statistics */ - char queue_name[30]; + char queue_name[31]; struct workqueue_struct *stats_queue; /* Debugfs root entry */ diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/mediatek/airoha_eth.c index 1c5b85a86df1..1fb46db0c1e9 100644 --- a/drivers/net/ethernet/mediatek/airoha_eth.c +++ b/drivers/net/ethernet/mediatek/airoha_eth.c @@ -18,6 +18,7 @@ #include <uapi/linux/ppp_defs.h> #define AIROHA_MAX_NUM_GDM_PORTS 1 +#define AIROHA_MAX_NUM_QDMA 2 #define AIROHA_MAX_NUM_RSTS 3 #define AIROHA_MAX_NUM_XSI_RSTS 5 #define AIROHA_MAX_MTU 2000 @@ -727,7 +728,7 @@ struct airoha_queue_entry { }; struct airoha_queue { - struct airoha_eth *eth; + struct airoha_qdma *qdma; /* protect concurrent queue accesses */ spinlock_t lock; @@ -746,7 +747,7 @@ struct airoha_queue { }; struct airoha_tx_irq_queue { - struct airoha_eth *eth; + struct airoha_qdma *qdma; struct napi_struct napi; u32 *q; @@ -782,9 +783,30 @@ struct airoha_hw_stats { u64 rx_len[7]; }; +struct airoha_qdma { + struct airoha_eth *eth; + void __iomem *regs; + + /* protect concurrent irqmask accesses */ + spinlock_t irq_lock; + u32 irqmask[QDMA_INT_REG_MAX]; + int irq; + + struct airoha_tx_irq_queue q_tx_irq[AIROHA_NUM_TX_IRQ]; + + struct airoha_queue q_tx[AIROHA_NUM_TX_RING]; + struct airoha_queue q_rx[AIROHA_NUM_RX_RING]; + + /* descriptor and packet buffers for qdma hw forward */ + struct { + void *desc; + void *q; + } hfwd; +}; + struct airoha_gdm_port { + struct airoha_qdma *qdma; struct net_device *dev; - struct airoha_eth *eth; int id; struct airoha_hw_stats stats; @@ -794,31 +816,15 @@ struct airoha_eth { struct device *dev; unsigned long state; - - void __iomem *qdma_regs; void __iomem *fe_regs; - /* protect concurrent irqmask accesses */ - spinlock_t irq_lock; - u32 irqmask[QDMA_INT_REG_MAX]; - int irq; - struct reset_control_bulk_data rsts[AIROHA_MAX_NUM_RSTS]; struct reset_control_bulk_data xsi_rsts[AIROHA_MAX_NUM_XSI_RSTS]; - struct airoha_gdm_port *ports[AIROHA_MAX_NUM_GDM_PORTS]; - struct net_device *napi_dev; - struct airoha_queue q_tx[AIROHA_NUM_TX_RING]; - struct airoha_queue q_rx[AIROHA_NUM_RX_RING]; - struct airoha_tx_irq_queue q_tx_irq[AIROHA_NUM_TX_IRQ]; - - /* descriptor and packet buffers for qdma hw forward */ - struct { - void *desc; - void *q; - } hfwd; + struct airoha_qdma qdma[AIROHA_MAX_NUM_QDMA]; + struct airoha_gdm_port *ports[AIROHA_MAX_NUM_GDM_PORTS]; }; static u32 airoha_rr(void __iomem *base, u32 offset) @@ -850,48 +856,48 @@ static u32 airoha_rmw(void __iomem *base, u32 offset, u32 mask, u32 val) #define airoha_fe_clear(eth, offset, val) \ airoha_rmw((eth)->fe_regs, (offset), (val), 0) -#define airoha_qdma_rr(eth, offset) \ - airoha_rr((eth)->qdma_regs, (offset)) -#define airoha_qdma_wr(eth, offset, val) \ - airoha_wr((eth)->qdma_regs, (offset), (val)) -#define airoha_qdma_rmw(eth, offset, mask, val) \ - airoha_rmw((eth)->qdma_regs, (offset), (mask), (val)) -#define airoha_qdma_set(eth, offset, val) \ - airoha_rmw((eth)->qdma_regs, (offset), 0, (val)) -#define airoha_qdma_clear(eth, offset, val) \ - airoha_rmw((eth)->qdma_regs, (offset), (val), 0) - -static void airoha_qdma_set_irqmask(struct airoha_eth *eth, int index, +#define airoha_qdma_rr(qdma, offset) \ + airoha_rr((qdma)->regs, (offset)) +#define airoha_qdma_wr(qdma, offset, val) \ + airoha_wr((qdma)->regs, (offset), (val)) +#define airoha_qdma_rmw(qdma, offset, mask, val) \ + airoha_rmw((qdma)->regs, (offset), (mask), (val)) +#define airoha_qdma_set(qdma, offset, val) \ + airoha_rmw((qdma)->regs, (offset), 0, (val)) +#define airoha_qdma_clear(qdma, offset, val) \ + airoha_rmw((qdma)->regs, (offset), (val), 0) + +static void airoha_qdma_set_irqmask(struct airoha_qdma *qdma, int index, u32 clear, u32 set) { unsigned long flags; - if (WARN_ON_ONCE(index >= ARRAY_SIZE(eth->irqmask))) + if (WARN_ON_ONCE(index >= ARRAY_SIZE(qdma->irqmask))) return; - spin_lock_irqsave(ð->irq_lock, flags); + spin_lock_irqsave(&qdma->irq_lock, flags); - eth->irqmask[index] &= ~clear; - eth->irqmask[index] |= set; - airoha_qdma_wr(eth, REG_INT_ENABLE(index), eth->irqmask[index]); + qdma->irqmask[index] &= ~clear; + qdma->irqmask[index] |= set; + airoha_qdma_wr(qdma, REG_INT_ENABLE(index), qdma->irqmask[index]); /* Read irq_enable register in order to guarantee the update above * completes in the spinlock critical section. */ - airoha_qdma_rr(eth, REG_INT_ENABLE(index)); + airoha_qdma_rr(qdma, REG_INT_ENABLE(index)); - spin_unlock_irqrestore(ð->irq_lock, flags); + spin_unlock_irqrestore(&qdma->irq_lock, flags); } -static void airoha_qdma_irq_enable(struct airoha_eth *eth, int index, +static void airoha_qdma_irq_enable(struct airoha_qdma *qdma, int index, u32 mask) { - airoha_qdma_set_irqmask(eth, index, 0, mask); + airoha_qdma_set_irqmask(qdma, index, 0, mask); } -static void airoha_qdma_irq_disable(struct airoha_eth *eth, int index, +static void airoha_qdma_irq_disable(struct airoha_qdma *qdma, int index, u32 mask) { - airoha_qdma_set_irqmask(eth, index, mask, 0); + airoha_qdma_set_irqmask(qdma, index, mask, 0); } static void airoha_set_macaddr(struct airoha_eth *eth, const u8 *addr) @@ -1383,8 +1389,9 @@ static int airoha_fe_init(struct airoha_eth *eth) static int airoha_qdma_fill_rx_queue(struct airoha_queue *q) { enum dma_data_direction dir = page_pool_get_dma_dir(q->page_pool); - struct airoha_eth *eth = q->eth; - int qid = q - ð->q_rx[0]; + struct airoha_qdma *qdma = q->qdma; + struct airoha_eth *eth = qdma->eth; + int qid = q - &qdma->q_rx[0]; int nframes = 0; while (q->queued < q->ndesc - 1) { @@ -1420,7 +1427,8 @@ static int airoha_qdma_fill_rx_queue(struct airoha_queue *q) WRITE_ONCE(desc->msg2, 0); WRITE_ONCE(desc->msg3, 0); - airoha_qdma_rmw(eth, REG_RX_CPU_IDX(qid), RX_RING_CPU_IDX_MASK, + airoha_qdma_rmw(qdma, REG_RX_CPU_IDX(qid), + RX_RING_CPU_IDX_MASK, FIELD_PREP(RX_RING_CPU_IDX_MASK, q->head)); } @@ -1450,8 +1458,9 @@ static int airoha_qdma_get_gdm_port(struct airoha_eth *eth, static int airoha_qdma_rx_process(struct airoha_queue *q, int budget) { enum dma_data_direction dir = page_pool_get_dma_dir(q->page_pool); - struct airoha_eth *eth = q->eth; - int qid = q - ð->q_rx[0]; + struct airoha_qdma *qdma = q->qdma; + struct airoha_eth *eth = qdma->eth; + int qid = q - &qdma->q_rx[0]; int done = 0; while (done < budget) { @@ -1513,7 +1522,6 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget) static int airoha_qdma_rx_napi_poll(struct napi_struct *napi, int budget) { struct airoha_queue *q = container_of(napi, struct airoha_queue, napi); - struct airoha_eth *eth = q->eth; int cur, done = 0; do { @@ -1522,14 +1530,14 @@ static int airoha_qdma_rx_napi_poll(struct napi_struct *napi, int budget) } while (cur && done < budget); if (done < budget && napi_complete(napi)) - airoha_qdma_irq_enable(eth, QDMA_INT_REG_IDX1, + airoha_qdma_irq_enable(q->qdma, QDMA_INT_REG_IDX1, RX_DONE_INT_MASK); return done; } -static int airoha_qdma_init_rx_queue(struct airoha_eth *eth, - struct airoha_queue *q, int ndesc) +static int airoha_qdma_init_rx_queue(struct airoha_queue *q, + struct airoha_qdma *qdma, int ndesc) { const struct page_pool_params pp_params = { .order = 0, @@ -1538,15 +1546,16 @@ static int airoha_qdma_init_rx_queue(struct airoha_eth *eth, .dma_dir = DMA_FROM_DEVICE, .max_len = PAGE_SIZE, .nid = NUMA_NO_NODE, - .dev = eth->dev, + .dev = qdma->eth->dev, .napi = &q->napi, }; - int qid = q - ð->q_rx[0], thr; + struct airoha_eth *eth = qdma->eth; + int qid = q - &qdma->q_rx[0], thr; dma_addr_t dma_addr; q->buf_size = PAGE_SIZE / 2; q->ndesc = ndesc; - q->eth = eth; + q->qdma = qdma; q->entry = devm_kzalloc(eth->dev, q->ndesc * sizeof(*q->entry), GFP_KERNEL); @@ -1568,14 +1577,15 @@ static int airoha_qdma_init_rx_queue(struct airoha_eth *eth, netif_napi_add(eth->napi_dev, &q->napi, airoha_qdma_rx_napi_poll); - airoha_qdma_wr(eth, REG_RX_RING_BASE(qid), dma_addr); - airoha_qdma_rmw(eth, REG_RX_RING_SIZE(qid), RX_RING_SIZE_MASK, + airoha_qdma_wr(qdma, REG_RX_RING_BASE(qid), dma_addr); + airoha_qdma_rmw(qdma, REG_RX_RING_SIZE(qid), + RX_RING_SIZE_MASK, FIELD_PREP(RX_RING_SIZE_MASK, ndesc)); thr = clamp(ndesc >> 3, 1, 32); - airoha_qdma_rmw(eth, REG_RX_RING_SIZE(qid), RX_RING_THR_MASK, + airoha_qdma_rmw(qdma, REG_RX_RING_SIZE(qid), RX_RING_THR_MASK, FIELD_PREP(RX_RING_THR_MASK, thr)); - airoha_qdma_rmw(eth, REG_RX_DMA_IDX(qid), RX_RING_DMA_IDX_MASK, + airoha_qdma_rmw(qdma, REG_RX_DMA_IDX(qid), RX_RING_DMA_IDX_MASK, FIELD_PREP(RX_RING_DMA_IDX_MASK, q->head)); airoha_qdma_fill_rx_queue(q); @@ -1585,7 +1595,7 @@ static int airoha_qdma_init_rx_queue(struct airoha_eth *eth, static void airoha_qdma_cleanup_rx_queue(struct airoha_queue *q) { - struct airoha_eth *eth = q->eth; + struct airoha_eth *eth = q->qdma->eth; while (q->queued) { struct airoha_queue_entry *e = &q->entry[q->tail]; @@ -1599,11 +1609,11 @@ static void airoha_qdma_cleanup_rx_queue(struct airoha_queue *q) } } -static int airoha_qdma_init_rx(struct airoha_eth *eth) +static int airoha_qdma_init_rx(struct airoha_qdma *qdma) { int i; - for (i = 0; i < ARRAY_SIZE(eth->q_rx); i++) { + for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) { int err; if (!(RX_DONE_INT_MASK & BIT(i))) { @@ -1611,7 +1621,7 @@ static int airoha_qdma_init_rx(struct airoha_eth *eth) continue; } - err = airoha_qdma_init_rx_queue(eth, ð->q_rx[i], + err = airoha_qdma_init_rx_queue(&qdma->q_rx[i], qdma, RX_DSCP_NUM(i)); if (err) return err; @@ -1623,12 +1633,14 @@ static int airoha_qdma_init_rx(struct airoha_eth *eth) static int airoha_qdma_tx_napi_poll(struct napi_struct *napi, int budget) { struct airoha_tx_irq_queue *irq_q; + struct airoha_qdma *qdma; struct airoha_eth *eth; int id, done = 0; irq_q = container_of(napi, struct airoha_tx_irq_queue, napi); - eth = irq_q->eth; - id = irq_q - ð->q_tx_irq[0]; + qdma = irq_q->qdma; + id = irq_q - &qdma->q_tx_irq[0]; + eth = qdma->eth; while (irq_q->queued > 0 && done < budget) { u32 qid, last, val = irq_q->q[irq_q->head]; @@ -1645,10 +1657,10 @@ static int airoha_qdma_tx_napi_poll(struct napi_struct *napi, int budget) last = FIELD_GET(IRQ_DESC_IDX_MASK, val); qid = FIELD_GET(IRQ_RING_IDX_MASK, val); - if (qid >= ARRAY_SIZE(eth->q_tx)) + if (qid >= ARRAY_SIZE(qdma->q_tx)) continue; - q = ð->q_tx[qid]; + q = &qdma->q_tx[qid]; if (!q->ndesc) continue; @@ -1697,28 +1709,29 @@ static int airoha_qdma_tx_napi_poll(struct napi_struct *napi, int budget) int i, len = done >> 7; for (i = 0; i < len; i++) - airoha_qdma_rmw(eth, REG_IRQ_CLEAR_LEN(id), + airoha_qdma_rmw(qdma, REG_IRQ_CLEAR_LEN(id), IRQ_CLEAR_LEN_MASK, 0x80); - airoha_qdma_rmw(eth, REG_IRQ_CLEAR_LEN(id), + airoha_qdma_rmw(qdma, REG_IRQ_CLEAR_LEN(id), IRQ_CLEAR_LEN_MASK, (done & 0x7f)); } if (done < budget && napi_complete(napi)) - airoha_qdma_irq_enable(eth, QDMA_INT_REG_IDX0, + airoha_qdma_irq_enable(qdma, QDMA_INT_REG_IDX0, TX_DONE_INT_MASK(id)); return done; } -static int airoha_qdma_init_tx_queue(struct airoha_eth *eth, - struct airoha_queue *q, int size) +static int airoha_qdma_init_tx_queue(struct airoha_queue *q, + struct airoha_qdma *qdma, int size) { - int i, qid = q - ð->q_tx[0]; + struct airoha_eth *eth = qdma->eth; + int i, qid = q - &qdma->q_tx[0]; dma_addr_t dma_addr; spin_lock_init(&q->lock); q->ndesc = size; - q->eth = eth; + q->qdma = qdma; q->free_thr = 1 + MAX_SKB_FRAGS; q->entry = devm_kzalloc(eth->dev, q->ndesc * sizeof(*q->entry), @@ -1738,20 +1751,20 @@ static int airoha_qdma_init_tx_queue(struct airoha_eth *eth, WRITE_ONCE(q->desc[i].ctrl, cpu_to_le32(val)); } - airoha_qdma_wr(eth, REG_TX_RING_BASE(qid), dma_addr); - airoha_qdma_rmw(eth, REG_TX_CPU_IDX(qid), TX_RING_CPU_IDX_MASK, + airoha_qdma_wr(qdma, REG_TX_RING_BASE(qid), dma_addr); + airoha_qdma_rmw(qdma, REG_TX_CPU_IDX(qid), TX_RING_CPU_IDX_MASK, FIELD_PREP(TX_RING_CPU_IDX_MASK, q->head)); - airoha_qdma_rmw(eth, REG_TX_DMA_IDX(qid), TX_RING_DMA_IDX_MASK, + airoha_qdma_rmw(qdma, REG_TX_DMA_IDX(qid), TX_RING_DMA_IDX_MASK, FIELD_PREP(TX_RING_DMA_IDX_MASK, q->head)); return 0; } -static int airoha_qdma_tx_irq_init(struct airoha_eth *eth, - struct airoha_tx_irq_queue *irq_q, - int size) +static int airoha_qdma_tx_irq_init(struct airoha_tx_irq_queue *irq_q, + struct airoha_qdma *qdma, int size) { - int id = irq_q - ð->q_tx_irq[0]; + int id = irq_q - &qdma->q_tx_irq[0]; + struct airoha_eth *eth = qdma->eth; dma_addr_t dma_addr; netif_napi_add_tx(eth->napi_dev, &irq_q->napi, @@ -1763,30 +1776,30 @@ static int airoha_qdma_tx_irq_init(struct airoha_eth *eth, memset(irq_q->q, 0xff, size * sizeof(u32)); irq_q->size = size; - irq_q->eth = eth; + irq_q->qdma = qdma; - airoha_qdma_wr(eth, REG_TX_IRQ_BASE(id), dma_addr); - airoha_qdma_rmw(eth, REG_TX_IRQ_CFG(id), TX_IRQ_DEPTH_MASK, + airoha_qdma_wr(qdma, REG_TX_IRQ_BASE(id), dma_addr); + airoha_qdma_rmw(qdma, REG_TX_IRQ_CFG(id), TX_IRQ_DEPTH_MASK, FIELD_PREP(TX_IRQ_DEPTH_MASK, size)); - airoha_qdma_rmw(eth, REG_TX_IRQ_CFG(id), TX_IRQ_THR_MASK, + airoha_qdma_rmw(qdma, REG_TX_IRQ_CFG(id), TX_IRQ_THR_MASK, FIELD_PREP(TX_IRQ_THR_MASK, 1)); return 0; } -static int airoha_qdma_init_tx(struct airoha_eth *eth) +static int airoha_qdma_init_tx(struct airoha_qdma *qdma) { int i, err; - for (i = 0; i < ARRAY_SIZE(eth->q_tx_irq); i++) { - err = airoha_qdma_tx_irq_init(eth, ð->q_tx_irq[i], + for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++) { + err = airoha_qdma_tx_irq_init(&qdma->q_tx_irq[i], qdma, IRQ_QUEUE_LEN(i)); if (err) return err; } - for (i = 0; i < ARRAY_SIZE(eth->q_tx); i++) { - err = airoha_qdma_init_tx_queue(eth, ð->q_tx[i], + for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) { + err = airoha_qdma_init_tx_queue(&qdma->q_tx[i], qdma, TX_DSCP_NUM); if (err) return err; @@ -1797,7 +1810,7 @@ static int airoha_qdma_init_tx(struct airoha_eth *eth) static void airoha_qdma_cleanup_tx_queue(struct airoha_queue *q) { - struct airoha_eth *eth = q->eth; + struct airoha_eth *eth = q->qdma->eth; spin_lock_bh(&q->lock); while (q->queued) { @@ -1814,34 +1827,35 @@ static void airoha_qdma_cleanup_tx_queue(struct airoha_queue *q) spin_unlock_bh(&q->lock); } -static int airoha_qdma_init_hfwd_queues(struct airoha_eth *eth) +static int airoha_qdma_init_hfwd_queues(struct airoha_qdma *qdma) { + struct airoha_eth *eth = qdma->eth; dma_addr_t dma_addr; u32 status; int size; size = HW_DSCP_NUM * sizeof(struct airoha_qdma_fwd_desc); - eth->hfwd.desc = dmam_alloc_coherent(eth->dev, size, &dma_addr, - GFP_KERNEL); - if (!eth->hfwd.desc) + qdma->hfwd.desc = dmam_alloc_coherent(eth->dev, size, &dma_addr, + GFP_KERNEL); + if (!qdma->hfwd.desc) return -ENOMEM; - airoha_qdma_wr(eth, REG_FWD_DSCP_BASE, dma_addr); + airoha_qdma_wr(qdma, REG_FWD_DSCP_BASE, dma_addr); size = AIROHA_MAX_PACKET_SIZE * HW_DSCP_NUM; - eth->hfwd.q = dmam_alloc_coherent(eth->dev, size, &dma_addr, - GFP_KERNEL); - if (!eth->hfwd.q) + qdma->hfwd.q = dmam_alloc_coherent(eth->dev, size, &dma_addr, + GFP_KERNEL); + if (!qdma->hfwd.q) return -ENOMEM; - airoha_qdma_wr(eth, REG_FWD_BUF_BASE, dma_addr); + airoha_qdma_wr(qdma, REG_FWD_BUF_BASE, dma_addr); - airoha_qdma_rmw(eth, REG_HW_FWD_DSCP_CFG, + airoha_qdma_rmw(qdma, REG_HW_FWD_DSCP_CFG, HW_FWD_DSCP_PAYLOAD_SIZE_MASK, FIELD_PREP(HW_FWD_DSCP_PAYLOAD_SIZE_MASK, 0)); - airoha_qdma_rmw(eth, REG_FWD_DSCP_LOW_THR, FWD_DSCP_LOW_THR_MASK, + airoha_qdma_rmw(qdma, REG_FWD_DSCP_LOW_THR, FWD_DSCP_LOW_THR_MASK, FIELD_PREP(FWD_DSCP_LOW_THR_MASK, 128)); - airoha_qdma_rmw(eth, REG_LMGR_INIT_CFG, + airoha_qdma_rmw(qdma, REG_LMGR_INIT_CFG, LMGR_INIT_START | LMGR_SRAM_MODE_MASK | HW_FWD_DESC_NUM_MASK, FIELD_PREP(HW_FWD_DESC_NUM_MASK, HW_DSCP_NUM) | @@ -1849,87 +1863,87 @@ static int airoha_qdma_init_hfwd_queues(struct airoha_eth *eth) return read_poll_timeout(airoha_qdma_rr, status, !(status & LMGR_INIT_START), USEC_PER_MSEC, - 30 * USEC_PER_MSEC, true, eth, + 30 * USEC_PER_MSEC, true, qdma, REG_LMGR_INIT_CFG); } -static void airoha_qdma_init_qos(struct airoha_eth *eth) +static void airoha_qdma_init_qos(struct airoha_qdma *qdma) { - airoha_qdma_clear(eth, REG_TXWRR_MODE_CFG, TWRR_WEIGHT_SCALE_MASK); - airoha_qdma_set(eth, REG_TXWRR_MODE_CFG, TWRR_WEIGHT_BASE_MASK); + airoha_qdma_clear(qdma, REG_TXWRR_MODE_CFG, TWRR_WEIGHT_SCALE_MASK); + airoha_qdma_set(qdma, REG_TXWRR_MODE_CFG, TWRR_WEIGHT_BASE_MASK); - airoha_qdma_clear(eth, REG_PSE_BUF_USAGE_CFG, + airoha_qdma_clear(qdma, REG_PSE_BUF_USAGE_CFG, PSE_BUF_ESTIMATE_EN_MASK); - airoha_qdma_set(eth, REG_EGRESS_RATE_METER_CFG, + airoha_qdma_set(qdma, REG_EGRESS_RATE_METER_CFG, EGRESS_RATE_METER_EN_MASK | EGRESS_RATE_METER_EQ_RATE_EN_MASK); /* 2047us x 31 = 63.457ms */ - airoha_qdma_rmw(eth, REG_EGRESS_RATE_METER_CFG, + airoha_qdma_rmw(qdma, REG_EGRESS_RATE_METER_CFG, EGRESS_RATE_METER_WINDOW_SZ_MASK, FIELD_PREP(EGRESS_RATE_METER_WINDOW_SZ_MASK, 0x1f)); - airoha_qdma_rmw(eth, REG_EGRESS_RATE_METER_CFG, + airoha_qdma_rmw(qdma, REG_EGRESS_RATE_METER_CFG, EGRESS_RATE_METER_TIMESLICE_MASK, FIELD_PREP(EGRESS_RATE_METER_TIMESLICE_MASK, 0x7ff)); /* ratelimit init */ - airoha_qdma_set(eth, REG_GLB_TRTCM_CFG, GLB_TRTCM_EN_MASK); + airoha_qdma_set(qdma, REG_GLB_TRTCM_CFG, GLB_TRTCM_EN_MASK); /* fast-tick 25us */ - airoha_qdma_rmw(eth, REG_GLB_TRTCM_CFG, GLB_FAST_TICK_MASK, + airoha_qdma_rmw(qdma, REG_GLB_TRTCM_CFG, GLB_FAST_TICK_MASK, FIELD_PREP(GLB_FAST_TICK_MASK, 25)); - airoha_qdma_rmw(eth, REG_GLB_TRTCM_CFG, GLB_SLOW_TICK_RATIO_MASK, + airoha_qdma_rmw(qdma, REG_GLB_TRTCM_CFG, GLB_SLOW_TICK_RATIO_MASK, FIELD_PREP(GLB_SLOW_TICK_RATIO_MASK, 40)); - airoha_qdma_set(eth, REG_EGRESS_TRTCM_CFG, EGRESS_TRTCM_EN_MASK); - airoha_qdma_rmw(eth, REG_EGRESS_TRTCM_CFG, EGRESS_FAST_TICK_MASK, + airoha_qdma_set(qdma, REG_EGRESS_TRTCM_CFG, EGRESS_TRTCM_EN_MASK); + airoha_qdma_rmw(qdma, REG_EGRESS_TRTCM_CFG, EGRESS_FAST_TICK_MASK, FIELD_PREP(EGRESS_FAST_TICK_MASK, 25)); - airoha_qdma_rmw(eth, REG_EGRESS_TRTCM_CFG, + airoha_qdma_rmw(qdma, REG_EGRESS_TRTCM_CFG, EGRESS_SLOW_TICK_RATIO_MASK, FIELD_PREP(EGRESS_SLOW_TICK_RATIO_MASK, 40)); - airoha_qdma_set(eth, REG_INGRESS_TRTCM_CFG, INGRESS_TRTCM_EN_MASK); - airoha_qdma_clear(eth, REG_INGRESS_TRTCM_CFG, + airoha_qdma_set(qdma, REG_INGRESS_TRTCM_CFG, INGRESS_TRTCM_EN_MASK); + airoha_qdma_clear(qdma, REG_INGRESS_TRTCM_CFG, INGRESS_TRTCM_MODE_MASK); - airoha_qdma_rmw(eth, REG_INGRESS_TRTCM_CFG, INGRESS_FAST_TICK_MASK, + airoha_qdma_rmw(qdma, REG_INGRESS_TRTCM_CFG, INGRESS_FAST_TICK_MASK, FIELD_PREP(INGRESS_FAST_TICK_MASK, 125)); - airoha_qdma_rmw(eth, REG_INGRESS_TRTCM_CFG, + airoha_qdma_rmw(qdma, REG_INGRESS_TRTCM_CFG, INGRESS_SLOW_TICK_RATIO_MASK, FIELD_PREP(INGRESS_SLOW_TICK_RATIO_MASK, 8)); - airoha_qdma_set(eth, REG_SLA_TRTCM_CFG, SLA_TRTCM_EN_MASK); - airoha_qdma_rmw(eth, REG_SLA_TRTCM_CFG, SLA_FAST_TICK_MASK, + airoha_qdma_set(qdma, REG_SLA_TRTCM_CFG, SLA_TRTCM_EN_MASK); + airoha_qdma_rmw(qdma, REG_SLA_TRTCM_CFG, SLA_FAST_TICK_MASK, FIELD_PREP(SLA_FAST_TICK_MASK, 25)); - airoha_qdma_rmw(eth, REG_SLA_TRTCM_CFG, SLA_SLOW_TICK_RATIO_MASK, + airoha_qdma_rmw(qdma, REG_SLA_TRTCM_CFG, SLA_SLOW_TICK_RATIO_MASK, FIELD_PREP(SLA_SLOW_TICK_RATIO_MASK, 40)); } -static int airoha_qdma_hw_init(struct airoha_eth *eth) +static int airoha_qdma_hw_init(struct airoha_qdma *qdma) { int i; /* clear pending irqs */ - for (i = 0; i < ARRAY_SIZE(eth->irqmask); i++) - airoha_qdma_wr(eth, REG_INT_STATUS(i), 0xffffffff); + for (i = 0; i < ARRAY_SIZE(qdma->irqmask); i++) + airoha_qdma_wr(qdma, REG_INT_STATUS(i), 0xffffffff); /* setup irqs */ - airoha_qdma_irq_enable(eth, QDMA_INT_REG_IDX0, INT_IDX0_MASK); - airoha_qdma_irq_enable(eth, QDMA_INT_REG_IDX1, INT_IDX1_MASK); - airoha_qdma_irq_enable(eth, QDMA_INT_REG_IDX4, INT_IDX4_MASK); + airoha_qdma_irq_enable(qdma, QDMA_INT_REG_IDX0, INT_IDX0_MASK); + airoha_qdma_irq_enable(qdma, QDMA_INT_REG_IDX1, INT_IDX1_MASK); + airoha_qdma_irq_enable(qdma, QDMA_INT_REG_IDX4, INT_IDX4_MASK); /* setup irq binding */ - for (i = 0; i < ARRAY_SIZE(eth->q_tx); i++) { - if (!eth->q_tx[i].ndesc) + for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) { + if (!qdma->q_tx[i].ndesc) continue; if (TX_RING_IRQ_BLOCKING_MAP_MASK & BIT(i)) - airoha_qdma_set(eth, REG_TX_RING_BLOCKING(i), + airoha_qdma_set(qdma, REG_TX_RING_BLOCKING(i), TX_RING_IRQ_BLOCKING_CFG_MASK); else - airoha_qdma_clear(eth, REG_TX_RING_BLOCKING(i), + airoha_qdma_clear(qdma, REG_TX_RING_BLOCKING(i), TX_RING_IRQ_BLOCKING_CFG_MASK); } - airoha_qdma_wr(eth, REG_QDMA_GLOBAL_CFG, + airoha_qdma_wr(qdma, REG_QDMA_GLOBAL_CFG, GLOBAL_CFG_RX_2B_OFFSET_MASK | FIELD_PREP(GLOBAL_CFG_DMA_PREFERENCE_MASK, 3) | GLOBAL_CFG_CPU_TXR_RR_MASK | @@ -1940,18 +1954,18 @@ static int airoha_qdma_hw_init(struct airoha_eth *eth) GLOBAL_CFG_TX_WB_DONE_MASK | FIELD_PREP(GLOBAL_CFG_MAX_ISSUE_NUM_MASK, 2)); - airoha_qdma_init_qos(eth); + airoha_qdma_init_qos(qdma); /* disable qdma rx delay interrupt */ - for (i = 0; i < ARRAY_SIZE(eth->q_rx); i++) { - if (!eth->q_rx[i].ndesc) + for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) { + if (!qdma->q_rx[i].ndesc) continue; - airoha_qdma_clear(eth, REG_RX_DELAY_INT_IDX(i), + airoha_qdma_clear(qdma, REG_RX_DELAY_INT_IDX(i), RX_DELAY_INT_MASK); } - airoha_qdma_set(eth, REG_TXQ_CNGST_CFG, + airoha_qdma_set(qdma, REG_TXQ_CNGST_CFG, TXQ_CNGST_DROP_EN | TXQ_CNGST_DEI_DROP_EN); return 0; @@ -1959,150 +1973,180 @@ static int airoha_qdma_hw_init(struct airoha_eth *eth) static irqreturn_t airoha_irq_handler(int irq, void *dev_instance) { - struct airoha_eth *eth = dev_instance; - u32 intr[ARRAY_SIZE(eth->irqmask)]; + struct airoha_qdma *qdma = dev_instance; + u32 intr[ARRAY_SIZE(qdma->irqmask)]; int i; - for (i = 0; i < ARRAY_SIZE(eth->irqmask); i++) { - intr[i] = airoha_qdma_rr(eth, REG_INT_STATUS(i)); - intr[i] &= eth->irqmask[i]; - airoha_qdma_wr(eth, REG_INT_STATUS(i), intr[i]); + for (i = 0; i < ARRAY_SIZE(qdma->irqmask); i++) { + intr[i] = airoha_qdma_rr(qdma, REG_INT_STATUS(i)); + intr[i] &= qdma->irqmask[i]; + airoha_qdma_wr(qdma, REG_INT_STATUS(i), intr[i]); } - if (!test_bit(DEV_STATE_INITIALIZED, ð->state)) + if (!test_bit(DEV_STATE_INITIALIZED, &qdma->eth->state)) return IRQ_NONE; if (intr[1] & RX_DONE_INT_MASK) { - airoha_qdma_irq_disable(eth, QDMA_INT_REG_IDX1, + airoha_qdma_irq_disable(qdma, QDMA_INT_REG_IDX1, RX_DONE_INT_MASK); - for (i = 0; i < ARRAY_SIZE(eth->q_rx); i++) { - if (!eth->q_rx[i].ndesc) + for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) { + if (!qdma->q_rx[i].ndesc) continue; if (intr[1] & BIT(i)) - napi_schedule(ð->q_rx[i].napi); + napi_schedule(&qdma->q_rx[i].napi); } } if (intr[0] & INT_TX_MASK) { - for (i = 0; i < ARRAY_SIZE(eth->q_tx_irq); i++) { - struct airoha_tx_irq_queue *irq_q = ð->q_tx_irq[i]; + for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++) { + struct airoha_tx_irq_queue *irq_q = &qdma->q_tx_irq[i]; u32 status, head; if (!(intr[0] & TX_DONE_INT_MASK(i))) continue; - airoha_qdma_irq_disable(eth, QDMA_INT_REG_IDX0, + airoha_qdma_irq_disable(qdma, QDMA_INT_REG_IDX0, TX_DONE_INT_MASK(i)); - status = airoha_qdma_rr(eth, REG_IRQ_STATUS(i)); + status = airoha_qdma_rr(qdma, REG_IRQ_STATUS(i)); head = FIELD_GET(IRQ_HEAD_IDX_MASK, status); irq_q->head = head % irq_q->size; irq_q->queued = FIELD_GET(IRQ_ENTRY_LEN_MASK, status); - napi_schedule(ð->q_tx_irq[i].napi); + napi_schedule(&qdma->q_tx_irq[i].napi); } } return IRQ_HANDLED; } -static int airoha_qdma_init(struct airoha_eth *eth) +static int airoha_qdma_init(struct platform_device *pdev, + struct airoha_eth *eth, + struct airoha_qdma *qdma) { - int err; + int err, id = qdma - ð->qdma[0]; + const char *res; - err = devm_request_irq(eth->dev, eth->irq, airoha_irq_handler, - IRQF_SHARED, KBUILD_MODNAME, eth); - if (err) - return err; + spin_lock_init(&qdma->irq_lock); + qdma->eth = eth; + + res = devm_kasprintf(eth->dev, GFP_KERNEL, "qdma%d", id); + if (!res) + return -ENOMEM; - err = airoha_qdma_init_rx(eth); + qdma->regs = devm_platform_ioremap_resource_byname(pdev, res); + if (IS_ERR(qdma->regs)) + return dev_err_probe(eth->dev, PTR_ERR(qdma->regs), + "failed to iomap qdma%d regs\n", id); + + qdma->irq = platform_get_irq(pdev, 4 * id); + if (qdma->irq < 0) + return qdma->irq; + + err = devm_request_irq(eth->dev, qdma->irq, airoha_irq_handler, + IRQF_SHARED, KBUILD_MODNAME, qdma); if (err) return err; - err = airoha_qdma_init_tx(eth); + err = airoha_qdma_init_rx(qdma); if (err) return err; - err = airoha_qdma_init_hfwd_queues(eth); + err = airoha_qdma_init_tx(qdma); if (err) return err; - err = airoha_qdma_hw_init(eth); + err = airoha_qdma_init_hfwd_queues(qdma); if (err) return err; - set_bit(DEV_STATE_INITIALIZED, ð->state); - - return 0; + return airoha_qdma_hw_init(qdma); } -static int airoha_hw_init(struct airoha_eth *eth) +static int airoha_hw_init(struct platform_device *pdev, + struct airoha_eth *eth) { - int err; + int err, i; /* disable xsi */ - reset_control_bulk_assert(ARRAY_SIZE(eth->xsi_rsts), eth->xsi_rsts); + err = reset_control_bulk_assert(ARRAY_SIZE(eth->xsi_rsts), + eth->xsi_rsts); + if (err) + return err; + + err = reset_control_bulk_assert(ARRAY_SIZE(eth->rsts), eth->rsts); + if (err) + return err; - reset_control_bulk_assert(ARRAY_SIZE(eth->rsts), eth->rsts); - msleep(20); - reset_control_bulk_deassert(ARRAY_SIZE(eth->rsts), eth->rsts); msleep(20); + err = reset_control_bulk_deassert(ARRAY_SIZE(eth->rsts), eth->rsts); + if (err) + return err; + msleep(20); err = airoha_fe_init(eth); if (err) return err; - return airoha_qdma_init(eth); + for (i = 0; i < ARRAY_SIZE(eth->qdma); i++) { + err = airoha_qdma_init(pdev, eth, ð->qdma[i]); + if (err) + return err; + } + + set_bit(DEV_STATE_INITIALIZED, ð->state); + + return 0; } -static void airoha_hw_cleanup(struct airoha_eth *eth) +static void airoha_hw_cleanup(struct airoha_qdma *qdma) { int i; - for (i = 0; i < ARRAY_SIZE(eth->q_rx); i++) { - if (!eth->q_rx[i].ndesc) + for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) { + if (!qdma->q_rx[i].ndesc) continue; - napi_disable(ð->q_rx[i].napi); - netif_napi_del(ð->q_rx[i].napi); - airoha_qdma_cleanup_rx_queue(ð->q_rx[i]); - if (eth->q_rx[i].page_pool) - page_pool_destroy(eth->q_rx[i].page_pool); + napi_disable(&qdma->q_rx[i].napi); + netif_napi_del(&qdma->q_rx[i].napi); + airoha_qdma_cleanup_rx_queue(&qdma->q_rx[i]); + if (qdma->q_rx[i].page_pool) + page_pool_destroy(qdma->q_rx[i].page_pool); } - for (i = 0; i < ARRAY_SIZE(eth->q_tx_irq); i++) { - napi_disable(ð->q_tx_irq[i].napi); - netif_napi_del(ð->q_tx_irq[i].napi); + for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++) { + napi_disable(&qdma->q_tx_irq[i].napi); + netif_napi_del(&qdma->q_tx_irq[i].napi); } - for (i = 0; i < ARRAY_SIZE(eth->q_tx); i++) { - if (!eth->q_tx[i].ndesc) + for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) { + if (!qdma->q_tx[i].ndesc) continue; - airoha_qdma_cleanup_tx_queue(ð->q_tx[i]); + airoha_qdma_cleanup_tx_queue(&qdma->q_tx[i]); } } -static void airoha_qdma_start_napi(struct airoha_eth *eth) +static void airoha_qdma_start_napi(struct airoha_qdma *qdma) { int i; - for (i = 0; i < ARRAY_SIZE(eth->q_tx_irq); i++) - napi_enable(ð->q_tx_irq[i].napi); + for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++) + napi_enable(&qdma->q_tx_irq[i].napi); - for (i = 0; i < ARRAY_SIZE(eth->q_rx); i++) { - if (!eth->q_rx[i].ndesc) + for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) { + if (!qdma->q_rx[i].ndesc) continue; - napi_enable(ð->q_rx[i].napi); + napi_enable(&qdma->q_rx[i].napi); } } static void airoha_update_hw_stats(struct airoha_gdm_port *port) { - struct airoha_eth *eth = port->eth; + struct airoha_eth *eth = port->qdma->eth; u32 val, i = 0; spin_lock(&port->stats.lock); @@ -2247,23 +2291,24 @@ static void airoha_update_hw_stats(struct airoha_gdm_port *port) static int airoha_dev_open(struct net_device *dev) { struct airoha_gdm_port *port = netdev_priv(dev); - struct airoha_eth *eth = port->eth; + struct airoha_qdma *qdma = port->qdma; int err; netif_tx_start_all_queues(dev); - err = airoha_set_gdm_ports(eth, true); + err = airoha_set_gdm_ports(qdma->eth, true); if (err) return err; if (netdev_uses_dsa(dev)) - airoha_fe_set(eth, REG_GDM_INGRESS_CFG(port->id), + airoha_fe_set(qdma->eth, REG_GDM_INGRESS_CFG(port->id), GDM_STAG_EN_MASK); else - airoha_fe_clear(eth, REG_GDM_INGRESS_CFG(port->id), + airoha_fe_clear(qdma->eth, REG_GDM_INGRESS_CFG(port->id), GDM_STAG_EN_MASK); - airoha_qdma_set(eth, REG_QDMA_GLOBAL_CFG, GLOBAL_CFG_TX_DMA_EN_MASK); - airoha_qdma_set(eth, REG_QDMA_GLOBAL_CFG, GLOBAL_CFG_RX_DMA_EN_MASK); + airoha_qdma_set(qdma, REG_QDMA_GLOBAL_CFG, + GLOBAL_CFG_TX_DMA_EN_MASK | + GLOBAL_CFG_RX_DMA_EN_MASK); return 0; } @@ -2271,16 +2316,17 @@ static int airoha_dev_open(struct net_device *dev) static int airoha_dev_stop(struct net_device *dev) { struct airoha_gdm_port *port = netdev_priv(dev); - struct airoha_eth *eth = port->eth; + struct airoha_qdma *qdma = port->qdma; int err; netif_tx_disable(dev); - err = airoha_set_gdm_ports(eth, false); + err = airoha_set_gdm_ports(qdma->eth, false); if (err) return err; - airoha_qdma_clear(eth, REG_QDMA_GLOBAL_CFG, GLOBAL_CFG_TX_DMA_EN_MASK); - airoha_qdma_clear(eth, REG_QDMA_GLOBAL_CFG, GLOBAL_CFG_RX_DMA_EN_MASK); + airoha_qdma_clear(qdma, REG_QDMA_GLOBAL_CFG, + GLOBAL_CFG_TX_DMA_EN_MASK | + GLOBAL_CFG_RX_DMA_EN_MASK); return 0; } @@ -2294,7 +2340,7 @@ static int airoha_dev_set_macaddr(struct net_device *dev, void *p) if (err) return err; - airoha_set_macaddr(port->eth, dev->dev_addr); + airoha_set_macaddr(port->qdma->eth, dev->dev_addr); return 0; } @@ -2303,7 +2349,7 @@ static int airoha_dev_init(struct net_device *dev) { struct airoha_gdm_port *port = netdev_priv(dev); - airoha_set_macaddr(port->eth, dev->dev_addr); + airoha_set_macaddr(port->qdma->eth, dev->dev_addr); return 0; } @@ -2337,7 +2383,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, struct airoha_gdm_port *port = netdev_priv(dev); u32 msg0 = 0, msg1, len = skb_headlen(skb); int i, qid = skb_get_queue_mapping(skb); - struct airoha_eth *eth = port->eth; + struct airoha_qdma *qdma = port->qdma; u32 nr_frags = 1 + sinfo->nr_frags; struct netdev_queue *txq; struct airoha_queue *q; @@ -2367,7 +2413,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, msg1 = FIELD_PREP(QDMA_ETH_TXMSG_FPORT_MASK, fport) | FIELD_PREP(QDMA_ETH_TXMSG_METER_MASK, 0x7f); - q = ð->q_tx[qid]; + q = &qdma->q_tx[qid]; if (WARN_ON_ONCE(!q->ndesc)) goto error; @@ -2411,7 +2457,8 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, e->dma_addr = addr; e->dma_len = len; - airoha_qdma_rmw(eth, REG_TX_CPU_IDX(qid), TX_RING_CPU_IDX_MASK, + airoha_qdma_rmw(qdma, REG_TX_CPU_IDX(qid), + TX_RING_CPU_IDX_MASK, FIELD_PREP(TX_RING_CPU_IDX_MASK, index)); data = skb_frag_address(frag); @@ -2448,7 +2495,7 @@ static void airoha_ethtool_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { struct airoha_gdm_port *port = netdev_priv(dev); - struct airoha_eth *eth = port->eth; + struct airoha_eth *eth = port->qdma->eth; strscpy(info->driver, eth->dev->driver->name, sizeof(info->driver)); strscpy(info->bus_info, dev_name(eth->dev), sizeof(info->bus_info)); @@ -2529,6 +2576,7 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np) { const __be32 *id_ptr = of_get_property(np, "reg", NULL); struct airoha_gdm_port *port; + struct airoha_qdma *qdma; struct net_device *dev; int err, index; u32 id; @@ -2558,6 +2606,7 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np) return -ENOMEM; } + qdma = ð->qdma[index % AIROHA_MAX_NUM_QDMA]; dev->netdev_ops = &airoha_netdev_ops; dev->ethtool_ops = &airoha_ethtool_ops; dev->max_mtu = AIROHA_MAX_MTU; @@ -2567,6 +2616,7 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np) NETIF_F_SG | NETIF_F_TSO; dev->features |= dev->hw_features; dev->dev.of_node = np; + dev->irq = qdma->irq; SET_NETDEV_DEV(dev, eth->dev); err = of_get_ethdev_address(np, dev); @@ -2582,8 +2632,8 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np) port = netdev_priv(dev); u64_stats_init(&port->stats.syncp); spin_lock_init(&port->stats.lock); + port->qdma = qdma; port->dev = dev; - port->eth = eth; port->id = id; eth->ports[index] = port; @@ -2613,11 +2663,6 @@ static int airoha_probe(struct platform_device *pdev) return dev_err_probe(eth->dev, PTR_ERR(eth->fe_regs), "failed to iomap fe regs\n"); - eth->qdma_regs = devm_platform_ioremap_resource_byname(pdev, "qdma0"); - if (IS_ERR(eth->qdma_regs)) - return dev_err_probe(eth->dev, PTR_ERR(eth->qdma_regs), - "failed to iomap qdma regs\n"); - eth->rsts[0].id = "fe"; eth->rsts[1].id = "pdma"; eth->rsts[2].id = "qdma"; @@ -2642,11 +2687,6 @@ static int airoha_probe(struct platform_device *pdev) return err; } - spin_lock_init(ð->irq_lock); - eth->irq = platform_get_irq(pdev, 0); - if (eth->irq < 0) - return eth->irq; - eth->napi_dev = alloc_netdev_dummy(0); if (!eth->napi_dev) return -ENOMEM; @@ -2656,11 +2696,13 @@ static int airoha_probe(struct platform_device *pdev) strscpy(eth->napi_dev->name, "qdma_eth", sizeof(eth->napi_dev->name)); platform_set_drvdata(pdev, eth); - err = airoha_hw_init(eth); + err = airoha_hw_init(pdev, eth); if (err) goto error; - airoha_qdma_start_napi(eth); + for (i = 0; i < ARRAY_SIZE(eth->qdma); i++) + airoha_qdma_start_napi(ð->qdma[i]); + for_each_child_of_node(pdev->dev.of_node, np) { if (!of_device_is_compatible(np, "airoha,eth-mac")) continue; @@ -2678,7 +2720,9 @@ static int airoha_probe(struct platform_device *pdev) return 0; error: - airoha_hw_cleanup(eth); + for (i = 0; i < ARRAY_SIZE(eth->qdma); i++) + airoha_hw_cleanup(ð->qdma[i]); + for (i = 0; i < ARRAY_SIZE(eth->ports); i++) { struct airoha_gdm_port *port = eth->ports[i]; @@ -2696,7 +2740,9 @@ static void airoha_remove(struct platform_device *pdev) struct airoha_eth *eth = platform_get_drvdata(pdev); int i; - airoha_hw_cleanup(eth); + for (i = 0; i < ARRAY_SIZE(eth->qdma); i++) + airoha_hw_cleanup(ð->qdma[i]); + for (i = 0; i < ARRAY_SIZE(eth->ports); i++) { struct airoha_gdm_port *port = eth->ports[i]; diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index eb1708b43aa3..0d5225f1d3ee 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -724,12 +724,8 @@ enum mtk_clks_map { MTK_CLK_ETHWARP_WOCPU2, MTK_CLK_ETHWARP_WOCPU1, MTK_CLK_ETHWARP_WOCPU0, - MTK_CLK_TOP_USXGMII_SBUS_0_SEL, - MTK_CLK_TOP_USXGMII_SBUS_1_SEL, MTK_CLK_TOP_SGM_0_SEL, MTK_CLK_TOP_SGM_1_SEL, - MTK_CLK_TOP_XFI_PHY_0_XTAL_SEL, - MTK_CLK_TOP_XFI_PHY_1_XTAL_SEL, MTK_CLK_TOP_ETH_GMII_SEL, MTK_CLK_TOP_ETH_REFCK_50M_SEL, MTK_CLK_TOP_ETH_SYS_200M_SEL, @@ -800,19 +796,9 @@ enum mtk_clks_map { BIT_ULL(MTK_CLK_GP3) | BIT_ULL(MTK_CLK_XGP1) | \ BIT_ULL(MTK_CLK_XGP2) | BIT_ULL(MTK_CLK_XGP3) | \ BIT_ULL(MTK_CLK_CRYPTO) | \ - BIT_ULL(MTK_CLK_SGMII_TX_250M) | \ - BIT_ULL(MTK_CLK_SGMII_RX_250M) | \ - BIT_ULL(MTK_CLK_SGMII2_TX_250M) | \ - BIT_ULL(MTK_CLK_SGMII2_RX_250M) | \ BIT_ULL(MTK_CLK_ETHWARP_WOCPU2) | \ BIT_ULL(MTK_CLK_ETHWARP_WOCPU1) | \ BIT_ULL(MTK_CLK_ETHWARP_WOCPU0) | \ - BIT_ULL(MTK_CLK_TOP_USXGMII_SBUS_0_SEL) | \ - BIT_ULL(MTK_CLK_TOP_USXGMII_SBUS_1_SEL) | \ - BIT_ULL(MTK_CLK_TOP_SGM_0_SEL) | \ - BIT_ULL(MTK_CLK_TOP_SGM_1_SEL) | \ - BIT_ULL(MTK_CLK_TOP_XFI_PHY_0_XTAL_SEL) | \ - BIT_ULL(MTK_CLK_TOP_XFI_PHY_1_XTAL_SEL) | \ BIT_ULL(MTK_CLK_TOP_ETH_GMII_SEL) | \ BIT_ULL(MTK_CLK_TOP_ETH_REFCK_50M_SEL) | \ BIT_ULL(MTK_CLK_TOP_ETH_SYS_200M_SEL) | \ diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index 943d6918c2ec..cd17a3f4faf8 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -2036,20 +2036,20 @@ static int mlx4_en_get_module_info(struct net_device *dev, switch (data[0] /* identifier */) { case MLX4_MODULE_ID_QSFP: modinfo->type = ETH_MODULE_SFF_8436; - modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN; + modinfo->eeprom_len = ETH_MODULE_SFF_8436_MAX_LEN; break; case MLX4_MODULE_ID_QSFP_PLUS: if (data[1] >= 0x3) { /* revision id */ modinfo->type = ETH_MODULE_SFF_8636; - modinfo->eeprom_len = ETH_MODULE_SFF_8636_LEN; + modinfo->eeprom_len = ETH_MODULE_SFF_8636_MAX_LEN; } else { modinfo->type = ETH_MODULE_SFF_8436; - modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN; + modinfo->eeprom_len = ETH_MODULE_SFF_8436_MAX_LEN; } break; case MLX4_MODULE_ID_QSFP28: modinfo->type = ETH_MODULE_SFF_8636; - modinfo->eeprom_len = ETH_MODULE_SFF_8636_LEN; + modinfo->eeprom_len = ETH_MODULE_SFF_8636_MAX_LEN; break; case MLX4_MODULE_ID_SFP: modinfo->type = ETH_MODULE_SFF_8472; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index b61b7d966114..76ad46bf477d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -224,6 +224,7 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) if (MLX5_CAP_GEN(dev, mcam_reg)) { mlx5_get_mcam_access_reg_group(dev, MLX5_MCAM_REGS_FIRST_128); mlx5_get_mcam_access_reg_group(dev, MLX5_MCAM_REGS_0x9100_0x917F); + mlx5_get_mcam_access_reg_group(dev, MLX5_MCAM_REGS_0x9180_0x91FF); } if (MLX5_CAP_GEN(dev, qcam_reg)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index 0361741632a6..b306ae79bf97 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -38,6 +38,10 @@ #include "lib/eq.h" #include "en.h" #include "clock.h" +#ifdef CONFIG_X86 +#include <linux/timekeeping.h> +#include <linux/cpufeature.h> +#endif /* CONFIG_X86 */ enum { MLX5_PIN_MODE_IN = 0x0, @@ -148,6 +152,87 @@ static int mlx5_set_mtutc(struct mlx5_core_dev *dev, u32 *mtutc, u32 size) MLX5_REG_MTUTC, 0, 1); } +#ifdef CONFIG_X86 +static bool mlx5_is_ptm_source_time_available(struct mlx5_core_dev *dev) +{ + u32 out[MLX5_ST_SZ_DW(mtptm_reg)] = {0}; + u32 in[MLX5_ST_SZ_DW(mtptm_reg)] = {0}; + int err; + + if (!MLX5_CAP_MCAM_REG3(dev, mtptm)) + return false; + + err = mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out), MLX5_REG_MTPTM, + 0, 0); + if (err) + return false; + + return !!MLX5_GET(mtptm_reg, out, psta); +} + +static int mlx5_mtctr_syncdevicetime(ktime_t *device_time, + struct system_counterval_t *sys_counterval, + void *ctx) +{ + u32 out[MLX5_ST_SZ_DW(mtctr_reg)] = {0}; + u32 in[MLX5_ST_SZ_DW(mtctr_reg)] = {0}; + struct mlx5_core_dev *mdev = ctx; + bool real_time_mode; + u64 host, device; + int err; + + real_time_mode = mlx5_real_time_mode(mdev); + + MLX5_SET(mtctr_reg, in, first_clock_timestamp_request, + MLX5_MTCTR_REQUEST_PTM_ROOT_CLOCK); + MLX5_SET(mtctr_reg, in, second_clock_timestamp_request, + real_time_mode ? MLX5_MTCTR_REQUEST_REAL_TIME_CLOCK : + MLX5_MTCTR_REQUEST_FREE_RUNNING_COUNTER); + + err = mlx5_core_access_reg(mdev, in, sizeof(in), out, sizeof(out), MLX5_REG_MTCTR, + 0, 0); + if (err) + return err; + + if (!MLX5_GET(mtctr_reg, out, first_clock_valid) || + !MLX5_GET(mtctr_reg, out, second_clock_valid)) + return -EINVAL; + + host = MLX5_GET64(mtctr_reg, out, first_clock_timestamp); + *sys_counterval = (struct system_counterval_t) { + .cycles = host, + .cs_id = CSID_X86_ART, + .use_nsecs = true, + }; + + device = MLX5_GET64(mtctr_reg, out, second_clock_timestamp); + if (real_time_mode) + *device_time = ns_to_ktime(REAL_TIME_TO_NS(device >> 32, device & U32_MAX)); + else + *device_time = mlx5_timecounter_cyc2time(&mdev->clock, device); + + return 0; +} + +static int mlx5_ptp_getcrosststamp(struct ptp_clock_info *ptp, + struct system_device_crosststamp *cts) +{ + struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info); + struct system_time_snapshot history_begin = {0}; + struct mlx5_core_dev *mdev; + + mdev = container_of(clock, struct mlx5_core_dev, clock); + + if (!mlx5_is_ptm_source_time_available(mdev)) + return -EBUSY; + + ktime_get_snapshot(&history_begin); + + return get_device_system_crosststamp(mlx5_mtctr_syncdevicetime, mdev, + &history_begin, cts); +} +#endif /* CONFIG_X86 */ + static u64 mlx5_read_time(struct mlx5_core_dev *dev, struct ptp_system_timestamp *sts, bool real_time) @@ -1034,6 +1119,12 @@ static void mlx5_init_timer_clock(struct mlx5_core_dev *mdev) if (MLX5_CAP_MCAM_REG(mdev, mtutc)) mlx5_init_timer_max_freq_adjustment(mdev); +#ifdef CONFIG_X86 + if (MLX5_CAP_MCAM_REG3(mdev, mtptm) && + MLX5_CAP_MCAM_REG3(mdev, mtctr) && boot_cpu_has(X86_FEATURE_ART)) + clock->ptp_info.getcrosststamp = mlx5_ptp_getcrosststamp; +#endif /* CONFIG_X86 */ + mlx5_timecounter_init(mdev); mlx5_init_clock_info(mdev); mlx5_init_overflow_period(clock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 5b7e6f4b5c7e..4b88d969a66c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -923,6 +923,11 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev, } mlx5_pci_vsc_init(dev); + + err = pci_enable_ptm(pdev, NULL); + if (err) + mlx5_core_info(dev, "PTM is not supported by PCIe\n"); + return 0; err_clr_master: @@ -939,6 +944,7 @@ static void mlx5_pci_close(struct mlx5_core_dev *dev) * before removing the pci bars */ mlx5_drain_health_wq(dev); + pci_disable_ptm(dev->pdev); iounmap(dev->iseg); release_bar(dev->pdev); mlx5_pci_disable_device(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index d894a88fa9f2..972e8e9df585 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -608,6 +608,11 @@ enum { RELEASE_ALL_PAGES_MASK = 0x4000, }; +/* This limit is based on the capability of the firmware as it cannot release + * more than 50000 back to the host in one go. + */ +#define MAX_RECLAIM_NPAGES (-50000) + static int req_pages_handler(struct notifier_block *nb, unsigned long type, void *data) { @@ -639,7 +644,16 @@ static int req_pages_handler(struct notifier_block *nb, req->dev = dev; req->func_id = func_id; - req->npages = npages; + + /* npages > 0 means HCA asking host to allocate/give pages, + * npages < 0 means HCA asking host to reclaim back the pages allocated. + * Here we are restricting the maximum number of pages that can be + * reclaimed to be MAX_RECLAIM_NPAGES. Note that MAX_RECLAIM_NPAGES is + * a negative value. + * Since MAX_RECLAIM is negative, we are using max() to restrict + * req->npages (and not min ()). + */ + req->npages = max_t(s32, npages, MAX_RECLAIM_NPAGES); req->ec_function = ec_function; req->release_all = release_all; INIT_WORK(&req->work, pages_work_handler); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c index d61478c0c632..303d2ce4dc1e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c @@ -411,7 +411,7 @@ static const struct thermal_cooling_device_ops mlxsw_cooling_ops = { static int mlxsw_thermal_module_tz_init(struct mlxsw_thermal_module *module_tz) { - char tz_name[THERMAL_NAME_LENGTH]; + char tz_name[40]; int err; if (module_tz->slot_index) @@ -445,17 +445,13 @@ static void mlxsw_thermal_module_tz_fini(struct thermal_zone_device *tzdev) thermal_zone_device_unregister(tzdev); } -static void -mlxsw_thermal_module_init(struct device *dev, struct mlxsw_core *core, - struct mlxsw_thermal *thermal, +static int +mlxsw_thermal_module_init(struct mlxsw_thermal *thermal, struct mlxsw_thermal_area *area, u8 module) { struct mlxsw_thermal_module *module_tz; module_tz = &area->tz_module_arr[module]; - /* Skip if parent is already set (case of port split). */ - if (module_tz->parent) - return; module_tz->module = module; module_tz->slot_index = area->slot_index; module_tz->parent = thermal; @@ -465,15 +461,13 @@ mlxsw_thermal_module_init(struct device *dev, struct mlxsw_core *core, sizeof(thermal->trips)); memcpy(module_tz->cooling_states, default_cooling_states, sizeof(thermal->cooling_states)); + + return mlxsw_thermal_module_tz_init(module_tz); } static void mlxsw_thermal_module_fini(struct mlxsw_thermal_module *module_tz) { - if (module_tz && module_tz->tzdev) { - mlxsw_thermal_module_tz_fini(module_tz->tzdev); - module_tz->tzdev = NULL; - module_tz->parent = NULL; - } + mlxsw_thermal_module_tz_fini(module_tz->tzdev); } static int @@ -481,7 +475,6 @@ mlxsw_thermal_modules_init(struct device *dev, struct mlxsw_core *core, struct mlxsw_thermal *thermal, struct mlxsw_thermal_area *area) { - struct mlxsw_thermal_module *module_tz; char mgpir_pl[MLXSW_REG_MGPIR_LEN]; int i, err; @@ -503,22 +496,16 @@ mlxsw_thermal_modules_init(struct device *dev, struct mlxsw_core *core, if (!area->tz_module_arr) return -ENOMEM; - for (i = 0; i < area->tz_module_num; i++) - mlxsw_thermal_module_init(dev, core, thermal, area, i); - for (i = 0; i < area->tz_module_num; i++) { - module_tz = &area->tz_module_arr[i]; - if (!module_tz->parent) - continue; - err = mlxsw_thermal_module_tz_init(module_tz); + err = mlxsw_thermal_module_init(thermal, area, i); if (err) - goto err_thermal_module_tz_init; + goto err_thermal_module_init; } return 0; -err_thermal_module_tz_init: - for (i = area->tz_module_num - 1; i >= 0; i--) +err_thermal_module_init: + for (i--; i >= 0; i--) mlxsw_thermal_module_fini(&area->tz_module_arr[i]); kfree(area->tz_module_arr); return err; @@ -821,10 +808,7 @@ err_linecards_event_ops_register: err_thermal_gearboxes_init: mlxsw_thermal_modules_fini(thermal, &thermal->line_cards[0]); err_thermal_modules_init: - if (thermal->tzdev) { - thermal_zone_device_unregister(thermal->tzdev); - thermal->tzdev = NULL; - } + thermal_zone_device_unregister(thermal->tzdev); err_thermal_zone_device_register: err_thermal_cooling_device_register: for (i = 0; i < MLXSW_MFCR_PWMS_MAX; i++) @@ -845,10 +829,7 @@ void mlxsw_thermal_fini(struct mlxsw_thermal *thermal) thermal); mlxsw_thermal_gearboxes_fini(thermal, &thermal->line_cards[0]); mlxsw_thermal_modules_fini(thermal, &thermal->line_cards[0]); - if (thermal->tzdev) { - thermal_zone_device_unregister(thermal->tzdev); - thermal->tzdev = NULL; - } + thermal_zone_device_unregister(thermal->tzdev); for (i = 0; i < MLXSW_MFCR_PWMS_MAX; i++) thermal_cooling_device_unregister(thermal->cdevs[i].cdev); diff --git a/drivers/net/ethernet/meta/Kconfig b/drivers/net/ethernet/meta/Kconfig index c002ede36402..85519690b837 100644 --- a/drivers/net/ethernet/meta/Kconfig +++ b/drivers/net/ethernet/meta/Kconfig @@ -23,6 +23,8 @@ config FBNIC depends on !S390 depends on MAX_SKB_FRAGS < 22 depends on PCI_MSI + select NET_DEVLINK + select PAGE_POOL select PHYLINK help This driver supports Meta Platforms Host Network Interface. diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 3e51b3a9b0a5..9dc9de39bb8f 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -1271,8 +1271,8 @@ static int prueth_probe(struct platform_device *pdev) goto exit_iep; } - if (of_find_property(eth0_node, "ti,half-duplex-capable", NULL)) - prueth->emac[PRUETH_MAC0]->half_duplex = 1; + prueth->emac[PRUETH_MAC0]->half_duplex = + of_property_read_bool(eth0_node, "ti,half-duplex-capable"); prueth->emac[PRUETH_MAC0]->iep = prueth->iep0; } @@ -1285,8 +1285,8 @@ static int prueth_probe(struct platform_device *pdev) goto netdev_exit; } - if (of_find_property(eth1_node, "ti,half-duplex-capable", NULL)) - prueth->emac[PRUETH_MAC1]->half_duplex = 1; + prueth->emac[PRUETH_MAC1]->half_duplex = + of_property_read_bool(eth1_node, "ti,half-duplex-capable"); prueth->emac[PRUETH_MAC1]->iep = prueth->iep0; } diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c index e180c1166170..54b7e27608ce 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c @@ -1045,8 +1045,8 @@ static int prueth_probe(struct platform_device *pdev) goto exit_iep; } - if (of_find_property(eth0_node, "ti,half-duplex-capable", NULL)) - prueth->emac[PRUETH_MAC0]->half_duplex = 1; + prueth->emac[PRUETH_MAC0]->half_duplex = + of_property_read_bool(eth0_node, "ti,half-duplex-capable"); prueth->emac[PRUETH_MAC0]->iep = prueth->iep0; } @@ -1059,8 +1059,8 @@ static int prueth_probe(struct platform_device *pdev) goto netdev_exit; } - if (of_find_property(eth1_node, "ti,half-duplex-capable", NULL)) - prueth->emac[PRUETH_MAC1]->half_duplex = 1; + prueth->emac[PRUETH_MAC1]->half_duplex = + of_property_read_bool(eth1_node, "ti,half-duplex-capable"); prueth->emac[PRUETH_MAC1]->iep = prueth->iep1; } diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c index 1eecba984f3b..2b3d6586f44a 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c @@ -251,10 +251,7 @@ static struct sk_buff *wx_build_skb(struct wx_ring *rx_ring, rx_buffer->page_offset; /* prefetch first cache line of first page */ - prefetch(page_addr); -#if L1_CACHE_BYTES < 128 - prefetch(page_addr + L1_CACHE_BYTES); -#endif + net_prefetch(page_addr); /* allocate a skb to store the frags */ skb = napi_alloc_skb(&rx_ring->q_vector->napi, WX_RXBUFFER_256); diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index fa5500decc96..0d5b300107e0 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -29,26 +29,26 @@ /* Configuration options */ /* Accept all incoming packets. Default: disabled (cleared) */ -#define XAE_OPTION_PROMISC (1 << 0) +#define XAE_OPTION_PROMISC BIT(0) /* Jumbo frame support for Tx & Rx. Default: disabled (cleared) */ -#define XAE_OPTION_JUMBO (1 << 1) +#define XAE_OPTION_JUMBO BIT(1) /* VLAN Rx & Tx frame support. Default: disabled (cleared) */ -#define XAE_OPTION_VLAN (1 << 2) +#define XAE_OPTION_VLAN BIT(2) /* Enable recognition of flow control frames on Rx. Default: enabled (set) */ -#define XAE_OPTION_FLOW_CONTROL (1 << 4) +#define XAE_OPTION_FLOW_CONTROL BIT(4) /* Strip FCS and PAD from incoming frames. Note: PAD from VLAN frames is not * stripped. Default: disabled (set) */ -#define XAE_OPTION_FCS_STRIP (1 << 5) +#define XAE_OPTION_FCS_STRIP BIT(5) /* Generate FCS field and add PAD automatically for outgoing frames. * Default: enabled (set) */ -#define XAE_OPTION_FCS_INSERT (1 << 6) +#define XAE_OPTION_FCS_INSERT BIT(6) /* Enable Length/Type error checking for incoming frames. When this option is * set, the MAC will filter frames that have a mismatched type/length field @@ -56,13 +56,13 @@ * types of frames are encountered. When this option is cleared, the MAC will * allow these types of frames to be received. Default: enabled (set) */ -#define XAE_OPTION_LENTYPE_ERR (1 << 7) +#define XAE_OPTION_LENTYPE_ERR BIT(7) /* Enable the transmitter. Default: enabled (set) */ -#define XAE_OPTION_TXEN (1 << 11) +#define XAE_OPTION_TXEN BIT(11) /* Enable the receiver. Default: enabled (set) */ -#define XAE_OPTION_RXEN (1 << 12) +#define XAE_OPTION_RXEN BIT(12) /* Default options set when device is initialized or reset */ #define XAE_OPTION_DEFAULTS \ @@ -326,11 +326,11 @@ #define XAE_MULTICAST_CAM_TABLE_NUM 4 /* Axi Ethernet Synthesis features */ -#define XAE_FEATURE_PARTIAL_RX_CSUM (1 << 0) -#define XAE_FEATURE_PARTIAL_TX_CSUM (1 << 1) -#define XAE_FEATURE_FULL_RX_CSUM (1 << 2) -#define XAE_FEATURE_FULL_TX_CSUM (1 << 3) -#define XAE_FEATURE_DMA_64BIT (1 << 4) +#define XAE_FEATURE_PARTIAL_RX_CSUM BIT(0) +#define XAE_FEATURE_PARTIAL_TX_CSUM BIT(1) +#define XAE_FEATURE_FULL_RX_CSUM BIT(2) +#define XAE_FEATURE_FULL_TX_CSUM BIT(3) +#define XAE_FEATURE_DMA_64BIT BIT(4) #define XAE_NO_CSUM_OFFLOAD 0 diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 02fdf66e07fa..ca04c298daa2 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -415,6 +415,7 @@ static void axienet_set_mac_address(struct net_device *ndev, static int netdev_set_mac_address(struct net_device *ndev, void *p) { struct sockaddr *addr = p; + axienet_set_mac_address(ndev, addr->sa_data); return 0; } @@ -613,8 +614,7 @@ static int axienet_device_reset(struct net_device *ndev) lp->options |= XAE_OPTION_VLAN; lp->options &= (~XAE_OPTION_JUMBO); - if ((ndev->mtu > XAE_MTU) && - (ndev->mtu <= XAE_JUMBO_MTU)) { + if (ndev->mtu > XAE_MTU && ndev->mtu <= XAE_JUMBO_MTU) { lp->max_frm_size = ndev->mtu + VLAN_ETH_HLEN + XAE_TRL_SIZE; @@ -1514,8 +1514,6 @@ static int axienet_open(struct net_device *ndev) int ret; struct axienet_local *lp = netdev_priv(ndev); - dev_dbg(&ndev->dev, "%s\n", __func__); - /* When we do an Axi Ethernet reset, it resets the complete core * including the MDIO. MDIO must be disabled before resetting. * Hold MDIO bus lock to avoid MDIO accesses during the reset. @@ -1576,8 +1574,6 @@ static int axienet_stop(struct net_device *ndev) struct axienet_local *lp = netdev_priv(ndev); int i; - dev_dbg(&ndev->dev, "axienet_close()\n"); - if (!lp->use_dmaengine) { napi_disable(&lp->napi_tx); napi_disable(&lp->napi_rx); @@ -1657,6 +1653,7 @@ static int axienet_change_mtu(struct net_device *ndev, int new_mtu) static void axienet_poll_controller(struct net_device *ndev) { struct axienet_local *lp = netdev_priv(ndev); + disable_irq(lp->tx_irq); disable_irq(lp->rx_irq); axienet_rx_irq(lp->tx_irq, ndev); @@ -2396,7 +2393,7 @@ static int axienet_probe(struct platform_device *pdev) goto cleanup_clk; } - if (!of_find_property(pdev->dev.of_node, "dmas", NULL)) { + if (!of_property_present(pdev->dev.of_node, "dmas")) { /* Find the DMA node, map the DMA registers, and decode the DMA IRQs */ np = of_parse_phandle(pdev->dev.of_node, "axistream-connected", 0); diff --git a/drivers/net/mdio/of_mdio.c b/drivers/net/mdio/of_mdio.c index 08e607f62e10..2f4fc664d2e1 100644 --- a/drivers/net/mdio/of_mdio.c +++ b/drivers/net/mdio/of_mdio.c @@ -390,7 +390,7 @@ EXPORT_SYMBOL(of_phy_get_and_connect); bool of_phy_is_fixed_link(struct device_node *np) { struct device_node *dn; - int len, err; + int err; const char *managed; /* New binding */ @@ -405,8 +405,7 @@ bool of_phy_is_fixed_link(struct device_node *np) return true; /* Old binding */ - if (of_get_property(np, "fixed-link", &len) && - len == (5 * sizeof(__be32))) + if (of_property_count_u32_elems(np, "fixed-link") == 5) return true; return false; diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 9c09293b5258..ffedf7648bed 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -38,7 +38,7 @@ #include <linux/etherdevice.h> #include <linux/utsname.h> -MODULE_AUTHOR("Maintainer: Matt Mackall <mpm@selenic.com>"); +MODULE_AUTHOR("Matt Mackall <mpm@selenic.com>"); MODULE_DESCRIPTION("Console driver for network interfaces"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 7752e9386b40..34752a87f98f 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -279,6 +279,15 @@ static struct phy_driver genphy_driver; static LIST_HEAD(phy_fixup_list); static DEFINE_MUTEX(phy_fixup_lock); +static bool phy_drv_wol_enabled(struct phy_device *phydev) +{ + struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; + + phy_ethtool_get_wol(phydev, &wol); + + return wol.wolopts != 0; +} + static bool mdio_bus_phy_may_suspend(struct phy_device *phydev) { struct device_driver *drv = phydev->mdio.dev.driver; @@ -288,6 +297,12 @@ static bool mdio_bus_phy_may_suspend(struct phy_device *phydev) if (!drv || !phydrv->suspend) return false; + /* If the PHY on the mido bus is not attached but has WOL enabled + * we cannot suspend the PHY. + */ + if (!netdev && phy_drv_wol_enabled(phydev)) + return false; + /* PHY not attached? May suspend if the PHY has not already been * suspended as part of a prior call to phy_disconnect() -> * phy_detach() -> phy_suspend() because the parent netdev might be the @@ -1975,7 +1990,6 @@ EXPORT_SYMBOL(phy_detach); int phy_suspend(struct phy_device *phydev) { - struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; struct net_device *netdev = phydev->attached_dev; const struct phy_driver *phydrv = phydev->drv; int ret; @@ -1983,8 +1997,7 @@ int phy_suspend(struct phy_device *phydev) if (phydev->suspended || !phydrv) return 0; - phy_ethtool_get_wol(phydev, &wol); - phydev->wol_enabled = wol.wolopts || + phydev->wol_enabled = phy_drv_wol_enabled(phydev) || (netdev && netdev->ethtool->wol_enabled); /* If the device has WOL enabled, we cannot suspend the PHY */ if (phydev->wol_enabled && !(phydrv->flags & PHY_ALWAYS_CALL_SUSPEND)) diff --git a/drivers/net/phy/qcom/qca807x.c b/drivers/net/phy/qcom/qca807x.c index 672c6929119a..ba558486c72f 100644 --- a/drivers/net/phy/qcom/qca807x.c +++ b/drivers/net/phy/qcom/qca807x.c @@ -733,16 +733,6 @@ static int qca807x_probe(struct phy_device *phydev) "qcom,dac-disable-bias-current-tweak"); #if IS_ENABLED(CONFIG_GPIOLIB) - /* Make sure we don't have mixed leds node and gpio-controller - * to prevent registering leds and having gpio-controller usage - * conflicting with them. - */ - if (of_find_property(node, "leds", NULL) && - of_find_property(node, "gpio-controller", NULL)) { - phydev_err(phydev, "Invalid property detected. LEDs and gpio-controller are mutually exclusive."); - return -EINVAL; - } - /* Do not register a GPIO controller unless flagged for it */ if (of_property_read_bool(node, "gpio-controller")) { ret = qca807x_gpio(phydev); diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c index 897b979ec03c..67ac4a2756ca 100644 --- a/drivers/net/phy/vitesse.c +++ b/drivers/net/phy/vitesse.c @@ -10,8 +10,10 @@ #include <linux/mii.h> #include <linux/ethtool.h> #include <linux/phy.h> +#include <linux/bitfield.h> /* Vitesse Extended Page Magic Register(s) */ +#define MII_VSC73XX_EXT_PAGE_1E 0x01 #define MII_VSC82X4_EXT_PAGE_16E 0x10 #define MII_VSC82X4_EXT_PAGE_17E 0x11 #define MII_VSC82X4_EXT_PAGE_18E 0x12 @@ -60,6 +62,15 @@ /* Vitesse Extended Page Access Register */ #define MII_VSC82X4_EXT_PAGE_ACCESS 0x1f +/* Vitesse VSC73XX Extended Control Register */ +#define MII_VSC73XX_PHY_CTRL_EXT3 0x14 + +#define MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_EN BIT(4) +#define MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_CNT GENMASK(3, 2) +#define MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_STA BIT(1) +#define MII_VSC73XX_DOWNSHIFT_MAX 5 +#define MII_VSC73XX_DOWNSHIFT_INVAL 1 + /* Vitesse VSC8601 Extended PHY Control Register 1 */ #define MII_VSC8601_EPHY_CTL 0x17 #define MII_VSC8601_EPHY_CTL_RGMII_SKEW (1 << 8) @@ -128,6 +139,74 @@ static int vsc73xx_write_page(struct phy_device *phydev, int page) return __phy_write(phydev, VSC73XX_EXT_PAGE_ACCESS, page); } +static int vsc73xx_get_downshift(struct phy_device *phydev, u8 *data) +{ + int val, enable, cnt; + + val = phy_read_paged(phydev, MII_VSC73XX_EXT_PAGE_1E, + MII_VSC73XX_PHY_CTRL_EXT3); + if (val < 0) + return val; + + enable = FIELD_GET(MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_EN, val); + cnt = FIELD_GET(MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_CNT, val) + 2; + + *data = enable ? cnt : DOWNSHIFT_DEV_DISABLE; + + return 0; +} + +static int vsc73xx_set_downshift(struct phy_device *phydev, u8 cnt) +{ + u16 mask, val; + int ret; + + if (cnt > MII_VSC73XX_DOWNSHIFT_MAX) + return -E2BIG; + else if (cnt == MII_VSC73XX_DOWNSHIFT_INVAL) + return -EINVAL; + + mask = MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_EN; + + if (!cnt) { + val = 0; + } else { + mask |= MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_CNT; + val = MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_EN | + FIELD_PREP(MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_CNT, + cnt - 2); + } + + ret = phy_modify_paged(phydev, MII_VSC73XX_EXT_PAGE_1E, + MII_VSC73XX_PHY_CTRL_EXT3, mask, val); + if (ret < 0) + return ret; + + return genphy_soft_reset(phydev); +} + +static int vsc73xx_get_tunable(struct phy_device *phydev, + struct ethtool_tunable *tuna, void *data) +{ + switch (tuna->id) { + case ETHTOOL_PHY_DOWNSHIFT: + return vsc73xx_get_downshift(phydev, data); + default: + return -EOPNOTSUPP; + } +} + +static int vsc73xx_set_tunable(struct phy_device *phydev, + struct ethtool_tunable *tuna, const void *data) +{ + switch (tuna->id) { + case ETHTOOL_PHY_DOWNSHIFT: + return vsc73xx_set_downshift(phydev, *(const u8 *)data); + default: + return -EOPNOTSUPP; + } +} + static void vsc73xx_config_init(struct phy_device *phydev) { /* Receiver init */ @@ -137,6 +216,9 @@ static void vsc73xx_config_init(struct phy_device *phydev) /* Config LEDs 0x61 */ phy_modify(phydev, MII_TPISTATUS, 0xff00, 0x0061); + + /* Enable downshift by default */ + vsc73xx_set_downshift(phydev, MII_VSC73XX_DOWNSHIFT_MAX); } static int vsc738x_config_init(struct phy_device *phydev) @@ -447,6 +529,8 @@ static struct phy_driver vsc82xx_driver[] = { .config_aneg = vsc73xx_config_aneg, .read_page = vsc73xx_read_page, .write_page = vsc73xx_write_page, + .get_tunable = vsc73xx_get_tunable, + .set_tunable = vsc73xx_set_tunable, }, { .phy_id = PHY_ID_VSC7388, .name = "Vitesse VSC7388", @@ -456,6 +540,8 @@ static struct phy_driver vsc82xx_driver[] = { .config_aneg = vsc73xx_config_aneg, .read_page = vsc73xx_read_page, .write_page = vsc73xx_write_page, + .get_tunable = vsc73xx_get_tunable, + .set_tunable = vsc73xx_set_tunable, }, { .phy_id = PHY_ID_VSC7395, .name = "Vitesse VSC7395", @@ -465,6 +551,8 @@ static struct phy_driver vsc82xx_driver[] = { .config_aneg = vsc73xx_config_aneg, .read_page = vsc73xx_read_page, .write_page = vsc73xx_write_page, + .get_tunable = vsc73xx_get_tunable, + .set_tunable = vsc73xx_set_tunable, }, { .phy_id = PHY_ID_VSC7398, .name = "Vitesse VSC7398", @@ -474,6 +562,8 @@ static struct phy_driver vsc82xx_driver[] = { .config_aneg = vsc73xx_config_aneg, .read_page = vsc73xx_read_page, .write_page = vsc73xx_write_page, + .get_tunable = vsc73xx_get_tunable, + .set_tunable = vsc73xx_set_tunable, }, { .phy_id = PHY_ID_VSC8662, .name = "Vitesse VSC8662", diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 426e68a95067..34499b91a8bd 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -1696,6 +1696,7 @@ static void veth_setup(struct net_device *dev) dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; dev->priv_flags |= IFF_NO_QUEUE; dev->priv_flags |= IFF_PHONY_HEADROOM; + dev->priv_flags |= IFF_DISABLE_NETPOLL; dev->netdev_ops = &veth_netdev_ops; dev->xdp_metadata_ops = &veth_xdp_metadata_ops; diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index bf664ec9341b..802153e23073 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -244,7 +244,7 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, restart_tx = true; } - consume_skb(skb); + virtio_transport_consume_skb_sent(skb, true); } } while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len))); if (added) @@ -451,6 +451,8 @@ static struct virtio_transport vhost_transport = { .notify_buffer_size = virtio_transport_notify_buffer_size, .notify_set_rcvlowat = virtio_transport_notify_set_rcvlowat, + .unsent_bytes = virtio_transport_unsent_bytes, + .read_skb = virtio_transport_read_skb, }, diff --git a/include/linux/filter.h b/include/linux/filter.h index b6672ff61407..64e1506fefb8 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1616,7 +1616,7 @@ extern struct static_key_false bpf_sk_lookup_enabled; _all_pass || _selected_sk ? SK_PASS : SK_DROP; \ }) -static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol, +static inline bool bpf_sk_lookup_run_v4(const struct net *net, int protocol, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 dport, const int ifindex, struct sock **psk) @@ -1653,7 +1653,7 @@ static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol, } #if IS_ENABLED(CONFIG_IPV6) -static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, +static inline bool bpf_sk_lookup_run_v6(const struct net *net, int protocol, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 383a0ea2ab91..a6e2aadbb91b 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -89,6 +89,7 @@ struct ipv6_devconf { __u8 ioam6_enabled; __u8 ndisc_evict_nocarrier; __u8 ra_honor_pio_life; + __u8 ra_honor_pio_pflag; struct ctl_table_header *sysctl_header; }; diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index d94bfd9ac8cc..3b9de09871f6 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -37,8 +37,9 @@ static inline bool linkmode_empty(const unsigned long *src) return bitmap_empty(src, __ETHTOOL_LINK_MODE_MASK_NBITS); } -static inline int linkmode_andnot(unsigned long *dst, const unsigned long *src1, - const unsigned long *src2) +static inline bool linkmode_andnot(unsigned long *dst, + const unsigned long *src1, + const unsigned long *src2) { return bitmap_andnot(dst, src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); } diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index ba875a619b97..a94bc9e3af96 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1243,7 +1243,8 @@ enum mlx5_pcam_feature_groups { enum mlx5_mcam_reg_groups { MLX5_MCAM_REGS_FIRST_128 = 0x0, MLX5_MCAM_REGS_0x9100_0x917F = 0x2, - MLX5_MCAM_REGS_NUM = 0x3, + MLX5_MCAM_REGS_0x9180_0x91FF = 0x3, + MLX5_MCAM_REGS_NUM = 0x4, }; enum mlx5_mcam_feature_groups { @@ -1392,6 +1393,10 @@ enum mlx5_qcam_feature_groups { MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_0x9100_0x917F], \ mng_access_reg_cap_mask.access_regs2.reg) +#define MLX5_CAP_MCAM_REG3(mdev, reg) \ + MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_0x9180_0x91FF], \ + mng_access_reg_cap_mask.access_regs3.reg) + #define MLX5_CAP_MCAM_FEATURE(mdev, fld) \ MLX5_GET(mcam_reg, (mdev)->caps.mcam, mng_feature_cap_mask.enhanced_features.fld) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index a96438ded15f..9f42834f57c5 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -159,6 +159,8 @@ enum { MLX5_REG_MSECQ = 0x9155, MLX5_REG_MSEES = 0x9156, MLX5_REG_MIRC = 0x9162, + MLX5_REG_MTPTM = 0x9180, + MLX5_REG_MTCTR = 0x9181, MLX5_REG_SBCAM = 0xB01F, MLX5_REG_RESOURCE_DUMP = 0xC000, MLX5_REG_DTOR = 0xC00E, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index cab228cf51c6..234ad6f16e92 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -10401,6 +10401,18 @@ struct mlx5_ifc_mcam_access_reg_bits2 { u8 regs_31_to_0[0x20]; }; +struct mlx5_ifc_mcam_access_reg_bits3 { + u8 regs_127_to_96[0x20]; + + u8 regs_95_to_64[0x20]; + + u8 regs_63_to_32[0x20]; + + u8 regs_31_to_2[0x1e]; + u8 mtctr[0x1]; + u8 mtptm[0x1]; +}; + struct mlx5_ifc_mcam_reg_bits { u8 reserved_at_0[0x8]; u8 feature_group[0x8]; @@ -10413,6 +10425,7 @@ struct mlx5_ifc_mcam_reg_bits { struct mlx5_ifc_mcam_access_reg_bits access_regs; struct mlx5_ifc_mcam_access_reg_bits1 access_regs1; struct mlx5_ifc_mcam_access_reg_bits2 access_regs2; + struct mlx5_ifc_mcam_access_reg_bits3 access_regs3; u8 reserved_at_0[0x80]; } mng_access_reg_cap_mask; @@ -11166,6 +11179,34 @@ struct mlx5_ifc_mtmp_reg_bits { u8 sensor_name_lo[0x20]; }; +struct mlx5_ifc_mtptm_reg_bits { + u8 reserved_at_0[0x10]; + u8 psta[0x1]; + u8 reserved_at_11[0xf]; + + u8 reserved_at_20[0x60]; +}; + +enum { + MLX5_MTCTR_REQUEST_NOP = 0x0, + MLX5_MTCTR_REQUEST_PTM_ROOT_CLOCK = 0x1, + MLX5_MTCTR_REQUEST_FREE_RUNNING_COUNTER = 0x2, + MLX5_MTCTR_REQUEST_REAL_TIME_CLOCK = 0x3, +}; + +struct mlx5_ifc_mtctr_reg_bits { + u8 first_clock_timestamp_request[0x8]; + u8 second_clock_timestamp_request[0x8]; + u8 reserved_at_10[0x10]; + + u8 first_clock_valid[0x1]; + u8 second_clock_valid[0x1]; + u8 reserved_at_22[0x1e]; + + u8 first_clock_timestamp[0x40]; + u8 second_clock_timestamp[0x40]; +}; + union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_bufferx_reg_bits bufferx_reg; struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits eth_2819_cntrs_grp_data_layout; @@ -11230,6 +11271,8 @@ union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_mrtc_reg_bits mrtc_reg; struct mlx5_ifc_mtcap_reg_bits mtcap_reg; struct mlx5_ifc_mtmp_reg_bits mtmp_reg; + struct mlx5_ifc_mtptm_reg_bits mtptm_reg; + struct mlx5_ifc_mtctr_reg_bits mtctr_reg; u8 reserved_at_0[0x60e0]; }; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 607009150b5f..0ef3eaa23f4b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1689,38 +1689,6 @@ enum netdev_priv_flags { IFF_SEE_ALL_HWTSTAMP_REQUESTS = BIT_ULL(33), }; -#define IFF_802_1Q_VLAN IFF_802_1Q_VLAN -#define IFF_EBRIDGE IFF_EBRIDGE -#define IFF_BONDING IFF_BONDING -#define IFF_ISATAP IFF_ISATAP -#define IFF_WAN_HDLC IFF_WAN_HDLC -#define IFF_XMIT_DST_RELEASE IFF_XMIT_DST_RELEASE -#define IFF_DONT_BRIDGE IFF_DONT_BRIDGE -#define IFF_DISABLE_NETPOLL IFF_DISABLE_NETPOLL -#define IFF_MACVLAN_PORT IFF_MACVLAN_PORT -#define IFF_BRIDGE_PORT IFF_BRIDGE_PORT -#define IFF_OVS_DATAPATH IFF_OVS_DATAPATH -#define IFF_TX_SKB_SHARING IFF_TX_SKB_SHARING -#define IFF_UNICAST_FLT IFF_UNICAST_FLT -#define IFF_TEAM_PORT IFF_TEAM_PORT -#define IFF_SUPP_NOFCS IFF_SUPP_NOFCS -#define IFF_LIVE_ADDR_CHANGE IFF_LIVE_ADDR_CHANGE -#define IFF_MACVLAN IFF_MACVLAN -#define IFF_XMIT_DST_RELEASE_PERM IFF_XMIT_DST_RELEASE_PERM -#define IFF_L3MDEV_MASTER IFF_L3MDEV_MASTER -#define IFF_NO_QUEUE IFF_NO_QUEUE -#define IFF_OPENVSWITCH IFF_OPENVSWITCH -#define IFF_L3MDEV_SLAVE IFF_L3MDEV_SLAVE -#define IFF_TEAM IFF_TEAM -#define IFF_RXFH_CONFIGURED IFF_RXFH_CONFIGURED -#define IFF_PHONY_HEADROOM IFF_PHONY_HEADROOM -#define IFF_MACSEC IFF_MACSEC -#define IFF_NO_RX_HANDLER IFF_NO_RX_HANDLER -#define IFF_FAILOVER IFF_FAILOVER -#define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE -#define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER -#define IFF_TX_SKB_NO_LINEAR IFF_TX_SKB_NO_LINEAR - /* Specifies the type of the struct net_device::ml_priv pointer */ enum netdev_ml_priv_type { ML_PRIV_NONE, diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 29c3ea5b6e93..cf8f6ce06742 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1225,7 +1225,7 @@ static inline bool skb_unref(struct sk_buff *skb) { if (unlikely(!skb)) return false; - if (likely(refcount_read(&skb->users) == 1)) + if (!IS_ENABLED(CONFIG_DEBUG_NET) && likely(refcount_read(&skb->users) == 1)) smp_rmb(); else if (likely(!refcount_dec_and_test(&skb->users))) return false; diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index c82089dee0c8..0387d64e2c66 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -133,6 +133,7 @@ struct virtio_vsock_sock { u32 tx_cnt; u32 peer_fwd_cnt; u32 peer_buf_alloc; + size_t bytes_unsent; /* Protected by rx_lock */ u32 fwd_cnt; @@ -193,6 +194,11 @@ s64 virtio_transport_stream_has_data(struct vsock_sock *vsk); s64 virtio_transport_stream_has_space(struct vsock_sock *vsk); u32 virtio_transport_seqpacket_has_data(struct vsock_sock *vsk); +ssize_t virtio_transport_unsent_bytes(struct vsock_sock *vsk); + +void virtio_transport_consume_skb_sent(struct sk_buff *skb, + bool consume); + int virtio_transport_do_socket_init(struct vsock_sock *vsk, struct vsock_sock *psk); int diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 62a407db1bf5..b18e81f0c9e1 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -37,10 +37,14 @@ struct prefix_info { struct __packed { #if defined(__BIG_ENDIAN_BITFIELD) __u8 onlink : 1, - autoconf : 1, - reserved : 6; + autoconf : 1, + routeraddr : 1, + preferpd : 1, + reserved : 4; #elif defined(__LITTLE_ENDIAN_BITFIELD) - __u8 reserved : 6, + __u8 reserved : 4, + preferpd : 1, + routeraddr : 1, autoconf : 1, onlink : 1; #else diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 535701efc1e5..fc504d2da3d0 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -169,6 +169,9 @@ struct vsock_transport { void (*notify_buffer_size)(struct vsock_sock *, u64 *); int (*notify_set_rcvlowat)(struct vsock_sock *vsk, int val); + /* SIOCOUTQ ioctl */ + ssize_t (*unsent_bytes)(struct vsock_sock *vsk); + /* Shutdown. */ int (*shutdown)(struct vsock_sock *, int); diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 533a7337865a..74dd90ff5f12 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -40,7 +40,7 @@ static inline unsigned int __inet6_ehashfn(const u32 lhash, * * The sockhash lock must be held as a reader here. */ -struct sock *__inet6_lookup_established(struct net *net, +struct sock *__inet6_lookup_established(const struct net *net, struct inet_hashinfo *hashinfo, const struct in6_addr *saddr, const __be16 sport, @@ -56,7 +56,7 @@ inet6_ehashfn_t inet6_ehashfn; INDIRECT_CALLABLE_DECLARE(inet6_ehashfn_t udp6_ehashfn); -struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, +struct sock *inet6_lookup_reuseport(const struct net *net, struct sock *sk, struct sk_buff *skb, int doff, const struct in6_addr *saddr, __be16 sport, @@ -64,7 +64,7 @@ struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, unsigned short hnum, inet6_ehashfn_t *ehashfn); -struct sock *inet6_lookup_listener(struct net *net, +struct sock *inet6_lookup_listener(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -73,7 +73,7 @@ struct sock *inet6_lookup_listener(struct net *net, const unsigned short hnum, const int dif, const int sdif); -struct sock *inet6_lookup_run_sk_lookup(struct net *net, +struct sock *inet6_lookup_run_sk_lookup(const struct net *net, int protocol, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -82,7 +82,7 @@ struct sock *inet6_lookup_run_sk_lookup(struct net *net, const u16 hnum, const int dif, inet6_ehashfn_t *ehashfn); -static inline struct sock *__inet6_lookup(struct net *net, +static inline struct sock *__inet6_lookup(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -167,7 +167,7 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo, iif, sdif, refcounted); } -struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, +struct sock *inet6_lookup(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const __be16 dport, @@ -175,7 +175,7 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, int inet6_hash(struct sock *sk); -static inline bool inet6_match(struct net *net, const struct sock *sk, +static inline bool inet6_match(const struct net *net, const struct sock *sk, const struct in6_addr *saddr, const struct in6_addr *daddr, const __portpair ports, diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 7f1b38458743..5eea47f135a4 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -304,7 +304,7 @@ int __inet_hash(struct sock *sk, struct sock *osk); int inet_hash(struct sock *sk); void inet_unhash(struct sock *sk); -struct sock *__inet_lookup_listener(struct net *net, +struct sock *__inet_lookup_listener(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const __be32 saddr, const __be16 sport, @@ -351,7 +351,7 @@ static inline struct sock *inet_lookup_listener(struct net *net, ((__force __u64)(__be32)(__saddr))) #endif /* __BIG_ENDIAN */ -static inline bool inet_match(struct net *net, const struct sock *sk, +static inline bool inet_match(const struct net *net, const struct sock *sk, const __addrpair cookie, const __portpair ports, int dif, int sdif) { @@ -368,7 +368,7 @@ static inline bool inet_match(struct net *net, const struct sock *sk, /* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need * not check it for lookups anymore, thanks Alexey. -DaveM */ -struct sock *__inet_lookup_established(struct net *net, +struct sock *__inet_lookup_established(const struct net *net, struct inet_hashinfo *hashinfo, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 hnum, @@ -382,13 +382,13 @@ inet_ehashfn_t inet_ehashfn; INDIRECT_CALLABLE_DECLARE(inet_ehashfn_t udp_ehashfn); -struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk, +struct sock *inet_lookup_reuseport(const struct net *net, struct sock *sk, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, __be32 daddr, unsigned short hnum, inet_ehashfn_t *ehashfn); -struct sock *inet_lookup_run_sk_lookup(struct net *net, +struct sock *inet_lookup_run_sk_lookup(const struct net *net, int protocol, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index f9ddd47dc4f8..394c3b66065e 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -150,7 +150,8 @@ static inline bool inet_bound_dev_eq(bool l3mdev_accept, int bound_dev_if, return bound_dev_if == dif || bound_dev_if == sdif; } -static inline bool inet_sk_bound_dev_eq(struct net *net, int bound_dev_if, +static inline bool inet_sk_bound_dev_eq(const struct net *net, + int bound_dev_if, int dif, int sdif) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index 11cefd50704d..8a3465c8c2c5 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -82,7 +82,7 @@ extern const struct ipv6_stub *ipv6_stub __read_mostly; struct ipv6_bpf_stub { int (*inet6_bind)(struct sock *sk, struct sockaddr *uaddr, int addr_len, u32 flags); - struct sock *(*udp6_lib_lookup)(struct net *net, + struct sock *(*udp6_lib_lookup)(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif, int sdif, struct udp_table *tbl, diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 20c34bd7a077..e67b483cc8bb 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -451,8 +451,8 @@ struct pernet_operations { /* Following method is called with RTNL held. */ void (*exit_batch_rtnl)(struct list_head *net_exit_list, struct list_head *dev_kill_list); - unsigned int *id; - size_t size; + unsigned int * const id; + const size_t size; }; /* diff --git a/include/net/rstreason.h b/include/net/rstreason.h index 2575c85d7f7a..69cb2e52b7da 100644 --- a/include/net/rstreason.h +++ b/include/net/rstreason.h @@ -17,6 +17,12 @@ FN(TCP_ABORT_ON_DATA) \ FN(TCP_TIMEWAIT_SOCKET) \ FN(INVALID_SYN) \ + FN(TCP_ABORT_ON_CLOSE) \ + FN(TCP_ABORT_ON_LINGER) \ + FN(TCP_ABORT_ON_MEMORY) \ + FN(TCP_STATE) \ + FN(TCP_KEEPALIVE_TIMEOUT) \ + FN(TCP_DISCONNECT_WITH_DATA) \ FN(MPTCP_RST_EUNSPEC) \ FN(MPTCP_RST_EMPTCP) \ FN(MPTCP_RST_ERESOURCE) \ @@ -84,6 +90,39 @@ enum sk_rst_reason { * an error, send a reset" */ SK_RST_REASON_INVALID_SYN, + /** + * @SK_RST_REASON_TCP_ABORT_ON_CLOSE: abort on close + * corresponding to LINUX_MIB_TCPABORTONCLOSE + */ + SK_RST_REASON_TCP_ABORT_ON_CLOSE, + /** + * @SK_RST_REASON_TCP_ABORT_ON_LINGER: abort on linger + * corresponding to LINUX_MIB_TCPABORTONLINGER + */ + SK_RST_REASON_TCP_ABORT_ON_LINGER, + /** + * @SK_RST_REASON_TCP_ABORT_ON_MEMORY: abort on memory + * corresponding to LINUX_MIB_TCPABORTONMEMORY + */ + SK_RST_REASON_TCP_ABORT_ON_MEMORY, + /** + * @SK_RST_REASON_TCP_STATE: abort on tcp state + * Please see RFC 9293 for all possible reset conditions + */ + SK_RST_REASON_TCP_STATE, + /** + * @SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT: time to timeout + * When we have already run out of all the chances, which means + * keepalive timeout, we have to reset the connection + */ + SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT, + /** + * @SK_RST_REASON_TCP_DISCONNECT_WITH_DATA: disconnect when write + * queue is not empty + * It means user has written data into the write queue when doing + * disconnecting, so we have to send an RST. + */ + SK_RST_REASON_TCP_DISCONNECT_WITH_DATA, /* Copy from include/uapi/linux/mptcp.h. * These reset fields will not be changed since they adhere to diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h index 6ec140b0a61b..6e4faf3ee76f 100644 --- a/include/net/sock_reuseport.h +++ b/include/net/sock_reuseport.h @@ -26,7 +26,7 @@ struct sock_reuseport { unsigned int bind_inany:1; unsigned int has_conns:1; struct bpf_prog __rcu *prog; /* optional BPF sock selector */ - struct sock *socks[]; /* array of sock pointers */ + struct sock *socks[] __counted_by(max_socks); }; extern int reuseport_alloc(struct sock *sk, bool bind_inany); diff --git a/include/net/udp.h b/include/net/udp.h index c4e05b14b648..5ca53b1cec67 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -79,7 +79,8 @@ struct udp_table { extern struct udp_table udp_table; void udp_table_init(struct udp_table *, const char *); static inline struct udp_hslot *udp_hashslot(struct udp_table *table, - struct net *net, unsigned int num) + const struct net *net, + unsigned int num) { return &table->hash[udp_hashfn(net, num, table->mask)]; } @@ -245,7 +246,7 @@ static inline int udp_rqueue_get(struct sock *sk) return sk_rmem_alloc_get(sk) - READ_ONCE(udp_sk(sk)->forward_deficit); } -static inline bool udp_sk_bound_dev_eq(struct net *net, int bound_dev_if, +static inline bool udp_sk_bound_dev_eq(const struct net *net, int bound_dev_if, int dif, int sdif) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) @@ -296,18 +297,19 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, int udp_lib_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen, int (*push_pending_frames)(struct sock *)); -struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, +struct sock *udp4_lib_lookup(const struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif); -struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, +struct sock *__udp4_lib_lookup(const struct net *net, __be32 saddr, + __be16 sport, __be32 daddr, __be16 dport, int dif, int sdif, struct udp_table *tbl, struct sk_buff *skb); struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport); -struct sock *udp6_lib_lookup(struct net *net, +struct sock *udp6_lib_lookup(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif); -struct sock *__udp6_lib_lookup(struct net *net, +struct sock *__udp6_lib_lookup(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif, int sdif, struct udp_table *tbl, diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 6a823ba906c6..11e4dd4f09ed 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -125,7 +125,7 @@ static int ops_init(const struct pernet_operations *ops, struct net *net) int err = -ENOMEM; void *data = NULL; - if (ops->id && ops->size) { + if (ops->id) { data = kzalloc(ops->size, GFP_KERNEL); if (!data) goto out; @@ -140,7 +140,7 @@ static int ops_init(const struct pernet_operations *ops, struct net *net) if (!err) return 0; - if (ops->id && ops->size) { + if (ops->id) { ng = rcu_dereference_protected(net->gen, lockdep_is_held(&pernet_ops_rwsem)); ng->ptr[*ops->id] = NULL; @@ -182,7 +182,8 @@ static void ops_free_list(const struct pernet_operations *ops, struct list_head *net_exit_list) { struct net *net; - if (ops->size && ops->id) { + + if (ops->id) { list_for_each_entry(net, net_exit_list, exit_list) kfree(net_generic(net, *ops->id)); } @@ -308,16 +309,38 @@ struct net *get_net_ns_by_id(const struct net *net, int id) } EXPORT_SYMBOL_GPL(get_net_ns_by_id); +static __net_init void preinit_net_sysctl(struct net *net) +{ + net->core.sysctl_somaxconn = SOMAXCONN; + /* Limits per socket sk_omem_alloc usage. + * TCP zerocopy regular usage needs 128 KB. + */ + net->core.sysctl_optmem_max = 128 * 1024; + net->core.sysctl_txrehash = SOCK_TXREHASH_ENABLED; +} + /* init code that must occur even if setup_net() is not called. */ -static __net_init void preinit_net(struct net *net) +static __net_init void preinit_net(struct net *net, struct user_namespace *user_ns) { + refcount_set(&net->passive, 1); + refcount_set(&net->ns.count, 1); + ref_tracker_dir_init(&net->refcnt_tracker, 128, "net refcnt"); ref_tracker_dir_init(&net->notrefcnt_tracker, 128, "net notrefcnt"); + + get_random_bytes(&net->hash_mix, sizeof(u32)); + net->dev_base_seq = 1; + net->user_ns = user_ns; + + idr_init(&net->netns_ids); + spin_lock_init(&net->nsid_lock); + mutex_init(&net->ipv4.ra_mutex); + preinit_net_sysctl(net); } /* * setup_net runs the initializers for the network namespace object. */ -static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) +static __net_init int setup_net(struct net *net) { /* Must be called with pernet_ops_rwsem held */ const struct pernet_operations *ops, *saved_ops; @@ -325,19 +348,9 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) LIST_HEAD(dev_kill_list); int error = 0; - refcount_set(&net->ns.count, 1); - ref_tracker_dir_init(&net->refcnt_tracker, 128, "net refcnt"); - - refcount_set(&net->passive, 1); - get_random_bytes(&net->hash_mix, sizeof(u32)); preempt_disable(); net->net_cookie = gen_cookie_next(&net_cookie); preempt_enable(); - net->dev_base_seq = 1; - net->user_ns = user_ns; - idr_init(&net->netns_ids); - spin_lock_init(&net->nsid_lock); - mutex_init(&net->ipv4.ra_mutex); list_for_each_entry(ops, &pernet_list, list) { error = ops_init(ops, net); @@ -382,32 +395,6 @@ out_undo: goto out; } -static int __net_init net_defaults_init_net(struct net *net) -{ - net->core.sysctl_somaxconn = SOMAXCONN; - /* Limits per socket sk_omem_alloc usage. - * TCP zerocopy regular usage needs 128 KB. - */ - net->core.sysctl_optmem_max = 128 * 1024; - net->core.sysctl_txrehash = SOCK_TXREHASH_ENABLED; - - return 0; -} - -static struct pernet_operations net_defaults_ops = { - .init = net_defaults_init_net, -}; - -static __init int net_defaults_init(void) -{ - if (register_pernet_subsys(&net_defaults_ops)) - panic("Cannot initialize net default settings"); - - return 0; -} - -core_initcall(net_defaults_init); - #ifdef CONFIG_NET_NS static struct ucounts *inc_net_namespaces(struct user_namespace *ns) { @@ -496,8 +483,7 @@ struct net *copy_net_ns(unsigned long flags, goto dec_ucounts; } - preinit_net(net); - refcount_set(&net->passive, 1); + preinit_net(net, user_ns); net->ucounts = ucounts; get_user_ns(user_ns); @@ -505,7 +491,7 @@ struct net *copy_net_ns(unsigned long flags, if (rv < 0) goto put_userns; - rv = setup_net(net, user_ns); + rv = setup_net(net); up_read(&pernet_ops_rwsem); @@ -1199,9 +1185,10 @@ void __init net_ns_init(void) #ifdef CONFIG_KEYS init_net.key_domain = &init_net_key_domain; #endif + preinit_net(&init_net, &init_user_ns); + down_write(&pernet_ops_rwsem); - preinit_net(&init_net); - if (setup_net(&init_net, &init_user_ns)) + if (setup_net(&init_net)) panic("Could not setup the initial network namespace"); init_net_initialized = true; @@ -1244,7 +1231,7 @@ static int __register_pernet_operations(struct list_head *list, LIST_HEAD(net_exit_list); list_add_tail(&ops->list, list); - if (ops->init || (ops->id && ops->size)) { + if (ops->init || ops->id) { /* We held write locked pernet_ops_rwsem, and parallel * setup_net() and cleanup_net() are not possible. */ @@ -1310,6 +1297,9 @@ static int register_pernet_operations(struct list_head *list, { int error; + if (WARN_ON(!!ops->id ^ !!ops->size)) + return -EINVAL; + if (ops->id) { error = ida_alloc_min(&net_generic_ids, MIN_PERNET_OPS_ID, GFP_KERNEL); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 83f8cd8aa2d1..de2a044cc665 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -314,8 +314,8 @@ void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) fragsz = SKB_DATA_ALIGN(fragsz); local_lock_nested_bh(&napi_alloc_cache.bh_lock); - data = __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, - align_mask); + data = __page_frag_alloc_align(&nc->page, fragsz, + GFP_ATOMIC | __GFP_NOWARN, align_mask); local_unlock_nested_bh(&napi_alloc_cache.bh_lock); return data; @@ -330,7 +330,8 @@ void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) struct page_frag_cache *nc = this_cpu_ptr(&netdev_alloc_cache); fragsz = SKB_DATA_ALIGN(fragsz); - data = __page_frag_alloc_align(nc, fragsz, GFP_ATOMIC, + data = __page_frag_alloc_align(nc, fragsz, + GFP_ATOMIC | __GFP_NOWARN, align_mask); } else { local_bh_disable(); @@ -349,7 +350,7 @@ static struct sk_buff *napi_skb_cache_get(void) local_lock_nested_bh(&napi_alloc_cache.bh_lock); if (unlikely(!nc->skb_count)) { nc->skb_count = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, - GFP_ATOMIC, + GFP_ATOMIC | __GFP_NOWARN, NAPI_SKB_CACHE_BULK, nc->skb_cache); if (unlikely(!nc->skb_count)) { @@ -418,7 +419,8 @@ struct sk_buff *slab_build_skb(void *data) struct sk_buff *skb; unsigned int size; - skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(net_hotdata.skbuff_cache, + GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL; @@ -469,7 +471,8 @@ struct sk_buff *__build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb; - skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(net_hotdata.skbuff_cache, + GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL; diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index 5a165286e4d8..4211710393a8 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -173,10 +173,9 @@ static bool __reuseport_detach_closed_sock(struct sock *sk, static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks) { - unsigned int size = sizeof(struct sock_reuseport) + - sizeof(struct sock *) * max_socks; - struct sock_reuseport *reuse = kzalloc(size, GFP_ATOMIC); + struct sock_reuseport *reuse; + reuse = kzalloc(struct_size(reuse, socks, max_socks), GFP_ATOMIC); if (!reuse) return NULL; diff --git a/net/ethtool/cmis.h b/net/ethtool/cmis.h index e71cc3e1b7eb..3e7c293af78c 100644 --- a/net/ethtool/cmis.h +++ b/net/ethtool/cmis.h @@ -108,7 +108,6 @@ void ethtool_cmis_cdb_check_completion_flag(u8 cmis_rev, u8 *flags); void ethtool_cmis_page_init(struct ethtool_module_eeprom *page_data, u8 page, u32 offset, u32 length); -void ethtool_cmis_page_fini(struct ethtool_module_eeprom *page_data); struct ethtool_cmis_cdb * ethtool_cmis_cdb_init(struct net_device *dev, diff --git a/net/ethtool/linkinfo.c b/net/ethtool/linkinfo.c index 5c317d23787b..30b8ce275159 100644 --- a/net/ethtool/linkinfo.c +++ b/net/ethtool/linkinfo.c @@ -35,7 +35,7 @@ static int linkinfo_prepare_data(const struct ethnl_req_info *req_base, if (ret < 0) return ret; ret = __ethtool_get_link_ksettings(dev, &data->ksettings); - if (ret < 0 && info) + if (ret < 0) GENL_SET_ERR_MSG(info, "failed to retrieve link settings"); ethnl_ops_complete(dev); diff --git a/net/ethtool/linkmodes.c b/net/ethtool/linkmodes.c index b2591db49f7d..259cd9ef1f2a 100644 --- a/net/ethtool/linkmodes.c +++ b/net/ethtool/linkmodes.c @@ -40,7 +40,7 @@ static int linkmodes_prepare_data(const struct ethnl_req_info *req_base, return ret; ret = __ethtool_get_link_ksettings(dev, &data->ksettings); - if (ret < 0 && info) { + if (ret < 0) { GENL_SET_ERR_MSG(info, "failed to retrieve link settings"); goto out; } diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c index c678b484a079..56b99606f00b 100644 --- a/net/ethtool/strset.c +++ b/net/ethtool/strset.c @@ -289,8 +289,7 @@ static int strset_prepare_data(const struct ethnl_req_info *req_base, for (i = 0; i < ETH_SS_COUNT; i++) { if ((req_info->req_ids & (1U << i)) && data->sets[i].per_dev) { - if (info) - GENL_SET_ERR_MSG(info, "requested per device strings without dev"); + GENL_SET_ERR_MSG(info, "requested per device strings without dev"); return -EINVAL; } } diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 8e94ed7c56a0..6d2c97f8e9ef 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -661,7 +661,8 @@ config TCP_CONG_CDG For further details see: D.A. Hayes and G. Armitage. "Revisiting TCP congestion control using - delay gradients." In Networking 2011. Preprint: http://goo.gl/No3vdg + delay gradients." In Networking 2011. Preprint: + http://caia.swin.edu.au/cv/dahayes/content/networking2011-cdg-preprint.pdf config TCP_CONG_BBR tristate "BBR TCP" diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 48d0d494185b..9bfcfd016e18 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -310,7 +310,7 @@ inet_lhash2_bucket_sk(struct inet_hashinfo *h, struct sock *sk) return inet_lhash2_bucket(h, hash); } -static inline int compute_score(struct sock *sk, struct net *net, +static inline int compute_score(struct sock *sk, const struct net *net, const unsigned short hnum, const __be32 daddr, const int dif, const int sdif) { @@ -348,7 +348,7 @@ static inline int compute_score(struct sock *sk, struct net *net, * Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to * the selected sock or an error. */ -struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk, +struct sock *inet_lookup_reuseport(const struct net *net, struct sock *sk, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, __be32 daddr, unsigned short hnum, @@ -374,7 +374,7 @@ EXPORT_SYMBOL_GPL(inet_lookup_reuseport); */ /* called with rcu_read_lock() : No refcount taken on the socket */ -static struct sock *inet_lhash2_lookup(struct net *net, +static struct sock *inet_lhash2_lookup(const struct net *net, struct inet_listen_hashbucket *ilb2, struct sk_buff *skb, int doff, const __be32 saddr, __be16 sport, @@ -401,7 +401,7 @@ static struct sock *inet_lhash2_lookup(struct net *net, return result; } -struct sock *inet_lookup_run_sk_lookup(struct net *net, +struct sock *inet_lookup_run_sk_lookup(const struct net *net, int protocol, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, @@ -423,7 +423,7 @@ struct sock *inet_lookup_run_sk_lookup(struct net *net, return sk; } -struct sock *__inet_lookup_listener(struct net *net, +struct sock *__inet_lookup_listener(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const __be32 saddr, __be16 sport, @@ -488,7 +488,7 @@ void sock_edemux(struct sk_buff *skb) } EXPORT_SYMBOL(sock_edemux); -struct sock *__inet_lookup_established(struct net *net, +struct sock *__inet_lookup_established(const struct net *net, struct inet_hashinfo *hashinfo, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 hnum, diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index b90d0f78ac80..8a10a7c67834 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1534,6 +1534,7 @@ void ip_flush_pending_frames(struct sock *sk) { __ip_flush_pending_frames(sk, &sk->sk_write_queue, &inet_sk(sk)->cork.base); } +EXPORT_SYMBOL_GPL(ip_flush_pending_frames); struct sk_buff *ip_make_skb(struct sock *sk, struct flowi4 *fl4, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e03a342c9162..8514257f4ecd 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2833,7 +2833,7 @@ void __tcp_close(struct sock *sk, long timeout) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE); tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, sk->sk_allocation, - SK_RST_REASON_NOT_SPECIFIED); + SK_RST_REASON_TCP_ABORT_ON_CLOSE); } else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) { /* Check zero linger _after_ checking for unread data. */ sk->sk_prot->disconnect(sk, 0); @@ -2908,7 +2908,7 @@ adjudge_to_death: if (READ_ONCE(tp->linger2) < 0) { tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, GFP_ATOMIC, - SK_RST_REASON_NOT_SPECIFIED); + SK_RST_REASON_TCP_ABORT_ON_LINGER); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONLINGER); } else { @@ -2927,7 +2927,7 @@ adjudge_to_death: if (tcp_check_oom(sk, 0)) { tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, GFP_ATOMIC, - SK_RST_REASON_NOT_SPECIFIED); + SK_RST_REASON_TCP_ABORT_ON_MEMORY); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); } else if (!check_net(sock_net(sk))) { @@ -3025,13 +3025,16 @@ int tcp_disconnect(struct sock *sk, int flags) inet_csk_listen_stop(sk); } else if (unlikely(tp->repair)) { WRITE_ONCE(sk->sk_err, ECONNABORTED); - } else if (tcp_need_reset(old_state) || - (tp->snd_nxt != tp->write_seq && - (1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK))) { + } else if (tcp_need_reset(old_state)) { + tcp_send_active_reset(sk, gfp_any(), SK_RST_REASON_TCP_STATE); + WRITE_ONCE(sk->sk_err, ECONNRESET); + } else if (tp->snd_nxt != tp->write_seq && + (1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK)) { /* The last check adjusts for discrepancy of Linux wrt. RFC * states */ - tcp_send_active_reset(sk, gfp_any(), SK_RST_REASON_NOT_SPECIFIED); + tcp_send_active_reset(sk, gfp_any(), + SK_RST_REASON_TCP_DISCONNECT_WITH_DATA); WRITE_ONCE(sk->sk_err, ECONNRESET); } else if (old_state == TCP_SYN_SENT) WRITE_ONCE(sk->sk_err, ECONNRESET); @@ -4649,7 +4652,7 @@ int tcp_abort(struct sock *sk, int err) if (!sock_flag(sk, SOCK_DEAD)) { if (tcp_need_reset(sk->sk_state)) tcp_send_active_reset(sk, GFP_ATOMIC, - SK_RST_REASON_NOT_SPECIFIED); + SK_RST_REASON_TCP_STATE); tcp_done_with_error(sk, err); } diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c index 52b1f2665dfa..81b96331b2bb 100644 --- a/net/ipv4/tcp_htcp.c +++ b/net/ipv4/tcp_htcp.c @@ -185,7 +185,7 @@ static inline void htcp_alpha_update(struct htcp *ca) u32 scale = (HZ << 3) / (10 * minRTT); /* clamping ratio to interval [0.5,10]<<3 */ - scale = min(max(scale, 1U << 2), 10U << 3); + scale = clamp(scale, 1U << 2, 10U << 3); factor = (factor << 3) / scale; if (!factor) factor = 1; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 16c48df8df4c..cdd0def14427 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3649,7 +3649,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority, /* skb of trace_tcp_send_reset() keeps the skb that caused RST, * skb here is different to the troublesome skb, so use NULL */ - trace_tcp_send_reset(sk, NULL, SK_RST_REASON_NOT_SPECIFIED); + trace_tcp_send_reset(sk, NULL, reason); } /* Send a crossed SYN-ACK during socket establishment. diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 4d40615dc8fc..86169127e4d1 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -125,7 +125,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) do_reset = true; if (do_reset) tcp_send_active_reset(sk, GFP_ATOMIC, - SK_RST_REASON_NOT_SPECIFIED); + SK_RST_REASON_TCP_ABORT_ON_MEMORY); tcp_done(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); return 1; @@ -779,7 +779,7 @@ static void tcp_keepalive_timer (struct timer_list *t) goto out; } } - tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_NOT_SPECIFIED); + tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_TCP_STATE); goto death; } @@ -807,7 +807,7 @@ static void tcp_keepalive_timer (struct timer_list *t) (user_timeout == 0 && icsk->icsk_probes_out >= keepalive_probes(tp))) { tcp_send_active_reset(sk, GFP_ATOMIC, - SK_RST_REASON_NOT_SPECIFIED); + SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT); tcp_write_err(sk); goto out; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 49c622e743e8..ddb86baaea6c 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -365,7 +365,7 @@ int udp_v4_get_port(struct sock *sk, unsigned short snum) return udp_lib_get_port(sk, snum, hash2_nulladdr); } -static int compute_score(struct sock *sk, struct net *net, +static int compute_score(struct sock *sk, const struct net *net, __be32 saddr, __be16 sport, __be32 daddr, unsigned short hnum, int dif, int sdif) @@ -420,7 +420,7 @@ u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, } /* called with rcu_read_lock() */ -static struct sock *udp4_lib_lookup2(struct net *net, +static struct sock *udp4_lib_lookup2(const struct net *net, __be32 saddr, __be16 sport, __be32 daddr, unsigned int hnum, int dif, int sdif, @@ -480,7 +480,7 @@ rescore: /* UDP is nearly always wildcards out the wazoo, it makes no sense to try * harder than this. -DaveM */ -struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, +struct sock *__udp4_lib_lookup(const struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif, int sdif, struct udp_table *udptable, struct sk_buff *skb) { @@ -561,7 +561,7 @@ struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb, * Does increment socket refcount. */ #if IS_ENABLED(CONFIG_NF_TPROXY_IPV4) || IS_ENABLED(CONFIG_NF_SOCKET_IPV4) -struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, +struct sock *udp4_lib_lookup(const struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif) { struct sock *sk; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index f70d8757af1a..c87d008aefa4 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -239,6 +239,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .ioam6_id_wide = IOAM6_DEFAULT_IF_ID_WIDE, .ndisc_evict_nocarrier = 1, .ra_honor_pio_life = 0, + .ra_honor_pio_pflag = 0, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -302,6 +303,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .ioam6_id_wide = IOAM6_DEFAULT_IF_ID_WIDE, .ndisc_evict_nocarrier = 1, .ra_honor_pio_life = 0, + .ra_honor_pio_pflag = 0, }; /* Check if link is ready: is it up and is a valid qdisc available */ @@ -2762,6 +2764,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) u32 addr_flags = 0; struct inet6_dev *in6_dev; struct net *net = dev_net(dev); + bool ignore_autoconf = false; pinfo = (struct prefix_info *) opt; @@ -2864,7 +2867,8 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) /* Try to figure out our local address for this prefix */ - if (pinfo->autoconf && in6_dev->cnf.autoconf) { + ignore_autoconf = READ_ONCE(in6_dev->cnf.ra_honor_pio_pflag) && pinfo->preferpd; + if (pinfo->autoconf && in6_dev->cnf.autoconf && !ignore_autoconf) { struct in6_addr addr; bool tokenized = false, dev_addr_generated = false; @@ -6926,6 +6930,15 @@ static const struct ctl_table addrconf_sysctl[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, + { + .procname = "ra_honor_pio_pflag", + .data = &ipv6_devconf.ra_honor_pio_pflag, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, #ifdef CONFIG_IPV6_ROUTER_PREF { .procname = "accept_ra_rtr_pref", diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 6db71bb1cd30..9ec05e354baa 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -46,7 +46,7 @@ EXPORT_SYMBOL_GPL(inet6_ehashfn); * * The sockhash lock must be held as a reader here. */ -struct sock *__inet6_lookup_established(struct net *net, +struct sock *__inet6_lookup_established(const struct net *net, struct inet_hashinfo *hashinfo, const struct in6_addr *saddr, const __be16 sport, @@ -89,7 +89,7 @@ found: } EXPORT_SYMBOL(__inet6_lookup_established); -static inline int compute_score(struct sock *sk, struct net *net, +static inline int compute_score(struct sock *sk, const struct net *net, const unsigned short hnum, const struct in6_addr *daddr, const int dif, const int sdif) @@ -126,7 +126,7 @@ static inline int compute_score(struct sock *sk, struct net *net, * Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to * the selected sock or an error. */ -struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, +struct sock *inet6_lookup_reuseport(const struct net *net, struct sock *sk, struct sk_buff *skb, int doff, const struct in6_addr *saddr, __be16 sport, @@ -147,7 +147,7 @@ struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, EXPORT_SYMBOL_GPL(inet6_lookup_reuseport); /* called with rcu_read_lock() */ -static struct sock *inet6_lhash2_lookup(struct net *net, +static struct sock *inet6_lhash2_lookup(const struct net *net, struct inet_listen_hashbucket *ilb2, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -174,7 +174,7 @@ static struct sock *inet6_lhash2_lookup(struct net *net, return result; } -struct sock *inet6_lookup_run_sk_lookup(struct net *net, +struct sock *inet6_lookup_run_sk_lookup(const struct net *net, int protocol, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -199,7 +199,7 @@ struct sock *inet6_lookup_run_sk_lookup(struct net *net, } EXPORT_SYMBOL_GPL(inet6_lookup_run_sk_lookup); -struct sock *inet6_lookup_listener(struct net *net, +struct sock *inet6_lookup_listener(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -243,7 +243,8 @@ done: } EXPORT_SYMBOL_GPL(inet6_lookup_listener); -struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, +struct sock *inet6_lookup(const struct net *net, + struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const __be16 dport, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 6602a2e9cdb5..52dfbb2ff1a8 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -114,7 +114,7 @@ void udp_v6_rehash(struct sock *sk) udp_lib_rehash(sk, new_hash); } -static int compute_score(struct sock *sk, struct net *net, +static int compute_score(struct sock *sk, const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, unsigned short hnum, int dif, int sdif) @@ -160,7 +160,7 @@ static int compute_score(struct sock *sk, struct net *net, } /* called with rcu_read_lock() */ -static struct sock *udp6_lib_lookup2(struct net *net, +static struct sock *udp6_lib_lookup2(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, unsigned int hnum, int dif, int sdif, struct udp_hslot *hslot2, @@ -217,7 +217,7 @@ rescore: } /* rcu_read_lock() must be held */ -struct sock *__udp6_lib_lookup(struct net *net, +struct sock *__udp6_lib_lookup(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif, int sdif, struct udp_table *udptable, @@ -300,7 +300,7 @@ struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb, * Does increment socket refcount. */ #if IS_ENABLED(CONFIG_NF_TPROXY_IPV6) || IS_ENABLED(CONFIG_NF_SOCKET_IPV6) -struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, +struct sock *udp6_lib_lookup(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif) { struct sock *sk; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 2e86f520f799..ce3b316e2327 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -142,9 +142,28 @@ static inline struct l2tp_net *l2tp_pernet(const struct net *net) static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel) { + struct sock *sk = tunnel->sock; + trace_free_tunnel(tunnel); - sock_put(tunnel->sock); - /* the tunnel is freed in the socket destructor */ + + if (sk) { + /* Disable udp encapsulation */ + switch (tunnel->encap) { + case L2TP_ENCAPTYPE_UDP: + /* No longer an encapsulation socket. See net/ipv4/udp.c */ + WRITE_ONCE(udp_sk(sk)->encap_type, 0); + udp_sk(sk)->encap_rcv = NULL; + udp_sk(sk)->encap_destroy = NULL; + break; + case L2TP_ENCAPTYPE_IP: + break; + } + + tunnel->sock = NULL; + sock_put(sk); + } + + kfree_rcu(tunnel, rcu); } static void l2tp_session_free(struct l2tp_session *session) @@ -152,18 +171,29 @@ static void l2tp_session_free(struct l2tp_session *session) trace_free_session(session); if (session->tunnel) l2tp_tunnel_dec_refcount(session->tunnel); - kfree(session); + kfree_rcu(session, rcu); } -struct l2tp_tunnel *l2tp_sk_to_tunnel(struct sock *sk) +struct l2tp_tunnel *l2tp_sk_to_tunnel(const struct sock *sk) { - struct l2tp_tunnel *tunnel = sk->sk_user_data; + const struct net *net = sock_net(sk); + unsigned long tunnel_id, tmp; + struct l2tp_tunnel *tunnel; + struct l2tp_net *pn; - if (tunnel) - if (WARN_ON(tunnel->magic != L2TP_TUNNEL_MAGIC)) - return NULL; + rcu_read_lock_bh(); + pn = l2tp_pernet(net); + idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { + if (tunnel && + tunnel->sock == sk && + refcount_inc_not_zero(&tunnel->ref_count)) { + rcu_read_unlock_bh(); + return tunnel; + } + } + rcu_read_unlock_bh(); - return tunnel; + return NULL; } EXPORT_SYMBOL_GPL(l2tp_sk_to_tunnel); @@ -254,7 +284,14 @@ struct l2tp_session *l2tp_v3_session_get(const struct net *net, struct sock *sk, hash_for_each_possible_rcu(pn->l2tp_v3_session_htable, session, hlist, key) { - if (session->tunnel->sock == sk && + /* session->tunnel may be NULL if another thread is in + * l2tp_session_register and has added an item to + * l2tp_v3_session_htable but hasn't yet added the + * session to its tunnel's session_list. + */ + struct l2tp_tunnel *tunnel = READ_ONCE(session->tunnel); + + if (tunnel && tunnel->sock == sk && refcount_inc_not_zero(&session->ref_count)) { rcu_read_unlock_bh(); return session; @@ -387,12 +424,12 @@ static int l2tp_session_collision_add(struct l2tp_net *pn, /* If existing session isn't already in the session hlist, add it. */ if (!hash_hashed(&session2->hlist)) - hash_add(pn->l2tp_v3_session_htable, &session2->hlist, - session2->hlist_key); + hash_add_rcu(pn->l2tp_v3_session_htable, &session2->hlist, + session2->hlist_key); /* Add new session to the hlist and collision list */ - hash_add(pn->l2tp_v3_session_htable, &session1->hlist, - session1->hlist_key); + hash_add_rcu(pn->l2tp_v3_session_htable, &session1->hlist, + session1->hlist_key); refcount_inc(&clist->ref_count); l2tp_session_coll_list_add(clist, session1); @@ -408,7 +445,7 @@ static void l2tp_session_collision_del(struct l2tp_net *pn, lockdep_assert_held(&pn->l2tp_session_idr_lock); - hash_del(&session->hlist); + hash_del_rcu(&session->hlist); if (clist) { /* Remove session from its collision list. If there @@ -442,6 +479,7 @@ int l2tp_session_register(struct l2tp_session *session, { struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); struct l2tp_session *other_session = NULL; + void *old = NULL; u32 session_key; int err; @@ -482,15 +520,22 @@ int l2tp_session_register(struct l2tp_session *session, } l2tp_tunnel_inc_refcount(tunnel); - list_add(&session->list, &tunnel->session_list); + WRITE_ONCE(session->tunnel, tunnel); + list_add_rcu(&session->list, &tunnel->session_list); + /* this makes session available to lockless getters */ if (tunnel->version == L2TP_HDR_VER_3) { if (!other_session) - idr_replace(&pn->l2tp_v3_session_idr, session, session_key); + old = idr_replace(&pn->l2tp_v3_session_idr, session, session_key); } else { - idr_replace(&pn->l2tp_v2_session_idr, session, session_key); + old = idr_replace(&pn->l2tp_v2_session_idr, session, session_key); } + /* old should be NULL, unless something removed or modified + * the IDR entry after our idr_alloc_32 above (which shouldn't + * happen). + */ + WARN_ON_ONCE(old); out: spin_unlock_bh(&pn->l2tp_session_idr_lock); spin_unlock_bh(&tunnel->list_lock); @@ -797,7 +842,8 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, if (!session->lns_mode && !session->send_seq) { trace_session_seqnum_lns_enable(session); session->send_seq = 1; - l2tp_session_set_header_len(session, tunnel->version); + l2tp_session_set_header_len(session, tunnel->version, + tunnel->encap); } } else { /* No sequence numbers. @@ -818,7 +864,8 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, if (!session->lns_mode && session->send_seq) { trace_session_seqnum_lns_disable(session); session->send_seq = 0; - l2tp_session_set_header_len(session, tunnel->version); + l2tp_session_set_header_len(session, tunnel->version, + tunnel->encap); } else if (session->send_seq) { pr_debug_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", session->name); @@ -1218,44 +1265,6 @@ EXPORT_SYMBOL_GPL(l2tp_xmit_skb); * Tinnel and session create/destroy. *****************************************************************************/ -/* Tunnel socket destruct hook. - * The tunnel context is deleted only when all session sockets have been - * closed. - */ -static void l2tp_tunnel_destruct(struct sock *sk) -{ - struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); - - if (!tunnel) - goto end; - - /* Disable udp encapsulation */ - switch (tunnel->encap) { - case L2TP_ENCAPTYPE_UDP: - /* No longer an encapsulation socket. See net/ipv4/udp.c */ - WRITE_ONCE(udp_sk(sk)->encap_type, 0); - udp_sk(sk)->encap_rcv = NULL; - udp_sk(sk)->encap_destroy = NULL; - break; - case L2TP_ENCAPTYPE_IP: - break; - } - - /* Remove hooks into tunnel socket */ - write_lock_bh(&sk->sk_callback_lock); - sk->sk_destruct = tunnel->old_sk_destruct; - sk->sk_user_data = NULL; - write_unlock_bh(&sk->sk_callback_lock); - - /* Call the original destructor */ - if (sk->sk_destruct) - (*sk->sk_destruct)(sk); - - kfree_rcu(tunnel, rcu); -end: - return; -} - /* Remove an l2tp session from l2tp_core's lists. */ static void l2tp_session_unhash(struct l2tp_session *session) { @@ -1288,8 +1297,6 @@ static void l2tp_session_unhash(struct l2tp_session *session) spin_unlock_bh(&pn->l2tp_session_idr_lock); spin_unlock_bh(&tunnel->list_lock); - - synchronize_rcu(); } } @@ -1301,28 +1308,21 @@ static void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel) spin_lock_bh(&tunnel->list_lock); tunnel->acpt_newsess = false; - for (;;) { - session = list_first_entry_or_null(&tunnel->session_list, - struct l2tp_session, list); - if (!session) - break; - l2tp_session_inc_refcount(session); - list_del_init(&session->list); - spin_unlock_bh(&tunnel->list_lock); + list_for_each_entry(session, &tunnel->session_list, list) l2tp_session_delete(session); - spin_lock_bh(&tunnel->list_lock); - l2tp_session_dec_refcount(session); - } spin_unlock_bh(&tunnel->list_lock); } /* Tunnel socket destroy hook for UDP encapsulation */ static void l2tp_udp_encap_destroy(struct sock *sk) { - struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); + struct l2tp_tunnel *tunnel; - if (tunnel) + tunnel = l2tp_sk_to_tunnel(sk); + if (tunnel) { l2tp_tunnel_delete(tunnel); + l2tp_tunnel_dec_refcount(tunnel); + } } static void l2tp_tunnel_remove(struct net *net, struct l2tp_tunnel *tunnel) @@ -1505,7 +1505,6 @@ int l2tp_tunnel_create(int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, tunnel->tunnel_id = tunnel_id; tunnel->peer_tunnel_id = peer_tunnel_id; - tunnel->magic = L2TP_TUNNEL_MAGIC; sprintf(&tunnel->name[0], "tunl %u", tunnel_id); spin_lock_init(&tunnel->list_lock); tunnel->acpt_newsess = true; @@ -1531,6 +1530,8 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_create); static int l2tp_validate_socket(const struct sock *sk, const struct net *net, enum l2tp_encap_type encap) { + struct l2tp_tunnel *tunnel; + if (!net_eq(sock_net(sk), net)) return -EINVAL; @@ -1544,8 +1545,11 @@ static int l2tp_validate_socket(const struct sock *sk, const struct net *net, (encap == L2TP_ENCAPTYPE_IP && sk->sk_protocol != IPPROTO_L2TP)) return -EPROTONOSUPPORT; - if (sk->sk_user_data) + tunnel = l2tp_sk_to_tunnel(sk); + if (tunnel) { + l2tp_tunnel_dec_refcount(tunnel); return -EBUSY; + } return 0; } @@ -1584,12 +1588,10 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, ret = l2tp_validate_socket(sk, net, tunnel->encap); if (ret < 0) goto err_inval_sock; - rcu_assign_sk_user_data(sk, tunnel); write_unlock_bh(&sk->sk_callback_lock); if (tunnel->encap == L2TP_ENCAPTYPE_UDP) { struct udp_tunnel_sock_cfg udp_cfg = { - .sk_user_data = tunnel, .encap_type = UDP_ENCAP_L2TPINUDP, .encap_rcv = l2tp_udp_encap_recv, .encap_err_rcv = l2tp_udp_encap_err_recv, @@ -1599,8 +1601,6 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, setup_udp_tunnel_sock(net, sock, &udp_cfg); } - tunnel->old_sk_destruct = sk->sk_destruct; - sk->sk_destruct = &l2tp_tunnel_destruct; sk->sk_allocation = GFP_ATOMIC; release_sock(sk); @@ -1647,23 +1647,37 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_delete); void l2tp_session_delete(struct l2tp_session *session) { - if (test_and_set_bit(0, &session->dead)) - return; + if (!test_and_set_bit(0, &session->dead)) { + trace_delete_session(session); + l2tp_session_inc_refcount(session); + queue_work(l2tp_wq, &session->del_work); + } +} +EXPORT_SYMBOL_GPL(l2tp_session_delete); + +/* Workqueue session deletion function */ +static void l2tp_session_del_work(struct work_struct *work) +{ + struct l2tp_session *session = container_of(work, struct l2tp_session, + del_work); - trace_delete_session(session); l2tp_session_unhash(session); l2tp_session_queue_purge(session); if (session->session_close) (*session->session_close)(session); + /* drop initial ref */ + l2tp_session_dec_refcount(session); + + /* drop workqueue ref */ l2tp_session_dec_refcount(session); } -EXPORT_SYMBOL_GPL(l2tp_session_delete); /* We come here whenever a session's send_seq, cookie_len or * l2specific_type parameters are set. */ -void l2tp_session_set_header_len(struct l2tp_session *session, int version) +void l2tp_session_set_header_len(struct l2tp_session *session, int version, + enum l2tp_encap_type encap) { if (version == L2TP_HDR_VER_2) { session->hdr_len = 6; @@ -1672,7 +1686,7 @@ void l2tp_session_set_header_len(struct l2tp_session *session, int version) } else { session->hdr_len = 4 + session->cookie_len; session->hdr_len += l2tp_get_l2specific_len(session); - if (session->tunnel->encap == L2TP_ENCAPTYPE_UDP) + if (encap == L2TP_ENCAPTYPE_UDP) session->hdr_len += 4; } } @@ -1686,7 +1700,6 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn session = kzalloc(sizeof(*session) + priv_size, GFP_KERNEL); if (session) { session->magic = L2TP_SESSION_MAGIC; - session->tunnel = tunnel; session->session_id = session_id; session->peer_session_id = peer_session_id; @@ -1710,6 +1723,7 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn INIT_HLIST_NODE(&session->hlist); INIT_LIST_HEAD(&session->clist); INIT_LIST_HEAD(&session->list); + INIT_WORK(&session->del_work, l2tp_session_del_work); if (cfg) { session->pwtype = cfg->pw_type; @@ -1724,7 +1738,7 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn memcpy(&session->peer_cookie[0], &cfg->peer_cookie[0], cfg->peer_cookie_len); } - l2tp_session_set_header_len(session, tunnel->version); + l2tp_session_set_header_len(session, tunnel->version, tunnel->encap); refcount_set(&session->ref_count, 1); @@ -1753,7 +1767,7 @@ static __net_init int l2tp_init_net(struct net *net) return 0; } -static __net_exit void l2tp_exit_net(struct net *net) +static __net_exit void l2tp_pre_exit_net(struct net *net) { struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_tunnel *tunnel = NULL; @@ -1767,8 +1781,12 @@ static __net_exit void l2tp_exit_net(struct net *net) rcu_read_unlock_bh(); if (l2tp_wq) - flush_workqueue(l2tp_wq); - rcu_barrier(); + drain_workqueue(l2tp_wq); +} + +static __net_exit void l2tp_exit_net(struct net *net) +{ + struct l2tp_net *pn = l2tp_pernet(net); idr_destroy(&pn->l2tp_v2_session_idr); idr_destroy(&pn->l2tp_v3_session_idr); @@ -1778,6 +1796,7 @@ static __net_exit void l2tp_exit_net(struct net *net) static struct pernet_operations l2tp_net_ops = { .init = l2tp_init_net, .exit = l2tp_exit_net, + .pre_exit = l2tp_pre_exit_net, .id = &l2tp_net_id, .size = sizeof(struct l2tp_net), }; diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 8ac81bc1bc6f..c907687705b9 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -16,7 +16,6 @@ #endif /* Random numbers used for internal consistency checks of tunnel and session structures */ -#define L2TP_TUNNEL_MAGIC 0x42114DDA #define L2TP_SESSION_MAGIC 0x0C04EB7D struct sk_buff; @@ -67,6 +66,7 @@ struct l2tp_session_coll_list { struct l2tp_session { int magic; /* should be L2TP_SESSION_MAGIC */ long dead; + struct rcu_head rcu; struct l2tp_tunnel *tunnel; /* back pointer to tunnel context */ u32 session_id; @@ -103,6 +103,7 @@ struct l2tp_session { int reorder_skip; /* set if skip to next nr */ enum l2tp_pwtype pwtype; struct l2tp_stats stats; + struct work_struct del_work; /* Session receive handler for data packets. * Each pseudowire implementation should implement this callback in order to @@ -155,8 +156,6 @@ struct l2tp_tunnel_cfg { */ #define L2TP_TUNNEL_NAME_MAX 20 struct l2tp_tunnel { - int magic; /* Should be L2TP_TUNNEL_MAGIC */ - unsigned long dead; struct rcu_head rcu; @@ -176,7 +175,6 @@ struct l2tp_tunnel { struct net *l2tp_net; /* the net we belong to */ refcount_t ref_count; - void (*old_sk_destruct)(struct sock *sk); struct sock *sock; /* parent socket */ int fd; /* parent fd, if tunnel socket was created * by userspace @@ -260,7 +258,8 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb); /* Transmit path helpers for sending packets over the tunnel socket. */ -void l2tp_session_set_header_len(struct l2tp_session *session, int version); +void l2tp_session_set_header_len(struct l2tp_session *session, int version, + enum l2tp_encap_type encap); int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb); /* Pseudowire management. @@ -273,10 +272,7 @@ void l2tp_nl_unregister_ops(enum l2tp_pwtype pw_type); /* IOCTL helper for IP encap modules. */ int l2tp_ioctl(struct sock *sk, int cmd, int *karg); -/* Extract the tunnel structure from a socket's sk_user_data pointer, - * validating the tunnel magic feather. - */ -struct l2tp_tunnel *l2tp_sk_to_tunnel(struct sock *sk); +struct l2tp_tunnel *l2tp_sk_to_tunnel(const struct sock *sk); static inline int l2tp_get_l2specific_len(struct l2tp_session *session) { diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 8ba00ad433c2..cc8a3ce716e9 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -322,7 +322,7 @@ err_sess_dev: l2tp_session_dec_refcount(session); free_netdev(dev); err_sess: - kfree(session); + l2tp_session_dec_refcount(session); err: return rc; } diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index e48aa177d74c..f21dcbf3efd5 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -235,14 +235,17 @@ static void l2tp_ip_close(struct sock *sk, long timeout) static void l2tp_ip_destroy_sock(struct sock *sk) { - struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); - struct sk_buff *skb; + struct l2tp_tunnel *tunnel; - while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) - kfree_skb(skb); + lock_sock(sk); + ip_flush_pending_frames(sk); + release_sock(sk); - if (tunnel) + tunnel = l2tp_sk_to_tunnel(sk); + if (tunnel) { l2tp_tunnel_delete(tunnel); + l2tp_tunnel_dec_refcount(tunnel); + } } static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index d217ff1f229e..3b0465f2d60d 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -246,14 +246,17 @@ static void l2tp_ip6_close(struct sock *sk, long timeout) static void l2tp_ip6_destroy_sock(struct sock *sk) { - struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); + struct l2tp_tunnel *tunnel; lock_sock(sk); ip6_flush_pending_frames(sk); release_sock(sk); - if (tunnel) + tunnel = l2tp_sk_to_tunnel(sk); + if (tunnel) { l2tp_tunnel_delete(tunnel); + l2tp_tunnel_dec_refcount(tunnel); + } } static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index d105030520f9..fc43ecbd128c 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -692,8 +692,10 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf session->recv_seq = nla_get_u8(info->attrs[L2TP_ATTR_RECV_SEQ]); if (info->attrs[L2TP_ATTR_SEND_SEQ]) { + struct l2tp_tunnel *tunnel = session->tunnel; + session->send_seq = nla_get_u8(info->attrs[L2TP_ATTR_SEND_SEQ]); - l2tp_session_set_header_len(session, session->tunnel->version); + l2tp_session_set_header_len(session, tunnel->version, tunnel->encap); } if (info->attrs[L2TP_ATTR_LNS_MODE]) diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 3596290047b2..9b4273fd518a 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -119,7 +119,6 @@ struct pppol2tp_session { struct mutex sk_lock; /* Protects .sk */ struct sock __rcu *sk; /* Pointer to the session PPPoX socket */ struct sock *__sk; /* Copy of .sk, for cleanup */ - struct rcu_head rcu; /* For asynchronous release */ }; static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb); @@ -157,20 +156,16 @@ static inline struct l2tp_session *pppol2tp_sock_to_session(struct sock *sk) if (!sk) return NULL; - sock_hold(sk); - session = (struct l2tp_session *)(sk->sk_user_data); - if (!session) { - sock_put(sk); - goto out; - } - if (WARN_ON(session->magic != L2TP_SESSION_MAGIC)) { - session = NULL; - sock_put(sk); - goto out; + rcu_read_lock(); + session = rcu_dereference_sk_user_data(sk); + if (session && refcount_inc_not_zero(&session->ref_count)) { + rcu_read_unlock(); + WARN_ON_ONCE(session->magic != L2TP_SESSION_MAGIC); + return session; } + rcu_read_unlock(); -out: - return session; + return NULL; } /***************************************************************************** @@ -318,12 +313,12 @@ static int pppol2tp_sendmsg(struct socket *sock, struct msghdr *m, l2tp_xmit_skb(session, skb); local_bh_enable(); - sock_put(sk); + l2tp_session_dec_refcount(session); return total_len; error_put_sess: - sock_put(sk); + l2tp_session_dec_refcount(session); error: return error; } @@ -377,12 +372,12 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) l2tp_xmit_skb(session, skb); local_bh_enable(); - sock_put(sk); + l2tp_session_dec_refcount(session); return 1; abort_put_sess: - sock_put(sk); + l2tp_session_dec_refcount(session); abort: /* Free the original skb */ kfree_skb(skb); @@ -393,28 +388,31 @@ abort: * Session (and tunnel control) socket create/destroy. *****************************************************************************/ -static void pppol2tp_put_sk(struct rcu_head *head) -{ - struct pppol2tp_session *ps; - - ps = container_of(head, typeof(*ps), rcu); - sock_put(ps->__sk); -} - /* Really kill the session socket. (Called from sock_put() if * refcnt == 0.) */ static void pppol2tp_session_destruct(struct sock *sk) { - struct l2tp_session *session = sk->sk_user_data; - skb_queue_purge(&sk->sk_receive_queue); skb_queue_purge(&sk->sk_write_queue); +} - if (session) { - sk->sk_user_data = NULL; - if (WARN_ON(session->magic != L2TP_SESSION_MAGIC)) - return; +static void pppol2tp_session_close(struct l2tp_session *session) +{ + struct pppol2tp_session *ps; + + ps = l2tp_session_priv(session); + mutex_lock(&ps->sk_lock); + ps->__sk = rcu_dereference_protected(ps->sk, + lockdep_is_held(&ps->sk_lock)); + RCU_INIT_POINTER(ps->sk, NULL); + mutex_unlock(&ps->sk_lock); + if (ps->__sk) { + /* detach socket */ + rcu_assign_sk_user_data(ps->__sk, NULL); + sock_put(ps->__sk); + + /* drop ref taken when we referenced socket via sk_user_data */ l2tp_session_dec_refcount(session); } } @@ -444,30 +442,13 @@ static int pppol2tp_release(struct socket *sock) session = pppol2tp_sock_to_session(sk); if (session) { - struct pppol2tp_session *ps; - l2tp_session_delete(session); - - ps = l2tp_session_priv(session); - mutex_lock(&ps->sk_lock); - ps->__sk = rcu_dereference_protected(ps->sk, - lockdep_is_held(&ps->sk_lock)); - RCU_INIT_POINTER(ps->sk, NULL); - mutex_unlock(&ps->sk_lock); - call_rcu(&ps->rcu, pppol2tp_put_sk); - - /* Rely on the sock_put() call at the end of the function for - * dropping the reference held by pppol2tp_sock_to_session(). - * The last reference will be dropped by pppol2tp_put_sk(). - */ + /* drop ref taken by pppol2tp_sock_to_session */ + l2tp_session_dec_refcount(session); } release_sock(sk); - /* This will delete the session context via - * pppol2tp_session_destruct() if the socket's refcnt drops to - * zero. - */ sock_put(sk); return 0; @@ -506,6 +487,7 @@ static int pppol2tp_create(struct net *net, struct socket *sock, int kern) goto out; sock_init_data(sock, sk); + sock_set_flag(sk, SOCK_RCU_FREE); sock->state = SS_UNCONNECTED; sock->ops = &pppol2tp_ops; @@ -542,6 +524,7 @@ static void pppol2tp_session_init(struct l2tp_session *session) struct pppol2tp_session *ps; session->recv_skb = pppol2tp_recv; + session->session_close = pppol2tp_session_close; if (IS_ENABLED(CONFIG_L2TP_DEBUGFS)) session->show = pppol2tp_show; @@ -787,6 +770,8 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, goto end; } + drop_refcnt = true; + pppol2tp_session_init(session); ps = l2tp_session_priv(session); l2tp_session_inc_refcount(session); @@ -795,10 +780,10 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, error = l2tp_session_register(session, tunnel); if (error < 0) { mutex_unlock(&ps->sk_lock); - kfree(session); + l2tp_session_dec_refcount(session); goto end; } - drop_refcnt = true; + new_session = true; } @@ -830,12 +815,13 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, out_no_ppp: /* This is how we get the session context from the socket. */ - sk->sk_user_data = session; + sock_hold(sk); + rcu_assign_sk_user_data(sk, session); rcu_assign_pointer(ps->sk, sk); mutex_unlock(&ps->sk_lock); /* Keep the reference we've grabbed on the session: sk doesn't expect - * the session to disappear. pppol2tp_session_destruct() is responsible + * the session to disappear. pppol2tp_session_close() is responsible * for dropping it. */ drop_refcnt = false; @@ -891,7 +877,7 @@ static int pppol2tp_session_create(struct net *net, struct l2tp_tunnel *tunnel, return 0; err_sess: - kfree(session); + l2tp_session_dec_refcount(session); err: return error; } @@ -1002,7 +988,7 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr, error = len; - sock_put(sk); + l2tp_session_dec_refcount(session); end: return error; } @@ -1205,7 +1191,8 @@ static int pppol2tp_session_setsockopt(struct sock *sk, po->chan.hdrlen = val ? PPPOL2TP_L2TP_HDR_SIZE_SEQ : PPPOL2TP_L2TP_HDR_SIZE_NOSEQ; } - l2tp_session_set_header_len(session, session->tunnel->version); + l2tp_session_set_header_len(session, session->tunnel->version, + session->tunnel->encap); break; case PPPOL2TP_SO_LNSMODE: @@ -1274,7 +1261,7 @@ static int pppol2tp_setsockopt(struct socket *sock, int level, int optname, err = pppol2tp_session_setsockopt(sk, session, optname, val); } - sock_put(sk); + l2tp_session_dec_refcount(session); end: return err; } @@ -1395,7 +1382,7 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, int optname, err = 0; end_put_sess: - sock_put(sk); + l2tp_session_dec_refcount(session); end: return err; } @@ -1406,8 +1393,6 @@ end: * L2TPv2, we dump only L2TPv2 tunnels and sessions here. *****************************************************************************/ -static unsigned int pppol2tp_net_id; - #ifdef CONFIG_PROC_FS struct pppol2tp_seq_data { @@ -1513,7 +1498,7 @@ static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v) seq_printf(m, "\nTUNNEL '%s', %c %d\n", tunnel->name, - (tunnel == tunnel->sock->sk_user_data) ? 'Y' : 'N', + tunnel->sock ? 'Y' : 'N', refcount_read(&tunnel->ref_count) - 1); seq_printf(m, " %08x %ld/%ld/%ld %ld/%ld/%ld\n", 0, @@ -1641,7 +1626,6 @@ static __net_exit void pppol2tp_exit_net(struct net *net) static struct pernet_operations pppol2tp_net_ops = { .init = pppol2tp_init_net, .exit = pppol2tp_exit_net, - .id = &pppol2tp_net_id, }; /***************************************************************************** diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index de52a9191da0..43288b408fde 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -486,6 +486,9 @@ static int mctp_ioctl_droptag(struct mctp_sock *msk, bool tagv2, tag = ctl.tag & MCTP_TAG_MASK; rc = -EINVAL; + if (ctl.peer_addr == MCTP_ADDR_NULL) + ctl.peer_addr = MCTP_ADDR_ANY; + spin_lock_irqsave(&net->mctp.keys_lock, flags); hlist_for_each_entry_safe(key, tmp, &msk->keys, sklist) { /* we do an irqsave here, even though we know the irq state, diff --git a/net/rds/ib.h b/net/rds/ib.h index 2ba71102b1f1..8ef3178ed4d6 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -369,9 +369,6 @@ int rds_ib_conn_alloc(struct rds_connection *conn, gfp_t gfp); void rds_ib_conn_free(void *arg); int rds_ib_conn_path_connect(struct rds_conn_path *cp); void rds_ib_conn_path_shutdown(struct rds_conn_path *cp); -void rds_ib_state_change(struct sock *sk); -int rds_ib_listen_init(void); -void rds_ib_listen_stop(void); __printf(2, 3) void __rds_ib_conn_error(struct rds_connection *conn, const char *, ...); int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, @@ -402,7 +399,6 @@ void rds_ib_inc_free(struct rds_incoming *inc); int rds_ib_inc_copy_to_user(struct rds_incoming *inc, struct iov_iter *to); void rds_ib_recv_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc, struct rds_ib_ack_state *state); -void rds_ib_recv_tasklet_fn(unsigned long data); void rds_ib_recv_init_ring(struct rds_ib_connection *ic); void rds_ib_recv_clear_ring(struct rds_ib_connection *ic); void rds_ib_recv_init_ack(struct rds_ib_connection *ic); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 08de24658f4f..80d682f89b23 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -856,7 +856,6 @@ bool rxrpc_new_incoming_call(struct rxrpc_local *local, struct rxrpc_connection *conn, struct sockaddr_rxrpc *peer_srx, struct sk_buff *skb); -void rxrpc_accept_incoming_calls(struct rxrpc_local *); int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long); /* @@ -969,7 +968,6 @@ void rxrpc_connect_client_calls(struct rxrpc_local *local); void rxrpc_expose_client_call(struct rxrpc_call *); void rxrpc_disconnect_client_call(struct rxrpc_bundle *, struct rxrpc_call *); void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle); -void rxrpc_put_client_conn(struct rxrpc_connection *, enum rxrpc_conn_trace); void rxrpc_discard_expired_client_conns(struct rxrpc_local *local); void rxrpc_clean_up_local_conns(struct rxrpc_local *); diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 8e3093938cd2..0316217b7687 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1466,10 +1466,6 @@ connect_abort: static int smc_connect_check_aclc(struct smc_init_info *ini, struct smc_clc_msg_accept_confirm *aclc) { - if (aclc->hdr.typev1 != SMC_TYPE_R && - aclc->hdr.typev1 != SMC_TYPE_D) - return SMC_CLC_DECL_MODEUNSUPP; - if (aclc->hdr.version >= SMC_V2) { if ((aclc->hdr.typev1 == SMC_TYPE_R && !smcr_indicated(ini->smc_type_v2)) || @@ -1523,10 +1519,6 @@ static int __smc_connect(struct smc_sock *smc) ini->smcd_version &= ~SMC_V1; ini->smcr_version = 0; ini->smc_type_v1 = SMC_TYPE_N; - if (!ini->smcd_version) { - rc = SMC_CLC_DECL_GETVLANERR; - goto fallback; - } } rc = smc_find_proposal_devices(smc, ini); diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 3b95828d9976..71fb334d8234 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -2250,7 +2250,7 @@ int smcr_buf_reg_lgr(struct smc_link *lnk) } static struct smc_buf_desc *smcr_new_buf_create(struct smc_link_group *lgr, - bool is_rmb, int bufsize) + int bufsize) { struct smc_buf_desc *buf_desc; @@ -2398,7 +2398,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) if (is_smcd) buf_desc = smcd_new_buf_create(lgr, is_rmb, bufsize); else - buf_desc = smcr_new_buf_create(lgr, is_rmb, bufsize); + buf_desc = smcr_new_buf_create(lgr, bufsize); if (PTR_ERR(buf_desc) == -ENOMEM) break; diff --git a/net/smc/smc_loopback.h b/net/smc/smc_loopback.h index 6dd4292dae56..04dc6808d2e1 100644 --- a/net/smc/smc_loopback.h +++ b/net/smc/smc_loopback.h @@ -15,7 +15,6 @@ #define _SMC_LOOPBACK_H #include <linux/device.h> -#include <linux/err.h> #include <net/smc.h> #if IS_ENABLED(CONFIG_SMC_LO) diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 5a526ebafeb4..3c9e25f6a1d2 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -163,8 +163,12 @@ static int bearer_name_validate(const char *name, /* return bearer name components, if necessary */ if (name_parts) { - strcpy(name_parts->media_name, media_name); - strcpy(name_parts->if_name, if_name); + if (strscpy(name_parts->media_name, media_name, + TIPC_MAX_MEDIA_NAME) < 0) + return 0; + if (strscpy(name_parts->if_name, if_name, + TIPC_MAX_IF_NAME) < 0) + return 0; } return 1; } diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 4b040285aa78..58e639e82942 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -112,6 +112,7 @@ #include <net/sock.h> #include <net/af_vsock.h> #include <uapi/linux/vm_sockets.h> +#include <uapi/asm-generic/ioctls.h> static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr); static void vsock_sk_destruct(struct sock *sk); @@ -1292,6 +1293,57 @@ int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, } EXPORT_SYMBOL_GPL(vsock_dgram_recvmsg); +static int vsock_do_ioctl(struct socket *sock, unsigned int cmd, + int __user *arg) +{ + struct sock *sk = sock->sk; + struct vsock_sock *vsk; + int ret; + + vsk = vsock_sk(sk); + + switch (cmd) { + case SIOCOUTQ: { + ssize_t n_bytes; + + if (!vsk->transport || !vsk->transport->unsent_bytes) { + ret = -EOPNOTSUPP; + break; + } + + if (sock_type_connectible(sk->sk_type) && sk->sk_state == TCP_LISTEN) { + ret = -EINVAL; + break; + } + + n_bytes = vsk->transport->unsent_bytes(vsk); + if (n_bytes < 0) { + ret = n_bytes; + break; + } + + ret = put_user(n_bytes, arg); + break; + } + default: + ret = -ENOIOCTLCMD; + } + + return ret; +} + +static int vsock_ioctl(struct socket *sock, unsigned int cmd, + unsigned long arg) +{ + int ret; + + lock_sock(sock->sk); + ret = vsock_do_ioctl(sock, cmd, (int __user *)arg); + release_sock(sock->sk); + + return ret; +} + static const struct proto_ops vsock_dgram_ops = { .family = PF_VSOCK, .owner = THIS_MODULE, @@ -1302,7 +1354,7 @@ static const struct proto_ops vsock_dgram_ops = { .accept = sock_no_accept, .getname = vsock_getname, .poll = vsock_poll, - .ioctl = sock_no_ioctl, + .ioctl = vsock_ioctl, .listen = sock_no_listen, .shutdown = vsock_shutdown, .sendmsg = vsock_dgram_sendmsg, @@ -2286,7 +2338,7 @@ static const struct proto_ops vsock_stream_ops = { .accept = vsock_accept, .getname = vsock_getname, .poll = vsock_poll, - .ioctl = sock_no_ioctl, + .ioctl = vsock_ioctl, .listen = vsock_listen, .shutdown = vsock_shutdown, .setsockopt = vsock_connectible_setsockopt, @@ -2308,7 +2360,7 @@ static const struct proto_ops vsock_seqpacket_ops = { .accept = vsock_accept, .getname = vsock_getname, .poll = vsock_poll, - .ioctl = sock_no_ioctl, + .ioctl = vsock_ioctl, .listen = vsock_listen, .shutdown = vsock_shutdown, .setsockopt = vsock_connectible_setsockopt, diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 64a07acfef12..e0160da4ef43 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -311,7 +311,7 @@ static void virtio_transport_tx_work(struct work_struct *work) virtqueue_disable_cb(vq); while ((skb = virtqueue_get_buf(vq, &len)) != NULL) { - consume_skb(skb); + virtio_transport_consume_skb_sent(skb, true); added = true; } } while (!virtqueue_enable_cb(vq)); @@ -540,6 +540,8 @@ static struct virtio_transport virtio_transport = { .notify_buffer_size = virtio_transport_notify_buffer_size, .notify_set_rcvlowat = virtio_transport_notify_set_rcvlowat, + .unsent_bytes = virtio_transport_unsent_bytes, + .read_skb = virtio_transport_read_skb, }, diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 16ff976a86e3..884ee128851e 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -463,6 +463,26 @@ void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct sk_buff * } EXPORT_SYMBOL_GPL(virtio_transport_inc_tx_pkt); +void virtio_transport_consume_skb_sent(struct sk_buff *skb, bool consume) +{ + struct sock *s = skb->sk; + + if (s && skb->len) { + struct vsock_sock *vs = vsock_sk(s); + struct virtio_vsock_sock *vvs; + + vvs = vs->trans; + + spin_lock_bh(&vvs->tx_lock); + vvs->bytes_unsent -= skb->len; + spin_unlock_bh(&vvs->tx_lock); + } + + if (consume) + consume_skb(skb); +} +EXPORT_SYMBOL_GPL(virtio_transport_consume_skb_sent); + u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 credit) { u32 ret; @@ -475,6 +495,7 @@ u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 credit) if (ret > credit) ret = credit; vvs->tx_cnt += ret; + vvs->bytes_unsent += ret; spin_unlock_bh(&vvs->tx_lock); return ret; @@ -488,6 +509,7 @@ void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit) spin_lock_bh(&vvs->tx_lock); vvs->tx_cnt -= credit; + vvs->bytes_unsent -= credit; spin_unlock_bh(&vvs->tx_lock); } EXPORT_SYMBOL_GPL(virtio_transport_put_credit); @@ -1090,6 +1112,19 @@ void virtio_transport_destruct(struct vsock_sock *vsk) } EXPORT_SYMBOL_GPL(virtio_transport_destruct); +ssize_t virtio_transport_unsent_bytes(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + size_t ret; + + spin_lock_bh(&vvs->tx_lock); + ret = vvs->bytes_unsent; + spin_unlock_bh(&vvs->tx_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(virtio_transport_unsent_bytes); + static int virtio_transport_reset(struct vsock_sock *vsk, struct sk_buff *skb) { diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c index 6dea6119f5b2..6e78927a598e 100644 --- a/net/vmw_vsock/vsock_loopback.c +++ b/net/vmw_vsock/vsock_loopback.c @@ -98,6 +98,8 @@ static struct virtio_transport loopback_transport = { .notify_buffer_size = virtio_transport_notify_buffer_size, .notify_set_rcvlowat = virtio_transport_notify_set_rcvlowat, + .unsent_bytes = virtio_transport_unsent_bytes, + .read_skb = virtio_transport_read_skb, }, @@ -123,6 +125,10 @@ static void vsock_loopback_work(struct work_struct *work) spin_unlock_bh(&vsock->pkt_queue.lock); while ((skb = __skb_dequeue(&pkts))) { + /* Decrement the bytes_unsent counter without deallocating skb + * It is freed by the receiver. + */ + virtio_transport_consume_skb_sent(skb, false); virtio_transport_deliver_tap_pkt(skb); virtio_transport_recv_pkt(&loopback_transport, skb); } diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c index fcb18a5a6d70..e16cef160bc2 100644 --- a/tools/net/ynl/lib/ynl.c +++ b/tools/net/ynl/lib/ynl.c @@ -696,14 +696,14 @@ ynl_sock_create(const struct ynl_family *yf, struct ynl_error *yse) addr.nl_family = AF_NETLINK; if (bind(ys->socket, (struct sockaddr *)&addr, sizeof(addr)) < 0) { __perr(yse, "unable to bind to a socket address"); - goto err_close_sock;; + goto err_close_sock; } memset(&addr, 0, sizeof(addr)); addrlen = sizeof(addr); if (getsockname(ys->socket, (struct sockaddr *)&addr, &addrlen) < 0) { __perr(yse, "unable to read socket address"); - goto err_close_sock;; + goto err_close_sock; } ys->portid = addr.nl_pid; ys->seq = random(); diff --git a/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py b/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py index 026d98976c35..05b6fbb3fcdd 100755 --- a/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py +++ b/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py @@ -1,6 +1,7 @@ #!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 +import errno import time import os from lib.py import ksft_run, ksft_exit, ksft_pr @@ -61,7 +62,7 @@ def test_pp_alloc(cfg, netdevnl): try: stats = get_stats() except NlError as e: - if e.nl_msg.error == -95: + if e.nl_msg.error == -errno.EOPNOTSUPP: stats = {} else: raise diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py index a5e800b8f103..1ea9bb695e94 100644 --- a/tools/testing/selftests/drivers/net/lib/py/env.py +++ b/tools/testing/selftests/drivers/net/lib/py/env.py @@ -4,6 +4,7 @@ import os import time from pathlib import Path from lib.py import KsftSkipEx, KsftXfailEx +from lib.py import ksft_setup from lib.py import cmd, ethtool, ip from lib.py import NetNS, NetdevSimDev from .remote import Remote @@ -14,7 +15,7 @@ def _load_env_file(src_path): src_dir = Path(src_path).parent.resolve() if not (src_dir / "net.config").exists(): - return env + return ksft_setup(env) with open((src_dir / "net.config").as_posix(), 'r') as fp: for line in fp.readlines(): @@ -30,7 +31,7 @@ def _load_env_file(src_path): if len(pair) != 2: raise Exception("Can't parse configuration line:", full_file) env[pair[0]] = pair[1] - return env + return ksft_setup(env) class NetDrvEnv: diff --git a/tools/testing/selftests/drivers/net/stats.py b/tools/testing/selftests/drivers/net/stats.py index 820b8e0a22c6..63e3c045a3b2 100755 --- a/tools/testing/selftests/drivers/net/stats.py +++ b/tools/testing/selftests/drivers/net/stats.py @@ -1,10 +1,13 @@ #!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 +import errno from lib.py import ksft_run, ksft_exit, ksft_pr from lib.py import ksft_ge, ksft_eq, ksft_in, ksft_true, ksft_raises, KsftSkipEx, KsftXfailEx +from lib.py import ksft_disruptive from lib.py import EthtoolFamily, NetdevFamily, RtnlFamily, NlError from lib.py import NetDrvEnv +from lib.py import ip, defer ethnl = EthtoolFamily() netfam = NetdevFamily() @@ -17,7 +20,7 @@ def check_pause(cfg) -> None: try: ethnl.pause_get({"header": {"dev-index": cfg.ifindex}}) except NlError as e: - if e.error == 95: + if e.error == errno.EOPNOTSUPP: raise KsftXfailEx("pause not supported by the device") raise @@ -32,7 +35,7 @@ def check_fec(cfg) -> None: try: ethnl.fec_get({"header": {"dev-index": cfg.ifindex}}) except NlError as e: - if e.error == 95: + if e.error == errno.EOPNOTSUPP: raise KsftXfailEx("FEC not supported by the device") raise @@ -117,7 +120,7 @@ def qstat_by_ifindex(cfg) -> None: # loopback has no stats with ksft_raises(NlError) as cm: netfam.qstats_get({"ifindex": 1}, dump=True) - ksft_eq(cm.exception.nl_msg.error, -95) + ksft_eq(cm.exception.nl_msg.error, -errno.EOPNOTSUPP) ksft_eq(cm.exception.nl_msg.extack['bad-attr'], '.ifindex') # Try to get stats for lowest unused ifindex but not 0 @@ -133,9 +136,31 @@ def qstat_by_ifindex(cfg) -> None: ksft_eq(cm.exception.nl_msg.extack['bad-attr'], '.ifindex') +@ksft_disruptive +def check_down(cfg) -> None: + try: + qstat = netfam.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0] + except NlError as e: + if e.error == errno.EOPNOTSUPP: + raise KsftSkipEx("qstats not supported by the device") + raise + + ip(f"link set dev {cfg.dev['ifname']} down") + defer(ip, f"link set dev {cfg.dev['ifname']} up") + + qstat2 = netfam.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0] + for k, v in qstat.items(): + ksft_ge(qstat2[k], qstat[k], comment=f"{k} went backwards on device down") + + # exercise per-queue API to make sure that "device down" state + # is handled correctly and doesn't crash + netfam.qstats_get({"ifindex": cfg.ifindex, "scope": "queue"}, dump=True) + + def main() -> None: with NetDrvEnv(__file__) as cfg: - ksft_run([check_pause, check_fec, pkt_byte_sum, qstat_by_ifindex], + ksft_run([check_pause, check_fec, pkt_byte_sum, qstat_by_ifindex, + check_down], args=(cfg, )) ksft_exit() diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py index f26c20df9db4..f663e0daec0d 100644 --- a/tools/testing/selftests/net/lib/py/ksft.py +++ b/tools/testing/selftests/net/lib/py/ksft.py @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 import builtins +import functools import inspect import sys import time @@ -10,6 +11,7 @@ from .utils import global_defer_queue KSFT_RESULT = None KSFT_RESULT_ALL = True +KSFT_DISRUPTIVE = True class KsftFailEx(Exception): @@ -32,8 +34,18 @@ def _fail(*args): global KSFT_RESULT KSFT_RESULT = False - frame = inspect.stack()[2] - ksft_pr("At " + frame.filename + " line " + str(frame.lineno) + ":") + stack = inspect.stack() + started = False + for frame in reversed(stack[2:]): + # Start printing from the test case function + if not started: + if frame.function == 'ksft_run': + started = True + continue + + ksft_pr("Check| At " + frame.filename + ", line " + str(frame.lineno) + + ", in " + frame.function + ":") + ksft_pr("Check| " + frame.code_context[0].strip()) ksft_pr(*args) @@ -127,6 +139,44 @@ def ksft_flush_defer(): KSFT_RESULT = False +def ksft_disruptive(func): + """ + Decorator that marks the test as disruptive (e.g. the test + that can down the interface). Disruptive tests can be skipped + by passing DISRUPTIVE=False environment variable. + """ + + @functools.wraps(func) + def wrapper(*args, **kwargs): + if not KSFT_DISRUPTIVE: + raise KsftSkipEx(f"marked as disruptive") + return func(*args, **kwargs) + return wrapper + + +def ksft_setup(env): + """ + Setup test framework global state from the environment. + """ + + def get_bool(env, name): + value = env.get(name, "").lower() + if value in ["yes", "true"]: + return True + if value in ["no", "false"]: + return False + try: + return bool(int(value)) + except: + raise Exception(f"failed to parse {name}") + + if "DISRUPTIVE" in env: + global KSFT_DISRUPTIVE + KSFT_DISRUPTIVE = get_bool(env, "DISRUPTIVE") + + return env + + def ksft_run(cases=None, globs=None, case_pfx=None, args=()): cases = cases or [] diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c index 554b290fefdc..a3d448a075e3 100644 --- a/tools/testing/vsock/util.c +++ b/tools/testing/vsock/util.c @@ -139,7 +139,7 @@ int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_po } /* Connect to <cid, port> and return the file descriptor. */ -static int vsock_connect(unsigned int cid, unsigned int port, int type) +int vsock_connect(unsigned int cid, unsigned int port, int type) { union { struct sockaddr sa; @@ -226,8 +226,8 @@ static int vsock_listen(unsigned int cid, unsigned int port, int type) /* Listen on <cid, port> and return the first incoming connection. The remote * address is stored to clientaddrp. clientaddrp may be NULL. */ -static int vsock_accept(unsigned int cid, unsigned int port, - struct sockaddr_vm *clientaddrp, int type) +int vsock_accept(unsigned int cid, unsigned int port, + struct sockaddr_vm *clientaddrp, int type) { union { struct sockaddr sa; diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h index e95e62485959..fff22d4a14c0 100644 --- a/tools/testing/vsock/util.h +++ b/tools/testing/vsock/util.h @@ -39,6 +39,9 @@ struct test_case { void init_signals(void); unsigned int parse_cid(const char *str); unsigned int parse_port(const char *str); +int vsock_connect(unsigned int cid, unsigned int port, int type); +int vsock_accept(unsigned int cid, unsigned int port, + struct sockaddr_vm *clientaddrp, int type); int vsock_stream_connect(unsigned int cid, unsigned int port); int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_port, int type); diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index f851f8961247..8d38dbf8f41f 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -20,6 +20,8 @@ #include <sys/mman.h> #include <poll.h> #include <signal.h> +#include <sys/ioctl.h> +#include <linux/sockios.h> #include "vsock_test_zerocopy.h" #include "timeout.h" @@ -1238,6 +1240,79 @@ static void test_double_bind_connect_client(const struct test_opts *opts) } } +#define MSG_BUF_IOCTL_LEN 64 +static void test_unsent_bytes_server(const struct test_opts *opts, int type) +{ + unsigned char buf[MSG_BUF_IOCTL_LEN]; + int client_fd; + + client_fd = vsock_accept(VMADDR_CID_ANY, opts->peer_port, NULL, type); + if (client_fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + recv_buf(client_fd, buf, sizeof(buf), 0, sizeof(buf)); + control_writeln("RECEIVED"); + + close(client_fd); +} + +static void test_unsent_bytes_client(const struct test_opts *opts, int type) +{ + unsigned char buf[MSG_BUF_IOCTL_LEN]; + int ret, fd, sock_bytes_unsent; + + fd = vsock_connect(opts->peer_cid, opts->peer_port, type); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + for (int i = 0; i < sizeof(buf); i++) + buf[i] = rand() & 0xFF; + + send_buf(fd, buf, sizeof(buf), 0, sizeof(buf)); + control_expectln("RECEIVED"); + + ret = ioctl(fd, SIOCOUTQ, &sock_bytes_unsent); + if (ret < 0) { + if (errno == EOPNOTSUPP) { + fprintf(stderr, "Test skipped, SIOCOUTQ not supported.\n"); + } else { + perror("ioctl"); + exit(EXIT_FAILURE); + } + } else if (ret == 0 && sock_bytes_unsent != 0) { + fprintf(stderr, + "Unexpected 'SIOCOUTQ' value, expected 0, got %i\n", + sock_bytes_unsent); + exit(EXIT_FAILURE); + } + + close(fd); +} + +static void test_stream_unsent_bytes_client(const struct test_opts *opts) +{ + test_unsent_bytes_client(opts, SOCK_STREAM); +} + +static void test_stream_unsent_bytes_server(const struct test_opts *opts) +{ + test_unsent_bytes_server(opts, SOCK_STREAM); +} + +static void test_seqpacket_unsent_bytes_client(const struct test_opts *opts) +{ + test_unsent_bytes_client(opts, SOCK_SEQPACKET); +} + +static void test_seqpacket_unsent_bytes_server(const struct test_opts *opts) +{ + test_unsent_bytes_server(opts, SOCK_SEQPACKET); +} + #define RCVLOWAT_CREDIT_UPD_BUF_SIZE (1024 * 128) /* This define is the same as in 'include/linux/virtio_vsock.h': * it is used to decide when to send credit update message during @@ -1523,6 +1598,16 @@ static struct test_case test_cases[] = { .run_client = test_stream_rcvlowat_def_cred_upd_client, .run_server = test_stream_cred_upd_on_low_rx_bytes, }, + { + .name = "SOCK_STREAM ioctl(SIOCOUTQ) 0 unsent bytes", + .run_client = test_stream_unsent_bytes_client, + .run_server = test_stream_unsent_bytes_server, + }, + { + .name = "SOCK_SEQPACKET ioctl(SIOCOUTQ) 0 unsent bytes", + .run_client = test_seqpacket_unsent_bytes_client, + .run_server = test_seqpacket_unsent_bytes_server, + }, {}, }; |