diff options
83 files changed, 1176 insertions, 581 deletions
diff --git a/Documentation/devicetree/bindings/net/brcm,amac.txt b/Documentation/devicetree/bindings/net/brcm,amac.txt index 2fefa1a44afd..ad16c1f481f7 100644 --- a/Documentation/devicetree/bindings/net/brcm,amac.txt +++ b/Documentation/devicetree/bindings/net/brcm,amac.txt @@ -11,6 +11,7 @@ Required properties: - reg-names: Names of the registers. "amac_base": Address and length of the GMAC registers "idm_base": Address and length of the GMAC IDM registers + (required for NSP and Northstar2) "nicpm_base": Address and length of the NIC Port Manager registers (required for Northstar2) - interrupts: Interrupt number diff --git a/Documentation/devicetree/bindings/net/brcm,bgmac-nsp.txt b/Documentation/devicetree/bindings/net/brcm,bgmac-nsp.txt deleted file mode 100644 index 022946caa7e2..000000000000 --- a/Documentation/devicetree/bindings/net/brcm,bgmac-nsp.txt +++ /dev/null @@ -1,24 +0,0 @@ -Broadcom GMAC Ethernet Controller Device Tree Bindings -------------------------------------------------------------- - -Required properties: - - compatible: "brcm,bgmac-nsp" - - reg: Address and length of the GMAC registers, - Address and length of the GMAC IDM registers - - reg-names: Names of the registers. Must have both "gmac_base" and - "idm_base" - - interrupts: Interrupt number - -Optional properties: -- mac-address: See ethernet.txt file in the same directory - -Examples: - -gmac0: ethernet@18022000 { - compatible = "brcm,bgmac-nsp"; - reg = <0x18022000 0x1000>, - <0x18110000 0x1000>; - reg-names = "gmac_base", "idm_base"; - interrupts = <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>; - status = "disabled"; -}; diff --git a/Documentation/devicetree/bindings/ptp/brcm,ptp-dte.txt b/Documentation/devicetree/bindings/ptp/brcm,ptp-dte.txt index 07590bcdad15..7c04e22a5d6a 100644 --- a/Documentation/devicetree/bindings/ptp/brcm,ptp-dte.txt +++ b/Documentation/devicetree/bindings/ptp/brcm,ptp-dte.txt @@ -1,13 +1,20 @@ -* Broadcom Digital Timing Engine(DTE) based PTP clock driver +* Broadcom Digital Timing Engine(DTE) based PTP clock Required properties: -- compatible: should be "brcm,ptp-dte" +- compatible: should contain the core compatibility string + and the SoC compatibility string. The SoC + compatibility string is to handle SoC specific + hardware differences. + Core compatibility string: + "brcm,ptp-dte" + SoC compatibility strings: + "brcm,iproc-ptp-dte" - for iproc based SoC's - reg: address and length of the DTE block's NCO registers Example: -ptp_dte: ptp_dte@180af650 { - compatible = "brcm,ptp-dte"; +ptp: ptp-dte@180af650 { + compatible = "brcm,iproc-ptp-dte", "brcm,ptp-dte"; reg = <0x180af650 0x10>; status = "okay"; }; diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c index 292dec18ffb8..07bdd51b3b9a 100644 --- a/drivers/atm/zatm.c +++ b/drivers/atm/zatm.c @@ -1613,7 +1613,7 @@ static int zatm_init_one(struct pci_dev *pci_dev, ret = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(32)); if (ret < 0) - goto out_disable; + goto out_release; zatm_dev->pci_dev = pci_dev; dev->dev_data = zatm_dev; diff --git a/drivers/isdn/divert/isdn_divert.c b/drivers/isdn/divert/isdn_divert.c index 060d357f107f..6f423bc49d0d 100644 --- a/drivers/isdn/divert/isdn_divert.c +++ b/drivers/isdn/divert/isdn_divert.c @@ -485,18 +485,19 @@ static int isdn_divert_icall(isdn_ctrl *ic) cs->deflect_dest[0] = '\0'; retval = 4; /* only proceed */ } - sprintf(cs->info, "%d 0x%lx %s %s %s %s 0x%x 0x%x %d %d %s\n", - cs->akt_state, - cs->divert_id, - divert_if.drv_to_name(cs->ics.driver), - (ic->command == ISDN_STAT_ICALLW) ? "1" : "0", - cs->ics.parm.setup.phone, - cs->ics.parm.setup.eazmsn, - cs->ics.parm.setup.si1, - cs->ics.parm.setup.si2, - cs->ics.parm.setup.screen, - dv->rule.waittime, - cs->deflect_dest); + snprintf(cs->info, sizeof(cs->info), + "%d 0x%lx %s %s %s %s 0x%x 0x%x %d %d %s\n", + cs->akt_state, + cs->divert_id, + divert_if.drv_to_name(cs->ics.driver), + (ic->command == ISDN_STAT_ICALLW) ? "1" : "0", + cs->ics.parm.setup.phone, + cs->ics.parm.setup.eazmsn, + cs->ics.parm.setup.si1, + cs->ics.parm.setup.si2, + cs->ics.parm.setup.screen, + dv->rule.waittime, + cs->deflect_dest); if ((dv->rule.action == DEFLECT_REPORT) || (dv->rule.action == DEFLECT_REJECT)) { put_info_buffer(cs->info); diff --git a/drivers/isdn/hardware/avm/c4.c b/drivers/isdn/hardware/avm/c4.c index 40c7e2cf423b..034cabac699d 100644 --- a/drivers/isdn/hardware/avm/c4.c +++ b/drivers/isdn/hardware/avm/c4.c @@ -42,7 +42,7 @@ static char *revision = "$Revision: 1.1.2.2 $"; static bool suppress_pollack; -static struct pci_device_id c4_pci_tbl[] = { +static const struct pci_device_id c4_pci_tbl[] = { { PCI_VENDOR_ID_DEC, PCI_DEVICE_ID_DEC_21285, PCI_VENDOR_ID_AVM, PCI_DEVICE_ID_AVM_C4, 0, 0, (unsigned long)4 }, { PCI_VENDOR_ID_DEC, PCI_DEVICE_ID_DEC_21285, PCI_VENDOR_ID_AVM, PCI_DEVICE_ID_AVM_C2, 0, 0, (unsigned long)2 }, { } /* Terminating entry */ diff --git a/drivers/isdn/hardware/eicon/divasmain.c b/drivers/isdn/hardware/eicon/divasmain.c index 8b7ad4f1ab01..b2023e08dcd2 100644 --- a/drivers/isdn/hardware/eicon/divasmain.c +++ b/drivers/isdn/hardware/eicon/divasmain.c @@ -110,7 +110,7 @@ typedef struct _diva_os_thread_dpc { /* This table should be sorted by PCI device ID */ -static struct pci_device_id divas_pci_tbl[] = { +static const struct pci_device_id divas_pci_tbl[] = { /* Diva Server BRI-2M PCI 0xE010 */ { PCI_VDEVICE(EICON, PCI_DEVICE_ID_EICON_MAESTRA), CARDTYPE_MAESTRA_PCI }, diff --git a/drivers/isdn/hardware/mISDN/avmfritz.c b/drivers/isdn/hardware/mISDN/avmfritz.c index e3fa1cd64470..dce6632daae1 100644 --- a/drivers/isdn/hardware/mISDN/avmfritz.c +++ b/drivers/isdn/hardware/mISDN/avmfritz.c @@ -1142,7 +1142,7 @@ fritz_remove_pci(struct pci_dev *pdev) pr_info("%s: drvdata already removed\n", __func__); } -static struct pci_device_id fcpci_ids[] = { +static const struct pci_device_id fcpci_ids[] = { { PCI_VENDOR_ID_AVM, PCI_DEVICE_ID_AVM_A1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, (unsigned long) "Fritz!Card PCI"}, { PCI_VENDOR_ID_AVM, PCI_DEVICE_ID_AVM_A1_V2, PCI_ANY_ID, PCI_ANY_ID, diff --git a/drivers/isdn/hardware/mISDN/hfcmulti.c b/drivers/isdn/hardware/mISDN/hfcmulti.c index aea0c9616ea5..3cf07b8ced1c 100644 --- a/drivers/isdn/hardware/mISDN/hfcmulti.c +++ b/drivers/isdn/hardware/mISDN/hfcmulti.c @@ -5348,7 +5348,7 @@ static const struct hm_map hfcm_map[] = { #undef H #define H(x) ((unsigned long)&hfcm_map[x]) -static struct pci_device_id hfmultipci_ids[] = { +static const struct pci_device_id hfmultipci_ids[] = { /* Cards with HFC-4S Chip */ { PCI_VENDOR_ID_CCD, PCI_DEVICE_ID_CCD_HFC4S, PCI_VENDOR_ID_CCD, diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c index 5dc246d71c16..d2e401a8090e 100644 --- a/drivers/isdn/hardware/mISDN/hfcpci.c +++ b/drivers/isdn/hardware/mISDN/hfcpci.c @@ -2161,7 +2161,7 @@ static const struct _hfc_map hfc_map[] = {}, }; -static struct pci_device_id hfc_ids[] = +static const struct pci_device_id hfc_ids[] = { { PCI_VDEVICE(CCD, PCI_DEVICE_ID_CCD_2BD0), (unsigned long) &hfc_map[0] }, diff --git a/drivers/isdn/hardware/mISDN/netjet.c b/drivers/isdn/hardware/mISDN/netjet.c index afde4edef9ae..6a6d848bd18e 100644 --- a/drivers/isdn/hardware/mISDN/netjet.c +++ b/drivers/isdn/hardware/mISDN/netjet.c @@ -1137,7 +1137,7 @@ static void nj_remove(struct pci_dev *pdev) /* We cannot select cards with PCI_SUB... IDs, since here are cards with * SUB IDs set to PCI_ANY_ID, so we need to match all and reject * known other cards which not work with this driver - see probe function */ -static struct pci_device_id nj_pci_ids[] = { +static const struct pci_device_id nj_pci_ids[] = { { PCI_VENDOR_ID_TIGERJET, PCI_DEVICE_ID_TIGERJET_300, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, { } diff --git a/drivers/isdn/hardware/mISDN/w6692.c b/drivers/isdn/hardware/mISDN/w6692.c index 3052c836b89f..d80072fef434 100644 --- a/drivers/isdn/hardware/mISDN/w6692.c +++ b/drivers/isdn/hardware/mISDN/w6692.c @@ -1398,7 +1398,7 @@ w6692_remove_pci(struct pci_dev *pdev) pr_notice("%s: drvdata already removed\n", __func__); } -static struct pci_device_id w6692_ids[] = { +static const struct pci_device_id w6692_ids[] = { { PCI_VENDOR_ID_DYNALINK, PCI_DEVICE_ID_DYNALINK_IS64PH, PCI_ANY_ID, PCI_ANY_ID, 0, 0, (ulong)&w6692_map[0]}, { PCI_VENDOR_ID_WINBOND2, PCI_DEVICE_ID_WINBOND2_6692, diff --git a/drivers/isdn/hisax/config.c b/drivers/isdn/hisax/config.c index c7d68675b028..7108bdb8742e 100644 --- a/drivers/isdn/hisax/config.c +++ b/drivers/isdn/hisax/config.c @@ -1909,7 +1909,7 @@ static void EChannel_proc_rcv(struct hisax_d_if *d_if) #ifdef CONFIG_PCI #include <linux/pci.h> -static struct pci_device_id hisax_pci_tbl[] __used = { +static const struct pci_device_id hisax_pci_tbl[] __used = { #ifdef CONFIG_HISAX_FRITZPCI {PCI_VDEVICE(AVM, PCI_DEVICE_ID_AVM_A1) }, #endif diff --git a/drivers/isdn/hisax/hfc4s8s_l1.c b/drivers/isdn/hisax/hfc4s8s_l1.c index 90f051ce0259..9090cc1e1f29 100644 --- a/drivers/isdn/hisax/hfc4s8s_l1.c +++ b/drivers/isdn/hisax/hfc4s8s_l1.c @@ -86,7 +86,7 @@ typedef struct { char *device_name; } hfc4s8s_param; -static struct pci_device_id hfc4s8s_ids[] = { +static const struct pci_device_id hfc4s8s_ids[] = { {.vendor = PCI_VENDOR_ID_CCD, .device = PCI_DEVICE_ID_4S, .subvendor = 0x1397, diff --git a/drivers/isdn/hisax/hisax_fcpcipnp.c b/drivers/isdn/hisax/hisax_fcpcipnp.c index 5a9f39ed1d5d..e4f7573ba9bf 100644 --- a/drivers/isdn/hisax/hisax_fcpcipnp.c +++ b/drivers/isdn/hisax/hisax_fcpcipnp.c @@ -52,7 +52,7 @@ module_param(debug, int, 0); MODULE_AUTHOR("Kai Germaschewski <kai.germaschewski@gmx.de>/Karsten Keil <kkeil@suse.de>"); MODULE_DESCRIPTION("AVM Fritz!PCI/PnP ISDN driver"); -static struct pci_device_id fcpci_ids[] = { +static const struct pci_device_id fcpci_ids[] = { { .vendor = PCI_VENDOR_ID_AVM, .device = PCI_DEVICE_ID_AVM_A1, .subvendor = PCI_ANY_ID, diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 14ff622190a5..181839d6fbea 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4596,7 +4596,7 @@ static int bond_check_params(struct bond_params *params) } ad_user_port_key = valptr->value; - if (bond_mode == BOND_MODE_TLB) { + if ((bond_mode == BOND_MODE_TLB) || (bond_mode == BOND_MODE_ALB)) { bond_opt_initstr(&newval, "default"); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_TLB_DYNAMIC_LB), &newval); diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index e68d368e20ac..7f36d3e3c98b 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1665,6 +1665,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .dev_name = "BCM53125", .vlans = 4096, .enabled_ports = 0xff, + .arl_entries = 4, .cpu_port = B53_CPU_PORT, .vta_regs = B53_VTA_REGS, .duplex_reg = B53_DUPLEX_STAT_GE, diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 53b088166c28..5bcdd33101b0 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3178,6 +3178,7 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = { .port_set_jumbo_size = mv88e6165_port_set_jumbo_size, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_limit = mv88e6390_port_pause_limit, + .port_set_cmode = mv88e6390x_port_set_cmode, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6390_g1_stats_snapshot, diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index d3906f6b01bd..86058a9f3417 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -1785,16 +1785,18 @@ static int xgene_enet_get_resources(struct xgene_enet_pdata *pdata) xgene_enet_gpiod_get(pdata); - pdata->clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(pdata->clk)) { - /* Abort if the clock is defined but couldn't be retrived. - * Always abort if the clock is missing on DT system as - * the driver can't cope with this case. - */ - if (PTR_ERR(pdata->clk) != -ENOENT || dev->of_node) - return PTR_ERR(pdata->clk); - /* Firmware may have set up the clock already. */ - dev_info(dev, "clocks have been setup already\n"); + if (pdata->phy_mode != PHY_INTERFACE_MODE_SGMII) { + pdata->clk = devm_clk_get(&pdev->dev, NULL); + if (IS_ERR(pdata->clk)) { + /* Abort if the clock is defined but couldn't be + * retrived. Always abort if the clock is missing on + * DT system as the driver can't cope with this case. + */ + if (PTR_ERR(pdata->clk) != -ENOENT || dev->of_node) + return PTR_ERR(pdata->clk); + /* Firmware may have set up the clock already. */ + dev_info(dev, "clocks have been setup already\n"); + } } if (pdata->phy_mode != PHY_INTERFACE_MODE_XGMII) diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c index 73aca97a96bc..d937083db9a4 100644 --- a/drivers/net/ethernet/broadcom/bgmac-platform.c +++ b/drivers/net/ethernet/broadcom/bgmac-platform.c @@ -50,11 +50,14 @@ static u32 platform_bgmac_idm_read(struct bgmac *bgmac, u16 offset) static void platform_bgmac_idm_write(struct bgmac *bgmac, u16 offset, u32 value) { - return writel(value, bgmac->plat.idm_base + offset); + writel(value, bgmac->plat.idm_base + offset); } static bool platform_bgmac_clk_enabled(struct bgmac *bgmac) { + if (!bgmac->plat.idm_base) + return true; + if ((bgmac_idm_read(bgmac, BCMA_IOCTL) & BGMAC_CLK_EN) != BGMAC_CLK_EN) return false; if (bgmac_idm_read(bgmac, BCMA_RESET_CTL) & BCMA_RESET_CTL_RESET) @@ -66,6 +69,9 @@ static void platform_bgmac_clk_enable(struct bgmac *bgmac, u32 flags) { u32 val; + if (!bgmac->plat.idm_base) + return; + /* The Reset Control register only contains a single bit to show if the * controller is currently in reset. Do a sanity check here, just in * case the bootloader happened to leave the device in reset. @@ -180,6 +186,7 @@ static int bgmac_probe(struct platform_device *pdev) bgmac->feature_flags |= BGMAC_FEAT_CMDCFG_SR_REV4; bgmac->feature_flags |= BGMAC_FEAT_TX_MASK_SETUP; bgmac->feature_flags |= BGMAC_FEAT_RX_MASK_SETUP; + bgmac->feature_flags |= BGMAC_FEAT_IDM_MASK; bgmac->dev = &pdev->dev; bgmac->dma_dev = &pdev->dev; @@ -207,15 +214,13 @@ static int bgmac_probe(struct platform_device *pdev) return PTR_ERR(bgmac->plat.base); regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "idm_base"); - if (!regs) { - dev_err(&pdev->dev, "Unable to obtain idm resource\n"); - return -EINVAL; + if (regs) { + bgmac->plat.idm_base = devm_ioremap_resource(&pdev->dev, regs); + if (IS_ERR(bgmac->plat.idm_base)) + return PTR_ERR(bgmac->plat.idm_base); + bgmac->feature_flags &= ~BGMAC_FEAT_IDM_MASK; } - bgmac->plat.idm_base = devm_ioremap_resource(&pdev->dev, regs); - if (IS_ERR(bgmac->plat.idm_base)) - return PTR_ERR(bgmac->plat.idm_base); - regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nicpm_base"); if (regs) { bgmac->plat.nicpm_base = devm_ioremap_resource(&pdev->dev, diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index ba4d2e145bb9..48d672b204a4 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -622,9 +622,11 @@ static int bgmac_dma_alloc(struct bgmac *bgmac) BUILD_BUG_ON(BGMAC_MAX_TX_RINGS > ARRAY_SIZE(ring_base)); BUILD_BUG_ON(BGMAC_MAX_RX_RINGS > ARRAY_SIZE(ring_base)); - if (!(bgmac_idm_read(bgmac, BCMA_IOST) & BCMA_IOST_DMA64)) { - dev_err(bgmac->dev, "Core does not report 64-bit DMA\n"); - return -ENOTSUPP; + if (!(bgmac->feature_flags & BGMAC_FEAT_IDM_MASK)) { + if (!(bgmac_idm_read(bgmac, BCMA_IOST) & BCMA_IOST_DMA64)) { + dev_err(bgmac->dev, "Core does not report 64-bit DMA\n"); + return -ENOTSUPP; + } } for (i = 0; i < BGMAC_MAX_TX_RINGS; i++) { @@ -855,9 +857,11 @@ static void bgmac_mac_speed(struct bgmac *bgmac) static void bgmac_miiconfig(struct bgmac *bgmac) { if (bgmac->feature_flags & BGMAC_FEAT_FORCE_SPEED_2500) { - bgmac_idm_write(bgmac, BCMA_IOCTL, - bgmac_idm_read(bgmac, BCMA_IOCTL) | 0x40 | - BGMAC_BCMA_IOCTL_SW_CLKEN); + if (!(bgmac->feature_flags & BGMAC_FEAT_IDM_MASK)) { + bgmac_idm_write(bgmac, BCMA_IOCTL, + bgmac_idm_read(bgmac, BCMA_IOCTL) | + 0x40 | BGMAC_BCMA_IOCTL_SW_CLKEN); + } bgmac->mac_speed = SPEED_2500; bgmac->mac_duplex = DUPLEX_FULL; bgmac_mac_speed(bgmac); @@ -874,11 +878,36 @@ static void bgmac_miiconfig(struct bgmac *bgmac) } } +static void bgmac_chip_reset_idm_config(struct bgmac *bgmac) +{ + u32 iost; + + iost = bgmac_idm_read(bgmac, BCMA_IOST); + if (bgmac->feature_flags & BGMAC_FEAT_IOST_ATTACHED) + iost &= ~BGMAC_BCMA_IOST_ATTACHED; + + /* 3GMAC: for BCM4707 & BCM47094, only do core reset at bgmac_probe() */ + if (!(bgmac->feature_flags & BGMAC_FEAT_NO_RESET)) { + u32 flags = 0; + + if (iost & BGMAC_BCMA_IOST_ATTACHED) { + flags = BGMAC_BCMA_IOCTL_SW_CLKEN; + if (!bgmac->has_robosw) + flags |= BGMAC_BCMA_IOCTL_SW_RESET; + } + bgmac_clk_enable(bgmac, flags); + } + + if (iost & BGMAC_BCMA_IOST_ATTACHED && !bgmac->has_robosw) + bgmac_idm_write(bgmac, BCMA_IOCTL, + bgmac_idm_read(bgmac, BCMA_IOCTL) & + ~BGMAC_BCMA_IOCTL_SW_RESET); +} + /* http://bcm-v4.sipsolutions.net/mac-gbit/gmac/chipreset */ static void bgmac_chip_reset(struct bgmac *bgmac) { u32 cmdcfg_sr; - u32 iost; int i; if (bgmac_clk_enabled(bgmac)) { @@ -899,20 +928,8 @@ static void bgmac_chip_reset(struct bgmac *bgmac) /* TODO: Clear software multicast filter list */ } - iost = bgmac_idm_read(bgmac, BCMA_IOST); - if (bgmac->feature_flags & BGMAC_FEAT_IOST_ATTACHED) - iost &= ~BGMAC_BCMA_IOST_ATTACHED; - - /* 3GMAC: for BCM4707 & BCM47094, only do core reset at bgmac_probe() */ - if (!(bgmac->feature_flags & BGMAC_FEAT_NO_RESET)) { - u32 flags = 0; - if (iost & BGMAC_BCMA_IOST_ATTACHED) { - flags = BGMAC_BCMA_IOCTL_SW_CLKEN; - if (!bgmac->has_robosw) - flags |= BGMAC_BCMA_IOCTL_SW_RESET; - } - bgmac_clk_enable(bgmac, flags); - } + if (!(bgmac->feature_flags & BGMAC_FEAT_IDM_MASK)) + bgmac_chip_reset_idm_config(bgmac); /* Request Misc PLL for corerev > 2 */ if (bgmac->feature_flags & BGMAC_FEAT_MISC_PLL_REQ) { @@ -970,11 +987,6 @@ static void bgmac_chip_reset(struct bgmac *bgmac) BGMAC_CHIPCTL_7_IF_TYPE_RGMII); } - if (iost & BGMAC_BCMA_IOST_ATTACHED && !bgmac->has_robosw) - bgmac_idm_write(bgmac, BCMA_IOCTL, - bgmac_idm_read(bgmac, BCMA_IOCTL) & - ~BGMAC_BCMA_IOCTL_SW_RESET); - /* http://bcm-v4.sipsolutions.net/mac-gbit/gmac/gmac_reset * Specs don't say about using BGMAC_CMDCFG_SR, but in this routine * BGMAC_CMDCFG is read _after_ putting chip in a reset. So it has to @@ -1497,8 +1509,10 @@ int bgmac_enet_probe(struct bgmac *bgmac) bgmac_clk_enable(bgmac, 0); /* This seems to be fixing IRQ by assigning OOB #6 to the core */ - if (bgmac->feature_flags & BGMAC_FEAT_IRQ_ID_OOB_6) - bgmac_idm_write(bgmac, BCMA_OOB_SEL_OUT_A30, 0x86); + if (!(bgmac->feature_flags & BGMAC_FEAT_IDM_MASK)) { + if (bgmac->feature_flags & BGMAC_FEAT_IRQ_ID_OOB_6) + bgmac_idm_write(bgmac, BCMA_OOB_SEL_OUT_A30, 0x86); + } bgmac_chip_reset(bgmac); diff --git a/drivers/net/ethernet/broadcom/bgmac.h b/drivers/net/ethernet/broadcom/bgmac.h index c1818766c501..443d57b10264 100644 --- a/drivers/net/ethernet/broadcom/bgmac.h +++ b/drivers/net/ethernet/broadcom/bgmac.h @@ -425,6 +425,7 @@ #define BGMAC_FEAT_CC4_IF_SW_TYPE BIT(17) #define BGMAC_FEAT_CC4_IF_SW_TYPE_RGMII BIT(18) #define BGMAC_FEAT_CC7_IF_TYPE_RGMII BIT(19) +#define BGMAC_FEAT_IDM_MASK BIT(20) struct bgmac_slot_info { union { diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index 43423744fdfa..1e33abde4a3e 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -2886,7 +2886,7 @@ static int bnx2x_test_nvram_tbl(struct bnx2x *bp, static int bnx2x_test_nvram(struct bnx2x *bp) { - const struct crc_pair nvram_tbl[] = { + static const struct crc_pair nvram_tbl[] = { { 0, 0x14 }, /* bootstrap */ { 0x14, 0xec }, /* dir */ { 0x100, 0x350 }, /* manuf_info */ @@ -2895,7 +2895,7 @@ static int bnx2x_test_nvram(struct bnx2x *bp) { 0x708, 0x70 }, /* manuf_key_info */ { 0, 0 } }; - const struct crc_pair nvram_tbl2[] = { + static const struct crc_pair nvram_tbl2[] = { { 0x7e8, 0x350 }, /* manuf_info2 */ { 0xb38, 0xf0 }, /* feature_info */ { 0, 0 } @@ -3162,7 +3162,8 @@ static void bnx2x_get_strings(struct net_device *dev, u32 stringset, u8 *buf) if (is_multi(bp)) { for_each_eth_queue(bp, i) { memset(queue_name, 0, sizeof(queue_name)); - sprintf(queue_name, "%d", i); + snprintf(queue_name, sizeof(queue_name), + "%d", i); for (j = 0; j < BNX2X_NUM_Q_STATS; j++) snprintf(buf + (k + j)*ETH_GSTRING_LEN, ETH_GSTRING_LEN, diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index daca1c9d254b..7b0b399aaedd 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1202,12 +1202,21 @@ static struct enet_cb *bcmgenet_get_txcb(struct bcmgenet_priv *priv, return tx_cb_ptr; } -/* Simple helper to free a control block's resources */ -static void bcmgenet_free_cb(struct enet_cb *cb) +static struct enet_cb *bcmgenet_put_txcb(struct bcmgenet_priv *priv, + struct bcmgenet_tx_ring *ring) { - dev_kfree_skb_any(cb->skb); - cb->skb = NULL; - dma_unmap_addr_set(cb, dma_addr, 0); + struct enet_cb *tx_cb_ptr; + + tx_cb_ptr = ring->cbs; + tx_cb_ptr += ring->write_ptr - ring->cb_ptr; + + /* Rewinding local write pointer */ + if (ring->write_ptr == ring->cb_ptr) + ring->write_ptr = ring->end_ptr; + else + ring->write_ptr--; + + return tx_cb_ptr; } static inline void bcmgenet_rx_ring16_int_disable(struct bcmgenet_rx_ring *ring) @@ -1260,18 +1269,72 @@ static inline void bcmgenet_tx_ring_int_disable(struct bcmgenet_tx_ring *ring) INTRL2_CPU_MASK_SET); } +/* Simple helper to free a transmit control block's resources + * Returns an skb when the last transmit control block associated with the + * skb is freed. The skb should be freed by the caller if necessary. + */ +static struct sk_buff *bcmgenet_free_tx_cb(struct device *dev, + struct enet_cb *cb) +{ + struct sk_buff *skb; + + skb = cb->skb; + + if (skb) { + cb->skb = NULL; + if (cb == GENET_CB(skb)->first_cb) + dma_unmap_single(dev, dma_unmap_addr(cb, dma_addr), + dma_unmap_len(cb, dma_len), + DMA_TO_DEVICE); + else + dma_unmap_page(dev, dma_unmap_addr(cb, dma_addr), + dma_unmap_len(cb, dma_len), + DMA_TO_DEVICE); + dma_unmap_addr_set(cb, dma_addr, 0); + + if (cb == GENET_CB(skb)->last_cb) + return skb; + + } else if (dma_unmap_addr(cb, dma_addr)) { + dma_unmap_page(dev, + dma_unmap_addr(cb, dma_addr), + dma_unmap_len(cb, dma_len), + DMA_TO_DEVICE); + dma_unmap_addr_set(cb, dma_addr, 0); + } + + return 0; +} + +/* Simple helper to free a receive control block's resources */ +static struct sk_buff *bcmgenet_free_rx_cb(struct device *dev, + struct enet_cb *cb) +{ + struct sk_buff *skb; + + skb = cb->skb; + cb->skb = NULL; + + if (dma_unmap_addr(cb, dma_addr)) { + dma_unmap_single(dev, dma_unmap_addr(cb, dma_addr), + dma_unmap_len(cb, dma_len), DMA_FROM_DEVICE); + dma_unmap_addr_set(cb, dma_addr, 0); + } + + return skb; +} + /* Unlocked version of the reclaim routine */ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev, struct bcmgenet_tx_ring *ring) { struct bcmgenet_priv *priv = netdev_priv(dev); - struct device *kdev = &priv->pdev->dev; - struct enet_cb *tx_cb_ptr; - unsigned int pkts_compl = 0; + unsigned int txbds_processed = 0; unsigned int bytes_compl = 0; - unsigned int c_index; + unsigned int pkts_compl = 0; unsigned int txbds_ready; - unsigned int txbds_processed = 0; + unsigned int c_index; + struct sk_buff *skb; /* Clear status before servicing to reduce spurious interrupts */ if (ring->index == DESC_INDEX) @@ -1292,21 +1355,12 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev, /* Reclaim transmitted buffers */ while (txbds_processed < txbds_ready) { - tx_cb_ptr = &priv->tx_cbs[ring->clean_ptr]; - if (tx_cb_ptr->skb) { + skb = bcmgenet_free_tx_cb(&priv->pdev->dev, + &priv->tx_cbs[ring->clean_ptr]); + if (skb) { pkts_compl++; - bytes_compl += GENET_CB(tx_cb_ptr->skb)->bytes_sent; - dma_unmap_single(kdev, - dma_unmap_addr(tx_cb_ptr, dma_addr), - dma_unmap_len(tx_cb_ptr, dma_len), - DMA_TO_DEVICE); - bcmgenet_free_cb(tx_cb_ptr); - } else if (dma_unmap_addr(tx_cb_ptr, dma_addr)) { - dma_unmap_page(kdev, - dma_unmap_addr(tx_cb_ptr, dma_addr), - dma_unmap_len(tx_cb_ptr, dma_len), - DMA_TO_DEVICE); - dma_unmap_addr_set(tx_cb_ptr, dma_addr, 0); + bytes_compl += GENET_CB(skb)->bytes_sent; + dev_kfree_skb_any(skb); } txbds_processed++; @@ -1380,95 +1434,6 @@ static void bcmgenet_tx_reclaim_all(struct net_device *dev) bcmgenet_tx_reclaim(dev, &priv->tx_rings[DESC_INDEX]); } -/* Transmits a single SKB (either head of a fragment or a single SKB) - * caller must hold priv->lock - */ -static int bcmgenet_xmit_single(struct net_device *dev, - struct sk_buff *skb, - u16 dma_desc_flags, - struct bcmgenet_tx_ring *ring) -{ - struct bcmgenet_priv *priv = netdev_priv(dev); - struct device *kdev = &priv->pdev->dev; - struct enet_cb *tx_cb_ptr; - unsigned int skb_len; - dma_addr_t mapping; - u32 length_status; - int ret; - - tx_cb_ptr = bcmgenet_get_txcb(priv, ring); - - if (unlikely(!tx_cb_ptr)) - BUG(); - - tx_cb_ptr->skb = skb; - - skb_len = skb_headlen(skb); - - mapping = dma_map_single(kdev, skb->data, skb_len, DMA_TO_DEVICE); - ret = dma_mapping_error(kdev, mapping); - if (ret) { - priv->mib.tx_dma_failed++; - netif_err(priv, tx_err, dev, "Tx DMA map failed\n"); - dev_kfree_skb(skb); - return ret; - } - - dma_unmap_addr_set(tx_cb_ptr, dma_addr, mapping); - dma_unmap_len_set(tx_cb_ptr, dma_len, skb_len); - length_status = (skb_len << DMA_BUFLENGTH_SHIFT) | dma_desc_flags | - (priv->hw_params->qtag_mask << DMA_TX_QTAG_SHIFT) | - DMA_TX_APPEND_CRC; - - if (skb->ip_summed == CHECKSUM_PARTIAL) - length_status |= DMA_TX_DO_CSUM; - - dmadesc_set(priv, tx_cb_ptr->bd_addr, mapping, length_status); - - return 0; -} - -/* Transmit a SKB fragment */ -static int bcmgenet_xmit_frag(struct net_device *dev, - skb_frag_t *frag, - u16 dma_desc_flags, - struct bcmgenet_tx_ring *ring) -{ - struct bcmgenet_priv *priv = netdev_priv(dev); - struct device *kdev = &priv->pdev->dev; - struct enet_cb *tx_cb_ptr; - unsigned int frag_size; - dma_addr_t mapping; - int ret; - - tx_cb_ptr = bcmgenet_get_txcb(priv, ring); - - if (unlikely(!tx_cb_ptr)) - BUG(); - - tx_cb_ptr->skb = NULL; - - frag_size = skb_frag_size(frag); - - mapping = skb_frag_dma_map(kdev, frag, 0, frag_size, DMA_TO_DEVICE); - ret = dma_mapping_error(kdev, mapping); - if (ret) { - priv->mib.tx_dma_failed++; - netif_err(priv, tx_err, dev, "%s: Tx DMA map failed\n", - __func__); - return ret; - } - - dma_unmap_addr_set(tx_cb_ptr, dma_addr, mapping); - dma_unmap_len_set(tx_cb_ptr, dma_len, frag_size); - - dmadesc_set(priv, tx_cb_ptr->bd_addr, mapping, - (frag_size << DMA_BUFLENGTH_SHIFT) | dma_desc_flags | - (priv->hw_params->qtag_mask << DMA_TX_QTAG_SHIFT)); - - return 0; -} - /* Reallocate the SKB to put enough headroom in front of it and insert * the transmit checksum offsets in the descriptors */ @@ -1535,11 +1500,16 @@ static struct sk_buff *bcmgenet_put_tx_csum(struct net_device *dev, static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) { struct bcmgenet_priv *priv = netdev_priv(dev); + struct device *kdev = &priv->pdev->dev; struct bcmgenet_tx_ring *ring = NULL; + struct enet_cb *tx_cb_ptr; struct netdev_queue *txq; unsigned long flags = 0; int nr_frags, index; - u16 dma_desc_flags; + dma_addr_t mapping; + unsigned int size; + skb_frag_t *frag; + u32 len_stat; int ret; int i; @@ -1592,29 +1562,53 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) } } - dma_desc_flags = DMA_SOP; - if (nr_frags == 0) - dma_desc_flags |= DMA_EOP; + for (i = 0; i <= nr_frags; i++) { + tx_cb_ptr = bcmgenet_get_txcb(priv, ring); - /* Transmit single SKB or head of fragment list */ - ret = bcmgenet_xmit_single(dev, skb, dma_desc_flags, ring); - if (ret) { - ret = NETDEV_TX_OK; - goto out; - } + if (unlikely(!tx_cb_ptr)) + BUG(); + + if (!i) { + /* Transmit single SKB or head of fragment list */ + GENET_CB(skb)->first_cb = tx_cb_ptr; + size = skb_headlen(skb); + mapping = dma_map_single(kdev, skb->data, size, + DMA_TO_DEVICE); + } else { + /* xmit fragment */ + frag = &skb_shinfo(skb)->frags[i - 1]; + size = skb_frag_size(frag); + mapping = skb_frag_dma_map(kdev, frag, 0, size, + DMA_TO_DEVICE); + } - /* xmit fragment */ - for (i = 0; i < nr_frags; i++) { - ret = bcmgenet_xmit_frag(dev, - &skb_shinfo(skb)->frags[i], - (i == nr_frags - 1) ? DMA_EOP : 0, - ring); + ret = dma_mapping_error(kdev, mapping); if (ret) { + priv->mib.tx_dma_failed++; + netif_err(priv, tx_err, dev, "Tx DMA map failed\n"); ret = NETDEV_TX_OK; - goto out; + goto out_unmap_frags; + } + dma_unmap_addr_set(tx_cb_ptr, dma_addr, mapping); + dma_unmap_len_set(tx_cb_ptr, dma_len, size); + + tx_cb_ptr->skb = skb; + + len_stat = (size << DMA_BUFLENGTH_SHIFT) | + (priv->hw_params->qtag_mask << DMA_TX_QTAG_SHIFT); + + if (!i) { + len_stat |= DMA_TX_APPEND_CRC | DMA_SOP; + if (skb->ip_summed == CHECKSUM_PARTIAL) + len_stat |= DMA_TX_DO_CSUM; } + if (i == nr_frags) + len_stat |= DMA_EOP; + + dmadesc_set(priv, tx_cb_ptr->bd_addr, mapping, len_stat); } + GENET_CB(skb)->last_cb = tx_cb_ptr; skb_tx_timestamp(skb); /* Decrement total BD count and advance our write pointer */ @@ -1635,6 +1629,19 @@ out: spin_unlock_irqrestore(&ring->lock, flags); return ret; + +out_unmap_frags: + /* Back up for failed control block mapping */ + bcmgenet_put_txcb(priv, ring); + + /* Unmap successfully mapped control blocks */ + while (i-- > 0) { + tx_cb_ptr = bcmgenet_put_txcb(priv, ring); + bcmgenet_free_tx_cb(kdev, tx_cb_ptr); + } + + dev_kfree_skb(skb); + goto out; } static struct sk_buff *bcmgenet_rx_refill(struct bcmgenet_priv *priv, @@ -1666,14 +1673,12 @@ static struct sk_buff *bcmgenet_rx_refill(struct bcmgenet_priv *priv, } /* Grab the current Rx skb from the ring and DMA-unmap it */ - rx_skb = cb->skb; - if (likely(rx_skb)) - dma_unmap_single(kdev, dma_unmap_addr(cb, dma_addr), - priv->rx_buf_len, DMA_FROM_DEVICE); + rx_skb = bcmgenet_free_rx_cb(kdev, cb); /* Put the new Rx skb on the ring */ cb->skb = skb; dma_unmap_addr_set(cb, dma_addr, mapping); + dma_unmap_len_set(cb, dma_len, priv->rx_buf_len); dmadesc_set_addr(priv, cb->bd_addr, mapping); /* Return the current Rx skb to caller */ @@ -1880,22 +1885,16 @@ static int bcmgenet_alloc_rx_buffers(struct bcmgenet_priv *priv, static void bcmgenet_free_rx_buffers(struct bcmgenet_priv *priv) { - struct device *kdev = &priv->pdev->dev; + struct sk_buff *skb; struct enet_cb *cb; int i; for (i = 0; i < priv->num_rx_bds; i++) { cb = &priv->rx_cbs[i]; - if (dma_unmap_addr(cb, dma_addr)) { - dma_unmap_single(kdev, - dma_unmap_addr(cb, dma_addr), - priv->rx_buf_len, DMA_FROM_DEVICE); - dma_unmap_addr_set(cb, dma_addr, 0); - } - - if (cb->skb) - bcmgenet_free_cb(cb); + skb = bcmgenet_free_rx_cb(&priv->pdev->dev, cb); + if (skb) + dev_kfree_skb_any(skb); } } @@ -2479,8 +2478,10 @@ static int bcmgenet_dma_teardown(struct bcmgenet_priv *priv) static void bcmgenet_fini_dma(struct bcmgenet_priv *priv) { - int i; struct netdev_queue *txq; + struct sk_buff *skb; + struct enet_cb *cb; + int i; bcmgenet_fini_rx_napi(priv); bcmgenet_fini_tx_napi(priv); @@ -2489,10 +2490,10 @@ static void bcmgenet_fini_dma(struct bcmgenet_priv *priv) bcmgenet_dma_teardown(priv); for (i = 0; i < priv->num_tx_bds; i++) { - if (priv->tx_cbs[i].skb != NULL) { - dev_kfree_skb(priv->tx_cbs[i].skb); - priv->tx_cbs[i].skb = NULL; - } + cb = priv->tx_cbs + i; + skb = bcmgenet_free_tx_cb(&priv->pdev->dev, cb); + if (skb) + dev_kfree_skb(skb); } for (i = 0; i < priv->hw_params->tx_queues; i++) { diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index efd07020b89f..b9344de669f8 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -544,6 +544,8 @@ struct bcmgenet_hw_params { }; struct bcmgenet_skb_cb { + struct enet_cb *first_cb; /* First control block of SKB */ + struct enet_cb *last_cb; /* Last control block of SKB */ unsigned int bytes_sent; /* bytes on the wire (no TSB) */ }; diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c index 28ecda3d3404..ebd353bc78ff 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c @@ -335,7 +335,7 @@ lio_ethtool_get_channels(struct net_device *dev, static int lio_get_eeprom_len(struct net_device *netdev) { - u8 buf[128]; + u8 buf[192]; struct lio *lio = GET_LIO(netdev); struct octeon_device *oct_dev = lio->oct_dev; struct octeon_board_info *board_info; diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index a0ca68ce3fbb..79112563a25a 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1008,7 +1008,7 @@ static void bgx_print_qlm_mode(struct bgx *bgx, u8 lmacid) { struct device *dev = &bgx->pdev->dev; struct lmac *lmac; - char str[20]; + char str[27]; if (!bgx->is_dlm && lmacid) return; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c index 50517cfd9671..9f9d6cae39d5 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c @@ -441,7 +441,8 @@ void cxgb4_ptp_init(struct adapter *adapter) adapter->ptp_clock = ptp_clock_register(&adapter->ptp_clock_info, &adapter->pdev->dev); - if (!adapter->ptp_clock) { + if (IS_ERR_OR_NULL(adapter->ptp_clock)) { + adapter->ptp_clock = NULL; dev_err(adapter->pdev_dev, "PTP %s Clock registration has failed\n", __func__); return; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h index 99987d8e437e..aa28299aef5f 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h @@ -174,6 +174,8 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN CH_PCI_ID_TABLE_FENTRY(0x50a0), /* Custom T540-CR */ CH_PCI_ID_TABLE_FENTRY(0x50a1), /* Custom T540-CR */ CH_PCI_ID_TABLE_FENTRY(0x50a2), /* Custom T540-KR4 */ + CH_PCI_ID_TABLE_FENTRY(0x50a3), /* Custom T580-KR4 */ + CH_PCI_ID_TABLE_FENTRY(0x50a4), /* Custom 2x T540-CR */ /* T6 adapters: */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c index ff864a187d5a..a37166ee577b 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -776,8 +776,9 @@ void hns_ae_update_led_status(struct hnae_handle *handle) assert(handle); mac_cb = hns_get_mac_cb(handle); - if (!mac_cb->cpld_ctrl) + if (mac_cb->media_type != HNAE_MEDIA_TYPE_FIBER) return; + hns_set_led_opt(mac_cb); } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c index 7a8addda726e..408b63faf9a8 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c @@ -53,6 +53,34 @@ static u32 dsaf_read_sub(struct dsaf_device *dsaf_dev, u32 reg) return ret; } +static void hns_dsaf_acpi_ledctrl_by_port(struct hns_mac_cb *mac_cb, u8 op_type, + u32 link, u32 port, u32 act) +{ + union acpi_object *obj; + union acpi_object obj_args[3], argv4; + + obj_args[0].integer.type = ACPI_TYPE_INTEGER; + obj_args[0].integer.value = link; + obj_args[1].integer.type = ACPI_TYPE_INTEGER; + obj_args[1].integer.value = port; + obj_args[2].integer.type = ACPI_TYPE_INTEGER; + obj_args[2].integer.value = act; + + argv4.type = ACPI_TYPE_PACKAGE; + argv4.package.count = 3; + argv4.package.elements = obj_args; + + obj = acpi_evaluate_dsm(ACPI_HANDLE(mac_cb->dev), + &hns_dsaf_acpi_dsm_guid, 0, op_type, &argv4); + if (!obj) { + dev_warn(mac_cb->dev, "ledctrl fail, link:%d port:%d act:%d!\n", + link, port, act); + return; + } + + ACPI_FREE(obj); +} + static void hns_cpld_set_led(struct hns_mac_cb *mac_cb, int link_status, u16 speed, int data) { @@ -93,6 +121,18 @@ static void hns_cpld_set_led(struct hns_mac_cb *mac_cb, int link_status, } } +static void hns_cpld_set_led_acpi(struct hns_mac_cb *mac_cb, int link_status, + u16 speed, int data) +{ + if (!mac_cb) { + pr_err("cpld_led_set mac_cb is null!\n"); + return; + } + + hns_dsaf_acpi_ledctrl_by_port(mac_cb, HNS_OP_LED_SET_FUNC, + link_status, mac_cb->mac_id, data); +} + static void cpld_led_reset(struct hns_mac_cb *mac_cb) { if (!mac_cb || !mac_cb->cpld_ctrl) @@ -103,6 +143,20 @@ static void cpld_led_reset(struct hns_mac_cb *mac_cb) mac_cb->cpld_led_value = CPLD_LED_DEFAULT_VALUE; } +static void cpld_led_reset_acpi(struct hns_mac_cb *mac_cb) +{ + if (!mac_cb) { + pr_err("cpld_led_reset mac_cb is null!\n"); + return; + } + + if (mac_cb->media_type != HNAE_MEDIA_TYPE_FIBER) + return; + + hns_dsaf_acpi_ledctrl_by_port(mac_cb, HNS_OP_LED_SET_FUNC, + 0, mac_cb->mac_id, 0); +} + static int cpld_set_led_id(struct hns_mac_cb *mac_cb, enum hnae_led_state status) { @@ -604,8 +658,8 @@ struct dsaf_misc_op *hns_misc_op_get(struct dsaf_device *dsaf_dev) misc_op->cfg_serdes_loopback = hns_mac_config_sds_loopback; } else if (is_acpi_node(dsaf_dev->dev->fwnode)) { - misc_op->cpld_set_led = hns_cpld_set_led; - misc_op->cpld_reset_led = cpld_led_reset; + misc_op->cpld_set_led = hns_cpld_set_led_acpi; + misc_op->cpld_reset_led = cpld_led_reset_acpi; misc_op->cpld_set_led_id = cpld_set_led_id; misc_op->dsaf_reset = hns_dsaf_rst_acpi; diff --git a/drivers/net/ethernet/mellanox/mlx4/alloc.c b/drivers/net/ethernet/mellanox/mlx4/alloc.c index d94b3744a5b9..b651c1210555 100644 --- a/drivers/net/ethernet/mellanox/mlx4/alloc.c +++ b/drivers/net/ethernet/mellanox/mlx4/alloc.c @@ -283,7 +283,7 @@ int mlx4_zone_add_one(struct mlx4_zone_allocator *zone_alloc, } /* Should be called under a lock */ -static int __mlx4_zone_remove_one_entry(struct mlx4_zone_entry *entry) +static void __mlx4_zone_remove_one_entry(struct mlx4_zone_entry *entry) { struct mlx4_zone_allocator *zone_alloc = entry->allocator; @@ -315,8 +315,6 @@ static int __mlx4_zone_remove_one_entry(struct mlx4_zone_entry *entry) } zone_alloc->mask = mask; } - - return 0; } void mlx4_zone_allocator_destroy(struct mlx4_zone_allocator *zone_alloc) @@ -457,7 +455,7 @@ struct mlx4_bitmap *mlx4_zone_get_bitmap(struct mlx4_zone_allocator *zones, u32 int mlx4_zone_remove_one(struct mlx4_zone_allocator *zones, u32 uid) { struct mlx4_zone_entry *zone; - int res; + int res = 0; spin_lock(&zones->lock); @@ -468,7 +466,7 @@ int mlx4_zone_remove_one(struct mlx4_zone_allocator *zones, u32 uid) goto out; } - res = __mlx4_zone_remove_one_entry(zone); + __mlx4_zone_remove_one_entry(zone); out: spin_unlock(&zones->lock); diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index 746d94e28470..60850bfa3d32 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -766,11 +766,13 @@ static void emac_shutdown(struct platform_device *pdev) struct emac_adapter *adpt = netdev_priv(netdev); struct emac_sgmii *sgmii = &adpt->phy; - /* Closing the SGMII turns off its interrupts */ - sgmii->close(adpt); + if (netdev->flags & IFF_UP) { + /* Closing the SGMII turns off its interrupts */ + sgmii->close(adpt); - /* Resetting the MAC turns off all DMA and its interrupts */ - emac_mac_reset(adpt); + /* Resetting the MAC turns off all DMA and its interrupts */ + emac_mac_reset(adpt); + } } static struct platform_driver emac_platform_driver = { diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c index b607936e1b3e..9c0488e0f08e 100644 --- a/drivers/net/ethernet/sgi/ioc3-eth.c +++ b/drivers/net/ethernet/sgi/ioc3-eth.c @@ -90,17 +90,13 @@ struct ioc3_private { spinlock_t ioc3_lock; struct mii_if_info mii; + struct net_device *dev; struct pci_dev *pdev; /* Members used by autonegotiation */ struct timer_list ioc3_timer; }; -static inline struct net_device *priv_netdev(struct ioc3_private *dev) -{ - return (void *)dev - ((sizeof(struct net_device) + 31) & ~31); -} - static int ioc3_ioctl(struct net_device *dev, struct ifreq *rq, int cmd); static void ioc3_set_multicast_list(struct net_device *dev); static int ioc3_start_xmit(struct sk_buff *skb, struct net_device *dev); @@ -427,7 +423,7 @@ static void ioc3_get_eaddr_nic(struct ioc3_private *ip) nic[i] = nic_read_byte(ioc3); for (i = 2; i < 8; i++) - priv_netdev(ip)->dev_addr[i - 2] = nic[i]; + ip->dev->dev_addr[i - 2] = nic[i]; } /* @@ -439,7 +435,7 @@ static void ioc3_get_eaddr(struct ioc3_private *ip) { ioc3_get_eaddr_nic(ip); - printk("Ethernet address is %pM.\n", priv_netdev(ip)->dev_addr); + printk("Ethernet address is %pM.\n", ip->dev->dev_addr); } static void __ioc3_set_mac_address(struct net_device *dev) @@ -790,13 +786,12 @@ static void ioc3_timer(unsigned long data) */ static int ioc3_mii_init(struct ioc3_private *ip) { - struct net_device *dev = priv_netdev(ip); int i, found = 0, res = 0; int ioc3_phy_workaround = 1; u16 word; for (i = 0; i < 32; i++) { - word = ioc3_mdio_read(dev, i, MII_PHYSID1); + word = ioc3_mdio_read(ip->dev, i, MII_PHYSID1); if (word != 0xffff && word != 0x0000) { found = 1; @@ -1276,6 +1271,7 @@ static int ioc3_probe(struct pci_dev *pdev, const struct pci_device_id *ent) SET_NETDEV_DEV(dev, &pdev->dev); ip = netdev_priv(dev); + ip->dev = dev; dev->irq = pdev->irq; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index f233bf8b4ebb..c4407e8e39a3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -117,7 +117,7 @@ static void dwmac4_tx_queue_routing(struct mac_device_info *hw, void __iomem *ioaddr = hw->pcsr; u32 value; - const struct stmmac_rx_routing route_possibilities[] = { + static const struct stmmac_rx_routing route_possibilities[] = { { GMAC_RXQCTRL_AVCPQ_MASK, GMAC_RXQCTRL_AVCPQ_SHIFT }, { GMAC_RXQCTRL_PTPQ_MASK, GMAC_RXQCTRL_PTPQ_SHIFT }, { GMAC_RXQCTRL_DCBCPQ_MASK, GMAC_RXQCTRL_DCBCPQ_SHIFT }, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 1853f7ff6657..1763e48c84e2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -4120,8 +4120,15 @@ int stmmac_dvr_probe(struct device *device, if ((phyaddr >= 0) && (phyaddr <= 31)) priv->plat->phy_addr = phyaddr; - if (priv->plat->stmmac_rst) + if (priv->plat->stmmac_rst) { + ret = reset_control_assert(priv->plat->stmmac_rst); reset_control_deassert(priv->plat->stmmac_rst); + /* Some reset controllers have only reset callback instead of + * assert + deassert callbacks pair. + */ + if (ret == -ENOTSUPP) + reset_control_reset(priv->plat->stmmac_rst); + } /* Init MAC and get the capabilities */ ret = stmmac_hw_init(priv); diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 46cb7f8955a2..4bb04aaf9650 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -9532,7 +9532,7 @@ static struct niu_parent *niu_get_parent(struct niu *np, p = niu_new_parent(np, id, ptype); if (p) { - char port_name[6]; + char port_name[8]; int err; sprintf(port_name, "port%d", port); @@ -9553,7 +9553,7 @@ static void niu_put_parent(struct niu *np) { struct niu_parent *p = np->parent; u8 port = np->port; - char port_name[6]; + char port_name[8]; BUG_ON(!p || p->ports[port] != np); diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c index 711fbbbc4b1f..163d8d16bc24 100644 --- a/drivers/net/ethernet/tehuti/tehuti.c +++ b/drivers/net/ethernet/tehuti/tehuti.c @@ -654,6 +654,8 @@ static int bdx_ioctl_priv(struct net_device *ndev, struct ifreq *ifr, int cmd) RET(-EFAULT); } DBG("%d 0x%x 0x%x\n", data[0], data[1], data[2]); + } else { + return -EOPNOTSUPP; } if (!capable(CAP_SYS_RAWIO)) diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 1850e348f555..badd0a8caeb9 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -3089,6 +3089,31 @@ static int cpsw_probe(struct platform_device *pdev) cpsw->quirk_irq = true; } + ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + + ndev->netdev_ops = &cpsw_netdev_ops; + ndev->ethtool_ops = &cpsw_ethtool_ops; + netif_napi_add(ndev, &cpsw->napi_rx, cpsw_rx_poll, CPSW_POLL_WEIGHT); + netif_tx_napi_add(ndev, &cpsw->napi_tx, cpsw_tx_poll, CPSW_POLL_WEIGHT); + cpsw_split_res(ndev); + + /* register the network device */ + SET_NETDEV_DEV(ndev, &pdev->dev); + ret = register_netdev(ndev); + if (ret) { + dev_err(priv->dev, "error registering net device\n"); + ret = -ENODEV; + goto clean_ale_ret; + } + + if (cpsw->data.dual_emac) { + ret = cpsw_probe_dual_emac(priv); + if (ret) { + cpsw_err(priv, probe, "error probe slave 2 emac interface\n"); + goto clean_unregister_netdev_ret; + } + } + /* Grab RX and TX IRQs. Note that we also have RX_THRESHOLD and * MISC IRQs which are always kept disabled with this driver so * we will not request them. @@ -3127,33 +3152,9 @@ static int cpsw_probe(struct platform_device *pdev) goto clean_ale_ret; } - ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; - - ndev->netdev_ops = &cpsw_netdev_ops; - ndev->ethtool_ops = &cpsw_ethtool_ops; - netif_napi_add(ndev, &cpsw->napi_rx, cpsw_rx_poll, CPSW_POLL_WEIGHT); - netif_tx_napi_add(ndev, &cpsw->napi_tx, cpsw_tx_poll, CPSW_POLL_WEIGHT); - cpsw_split_res(ndev); - - /* register the network device */ - SET_NETDEV_DEV(ndev, &pdev->dev); - ret = register_netdev(ndev); - if (ret) { - dev_err(priv->dev, "error registering net device\n"); - ret = -ENODEV; - goto clean_ale_ret; - } - cpsw_notice(priv, probe, "initialized device (regs %pa, irq %d, pool size %d)\n", &ss_res->start, ndev->irq, dma_params.descs_pool_size); - if (cpsw->data.dual_emac) { - ret = cpsw_probe_dual_emac(priv); - if (ret) { - cpsw_err(priv, probe, "error probe slave 2 emac interface\n"); - goto clean_unregister_netdev_ret; - } - } pm_runtime_put(&pdev->dev); diff --git a/drivers/net/phy/mdio-mux.c b/drivers/net/phy/mdio-mux.c index 00755b6a42cf..c608e1dfaf09 100644 --- a/drivers/net/phy/mdio-mux.c +++ b/drivers/net/phy/mdio-mux.c @@ -135,8 +135,8 @@ int mdio_mux_init(struct device *dev, for_each_available_child_of_node(dev->of_node, child_bus_node) { int v; - v = of_mdio_parse_addr(dev, child_bus_node); - if (v < 0) { + r = of_property_read_u32(child_bus_node, "reg", &v); + if (r) { dev_err(dev, "Error: Failed to find reg for child %s\n", of_node_full_name(child_bus_node)); diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 13028833bee3..bd4303944e44 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -120,6 +120,7 @@ struct ppp { int n_channels; /* how many channels are attached 54 */ spinlock_t rlock; /* lock for receive side 58 */ spinlock_t wlock; /* lock for transmit side 5c */ + int *xmit_recursion __percpu; /* xmit recursion detect */ int mru; /* max receive unit 60 */ unsigned int flags; /* control bits 64 */ unsigned int xstate; /* transmit state bits 68 */ @@ -1025,6 +1026,7 @@ static int ppp_dev_configure(struct net *src_net, struct net_device *dev, struct ppp *ppp = netdev_priv(dev); int indx; int err; + int cpu; ppp->dev = dev; ppp->ppp_net = src_net; @@ -1039,6 +1041,15 @@ static int ppp_dev_configure(struct net *src_net, struct net_device *dev, INIT_LIST_HEAD(&ppp->channels); spin_lock_init(&ppp->rlock); spin_lock_init(&ppp->wlock); + + ppp->xmit_recursion = alloc_percpu(int); + if (!ppp->xmit_recursion) { + err = -ENOMEM; + goto err1; + } + for_each_possible_cpu(cpu) + (*per_cpu_ptr(ppp->xmit_recursion, cpu)) = 0; + #ifdef CONFIG_PPP_MULTILINK ppp->minseq = -1; skb_queue_head_init(&ppp->mrq); @@ -1050,11 +1061,15 @@ static int ppp_dev_configure(struct net *src_net, struct net_device *dev, err = ppp_unit_register(ppp, conf->unit, conf->ifname_is_set); if (err < 0) - return err; + goto err2; conf->file->private_data = &ppp->file; return 0; +err2: + free_percpu(ppp->xmit_recursion); +err1: + return err; } static const struct nla_policy ppp_nl_policy[IFLA_PPP_MAX + 1] = { @@ -1400,18 +1415,16 @@ static void __ppp_xmit_process(struct ppp *ppp) ppp_xmit_unlock(ppp); } -static DEFINE_PER_CPU(int, ppp_xmit_recursion); - static void ppp_xmit_process(struct ppp *ppp) { local_bh_disable(); - if (unlikely(__this_cpu_read(ppp_xmit_recursion))) + if (unlikely(*this_cpu_ptr(ppp->xmit_recursion))) goto err; - __this_cpu_inc(ppp_xmit_recursion); + (*this_cpu_ptr(ppp->xmit_recursion))++; __ppp_xmit_process(ppp); - __this_cpu_dec(ppp_xmit_recursion); + (*this_cpu_ptr(ppp->xmit_recursion))--; local_bh_enable(); @@ -1905,7 +1918,7 @@ static void __ppp_channel_push(struct channel *pch) read_lock(&pch->upl); ppp = pch->ppp; if (ppp) - __ppp_xmit_process(ppp); + ppp_xmit_process(ppp); read_unlock(&pch->upl); } } @@ -1914,9 +1927,7 @@ static void ppp_channel_push(struct channel *pch) { local_bh_disable(); - __this_cpu_inc(ppp_xmit_recursion); __ppp_channel_push(pch); - __this_cpu_dec(ppp_xmit_recursion); local_bh_enable(); } @@ -3057,6 +3068,7 @@ static void ppp_destroy_interface(struct ppp *ppp) #endif /* CONFIG_PPP_FILTER */ kfree_skb(ppp->xmit_pending); + free_percpu(ppp->xmit_recursion); free_netdev(ppp->dev); } diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index d103a1d4fb36..8f572b9f3625 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -768,8 +768,10 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_ u8 *buf; int len; int temp; + int err; u8 iface_no; struct usb_cdc_parsed_header hdr; + u16 curr_ntb_format; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) @@ -874,6 +876,32 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_ goto error2; } + /* + * Some Huawei devices have been observed to come out of reset in NDP32 mode. + * Let's check if this is the case, and set the device to NDP16 mode again if + * needed. + */ + if (ctx->drvflags & CDC_NCM_FLAG_RESET_NTB16) { + err = usbnet_read_cmd(dev, USB_CDC_GET_NTB_FORMAT, + USB_TYPE_CLASS | USB_DIR_IN | USB_RECIP_INTERFACE, + 0, iface_no, &curr_ntb_format, 2); + if (err < 0) { + goto error2; + } + + if (curr_ntb_format == USB_CDC_NCM_NTB32_FORMAT) { + dev_info(&intf->dev, "resetting NTB format to 16-bit"); + err = usbnet_write_cmd(dev, USB_CDC_SET_NTB_FORMAT, + USB_TYPE_CLASS | USB_DIR_OUT + | USB_RECIP_INTERFACE, + USB_CDC_NCM_NTB16_FORMAT, + iface_no, NULL, 0); + + if (err < 0) + goto error2; + } + } + cdc_ncm_find_endpoints(dev, ctx->data); cdc_ncm_find_endpoints(dev, ctx->control); if (!dev->in || !dev->out || !dev->status) { diff --git a/drivers/net/usb/huawei_cdc_ncm.c b/drivers/net/usb/huawei_cdc_ncm.c index 2680a65cd5e4..63f28908afda 100644 --- a/drivers/net/usb/huawei_cdc_ncm.c +++ b/drivers/net/usb/huawei_cdc_ncm.c @@ -80,6 +80,12 @@ static int huawei_cdc_ncm_bind(struct usbnet *usbnet_dev, * be at the end of the frame. */ drvflags |= CDC_NCM_FLAG_NDP_TO_END; + + /* Additionally, it has been reported that some Huawei E3372H devices, with + * firmware version 21.318.01.00.541, come out of reset in NTB32 format mode, hence + * needing to be set to the NTB16 one again. + */ + drvflags |= CDC_NCM_FLAG_RESET_NTB16; ret = cdc_ncm_bind_common(usbnet_dev, intf, 1, drvflags); if (ret) goto err; diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 2dfca96a63b6..340c13484e5c 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -898,6 +898,7 @@ static const struct ethtool_ops smsc95xx_ethtool_ops = { .set_wol = smsc95xx_ethtool_set_wol, .get_link_ksettings = smsc95xx_get_link_ksettings, .set_link_ksettings = smsc95xx_set_link_ksettings, + .get_ts_info = ethtool_op_get_ts_info, }; static int smsc95xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h index ba1c9f93592b..9c51b8be0038 100644 --- a/drivers/net/vmxnet3/vmxnet3_int.h +++ b/drivers/net/vmxnet3/vmxnet3_int.h @@ -311,7 +311,7 @@ struct vmxnet3_intr { u8 num_intrs; /* # of intr vectors */ u8 event_intr_idx; /* idx of the intr vector for event */ u8 mod_levels[VMXNET3_LINUX_MAX_MSIX_VECT]; /* moderation level */ - char event_msi_vector_name[IFNAMSIZ+11]; + char event_msi_vector_name[IFNAMSIZ+17]; #ifdef CONFIG_PCI_MSI struct msix_entry msix_entries[VMXNET3_LINUX_MAX_MSIX_VECT]; #endif diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c index 6e2e760d98b1..0b75def39c6c 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c @@ -5704,7 +5704,7 @@ static void rt2800_init_freq_calibration(struct rt2x00_dev *rt2x00dev) static void rt2800_init_bbp_5592_glrt(struct rt2x00_dev *rt2x00dev) { - const u8 glrt_table[] = { + static const u8 glrt_table[] = { 0xE0, 0x1F, 0X38, 0x32, 0x08, 0x28, 0x19, 0x0A, 0xFF, 0x00, /* 128 ~ 137 */ 0x16, 0x10, 0x10, 0x0B, 0x36, 0x2C, 0x26, 0x24, 0x42, 0x36, /* 138 ~ 147 */ 0x30, 0x2D, 0x4C, 0x46, 0x3D, 0x40, 0x3E, 0x42, 0x3D, 0x40, /* 148 ~ 157 */ diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 360c082e885c..d41d40ac3efd 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -85,7 +85,7 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, int __ret = 0; \ if (cgroup_bpf_enabled && (sock_ops)->sk) { \ typeof(sk) __sk = sk_to_full_sk((sock_ops)->sk); \ - if (sk_fullsock(__sk)) \ + if (__sk && sk_fullsock(__sk)) \ __ret = __cgroup_bpf_run_filter_sock_ops(__sk, \ sock_ops, \ BPF_CGROUP_SOCK_OPS); \ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 621076f56251..8e5d31f6faef 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -43,6 +43,7 @@ struct bpf_reg_state { u32 min_align; u32 aux_off; u32 aux_off_align; + bool value_from_signed; }; enum bpf_stack_slot_type { diff --git a/include/linux/jhash.h b/include/linux/jhash.h index 348c6f47e4cc..8037850f3104 100644 --- a/include/linux/jhash.h +++ b/include/linux/jhash.h @@ -85,19 +85,18 @@ static inline u32 jhash(const void *key, u32 length, u32 initval) k += 12; } /* Last block: affect all 32 bits of (c) */ - /* All the case statements fall through */ switch (length) { - case 12: c += (u32)k[11]<<24; - case 11: c += (u32)k[10]<<16; - case 10: c += (u32)k[9]<<8; - case 9: c += k[8]; - case 8: b += (u32)k[7]<<24; - case 7: b += (u32)k[6]<<16; - case 6: b += (u32)k[5]<<8; - case 5: b += k[4]; - case 4: a += (u32)k[3]<<24; - case 3: a += (u32)k[2]<<16; - case 2: a += (u32)k[1]<<8; + case 12: c += (u32)k[11]<<24; /* fall through */ + case 11: c += (u32)k[10]<<16; /* fall through */ + case 10: c += (u32)k[9]<<8; /* fall through */ + case 9: c += k[8]; /* fall through */ + case 8: b += (u32)k[7]<<24; /* fall through */ + case 7: b += (u32)k[6]<<16; /* fall through */ + case 6: b += (u32)k[5]<<8; /* fall through */ + case 5: b += k[4]; /* fall through */ + case 4: a += (u32)k[3]<<24; /* fall through */ + case 3: a += (u32)k[2]<<16; /* fall through */ + case 2: a += (u32)k[1]<<8; /* fall through */ case 1: a += k[0]; __jhash_final(a, b, c); case 0: /* Nothing left to add */ @@ -131,10 +130,10 @@ static inline u32 jhash2(const u32 *k, u32 length, u32 initval) k += 3; } - /* Handle the last 3 u32's: all the case statements fall through */ + /* Handle the last 3 u32's */ switch (length) { - case 3: c += k[2]; - case 2: b += k[1]; + case 3: c += k[2]; /* fall through */ + case 2: b += k[1]; /* fall through */ case 1: a += k[0]; __jhash_final(a, b, c); case 0: /* Nothing left to add */ diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index a4b97be30b28..22f081065d49 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -61,8 +61,6 @@ typedef unsigned int nf_hookfn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); struct nf_hook_ops { - struct list_head list; - /* User fills in from here down. */ nf_hookfn *hook; struct net_device *dev; @@ -160,13 +158,6 @@ int nf_register_net_hooks(struct net *net, const struct nf_hook_ops *reg, void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg, unsigned int n); -int nf_register_hook(struct nf_hook_ops *reg); -void nf_unregister_hook(struct nf_hook_ops *reg); -int nf_register_hooks(struct nf_hook_ops *reg, unsigned int n); -void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n); -int _nf_register_hooks(struct nf_hook_ops *reg, unsigned int n); -void _nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n); - /* Functions to register get/setsockopt ranges (non-inclusive). You need to check permissions yourself! */ int nf_register_sockopt(struct nf_sockopt_ops *reg); diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index 021f7a88f52c..1a59699cf82a 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -83,6 +83,7 @@ /* Driver flags */ #define CDC_NCM_FLAG_NDP_TO_END 0x02 /* NDP is placed at end of frame */ #define CDC_MBIM_FLAG_AVOID_ALTSETTING_TOGGLE 0x04 /* Avoid altsetting toggle during init */ +#define CDC_NCM_FLAG_RESET_NTB16 0x08 /* set NDP16 one more time after altsetting switch */ #define cdc_ncm_comm_intf_is_mbim(x) ((x)->desc.bInterfaceSubClass == USB_CDC_SUBCLASS_MBIM && \ (x)->desc.bInterfaceProtocol == USB_CDC_PROTO_NONE) diff --git a/include/net/netlink.h b/include/net/netlink.h index 01709172b3d3..ef8e6c3a80a6 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -98,8 +98,8 @@ * nla_put_u8(skb, type, value) add u8 attribute to skb * nla_put_u16(skb, type, value) add u16 attribute to skb * nla_put_u32(skb, type, value) add u32 attribute to skb - * nla_put_u64_64bits(skb, type, - * value, padattr) add u64 attribute to skb + * nla_put_u64_64bit(skb, type, + * value, padattr) add u64 attribute to skb * nla_put_s8(skb, type, value) add s8 attribute to skb * nla_put_s16(skb, type, value) add s16 attribute to skb * nla_put_s32(skb, type, value) add s32 attribute to skb diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index a9519a06a23b..980807d7506f 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -469,6 +469,8 @@ _sctp_walk_params((pos), (chunk), ntohs((chunk)->chunk_hdr.length), member) #define _sctp_walk_params(pos, chunk, end, member)\ for (pos.v = chunk->member;\ + (pos.v + offsetof(struct sctp_paramhdr, length) + sizeof(pos.p->length) <\ + (void *)chunk + end) &&\ pos.v <= (void *)chunk + end - ntohs(pos.p->length) &&\ ntohs(pos.p->length) >= sizeof(struct sctp_paramhdr);\ pos.v += SCTP_PAD4(ntohs(pos.p->length))) @@ -479,6 +481,8 @@ _sctp_walk_errors((err), (chunk_hdr), ntohs((chunk_hdr)->length)) #define _sctp_walk_errors(err, chunk_hdr, end)\ for (err = (sctp_errhdr_t *)((void *)chunk_hdr + \ sizeof(struct sctp_chunkhdr));\ + ((void *)err + offsetof(sctp_errhdr_t, length) + sizeof(err->length) <\ + (void *)chunk_hdr + end) &&\ (void *)err <= (void *)chunk_hdr + end - ntohs(err->length) &&\ ntohs(err->length) >= sizeof(sctp_errhdr_t); \ err = (sctp_errhdr_t *)((void *)err + SCTP_PAD4(ntohs(err->length)))) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6a86723c5b64..af9e84a4944e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -504,6 +504,7 @@ static void reset_reg_range_values(struct bpf_reg_state *regs, u32 regno) { regs[regno].min_value = BPF_REGISTER_MIN_RANGE; regs[regno].max_value = BPF_REGISTER_MAX_RANGE; + regs[regno].value_from_signed = false; regs[regno].min_align = 0; } @@ -777,12 +778,13 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, return -EACCES; } -static bool is_pointer_value(struct bpf_verifier_env *env, int regno) +static bool __is_pointer_value(bool allow_ptr_leaks, + const struct bpf_reg_state *reg) { - if (env->allow_ptr_leaks) + if (allow_ptr_leaks) return false; - switch (env->cur_state.regs[regno].type) { + switch (reg->type) { case UNKNOWN_VALUE: case CONST_IMM: return false; @@ -791,6 +793,11 @@ static bool is_pointer_value(struct bpf_verifier_env *env, int regno) } } +static bool is_pointer_value(struct bpf_verifier_env *env, int regno) +{ + return __is_pointer_value(env->allow_ptr_leaks, &env->cur_state.regs[regno]); +} + static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg, int off, int size, bool strict) { @@ -1832,10 +1839,24 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, dst_align = dst_reg->min_align; /* We don't know anything about what was done to this register, mark it - * as unknown. + * as unknown. Also, if both derived bounds came from signed/unsigned + * mixed compares and one side is unbounded, we cannot really do anything + * with them as boundaries cannot be trusted. Thus, arithmetic of two + * regs of such kind will get invalidated bounds on the dst side. */ - if (min_val == BPF_REGISTER_MIN_RANGE && - max_val == BPF_REGISTER_MAX_RANGE) { + if ((min_val == BPF_REGISTER_MIN_RANGE && + max_val == BPF_REGISTER_MAX_RANGE) || + (BPF_SRC(insn->code) == BPF_X && + ((min_val != BPF_REGISTER_MIN_RANGE && + max_val == BPF_REGISTER_MAX_RANGE) || + (min_val == BPF_REGISTER_MIN_RANGE && + max_val != BPF_REGISTER_MAX_RANGE) || + (dst_reg->min_value != BPF_REGISTER_MIN_RANGE && + dst_reg->max_value == BPF_REGISTER_MAX_RANGE) || + (dst_reg->min_value == BPF_REGISTER_MIN_RANGE && + dst_reg->max_value != BPF_REGISTER_MAX_RANGE)) && + regs[insn->dst_reg].value_from_signed != + regs[insn->src_reg].value_from_signed)) { reset_reg_range_values(regs, insn->dst_reg); return; } @@ -2023,6 +2044,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) regs[insn->dst_reg].max_value = insn->imm; regs[insn->dst_reg].min_value = insn->imm; regs[insn->dst_reg].min_align = calc_align(insn->imm); + regs[insn->dst_reg].value_from_signed = false; } } else if (opcode > BPF_END) { @@ -2198,40 +2220,63 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg, struct bpf_reg_state *false_reg, u64 val, u8 opcode) { + bool value_from_signed = true; + bool is_range = true; + switch (opcode) { case BPF_JEQ: /* If this is false then we know nothing Jon Snow, but if it is * true then we know for sure. */ true_reg->max_value = true_reg->min_value = val; + is_range = false; break; case BPF_JNE: /* If this is true we know nothing Jon Snow, but if it is false * we know the value for sure; */ false_reg->max_value = false_reg->min_value = val; + is_range = false; break; case BPF_JGT: - /* Unsigned comparison, the minimum value is 0. */ - false_reg->min_value = 0; + value_from_signed = false; /* fallthrough */ case BPF_JSGT: + if (true_reg->value_from_signed != value_from_signed) + reset_reg_range_values(true_reg, 0); + if (false_reg->value_from_signed != value_from_signed) + reset_reg_range_values(false_reg, 0); + if (opcode == BPF_JGT) { + /* Unsigned comparison, the minimum value is 0. */ + false_reg->min_value = 0; + } /* If this is false then we know the maximum val is val, * otherwise we know the min val is val+1. */ false_reg->max_value = val; + false_reg->value_from_signed = value_from_signed; true_reg->min_value = val + 1; + true_reg->value_from_signed = value_from_signed; break; case BPF_JGE: - /* Unsigned comparison, the minimum value is 0. */ - false_reg->min_value = 0; + value_from_signed = false; /* fallthrough */ case BPF_JSGE: + if (true_reg->value_from_signed != value_from_signed) + reset_reg_range_values(true_reg, 0); + if (false_reg->value_from_signed != value_from_signed) + reset_reg_range_values(false_reg, 0); + if (opcode == BPF_JGE) { + /* Unsigned comparison, the minimum value is 0. */ + false_reg->min_value = 0; + } /* If this is false then we know the maximum value is val - 1, * otherwise we know the mimimum value is val. */ false_reg->max_value = val - 1; + false_reg->value_from_signed = value_from_signed; true_reg->min_value = val; + true_reg->value_from_signed = value_from_signed; break; default: break; @@ -2239,6 +2284,12 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg, check_reg_overflow(false_reg); check_reg_overflow(true_reg); + if (is_range) { + if (__is_pointer_value(false, false_reg)) + reset_reg_range_values(false_reg, 0); + if (__is_pointer_value(false, true_reg)) + reset_reg_range_values(true_reg, 0); + } } /* Same as above, but for the case that dst_reg is a CONST_IMM reg and src_reg @@ -2248,41 +2299,64 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg, struct bpf_reg_state *false_reg, u64 val, u8 opcode) { + bool value_from_signed = true; + bool is_range = true; + switch (opcode) { case BPF_JEQ: /* If this is false then we know nothing Jon Snow, but if it is * true then we know for sure. */ true_reg->max_value = true_reg->min_value = val; + is_range = false; break; case BPF_JNE: /* If this is true we know nothing Jon Snow, but if it is false * we know the value for sure; */ false_reg->max_value = false_reg->min_value = val; + is_range = false; break; case BPF_JGT: - /* Unsigned comparison, the minimum value is 0. */ - true_reg->min_value = 0; + value_from_signed = false; /* fallthrough */ case BPF_JSGT: + if (true_reg->value_from_signed != value_from_signed) + reset_reg_range_values(true_reg, 0); + if (false_reg->value_from_signed != value_from_signed) + reset_reg_range_values(false_reg, 0); + if (opcode == BPF_JGT) { + /* Unsigned comparison, the minimum value is 0. */ + true_reg->min_value = 0; + } /* * If this is false, then the val is <= the register, if it is * true the register <= to the val. */ false_reg->min_value = val; + false_reg->value_from_signed = value_from_signed; true_reg->max_value = val - 1; + true_reg->value_from_signed = value_from_signed; break; case BPF_JGE: - /* Unsigned comparison, the minimum value is 0. */ - true_reg->min_value = 0; + value_from_signed = false; /* fallthrough */ case BPF_JSGE: + if (true_reg->value_from_signed != value_from_signed) + reset_reg_range_values(true_reg, 0); + if (false_reg->value_from_signed != value_from_signed) + reset_reg_range_values(false_reg, 0); + if (opcode == BPF_JGE) { + /* Unsigned comparison, the minimum value is 0. */ + true_reg->min_value = 0; + } /* If this is false then constant < register, if it is true then * the register < constant. */ false_reg->min_value = val + 1; + false_reg->value_from_signed = value_from_signed; true_reg->max_value = val; + true_reg->value_from_signed = value_from_signed; break; default: break; @@ -2290,6 +2364,12 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg, check_reg_overflow(false_reg); check_reg_overflow(true_reg); + if (is_range) { + if (__is_pointer_value(false, false_reg)) + reset_reg_range_values(false_reg, 0); + if (__is_pointer_value(false, true_reg)) + reset_reg_range_values(true_reg, 0); + } } static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id, diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index f0f3447e8aa4..861ae2a165f4 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -34,11 +34,11 @@ static struct lock_class_key bridge_netdev_addr_lock_key; netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); - const unsigned char *dest = skb->data; struct net_bridge_fdb_entry *dst; struct net_bridge_mdb_entry *mdst; struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats); const struct nf_br_ops *nf_ops; + const unsigned char *dest; u16 vid = 0; rcu_read_lock(); @@ -61,6 +61,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid)) goto out; + dest = eth_hdr(skb)->h_dest; if (is_broadcast_ether_addr(dest)) { br_flood(br, skb, BR_PKT_BROADCAST, false, true); } else if (is_multicast_ether_addr(dest)) { diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 013f2290bfa5..7637f58c1226 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -131,11 +131,11 @@ static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br, int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_bridge_port *p = br_port_get_rcu(skb->dev); - const unsigned char *dest = eth_hdr(skb)->h_dest; enum br_pkt_type pkt_type = BR_PKT_UNICAST; struct net_bridge_fdb_entry *dst = NULL; struct net_bridge_mdb_entry *mdst; bool local_rcv, mcast_hit = false; + const unsigned char *dest; struct net_bridge *br; u16 vid = 0; @@ -153,6 +153,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, false); local_rcv = !!(br->dev->flags & IFF_PROMISC); + dest = eth_hdr(skb)->h_dest; if (is_multicast_ether_addr(dest)) { /* by definition the broadcast is also a multicast address */ if (is_broadcast_ether_addr(dest)) { diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 82fd4c9c4a1b..06b147d7d9e2 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -28,6 +28,7 @@ static int dev_ifname(struct net *net, struct ifreq __user *arg) if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) return -EFAULT; + ifr.ifr_name[IFNAMSIZ-1] = 0; error = netdev_get_name(net, ifr.ifr_name, ifr.ifr_ifindex); if (error) @@ -424,6 +425,8 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) if (copy_from_user(&iwr, arg, sizeof(iwr))) return -EFAULT; + iwr.ifr_name[sizeof(iwr.ifr_name) - 1] = 0; + return wext_handle_ioctl(net, &iwr, cmd, arg); } diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index a0093e1b0235..fdcb1bcd2afa 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -400,6 +400,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, err = -ENOMEM; goto errout; } + refcount_set(&rule->refcnt, 1); rule->fr_net = net; rule->pref = tb[FRA_PRIORITY] ? nla_get_u32(tb[FRA_PRIORITY]) @@ -517,8 +518,6 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, last = r; } - refcount_set(&rule->refcnt, 1); - if (last) list_add_rcu(&rule->list, &last->list); else diff --git a/net/core/filter.c b/net/core/filter.c index c7f737058d89..f44fc22fd45a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2248,7 +2248,7 @@ static int bpf_skb_adjust_net(struct sk_buff *skb, s32 len_diff) bpf_skb_net_grow(skb, len_diff_abs); bpf_compute_data_end(skb); - return 0; + return ret; } BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, diff --git a/net/core/netpoll.c b/net/core/netpoll.c index d3408a693166..8357f164c660 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -277,7 +277,7 @@ static void zap_completion_queue(void) struct sk_buff *skb = clist; clist = clist->next; if (!skb_irq_freeable(skb)) { - refcount_inc(&skb->users); + refcount_set(&skb->users, 1); dev_kfree_skb_any(skb); /* put this one back */ } else { __kfree_skb(skb); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d1ba90980be1..9201e3621351 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2031,7 +2031,8 @@ static int do_setlink(const struct sk_buff *skb, struct sockaddr *sa; int len; - len = sizeof(sa_family_t) + dev->addr_len; + len = sizeof(sa_family_t) + max_t(size_t, dev->addr_len, + sizeof(*sa)); sa = kmalloc(len, GFP_KERNEL); if (!sa) { err = -ENOMEM; @@ -4241,6 +4242,7 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi switch (event) { case NETDEV_REBOOT: + case NETDEV_CHANGEADDR: case NETDEV_CHANGENAME: case NETDEV_FEAT_CHANGE: case NETDEV_BONDING_FAILOVER: diff --git a/net/dccp/input.c b/net/dccp/input.c index 4a05d7876850..fa6be9750bb4 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -126,7 +126,7 @@ static int dccp_rcv_closereq(struct sock *sk, struct sk_buff *skb) static u16 dccp_reset_code_convert(const u8 code) { - const u16 error_code[] = { + static const u16 error_code[] = { [DCCP_RESET_CODE_CLOSED] = 0, /* normal termination */ [DCCP_RESET_CODE_UNSPECIFIED] = 0, /* nothing known */ [DCCP_RESET_CODE_ABORTED] = ECONNRESET, diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 4e678fa892dd..044d2a159a3c 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1334,13 +1334,14 @@ static struct pernet_operations fib_net_ops = { void __init ip_fib_init(void) { - rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, NULL); - rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, NULL); - rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, NULL); + fib_trie_init(); register_pernet_subsys(&fib_net_ops); + register_netdevice_notifier(&fib_netdev_notifier); register_inetaddr_notifier(&fib_inetaddr_notifier); - fib_trie_init(); + rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, NULL); + rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, NULL); + rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, NULL); } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 7eb252dcecee..50c74cd890bc 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -599,6 +599,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, hlen = iph->ihl * 4; mtu = mtu - hlen; /* Size of data space */ IPCB(skb)->flags |= IPSKB_FRAG_COMPLETE; + ll_rs = LL_RESERVED_SPACE(rt->dst.dev); /* When frag_list is given, use it. First, check its validity: * some transformers could create wrong frag_list or break existing @@ -614,14 +615,15 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, if (first_len - hlen > mtu || ((first_len - hlen) & 7) || ip_is_fragment(iph) || - skb_cloned(skb)) + skb_cloned(skb) || + skb_headroom(skb) < ll_rs) goto slow_path; skb_walk_frags(skb, frag) { /* Correct geometry. */ if (frag->len > mtu || ((frag->len & 7) && frag->next) || - skb_headroom(frag) < hlen) + skb_headroom(frag) < hlen + ll_rs) goto slow_path_clean; /* Partially cloned skb? */ @@ -711,8 +713,6 @@ slow_path: left = skb->len - hlen; /* Space per frame */ ptr = hlen; /* Where to start from */ - ll_rs = LL_RESERVED_SPACE(rt->dst.dev); - /* * Fragment the datagram. */ diff --git a/net/ipv4/netfilter/nf_tables_arp.c b/net/ipv4/netfilter/nf_tables_arp.c index 805c8ddfe860..4bbc273b45e8 100644 --- a/net/ipv4/netfilter/nf_tables_arp.c +++ b/net/ipv4/netfilter/nf_tables_arp.c @@ -72,8 +72,7 @@ static const struct nf_chain_type filter_arp = { .family = NFPROTO_ARP, .owner = THIS_MODULE, .hook_mask = (1 << NF_ARP_IN) | - (1 << NF_ARP_OUT) | - (1 << NF_ARP_FORWARD), + (1 << NF_ARP_OUT), }; static int __init nf_tables_arp_init(void) diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 0905cf04c2a4..03ad8778c395 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -335,6 +335,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) treq->rcv_isn = ntohl(th->seq) - 1; treq->snt_isn = cookie; treq->ts_off = 0; + treq->txhash = net_tx_rndhash(); req->mss = mss; ireq->ir_num = ntohs(th->dest); ireq->ir_rmt_port = th->source; diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index dbcc9352a48f..69ee877574d0 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -112,7 +112,8 @@ struct bbr { cwnd_gain:10, /* current gain for setting cwnd */ full_bw_cnt:3, /* number of rounds without large bw gains */ cycle_idx:3, /* current index in pacing_gain cycle array */ - unused_b:6; + has_seen_rtt:1, /* have we seen an RTT sample yet? */ + unused_b:5; u32 prior_cwnd; /* prior cwnd upon entering loss recovery */ u32 full_bw; /* recent bw, to estimate if pipe is full */ }; @@ -211,6 +212,35 @@ static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain) return rate >> BW_SCALE; } +/* Convert a BBR bw and gain factor to a pacing rate in bytes per second. */ +static u32 bbr_bw_to_pacing_rate(struct sock *sk, u32 bw, int gain) +{ + u64 rate = bw; + + rate = bbr_rate_bytes_per_sec(sk, rate, gain); + rate = min_t(u64, rate, sk->sk_max_pacing_rate); + return rate; +} + +/* Initialize pacing rate to: high_gain * init_cwnd / RTT. */ +static void bbr_init_pacing_rate_from_rtt(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + u64 bw; + u32 rtt_us; + + if (tp->srtt_us) { /* any RTT sample yet? */ + rtt_us = max(tp->srtt_us >> 3, 1U); + bbr->has_seen_rtt = 1; + } else { /* no RTT sample yet */ + rtt_us = USEC_PER_MSEC; /* use nominal default RTT */ + } + bw = (u64)tp->snd_cwnd * BW_UNIT; + do_div(bw, rtt_us); + sk->sk_pacing_rate = bbr_bw_to_pacing_rate(sk, bw, bbr_high_gain); +} + /* Pace using current bw estimate and a gain factor. In order to help drive the * network toward lower queues while maintaining high utilization and low * latency, the average pacing rate aims to be slightly (~1%) lower than the @@ -220,12 +250,13 @@ static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain) */ static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain) { + struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); - u64 rate = bw; + u32 rate = bbr_bw_to_pacing_rate(sk, bw, gain); - rate = bbr_rate_bytes_per_sec(sk, rate, gain); - rate = min_t(u64, rate, sk->sk_max_pacing_rate); - if (bbr->mode != BBR_STARTUP || rate > sk->sk_pacing_rate) + if (unlikely(!bbr->has_seen_rtt && tp->srtt_us)) + bbr_init_pacing_rate_from_rtt(sk); + if (bbr_full_bw_reached(sk) || rate > sk->sk_pacing_rate) sk->sk_pacing_rate = rate; } @@ -798,7 +829,6 @@ static void bbr_init(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); - u64 bw; bbr->prior_cwnd = 0; bbr->tso_segs_goal = 0; /* default segs per skb until first ACK */ @@ -814,11 +844,8 @@ static void bbr_init(struct sock *sk) minmax_reset(&bbr->bw, bbr->rtt_cnt, 0); /* init max bw to 0 */ - /* Initialize pacing rate to: high_gain * init_cwnd / RTT. */ - bw = (u64)tp->snd_cwnd * BW_UNIT; - do_div(bw, (tp->srtt_us >> 3) ? : USEC_PER_MSEC); - sk->sk_pacing_rate = 0; /* force an update of sk_pacing_rate */ - bbr_set_pacing_rate(sk, bw, bbr_high_gain); + bbr->has_seen_rtt = 0; + bbr_init_pacing_rate_from_rtt(sk); bbr->restore_cwnd = 0; bbr->round_start = 0; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 25294d43e147..b057653ceca9 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1388,6 +1388,11 @@ void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len) unlock_sock_fast(sk, slow); } + /* we cleared the head states previously only if the skb lacks any IP + * options, see __udp_queue_rcv_skb(). + */ + if (unlikely(IPCB(skb)->opt.optlen > 0)) + skb_release_head_state(skb); consume_stateless_skb(skb); } EXPORT_SYMBOL_GPL(skb_consume_udp); @@ -1779,8 +1784,12 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) sk_mark_napi_id_once(sk, skb); } - /* clear all pending head states while they are hot in the cache */ - skb_release_head_state(skb); + /* At recvmsg() time we need skb->dst to process IP options-related + * cmsg, elsewhere can we clear all pending head states while they are + * hot in the cache + */ + if (likely(IPCB(skb)->opt.optlen == 0)) + skb_release_head_state(skb); rc = __udp_enqueue_schedule_skb(sk, skb); if (rc < 0) { diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index e9065b8d3af8..abb2c307fbe8 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -78,7 +78,7 @@ EXPORT_SYMBOL(ipv6_select_ident); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) { - u16 offset = sizeof(struct ipv6hdr); + unsigned int offset = sizeof(struct ipv6hdr); unsigned int packet_len = skb_tail_pointer(skb) - skb_network_header(skb); int found_rhdr = 0; @@ -86,6 +86,7 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) while (offset <= packet_len) { struct ipv6_opt_hdr *exthdr; + unsigned int len; switch (**nexthdr) { @@ -111,7 +112,10 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) + offset); - offset += ipv6_optlen(exthdr); + len = ipv6_optlen(exthdr); + if (len + offset >= IPV6_MAXPLEN) + return -EINVAL; + offset += len; *nexthdr = &exthdr->nexthdr; } diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 7b75b0620730..4e7817abc0b9 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -216,6 +216,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) treq->rcv_isn = ntohl(th->seq) - 1; treq->snt_isn = cookie; treq->ts_off = 0; + treq->txhash = net_tx_rndhash(); /* * We need to lookup the dst_entry to get the correct window size. diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 552d606e57ca..974cf2a3795a 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -227,114 +227,6 @@ void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg, } EXPORT_SYMBOL(nf_unregister_net_hooks); -static LIST_HEAD(nf_hook_list); - -static int _nf_register_hook(struct nf_hook_ops *reg) -{ - struct net *net, *last; - int ret; - - for_each_net(net) { - ret = nf_register_net_hook(net, reg); - if (ret && ret != -ENOENT) - goto rollback; - } - list_add_tail(®->list, &nf_hook_list); - - return 0; -rollback: - last = net; - for_each_net(net) { - if (net == last) - break; - nf_unregister_net_hook(net, reg); - } - return ret; -} - -int nf_register_hook(struct nf_hook_ops *reg) -{ - int ret; - - rtnl_lock(); - ret = _nf_register_hook(reg); - rtnl_unlock(); - - return ret; -} -EXPORT_SYMBOL(nf_register_hook); - -static void _nf_unregister_hook(struct nf_hook_ops *reg) -{ - struct net *net; - - list_del(®->list); - for_each_net(net) - nf_unregister_net_hook(net, reg); -} - -void nf_unregister_hook(struct nf_hook_ops *reg) -{ - rtnl_lock(); - _nf_unregister_hook(reg); - rtnl_unlock(); -} -EXPORT_SYMBOL(nf_unregister_hook); - -int nf_register_hooks(struct nf_hook_ops *reg, unsigned int n) -{ - unsigned int i; - int err = 0; - - for (i = 0; i < n; i++) { - err = nf_register_hook(®[i]); - if (err) - goto err; - } - return err; - -err: - if (i > 0) - nf_unregister_hooks(reg, i); - return err; -} -EXPORT_SYMBOL(nf_register_hooks); - -/* Caller MUST take rtnl_lock() */ -int _nf_register_hooks(struct nf_hook_ops *reg, unsigned int n) -{ - unsigned int i; - int err = 0; - - for (i = 0; i < n; i++) { - err = _nf_register_hook(®[i]); - if (err) - goto err; - } - return err; - -err: - if (i > 0) - _nf_unregister_hooks(reg, i); - return err; -} -EXPORT_SYMBOL(_nf_register_hooks); - -void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n) -{ - while (n-- > 0) - nf_unregister_hook(®[n]); -} -EXPORT_SYMBOL(nf_unregister_hooks); - -/* Caller MUST take rtnl_lock */ -void _nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n) -{ - while (n-- > 0) - _nf_unregister_hook(®[n]); -} -EXPORT_SYMBOL(_nf_unregister_hooks); - /* Returns 1 if okfn() needs to be executed by the caller, * -EPERM for NF_DROP, 0 otherwise. Caller must hold rcu_read_lock. */ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state, @@ -450,40 +342,9 @@ void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *); EXPORT_SYMBOL(nf_nat_decode_session_hook); #endif -static int nf_register_hook_list(struct net *net) -{ - struct nf_hook_ops *elem; - int ret; - - rtnl_lock(); - list_for_each_entry(elem, &nf_hook_list, list) { - ret = nf_register_net_hook(net, elem); - if (ret && ret != -ENOENT) - goto out_undo; - } - rtnl_unlock(); - return 0; - -out_undo: - list_for_each_entry_continue_reverse(elem, &nf_hook_list, list) - nf_unregister_net_hook(net, elem); - rtnl_unlock(); - return ret; -} - -static void nf_unregister_hook_list(struct net *net) -{ - struct nf_hook_ops *elem; - - rtnl_lock(); - list_for_each_entry(elem, &nf_hook_list, list) - nf_unregister_net_hook(net, elem); - rtnl_unlock(); -} - static int __net_init netfilter_net_init(struct net *net) { - int i, h, ret; + int i, h; for (i = 0; i < ARRAY_SIZE(net->nf.hooks); i++) { for (h = 0; h < NF_MAX_HOOKS; h++) @@ -500,16 +361,12 @@ static int __net_init netfilter_net_init(struct net *net) return -ENOMEM; } #endif - ret = nf_register_hook_list(net); - if (ret) - remove_proc_entry("netfilter", net->proc_net); - return ret; + return 0; } static void __net_exit netfilter_net_exit(struct net *net) { - nf_unregister_hook_list(net); remove_proc_entry("netfilter", net->proc_net); } diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index e03d16ed550d..899c2c36da13 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -422,7 +422,7 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) h = nf_ct_expect_dst_hash(net, &expect->tuple); hlist_for_each_entry_safe(i, next, &nf_ct_expect_hash[h], hnode) { if (expect_matches(i, expect)) { - if (nf_ct_remove_expect(expect)) + if (nf_ct_remove_expect(i)) break; } else if (expect_clash(i, expect)) { ret = -EBUSY; diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 832c5a08d9a5..eb541786ccb7 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -222,20 +222,21 @@ find_appropriate_src(struct net *net, .tuple = tuple, .zone = zone }; - struct rhlist_head *hl; + struct rhlist_head *hl, *h; hl = rhltable_lookup(&nf_nat_bysource_table, &key, nf_nat_bysource_params); - if (!hl) - return 0; - ct = container_of(hl, typeof(*ct), nat_bysource); + rhl_for_each_entry_rcu(ct, h, hl, nat_bysource) { + nf_ct_invert_tuplepr(result, + &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + result->dst = tuple->dst; - nf_ct_invert_tuplepr(result, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple); - result->dst = tuple->dst; + if (in_range(l3proto, l4proto, result, range)) + return 1; + } - return in_range(l3proto, l4proto, result, range); + return 0; } /* For [FUTURE] fragmentation handling, we want the least-used diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 92b05e188fd1..733d3e4a30d8 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -472,8 +472,7 @@ static void nfnetlink_rcv_skb_batch(struct sk_buff *skb, struct nlmsghdr *nlh) if (msglen > skb->len) msglen = skb->len; - if (nlh->nlmsg_len < NLMSG_HDRLEN || - skb->len < NLMSG_HDRLEN + sizeof(struct nfgenmsg)) + if (skb->len < NLMSG_HDRLEN + sizeof(struct nfgenmsg)) return; err = nla_parse(cda, NFNL_BATCH_MAX, attr, attrlen, nfnl_batch_policy, @@ -500,7 +499,8 @@ static void nfnetlink_rcv(struct sk_buff *skb) { struct nlmsghdr *nlh = nlmsg_hdr(skb); - if (nlh->nlmsg_len < NLMSG_HDRLEN || + if (skb->len < NLMSG_HDRLEN || + nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len) return; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 08679ebb3068..e3c4c6c3fef7 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -629,6 +629,34 @@ ovs_ct_find_existing(struct net *net, const struct nf_conntrack_zone *zone, return ct; } +static +struct nf_conn *ovs_ct_executed(struct net *net, + const struct sw_flow_key *key, + const struct ovs_conntrack_info *info, + struct sk_buff *skb, + bool *ct_executed) +{ + struct nf_conn *ct = NULL; + + /* If no ct, check if we have evidence that an existing conntrack entry + * might be found for this skb. This happens when we lose a skb->_nfct + * due to an upcall, or if the direction is being forced. If the + * connection was not confirmed, it is not cached and needs to be run + * through conntrack again. + */ + *ct_executed = (key->ct_state & OVS_CS_F_TRACKED) && + !(key->ct_state & OVS_CS_F_INVALID) && + (key->ct_zone == info->zone.id); + + if (*ct_executed || (!key->ct_state && info->force)) { + ct = ovs_ct_find_existing(net, &info->zone, info->family, skb, + !!(key->ct_state & + OVS_CS_F_NAT_MASK)); + } + + return ct; +} + /* Determine whether skb->_nfct is equal to the result of conntrack lookup. */ static bool skb_nfct_cached(struct net *net, const struct sw_flow_key *key, @@ -637,24 +665,17 @@ static bool skb_nfct_cached(struct net *net, { enum ip_conntrack_info ctinfo; struct nf_conn *ct; + bool ct_executed = true; ct = nf_ct_get(skb, &ctinfo); - /* If no ct, check if we have evidence that an existing conntrack entry - * might be found for this skb. This happens when we lose a skb->_nfct - * due to an upcall. If the connection was not confirmed, it is not - * cached and needs to be run through conntrack again. - */ - if (!ct && key->ct_state & OVS_CS_F_TRACKED && - !(key->ct_state & OVS_CS_F_INVALID) && - key->ct_zone == info->zone.id) { - ct = ovs_ct_find_existing(net, &info->zone, info->family, skb, - !!(key->ct_state - & OVS_CS_F_NAT_MASK)); - if (ct) - nf_ct_get(skb, &ctinfo); - } if (!ct) + ct = ovs_ct_executed(net, key, info, skb, &ct_executed); + + if (ct) + nf_ct_get(skb, &ctinfo); + else return false; + if (!net_eq(net, read_pnet(&ct->ct_net))) return false; if (!nf_ct_zone_equal_any(info->ct, nf_ct_zone(ct))) @@ -679,7 +700,7 @@ static bool skb_nfct_cached(struct net *net, return false; } - return true; + return ct_executed; } #ifdef CONFIG_NF_NAT_NEEDED diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index e3beb28203eb..008bb34ee324 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -214,6 +214,7 @@ static void prb_clear_rxhash(struct tpacket_kbdq_core *, static void prb_fill_vlan_info(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void packet_flush_mclist(struct sock *sk); +static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb); struct packet_skb_cb { union { @@ -260,6 +261,7 @@ static int packet_direct_xmit(struct sk_buff *skb) if (skb != orig_skb) goto drop; + packet_pick_tx_queue(dev, skb); txq = skb_get_tx_queue(dev, skb); local_bh_disable(); @@ -2747,8 +2749,6 @@ tpacket_error: goto tpacket_error; } - packet_pick_tx_queue(dev, skb); - skb->destructor = tpacket_destruct_skb; __packet_set_status(po, ph, TP_STATUS_SENDING); packet_inc_pending(&po->tx_ring); @@ -2931,8 +2931,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->priority = sk->sk_priority; skb->mark = sockc.mark; - packet_pick_tx_queue(dev, skb); - if (po->has_vnet_hdr) { err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le()); if (err) diff --git a/net/rds/send.c b/net/rds/send.c index e81aa176f4e2..41b9f0f5bb9c 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -170,8 +170,8 @@ restart: * The acquire_in_xmit() check above ensures that only one * caller can increment c_send_gen at any time. */ - cp->cp_send_gen++; - send_gen = cp->cp_send_gen; + send_gen = READ_ONCE(cp->cp_send_gen) + 1; + WRITE_ONCE(cp->cp_send_gen, send_gen); /* * rds_conn_shutdown() sets the conn state and then tests RDS_IN_XMIT, @@ -431,7 +431,7 @@ over_batch: smp_mb(); if ((test_bit(0, &conn->c_map_queued) || !list_empty(&cp->cp_send_queue)) && - send_gen == cp->cp_send_gen) { + send_gen == READ_ONCE(cp->cp_send_gen)) { rds_stats_inc(s_send_lock_queue_raced); if (batch_count < send_batch_count) goto restart; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index aed6cf2e9fd8..f2e9ed34a963 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -835,7 +835,7 @@ out_nlmsg_trim: } static int -act_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, +tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, struct list_head *actions, int event) { struct sk_buff *skb; @@ -1018,7 +1018,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, } if (event == RTM_GETACTION) - ret = act_get_notify(net, portid, n, &actions, event); + ret = tcf_get_notify(net, portid, n, &actions, event); else { /* delete */ ret = tcf_del_notify(net, n, &actions, portid); if (ret) diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 4e16b02ed832..6110447fe51d 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -228,7 +228,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, sctp_adaptation_ind_param_t aiparam; sctp_supported_ext_param_t ext_param; int num_ext = 0; - __u8 extensions[3]; + __u8 extensions[4]; struct sctp_paramhdr *auth_chunks = NULL, *auth_hmacs = NULL; @@ -396,7 +396,7 @@ struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc, sctp_adaptation_ind_param_t aiparam; sctp_supported_ext_param_t ext_param; int num_ext = 0; - __u8 extensions[3]; + __u8 extensions[4]; struct sctp_paramhdr *auth_chunks = NULL, *auth_hmacs = NULL, *auth_random = NULL; diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 7e0405e1651d..412a7c82995a 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -120,7 +120,7 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, size_t insns_cnt, int strict_alignment, const char *license, __u32 kern_version, - char *log_buf, size_t log_buf_sz) + char *log_buf, size_t log_buf_sz, int log_level) { union bpf_attr attr; @@ -131,7 +131,7 @@ int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, attr.license = ptr_to_u64(license); attr.log_buf = ptr_to_u64(log_buf); attr.log_size = log_buf_sz; - attr.log_level = 2; + attr.log_level = log_level; log_buf[0] = 0; attr.kern_version = kern_version; attr.prog_flags = strict_alignment ? BPF_F_STRICT_ALIGNMENT : 0; diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 16de44a14b48..418c86e69bcb 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -38,7 +38,7 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, size_t insns_cnt, int strict_alignment, const char *license, __u32 kern_version, - char *log_buf, size_t log_buf_sz); + char *log_buf, size_t log_buf_sz, int log_level); int bpf_map_update_elem(int fd, const void *key, const void *value, __u64 flags); diff --git a/tools/testing/selftests/bpf/test_align.c b/tools/testing/selftests/bpf/test_align.c index bccebd935907..29793694cbc7 100644 --- a/tools/testing/selftests/bpf/test_align.c +++ b/tools/testing/selftests/bpf/test_align.c @@ -380,7 +380,7 @@ static int do_test_single(struct bpf_align_test *test) prog_len = probe_filter_length(prog); fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER, prog, prog_len, 1, "GPL", 0, - bpf_vlog, sizeof(bpf_vlog)); + bpf_vlog, sizeof(bpf_vlog), 2); if (fd_prog < 0) { printf("Failed to load program.\n"); printf("%s", bpf_vlog); diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 404aec520812..af7d173910f4 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -4969,7 +4969,7 @@ static struct bpf_test tests[] = { BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, sizeof(struct test_val), 4), BPF_MOV64_IMM(BPF_REG_4, 0), - BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2), + BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2), BPF_MOV64_IMM(BPF_REG_3, 0), BPF_EMIT_CALL(BPF_FUNC_probe_read), BPF_MOV64_IMM(BPF_REG_0, 0), @@ -4995,7 +4995,7 @@ static struct bpf_test tests[] = { BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, sizeof(struct test_val) + 1, 4), BPF_MOV64_IMM(BPF_REG_4, 0), - BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2), + BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2), BPF_MOV64_IMM(BPF_REG_3, 0), BPF_EMIT_CALL(BPF_FUNC_probe_read), BPF_MOV64_IMM(BPF_REG_0, 0), @@ -5023,7 +5023,7 @@ static struct bpf_test tests[] = { BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, sizeof(struct test_val) - 20, 4), BPF_MOV64_IMM(BPF_REG_4, 0), - BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2), + BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2), BPF_MOV64_IMM(BPF_REG_3, 0), BPF_EMIT_CALL(BPF_FUNC_probe_read), BPF_MOV64_IMM(BPF_REG_0, 0), @@ -5050,7 +5050,7 @@ static struct bpf_test tests[] = { BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, sizeof(struct test_val) - 19, 4), BPF_MOV64_IMM(BPF_REG_4, 0), - BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2), + BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2), BPF_MOV64_IMM(BPF_REG_3, 0), BPF_EMIT_CALL(BPF_FUNC_probe_read), BPF_MOV64_IMM(BPF_REG_0, 0), @@ -5510,6 +5510,476 @@ static struct bpf_test tests[] = { .errstr = "invalid bpf_context access", .prog_type = BPF_PROG_TYPE_LWT_IN, }, + { + "bounds checks mixing signed and unsigned, positive bounds", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, 2), + BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 3), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 4, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -1), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 3), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 2", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -1), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 5), + BPF_MOV64_IMM(BPF_REG_8, 0), + BPF_ALU64_REG(BPF_ADD, BPF_REG_8, BPF_REG_1), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_8, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_8), + BPF_ST_MEM(BPF_B, BPF_REG_8, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R8 invalid mem access 'inv'", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 3", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -1), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 4), + BPF_MOV64_REG(BPF_REG_8, BPF_REG_1), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_8, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_8), + BPF_ST_MEM(BPF_B, BPF_REG_8, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R8 invalid mem access 'inv'", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 4", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, 1), + BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 5", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -1), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 5), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 4), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 4), + BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 invalid mem access", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 6", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -512), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_6, -1), + BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_6, 5), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_4, 1, 4), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 1), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_ST_MEM(BPF_H, BPF_REG_10, -512, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_load_bytes), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "R4 min value is negative, either use unsigned", + .errstr = "R4 min value is negative, either use unsigned", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 7", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, 1024 * 1024 * 1024), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 3), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 8", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, 1024 * 1024 * 1024 + 1), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 3), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 9", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -1), + BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 10", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 10), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_LD_IMM64(BPF_REG_2, -9223372036854775808ULL), + BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 11", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 12", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -1), + BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2), + /* Dead branch. */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 13", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -6), + BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 14", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, 2), + BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2), + BPF_MOV64_IMM(BPF_REG_7, 1), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_7, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_1), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_7, 4, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_7), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 15", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1, + offsetof(struct __sk_buff, mark)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -1), + BPF_MOV64_IMM(BPF_REG_8, 2), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_9, 42, 6), + BPF_JMP_REG(BPF_JSGT, BPF_REG_8, BPF_REG_1, 3), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, -3), + BPF_JMP_IMM(BPF_JA, 0, 0, -7), + }, + .fixup_map1 = { 4 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 16", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -6), + BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_JMP_IMM(BPF_JGT, BPF_REG_0, 1, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, }; static int probe_filter_length(const struct bpf_insn *fp) @@ -5633,7 +6103,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER, prog, prog_len, test->flags & F_LOAD_WITH_STRICT_ALIGNMENT, - "GPL", 0, bpf_vlog, sizeof(bpf_vlog)); + "GPL", 0, bpf_vlog, sizeof(bpf_vlog), 1); expected_ret = unpriv && test->result_unpriv != UNDEF ? test->result_unpriv : test->result; |