diff --git a/Documentation/devicetree/bindings/net/mediatek-net.txt b/Documentation/devicetree/bindings/net/mediatek-net.txt index f09525772369..c010fafc66a8 100644 --- a/Documentation/devicetree/bindings/net/mediatek-net.txt +++ b/Documentation/devicetree/bindings/net/mediatek-net.txt @@ -24,7 +24,6 @@ Required properties: Optional properties: - interrupt-parent: Should be the phandle for the interrupt controller that services interrupts for this device -- mediatek,hwlro: the capability if the hardware supports LRO functions * Ethernet MAC node @@ -54,7 +53,6 @@ eth: ethernet@1b100000 { reset-names = "eth"; mediatek,ethsys = <ðsys>; mediatek,pctl = <&syscfg_pctl_a>; - mediatek,hwlro; #address-cells = <1>; #size-cells = <0>; diff --git a/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt b/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt index f9c32adab5c6..c35b5b428a7f 100644 --- a/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt +++ b/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt @@ -34,16 +34,17 @@ KSZ9031: All skew control options are specified in picoseconds. The minimum value is 0, and the maximum is property-dependent. The increment - step is 60ps. + step is 60ps. The default value is the neutral setting, so setting + rxc-skew-ps=<0> actually results in -900 picoseconds adjustment. Optional properties: - Maximum value of 1860: + Maximum value of 1860, default value 900: - rxc-skew-ps : Skew control of RX clock pad - txc-skew-ps : Skew control of TX clock pad - Maximum value of 900: + Maximum value of 900, default value 420: - rxdv-skew-ps : Skew control of RX CTL pad - txen-skew-ps : Skew control of TX CTL pad diff --git a/Documentation/devicetree/bindings/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt index c8ac222eac67..b519503be51a 100644 --- a/Documentation/devicetree/bindings/net/renesas,ravb.txt +++ b/Documentation/devicetree/bindings/net/renesas,ravb.txt @@ -10,6 +10,7 @@ Required properties: "renesas,etheravb-r8a7793" if the device is a part of R8A7793 SoC. "renesas,etheravb-r8a7794" if the device is a part of R8A7794 SoC. "renesas,etheravb-r8a7795" if the device is a part of R8A7795 SoC. + "renesas,etheravb-r8a7796" if the device is a part of R8A7796 SoC. "renesas,etheravb-rcar-gen2" for generic R-Car Gen 2 compatible interface. "renesas,etheravb-rcar-gen3" for generic R-Car Gen 3 compatible interface. @@ -33,7 +34,7 @@ Optional properties: - interrupt-parent: the phandle for the interrupt controller that services interrupts for this device. - interrupt-names: A list of interrupt names. - For the R8A7795 SoC this property is mandatory; + For the R8A779[56] SoCs this property is mandatory; it should include one entry per channel, named "ch%u", where %u is the channel number ranging from 0 to 24. For other SoCs this property is optional; if present diff --git a/MAINTAINERS b/MAINTAINERS index 4347bce8ada6..8b58a86988aa 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5033,6 +5033,13 @@ F: drivers/net/ethernet/freescale/fec_ptp.c F: drivers/net/ethernet/freescale/fec.h F: Documentation/devicetree/bindings/net/fsl-fec.txt +FREESCALE QORIQ DPAA FMAN DRIVER +M: Madalin Bucur +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/ethernet/freescale/fman +F: Documentation/devicetree/bindings/powerpc/fsl/fman.txt + FREESCALE QUICC ENGINE LIBRARY L: linuxppc-dev@lists.ozlabs.org S: Orphan @@ -13128,6 +13135,7 @@ F: arch/arm64/include/asm/xen/ XEN NETWORK BACKEND DRIVER M: Wei Liu +M: Paul Durrant L: xen-devel@lists.xenproject.org (moderated for non-subscribers) L: netdev@vger.kernel.org S: Supported diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 6bd63b84abd0..2f633df9f4e6 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -314,6 +314,7 @@ static const struct usb_device_id blacklist_table[] = { /* Marvell Bluetooth devices */ { USB_DEVICE(0x1286, 0x2044), .driver_info = BTUSB_MARVELL }, { USB_DEVICE(0x1286, 0x2046), .driver_info = BTUSB_MARVELL }, + { USB_DEVICE(0x1286, 0x204e), .driver_info = BTUSB_MARVELL }, /* Intel Bluetooth devices */ { USB_DEVICE(0x8087, 0x07da), .driver_info = BTUSB_CSR }, @@ -1042,6 +1043,10 @@ static int btusb_open(struct hci_dev *hdev) BT_DBG("%s", hdev->name); + err = usb_autopm_get_interface(data->intf); + if (err < 0) + return err; + /* Patching USB firmware files prior to starting any URBs of HCI path * It is more safe to use USB bulk channel for downloading USB patch */ @@ -1051,10 +1056,6 @@ static int btusb_open(struct hci_dev *hdev) return err; } - err = usb_autopm_get_interface(data->intf); - if (err < 0) - return err; - data->intf->needs_remote_wakeup = 1; if (test_and_set_bit(BTUSB_INTR_RUNNING, &data->flags)) diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index 6ea0e5ff1e44..856379cbb402 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -1046,7 +1046,7 @@ static void bgmac_enable(struct bgmac *bgmac) mode = (bgmac_read(bgmac, BGMAC_DEV_STATUS) & BGMAC_DS_MM_MASK) >> BGMAC_DS_MM_SHIFT; - if (bgmac->feature_flags & BGMAC_FEAT_CLKCTLST || mode != 0) + if (!(bgmac->feature_flags & BGMAC_FEAT_CLKCTLST) || mode != 0) bgmac_set(bgmac, BCMA_CLKCTLST, BCMA_CLKCTLST_FORCEHT); if (bgmac->feature_flags & BGMAC_FEAT_CLKCTLST && mode == 2) bgmac_cco_ctl_maskset(bgmac, 1, ~0, diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index 63144bb413d1..b32444a3ed79 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -3117,6 +3117,7 @@ static int macb_remove(struct platform_device *pdev) if (dev->phydev) phy_disconnect(dev->phydev); mdiobus_unregister(bp->mii_bus); + dev->phydev = NULL; mdiobus_free(bp->mii_bus); /* Shutdown the PHY if there is a GPIO reset */ diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index 9cffe48be156..1fb5d7239254 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -2728,6 +2728,26 @@ static int be_flash(struct be_adapter *adapter, const u8 *img, return 0; } +#define NCSI_UPDATE_LOG "NCSI section update is not supported in FW ver %s\n" +static bool be_fw_ncsi_supported(char *ver) +{ + int v1[4] = {3, 102, 148, 0}; /* Min ver that supports NCSI FW */ + int v2[4]; + int i; + + if (sscanf(ver, "%d.%d.%d.%d", &v2[0], &v2[1], &v2[2], &v2[3]) != 4) + return false; + + for (i = 0; i < 4; i++) { + if (v1[i] < v2[i]) + return true; + else if (v1[i] > v2[i]) + return false; + } + + return true; +} + /* For BE2, BE3 and BE3-R */ static int be_flash_BEx(struct be_adapter *adapter, const struct firmware *fw, @@ -2805,8 +2825,10 @@ static int be_flash_BEx(struct be_adapter *adapter, continue; if ((pflashcomp[i].optype == OPTYPE_NCSI_FW) && - memcmp(adapter->fw_ver, "3.102.148.0", 11) < 0) + !be_fw_ncsi_supported(adapter->fw_ver)) { + dev_info(dev, NCSI_UPDATE_LOG, adapter->fw_ver); continue; + } if (pflashcomp[i].optype == OPTYPE_PHY_FW && !phy_flashing_required(adapter)) @@ -3527,6 +3549,11 @@ int be_cmd_get_cntl_attributes(struct be_adapter *adapter) for (i = 0; i < CNTL_SERIAL_NUM_WORDS; i++) adapter->serial_num[i] = le32_to_cpu(serial_num[i]) & (BIT_MASK(16) - 1); + /* For BEx, since GET_FUNC_CONFIG command is not + * supported, we read funcnum here as a workaround. + */ + if (BEx_chip(adapter)) + adapter->pf_num = attribs->hba_attribs.pci_funcnum; } err: @@ -4950,7 +4977,7 @@ int be_cmd_set_logical_link_config(struct be_adapter *adapter, { int status; - if (BEx_chip(adapter)) + if (BE2_chip(adapter)) return -EOPNOTSUPP; status = __be_cmd_set_logical_link_config(adapter, link_state, diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h index 1bd82bcb3be5..09da2d82c2f0 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.h +++ b/drivers/net/ethernet/emulex/benet/be_cmds.h @@ -1720,7 +1720,11 @@ struct mgmt_hba_attribs { u32 rsvd2[55]; u8 rsvd3[3]; u8 phy_port; - u32 rsvd4[13]; + u32 rsvd4[15]; + u8 rsvd5[2]; + u8 pci_funcnum; + u8 rsvd6; + u32 rsvd7[6]; } __packed; struct mgmt_controller_attrib { diff --git a/drivers/net/ethernet/emulex/benet/be_hw.h b/drivers/net/ethernet/emulex/benet/be_hw.h index 92942c84d329..36e4232ed6b8 100644 --- a/drivers/net/ethernet/emulex/benet/be_hw.h +++ b/drivers/net/ethernet/emulex/benet/be_hw.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2005 - 2015 Emulex + * Copyright (C) 2005-2016 Broadcom. * All rights reserved. * * This program is free software; you can redistribute it and/or diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index dcb930a52613..cece8a08edca 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -724,14 +724,24 @@ void be_link_status_update(struct be_adapter *adapter, u8 link_status) netdev_info(netdev, "Link is %s\n", link_status ? "Up" : "Down"); } +static int be_gso_hdr_len(struct sk_buff *skb) +{ + if (skb->encapsulation) + return skb_inner_transport_offset(skb) + + inner_tcp_hdrlen(skb); + return skb_transport_offset(skb) + tcp_hdrlen(skb); +} + static void be_tx_stats_update(struct be_tx_obj *txo, struct sk_buff *skb) { struct be_tx_stats *stats = tx_stats(txo); - u64 tx_pkts = skb_shinfo(skb)->gso_segs ? : 1; + u32 tx_pkts = skb_shinfo(skb)->gso_segs ? : 1; + /* Account for headers which get duplicated in TSO pkt */ + u32 dup_hdr_len = tx_pkts > 1 ? be_gso_hdr_len(skb) * (tx_pkts - 1) : 0; u64_stats_update_begin(&stats->sync); stats->tx_reqs++; - stats->tx_bytes += skb->len; + stats->tx_bytes += skb->len + dup_hdr_len; stats->tx_pkts += tx_pkts; if (skb->encapsulation && skb->ip_summed == CHECKSUM_PARTIAL) stats->tx_vxlan_offload_pkts += tx_pkts; diff --git a/drivers/net/ethernet/freescale/fman/Makefile b/drivers/net/ethernet/freescale/fman/Makefile index 51fd2e6c1b84..60491779e49f 100644 --- a/drivers/net/ethernet/freescale/fman/Makefile +++ b/drivers/net/ethernet/freescale/fman/Makefile @@ -1,7 +1,9 @@ subdir-ccflags-y += -I$(srctree)/drivers/net/ethernet/freescale/fman -obj-y += fsl_fman.o fsl_fman_mac.o fsl_mac.o +obj-$(CONFIG_FSL_FMAN) += fsl_fman.o +obj-$(CONFIG_FSL_FMAN) += fsl_fman_port.o +obj-$(CONFIG_FSL_FMAN) += fsl_mac.o -fsl_fman-objs := fman_muram.o fman.o fman_sp.o fman_port.o -fsl_fman_mac-objs := fman_dtsec.o fman_memac.o fman_tgec.o -fsl_mac-objs += mac.o +fsl_fman-objs := fman_muram.o fman.o fman_sp.o +fsl_fman_port-objs := fman_port.o +fsl_mac-objs:= mac.o fman_dtsec.o fman_memac.o fman_tgec.o diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c index 1de2e1e51c2b..dafd9e1baba2 100644 --- a/drivers/net/ethernet/freescale/fman/fman.c +++ b/drivers/net/ethernet/freescale/fman/fman.c @@ -618,7 +618,7 @@ struct fman { unsigned long cam_offset; size_t cam_size; /* Fifo in MURAM */ - int fifo_offset; + unsigned long fifo_offset; size_t fifo_size; u32 liodn_base[64]; @@ -2036,7 +2036,7 @@ static int fman_init(struct fman *fman) /* allocate MURAM for FIFO according to total size */ fman->fifo_offset = fman_muram_alloc(fman->muram, fman->state->total_fifo_size); - if (IS_ERR_VALUE(fman->cam_offset)) { + if (IS_ERR_VALUE(fman->fifo_offset)) { free_init_resources(fman); dev_err(fman->dev, "%s: MURAM alloc for BMI FIFO failed\n", __func__); @@ -2115,6 +2115,7 @@ void fman_register_intr(struct fman *fman, enum fman_event_modules module, fman->intr_mng[event].isr_cb = isr_cb; fman->intr_mng[event].src_handle = src_arg; } +EXPORT_SYMBOL(fman_register_intr); /** * fman_unregister_intr @@ -2138,6 +2139,7 @@ void fman_unregister_intr(struct fman *fman, enum fman_event_modules module, fman->intr_mng[event].isr_cb = NULL; fman->intr_mng[event].src_handle = NULL; } +EXPORT_SYMBOL(fman_unregister_intr); /** * fman_set_port_params @@ -2241,6 +2243,7 @@ return_err: spin_unlock_irqrestore(&fman->spinlock, flags); return err; } +EXPORT_SYMBOL(fman_set_port_params); /** * fman_reset_mac @@ -2310,6 +2313,7 @@ int fman_reset_mac(struct fman *fman, u8 mac_id) return 0; } +EXPORT_SYMBOL(fman_reset_mac); /** * fman_set_mac_max_frame @@ -2327,8 +2331,7 @@ int fman_set_mac_max_frame(struct fman *fman, u8 mac_id, u16 mfl) * or equal to the port's max */ if ((!fman->state->port_mfl[mac_id]) || - (fman->state->port_mfl[mac_id] && - (mfl <= fman->state->port_mfl[mac_id]))) { + (mfl <= fman->state->port_mfl[mac_id])) { fman->state->mac_mfl[mac_id] = mfl; } else { dev_warn(fman->dev, "%s: MAC max_frame_length is larger than Port max_frame_length\n", @@ -2337,6 +2340,7 @@ int fman_set_mac_max_frame(struct fman *fman, u8 mac_id, u16 mfl) } return 0; } +EXPORT_SYMBOL(fman_set_mac_max_frame); /** * fman_get_clock_freq @@ -2363,6 +2367,7 @@ u32 fman_get_bmi_max_fifo_size(struct fman *fman) { return fman->state->bmi_max_fifo_size; } +EXPORT_SYMBOL(fman_get_bmi_max_fifo_size); /** * fman_get_revision @@ -2384,6 +2389,7 @@ void fman_get_revision(struct fman *fman, struct fman_rev_info *rev_info) FPM_REV1_MAJOR_SHIFT); rev_info->minor = tmp & FPM_REV1_MINOR_MASK; } +EXPORT_SYMBOL(fman_get_revision); /** * fman_get_qman_channel_id @@ -2419,6 +2425,7 @@ u32 fman_get_qman_channel_id(struct fman *fman, u32 port_id) return fman->state->qman_channel_base + i; } +EXPORT_SYMBOL(fman_get_qman_channel_id); /** * fman_get_mem_region @@ -2432,6 +2439,7 @@ struct resource *fman_get_mem_region(struct fman *fman) { return fman->state->res; } +EXPORT_SYMBOL(fman_get_mem_region); /* Bootargs defines */ /* Extra headroom for RX buffers - Default, min and max */ @@ -2453,7 +2461,7 @@ struct resource *fman_get_mem_region(struct fman *fman) * particular forwarding scenarios that add extra headers to the * forwarded frame. */ -int fsl_fm_rx_extra_headroom = FSL_FM_RX_EXTRA_HEADROOM; +static int fsl_fm_rx_extra_headroom = FSL_FM_RX_EXTRA_HEADROOM; module_param(fsl_fm_rx_extra_headroom, int, 0); MODULE_PARM_DESC(fsl_fm_rx_extra_headroom, "Extra headroom for Rx buffers"); @@ -2466,7 +2474,7 @@ MODULE_PARM_DESC(fsl_fm_rx_extra_headroom, "Extra headroom for Rx buffers"); * Could be overridden once, at boot-time, via the * fm_set_max_frm() callback. */ -int fsl_fm_max_frm = FSL_FM_MAX_FRAME_SIZE; +static int fsl_fm_max_frm = FSL_FM_MAX_FRAME_SIZE; module_param(fsl_fm_max_frm, int, 0); MODULE_PARM_DESC(fsl_fm_max_frm, "Maximum frame size, across all interfaces"); @@ -2538,6 +2546,7 @@ struct fman *fman_bind(struct device *fm_dev) { return (struct fman *)(dev_get_drvdata(get_device(fm_dev))); } +EXPORT_SYMBOL(fman_bind); static irqreturn_t fman_err_irq(int irq, void *handle) { @@ -2727,8 +2736,8 @@ static struct fman *read_dts_node(struct platform_device *of_dev) struct fman *fman; struct device_node *fm_node, *muram_node; struct resource *res; - const u32 *u32_prop; - int lenp, err, irq; + u32 val, range[2]; + int err, irq; struct clk *clk; u32 clk_rate; phys_addr_t phys_base_addr; @@ -2740,16 +2749,13 @@ static struct fman *read_dts_node(struct platform_device *of_dev) fm_node = of_node_get(of_dev->dev.of_node); - u32_prop = (const u32 *)of_get_property(fm_node, "cell-index", &lenp); - if (!u32_prop) { - dev_err(&of_dev->dev, "%s: of_get_property(%s, cell-index) failed\n", + err = of_property_read_u32(fm_node, "cell-index", &val); + if (err) { + dev_err(&of_dev->dev, "%s: failed to read cell-index for %s\n", __func__, fm_node->full_name); goto fman_node_put; } - if (WARN_ON(lenp != sizeof(u32))) - goto fman_node_put; - - fman->dts_params.id = (u8)fdt32_to_cpu(u32_prop[0]); + fman->dts_params.id = (u8)val; /* Get the FM interrupt */ res = platform_get_resource(of_dev, IORESOURCE_IRQ, 0); @@ -2796,18 +2802,15 @@ static struct fman *read_dts_node(struct platform_device *of_dev) /* Rounding to MHz */ fman->dts_params.clk_freq = DIV_ROUND_UP(clk_rate, 1000000); - u32_prop = (const u32 *)of_get_property(fm_node, - "fsl,qman-channel-range", - &lenp); - if (!u32_prop) { - dev_err(&of_dev->dev, "%s: of_get_property(%s, fsl,qman-channel-range) failed\n", + err = of_property_read_u32_array(fm_node, "fsl,qman-channel-range", + &range[0], 2); + if (err) { + dev_err(&of_dev->dev, "%s: failed to read fsl,qman-channel-range for %s\n", __func__, fm_node->full_name); goto fman_node_put; } - if (WARN_ON(lenp != sizeof(u32) * 2)) - goto fman_node_put; - fman->dts_params.qman_channel_base = fdt32_to_cpu(u32_prop[0]); - fman->dts_params.num_of_qman_channels = fdt32_to_cpu(u32_prop[1]); + fman->dts_params.qman_channel_base = range[0]; + fman->dts_params.num_of_qman_channels = range[1]; /* Get the MURAM base address and size */ muram_node = of_find_matching_node(fm_node, fman_muram_match); @@ -2858,7 +2861,7 @@ static struct fman *read_dts_node(struct platform_device *of_dev) fman->dts_params.base_addr = devm_ioremap(&of_dev->dev, phys_base_addr, mem_size); - if (fman->dts_params.base_addr == 0) { + if (!fman->dts_params.base_addr) { dev_err(&of_dev->dev, "%s: devm_ioremap() failed\n", __func__); goto fman_free; } @@ -2930,7 +2933,7 @@ static const struct of_device_id fman_match[] = { {} }; -MODULE_DEVICE_TABLE(of, fm_match); +MODULE_DEVICE_TABLE(of, fman_match); static struct platform_driver fman_driver = { .driver = { @@ -2940,4 +2943,25 @@ static struct platform_driver fman_driver = { .probe = fman_probe, }; -builtin_platform_driver(fman_driver); +static int __init fman_load(void) +{ + int err; + + pr_debug("FSL DPAA FMan driver\n"); + + err = platform_driver_register(&fman_driver); + if (err < 0) + pr_err("Error, platform_driver_register() = %d\n", err); + + return err; +} +module_init(fman_load); + +static void __exit fman_unload(void) +{ + platform_driver_unregister(&fman_driver); +} +module_exit(fman_unload); + +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_DESCRIPTION("Freescale DPAA Frame Manager driver"); diff --git a/drivers/net/ethernet/freescale/fman/fman_mac.h b/drivers/net/ethernet/freescale/fman/fman_mac.h index ddf0260176c9..dd6d0526f6c1 100644 --- a/drivers/net/ethernet/freescale/fman/fman_mac.h +++ b/drivers/net/ethernet/freescale/fman/fman_mac.h @@ -191,10 +191,6 @@ struct fman_mac_params { u16 max_speed; /* A handle to the FM object this port related to */ void *fm; - /* MDIO exceptions interrupt source - not valid for all - * MACs; MUST be set to 0 for MACs that don't have - * mdio-irq, or for polling - */ void *dev_id; /* device cookie used by the exception cbs */ fman_mac_exception_cb *event_cb; /* MDIO Events Callback Routine */ fman_mac_exception_cb *exception_cb;/* Exception Callback Routine */ diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c index 45e98fd8b79e..53ef51e3bd9e 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.c +++ b/drivers/net/ethernet/freescale/fman/fman_memac.c @@ -507,6 +507,9 @@ static void setup_sgmii_internal_phy(struct fman_mac *memac, { u16 tmp_reg16; + if (WARN_ON(!memac->pcsphy)) + return; + /* SGMII mode */ tmp_reg16 = IF_MODE_SGMII_EN; if (!fixed_link) @@ -1151,7 +1154,8 @@ struct fman_mac *memac_config(struct fman_mac_params *params) /* Save FMan revision */ fman_get_revision(memac->fm, &memac->fm_rev_info); - if (memac->phy_if == PHY_INTERFACE_MODE_SGMII) { + if (memac->phy_if == PHY_INTERFACE_MODE_SGMII || + memac->phy_if == PHY_INTERFACE_MODE_QSGMII) { if (!params->internal_phy_node) { pr_err("PCS PHY node is not available\n"); memac_free(memac); diff --git a/drivers/net/ethernet/freescale/fman/fman_muram.c b/drivers/net/ethernet/freescale/fman/fman_muram.c index 47394c45b6e8..5ec94d243da0 100644 --- a/drivers/net/ethernet/freescale/fman/fman_muram.c +++ b/drivers/net/ethernet/freescale/fman/fman_muram.c @@ -150,7 +150,8 @@ unsigned long fman_muram_alloc(struct muram_info *muram, size_t size) * * Free an allocated memory from FM-MURAM partition. */ -void fman_muram_free_mem(struct muram_info *muram, unsigned long offset, size_t size) +void fman_muram_free_mem(struct muram_info *muram, unsigned long offset, + size_t size) { unsigned long addr = fman_muram_offset_to_vbase(muram, offset); diff --git a/drivers/net/ethernet/freescale/fman/fman_muram.h b/drivers/net/ethernet/freescale/fman/fman_muram.h index 889649ad8931..453bf849eee1 100644 --- a/drivers/net/ethernet/freescale/fman/fman_muram.h +++ b/drivers/net/ethernet/freescale/fman/fman_muram.h @@ -46,6 +46,7 @@ unsigned long fman_muram_offset_to_vbase(struct muram_info *muram, unsigned long fman_muram_alloc(struct muram_info *muram, size_t size); -void fman_muram_free_mem(struct muram_info *muram, unsigned long offset, size_t size); +void fman_muram_free_mem(struct muram_info *muram, unsigned long offset, + size_t size); #endif /* __FM_MURAM_EXT */ diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c index 70c198d072dc..9f3bb50a2365 100644 --- a/drivers/net/ethernet/freescale/fman/fman_port.c +++ b/drivers/net/ethernet/freescale/fman/fman_port.c @@ -1477,7 +1477,8 @@ EXPORT_SYMBOL(fman_port_cfg_buf_prefix_content); */ int fman_port_disable(struct fman_port *port) { - u32 __iomem *bmi_cfg_reg, *bmi_status_reg, tmp; + u32 __iomem *bmi_cfg_reg, *bmi_status_reg; + u32 tmp; bool rx_port, failure = false; int count; @@ -1553,7 +1554,8 @@ EXPORT_SYMBOL(fman_port_disable); */ int fman_port_enable(struct fman_port *port) { - u32 __iomem *bmi_cfg_reg, tmp; + u32 __iomem *bmi_cfg_reg; + u32 tmp; bool rx_port; if (!is_init_done(port->cfg)) @@ -1623,7 +1625,7 @@ static int fman_port_probe(struct platform_device *of_dev) struct device_node *fm_node, *port_node; struct resource res; struct resource *dev_res; - const u32 *u32_prop; + u32 val; int err = 0, lenp; enum fman_port_type port_type; u16 port_speed; @@ -1652,28 +1654,20 @@ static int fman_port_probe(struct platform_device *of_dev) goto return_err; } - u32_prop = (const u32 *)of_get_property(port_node, "cell-index", &lenp); - if (!u32_prop) { - dev_err(port->dev, "%s: of_get_property(%s, cell-index) failed\n", + err = of_property_read_u32(port_node, "cell-index", &val); + if (err) { + dev_err(port->dev, "%s: reading cell-index for %s failed\n", __func__, port_node->full_name); err = -EINVAL; goto return_err; } - if (WARN_ON(lenp != sizeof(u32))) { - err = -EINVAL; - goto return_err; - } - port_id = (u8)fdt32_to_cpu(u32_prop[0]); - + port_id = (u8)val; port->dts_params.id = port_id; if (of_device_is_compatible(port_node, "fsl,fman-v3-port-tx")) { port_type = FMAN_PORT_TYPE_TX; port_speed = 1000; - u32_prop = (const u32 *)of_get_property(port_node, - "fsl,fman-10g-port", - &lenp); - if (u32_prop) + if (of_find_property(port_node, "fsl,fman-10g-port", &lenp)) port_speed = 10000; } else if (of_device_is_compatible(port_node, "fsl,fman-v2-port-tx")) { @@ -1686,9 +1680,7 @@ 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; - u32_prop = (const u32 *)of_get_property(port_node, - "fsl,fman-10g-port", &lenp); - if (u32_prop) + if (of_find_property(port_node, "fsl,fman-10g-port", &lenp)) port_speed = 10000; } else if (of_device_is_compatible(port_node, "fsl,fman-v2-port-rx")) { @@ -1743,7 +1735,7 @@ static int fman_port_probe(struct platform_device *of_dev) port->dts_params.base_addr = devm_ioremap(port->dev, res.start, resource_size(&res)); - if (port->dts_params.base_addr == 0) + if (!port->dts_params.base_addr) dev_err(port->dev, "%s: devm_ioremap() failed\n", __func__); dev_set_drvdata(&of_dev->dev, port); @@ -1775,4 +1767,25 @@ static struct platform_driver fman_port_driver = { .probe = fman_port_probe, }; -builtin_platform_driver(fman_port_driver); +static int __init fman_port_load(void) +{ + int err; + + pr_debug("FSL DPAA FMan driver\n"); + + err = platform_driver_register(&fman_port_driver); + if (err < 0) + pr_err("Error, platform_driver_register() = %d\n", err); + + return err; +} +module_init(fman_port_load); + +static void __exit fman_port_unload(void) +{ + platform_driver_unregister(&fman_port_driver); +} +module_exit(fman_port_unload); + +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_DESCRIPTION("Freescale DPAA Frame Manager Port driver"); diff --git a/drivers/net/ethernet/freescale/fman/fman_sp.c b/drivers/net/ethernet/freescale/fman/fman_sp.c index f9e7aa385cba..248f5bcca468 100644 --- a/drivers/net/ethernet/freescale/fman/fman_sp.c +++ b/drivers/net/ethernet/freescale/fman/fman_sp.c @@ -80,6 +80,7 @@ void fman_sp_set_buf_pools_in_asc_order_of_buf_sizes(struct fman_ext_pools } } } +EXPORT_SYMBOL(fman_sp_set_buf_pools_in_asc_order_of_buf_sizes); int fman_sp_build_buffer_struct(struct fman_sp_int_context_data_copy * int_context_data_copy, @@ -164,3 +165,5 @@ int fman_sp_build_buffer_struct(struct fman_sp_int_context_data_copy * return 0; } +EXPORT_SYMBOL(fman_sp_build_buffer_struct); + diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c index e33d9d24c1db..8fe6b3e253fa 100644 --- a/drivers/net/ethernet/freescale/fman/mac.c +++ b/drivers/net/ethernet/freescale/fman/mac.c @@ -469,9 +469,9 @@ static void adjust_link_memac(struct net_device *net_dev) /* Initializes driver's PHY state, and attaches to the PHY. * Returns 0 on success. */ -static int init_phy(struct net_device *net_dev, - struct mac_device *mac_dev, - void (*adj_lnk)(struct net_device *)) +static struct phy_device *init_phy(struct net_device *net_dev, + struct mac_device *mac_dev, + void (*adj_lnk)(struct net_device *)) { struct phy_device *phy_dev; struct mac_priv_s *priv = mac_dev->priv; @@ -480,7 +480,7 @@ static int init_phy(struct net_device *net_dev, priv->phy_if); if (!phy_dev) { netdev_err(net_dev, "Could not connect to PHY\n"); - return -ENODEV; + return NULL; } /* Remove any features not supported by the controller */ @@ -493,23 +493,23 @@ static int init_phy(struct net_device *net_dev, mac_dev->phy_dev = phy_dev; - return 0; + return phy_dev; } -static int dtsec_init_phy(struct net_device *net_dev, - struct mac_device *mac_dev) +static struct phy_device *dtsec_init_phy(struct net_device *net_dev, + struct mac_device *mac_dev) { return init_phy(net_dev, mac_dev, &adjust_link_dtsec); } -static int tgec_init_phy(struct net_device *net_dev, - struct mac_device *mac_dev) +static struct phy_device *tgec_init_phy(struct net_device *net_dev, + struct mac_device *mac_dev) { return init_phy(net_dev, mac_dev, adjust_link_void); } -static int memac_init_phy(struct net_device *net_dev, - struct mac_device *mac_dev) +static struct phy_device *memac_init_phy(struct net_device *net_dev, + struct mac_device *mac_dev) { return init_phy(net_dev, mac_dev, &adjust_link_memac); } @@ -583,31 +583,6 @@ static void setup_memac(struct mac_device *mac_dev) static DEFINE_MUTEX(eth_lock); -static const char phy_str[][11] = { - [PHY_INTERFACE_MODE_MII] = "mii", - [PHY_INTERFACE_MODE_GMII] = "gmii", - [PHY_INTERFACE_MODE_SGMII] = "sgmii", - [PHY_INTERFACE_MODE_TBI] = "tbi", - [PHY_INTERFACE_MODE_RMII] = "rmii", - [PHY_INTERFACE_MODE_RGMII] = "rgmii", - [PHY_INTERFACE_MODE_RGMII_ID] = "rgmii-id", - [PHY_INTERFACE_MODE_RGMII_RXID] = "rgmii-rxid", - [PHY_INTERFACE_MODE_RGMII_TXID] = "rgmii-txid", - [PHY_INTERFACE_MODE_RTBI] = "rtbi", - [PHY_INTERFACE_MODE_XGMII] = "xgmii" -}; - -static phy_interface_t __pure __attribute__((nonnull)) str2phy(const char *str) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(phy_str); i++) - if (strcmp(str, phy_str[i]) == 0) - return (phy_interface_t)i; - - return PHY_INTERFACE_MODE_MII; -} - static const u16 phy2speed[] = { [PHY_INTERFACE_MODE_MII] = SPEED_100, [PHY_INTERFACE_MODE_GMII] = SPEED_1000, @@ -678,7 +653,7 @@ MODULE_DEVICE_TABLE(of, mac_match); static int mac_probe(struct platform_device *_of_dev) { - int err, i, lenp, nph; + int err, i, nph; struct device *dev; struct device_node *mac_node, *dev_node; struct mac_device *mac_dev; @@ -686,9 +661,9 @@ static int mac_probe(struct platform_device *_of_dev) struct resource res; struct mac_priv_s *priv; const u8 *mac_addr; - const char *char_prop; - const u32 *u32_prop; + u32 val; u8 fman_id; + int phy_if; dev = &_of_dev->dev; mac_node = dev->of_node; @@ -749,16 +724,15 @@ static int mac_probe(struct platform_device *_of_dev) } /* Get the FMan cell-index */ - u32_prop = of_get_property(dev_node, "cell-index", &lenp); - if (!u32_prop) { - dev_err(dev, "of_get_property(%s, cell-index) failed\n", + err = of_property_read_u32(dev_node, "cell-index", &val); + if (err) { + dev_err(dev, "failed to read cell-index for %s\n", dev_node->full_name); err = -EINVAL; goto _return_of_node_put; } - WARN_ON(lenp != sizeof(u32)); /* cell-index 0 => FMan id 1 */ - fman_id = (u8)(fdt32_to_cpu(u32_prop[0]) + 1); + fman_id = (u8)(val + 1); priv->fman = fman_bind(&of_dev->dev); if (!priv->fman) { @@ -805,15 +779,14 @@ static int mac_probe(struct platform_device *_of_dev) } /* Get the cell-index */ - u32_prop = of_get_property(mac_node, "cell-index", &lenp); - if (!u32_prop) { - dev_err(dev, "of_get_property(%s, cell-index) failed\n", + err = of_property_read_u32(mac_node, "cell-index", &val); + if (err) { + dev_err(dev, "failed to read cell-index for %s\n", mac_node->full_name); err = -EINVAL; goto _return_dev_set_drvdata; } - WARN_ON(lenp != sizeof(u32)); - priv->cell_index = (u8)fdt32_to_cpu(u32_prop[0]); + priv->cell_index = (u8)val; /* Get the MAC address */ mac_addr = of_get_mac_address(mac_node); @@ -870,16 +843,14 @@ static int mac_probe(struct platform_device *_of_dev) } /* Get the PHY connection type */ - char_prop = (const char *)of_get_property(mac_node, - "phy-connection-type", NULL); - if (!char_prop) { + phy_if = of_get_phy_mode(mac_node); + if (phy_if < 0) { dev_warn(dev, - "of_get_property(%s, phy-connection-type) failed. Defaulting to MII\n", + "of_get_phy_mode() for %s failed. Defaulting to SGMII\n", mac_node->full_name); - priv->phy_if = PHY_INTERFACE_MODE_MII; - } else { - priv->phy_if = str2phy(char_prop); + phy_if = PHY_INTERFACE_MODE_SGMII; } + priv->phy_if = phy_if; priv->speed = phy2speed[priv->phy_if]; priv->max_speed = priv->speed; diff --git a/drivers/net/ethernet/freescale/fman/mac.h b/drivers/net/ethernet/freescale/fman/mac.h index 0211cc9a46d6..d7313f0c5135 100644 --- a/drivers/net/ethernet/freescale/fman/mac.h +++ b/drivers/net/ethernet/freescale/fman/mac.h @@ -58,7 +58,8 @@ struct mac_device { bool tx_pause_active; bool promisc; - int (*init_phy)(struct net_device *net_dev, struct mac_device *mac_dev); + struct phy_device *(*init_phy)(struct net_device *net_dev, + struct mac_device *mac_dev); int (*init)(struct mac_device *mac_dev); int (*start)(struct mac_device *mac_dev); int (*stop)(struct mac_device *mac_dev); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c index a68eef0ee65f..22e141005cd9 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c @@ -126,7 +126,7 @@ void hns_mac_adjust_link(struct hns_mac_cb *mac_cb, int speed, int duplex) (enum mac_speed)speed, duplex); if (ret) { dev_err(mac_cb->dev, - "adjust_link failed,%s mac%d ret = %#x!\n", + "adjust_link failed, %s mac%d ret = %#x!\n", mac_cb->dsaf_dev->ae_dev.name, mac_cb->mac_id, ret); return; @@ -149,7 +149,7 @@ static int hns_mac_get_inner_port_num(struct hns_mac_cb *mac_cb, if (mac_cb->dsaf_dev->dsaf_mode <= DSAF_MODE_ENABLE) { if (mac_cb->mac_id != DSAF_MAX_PORT_NUM) { dev_err(mac_cb->dev, - "input invalid,%s mac%d vmid%d !\n", + "input invalid, %s mac%d vmid%d !\n", mac_cb->dsaf_dev->ae_dev.name, mac_cb->mac_id, vmid); return -EINVAL; @@ -157,19 +157,19 @@ static int hns_mac_get_inner_port_num(struct hns_mac_cb *mac_cb, } else if (mac_cb->dsaf_dev->dsaf_mode < DSAF_MODE_MAX) { if (mac_cb->mac_id >= DSAF_MAX_PORT_NUM) { dev_err(mac_cb->dev, - "input invalid,%s mac%d vmid%d!\n", + "input invalid, %s mac%d vmid%d!\n", mac_cb->dsaf_dev->ae_dev.name, mac_cb->mac_id, vmid); return -EINVAL; } } else { - dev_err(mac_cb->dev, "dsaf mode invalid,%s mac%d!\n", + dev_err(mac_cb->dev, "dsaf mode invalid, %s mac%d!\n", mac_cb->dsaf_dev->ae_dev.name, mac_cb->mac_id); return -EINVAL; } if (vmid >= mac_cb->dsaf_dev->rcb_common[0]->max_vfn) { - dev_err(mac_cb->dev, "input invalid,%s mac%d vmid%d !\n", + dev_err(mac_cb->dev, "input invalid, %s mac%d vmid%d !\n", mac_cb->dsaf_dev->ae_dev.name, mac_cb->mac_id, vmid); return -EINVAL; } @@ -196,7 +196,7 @@ static int hns_mac_get_inner_port_num(struct hns_mac_cb *mac_cb, tmp_port = vmid; break; default: - dev_err(mac_cb->dev, "dsaf mode invalid,%s mac%d!\n", + dev_err(mac_cb->dev, "dsaf mode invalid, %s mac%d!\n", mac_cb->dsaf_dev->ae_dev.name, mac_cb->mac_id); return -EINVAL; } @@ -275,7 +275,7 @@ int hns_mac_set_multi(struct hns_mac_cb *mac_cb, ret = hns_dsaf_add_mac_mc_port(dsaf_dev, &mac_entry); if (ret) { dev_err(dsaf_dev->dev, - "set mac mc port failed,%s mac%d ret = %#x!\n", + "set mac mc port failed, %s mac%d ret = %#x!\n", mac_cb->dsaf_dev->ae_dev.name, mac_cb->mac_id, ret); return ret; @@ -305,7 +305,7 @@ int hns_mac_del_mac(struct hns_mac_cb *mac_cb, u32 vfn, char *mac) old_mac = &mac_cb->addr_entry_idx[vfn]; } else { dev_err(mac_cb->dev, - "vf queue is too large,%s mac%d queue = %#x!\n", + "vf queue is too large, %s mac%d queue = %#x!\n", mac_cb->dsaf_dev->ae_dev.name, mac_cb->mac_id, vfn); return -EINVAL; } @@ -547,7 +547,7 @@ int hns_mac_set_autoneg(struct hns_mac_cb *mac_cb, u8 enable) struct mac_driver *mac_ctrl_drv = hns_mac_get_drv(mac_cb); if (mac_cb->phy_if == PHY_INTERFACE_MODE_XGMII && enable) { - dev_err(mac_cb->dev, "enable autoneg is not allowed!"); + dev_err(mac_cb->dev, "enabling autoneg is not allowed!\n"); return -ENOTSUPP; } @@ -571,7 +571,7 @@ int hns_mac_set_pauseparam(struct hns_mac_cb *mac_cb, u32 rx_en, u32 tx_en) if (mac_cb->mac_type == HNAE_PORT_DEBUG) { if (is_ver1 && (tx_en || rx_en)) { - dev_err(mac_cb->dev, "macv1 cann't enable tx/rx_pause!"); + dev_err(mac_cb->dev, "macv1 can't enable tx/rx_pause!\n"); return -EINVAL; } } @@ -926,7 +926,7 @@ int hns_mac_get_cfg(struct dsaf_device *dsaf_dev, struct hns_mac_cb *mac_cb) ret = hns_mac_get_mode(mac_cb->phy_if); if (ret < 0) { dev_err(dsaf_dev->dev, - "hns_mac_get_mode failed,mac%d ret = %#x!\n", + "hns_mac_get_mode failed, mac%d ret = %#x!\n", mac_cb->mac_id, ret); return ret; } diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index ad4ab979507b..4a62ffd7729d 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -2323,6 +2323,41 @@ free_netdev: return err; } +static int mtk_get_chip_id(struct mtk_eth *eth, u32 *chip_id) +{ + u32 val[2], id[4]; + + regmap_read(eth->ethsys, ETHSYS_CHIPID0_3, &val[0]); + regmap_read(eth->ethsys, ETHSYS_CHIPID4_7, &val[1]); + + id[3] = ((val[0] >> 16) & 0xff) - '0'; + id[2] = ((val[0] >> 24) & 0xff) - '0'; + id[1] = (val[1] & 0xff) - '0'; + id[0] = ((val[1] >> 8) & 0xff) - '0'; + + *chip_id = (id[3] * 1000) + (id[2] * 100) + + (id[1] * 10) + id[0]; + + if (!(*chip_id)) { + dev_err(eth->dev, "failed to get chip id\n"); + return -ENODEV; + } + + dev_info(eth->dev, "chip id = %d\n", *chip_id); + + return 0; +} + +static bool mtk_is_hwlro_supported(struct mtk_eth *eth) +{ + switch (eth->chip_id) { + case MT7623_ETH: + return true; + } + + return false; +} + static int mtk_probe(struct platform_device *pdev) { struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); @@ -2362,8 +2397,6 @@ static int mtk_probe(struct platform_device *pdev) return PTR_ERR(eth->pctl); } - eth->hwlro = of_property_read_bool(pdev->dev.of_node, "mediatek,hwlro"); - for (i = 0; i < 3; i++) { eth->irq[i] = platform_get_irq(pdev, i); if (eth->irq[i] < 0) { @@ -2388,6 +2421,12 @@ static int mtk_probe(struct platform_device *pdev) if (err) return err; + err = mtk_get_chip_id(eth, ð->chip_id); + if (err) + return err; + + eth->hwlro = mtk_is_hwlro_supported(eth); + for_each_child_of_node(pdev->dev.of_node, mac_np) { if (!of_device_is_compatible(mac_np, "mediatek,eth-mac")) diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 30031959d6de..99b1c8e9f16f 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -342,6 +342,11 @@ #define GPIO_BIAS_CTRL 0xed0 #define GPIO_DRV_SEL10 0xf00 +/* ethernet subsystem chip id register */ +#define ETHSYS_CHIPID0_3 0x0 +#define ETHSYS_CHIPID4_7 0x4 +#define MT7623_ETH 7623 + /* ethernet subsystem config register */ #define ETHSYS_SYSCFG0 0x14 #define SYSCFG0_GE_MASK 0x3 @@ -534,6 +539,7 @@ struct mtk_eth { unsigned long sysclk; struct regmap *ethsys; struct regmap *pctl; + u32 chip_id; bool hwlro; atomic_t dma_refcnt; struct mtk_tx_ring tx_ring; diff --git a/drivers/net/ethernet/qualcomm/Kconfig b/drivers/net/ethernet/qualcomm/Kconfig index 9ba568db576f..d7720bf92d49 100644 --- a/drivers/net/ethernet/qualcomm/Kconfig +++ b/drivers/net/ethernet/qualcomm/Kconfig @@ -26,6 +26,7 @@ config QCA7000 config QCOM_EMAC tristate "Qualcomm Technologies, Inc. EMAC Gigabit Ethernet support" + depends on HAS_DMA && HAS_IOMEM select CRC32 select PHYLIB ---help--- diff --git a/drivers/net/ethernet/ti/cpsw-phy-sel.c b/drivers/net/ethernet/ti/cpsw-phy-sel.c index c3e85acfdc70..054a8dd23dae 100644 --- a/drivers/net/ethernet/ti/cpsw-phy-sel.c +++ b/drivers/net/ethernet/ti/cpsw-phy-sel.c @@ -30,6 +30,8 @@ #define AM33XX_GMII_SEL_RMII2_IO_CLK_EN BIT(7) #define AM33XX_GMII_SEL_RMII1_IO_CLK_EN BIT(6) +#define AM33XX_GMII_SEL_RGMII2_IDMODE BIT(5) +#define AM33XX_GMII_SEL_RGMII1_IDMODE BIT(4) #define GMII_SEL_MODE_MASK 0x3 @@ -48,6 +50,7 @@ static void cpsw_gmii_sel_am3352(struct cpsw_phy_sel_priv *priv, u32 reg; u32 mask; u32 mode = 0; + bool rgmii_id = false; reg = readl(priv->gmii_sel); @@ -57,10 +60,14 @@ static void cpsw_gmii_sel_am3352(struct cpsw_phy_sel_priv *priv, break; case PHY_INTERFACE_MODE_RGMII: + mode = AM33XX_GMII_SEL_MODE_RGMII; + break; + case PHY_INTERFACE_MODE_RGMII_ID: case PHY_INTERFACE_MODE_RGMII_RXID: case PHY_INTERFACE_MODE_RGMII_TXID: mode = AM33XX_GMII_SEL_MODE_RGMII; + rgmii_id = true; break; default: @@ -83,6 +90,13 @@ static void cpsw_gmii_sel_am3352(struct cpsw_phy_sel_priv *priv, mode |= AM33XX_GMII_SEL_RMII2_IO_CLK_EN; } + if (rgmii_id) { + if (slave == 0) + mode |= AM33XX_GMII_SEL_RGMII1_IDMODE; + else + mode |= AM33XX_GMII_SEL_RGMII2_IDMODE; + } + reg &= ~mask; reg |= mode; diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.c b/drivers/net/ethernet/toshiba/ps3_gelic_net.c index bc258d7e41df..272f2b1cb7ad 100644 --- a/drivers/net/ethernet/toshiba/ps3_gelic_net.c +++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.c @@ -1769,7 +1769,7 @@ static int ps3_gelic_driver_probe(struct ps3_system_bus_device *dev) gelic_ether_setup_netdev_ops(netdev, &card->napi); result = gelic_net_setup_netdev(netdev, card); if (result) { - dev_dbg(&dev->core, "%s: setup_netdev failed %d", + dev_dbg(&dev->core, "%s: setup_netdev failed %d\n", __func__, result); goto fail_setup_netdev; } diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 69e2a833a84f..35f9f9742a48 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -818,7 +818,7 @@ static irqreturn_t axienet_tx_irq(int irq, void *_ndev) goto out; } if (!(status & XAXIDMA_IRQ_ALL_MASK)) - dev_err(&ndev->dev, "No interrupts asserted in Tx path"); + dev_err(&ndev->dev, "No interrupts asserted in Tx path\n"); if (status & XAXIDMA_IRQ_ERROR_MASK) { dev_err(&ndev->dev, "DMA Tx error 0x%x\n", status); dev_err(&ndev->dev, "Current BD is at: 0x%x\n", @@ -867,7 +867,7 @@ static irqreturn_t axienet_rx_irq(int irq, void *_ndev) goto out; } if (!(status & XAXIDMA_IRQ_ALL_MASK)) - dev_err(&ndev->dev, "No interrupts asserted in Rx path"); + dev_err(&ndev->dev, "No interrupts asserted in Rx path\n"); if (status & XAXIDMA_IRQ_ERROR_MASK) { dev_err(&ndev->dev, "DMA Rx error 0x%x\n", status); dev_err(&ndev->dev, "Current BD is at: 0x%x\n", diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 5078a0d0db64..2651c8d8de2f 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -142,6 +142,7 @@ config MDIO_THUNDER config MDIO_XGENE tristate "APM X-Gene SoC MDIO bus controller" + depends on ARCH_XGENE || COMPILE_TEST help This module provides a driver for the MDIO busses found in the APM X-Gene SoC's. @@ -320,13 +321,6 @@ config XILINX_GMII2RGMII the Reduced Gigabit Media Independent Interface(RGMII) between Ethernet physical media devices and the Gigabit Ethernet controller. -config MDIO_XGENE - tristate "APM X-Gene SoC MDIO bus controller" - depends on ARCH_XGENE || COMPILE_TEST - help - This module provides a driver for the MDIO busses found in the - APM X-Gene SoC's. - endif # PHYLIB config MICREL_KS8995MA diff --git a/drivers/net/phy/mscc.c b/drivers/net/phy/mscc.c index a17573e3bd8a..77a6671d572e 100644 --- a/drivers/net/phy/mscc.c +++ b/drivers/net/phy/mscc.c @@ -13,6 +13,7 @@ #include #include #include +#include enum rgmii_rx_clock_delay { RGMII_RX_CLK_DELAY_0_2_NS = 0, @@ -37,6 +38,7 @@ enum rgmii_rx_clock_delay { #define MII_VSC85XX_INT_MASK 25 #define MII_VSC85XX_INT_MASK_MASK 0xa000 +#define MII_VSC85XX_INT_MASK_WOL 0x0040 #define MII_VSC85XX_INT_STATUS 26 #define MSCC_PHY_WOL_MAC_CONTROL 27 @@ -52,6 +54,17 @@ enum rgmii_rx_clock_delay { #define RGMII_RX_CLK_DELAY_MASK 0x0070 #define RGMII_RX_CLK_DELAY_POS 4 +#define MSCC_PHY_WOL_LOWER_MAC_ADDR 21 +#define MSCC_PHY_WOL_MID_MAC_ADDR 22 +#define MSCC_PHY_WOL_UPPER_MAC_ADDR 23 +#define MSCC_PHY_WOL_LOWER_PASSWD 24 +#define MSCC_PHY_WOL_MID_PASSWD 25 +#define MSCC_PHY_WOL_UPPER_PASSWD 26 + +#define MSCC_PHY_WOL_MAC_CONTROL 27 +#define SECURE_ON_ENABLE 0x8000 +#define SECURE_ON_PASSWD_LEN_4 0x4000 + /* Microsemi PHY ID's */ #define PHY_ID_VSC8531 0x00070570 #define PHY_ID_VSC8541 0x00070770 @@ -81,6 +94,117 @@ static int vsc85xx_phy_page_set(struct phy_device *phydev, u8 page) return rc; } +static int vsc85xx_wol_set(struct phy_device *phydev, + struct ethtool_wolinfo *wol) +{ + int rc; + u16 reg_val; + u8 i; + u16 pwd[3] = {0, 0, 0}; + struct ethtool_wolinfo *wol_conf = wol; + u8 *mac_addr = phydev->attached_dev->dev_addr; + + mutex_lock(&phydev->lock); + rc = vsc85xx_phy_page_set(phydev, MSCC_PHY_PAGE_EXTENDED_2); + if (rc != 0) + goto out_unlock; + + if (wol->wolopts & WAKE_MAGIC) { + /* Store the device address for the magic packet */ + for (i = 0; i < ARRAY_SIZE(pwd); i++) + pwd[i] = mac_addr[5 - (i * 2 + 1)] << 8 | + mac_addr[5 - i * 2]; + phy_write(phydev, MSCC_PHY_WOL_LOWER_MAC_ADDR, pwd[0]); + phy_write(phydev, MSCC_PHY_WOL_MID_MAC_ADDR, pwd[1]); + phy_write(phydev, MSCC_PHY_WOL_UPPER_MAC_ADDR, pwd[2]); + } else { + phy_write(phydev, MSCC_PHY_WOL_LOWER_MAC_ADDR, 0); + phy_write(phydev, MSCC_PHY_WOL_MID_MAC_ADDR, 0); + phy_write(phydev, MSCC_PHY_WOL_UPPER_MAC_ADDR, 0); + } + + if (wol_conf->wolopts & WAKE_MAGICSECURE) { + for (i = 0; i < ARRAY_SIZE(pwd); i++) + pwd[i] = wol_conf->sopass[5 - (i * 2 + 1)] << 8 | + wol_conf->sopass[5 - i * 2]; + phy_write(phydev, MSCC_PHY_WOL_LOWER_PASSWD, pwd[0]); + phy_write(phydev, MSCC_PHY_WOL_MID_PASSWD, pwd[1]); + phy_write(phydev, MSCC_PHY_WOL_UPPER_PASSWD, pwd[2]); + } else { + phy_write(phydev, MSCC_PHY_WOL_LOWER_PASSWD, 0); + phy_write(phydev, MSCC_PHY_WOL_MID_PASSWD, 0); + phy_write(phydev, MSCC_PHY_WOL_UPPER_PASSWD, 0); + } + + reg_val = phy_read(phydev, MSCC_PHY_WOL_MAC_CONTROL); + if (wol_conf->wolopts & WAKE_MAGICSECURE) + reg_val |= SECURE_ON_ENABLE; + else + reg_val &= ~SECURE_ON_ENABLE; + phy_write(phydev, MSCC_PHY_WOL_MAC_CONTROL, reg_val); + + rc = vsc85xx_phy_page_set(phydev, MSCC_PHY_PAGE_STANDARD); + if (rc != 0) + goto out_unlock; + + if (wol->wolopts & WAKE_MAGIC) { + /* Enable the WOL interrupt */ + reg_val = phy_read(phydev, MII_VSC85XX_INT_MASK); + reg_val |= MII_VSC85XX_INT_MASK_WOL; + rc = phy_write(phydev, MII_VSC85XX_INT_MASK, reg_val); + if (rc != 0) + goto out_unlock; + } else { + /* Disable the WOL interrupt */ + reg_val = phy_read(phydev, MII_VSC85XX_INT_MASK); + reg_val &= (~MII_VSC85XX_INT_MASK_WOL); + rc = phy_write(phydev, MII_VSC85XX_INT_MASK, reg_val); + if (rc != 0) + goto out_unlock; + } + /* Clear WOL iterrupt status */ + reg_val = phy_read(phydev, MII_VSC85XX_INT_STATUS); + +out_unlock: + mutex_unlock(&phydev->lock); + + return rc; +} + +static void vsc85xx_wol_get(struct phy_device *phydev, + struct ethtool_wolinfo *wol) +{ + int rc; + u16 reg_val; + u8 i; + u16 pwd[3] = {0, 0, 0}; + struct ethtool_wolinfo *wol_conf = wol; + + mutex_lock(&phydev->lock); + rc = vsc85xx_phy_page_set(phydev, MSCC_PHY_PAGE_EXTENDED_2); + if (rc != 0) + goto out_unlock; + + reg_val = phy_read(phydev, MSCC_PHY_WOL_MAC_CONTROL); + if (reg_val & SECURE_ON_ENABLE) + wol_conf->wolopts |= WAKE_MAGICSECURE; + if (wol_conf->wolopts & WAKE_MAGICSECURE) { + pwd[0] = phy_read(phydev, MSCC_PHY_WOL_LOWER_PASSWD); + pwd[1] = phy_read(phydev, MSCC_PHY_WOL_MID_PASSWD); + pwd[2] = phy_read(phydev, MSCC_PHY_WOL_UPPER_PASSWD); + for (i = 0; i < ARRAY_SIZE(pwd); i++) { + wol_conf->sopass[5 - i * 2] = pwd[i] & 0x00ff; + wol_conf->sopass[5 - (i * 2 + 1)] = (pwd[i] & 0xff00) + >> 8; + } + } + + rc = vsc85xx_phy_page_set(phydev, MSCC_PHY_PAGE_STANDARD); + +out_unlock: + mutex_unlock(&phydev->lock); +} + static u8 edge_rate_magic_get(u16 vddmac, int slowdown) { @@ -301,6 +425,8 @@ static struct phy_driver vsc85xx_driver[] = { .suspend = &genphy_suspend, .resume = &genphy_resume, .probe = &vsc85xx_probe, + .set_wol = &vsc85xx_wol_set, + .get_wol = &vsc85xx_wol_get, }, { .phy_id = PHY_ID_VSC8541, @@ -318,6 +444,8 @@ static struct phy_driver vsc85xx_driver[] = { .suspend = &genphy_suspend, .resume = &genphy_resume, .probe = &vsc85xx_probe, + .set_wol = &vsc85xx_wol_set, + .get_wol = &vsc85xx_wol_get, } }; diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c index 5fbf83d5aa57..65647533b401 100644 --- a/drivers/net/wan/fsl_ucc_hdlc.c +++ b/drivers/net/wan/fsl_ucc_hdlc.c @@ -295,11 +295,11 @@ free_ucc_pram: qe_muram_free(priv->ucc_pram_offset); free_tx_bd: dma_free_coherent(priv->dev, - TX_BD_RING_LEN * sizeof(struct qe_bd), + TX_BD_RING_LEN * sizeof(struct qe_bd *), priv->tx_bd_base, priv->dma_tx_bd); free_rx_bd: dma_free_coherent(priv->dev, - RX_BD_RING_LEN * sizeof(struct qe_bd), + RX_BD_RING_LEN * sizeof(struct qe_bd *), priv->rx_bd_base, priv->dma_rx_bd); free_uccf: ucc_fast_free(priv->uccf); @@ -688,7 +688,7 @@ static void uhdlc_memclean(struct ucc_hdlc_private *priv) if (priv->rx_bd_base) { dma_free_coherent(priv->dev, - RX_BD_RING_LEN * sizeof(struct qe_bd), + RX_BD_RING_LEN * sizeof(struct qe_bd *), priv->rx_bd_base, priv->dma_rx_bd); priv->rx_bd_base = NULL; @@ -697,7 +697,7 @@ static void uhdlc_memclean(struct ucc_hdlc_private *priv) if (priv->tx_bd_base) { dma_free_coherent(priv->dev, - TX_BD_RING_LEN * sizeof(struct qe_bd), + TX_BD_RING_LEN * sizeof(struct qe_bd *), priv->tx_bd_base, priv->dma_tx_bd); priv->tx_bd_base = NULL; diff --git a/drivers/net/xen-netback/Makefile b/drivers/net/xen-netback/Makefile index 11e02be9db1a..d49798a46b51 100644 --- a/drivers/net/xen-netback/Makefile +++ b/drivers/net/xen-netback/Makefile @@ -1,3 +1,3 @@ obj-$(CONFIG_XEN_NETDEV_BACKEND) := xen-netback.o -xen-netback-y := netback.o xenbus.o interface.o hash.o +xen-netback-y := netback.o xenbus.o interface.o hash.o rx.o diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index b38fb2cf3364..cf68149cbb55 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -91,13 +91,6 @@ struct xenvif_rx_meta { */ #define MAX_XEN_SKB_FRAGS (65536 / XEN_PAGE_SIZE + 1) -/* It's possible for an skb to have a maximal number of frags - * but still be less than MAX_BUFFER_OFFSET in size. Thus the - * worst-case number of copy operations is MAX_XEN_SKB_FRAGS per - * ring slot. - */ -#define MAX_GRANT_COPY_OPS (MAX_XEN_SKB_FRAGS * XEN_NETIF_RX_RING_SIZE) - #define NETBACK_INVALID_HANDLE -1 /* To avoid confusion, we define XEN_NETBK_LEGACY_SLOTS_MAX indicating @@ -133,6 +126,15 @@ struct xenvif_stats { unsigned long tx_frag_overflow; }; +#define COPY_BATCH_SIZE 64 + +struct xenvif_copy_state { + struct gnttab_copy op[COPY_BATCH_SIZE]; + RING_IDX idx[COPY_BATCH_SIZE]; + unsigned int num; + struct sk_buff_head *completed; +}; + struct xenvif_queue { /* Per-queue data for xenvif */ unsigned int id; /* Queue ID, 0-based */ char name[QUEUE_NAME_SIZE]; /* DEVNAME-qN */ @@ -189,12 +191,7 @@ struct xenvif_queue { /* Per-queue data for xenvif */ unsigned long last_rx_time; bool stalled; - struct gnttab_copy grant_copy_op[MAX_GRANT_COPY_OPS]; - - /* We create one meta structure per ring request we consume, so - * the maximum number is the same as the ring size. - */ - struct xenvif_rx_meta meta[XEN_NETIF_RX_RING_SIZE]; + struct xenvif_copy_state rx_copy; /* Transmit shaping: allow 'credit_bytes' every 'credit_usec'. */ unsigned long credit_bytes; @@ -260,7 +257,6 @@ struct xenvif { /* Frontend feature information. */ int gso_mask; - int gso_prefix_mask; u8 can_sg:1; u8 ip_csum:1; @@ -359,6 +355,7 @@ int xenvif_dealloc_kthread(void *data); irqreturn_t xenvif_ctrl_irq_fn(int irq, void *data); +void xenvif_rx_action(struct xenvif_queue *queue); void xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb); void xenvif_carrier_on(struct xenvif *vif); diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index fb50c6d5f6c3..74dc2bf71428 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -149,17 +149,8 @@ static u16 xenvif_select_queue(struct net_device *dev, struct sk_buff *skb, struct xenvif *vif = netdev_priv(dev); unsigned int size = vif->hash.size; - if (vif->hash.alg == XEN_NETIF_CTRL_HASH_ALGORITHM_NONE) { - u16 index = fallback(dev, skb) % dev->real_num_tx_queues; - - /* Make sure there is no hash information in the socket - * buffer otherwise it would be incorrectly forwarded - * to the frontend. - */ - skb_clear_hash(skb); - - return index; - } + if (vif->hash.alg == XEN_NETIF_CTRL_HASH_ALGORITHM_NONE) + return fallback(dev, skb) % dev->real_num_tx_queues; xenvif_set_skb_hash(vif, skb); @@ -208,6 +199,13 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev) cb = XENVIF_RX_CB(skb); cb->expires = jiffies + vif->drain_timeout; + /* If there is no hash algorithm configured then make sure there + * is no hash information in the socket buffer otherwise it + * would be incorrectly forwarded to the frontend. + */ + if (vif->hash.alg == XEN_NETIF_CTRL_HASH_ALGORITHM_NONE) + skb_clear_hash(skb); + xenvif_rx_queue_tail(queue, skb); xenvif_kick_thread(queue); @@ -319,9 +317,9 @@ static netdev_features_t xenvif_fix_features(struct net_device *dev, if (!vif->can_sg) features &= ~NETIF_F_SG; - if (~(vif->gso_mask | vif->gso_prefix_mask) & GSO_BIT(TCPV4)) + if (~(vif->gso_mask) & GSO_BIT(TCPV4)) features &= ~NETIF_F_TSO; - if (~(vif->gso_mask | vif->gso_prefix_mask) & GSO_BIT(TCPV6)) + if (~(vif->gso_mask) & GSO_BIT(TCPV6)) features &= ~NETIF_F_TSO6; if (!vif->ip_csum) features &= ~NETIF_F_IP_CSUM; @@ -467,7 +465,7 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, dev->netdev_ops = &xenvif_netdev_ops; dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | - NETIF_F_TSO | NETIF_F_TSO6; + NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_FRAGLIST; dev->features = dev->hw_features | NETIF_F_RXCSUM; dev->ethtool_ops = &xenvif_ethtool_ops; diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 3d0c989384b5..47b481095d77 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -106,13 +106,6 @@ static void push_tx_responses(struct xenvif_queue *queue); static inline int tx_work_todo(struct xenvif_queue *queue); -static struct xen_netif_rx_response *make_rx_response(struct xenvif_queue *queue, - u16 id, - s8 st, - u16 offset, - u16 size, - u16 flags); - static inline unsigned long idx_to_pfn(struct xenvif_queue *queue, u16 idx) { @@ -155,571 +148,11 @@ static inline pending_ring_idx_t pending_index(unsigned i) return i & (MAX_PENDING_REQS-1); } -static bool xenvif_rx_ring_slots_available(struct xenvif_queue *queue) -{ - RING_IDX prod, cons; - struct sk_buff *skb; - int needed; - - skb = skb_peek(&queue->rx_queue); - if (!skb) - return false; - - needed = DIV_ROUND_UP(skb->len, XEN_PAGE_SIZE); - if (skb_is_gso(skb)) - needed++; - if (skb->sw_hash) - needed++; - - do { - prod = queue->rx.sring->req_prod; - cons = queue->rx.req_cons; - - if (prod - cons >= needed) - return true; - - queue->rx.sring->req_event = prod + 1; - - /* Make sure event is visible before we check prod - * again. - */ - mb(); - } while (queue->rx.sring->req_prod != prod); - - return false; -} - -void xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb) -{ - unsigned long flags; - - spin_lock_irqsave(&queue->rx_queue.lock, flags); - - __skb_queue_tail(&queue->rx_queue, skb); - - queue->rx_queue_len += skb->len; - if (queue->rx_queue_len > queue->rx_queue_max) - netif_tx_stop_queue(netdev_get_tx_queue(queue->vif->dev, queue->id)); - - spin_unlock_irqrestore(&queue->rx_queue.lock, flags); -} - -static struct sk_buff *xenvif_rx_dequeue(struct xenvif_queue *queue) -{ - struct sk_buff *skb; - - spin_lock_irq(&queue->rx_queue.lock); - - skb = __skb_dequeue(&queue->rx_queue); - if (skb) - queue->rx_queue_len -= skb->len; - - spin_unlock_irq(&queue->rx_queue.lock); - - return skb; -} - -static void xenvif_rx_queue_maybe_wake(struct xenvif_queue *queue) -{ - spin_lock_irq(&queue->rx_queue.lock); - - if (queue->rx_queue_len < queue->rx_queue_max) - netif_tx_wake_queue(netdev_get_tx_queue(queue->vif->dev, queue->id)); - - spin_unlock_irq(&queue->rx_queue.lock); -} - - -static void xenvif_rx_queue_purge(struct xenvif_queue *queue) -{ - struct sk_buff *skb; - while ((skb = xenvif_rx_dequeue(queue)) != NULL) - kfree_skb(skb); -} - -static void xenvif_rx_queue_drop_expired(struct xenvif_queue *queue) -{ - struct sk_buff *skb; - - for(;;) { - skb = skb_peek(&queue->rx_queue); - if (!skb) - break; - if (time_before(jiffies, XENVIF_RX_CB(skb)->expires)) - break; - xenvif_rx_dequeue(queue); - kfree_skb(skb); - } -} - -struct netrx_pending_operations { - unsigned copy_prod, copy_cons; - unsigned meta_prod, meta_cons; - struct gnttab_copy *copy; - struct xenvif_rx_meta *meta; - int copy_off; - grant_ref_t copy_gref; -}; - -static struct xenvif_rx_meta *get_next_rx_buffer(struct xenvif_queue *queue, - struct netrx_pending_operations *npo) -{ - struct xenvif_rx_meta *meta; - struct xen_netif_rx_request req; - - RING_COPY_REQUEST(&queue->rx, queue->rx.req_cons++, &req); - - meta = npo->meta + npo->meta_prod++; - meta->gso_type = XEN_NETIF_GSO_TYPE_NONE; - meta->gso_size = 0; - meta->size = 0; - meta->id = req.id; - - npo->copy_off = 0; - npo->copy_gref = req.gref; - - return meta; -} - -struct gop_frag_copy { - struct xenvif_queue *queue; - struct netrx_pending_operations *npo; - struct xenvif_rx_meta *meta; - int head; - int gso_type; - int protocol; - int hash_present; - - struct page *page; -}; - -static void xenvif_setup_copy_gop(unsigned long gfn, - unsigned int offset, - unsigned int *len, - struct gop_frag_copy *info) -{ - struct gnttab_copy *copy_gop; - struct xen_page_foreign *foreign; - /* Convenient aliases */ - struct xenvif_queue *queue = info->queue; - struct netrx_pending_operations *npo = info->npo; - struct page *page = info->page; - - BUG_ON(npo->copy_off > MAX_BUFFER_OFFSET); - - if (npo->copy_off == MAX_BUFFER_OFFSET) - info->meta = get_next_rx_buffer(queue, npo); - - if (npo->copy_off + *len > MAX_BUFFER_OFFSET) - *len = MAX_BUFFER_OFFSET - npo->copy_off; - - copy_gop = npo->copy + npo->copy_prod++; - copy_gop->flags = GNTCOPY_dest_gref; - copy_gop->len = *len; - - foreign = xen_page_foreign(page); - if (foreign) { - copy_gop->source.domid = foreign->domid; - copy_gop->source.u.ref = foreign->gref; - copy_gop->flags |= GNTCOPY_source_gref; - } else { - copy_gop->source.domid = DOMID_SELF; - copy_gop->source.u.gmfn = gfn; - } - copy_gop->source.offset = offset; - - copy_gop->dest.domid = queue->vif->domid; - copy_gop->dest.offset = npo->copy_off; - copy_gop->dest.u.ref = npo->copy_gref; - - npo->copy_off += *len; - info->meta->size += *len; - - if (!info->head) - return; - - /* Leave a gap for the GSO descriptor. */ - if ((1 << info->gso_type) & queue->vif->gso_mask) - queue->rx.req_cons++; - - /* Leave a gap for the hash extra segment. */ - if (info->hash_present) - queue->rx.req_cons++; - - info->head = 0; /* There must be something in this buffer now */ -} - -static void xenvif_gop_frag_copy_grant(unsigned long gfn, - unsigned offset, - unsigned int len, - void *data) -{ - unsigned int bytes; - - while (len) { - bytes = len; - xenvif_setup_copy_gop(gfn, offset, &bytes, data); - offset += bytes; - len -= bytes; - } -} - -/* - * Set up the grant operations for this fragment. If it's a flipping - * interface, we also set up the unmap request from here. - */ -static void xenvif_gop_frag_copy(struct xenvif_queue *queue, struct sk_buff *skb, - struct netrx_pending_operations *npo, - struct page *page, unsigned long size, - unsigned long offset, int *head) -{ - struct gop_frag_copy info = { - .queue = queue, - .npo = npo, - .head = *head, - .gso_type = XEN_NETIF_GSO_TYPE_NONE, - /* xenvif_set_skb_hash() will have either set a s/w - * hash or cleared the hash depending on - * whether the the frontend wants a hash for this skb. - */ - .hash_present = skb->sw_hash, - }; - unsigned long bytes; - - if (skb_is_gso(skb)) { - if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) - info.gso_type = XEN_NETIF_GSO_TYPE_TCPV4; - else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) - info.gso_type = XEN_NETIF_GSO_TYPE_TCPV6; - } - - /* Data must not cross a page boundary. */ - BUG_ON(size + offset > PAGE_SIZE<meta + npo->meta_prod - 1; - - /* Skip unused frames from start of page */ - page += offset >> PAGE_SHIFT; - offset &= ~PAGE_MASK; - - while (size > 0) { - BUG_ON(offset >= PAGE_SIZE); - - bytes = PAGE_SIZE - offset; - if (bytes > size) - bytes = size; - - info.page = page; - gnttab_foreach_grant_in_range(page, offset, bytes, - xenvif_gop_frag_copy_grant, - &info); - size -= bytes; - offset = 0; - - /* Next page */ - if (size) { - BUG_ON(!PageCompound(page)); - page++; - } - } - - *head = info.head; -} - -/* - * Prepare an SKB to be transmitted to the frontend. - * - * This function is responsible for allocating grant operations, meta - * structures, etc. - * - * It returns the number of meta structures consumed. The number of - * ring slots used is always equal to the number of meta slots used - * plus the number of GSO descriptors used. Currently, we use either - * zero GSO descriptors (for non-GSO packets) or one descriptor (for - * frontend-side LRO). - */ -static int xenvif_gop_skb(struct sk_buff *skb, - struct netrx_pending_operations *npo, - struct xenvif_queue *queue) -{ - struct xenvif *vif = netdev_priv(skb->dev); - int nr_frags = skb_shinfo(skb)->nr_frags; - int i; - struct xen_netif_rx_request req; - struct xenvif_rx_meta *meta; - unsigned char *data; - int head = 1; - int old_meta_prod; - int gso_type; - - old_meta_prod = npo->meta_prod; - - gso_type = XEN_NETIF_GSO_TYPE_NONE; - if (skb_is_gso(skb)) { - if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) - gso_type = XEN_NETIF_GSO_TYPE_TCPV4; - else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) - gso_type = XEN_NETIF_GSO_TYPE_TCPV6; - } - - /* Set up a GSO prefix descriptor, if necessary */ - if ((1 << gso_type) & vif->gso_prefix_mask) { - RING_COPY_REQUEST(&queue->rx, queue->rx.req_cons++, &req); - meta = npo->meta + npo->meta_prod++; - meta->gso_type = gso_type; - meta->gso_size = skb_shinfo(skb)->gso_size; - meta->size = 0; - meta->id = req.id; - } - - RING_COPY_REQUEST(&queue->rx, queue->rx.req_cons++, &req); - meta = npo->meta + npo->meta_prod++; - - if ((1 << gso_type) & vif->gso_mask) { - meta->gso_type = gso_type; - meta->gso_size = skb_shinfo(skb)->gso_size; - } else { - meta->gso_type = XEN_NETIF_GSO_TYPE_NONE; - meta->gso_size = 0; - } - - meta->size = 0; - meta->id = req.id; - npo->copy_off = 0; - npo->copy_gref = req.gref; - - data = skb->data; - while (data < skb_tail_pointer(skb)) { - unsigned int offset = offset_in_page(data); - unsigned int len = PAGE_SIZE - offset; - - if (data + len > skb_tail_pointer(skb)) - len = skb_tail_pointer(skb) - data; - - xenvif_gop_frag_copy(queue, skb, npo, - virt_to_page(data), len, offset, &head); - data += len; - } - - for (i = 0; i < nr_frags; i++) { - xenvif_gop_frag_copy(queue, skb, npo, - skb_frag_page(&skb_shinfo(skb)->frags[i]), - skb_frag_size(&skb_shinfo(skb)->frags[i]), - skb_shinfo(skb)->frags[i].page_offset, - &head); - } - - return npo->meta_prod - old_meta_prod; -} - -/* - * This is a twin to xenvif_gop_skb. Assume that xenvif_gop_skb was - * used to set up the operations on the top of - * netrx_pending_operations, which have since been done. Check that - * they didn't give any errors and advance over them. - */ -static int xenvif_check_gop(struct xenvif *vif, int nr_meta_slots, - struct netrx_pending_operations *npo) -{ - struct gnttab_copy *copy_op; - int status = XEN_NETIF_RSP_OKAY; - int i; - - for (i = 0; i < nr_meta_slots; i++) { - copy_op = npo->copy + npo->copy_cons++; - if (copy_op->status != GNTST_okay) { - netdev_dbg(vif->dev, - "Bad status %d from copy to DOM%d.\n", - copy_op->status, vif->domid); - status = XEN_NETIF_RSP_ERROR; - } - } - - return status; -} - -static void xenvif_add_frag_responses(struct xenvif_queue *queue, int status, - struct xenvif_rx_meta *meta, - int nr_meta_slots) -{ - int i; - unsigned long offset; - - /* No fragments used */ - if (nr_meta_slots <= 1) - return; - - nr_meta_slots--; - - for (i = 0; i < nr_meta_slots; i++) { - int flags; - if (i == nr_meta_slots - 1) - flags = 0; - else - flags = XEN_NETRXF_more_data; - - offset = 0; - make_rx_response(queue, meta[i].id, status, offset, - meta[i].size, flags); - } -} - void xenvif_kick_thread(struct xenvif_queue *queue) { wake_up(&queue->wq); } -static void xenvif_rx_action(struct xenvif_queue *queue) -{ - struct xenvif *vif = queue->vif; - s8 status; - u16 flags; - struct xen_netif_rx_response *resp; - struct sk_buff_head rxq; - struct sk_buff *skb; - LIST_HEAD(notify); - int ret; - unsigned long offset; - bool need_to_notify = false; - - struct netrx_pending_operations npo = { - .copy = queue->grant_copy_op, - .meta = queue->meta, - }; - - skb_queue_head_init(&rxq); - - while (xenvif_rx_ring_slots_available(queue) - && (skb = xenvif_rx_dequeue(queue)) != NULL) { - queue->last_rx_time = jiffies; - - XENVIF_RX_CB(skb)->meta_slots_used = xenvif_gop_skb(skb, &npo, queue); - - __skb_queue_tail(&rxq, skb); - } - - BUG_ON(npo.meta_prod > ARRAY_SIZE(queue->meta)); - - if (!npo.copy_prod) - goto done; - - BUG_ON(npo.copy_prod > MAX_GRANT_COPY_OPS); - gnttab_batch_copy(queue->grant_copy_op, npo.copy_prod); - - while ((skb = __skb_dequeue(&rxq)) != NULL) { - struct xen_netif_extra_info *extra = NULL; - - if ((1 << queue->meta[npo.meta_cons].gso_type) & - vif->gso_prefix_mask) { - resp = RING_GET_RESPONSE(&queue->rx, - queue->rx.rsp_prod_pvt++); - - resp->flags = XEN_NETRXF_gso_prefix | XEN_NETRXF_more_data; - - resp->offset = queue->meta[npo.meta_cons].gso_size; - resp->id = queue->meta[npo.meta_cons].id; - resp->status = XENVIF_RX_CB(skb)->meta_slots_used; - - npo.meta_cons++; - XENVIF_RX_CB(skb)->meta_slots_used--; - } - - - queue->stats.tx_bytes += skb->len; - queue->stats.tx_packets++; - - status = xenvif_check_gop(vif, - XENVIF_RX_CB(skb)->meta_slots_used, - &npo); - - if (XENVIF_RX_CB(skb)->meta_slots_used == 1) - flags = 0; - else - flags = XEN_NETRXF_more_data; - - if (skb->ip_summed == CHECKSUM_PARTIAL) /* local packet? */ - flags |= XEN_NETRXF_csum_blank | XEN_NETRXF_data_validated; - else if (skb->ip_summed == CHECKSUM_UNNECESSARY) - /* remote but checksummed. */ - flags |= XEN_NETRXF_data_validated; - - offset = 0; - resp = make_rx_response(queue, queue->meta[npo.meta_cons].id, - status, offset, - queue->meta[npo.meta_cons].size, - flags); - - if ((1 << queue->meta[npo.meta_cons].gso_type) & - vif->gso_mask) { - extra = (struct xen_netif_extra_info *) - RING_GET_RESPONSE(&queue->rx, - queue->rx.rsp_prod_pvt++); - - resp->flags |= XEN_NETRXF_extra_info; - - extra->u.gso.type = queue->meta[npo.meta_cons].gso_type; - extra->u.gso.size = queue->meta[npo.meta_cons].gso_size; - extra->u.gso.pad = 0; - extra->u.gso.features = 0; - - extra->type = XEN_NETIF_EXTRA_TYPE_GSO; - extra->flags = 0; - } - - if (skb->sw_hash) { - /* Since the skb got here via xenvif_select_queue() - * we know that the hash has been re-calculated - * according to a configuration set by the frontend - * and therefore we know that it is legitimate to - * pass it to the frontend. - */ - if (resp->flags & XEN_NETRXF_extra_info) - extra->flags |= XEN_NETIF_EXTRA_FLAG_MORE; - else - resp->flags |= XEN_NETRXF_extra_info; - - extra = (struct xen_netif_extra_info *) - RING_GET_RESPONSE(&queue->rx, - queue->rx.rsp_prod_pvt++); - - extra->u.hash.algorithm = - XEN_NETIF_CTRL_HASH_ALGORITHM_TOEPLITZ; - - if (skb->l4_hash) - extra->u.hash.type = - skb->protocol == htons(ETH_P_IP) ? - _XEN_NETIF_CTRL_HASH_TYPE_IPV4_TCP : - _XEN_NETIF_CTRL_HASH_TYPE_IPV6_TCP; - else - extra->u.hash.type = - skb->protocol == htons(ETH_P_IP) ? - _XEN_NETIF_CTRL_HASH_TYPE_IPV4 : - _XEN_NETIF_CTRL_HASH_TYPE_IPV6; - - *(uint32_t *)extra->u.hash.value = - skb_get_hash_raw(skb); - - extra->type = XEN_NETIF_EXTRA_TYPE_HASH; - extra->flags = 0; - } - - xenvif_add_frag_responses(queue, status, - queue->meta + npo.meta_cons + 1, - XENVIF_RX_CB(skb)->meta_slots_used); - - RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->rx, ret); - - need_to_notify |= !!ret; - - npo.meta_cons += XENVIF_RX_CB(skb)->meta_slots_used; - dev_kfree_skb(skb); - } - -done: - if (need_to_notify) - notify_remote_via_irq(queue->rx_irq); -} - void xenvif_napi_schedule_or_enable_events(struct xenvif_queue *queue) { int more_to_do; @@ -1951,29 +1384,6 @@ static void push_tx_responses(struct xenvif_queue *queue) notify_remote_via_irq(queue->tx_irq); } -static struct xen_netif_rx_response *make_rx_response(struct xenvif_queue *queue, - u16 id, - s8 st, - u16 offset, - u16 size, - u16 flags) -{ - RING_IDX i = queue->rx.rsp_prod_pvt; - struct xen_netif_rx_response *resp; - - resp = RING_GET_RESPONSE(&queue->rx, i); - resp->offset = offset; - resp->flags = flags; - resp->id = id; - resp->status = (s16)size; - if (st < 0) - resp->status = (s16)st; - - queue->rx.rsp_prod_pvt = ++i; - - return resp; -} - void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx) { int ret; @@ -2055,170 +1465,6 @@ err: return err; } -static void xenvif_queue_carrier_off(struct xenvif_queue *queue) -{ - struct xenvif *vif = queue->vif; - - queue->stalled = true; - - /* At least one queue has stalled? Disable the carrier. */ - spin_lock(&vif->lock); - if (vif->stalled_queues++ == 0) { - netdev_info(vif->dev, "Guest Rx stalled"); - netif_carrier_off(vif->dev); - } - spin_unlock(&vif->lock); -} - -static void xenvif_queue_carrier_on(struct xenvif_queue *queue) -{ - struct xenvif *vif = queue->vif; - - queue->last_rx_time = jiffies; /* Reset Rx stall detection. */ - queue->stalled = false; - - /* All queues are ready? Enable the carrier. */ - spin_lock(&vif->lock); - if (--vif->stalled_queues == 0) { - netdev_info(vif->dev, "Guest Rx ready"); - netif_carrier_on(vif->dev); - } - spin_unlock(&vif->lock); -} - -static bool xenvif_rx_queue_stalled(struct xenvif_queue *queue) -{ - RING_IDX prod, cons; - - prod = queue->rx.sring->req_prod; - cons = queue->rx.req_cons; - - return !queue->stalled && prod - cons < 1 - && time_after(jiffies, - queue->last_rx_time + queue->vif->stall_timeout); -} - -static bool xenvif_rx_queue_ready(struct xenvif_queue *queue) -{ - RING_IDX prod, cons; - - prod = queue->rx.sring->req_prod; - cons = queue->rx.req_cons; - - return queue->stalled && prod - cons >= 1; -} - -static bool xenvif_have_rx_work(struct xenvif_queue *queue) -{ - return xenvif_rx_ring_slots_available(queue) - || (queue->vif->stall_timeout && - (xenvif_rx_queue_stalled(queue) - || xenvif_rx_queue_ready(queue))) - || kthread_should_stop() - || queue->vif->disabled; -} - -static long xenvif_rx_queue_timeout(struct xenvif_queue *queue) -{ - struct sk_buff *skb; - long timeout; - - skb = skb_peek(&queue->rx_queue); - if (!skb) - return MAX_SCHEDULE_TIMEOUT; - - timeout = XENVIF_RX_CB(skb)->expires - jiffies; - return timeout < 0 ? 0 : timeout; -} - -/* Wait until the guest Rx thread has work. - * - * The timeout needs to be adjusted based on the current head of the - * queue (and not just the head at the beginning). In particular, if - * the queue is initially empty an infinite timeout is used and this - * needs to be reduced when a skb is queued. - * - * This cannot be done with wait_event_timeout() because it only - * calculates the timeout once. - */ -static void xenvif_wait_for_rx_work(struct xenvif_queue *queue) -{ - DEFINE_WAIT(wait); - - if (xenvif_have_rx_work(queue)) - return; - - for (;;) { - long ret; - - prepare_to_wait(&queue->wq, &wait, TASK_INTERRUPTIBLE); - if (xenvif_have_rx_work(queue)) - break; - ret = schedule_timeout(xenvif_rx_queue_timeout(queue)); - if (!ret) - break; - } - finish_wait(&queue->wq, &wait); -} - -int xenvif_kthread_guest_rx(void *data) -{ - struct xenvif_queue *queue = data; - struct xenvif *vif = queue->vif; - - if (!vif->stall_timeout) - xenvif_queue_carrier_on(queue); - - for (;;) { - xenvif_wait_for_rx_work(queue); - - if (kthread_should_stop()) - break; - - /* This frontend is found to be rogue, disable it in - * kthread context. Currently this is only set when - * netback finds out frontend sends malformed packet, - * but we cannot disable the interface in softirq - * context so we defer it here, if this thread is - * associated with queue 0. - */ - if (unlikely(vif->disabled && queue->id == 0)) { - xenvif_carrier_off(vif); - break; - } - - if (!skb_queue_empty(&queue->rx_queue)) - xenvif_rx_action(queue); - - /* If the guest hasn't provided any Rx slots for a - * while it's probably not responsive, drop the - * carrier so packets are dropped earlier. - */ - if (vif->stall_timeout) { - if (xenvif_rx_queue_stalled(queue)) - xenvif_queue_carrier_off(queue); - else if (xenvif_rx_queue_ready(queue)) - xenvif_queue_carrier_on(queue); - } - - /* Queued packets may have foreign pages from other - * domains. These cannot be queued indefinitely as - * this would starve guests of grant refs and transmit - * slots. - */ - xenvif_rx_queue_drop_expired(queue); - - xenvif_rx_queue_maybe_wake(queue); - - cond_resched(); - } - - /* Bin any remaining skbs */ - xenvif_rx_queue_purge(queue); - - return 0; -} - static bool xenvif_dealloc_kthread_should_stop(struct xenvif_queue *queue) { /* Dealloc thread must remain running until all inflight diff --git a/drivers/net/xen-netback/rx.c b/drivers/net/xen-netback/rx.c new file mode 100644 index 000000000000..8e9ade6ccf18 --- /dev/null +++ b/drivers/net/xen-netback/rx.c @@ -0,0 +1,629 @@ +/* + * Copyright (c) 2016 Citrix Systems Inc. + * Copyright (c) 2002-2005, K A Fraser + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation; or, when distributed + * separately from the Linux kernel or incorporated into other + * software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ +#include "common.h" + +#include + +#include +#include + +static bool xenvif_rx_ring_slots_available(struct xenvif_queue *queue) +{ + RING_IDX prod, cons; + struct sk_buff *skb; + int needed; + + skb = skb_peek(&queue->rx_queue); + if (!skb) + return false; + + needed = DIV_ROUND_UP(skb->len, XEN_PAGE_SIZE); + if (skb_is_gso(skb)) + needed++; + if (skb->sw_hash) + needed++; + + do { + prod = queue->rx.sring->req_prod; + cons = queue->rx.req_cons; + + if (prod - cons >= needed) + return true; + + queue->rx.sring->req_event = prod + 1; + + /* Make sure event is visible before we check prod + * again. + */ + mb(); + } while (queue->rx.sring->req_prod != prod); + + return false; +} + +void xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb) +{ + unsigned long flags; + + spin_lock_irqsave(&queue->rx_queue.lock, flags); + + __skb_queue_tail(&queue->rx_queue, skb); + + queue->rx_queue_len += skb->len; + if (queue->rx_queue_len > queue->rx_queue_max) { + struct net_device *dev = queue->vif->dev; + + netif_tx_stop_queue(netdev_get_tx_queue(dev, queue->id)); + } + + spin_unlock_irqrestore(&queue->rx_queue.lock, flags); +} + +static struct sk_buff *xenvif_rx_dequeue(struct xenvif_queue *queue) +{ + struct sk_buff *skb; + + spin_lock_irq(&queue->rx_queue.lock); + + skb = __skb_dequeue(&queue->rx_queue); + if (skb) { + queue->rx_queue_len -= skb->len; + if (queue->rx_queue_len < queue->rx_queue_max) { + struct netdev_queue *txq; + + txq = netdev_get_tx_queue(queue->vif->dev, queue->id); + netif_tx_wake_queue(txq); + } + } + + spin_unlock_irq(&queue->rx_queue.lock); + + return skb; +} + +static void xenvif_rx_queue_purge(struct xenvif_queue *queue) +{ + struct sk_buff *skb; + + while ((skb = xenvif_rx_dequeue(queue)) != NULL) + kfree_skb(skb); +} + +static void xenvif_rx_queue_drop_expired(struct xenvif_queue *queue) +{ + struct sk_buff *skb; + + for (;;) { + skb = skb_peek(&queue->rx_queue); + if (!skb) + break; + if (time_before(jiffies, XENVIF_RX_CB(skb)->expires)) + break; + xenvif_rx_dequeue(queue); + kfree_skb(skb); + } +} + +static void xenvif_rx_copy_flush(struct xenvif_queue *queue) +{ + unsigned int i; + int notify; + + gnttab_batch_copy(queue->rx_copy.op, queue->rx_copy.num); + + for (i = 0; i < queue->rx_copy.num; i++) { + struct gnttab_copy *op; + + op = &queue->rx_copy.op[i]; + + /* If the copy failed, overwrite the status field in + * the corresponding response. + */ + if (unlikely(op->status != GNTST_okay)) { + struct xen_netif_rx_response *rsp; + + rsp = RING_GET_RESPONSE(&queue->rx, + queue->rx_copy.idx[i]); + rsp->status = op->status; + } + } + + queue->rx_copy.num = 0; + + /* Push responses for all completed packets. */ + RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->rx, notify); + if (notify) + notify_remote_via_irq(queue->rx_irq); + + __skb_queue_purge(queue->rx_copy.completed); +} + +static void xenvif_rx_copy_add(struct xenvif_queue *queue, + struct xen_netif_rx_request *req, + unsigned int offset, void *data, size_t len) +{ + struct gnttab_copy *op; + struct page *page; + struct xen_page_foreign *foreign; + + if (queue->rx_copy.num == COPY_BATCH_SIZE) + xenvif_rx_copy_flush(queue); + + op = &queue->rx_copy.op[queue->rx_copy.num]; + + page = virt_to_page(data); + + op->flags = GNTCOPY_dest_gref; + + foreign = xen_page_foreign(page); + if (foreign) { + op->source.domid = foreign->domid; + op->source.u.ref = foreign->gref; + op->flags |= GNTCOPY_source_gref; + } else { + op->source.u.gmfn = virt_to_gfn(data); + op->source.domid = DOMID_SELF; + } + + op->source.offset = xen_offset_in_page(data); + op->dest.u.ref = req->gref; + op->dest.domid = queue->vif->domid; + op->dest.offset = offset; + op->len = len; + + queue->rx_copy.idx[queue->rx_copy.num] = queue->rx.req_cons; + queue->rx_copy.num++; +} + +static unsigned int xenvif_gso_type(struct sk_buff *skb) +{ + if (skb_is_gso(skb)) { + if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) + return XEN_NETIF_GSO_TYPE_TCPV4; + else + return XEN_NETIF_GSO_TYPE_TCPV6; + } + return XEN_NETIF_GSO_TYPE_NONE; +} + +struct xenvif_pkt_state { + struct sk_buff *skb; + size_t remaining_len; + struct sk_buff *frag_iter; + int frag; /* frag == -1 => frag_iter->head */ + unsigned int frag_offset; + struct xen_netif_extra_info extras[XEN_NETIF_EXTRA_TYPE_MAX - 1]; + unsigned int extra_count; + unsigned int slot; +}; + +static void xenvif_rx_next_skb(struct xenvif_queue *queue, + struct xenvif_pkt_state *pkt) +{ + struct sk_buff *skb; + unsigned int gso_type; + + skb = xenvif_rx_dequeue(queue); + + queue->stats.tx_bytes += skb->len; + queue->stats.tx_packets++; + + /* Reset packet state. */ + memset(pkt, 0, sizeof(struct xenvif_pkt_state)); + + pkt->skb = skb; + pkt->frag_iter = skb; + pkt->remaining_len = skb->len; + pkt->frag = -1; + + gso_type = xenvif_gso_type(skb); + if ((1 << gso_type) & queue->vif->gso_mask) { + struct xen_netif_extra_info *extra; + + extra = &pkt->extras[XEN_NETIF_EXTRA_TYPE_GSO - 1]; + + extra->u.gso.type = gso_type; + extra->u.gso.size = skb_shinfo(skb)->gso_size; + extra->u.gso.pad = 0; + extra->u.gso.features = 0; + extra->type = XEN_NETIF_EXTRA_TYPE_GSO; + extra->flags = 0; + + pkt->extra_count++; + } + + if (skb->sw_hash) { + struct xen_netif_extra_info *extra; + + extra = &pkt->extras[XEN_NETIF_EXTRA_TYPE_HASH - 1]; + + extra->u.hash.algorithm = + XEN_NETIF_CTRL_HASH_ALGORITHM_TOEPLITZ; + + if (skb->l4_hash) + extra->u.hash.type = + skb->protocol == htons(ETH_P_IP) ? + _XEN_NETIF_CTRL_HASH_TYPE_IPV4_TCP : + _XEN_NETIF_CTRL_HASH_TYPE_IPV6_TCP; + else + extra->u.hash.type = + skb->protocol == htons(ETH_P_IP) ? + _XEN_NETIF_CTRL_HASH_TYPE_IPV4 : + _XEN_NETIF_CTRL_HASH_TYPE_IPV6; + + *(uint32_t *)extra->u.hash.value = skb_get_hash_raw(skb); + + extra->type = XEN_NETIF_EXTRA_TYPE_HASH; + extra->flags = 0; + + pkt->extra_count++; + } +} + +static void xenvif_rx_complete(struct xenvif_queue *queue, + struct xenvif_pkt_state *pkt) +{ + /* All responses are ready to be pushed. */ + queue->rx.rsp_prod_pvt = queue->rx.req_cons; + + __skb_queue_tail(queue->rx_copy.completed, pkt->skb); +} + +static void xenvif_rx_next_frag(struct xenvif_pkt_state *pkt) +{ + struct sk_buff *frag_iter = pkt->frag_iter; + unsigned int nr_frags = skb_shinfo(frag_iter)->nr_frags; + + pkt->frag++; + pkt->frag_offset = 0; + + if (pkt->frag >= nr_frags) { + if (frag_iter == pkt->skb) + pkt->frag_iter = skb_shinfo(frag_iter)->frag_list; + else + pkt->frag_iter = frag_iter->next; + + pkt->frag = -1; + } +} + +static void xenvif_rx_next_chunk(struct xenvif_queue *queue, + struct xenvif_pkt_state *pkt, + unsigned int offset, void **data, + size_t *len) +{ + struct sk_buff *frag_iter = pkt->frag_iter; + void *frag_data; + size_t frag_len, chunk_len; + + BUG_ON(!frag_iter); + + if (pkt->frag == -1) { + frag_data = frag_iter->data; + frag_len = skb_headlen(frag_iter); + } else { + skb_frag_t *frag = &skb_shinfo(frag_iter)->frags[pkt->frag]; + + frag_data = skb_frag_address(frag); + frag_len = skb_frag_size(frag); + } + + frag_data += pkt->frag_offset; + frag_len -= pkt->frag_offset; + + chunk_len = min(frag_len, XEN_PAGE_SIZE - offset); + chunk_len = min(chunk_len, + XEN_PAGE_SIZE - xen_offset_in_page(frag_data)); + + pkt->frag_offset += chunk_len; + + /* Advance to next frag? */ + if (frag_len == chunk_len) + xenvif_rx_next_frag(pkt); + + *data = frag_data; + *len = chunk_len; +} + +static void xenvif_rx_data_slot(struct xenvif_queue *queue, + struct xenvif_pkt_state *pkt, + struct xen_netif_rx_request *req, + struct xen_netif_rx_response *rsp) +{ + unsigned int offset = 0; + unsigned int flags; + + do { + size_t len; + void *data; + + xenvif_rx_next_chunk(queue, pkt, offset, &data, &len); + xenvif_rx_copy_add(queue, req, offset, data, len); + + offset += len; + pkt->remaining_len -= len; + + } while (offset < XEN_PAGE_SIZE && pkt->remaining_len > 0); + + if (pkt->remaining_len > 0) + flags = XEN_NETRXF_more_data; + else + flags = 0; + + if (pkt->slot == 0) { + struct sk_buff *skb = pkt->skb; + + if (skb->ip_summed == CHECKSUM_PARTIAL) + flags |= XEN_NETRXF_csum_blank | + XEN_NETRXF_data_validated; + else if (skb->ip_summed == CHECKSUM_UNNECESSARY) + flags |= XEN_NETRXF_data_validated; + + if (pkt->extra_count != 0) + flags |= XEN_NETRXF_extra_info; + } + + rsp->offset = 0; + rsp->flags = flags; + rsp->id = req->id; + rsp->status = (s16)offset; +} + +static void xenvif_rx_extra_slot(struct xenvif_queue *queue, + struct xenvif_pkt_state *pkt, + struct xen_netif_rx_request *req, + struct xen_netif_rx_response *rsp) +{ + struct xen_netif_extra_info *extra = (void *)rsp; + unsigned int i; + + pkt->extra_count--; + + for (i = 0; i < ARRAY_SIZE(pkt->extras); i++) { + if (pkt->extras[i].type) { + *extra = pkt->extras[i]; + + if (pkt->extra_count != 0) + extra->flags |= XEN_NETIF_EXTRA_FLAG_MORE; + + pkt->extras[i].type = 0; + return; + } + } + BUG(); +} + +void xenvif_rx_skb(struct xenvif_queue *queue) +{ + struct xenvif_pkt_state pkt; + + xenvif_rx_next_skb(queue, &pkt); + + do { + struct xen_netif_rx_request *req; + struct xen_netif_rx_response *rsp; + + req = RING_GET_REQUEST(&queue->rx, queue->rx.req_cons); + rsp = RING_GET_RESPONSE(&queue->rx, queue->rx.req_cons); + + /* Extras must go after the first data slot */ + if (pkt.slot != 0 && pkt.extra_count != 0) + xenvif_rx_extra_slot(queue, &pkt, req, rsp); + else + xenvif_rx_data_slot(queue, &pkt, req, rsp); + + queue->rx.req_cons++; + pkt.slot++; + } while (pkt.remaining_len > 0 || pkt.extra_count != 0); + + xenvif_rx_complete(queue, &pkt); +} + +#define RX_BATCH_SIZE 64 + +void xenvif_rx_action(struct xenvif_queue *queue) +{ + struct sk_buff_head completed_skbs; + unsigned int work_done = 0; + + __skb_queue_head_init(&completed_skbs); + queue->rx_copy.completed = &completed_skbs; + + while (xenvif_rx_ring_slots_available(queue) && + work_done < RX_BATCH_SIZE) { + xenvif_rx_skb(queue); + work_done++; + } + + /* Flush any pending copies and complete all skbs. */ + xenvif_rx_copy_flush(queue); +} + +static bool xenvif_rx_queue_stalled(struct xenvif_queue *queue) +{ + RING_IDX prod, cons; + + prod = queue->rx.sring->req_prod; + cons = queue->rx.req_cons; + + return !queue->stalled && + prod - cons < 1 && + time_after(jiffies, + queue->last_rx_time + queue->vif->stall_timeout); +} + +static bool xenvif_rx_queue_ready(struct xenvif_queue *queue) +{ + RING_IDX prod, cons; + + prod = queue->rx.sring->req_prod; + cons = queue->rx.req_cons; + + return queue->stalled && prod - cons >= 1; +} + +static bool xenvif_have_rx_work(struct xenvif_queue *queue) +{ + return xenvif_rx_ring_slots_available(queue) || + (queue->vif->stall_timeout && + (xenvif_rx_queue_stalled(queue) || + xenvif_rx_queue_ready(queue))) || + kthread_should_stop() || + queue->vif->disabled; +} + +static long xenvif_rx_queue_timeout(struct xenvif_queue *queue) +{ + struct sk_buff *skb; + long timeout; + + skb = skb_peek(&queue->rx_queue); + if (!skb) + return MAX_SCHEDULE_TIMEOUT; + + timeout = XENVIF_RX_CB(skb)->expires - jiffies; + return timeout < 0 ? 0 : timeout; +} + +/* Wait until the guest Rx thread has work. + * + * The timeout needs to be adjusted based on the current head of the + * queue (and not just the head at the beginning). In particular, if + * the queue is initially empty an infinite timeout is used and this + * needs to be reduced when a skb is queued. + * + * This cannot be done with wait_event_timeout() because it only + * calculates the timeout once. + */ +static void xenvif_wait_for_rx_work(struct xenvif_queue *queue) +{ + DEFINE_WAIT(wait); + + if (xenvif_have_rx_work(queue)) + return; + + for (;;) { + long ret; + + prepare_to_wait(&queue->wq, &wait, TASK_INTERRUPTIBLE); + if (xenvif_have_rx_work(queue)) + break; + ret = schedule_timeout(xenvif_rx_queue_timeout(queue)); + if (!ret) + break; + } + finish_wait(&queue->wq, &wait); +} + +static void xenvif_queue_carrier_off(struct xenvif_queue *queue) +{ + struct xenvif *vif = queue->vif; + + queue->stalled = true; + + /* At least one queue has stalled? Disable the carrier. */ + spin_lock(&vif->lock); + if (vif->stalled_queues++ == 0) { + netdev_info(vif->dev, "Guest Rx stalled"); + netif_carrier_off(vif->dev); + } + spin_unlock(&vif->lock); +} + +static void xenvif_queue_carrier_on(struct xenvif_queue *queue) +{ + struct xenvif *vif = queue->vif; + + queue->last_rx_time = jiffies; /* Reset Rx stall detection. */ + queue->stalled = false; + + /* All queues are ready? Enable the carrier. */ + spin_lock(&vif->lock); + if (--vif->stalled_queues == 0) { + netdev_info(vif->dev, "Guest Rx ready"); + netif_carrier_on(vif->dev); + } + spin_unlock(&vif->lock); +} + +int xenvif_kthread_guest_rx(void *data) +{ + struct xenvif_queue *queue = data; + struct xenvif *vif = queue->vif; + + if (!vif->stall_timeout) + xenvif_queue_carrier_on(queue); + + for (;;) { + xenvif_wait_for_rx_work(queue); + + if (kthread_should_stop()) + break; + + /* This frontend is found to be rogue, disable it in + * kthread context. Currently this is only set when + * netback finds out frontend sends malformed packet, + * but we cannot disable the interface in softirq + * context so we defer it here, if this thread is + * associated with queue 0. + */ + if (unlikely(vif->disabled && queue->id == 0)) { + xenvif_carrier_off(vif); + break; + } + + if (!skb_queue_empty(&queue->rx_queue)) + xenvif_rx_action(queue); + + /* If the guest hasn't provided any Rx slots for a + * while it's probably not responsive, drop the + * carrier so packets are dropped earlier. + */ + if (vif->stall_timeout) { + if (xenvif_rx_queue_stalled(queue)) + xenvif_queue_carrier_off(queue); + else if (xenvif_rx_queue_ready(queue)) + xenvif_queue_carrier_on(queue); + } + + /* Queued packets may have foreign pages from other + * domains. These cannot be queued indefinitely as + * this would starve guests of grant refs and transmit + * slots. + */ + xenvif_rx_queue_drop_expired(queue); + + cond_resched(); + } + + /* Bin any remaining skbs */ + xenvif_rx_queue_purge(queue); + + return 0; +} diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index daf4c7867102..7056404e3cb8 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -1135,7 +1135,6 @@ static int read_xenbus_vif_flags(struct backend_info *be) vif->can_sg = !!val; vif->gso_mask = 0; - vif->gso_prefix_mask = 0; if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv4", "%d", &val) < 0) @@ -1143,32 +1142,12 @@ static int read_xenbus_vif_flags(struct backend_info *be) if (val) vif->gso_mask |= GSO_BIT(TCPV4); - if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv4-prefix", - "%d", &val) < 0) - val = 0; - if (val) - vif->gso_prefix_mask |= GSO_BIT(TCPV4); - if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv6", "%d", &val) < 0) val = 0; if (val) vif->gso_mask |= GSO_BIT(TCPV6); - if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv6-prefix", - "%d", &val) < 0) - val = 0; - if (val) - vif->gso_prefix_mask |= GSO_BIT(TCPV6); - - if (vif->gso_mask & vif->gso_prefix_mask) { - xenbus_dev_fatal(dev, err, - "%s: gso and gso prefix flags are not " - "mutually exclusive", - dev->otherend); - return -EOPNOTSUPP; - } - if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-no-csum-offload", "%d", &val) < 0) val = 0; diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 59bdaa7527b6..477928b25940 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -418,7 +418,7 @@ static void afs_deliver_to_call(struct afs_call *call) &call->abort_code); if (ret == -EINPROGRESS || ret == -EAGAIN) return; - if (ret == 1) { + if (ret == 1 || ret < 0) { call->state = AFS_CALL_COMPLETE; goto done; } diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 174f43f43aff..c05216a8fbac 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -245,7 +245,7 @@ static inline struct team_port *team_get_port_by_index(struct team *team, return NULL; } -static inline int team_num_to_port_index(struct team *team, int num) +static inline int team_num_to_port_index(struct team *team, unsigned int num) { int en_port_count = ACCESS_ONCE(team->en_port_count); diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index c8135680c43e..e2288421fe6b 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -21,8 +21,6 @@ SOFTWARE IS DISCLAIMED. */ -#include - #include #include #include @@ -973,33 +971,58 @@ void __hci_req_enable_advertising(struct hci_request *req) static u8 append_local_name(struct hci_dev *hdev, u8 *ptr, u8 ad_len) { - size_t name_len; + size_t complete_len; + size_t short_len; int max_len; max_len = HCI_MAX_AD_LENGTH - ad_len - 2; - name_len = strlen(hdev->dev_name); - if (name_len > 0 && max_len > 0) { + complete_len = strlen(hdev->dev_name); + short_len = strlen(hdev->short_name); - if (name_len > max_len) { - name_len = max_len; - ptr[1] = EIR_NAME_SHORT; - } else - ptr[1] = EIR_NAME_COMPLETE; + /* no space left for name */ + if (max_len < 1) + return ad_len; - ptr[0] = name_len + 1; + /* no name set */ + if (!complete_len) + return ad_len; - memcpy(ptr + 2, hdev->dev_name, name_len); + /* complete name fits and is eq to max short name len or smaller */ + if (complete_len <= max_len && + complete_len <= HCI_MAX_SHORT_NAME_LENGTH) { + return eir_append_data(ptr, ad_len, EIR_NAME_COMPLETE, + hdev->dev_name, complete_len); + } - ad_len += (name_len + 2); - ptr += (name_len + 2); + /* short name set and fits */ + if (short_len && short_len <= max_len) { + return eir_append_data(ptr, ad_len, EIR_NAME_SHORT, + hdev->short_name, short_len); + } + + /* no short name set so shorten complete name */ + if (!short_len) { + return eir_append_data(ptr, ad_len, EIR_NAME_SHORT, + hdev->dev_name, max_len); } return ad_len; } +static u8 append_appearance(struct hci_dev *hdev, u8 *ptr, u8 ad_len) +{ + return eir_append_le16(ptr, ad_len, EIR_APPEARANCE, hdev->appearance); +} + static u8 create_default_scan_rsp_data(struct hci_dev *hdev, u8 *ptr) { - return append_local_name(hdev, ptr, 0); + u8 scan_rsp_len = 0; + + if (hdev->appearance) { + scan_rsp_len = append_appearance(hdev, ptr, scan_rsp_len); + } + + return append_local_name(hdev, ptr, scan_rsp_len); } static u8 create_instance_scan_rsp_data(struct hci_dev *hdev, u8 instance, @@ -1016,18 +1039,13 @@ static u8 create_instance_scan_rsp_data(struct hci_dev *hdev, u8 instance, instance_flags = adv_instance->flags; if ((instance_flags & MGMT_ADV_FLAG_APPEARANCE) && hdev->appearance) { - ptr[0] = 3; - ptr[1] = EIR_APPEARANCE; - put_unaligned_le16(hdev->appearance, ptr + 2); - scan_rsp_len += 4; - ptr += 4; + scan_rsp_len = append_appearance(hdev, ptr, scan_rsp_len); } - memcpy(ptr, adv_instance->scan_rsp_data, + memcpy(&ptr[scan_rsp_len], adv_instance->scan_rsp_data, adv_instance->scan_rsp_len); scan_rsp_len += adv_instance->scan_rsp_len; - ptr += adv_instance->scan_rsp_len; if (instance_flags & MGMT_ADV_FLAG_LOCAL_NAME) scan_rsp_len = append_local_name(hdev, ptr, scan_rsp_len); diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h index ac1e11006f38..6b06629245a8 100644 --- a/net/bluetooth/hci_request.h +++ b/net/bluetooth/hci_request.h @@ -20,6 +20,8 @@ SOFTWARE IS DISCLAIMED. */ +#include + #define hci_req_sync_lock(hdev) mutex_lock(&hdev->req_lock) #define hci_req_sync_unlock(hdev) mutex_unlock(&hdev->req_lock) @@ -103,3 +105,24 @@ static inline void hci_update_background_scan(struct hci_dev *hdev) void hci_request_setup(struct hci_dev *hdev); void hci_request_cancel_all(struct hci_dev *hdev); + +static inline u16 eir_append_data(u8 *eir, u16 eir_len, u8 type, + u8 *data, u8 data_len) +{ + eir[eir_len++] = sizeof(type) + data_len; + eir[eir_len++] = type; + memcpy(&eir[eir_len], data, data_len); + eir_len += data_len; + + return eir_len; +} + +static inline u16 eir_append_le16(u8 *eir, u16 eir_len, u8 type, u16 data) +{ + eir[eir_len++] = sizeof(type) + sizeof(data); + eir[eir_len++] = type; + put_unaligned_le16(data, &eir[eir_len]); + eir_len += sizeof(data); + + return eir_len; +} diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 19b8a5e9420d..736038085feb 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -867,27 +867,6 @@ static int read_controller_info(struct sock *sk, struct hci_dev *hdev, sizeof(rp)); } -static inline u16 eir_append_data(u8 *eir, u16 eir_len, u8 type, u8 *data, - u8 data_len) -{ - eir[eir_len++] = sizeof(type) + data_len; - eir[eir_len++] = type; - memcpy(&eir[eir_len], data, data_len); - eir_len += data_len; - - return eir_len; -} - -static inline u16 eir_append_le16(u8 *eir, u16 eir_len, u8 type, u16 data) -{ - eir[eir_len++] = sizeof(type) + sizeof(data); - eir[eir_len++] = type; - put_unaligned_le16(data, &eir[eir_len]); - eir_len += sizeof(data); - - return eir_len; -} - static u16 append_eir_data_to_buf(struct hci_dev *hdev, u8 *eir) { u16 eir_len = 0; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index cbd9343751a2..d8983e15f859 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5729,6 +5729,7 @@ int addrconf_sysctl_ignore_routes_with_linkdown(struct ctl_table *ctl, return ret; } +static int minus_one = -1; static const int one = 1; static const int two_five_five = 255; @@ -5789,7 +5790,8 @@ static const struct ctl_table addrconf_sysctl[] = { .data = &ipv6_devconf.rtr_solicits, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &minus_one, }, { .procname = "router_solicitation_interval", diff --git a/net/netfilter/core.c b/net/netfilter/core.c index c9d90eb64046..fcb5d1df11e9 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -65,49 +65,24 @@ static DEFINE_MUTEX(nf_hook_mutex); #define nf_entry_dereference(e) \ rcu_dereference_protected(e, lockdep_is_held(&nf_hook_mutex)) -static struct nf_hook_entry *nf_hook_entry_head(struct net *net, - const struct nf_hook_ops *reg) +static struct nf_hook_entry __rcu **nf_hook_entry_head(struct net *net, const struct nf_hook_ops *reg) { - struct nf_hook_entry *hook_head = NULL; - if (reg->pf != NFPROTO_NETDEV) - hook_head = nf_entry_dereference(net->nf.hooks[reg->pf] - [reg->hooknum]); - else if (reg->hooknum == NF_NETDEV_INGRESS) { -#ifdef CONFIG_NETFILTER_INGRESS - if (reg->dev && dev_net(reg->dev) == net) - hook_head = - nf_entry_dereference( - reg->dev->nf_hooks_ingress); -#endif - } - return hook_head; -} + return net->nf.hooks[reg->pf]+reg->hooknum; -/* must hold nf_hook_mutex */ -static void nf_set_hooks_head(struct net *net, const struct nf_hook_ops *reg, - struct nf_hook_entry *entry) -{ - switch (reg->pf) { - case NFPROTO_NETDEV: #ifdef CONFIG_NETFILTER_INGRESS - /* We already checked in nf_register_net_hook() that this is - * used from ingress. - */ - rcu_assign_pointer(reg->dev->nf_hooks_ingress, entry); -#endif - break; - default: - rcu_assign_pointer(net->nf.hooks[reg->pf][reg->hooknum], - entry); - break; + if (reg->hooknum == NF_NETDEV_INGRESS) { + if (reg->dev && dev_net(reg->dev) == net) + return ®->dev->nf_hooks_ingress; } +#endif + return NULL; } int nf_register_net_hook(struct net *net, const struct nf_hook_ops *reg) { - struct nf_hook_entry *hooks_entry; - struct nf_hook_entry *entry; + struct nf_hook_entry __rcu **pp; + struct nf_hook_entry *entry, *p; if (reg->pf == NFPROTO_NETDEV) { #ifndef CONFIG_NETFILTER_INGRESS @@ -119,6 +94,10 @@ int nf_register_net_hook(struct net *net, const struct nf_hook_ops *reg) return -EINVAL; } + pp = nf_hook_entry_head(net, reg); + if (!pp) + return -EINVAL; + entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return -ENOMEM; @@ -128,26 +107,15 @@ int nf_register_net_hook(struct net *net, const struct nf_hook_ops *reg) entry->next = NULL; mutex_lock(&nf_hook_mutex); - hooks_entry = nf_hook_entry_head(net, reg); - if (hooks_entry && hooks_entry->orig_ops->priority > reg->priority) { - /* This is the case where we need to insert at the head */ - entry->next = hooks_entry; - hooks_entry = NULL; - } - - while (hooks_entry && - reg->priority >= hooks_entry->orig_ops->priority && - nf_entry_dereference(hooks_entry->next)) { - hooks_entry = nf_entry_dereference(hooks_entry->next); - } - - if (hooks_entry) { - entry->next = nf_entry_dereference(hooks_entry->next); - rcu_assign_pointer(hooks_entry->next, entry); - } else { - nf_set_hooks_head(net, reg, entry); + /* Find the spot in the list */ + while ((p = nf_entry_dereference(*pp)) != NULL) { + if (reg->priority < p->orig_ops->priority) + break; + pp = &p->next; } + rcu_assign_pointer(entry->next, p); + rcu_assign_pointer(*pp, entry); mutex_unlock(&nf_hook_mutex); #ifdef CONFIG_NETFILTER_INGRESS @@ -163,33 +131,23 @@ EXPORT_SYMBOL(nf_register_net_hook); void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg) { - struct nf_hook_entry *hooks_entry; + struct nf_hook_entry __rcu **pp; + struct nf_hook_entry *p; + + pp = nf_hook_entry_head(net, reg); + if (WARN_ON_ONCE(!pp)) + return; mutex_lock(&nf_hook_mutex); - hooks_entry = nf_hook_entry_head(net, reg); - if (hooks_entry && hooks_entry->orig_ops == reg) { - nf_set_hooks_head(net, reg, - nf_entry_dereference(hooks_entry->next)); - goto unlock; - } - while (hooks_entry && nf_entry_dereference(hooks_entry->next)) { - struct nf_hook_entry *next = - nf_entry_dereference(hooks_entry->next); - struct nf_hook_entry *nnext; - - if (next->orig_ops != reg) { - hooks_entry = next; - continue; + while ((p = nf_entry_dereference(*pp)) != NULL) { + if (p->orig_ops == reg) { + rcu_assign_pointer(*pp, p->next); + break; } - nnext = nf_entry_dereference(next->next); - rcu_assign_pointer(hooks_entry->next, nnext); - hooks_entry = next; - break; + pp = &p->next; } - -unlock: mutex_unlock(&nf_hook_mutex); - if (!hooks_entry) { + if (!p) { WARN(1, "nf_unregister_net_hook: hook not found!\n"); return; } @@ -201,10 +159,10 @@ unlock: static_key_slow_dec(&nf_hooks_needed[reg->pf][reg->hooknum]); #endif synchronize_net(); - nf_queue_nf_hook_drop(net, hooks_entry); + nf_queue_nf_hook_drop(net, p); /* other cpu might still process nfqueue verdict that used reg */ synchronize_net(); - kfree(hooks_entry); + kfree(p); } EXPORT_SYMBOL(nf_unregister_net_hook); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 627f898c05b9..62bea4591054 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1832,7 +1832,7 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, /* Record the max length of recvmsg() calls for future allocations */ nlk->max_recvmsg_len = max(nlk->max_recvmsg_len, len); nlk->max_recvmsg_len = min_t(size_t, nlk->max_recvmsg_len, - 16384); + SKB_WITH_OVERHEAD(32768)); copied = data_skb->len; if (len < copied) { @@ -2083,8 +2083,9 @@ static int netlink_dump(struct sock *sk) if (alloc_min_size < nlk->max_recvmsg_len) { alloc_size = nlk->max_recvmsg_len; - skb = alloc_skb(alloc_size, GFP_KERNEL | - __GFP_NOWARN | __GFP_NORETRY); + skb = alloc_skb(alloc_size, + (GFP_KERNEL & ~__GFP_DIRECT_RECLAIM) | + __GFP_NOWARN | __GFP_NORETRY); } if (!skb) { alloc_size = alloc_min_size; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 33a4697d5539..11db0d619c00 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3952,6 +3952,7 @@ static int packet_notifier(struct notifier_block *this, } if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); + fanout_release(sk); po->ifindex = -1; if (po->prot_hook.dev) dev_put(po->prot_hook.dev); diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 44c9c2b0b190..2d59c9be40e1 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -678,9 +678,9 @@ static int rxrpc_release_sock(struct sock *sk) sk->sk_state = RXRPC_CLOSE; spin_unlock_bh(&sk->sk_receive_queue.lock); - if (rx->local && rx->local->service == rx) { + if (rx->local && rcu_access_pointer(rx->local->service) == rx) { write_lock(&rx->local->services_lock); - rx->local->service = NULL; + rcu_assign_pointer(rx->local->service, NULL); write_unlock(&rx->local->services_lock); } diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index d38dffd78085..f60e35576526 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -398,6 +398,7 @@ enum rxrpc_call_flag { RXRPC_CALL_EXPOSED, /* The call was exposed to the world */ RXRPC_CALL_RX_LAST, /* Received the last packet (at rxtx_top) */ RXRPC_CALL_TX_LAST, /* Last packet in Tx buffer (at rxtx_top) */ + RXRPC_CALL_SEND_PING, /* A ping will need to be sent */ RXRPC_CALL_PINGING, /* Ping in process */ RXRPC_CALL_RETRANS_TIMEOUT, /* Retransmission due to timeout occurred */ }; @@ -410,6 +411,7 @@ enum rxrpc_call_event { RXRPC_CALL_EV_ABORT, /* need to generate abort */ RXRPC_CALL_EV_TIMER, /* Timer expired */ RXRPC_CALL_EV_RESEND, /* Tx resend required */ + RXRPC_CALL_EV_PING, /* Ping send required */ }; /* @@ -466,6 +468,7 @@ struct rxrpc_call { struct rxrpc_sock __rcu *socket; /* socket responsible */ ktime_t ack_at; /* When deferred ACK needs to happen */ ktime_t resend_at; /* When next resend needs to happen */ + ktime_t ping_at; /* When next to send a ping */ ktime_t expire_at; /* When the call times out */ struct timer_list timer; /* Combined event timer */ struct work_struct processor; /* Event processor */ @@ -558,8 +561,10 @@ struct rxrpc_call { rxrpc_seq_t ackr_prev_seq; /* previous sequence number received */ rxrpc_seq_t ackr_consumed; /* Highest packet shown consumed */ rxrpc_seq_t ackr_seen; /* Highest packet shown seen */ - rxrpc_serial_t ackr_ping; /* Last ping sent */ - ktime_t ackr_ping_time; /* Time last ping sent */ + + /* ping management */ + rxrpc_serial_t ping_serial; /* Last ping sent */ + ktime_t ping_time; /* Time last ping sent */ /* transmission-phase ACK management */ ktime_t acks_latest_ts; /* Timestamp of latest ACK received */ @@ -728,8 +733,10 @@ extern const char rxrpc_rtt_rx_traces[rxrpc_rtt_rx__nr_trace][5]; enum rxrpc_timer_trace { rxrpc_timer_begin, rxrpc_timer_init_for_reply, + rxrpc_timer_init_for_send_reply, rxrpc_timer_expired, rxrpc_timer_set_for_ack, + rxrpc_timer_set_for_ping, rxrpc_timer_set_for_resend, rxrpc_timer_set_for_send, rxrpc_timer__nr_trace @@ -743,6 +750,7 @@ enum rxrpc_propose_ack_trace { rxrpc_propose_ack_ping_for_lost_ack, rxrpc_propose_ack_ping_for_lost_reply, rxrpc_propose_ack_ping_for_params, + rxrpc_propose_ack_processing_op, rxrpc_propose_ack_respond_to_ack, rxrpc_propose_ack_respond_to_ping, rxrpc_propose_ack_retry_tx, @@ -777,7 +785,7 @@ extern const char rxrpc_congest_modes[NR__RXRPC_CONGEST_MODES][10]; extern const char rxrpc_congest_changes[rxrpc_congest__nr_change][9]; extern const char *const rxrpc_pkts[]; -extern const char const rxrpc_ack_names[RXRPC_ACK__INVALID + 1][4]; +extern const char rxrpc_ack_names[RXRPC_ACK__INVALID + 1][4]; #include @@ -805,6 +813,7 @@ int rxrpc_reject_call(struct rxrpc_sock *); /* * call_event.c */ +void __rxrpc_set_timer(struct rxrpc_call *, enum rxrpc_timer_trace, ktime_t); void rxrpc_set_timer(struct rxrpc_call *, enum rxrpc_timer_trace, ktime_t); void rxrpc_propose_ACK(struct rxrpc_call *, u8, u16, u32, bool, bool, enum rxrpc_propose_ack_trace); @@ -1068,7 +1077,8 @@ extern const s8 rxrpc_ack_priority[]; /* * output.c */ -int rxrpc_send_call_packet(struct rxrpc_call *, u8); +int rxrpc_send_ack_packet(struct rxrpc_call *, bool); +int rxrpc_send_abort_packet(struct rxrpc_call *); int rxrpc_send_data_packet(struct rxrpc_call *, struct sk_buff *, bool); void rxrpc_reject_packets(struct rxrpc_local *); diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 3cac231d8405..832d854c2d5c 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -337,7 +337,7 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, /* Get the socket providing the service */ rx = rcu_dereference(local->service); - if (service_id == rx->srx.srx_service) + if (rx && service_id == rx->srx.srx_service) goto found_service; trace_rxrpc_abort("INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, @@ -565,7 +565,7 @@ out_discard: write_unlock_bh(&call->state_lock); write_unlock(&rx->call_lock); if (abort) { - rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ABORT); + rxrpc_send_abort_packet(call); rxrpc_release_call(rx, call); rxrpc_put_call(call, rxrpc_call_put); } diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 4f00476630b9..97a17ada4431 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -24,19 +24,20 @@ /* * Set the timer */ -void rxrpc_set_timer(struct rxrpc_call *call, enum rxrpc_timer_trace why, - ktime_t now) +void __rxrpc_set_timer(struct rxrpc_call *call, enum rxrpc_timer_trace why, + ktime_t now) { unsigned long t_j, now_j = jiffies; ktime_t t; bool queue = false; - read_lock_bh(&call->state_lock); - if (call->state < RXRPC_CALL_COMPLETE) { t = call->expire_at; - if (!ktime_after(t, now)) + if (!ktime_after(t, now)) { + trace_rxrpc_timer(call, why, now, now_j); + queue = true; goto out; + } if (!ktime_after(call->resend_at, now)) { call->resend_at = call->expire_at; @@ -54,6 +55,14 @@ void rxrpc_set_timer(struct rxrpc_call *call, enum rxrpc_timer_trace why, t = call->ack_at; } + if (!ktime_after(call->ping_at, now)) { + call->ping_at = call->expire_at; + if (!test_and_set_bit(RXRPC_CALL_EV_PING, &call->events)) + queue = true; + } else if (ktime_before(call->ping_at, t)) { + t = call->ping_at; + } + t_j = nsecs_to_jiffies(ktime_to_ns(ktime_sub(t, now))); t_j += jiffies; @@ -68,15 +77,45 @@ void rxrpc_set_timer(struct rxrpc_call *call, enum rxrpc_timer_trace why, mod_timer(&call->timer, t_j); trace_rxrpc_timer(call, why, now, now_j); } - - if (queue) - rxrpc_queue_call(call); } out: + if (queue) + rxrpc_queue_call(call); +} + +/* + * Set the timer + */ +void rxrpc_set_timer(struct rxrpc_call *call, enum rxrpc_timer_trace why, + ktime_t now) +{ + read_lock_bh(&call->state_lock); + __rxrpc_set_timer(call, why, now); read_unlock_bh(&call->state_lock); } +/* + * Propose a PING ACK be sent. + */ +static void rxrpc_propose_ping(struct rxrpc_call *call, + bool immediate, bool background) +{ + if (immediate) { + if (background && + !test_and_set_bit(RXRPC_CALL_EV_PING, &call->events)) + rxrpc_queue_call(call); + } else { + ktime_t now = ktime_get_real(); + ktime_t ping_at = ktime_add_ms(now, rxrpc_idle_ack_delay); + + if (ktime_before(ping_at, call->ping_at)) { + call->ping_at = ping_at; + rxrpc_set_timer(call, rxrpc_timer_set_for_ping, now); + } + } +} + /* * propose an ACK be sent */ @@ -90,6 +129,14 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, ktime_t now, ack_at; s8 prior = rxrpc_ack_priority[ack_reason]; + /* Pings are handled specially because we don't want to accidentally + * lose a ping response by subsuming it into a ping. + */ + if (ack_reason == RXRPC_ACK_PING) { + rxrpc_propose_ping(call, immediate, background); + goto trace; + } + /* Update DELAY, IDLE, REQUESTED and PING_RESPONSE ACK serial * numbers, but we don't alter the timeout. */ @@ -125,7 +172,6 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, expiry = rxrpc_soft_ack_delay; break; - case RXRPC_ACK_PING: case RXRPC_ACK_IDLE: if (rxrpc_idle_ack_delay < expiry) expiry = rxrpc_idle_ack_delay; @@ -253,7 +299,7 @@ static void rxrpc_resend(struct rxrpc_call *call, ktime_t now) goto out; rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false, rxrpc_propose_ack_ping_for_lost_ack); - rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ACK); + rxrpc_send_ack_packet(call, true); goto out; } @@ -328,12 +374,13 @@ void rxrpc_process_call(struct work_struct *work) recheck_state: if (test_and_clear_bit(RXRPC_CALL_EV_ABORT, &call->events)) { - rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ABORT); + rxrpc_send_abort_packet(call); goto recheck_state; } if (call->state == RXRPC_CALL_COMPLETE) { del_timer_sync(&call->timer); + rxrpc_notify_socket(call); goto out_put; } @@ -345,13 +392,17 @@ recheck_state: } if (test_and_clear_bit(RXRPC_CALL_EV_ACK, &call->events)) { - call->ack_at = call->expire_at; if (call->ackr_reason) { - rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ACK); + rxrpc_send_ack_packet(call, false); goto recheck_state; } } + if (test_and_clear_bit(RXRPC_CALL_EV_PING, &call->events)) { + rxrpc_send_ack_packet(call, true); + goto recheck_state; + } + if (test_and_clear_bit(RXRPC_CALL_EV_RESEND, &call->events)) { rxrpc_resend(call, now); goto recheck_state; diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 364b42dc3dce..4353a29f3b57 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -205,6 +205,7 @@ static void rxrpc_start_call_timer(struct rxrpc_call *call) expire_at = ktime_add_ms(now, rxrpc_max_call_lifetime); call->expire_at = expire_at; call->ack_at = expire_at; + call->ping_at = expire_at; call->resend_at = expire_at; call->timer.expires = jiffies + LONG_MAX / 2; rxrpc_set_timer(call, rxrpc_timer_begin, now); @@ -498,7 +499,7 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx) struct rxrpc_call, sock_link); rxrpc_get_call(call, rxrpc_call_got); rxrpc_abort_call("SKT", call, 0, RX_CALL_DEAD, ECONNRESET); - rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ABORT); + rxrpc_send_abort_packet(call); rxrpc_release_call(rx, call); rxrpc_put_call(call, rxrpc_call_put); } diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 3ad9f75031e3..44fb8d893c7d 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -625,9 +625,9 @@ static void rxrpc_input_ping_response(struct rxrpc_call *call, rxrpc_serial_t ping_serial; ktime_t ping_time; - ping_time = call->ackr_ping_time; + ping_time = call->ping_time; smp_rmb(); - ping_serial = call->ackr_ping; + ping_serial = call->ping_serial; if (!test_bit(RXRPC_CALL_PINGING, &call->flags) || before(orig_serial, ping_serial)) @@ -847,7 +847,8 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, if (call->rxtx_annotations[call->tx_top & RXRPC_RXTX_BUFF_MASK] & RXRPC_TX_ANNO_LAST && - summary.nr_acks == call->tx_top - hard_ack) + summary.nr_acks == call->tx_top - hard_ack && + rxrpc_is_client_call(call)) rxrpc_propose_ACK(call, RXRPC_ACK_PING, skew, sp->hdr.serial, false, true, rxrpc_propose_ack_ping_for_lost_reply); @@ -937,6 +938,33 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call, _leave(""); } +/* + * Handle a new call on a channel implicitly completing the preceding call on + * that channel. + * + * TODO: If callNumber > call_id + 1, renegotiate security. + */ +static void rxrpc_input_implicit_end_call(struct rxrpc_connection *conn, + struct rxrpc_call *call) +{ + switch (call->state) { + case RXRPC_CALL_SERVER_AWAIT_ACK: + rxrpc_call_completed(call); + break; + case RXRPC_CALL_COMPLETE: + break; + default: + if (rxrpc_abort_call("IMP", call, 0, RX_CALL_DEAD, ESHUTDOWN)) { + set_bit(RXRPC_CALL_EV_ABORT, &call->events); + rxrpc_queue_call(call); + } + break; + } + + __rxrpc_disconnect_call(conn, call); + rxrpc_notify_socket(call); +} + /* * post connection-level events to the connection * - this includes challenges, responses, some aborts and call terminal packet @@ -1145,6 +1173,16 @@ void rxrpc_data_ready(struct sock *udp_sk) } call = rcu_dereference(chan->call); + + if (sp->hdr.callNumber > chan->call_id) { + if (!(sp->hdr.flags & RXRPC_CLIENT_INITIATED)) { + rcu_read_unlock(); + goto reject_packet; + } + if (call) + rxrpc_input_implicit_end_call(conn, call); + call = NULL; + } } else { skew = 0; call = NULL; diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c index 9d1c721bc4e8..6dee55fad2d3 100644 --- a/net/rxrpc/misc.c +++ b/net/rxrpc/misc.c @@ -93,10 +93,9 @@ const s8 rxrpc_ack_priority[] = { [RXRPC_ACK_EXCEEDS_WINDOW] = 6, [RXRPC_ACK_NOSPACE] = 7, [RXRPC_ACK_PING_RESPONSE] = 8, - [RXRPC_ACK_PING] = 9, }; -const char const rxrpc_ack_names[RXRPC_ACK__INVALID + 1][4] = { +const char rxrpc_ack_names[RXRPC_ACK__INVALID + 1][4] = { "---", "REQ", "DUP", "OOS", "WIN", "MEM", "PNG", "PNR", "DLY", "IDL", "-?-" }; @@ -196,7 +195,9 @@ const char rxrpc_timer_traces[rxrpc_timer__nr_trace][8] = { [rxrpc_timer_begin] = "Begin ", [rxrpc_timer_expired] = "*EXPR*", [rxrpc_timer_init_for_reply] = "IniRpl", + [rxrpc_timer_init_for_send_reply] = "SndRpl", [rxrpc_timer_set_for_ack] = "SetAck", + [rxrpc_timer_set_for_ping] = "SetPng", [rxrpc_timer_set_for_send] = "SetTx ", [rxrpc_timer_set_for_resend] = "SetRTx", }; @@ -207,6 +208,7 @@ const char rxrpc_propose_ack_traces[rxrpc_propose_ack__nr_trace][8] = { [rxrpc_propose_ack_ping_for_lost_ack] = "LostAck", [rxrpc_propose_ack_ping_for_lost_reply] = "LostRpl", [rxrpc_propose_ack_ping_for_params] = "Params ", + [rxrpc_propose_ack_processing_op] = "ProcOp ", [rxrpc_propose_ack_respond_to_ack] = "Rsp2Ack", [rxrpc_propose_ack_respond_to_ping] = "Rsp2Png", [rxrpc_propose_ack_retry_tx] = "RetryTx", diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 0d47db886f6e..5dab1ff3a6c2 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -19,26 +19,27 @@ #include #include "ar-internal.h" -struct rxrpc_pkt_buffer { +struct rxrpc_ack_buffer { struct rxrpc_wire_header whdr; - union { - struct { - struct rxrpc_ackpacket ack; - u8 acks[255]; - u8 pad[3]; - }; - __be32 abort_code; - }; + struct rxrpc_ackpacket ack; + u8 acks[255]; + u8 pad[3]; struct rxrpc_ackinfo ackinfo; }; +struct rxrpc_abort_buffer { + struct rxrpc_wire_header whdr; + __be32 abort_code; +}; + /* * Fill out an ACK packet. */ static size_t rxrpc_fill_out_ack(struct rxrpc_call *call, - struct rxrpc_pkt_buffer *pkt, + struct rxrpc_ack_buffer *pkt, rxrpc_seq_t *_hard_ack, - rxrpc_seq_t *_top) + rxrpc_seq_t *_top, + u8 reason) { rxrpc_serial_t serial; rxrpc_seq_t hard_ack, top, seq; @@ -58,10 +59,10 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_call *call, pkt->ack.firstPacket = htonl(hard_ack + 1); pkt->ack.previousPacket = htonl(call->ackr_prev_seq); pkt->ack.serial = htonl(serial); - pkt->ack.reason = call->ackr_reason; + pkt->ack.reason = reason; pkt->ack.nAcks = top - hard_ack; - if (pkt->ack.reason == RXRPC_ACK_PING) + if (reason == RXRPC_ACK_PING) pkt->whdr.flags |= RXRPC_REQUEST_ACK; if (after(top, hard_ack)) { @@ -91,22 +92,19 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_call *call, } /* - * Send an ACK or ABORT call packet. + * Send an ACK call packet. */ -int rxrpc_send_call_packet(struct rxrpc_call *call, u8 type) +int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping) { struct rxrpc_connection *conn = NULL; - struct rxrpc_pkt_buffer *pkt; + struct rxrpc_ack_buffer *pkt; struct msghdr msg; struct kvec iov[2]; rxrpc_serial_t serial; rxrpc_seq_t hard_ack, top; size_t len, n; - bool ping = false; - int ioc, ret; - u32 abort_code; - - _enter("%u,%s", call->debug_id, rxrpc_pkts[type]); + int ret; + u8 reason; spin_lock_bh(&call->lock); if (call->conn) @@ -131,68 +129,44 @@ int rxrpc_send_call_packet(struct rxrpc_call *call, u8 type) pkt->whdr.cid = htonl(call->cid); pkt->whdr.callNumber = htonl(call->call_id); pkt->whdr.seq = 0; - pkt->whdr.type = type; - pkt->whdr.flags = conn->out_clientflag; + pkt->whdr.type = RXRPC_PACKET_TYPE_ACK; + pkt->whdr.flags = RXRPC_SLOW_START_OK | conn->out_clientflag; pkt->whdr.userStatus = 0; pkt->whdr.securityIndex = call->security_ix; pkt->whdr._rsvd = 0; pkt->whdr.serviceId = htons(call->service_id); - iov[0].iov_base = pkt; - iov[0].iov_len = sizeof(pkt->whdr); - len = sizeof(pkt->whdr); - - switch (type) { - case RXRPC_PACKET_TYPE_ACK: - spin_lock_bh(&call->lock); + spin_lock_bh(&call->lock); + if (ping) { + reason = RXRPC_ACK_PING; + } else { + reason = call->ackr_reason; if (!call->ackr_reason) { spin_unlock_bh(&call->lock); ret = 0; goto out; } - ping = (call->ackr_reason == RXRPC_ACK_PING); - n = rxrpc_fill_out_ack(call, pkt, &hard_ack, &top); call->ackr_reason = 0; - - spin_unlock_bh(&call->lock); - - - pkt->whdr.flags |= RXRPC_SLOW_START_OK; - - iov[0].iov_len += sizeof(pkt->ack) + n; - iov[1].iov_base = &pkt->ackinfo; - iov[1].iov_len = sizeof(pkt->ackinfo); - len += sizeof(pkt->ack) + n + sizeof(pkt->ackinfo); - ioc = 2; - break; - - case RXRPC_PACKET_TYPE_ABORT: - abort_code = call->abort_code; - pkt->abort_code = htonl(abort_code); - iov[0].iov_len += sizeof(pkt->abort_code); - len += sizeof(pkt->abort_code); - ioc = 1; - break; - - default: - BUG(); - ret = -ENOANO; - goto out; } + n = rxrpc_fill_out_ack(call, pkt, &hard_ack, &top, reason); + + spin_unlock_bh(&call->lock); + + iov[0].iov_base = pkt; + iov[0].iov_len = sizeof(pkt->whdr) + sizeof(pkt->ack) + n; + iov[1].iov_base = &pkt->ackinfo; + iov[1].iov_len = sizeof(pkt->ackinfo); + len = iov[0].iov_len + iov[1].iov_len; serial = atomic_inc_return(&conn->serial); pkt->whdr.serial = htonl(serial); - switch (type) { - case RXRPC_PACKET_TYPE_ACK: - trace_rxrpc_tx_ack(call, serial, - ntohl(pkt->ack.firstPacket), - ntohl(pkt->ack.serial), - pkt->ack.reason, pkt->ack.nAcks); - break; - } + trace_rxrpc_tx_ack(call, serial, + ntohl(pkt->ack.firstPacket), + ntohl(pkt->ack.serial), + pkt->ack.reason, pkt->ack.nAcks); if (ping) { - call->ackr_ping = serial; + call->ping_serial = serial; smp_wmb(); /* We need to stick a time in before we send the packet in case * the reply gets back before kernel_sendmsg() completes - but @@ -201,19 +175,19 @@ int rxrpc_send_call_packet(struct rxrpc_call *call, u8 type) * the packet transmission is more likely to happen towards the * end of the kernel_sendmsg() call. */ - call->ackr_ping_time = ktime_get_real(); + call->ping_time = ktime_get_real(); set_bit(RXRPC_CALL_PINGING, &call->flags); trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_ping, serial); } - ret = kernel_sendmsg(conn->params.local->socket, - &msg, iov, ioc, len); - if (ping) - call->ackr_ping_time = ktime_get_real(); - if (type == RXRPC_PACKET_TYPE_ACK && - call->state < RXRPC_CALL_COMPLETE) { + ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); + if (ping) + call->ping_time = ktime_get_real(); + + if (call->state < RXRPC_CALL_COMPLETE) { if (ret < 0) { - clear_bit(RXRPC_CALL_PINGING, &call->flags); + if (ping) + clear_bit(RXRPC_CALL_PINGING, &call->flags); rxrpc_propose_ACK(call, pkt->ack.reason, ntohs(pkt->ack.maxSkew), ntohl(pkt->ack.serial), @@ -235,6 +209,56 @@ out: return ret; } +/* + * Send an ABORT call packet. + */ +int rxrpc_send_abort_packet(struct rxrpc_call *call) +{ + struct rxrpc_connection *conn = NULL; + struct rxrpc_abort_buffer pkt; + struct msghdr msg; + struct kvec iov[1]; + rxrpc_serial_t serial; + int ret; + + spin_lock_bh(&call->lock); + if (call->conn) + conn = rxrpc_get_connection_maybe(call->conn); + spin_unlock_bh(&call->lock); + if (!conn) + return -ECONNRESET; + + msg.msg_name = &call->peer->srx.transport; + msg.msg_namelen = call->peer->srx.transport_len; + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_flags = 0; + + pkt.whdr.epoch = htonl(conn->proto.epoch); + pkt.whdr.cid = htonl(call->cid); + pkt.whdr.callNumber = htonl(call->call_id); + pkt.whdr.seq = 0; + pkt.whdr.type = RXRPC_PACKET_TYPE_ABORT; + pkt.whdr.flags = conn->out_clientflag; + pkt.whdr.userStatus = 0; + pkt.whdr.securityIndex = call->security_ix; + pkt.whdr._rsvd = 0; + pkt.whdr.serviceId = htons(call->service_id); + pkt.abort_code = htonl(call->abort_code); + + iov[0].iov_base = &pkt; + iov[0].iov_len = sizeof(pkt); + + serial = atomic_inc_return(&conn->serial); + pkt.whdr.serial = htonl(serial); + + ret = kernel_sendmsg(conn->params.local->socket, + &msg, iov, 1, sizeof(pkt)); + + rxrpc_put_connection(conn); + return ret; +} + /* * send a packet through the transport endpoint */ @@ -283,11 +307,12 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, /* If our RTT cache needs working on, request an ACK. Also request * ACKs if a DATA packet appears to have been lost. */ - if (retrans || - call->cong_mode == RXRPC_CALL_SLOW_START || - (call->peer->rtt_usage < 3 && sp->hdr.seq & 1) || - ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), - ktime_get_real())) + if (!(sp->hdr.flags & RXRPC_LAST_PACKET) && + (retrans || + call->cong_mode == RXRPC_CALL_SLOW_START || + (call->peer->rtt_usage < 3 && sp->hdr.seq & 1) || + ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), + ktime_get_real()))) whdr.flags |= RXRPC_REQUEST_ACK; if (IS_ENABLED(CONFIG_AF_RXRPC_INJECT_LOSS)) { diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index f05ea0a88076..c29362d50a92 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -143,7 +143,7 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) { rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, 0, serial, true, false, rxrpc_propose_ack_terminal_ack); - rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ACK); + rxrpc_send_ack_packet(call, false); } write_lock_bh(&call->state_lock); @@ -151,17 +151,21 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) switch (call->state) { case RXRPC_CALL_CLIENT_RECV_REPLY: __rxrpc_call_completed(call); + write_unlock_bh(&call->state_lock); break; case RXRPC_CALL_SERVER_RECV_REQUEST: call->tx_phase = true; call->state = RXRPC_CALL_SERVER_ACK_REQUEST; + call->ack_at = call->expire_at; + write_unlock_bh(&call->state_lock); + rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, 0, serial, false, true, + rxrpc_propose_ack_processing_op); break; default: + write_unlock_bh(&call->state_lock); break; } - - write_unlock_bh(&call->state_lock); } /* @@ -212,7 +216,7 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) true, false, rxrpc_propose_ack_rotate_rx); if (call->ackr_reason) - rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ACK); + rxrpc_send_ack_packet(call, false); } } @@ -652,7 +656,7 @@ excess_data: goto out; call_complete: *_abort = call->abort_code; - ret = call->error; + ret = -call->error; if (call->completion == RXRPC_CALL_SUCCEEDED) { ret = 1; if (size > 0) diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 627abed5f999..4374e7b9c7bf 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -381,7 +381,7 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, return 0; protocol_error: - rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ABORT); + rxrpc_send_abort_packet(call); _leave(" = -EPROTO"); return -EPROTO; @@ -471,7 +471,7 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, return 0; protocol_error: - rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ABORT); + rxrpc_send_abort_packet(call); _leave(" = -EPROTO"); return -EPROTO; @@ -523,7 +523,7 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, if (cksum != expected_cksum) { rxrpc_abort_call("VCK", call, seq, RXKADSEALEDINCON, EPROTO); - rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ABORT); + rxrpc_send_abort_packet(call); _leave(" = -EPROTO [csum failed]"); return -EPROTO; } diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 3322543d460a..b214a4d4a641 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -130,6 +130,11 @@ static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb, break; case RXRPC_CALL_SERVER_ACK_REQUEST: call->state = RXRPC_CALL_SERVER_SEND_REPLY; + call->ack_at = call->expire_at; + if (call->ackr_reason == RXRPC_ACK_DELAY) + call->ackr_reason = 0; + __rxrpc_set_timer(call, rxrpc_timer_init_for_send_reply, + ktime_get_real()); if (!last) break; case RXRPC_CALL_SERVER_SEND_REPLY: @@ -197,7 +202,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, do { /* Check to see if there's a ping ACK to reply to. */ if (call->ackr_reason == RXRPC_ACK_PING_RESPONSE) - rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ACK); + rxrpc_send_ack_packet(call, false); if (!skb) { size_t size, chunk, max, space; @@ -514,8 +519,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) } else if (cmd == RXRPC_CMD_SEND_ABORT) { ret = 0; if (rxrpc_abort_call("CMD", call, 0, abort_code, ECONNABORTED)) - ret = rxrpc_send_call_packet(call, - RXRPC_PACKET_TYPE_ABORT); + ret = rxrpc_send_abort_packet(call); } else if (cmd != RXRPC_CMD_SEND_DATA) { ret = -EINVAL; } else if (rxrpc_is_client_call(call) && @@ -597,7 +601,7 @@ void rxrpc_kernel_abort_call(struct socket *sock, struct rxrpc_call *call, lock_sock(sock->sk); if (rxrpc_abort_call(why, call, 0, abort_code, error)) - rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ABORT); + rxrpc_send_abort_packet(call); release_sock(sock->sk); _leave("");