diff options
152 files changed, 1468 insertions, 1106 deletions
diff --git a/Documentation/dev-tools/kunit/start.rst b/Documentation/dev-tools/kunit/start.rst index 9d6db892c41c..4e1d24db6b13 100644 --- a/Documentation/dev-tools/kunit/start.rst +++ b/Documentation/dev-tools/kunit/start.rst @@ -24,19 +24,16 @@ The wrapper can be run with: For more information on this wrapper (also called kunit_tool) checkout the :doc:`kunit-tool` page. -Creating a kunitconfig -====================== +Creating a .kunitconfig +======================= The Python script is a thin wrapper around Kbuild. As such, it needs to be -configured with a ``kunitconfig`` file. This file essentially contains the +configured with a ``.kunitconfig`` file. This file essentially contains the regular Kernel config, with the specific test targets as well. .. code-block:: bash - git clone -b master https://kunit.googlesource.com/kunitconfig $PATH_TO_KUNITCONFIG_REPO cd $PATH_TO_LINUX_REPO - ln -s $PATH_TO_KUNIT_CONFIG_REPO/kunitconfig kunitconfig - -You may want to add kunitconfig to your local gitignore. + cp arch/um/configs/kunit_defconfig .kunitconfig Verifying KUnit Works --------------------- @@ -151,7 +148,7 @@ and the following to ``drivers/misc/Makefile``: obj-$(CONFIG_MISC_EXAMPLE_TEST) += example-test.o -Now add it to your ``kunitconfig``: +Now add it to your ``.kunitconfig``: .. code-block:: none diff --git a/Documentation/networking/dsa/sja1105.rst b/Documentation/networking/dsa/sja1105.rst index eef20d0bcf7c..64553d8d91cb 100644 --- a/Documentation/networking/dsa/sja1105.rst +++ b/Documentation/networking/dsa/sja1105.rst @@ -230,12 +230,6 @@ simultaneously on two ports. The driver checks the consistency of the schedules against this restriction and errors out when appropriate. Schedule analysis is needed to avoid this, which is outside the scope of the document. -At the moment, the time-aware scheduler can only be triggered based on a -standalone clock and not based on PTP time. This means the base-time argument -from tc-taprio is ignored and the schedule starts right away. It also means it -is more difficult to phase-align the scheduler with the other devices in the -network. - Device Tree bindings and board design ===================================== diff --git a/MAINTAINERS b/MAINTAINERS index f9e9049a9947..34de47832883 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -771,6 +771,8 @@ F: drivers/thermal/thermal_mmio.c AMAZON ETHERNET DRIVERS M: Netanel Belgazal <netanel@amazon.com> +M: Arthur Kiyanovski <akiyano@amazon.com> +R: Guy Tzalik <gtzalik@amazon.com> R: Saeed Bishara <saeedb@amazon.com> R: Zorik Machulsky <zorik@amazon.com> L: netdev@vger.kernel.org @@ -7034,6 +7036,7 @@ L: linux-acpi@vger.kernel.org S: Maintained F: Documentation/firmware-guide/acpi/gpio-properties.rst F: drivers/gpio/gpiolib-acpi.c +F: drivers/gpio/gpiolib-acpi.h GPIO IR Transmitter M: Sean Young <sean@mess.org> @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 5 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc4 NAME = Kleptomaniac Octopus # *DOCUMENTATION* diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index a1349ca64669..e163b7b64c86 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -246,6 +246,7 @@ check_syscall_nr: */ li t1, -1 beq a7, t1, ret_from_syscall_rejected + blt a7, t1, 1f /* Call syscall */ la s0, sys_call_table slli t0, a7, RISCV_LGPTR diff --git a/arch/riscv/kernel/riscv_ksyms.c b/arch/riscv/kernel/riscv_ksyms.c index 4800cf703186..2a02b7eebee0 100644 --- a/arch/riscv/kernel/riscv_ksyms.c +++ b/arch/riscv/kernel/riscv_ksyms.c @@ -9,8 +9,5 @@ /* * Assembly functions that may be used (directly or indirectly) by modules */ -EXPORT_SYMBOL(__clear_user); -EXPORT_SYMBOL(__asm_copy_to_user); -EXPORT_SYMBOL(__asm_copy_from_user); EXPORT_SYMBOL(memset); EXPORT_SYMBOL(memcpy); diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S index fecd65657a6f..f29d2ba2c0a6 100644 --- a/arch/riscv/lib/uaccess.S +++ b/arch/riscv/lib/uaccess.S @@ -1,4 +1,5 @@ #include <linux/linkage.h> +#include <asm-generic/export.h> #include <asm/asm.h> #include <asm/csr.h> @@ -66,6 +67,8 @@ ENTRY(__asm_copy_from_user) j 3b ENDPROC(__asm_copy_to_user) ENDPROC(__asm_copy_from_user) +EXPORT_SYMBOL(__asm_copy_to_user) +EXPORT_SYMBOL(__asm_copy_from_user) ENTRY(__clear_user) @@ -108,6 +111,7 @@ ENTRY(__clear_user) bltu a0, a3, 5b j 3b ENDPROC(__clear_user) +EXPORT_SYMBOL(__clear_user) .section .fixup,"ax" .balign 4 diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c index 8f1900686640..8930ab7278e6 100644 --- a/arch/riscv/mm/cacheflush.c +++ b/arch/riscv/mm/cacheflush.c @@ -22,6 +22,7 @@ void flush_icache_all(void) else on_each_cpu(ipi_remote_fence_i, NULL, 1); } +EXPORT_SYMBOL(flush_icache_all); /* * Performs an icache flush for the given MM context. RISC-V has no direct diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c index 6ca015f92766..3ed7a0f144a9 100644 --- a/block/compat_ioctl.c +++ b/block/compat_ioctl.c @@ -6,6 +6,7 @@ #include <linux/compat.h> #include <linux/elevator.h> #include <linux/hdreg.h> +#include <linux/pr.h> #include <linux/slab.h> #include <linux/syscalls.h> #include <linux/types.h> @@ -354,6 +355,13 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) * but we call blkdev_ioctl, which gets the lock for us */ case BLKRRPART: + case BLKREPORTZONE: + case BLKRESETZONE: + case BLKOPENZONE: + case BLKCLOSEZONE: + case BLKFINISHZONE: + case BLKGETZONESZ: + case BLKGETNRZONES: return blkdev_ioctl(bdev, mode, cmd, (unsigned long)compat_ptr(arg)); case BLKBSZSET_32: @@ -401,6 +409,14 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) case BLKTRACETEARDOWN: /* compatible */ ret = blk_trace_ioctl(bdev, cmd, compat_ptr(arg)); return ret; + case IOC_PR_REGISTER: + case IOC_PR_RESERVE: + case IOC_PR_RELEASE: + case IOC_PR_PREEMPT: + case IOC_PR_PREEMPT_ABORT: + case IOC_PR_CLEAR: + return blkdev_ioctl(bdev, mode, cmd, + (unsigned long)compat_ptr(arg)); default: if (disk->fops->compat_ioctl) ret = disk->fops->compat_ioctl(bdev, mode, cmd, arg); diff --git a/drivers/ata/ahci_brcm.c b/drivers/ata/ahci_brcm.c index f41744b9b38a..66a570d0da83 100644 --- a/drivers/ata/ahci_brcm.c +++ b/drivers/ata/ahci_brcm.c @@ -76,8 +76,7 @@ enum brcm_ahci_version { }; enum brcm_ahci_quirks { - BRCM_AHCI_QUIRK_NO_NCQ = BIT(0), - BRCM_AHCI_QUIRK_SKIP_PHY_ENABLE = BIT(1), + BRCM_AHCI_QUIRK_SKIP_PHY_ENABLE = BIT(0), }; struct brcm_ahci_priv { @@ -213,19 +212,12 @@ static void brcm_sata_phys_disable(struct brcm_ahci_priv *priv) brcm_sata_phy_disable(priv, i); } -static u32 brcm_ahci_get_portmask(struct platform_device *pdev, +static u32 brcm_ahci_get_portmask(struct ahci_host_priv *hpriv, struct brcm_ahci_priv *priv) { - void __iomem *ahci; - struct resource *res; u32 impl; - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "ahci"); - ahci = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(ahci)) - return 0; - - impl = readl(ahci + HOST_PORTS_IMPL); + impl = readl(hpriv->mmio + HOST_PORTS_IMPL); if (fls(impl) > SATA_TOP_MAX_PHYS) dev_warn(priv->dev, "warning: more ports than PHYs (%#x)\n", @@ -233,9 +225,6 @@ static u32 brcm_ahci_get_portmask(struct platform_device *pdev, else if (!impl) dev_info(priv->dev, "no ports found\n"); - devm_iounmap(&pdev->dev, ahci); - devm_release_mem_region(&pdev->dev, res->start, resource_size(res)); - return impl; } @@ -285,6 +274,13 @@ static unsigned int brcm_ahci_read_id(struct ata_device *dev, /* Perform the SATA PHY reset sequence */ brcm_sata_phy_disable(priv, ap->port_no); + /* Reset the SATA clock */ + ahci_platform_disable_clks(hpriv); + msleep(10); + + ahci_platform_enable_clks(hpriv); + msleep(10); + /* Bring the PHY back on */ brcm_sata_phy_enable(priv, ap->port_no); @@ -347,11 +343,10 @@ static int brcm_ahci_suspend(struct device *dev) struct ata_host *host = dev_get_drvdata(dev); struct ahci_host_priv *hpriv = host->private_data; struct brcm_ahci_priv *priv = hpriv->plat_data; - int ret; - ret = ahci_platform_suspend(dev); brcm_sata_phys_disable(priv); - return ret; + + return ahci_platform_suspend(dev); } static int brcm_ahci_resume(struct device *dev) @@ -359,11 +354,44 @@ static int brcm_ahci_resume(struct device *dev) struct ata_host *host = dev_get_drvdata(dev); struct ahci_host_priv *hpriv = host->private_data; struct brcm_ahci_priv *priv = hpriv->plat_data; + int ret; + + /* Make sure clocks are turned on before re-configuration */ + ret = ahci_platform_enable_clks(hpriv); + if (ret) + return ret; brcm_sata_init(priv); brcm_sata_phys_enable(priv); brcm_sata_alpm_init(hpriv); - return ahci_platform_resume(dev); + + /* Since we had to enable clocks earlier on, we cannot use + * ahci_platform_resume() as-is since a second call to + * ahci_platform_enable_resources() would bump up the resources + * (regulators, clocks, PHYs) count artificially so we copy the part + * after ahci_platform_enable_resources(). + */ + ret = ahci_platform_enable_phys(hpriv); + if (ret) + goto out_disable_phys; + + ret = ahci_platform_resume_host(dev); + if (ret) + goto out_disable_platform_phys; + + /* We resumed so update PM runtime state */ + pm_runtime_disable(dev); + pm_runtime_set_active(dev); + pm_runtime_enable(dev); + + return 0; + +out_disable_platform_phys: + ahci_platform_disable_phys(hpriv); +out_disable_phys: + brcm_sata_phys_disable(priv); + ahci_platform_disable_clks(hpriv); + return ret; } #endif @@ -410,44 +438,71 @@ static int brcm_ahci_probe(struct platform_device *pdev) if (!IS_ERR_OR_NULL(priv->rcdev)) reset_control_deassert(priv->rcdev); - if ((priv->version == BRCM_SATA_BCM7425) || - (priv->version == BRCM_SATA_NSP)) { - priv->quirks |= BRCM_AHCI_QUIRK_NO_NCQ; + hpriv = ahci_platform_get_resources(pdev, 0); + if (IS_ERR(hpriv)) { + ret = PTR_ERR(hpriv); + goto out_reset; + } + + hpriv->plat_data = priv; + hpriv->flags = AHCI_HFLAG_WAKE_BEFORE_STOP | AHCI_HFLAG_NO_WRITE_TO_RO; + + switch (priv->version) { + case BRCM_SATA_BCM7425: + hpriv->flags |= AHCI_HFLAG_DELAY_ENGINE; + /* fall through */ + case BRCM_SATA_NSP: + hpriv->flags |= AHCI_HFLAG_NO_NCQ; priv->quirks |= BRCM_AHCI_QUIRK_SKIP_PHY_ENABLE; + break; + default: + break; } + ret = ahci_platform_enable_clks(hpriv); + if (ret) + goto out_reset; + + /* Must be first so as to configure endianness including that + * of the standard AHCI register space. + */ brcm_sata_init(priv); - priv->port_mask = brcm_ahci_get_portmask(pdev, priv); - if (!priv->port_mask) - return -ENODEV; + /* Initializes priv->port_mask which is used below */ + priv->port_mask = brcm_ahci_get_portmask(hpriv, priv); + if (!priv->port_mask) { + ret = -ENODEV; + goto out_disable_clks; + } + /* Must be done before ahci_platform_enable_phys() */ brcm_sata_phys_enable(priv); - hpriv = ahci_platform_get_resources(pdev, 0); - if (IS_ERR(hpriv)) - return PTR_ERR(hpriv); - hpriv->plat_data = priv; - hpriv->flags = AHCI_HFLAG_WAKE_BEFORE_STOP; - brcm_sata_alpm_init(hpriv); - ret = ahci_platform_enable_resources(hpriv); + ret = ahci_platform_enable_phys(hpriv); if (ret) - return ret; - - if (priv->quirks & BRCM_AHCI_QUIRK_NO_NCQ) - hpriv->flags |= AHCI_HFLAG_NO_NCQ; - hpriv->flags |= AHCI_HFLAG_NO_WRITE_TO_RO; + goto out_disable_phys; ret = ahci_platform_init_host(pdev, hpriv, &ahci_brcm_port_info, &ahci_platform_sht); if (ret) - return ret; + goto out_disable_platform_phys; dev_info(dev, "Broadcom AHCI SATA3 registered\n"); return 0; + +out_disable_platform_phys: + ahci_platform_disable_phys(hpriv); +out_disable_phys: + brcm_sata_phys_disable(priv); +out_disable_clks: + ahci_platform_disable_clks(hpriv); +out_reset: + if (!IS_ERR_OR_NULL(priv->rcdev)) + reset_control_assert(priv->rcdev); + return ret; } static int brcm_ahci_remove(struct platform_device *pdev) @@ -457,12 +512,12 @@ static int brcm_ahci_remove(struct platform_device *pdev) struct brcm_ahci_priv *priv = hpriv->plat_data; int ret; + brcm_sata_phys_disable(priv); + ret = ata_platform_remove_one(pdev); if (ret) return ret; - brcm_sata_phys_disable(priv); - return 0; } diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c index 8befce036af8..129556fcf6be 100644 --- a/drivers/ata/libahci_platform.c +++ b/drivers/ata/libahci_platform.c @@ -43,7 +43,7 @@ EXPORT_SYMBOL_GPL(ahci_platform_ops); * RETURNS: * 0 on success otherwise a negative error code */ -static int ahci_platform_enable_phys(struct ahci_host_priv *hpriv) +int ahci_platform_enable_phys(struct ahci_host_priv *hpriv) { int rc, i; @@ -74,6 +74,7 @@ disable_phys: } return rc; } +EXPORT_SYMBOL_GPL(ahci_platform_enable_phys); /** * ahci_platform_disable_phys - Disable PHYs @@ -81,7 +82,7 @@ disable_phys: * * This function disables all PHYs found in hpriv->phys. */ -static void ahci_platform_disable_phys(struct ahci_host_priv *hpriv) +void ahci_platform_disable_phys(struct ahci_host_priv *hpriv) { int i; @@ -90,6 +91,7 @@ static void ahci_platform_disable_phys(struct ahci_host_priv *hpriv) phy_exit(hpriv->phys[i]); } } +EXPORT_SYMBOL_GPL(ahci_platform_disable_phys); /** * ahci_platform_enable_clks - Enable platform clocks diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index e9017c570bc5..6f4ab5c5b52d 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -5329,6 +5329,30 @@ void ata_qc_complete(struct ata_queued_cmd *qc) } /** + * ata_qc_get_active - get bitmask of active qcs + * @ap: port in question + * + * LOCKING: + * spin_lock_irqsave(host lock) + * + * RETURNS: + * Bitmask of active qcs + */ +u64 ata_qc_get_active(struct ata_port *ap) +{ + u64 qc_active = ap->qc_active; + + /* ATA_TAG_INTERNAL is sent to hw as tag 0 */ + if (qc_active & (1ULL << ATA_TAG_INTERNAL)) { + qc_active |= (1 << 0); + qc_active &= ~(1ULL << ATA_TAG_INTERNAL); + } + + return qc_active; +} +EXPORT_SYMBOL_GPL(ata_qc_get_active); + +/** * ata_qc_complete_multiple - Complete multiple qcs successfully * @ap: port in question * @qc_active: new qc_active mask diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index 9239615d8a04..d55ee244d693 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -1280,7 +1280,7 @@ static void sata_fsl_host_intr(struct ata_port *ap) i, ioread32(hcr_base + CC), ioread32(hcr_base + CA)); } - ata_qc_complete_multiple(ap, ap->qc_active ^ done_mask); + ata_qc_complete_multiple(ap, ata_qc_get_active(ap) ^ done_mask); return; } else if ((ap->qc_active & (1ULL << ATA_TAG_INTERNAL))) { diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index 277f11909fc1..d7228f8e9297 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -2829,7 +2829,7 @@ static void mv_process_crpb_entries(struct ata_port *ap, struct mv_port_priv *pp } if (work_done) { - ata_qc_complete_multiple(ap, ap->qc_active ^ done_mask); + ata_qc_complete_multiple(ap, ata_qc_get_active(ap) ^ done_mask); /* Update the software queue position index in hardware */ writelfl((pp->crpb_dma & EDMA_RSP_Q_BASE_LO_MASK) | diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c index f3e62f5528bd..eb9dc14e5147 100644 --- a/drivers/ata/sata_nv.c +++ b/drivers/ata/sata_nv.c @@ -984,7 +984,7 @@ static irqreturn_t nv_adma_interrupt(int irq, void *dev_instance) check_commands = 0; check_commands &= ~(1 << pos); } - ata_qc_complete_multiple(ap, ap->qc_active ^ done_mask); + ata_qc_complete_multiple(ap, ata_qc_get_active(ap) ^ done_mask); } } diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index ee67bf929fac..861fc65a1b75 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -2707,7 +2707,7 @@ static const struct block_device_operations pktcdvd_ops = { .release = pkt_close, .ioctl = pkt_ioctl, #ifdef CONFIG_COMPAT - .ioctl = pkt_compat_ioctl, + .compat_ioctl = pkt_compat_ioctl, #endif .check_events = pkt_check_events, }; diff --git a/drivers/devfreq/Kconfig b/drivers/devfreq/Kconfig index defe1d438710..35535833b6f7 100644 --- a/drivers/devfreq/Kconfig +++ b/drivers/devfreq/Kconfig @@ -83,7 +83,6 @@ config ARM_EXYNOS_BUS_DEVFREQ select DEVFREQ_GOV_PASSIVE select DEVFREQ_EVENT_EXYNOS_PPMU select PM_DEVFREQ_EVENT - select PM_OPP help This adds the common DEVFREQ driver for Exynos Memory bus. Exynos Memory bus has one more group of memory bus (e.g, MIF and INT block). @@ -98,7 +97,7 @@ config ARM_TEGRA_DEVFREQ ARCH_TEGRA_132_SOC || ARCH_TEGRA_124_SOC || \ ARCH_TEGRA_210_SOC || \ COMPILE_TEST - select PM_OPP + depends on COMMON_CLK help This adds the DEVFREQ driver for the Tegra family of SoCs. It reads ACTMON counters of memory controllers and adjusts the @@ -109,7 +108,6 @@ config ARM_TEGRA20_DEVFREQ depends on (TEGRA_MC && TEGRA20_EMC) || COMPILE_TEST depends on COMMON_CLK select DEVFREQ_GOV_SIMPLE_ONDEMAND - select PM_OPP help This adds the DEVFREQ driver for the Tegra20 family of SoCs. It reads Memory Controller counters and adjusts the operating @@ -121,7 +119,6 @@ config ARM_RK3399_DMC_DEVFREQ select DEVFREQ_EVENT_ROCKCHIP_DFI select DEVFREQ_GOV_SIMPLE_ONDEMAND select PM_DEVFREQ_EVENT - select PM_OPP help This adds the DEVFREQ driver for the RK3399 DMC(Dynamic Memory Controller). It sets the frequency for the memory controller and reads the usage counts diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 8adffd42f8cb..6ab25fe1c423 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -553,8 +553,8 @@ config GPIO_TEGRA config GPIO_TEGRA186 tristate "NVIDIA Tegra186 GPIO support" - default ARCH_TEGRA_186_SOC - depends on ARCH_TEGRA_186_SOC || COMPILE_TEST + default ARCH_TEGRA_186_SOC || ARCH_TEGRA_194_SOC + depends on ARCH_TEGRA_186_SOC || ARCH_TEGRA_194_SOC || COMPILE_TEST depends on OF_GPIO select GPIOLIB_IRQCHIP select IRQ_DOMAIN_HIERARCHY diff --git a/drivers/gpio/gpio-aspeed-sgpio.c b/drivers/gpio/gpio-aspeed-sgpio.c index 7e99860ca447..8319812593e3 100644 --- a/drivers/gpio/gpio-aspeed-sgpio.c +++ b/drivers/gpio/gpio-aspeed-sgpio.c @@ -107,7 +107,7 @@ static void __iomem *bank_reg(struct aspeed_sgpio *gpio, return gpio->base + bank->irq_regs + GPIO_IRQ_STATUS; default: /* acturally if code runs to here, it's an error case */ - BUG_ON(1); + BUG(); } } diff --git a/drivers/gpio/gpio-mockup.c b/drivers/gpio/gpio-mockup.c index 56d647a30e3e..c4fdc192ea4e 100644 --- a/drivers/gpio/gpio-mockup.c +++ b/drivers/gpio/gpio-mockup.c @@ -226,7 +226,7 @@ static int gpio_mockup_get_direction(struct gpio_chip *gc, unsigned int offset) int direction; mutex_lock(&chip->lock); - direction = !chip->lines[offset].dir; + direction = chip->lines[offset].dir; mutex_unlock(&chip->lock); return direction; @@ -395,7 +395,7 @@ static int gpio_mockup_probe(struct platform_device *pdev) struct gpio_chip *gc; struct device *dev; const char *name; - int rv, base; + int rv, base, i; u16 ngpio; dev = &pdev->dev; @@ -447,6 +447,9 @@ static int gpio_mockup_probe(struct platform_device *pdev) if (!chip->lines) return -ENOMEM; + for (i = 0; i < gc->ngpio; i++) + chip->lines[i].dir = GPIO_LINE_DIRECTION_IN; + if (device_property_read_bool(dev, "named-gpio-lines")) { rv = gpio_mockup_name_lines(dev, chip); if (rv) diff --git a/drivers/gpio/gpio-mpc8xxx.c b/drivers/gpio/gpio-mpc8xxx.c index f1e164cecff8..5ae30de3490a 100644 --- a/drivers/gpio/gpio-mpc8xxx.c +++ b/drivers/gpio/gpio-mpc8xxx.c @@ -346,6 +346,7 @@ static int mpc8xxx_probe(struct platform_device *pdev) return -ENOMEM; gc = &mpc8xxx_gc->gc; + gc->parent = &pdev->dev; if (of_property_read_bool(np, "little-endian")) { ret = bgpio_init(gc, &pdev->dev, 4, diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index 6652bee01966..9853547e7276 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -568,16 +568,18 @@ static void pca953x_irq_mask(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct pca953x_chip *chip = gpiochip_get_data(gc); + irq_hw_number_t hwirq = irqd_to_hwirq(d); - chip->irq_mask[d->hwirq / BANK_SZ] &= ~BIT(d->hwirq % BANK_SZ); + clear_bit(hwirq, chip->irq_mask); } static void pca953x_irq_unmask(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct pca953x_chip *chip = gpiochip_get_data(gc); + irq_hw_number_t hwirq = irqd_to_hwirq(d); - chip->irq_mask[d->hwirq / BANK_SZ] |= BIT(d->hwirq % BANK_SZ); + set_bit(hwirq, chip->irq_mask); } static int pca953x_irq_set_wake(struct irq_data *d, unsigned int on) @@ -635,8 +637,7 @@ static int pca953x_irq_set_type(struct irq_data *d, unsigned int type) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct pca953x_chip *chip = gpiochip_get_data(gc); - int bank_nb = d->hwirq / BANK_SZ; - u8 mask = BIT(d->hwirq % BANK_SZ); + irq_hw_number_t hwirq = irqd_to_hwirq(d); if (!(type & IRQ_TYPE_EDGE_BOTH)) { dev_err(&chip->client->dev, "irq %d: unsupported type %d\n", @@ -644,15 +645,8 @@ static int pca953x_irq_set_type(struct irq_data *d, unsigned int type) return -EINVAL; } - if (type & IRQ_TYPE_EDGE_FALLING) - chip->irq_trig_fall[bank_nb] |= mask; - else - chip->irq_trig_fall[bank_nb] &= ~mask; - - if (type & IRQ_TYPE_EDGE_RISING) - chip->irq_trig_raise[bank_nb] |= mask; - else - chip->irq_trig_raise[bank_nb] &= ~mask; + assign_bit(hwirq, chip->irq_trig_fall, type & IRQ_TYPE_EDGE_FALLING); + assign_bit(hwirq, chip->irq_trig_raise, type & IRQ_TYPE_EDGE_RISING); return 0; } @@ -661,10 +655,10 @@ static void pca953x_irq_shutdown(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct pca953x_chip *chip = gpiochip_get_data(gc); - u8 mask = BIT(d->hwirq % BANK_SZ); + irq_hw_number_t hwirq = irqd_to_hwirq(d); - chip->irq_trig_raise[d->hwirq / BANK_SZ] &= ~mask; - chip->irq_trig_fall[d->hwirq / BANK_SZ] &= ~mask; + clear_bit(hwirq, chip->irq_trig_raise); + clear_bit(hwirq, chip->irq_trig_fall); } static bool pca953x_irq_pending(struct pca953x_chip *chip, unsigned long *pending) diff --git a/drivers/gpio/gpio-xgs-iproc.c b/drivers/gpio/gpio-xgs-iproc.c index 773e5c24309e..b21c2e436b61 100644 --- a/drivers/gpio/gpio-xgs-iproc.c +++ b/drivers/gpio/gpio-xgs-iproc.c @@ -280,7 +280,7 @@ static int iproc_gpio_probe(struct platform_device *pdev) return 0; } -static int __exit iproc_gpio_remove(struct platform_device *pdev) +static int iproc_gpio_remove(struct platform_device *pdev) { struct iproc_gpio_chip *chip; diff --git a/drivers/gpio/gpio-xtensa.c b/drivers/gpio/gpio-xtensa.c index 08d7c3b32038..c8af34a6368f 100644 --- a/drivers/gpio/gpio-xtensa.c +++ b/drivers/gpio/gpio-xtensa.c @@ -44,15 +44,14 @@ static inline unsigned long enable_cp(unsigned long *cpenable) unsigned long flags; local_irq_save(flags); - RSR_CPENABLE(*cpenable); - WSR_CPENABLE(*cpenable | BIT(XCHAL_CP_ID_XTIOP)); - + *cpenable = xtensa_get_sr(cpenable); + xtensa_set_sr(*cpenable | BIT(XCHAL_CP_ID_XTIOP), cpenable); return flags; } static inline void disable_cp(unsigned long flags, unsigned long cpenable) { - WSR_CPENABLE(cpenable); + xtensa_set_sr(cpenable, cpenable); local_irq_restore(flags); } diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 9913886ede90..78a16e42f222 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -220,6 +220,14 @@ int gpiod_get_direction(struct gpio_desc *desc) chip = gpiod_to_chip(desc); offset = gpio_chip_hwgpio(desc); + /* + * Open drain emulation using input mode may incorrectly report + * input here, fix that up. + */ + if (test_bit(FLAG_OPEN_DRAIN, &desc->flags) && + test_bit(FLAG_IS_OUT, &desc->flags)) + return 0; + if (!chip->get_direction) return -ENOTSUPP; @@ -4472,8 +4480,9 @@ static struct gpio_desc *gpiod_find(struct device *dev, const char *con_id, if (chip->ngpio <= p->chip_hwnum) { dev_err(dev, - "requested GPIO %d is out of range [0..%d] for chip %s\n", - idx, chip->ngpio, chip->label); + "requested GPIO %u (%u) is out of range [0..%u] for chip %s\n", + idx, p->chip_hwnum, chip->ngpio - 1, + chip->label); return ERR_PTR(-EINVAL); } diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 6f5e3bd13ad1..effc4250b230 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -15112,7 +15112,7 @@ intel_prepare_plane_fb(struct drm_plane *plane, return ret; fb_obj_bump_render_priority(obj); - intel_frontbuffer_flush(obj->frontbuffer, ORIGIN_DIRTYFB); + i915_gem_object_flush_frontbuffer(obj, ORIGIN_DIRTYFB); if (!new_plane_state->base.fence) { /* implicit fencing */ struct dma_fence *fence; diff --git a/drivers/gpu/drm/i915/display/intel_frontbuffer.c b/drivers/gpu/drm/i915/display/intel_frontbuffer.c index 84b164f31895..6cb02c912acc 100644 --- a/drivers/gpu/drm/i915/display/intel_frontbuffer.c +++ b/drivers/gpu/drm/i915/display/intel_frontbuffer.c @@ -229,11 +229,11 @@ static void frontbuffer_release(struct kref *ref) vma->display_alignment = I915_GTT_MIN_ALIGNMENT; spin_unlock(&obj->vma.lock); - obj->frontbuffer = NULL; + RCU_INIT_POINTER(obj->frontbuffer, NULL); spin_unlock(&to_i915(obj->base.dev)->fb_tracking.lock); i915_gem_object_put(obj); - kfree(front); + kfree_rcu(front, rcu); } struct intel_frontbuffer * @@ -242,11 +242,7 @@ intel_frontbuffer_get(struct drm_i915_gem_object *obj) struct drm_i915_private *i915 = to_i915(obj->base.dev); struct intel_frontbuffer *front; - spin_lock(&i915->fb_tracking.lock); - front = obj->frontbuffer; - if (front) - kref_get(&front->ref); - spin_unlock(&i915->fb_tracking.lock); + front = __intel_frontbuffer_get(obj); if (front) return front; @@ -262,13 +258,13 @@ intel_frontbuffer_get(struct drm_i915_gem_object *obj) i915_active_may_sleep(frontbuffer_retire)); spin_lock(&i915->fb_tracking.lock); - if (obj->frontbuffer) { + if (rcu_access_pointer(obj->frontbuffer)) { kfree(front); - front = obj->frontbuffer; + front = rcu_dereference_protected(obj->frontbuffer, true); kref_get(&front->ref); } else { i915_gem_object_get(obj); - obj->frontbuffer = front; + rcu_assign_pointer(obj->frontbuffer, front); } spin_unlock(&i915->fb_tracking.lock); diff --git a/drivers/gpu/drm/i915/display/intel_frontbuffer.h b/drivers/gpu/drm/i915/display/intel_frontbuffer.h index adc64d61a4a5..6d41f5394425 100644 --- a/drivers/gpu/drm/i915/display/intel_frontbuffer.h +++ b/drivers/gpu/drm/i915/display/intel_frontbuffer.h @@ -27,10 +27,10 @@ #include <linux/atomic.h> #include <linux/kref.h> +#include "gem/i915_gem_object_types.h" #include "i915_active.h" struct drm_i915_private; -struct drm_i915_gem_object; enum fb_op_origin { ORIGIN_GTT, @@ -45,6 +45,7 @@ struct intel_frontbuffer { atomic_t bits; struct i915_active write; struct drm_i915_gem_object *obj; + struct rcu_head rcu; }; void intel_frontbuffer_flip_prepare(struct drm_i915_private *i915, @@ -54,6 +55,35 @@ void intel_frontbuffer_flip_complete(struct drm_i915_private *i915, void intel_frontbuffer_flip(struct drm_i915_private *i915, unsigned frontbuffer_bits); +void intel_frontbuffer_put(struct intel_frontbuffer *front); + +static inline struct intel_frontbuffer * +__intel_frontbuffer_get(const struct drm_i915_gem_object *obj) +{ + struct intel_frontbuffer *front; + + if (likely(!rcu_access_pointer(obj->frontbuffer))) + return NULL; + + rcu_read_lock(); + do { + front = rcu_dereference(obj->frontbuffer); + if (!front) + break; + + if (unlikely(!kref_get_unless_zero(&front->ref))) + continue; + + if (likely(front == rcu_access_pointer(obj->frontbuffer))) + break; + + intel_frontbuffer_put(front); + } while (1); + rcu_read_unlock(); + + return front; +} + struct intel_frontbuffer * intel_frontbuffer_get(struct drm_i915_gem_object *obj); @@ -119,6 +149,4 @@ void intel_frontbuffer_track(struct intel_frontbuffer *old, struct intel_frontbuffer *new, unsigned int frontbuffer_bits); -void intel_frontbuffer_put(struct intel_frontbuffer *front); - #endif /* __INTEL_FRONTBUFFER_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c index 848ce07a8ec2..8a98a1aa7adc 100644 --- a/drivers/gpu/drm/i915/display/intel_overlay.c +++ b/drivers/gpu/drm/i915/display/intel_overlay.c @@ -279,12 +279,21 @@ static void intel_overlay_flip_prepare(struct intel_overlay *overlay, struct i915_vma *vma) { enum pipe pipe = overlay->crtc->pipe; + struct intel_frontbuffer *from = NULL, *to = NULL; WARN_ON(overlay->old_vma); - intel_frontbuffer_track(overlay->vma ? overlay->vma->obj->frontbuffer : NULL, - vma ? vma->obj->frontbuffer : NULL, - INTEL_FRONTBUFFER_OVERLAY(pipe)); + if (overlay->vma) + from = intel_frontbuffer_get(overlay->vma->obj); + if (vma) + to = intel_frontbuffer_get(vma->obj); + + intel_frontbuffer_track(from, to, INTEL_FRONTBUFFER_OVERLAY(pipe)); + + if (to) + intel_frontbuffer_put(to); + if (from) + intel_frontbuffer_put(from); intel_frontbuffer_flip_prepare(overlay->i915, INTEL_FRONTBUFFER_OVERLAY(pipe)); @@ -766,7 +775,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay, ret = PTR_ERR(vma); goto out_pin_section; } - intel_frontbuffer_flush(new_bo->frontbuffer, ORIGIN_DIRTYFB); + i915_gem_object_flush_frontbuffer(new_bo, ORIGIN_DIRTYFB); if (!overlay->active) { u32 oconfig; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c index b9f504ba3b32..18ee708585a9 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c @@ -20,7 +20,8 @@ static void __do_clflush(struct drm_i915_gem_object *obj) { GEM_BUG_ON(!i915_gem_object_has_pages(obj)); drm_clflush_sg(obj->mm.pages); - intel_frontbuffer_flush(obj->frontbuffer, ORIGIN_CPU); + + i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU); } static int clflush_work(struct dma_fence_work *base) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c index 9937b4c341f1..f86400a191b0 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c @@ -664,7 +664,7 @@ i915_gem_set_domain_ioctl(struct drm_device *dev, void *data, i915_gem_object_unlock(obj); if (write_domain) - intel_frontbuffer_invalidate(obj->frontbuffer, ORIGIN_CPU); + i915_gem_object_invalidate_frontbuffer(obj, ORIGIN_CPU); out_unpin: i915_gem_object_unpin_pages(obj); @@ -784,7 +784,7 @@ int i915_gem_object_prepare_write(struct drm_i915_gem_object *obj, } out: - intel_frontbuffer_invalidate(obj->frontbuffer, ORIGIN_CPU); + i915_gem_object_invalidate_frontbuffer(obj, ORIGIN_CPU); obj->mm.dirty = true; /* return with the pages pinned */ return 0; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index a50296cce0d8..a596548c07bf 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -280,7 +280,7 @@ i915_gem_object_flush_write_domain(struct drm_i915_gem_object *obj, for_each_ggtt_vma(vma, obj) intel_gt_flush_ggtt_writes(vma->vm->gt); - intel_frontbuffer_flush(obj->frontbuffer, ORIGIN_CPU); + i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU); for_each_ggtt_vma(vma, obj) { if (vma->iomap) @@ -308,6 +308,30 @@ i915_gem_object_flush_write_domain(struct drm_i915_gem_object *obj, obj->write_domain = 0; } +void __i915_gem_object_flush_frontbuffer(struct drm_i915_gem_object *obj, + enum fb_op_origin origin) +{ + struct intel_frontbuffer *front; + + front = __intel_frontbuffer_get(obj); + if (front) { + intel_frontbuffer_flush(front, origin); + intel_frontbuffer_put(front); + } +} + +void __i915_gem_object_invalidate_frontbuffer(struct drm_i915_gem_object *obj, + enum fb_op_origin origin) +{ + struct intel_frontbuffer *front; + + front = __intel_frontbuffer_get(obj); + if (front) { + intel_frontbuffer_invalidate(front, origin); + intel_frontbuffer_put(front); + } +} + void i915_gem_init__objects(struct drm_i915_private *i915) { INIT_WORK(&i915->mm.free_work, __i915_gem_free_work); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index 458cd51331f1..4b93591fd5c7 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -13,8 +13,8 @@ #include <drm/i915_drm.h> +#include "display/intel_frontbuffer.h" #include "i915_gem_object_types.h" - #include "i915_gem_gtt.h" void i915_gem_init__objects(struct drm_i915_private *i915); @@ -463,4 +463,25 @@ int i915_gem_object_wait_priority(struct drm_i915_gem_object *obj, unsigned int flags, const struct i915_sched_attr *attr); +void __i915_gem_object_flush_frontbuffer(struct drm_i915_gem_object *obj, + enum fb_op_origin origin); +void __i915_gem_object_invalidate_frontbuffer(struct drm_i915_gem_object *obj, + enum fb_op_origin origin); + +static inline void +i915_gem_object_flush_frontbuffer(struct drm_i915_gem_object *obj, + enum fb_op_origin origin) +{ + if (unlikely(rcu_access_pointer(obj->frontbuffer))) + __i915_gem_object_flush_frontbuffer(obj, origin); +} + +static inline void +i915_gem_object_invalidate_frontbuffer(struct drm_i915_gem_object *obj, + enum fb_op_origin origin) +{ + if (unlikely(rcu_access_pointer(obj->frontbuffer))) + __i915_gem_object_invalidate_frontbuffer(obj, origin); +} + #endif diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index 96008374a412..e3f3944fbd90 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -150,7 +150,7 @@ struct drm_i915_gem_object { */ u16 write_domain; - struct intel_frontbuffer *frontbuffer; + struct intel_frontbuffer __rcu *frontbuffer; /** Current tiling stride for the object, if it's tiled. */ unsigned int tiling_and_stride; diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c index a459a42ad5c2..7e64b7d7d330 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c @@ -94,8 +94,9 @@ static int __gt_park(struct intel_wakeref *wf) intel_uncore_forcewake_put(&i915->uncore, FORCEWAKE_ALL); } + /* Defer dropping the display power well for 100ms, it's slow! */ GEM_BUG_ON(!wakeref); - intel_display_power_put(i915, POWER_DOMAIN_GT_IRQ, wakeref); + intel_display_power_put_async(i915, POWER_DOMAIN_GT_IRQ, wakeref); i915_globals_park(); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index d034fa413164..905890e3ac24 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -161,7 +161,7 @@ i915_gem_phys_pwrite(struct drm_i915_gem_object *obj, * We manually control the domain here and pretend that it * remains coherent i.e. in the GTT domain, like shmem_pwrite. */ - intel_frontbuffer_invalidate(obj->frontbuffer, ORIGIN_CPU); + i915_gem_object_invalidate_frontbuffer(obj, ORIGIN_CPU); if (copy_from_user(vaddr, user_data, args->size)) return -EFAULT; @@ -169,7 +169,7 @@ i915_gem_phys_pwrite(struct drm_i915_gem_object *obj, drm_clflush_virt_range(vaddr, args->size); intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt); - intel_frontbuffer_flush(obj->frontbuffer, ORIGIN_CPU); + i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU); return 0; } @@ -589,7 +589,7 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_gem_object *obj, goto out_unpin; } - intel_frontbuffer_invalidate(obj->frontbuffer, ORIGIN_CPU); + i915_gem_object_invalidate_frontbuffer(obj, ORIGIN_CPU); user_data = u64_to_user_ptr(args->data_ptr); offset = args->offset; @@ -631,7 +631,7 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_gem_object *obj, user_data += page_length; offset += page_length; } - intel_frontbuffer_flush(obj->frontbuffer, ORIGIN_CPU); + i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU); i915_gem_object_unlock_fence(obj, fence); out_unpin: @@ -721,7 +721,7 @@ i915_gem_shmem_pwrite(struct drm_i915_gem_object *obj, offset = 0; } - intel_frontbuffer_flush(obj->frontbuffer, ORIGIN_CPU); + i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU); i915_gem_object_unlock_fence(obj, fence); return ret; diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index 2814218c5ba1..6f09aa0be80a 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -144,61 +144,40 @@ static inline s64 ktime_since(const ktime_t kt) return ktime_to_ns(ktime_sub(ktime_get(), kt)); } -static u64 __pmu_estimate_rc6(struct i915_pmu *pmu) -{ - u64 val; - - /* - * We think we are runtime suspended. - * - * Report the delta from when the device was suspended to now, - * on top of the last known real value, as the approximated RC6 - * counter value. - */ - val = ktime_since(pmu->sleep_last); - val += pmu->sample[__I915_SAMPLE_RC6].cur; - - pmu->sample[__I915_SAMPLE_RC6_ESTIMATED].cur = val; - - return val; -} - -static u64 __pmu_update_rc6(struct i915_pmu *pmu, u64 val) -{ - /* - * If we are coming back from being runtime suspended we must - * be careful not to report a larger value than returned - * previously. - */ - if (val >= pmu->sample[__I915_SAMPLE_RC6_ESTIMATED].cur) { - pmu->sample[__I915_SAMPLE_RC6_ESTIMATED].cur = 0; - pmu->sample[__I915_SAMPLE_RC6].cur = val; - } else { - val = pmu->sample[__I915_SAMPLE_RC6_ESTIMATED].cur; - } - - return val; -} - static u64 get_rc6(struct intel_gt *gt) { struct drm_i915_private *i915 = gt->i915; struct i915_pmu *pmu = &i915->pmu; unsigned long flags; + bool awake = false; u64 val; - val = 0; if (intel_gt_pm_get_if_awake(gt)) { val = __get_rc6(gt); intel_gt_pm_put_async(gt); + awake = true; } spin_lock_irqsave(&pmu->lock, flags); - if (val) - val = __pmu_update_rc6(pmu, val); + if (awake) { + pmu->sample[__I915_SAMPLE_RC6].cur = val; + } else { + /* + * We think we are runtime suspended. + * + * Report the delta from when the device was suspended to now, + * on top of the last known real value, as the approximated RC6 + * counter value. + */ + val = ktime_since(pmu->sleep_last); + val += pmu->sample[__I915_SAMPLE_RC6].cur; + } + + if (val < pmu->sample[__I915_SAMPLE_RC6_LAST_REPORTED].cur) + val = pmu->sample[__I915_SAMPLE_RC6_LAST_REPORTED].cur; else - val = __pmu_estimate_rc6(pmu); + pmu->sample[__I915_SAMPLE_RC6_LAST_REPORTED].cur = val; spin_unlock_irqrestore(&pmu->lock, flags); @@ -210,20 +189,11 @@ static void park_rc6(struct drm_i915_private *i915) struct i915_pmu *pmu = &i915->pmu; if (pmu->enable & config_enabled_mask(I915_PMU_RC6_RESIDENCY)) - __pmu_update_rc6(pmu, __get_rc6(&i915->gt)); + pmu->sample[__I915_SAMPLE_RC6].cur = __get_rc6(&i915->gt); pmu->sleep_last = ktime_get(); } -static void unpark_rc6(struct drm_i915_private *i915) -{ - struct i915_pmu *pmu = &i915->pmu; - - /* Estimate how long we slept and accumulate that into rc6 counters */ - if (pmu->enable & config_enabled_mask(I915_PMU_RC6_RESIDENCY)) - __pmu_estimate_rc6(pmu); -} - #else static u64 get_rc6(struct intel_gt *gt) @@ -232,7 +202,6 @@ static u64 get_rc6(struct intel_gt *gt) } static void park_rc6(struct drm_i915_private *i915) {} -static void unpark_rc6(struct drm_i915_private *i915) {} #endif @@ -281,8 +250,6 @@ void i915_pmu_gt_unparked(struct drm_i915_private *i915) */ __i915_pmu_maybe_start_timer(pmu); - unpark_rc6(i915); - spin_unlock_irq(&pmu->lock); } diff --git a/drivers/gpu/drm/i915/i915_pmu.h b/drivers/gpu/drm/i915/i915_pmu.h index bf52e3983631..6c1647c5daf2 100644 --- a/drivers/gpu/drm/i915/i915_pmu.h +++ b/drivers/gpu/drm/i915/i915_pmu.h @@ -18,7 +18,7 @@ enum { __I915_SAMPLE_FREQ_ACT = 0, __I915_SAMPLE_FREQ_REQ, __I915_SAMPLE_RC6, - __I915_SAMPLE_RC6_ESTIMATED, + __I915_SAMPLE_RC6_LAST_REPORTED, __I915_NUM_PMU_SAMPLERS }; diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index e5512f26e20a..01c822256b39 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -1104,8 +1104,14 @@ int i915_vma_move_to_active(struct i915_vma *vma, return err; if (flags & EXEC_OBJECT_WRITE) { - if (intel_frontbuffer_invalidate(obj->frontbuffer, ORIGIN_CS)) - i915_active_add_request(&obj->frontbuffer->write, rq); + struct intel_frontbuffer *front; + + front = __intel_frontbuffer_get(obj); + if (unlikely(front)) { + if (intel_frontbuffer_invalidate(front, ORIGIN_CS)) + i915_active_add_request(&front->write, rq); + intel_frontbuffer_put(front); + } dma_resv_add_excl_fence(vma->resv, &rq->fence); obj->write_domain = I915_GEM_DOMAIN_RENDER; diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c index f3f0c3f07391..1962c8330daa 100644 --- a/drivers/net/dsa/bcm_sf2_cfp.c +++ b/drivers/net/dsa/bcm_sf2_cfp.c @@ -358,7 +358,7 @@ static int bcm_sf2_cfp_ipv4_rule_set(struct bcm_sf2_priv *priv, int port, return -EINVAL; } - ip_frag = be32_to_cpu(fs->m_ext.data[0]); + ip_frag = !!(be32_to_cpu(fs->h_ext.data[0]) & 1); /* Locate the first rule available */ if (fs->location == RX_CLS_LOC_ANY) @@ -569,7 +569,7 @@ static int bcm_sf2_cfp_rule_cmp(struct bcm_sf2_priv *priv, int port, if (rule->fs.flow_type != fs->flow_type || rule->fs.ring_cookie != fs->ring_cookie || - rule->fs.m_ext.data[0] != fs->m_ext.data[0]) + rule->fs.h_ext.data[0] != fs->h_ext.data[0]) continue; switch (fs->flow_type & ~FLOW_EXT) { @@ -621,7 +621,7 @@ static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port, return -EINVAL; } - ip_frag = be32_to_cpu(fs->m_ext.data[0]); + ip_frag = !!(be32_to_cpu(fs->h_ext.data[0]) & 1); layout = &udf_tcpip6_layout; slice_num = bcm_sf2_get_slice_number(layout, 0); diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index a51ac088c0bc..1da5ac111499 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1569,8 +1569,8 @@ static int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled) if (enabled) { /* Enable VLAN filtering. */ - tpid = ETH_P_8021AD; - tpid2 = ETH_P_8021Q; + tpid = ETH_P_8021Q; + tpid2 = ETH_P_8021AD; } else { /* Disable VLAN filtering. */ tpid = ETH_P_SJA1105; @@ -1579,9 +1579,9 @@ static int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled) table = &priv->static_config.tables[BLK_IDX_GENERAL_PARAMS]; general_params = table->entries; - /* EtherType used to identify outer tagged (S-tag) VLAN traffic */ - general_params->tpid = tpid; /* EtherType used to identify inner tagged (C-tag) VLAN traffic */ + general_params->tpid = tpid; + /* EtherType used to identify outer tagged (S-tag) VLAN traffic */ general_params->tpid2 = tpid2; /* When VLAN filtering is on, we need to at least be able to * decode management traffic through the "backup plan". @@ -1855,7 +1855,7 @@ static netdev_tx_t sja1105_port_deferred_xmit(struct dsa_switch *ds, int port, if (!clone) goto out; - sja1105_ptp_txtstamp_skb(ds, slot, clone); + sja1105_ptp_txtstamp_skb(ds, port, clone); out: mutex_unlock(&priv->mgmt_lock); diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c index e6b611470043..a836fc38c4a4 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.c +++ b/drivers/net/dsa/sja1105/sja1105_ptp.c @@ -237,7 +237,7 @@ int sja1105_ptp_commit(struct dsa_switch *ds, struct sja1105_ptp_cmd *cmd, if (rw == SPI_WRITE) priv->info->ptp_cmd_packing(buf, cmd, PACK); - rc = sja1105_xfer_buf(priv, SPI_WRITE, regs->ptp_control, buf, + rc = sja1105_xfer_buf(priv, rw, regs->ptp_control, buf, SJA1105_SIZE_PTP_CMD); if (rw == SPI_READ) @@ -659,7 +659,7 @@ void sja1105_ptp_clock_unregister(struct dsa_switch *ds) ptp_data->clock = NULL; } -void sja1105_ptp_txtstamp_skb(struct dsa_switch *ds, int slot, +void sja1105_ptp_txtstamp_skb(struct dsa_switch *ds, int port, struct sk_buff *skb) { struct sja1105_private *priv = ds->priv; @@ -679,7 +679,7 @@ void sja1105_ptp_txtstamp_skb(struct dsa_switch *ds, int slot, goto out; } - rc = sja1105_ptpegr_ts_poll(ds, slot, &ts); + rc = sja1105_ptpegr_ts_poll(ds, port, &ts); if (rc < 0) { dev_err(ds->dev, "timed out polling for tstamp\n"); kfree_skb(skb); diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.c b/drivers/net/dsa/sja1105/sja1105_static_config.c index 0d03e13e9909..63d2311817c4 100644 --- a/drivers/net/dsa/sja1105/sja1105_static_config.c +++ b/drivers/net/dsa/sja1105/sja1105_static_config.c @@ -142,6 +142,9 @@ static size_t sja1105et_general_params_entry_packing(void *buf, void *entry_ptr, return size; } +/* TPID and TPID2 are intentionally reversed so that semantic + * compatibility with E/T is kept. + */ static size_t sja1105pqrs_general_params_entry_packing(void *buf, void *entry_ptr, enum packing_op op) @@ -166,9 +169,9 @@ sja1105pqrs_general_params_entry_packing(void *buf, void *entry_ptr, sja1105_packing(buf, &entry->mirr_port, 141, 139, size, op); sja1105_packing(buf, &entry->vlmarker, 138, 107, size, op); sja1105_packing(buf, &entry->vlmask, 106, 75, size, op); - sja1105_packing(buf, &entry->tpid, 74, 59, size, op); + sja1105_packing(buf, &entry->tpid2, 74, 59, size, op); sja1105_packing(buf, &entry->ignore2stf, 58, 58, size, op); - sja1105_packing(buf, &entry->tpid2, 57, 42, size, op); + sja1105_packing(buf, &entry->tpid, 57, 42, size, op); sja1105_packing(buf, &entry->queue_ts, 41, 41, size, op); sja1105_packing(buf, &entry->egrmirrvid, 40, 29, size, op); sja1105_packing(buf, &entry->egrmirrpcp, 28, 26, size, op); diff --git a/drivers/net/dsa/sja1105/sja1105_tas.c b/drivers/net/dsa/sja1105/sja1105_tas.c index 26b925b5dace..fa6750d973d7 100644 --- a/drivers/net/dsa/sja1105/sja1105_tas.c +++ b/drivers/net/dsa/sja1105/sja1105_tas.c @@ -477,11 +477,6 @@ int sja1105_setup_tc_taprio(struct dsa_switch *ds, int port, if (admin->cycle_time_extension) return -ENOTSUPP; - if (!ns_to_sja1105_delta(admin->base_time)) { - dev_err(ds->dev, "A base time of zero is not hardware-allowed\n"); - return -ERANGE; - } - for (i = 0; i < admin->num_entries; i++) { s64 delta_ns = admin->entries[i].interval; s64 delta_cycles = ns_to_sja1105_delta(delta_ns); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h index 7a6e82db4231..bacc8552bce1 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h @@ -1536,8 +1536,11 @@ void bnx2x_get_rss_ind_table(struct bnx2x_rss_config_obj *rss_obj, ((MAX_MAC_CREDIT_E2 - GET_NUM_VFS_PER_PATH(bp) * VF_MAC_CREDIT_CNT) / \ func_num + GET_NUM_VFS_PER_PF(bp) * VF_MAC_CREDIT_CNT) +#define BNX2X_VFS_VLAN_CREDIT(bp) \ + (GET_NUM_VFS_PER_PATH(bp) * VF_VLAN_CREDIT_CNT) + #define PF_VLAN_CREDIT_E2(bp, func_num) \ - ((MAX_MAC_CREDIT_E2 - GET_NUM_VFS_PER_PATH(bp) * VF_VLAN_CREDIT_CNT) / \ + ((MAX_VLAN_CREDIT_E2 - 1 - BNX2X_VFS_VLAN_CREDIT(bp)) / \ func_num + GET_NUM_VFS_PER_PF(bp) * VF_VLAN_CREDIT_CNT) #endif /* BNX2X_SP_VERBS */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index eda8e1269551..8b7d156f79d3 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -515,6 +515,7 @@ struct link_config { enum cc_pause requested_fc; /* flow control user has requested */ enum cc_pause fc; /* actual link flow control */ + enum cc_pause advertised_fc; /* actual advertised flow control */ enum cc_fec requested_fec; /* Forward Error Correction: */ enum cc_fec fec; /* requested and actual in use */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index 20ab3b6285a2..c837382ee522 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -807,8 +807,8 @@ static void get_pauseparam(struct net_device *dev, struct port_info *p = netdev_priv(dev); epause->autoneg = (p->link_cfg.requested_fc & PAUSE_AUTONEG) != 0; - epause->rx_pause = (p->link_cfg.fc & PAUSE_RX) != 0; - epause->tx_pause = (p->link_cfg.fc & PAUSE_TX) != 0; + epause->rx_pause = (p->link_cfg.advertised_fc & PAUSE_RX) != 0; + epause->tx_pause = (p->link_cfg.advertised_fc & PAUSE_TX) != 0; } static int set_pauseparam(struct net_device *dev, diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 19d18acfc9a6..844fdcf55118 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -4089,7 +4089,8 @@ static inline fw_port_cap32_t cc_to_fwcap_pause(enum cc_pause cc_pause) if (cc_pause & PAUSE_TX) fw_pause |= FW_PORT_CAP32_802_3_PAUSE; else - fw_pause |= FW_PORT_CAP32_802_3_ASM_DIR; + fw_pause |= FW_PORT_CAP32_802_3_ASM_DIR | + FW_PORT_CAP32_802_3_PAUSE; } else if (cc_pause & PAUSE_TX) { fw_pause |= FW_PORT_CAP32_802_3_ASM_DIR; } @@ -8563,17 +8564,17 @@ static fw_port_cap32_t lstatus_to_fwcap(u32 lstatus) void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl) { const struct fw_port_cmd *cmd = (const void *)rpl; - int action = FW_PORT_CMD_ACTION_G(be32_to_cpu(cmd->action_to_len16)); - struct adapter *adapter = pi->adapter; + fw_port_cap32_t pcaps, acaps, lpacaps, linkattr; struct link_config *lc = &pi->link_cfg; - int link_ok, linkdnrc; - enum fw_port_type port_type; + struct adapter *adapter = pi->adapter; + unsigned int speed, fc, fec, adv_fc; enum fw_port_module_type mod_type; - unsigned int speed, fc, fec; - fw_port_cap32_t pcaps, acaps, lpacaps, linkattr; + int action, link_ok, linkdnrc; + enum fw_port_type port_type; /* Extract the various fields from the Port Information message. */ + action = FW_PORT_CMD_ACTION_G(be32_to_cpu(cmd->action_to_len16)); switch (action) { case FW_PORT_ACTION_GET_PORT_INFO: { u32 lstatus = be32_to_cpu(cmd->u.info.lstatus_to_modtype); @@ -8611,6 +8612,7 @@ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl) } fec = fwcap_to_cc_fec(acaps); + adv_fc = fwcap_to_cc_pause(acaps); fc = fwcap_to_cc_pause(linkattr); speed = fwcap_to_speed(linkattr); @@ -8667,7 +8669,9 @@ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl) } if (link_ok != lc->link_ok || speed != lc->speed || - fc != lc->fc || fec != lc->fec) { /* something changed */ + fc != lc->fc || adv_fc != lc->advertised_fc || + fec != lc->fec) { + /* something changed */ if (!link_ok && lc->link_ok) { lc->link_down_rc = linkdnrc; dev_warn_ratelimited(adapter->pdev_dev, @@ -8677,6 +8681,7 @@ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl) } lc->link_ok = link_ok; lc->speed = speed; + lc->advertised_fc = adv_fc; lc->fc = fc; lc->fec = fec; diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index f6fc0875d5b0..f4d41f968afa 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -1690,8 +1690,8 @@ static void cxgb4vf_get_pauseparam(struct net_device *dev, struct port_info *pi = netdev_priv(dev); pauseparam->autoneg = (pi->link_cfg.requested_fc & PAUSE_AUTONEG) != 0; - pauseparam->rx_pause = (pi->link_cfg.fc & PAUSE_RX) != 0; - pauseparam->tx_pause = (pi->link_cfg.fc & PAUSE_TX) != 0; + pauseparam->rx_pause = (pi->link_cfg.advertised_fc & PAUSE_RX) != 0; + pauseparam->tx_pause = (pi->link_cfg.advertised_fc & PAUSE_TX) != 0; } /* diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h index ccca67cf4487..57cfd10a99ec 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h +++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h @@ -135,6 +135,7 @@ struct link_config { enum cc_pause requested_fc; /* flow control user has requested */ enum cc_pause fc; /* actual link flow control */ + enum cc_pause advertised_fc; /* actual advertised flow control */ enum cc_fec auto_fec; /* Forward Error Correction: */ enum cc_fec requested_fec; /* "automatic" (IEEE 802.3), */ diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c index 8a389d617a23..9d49ff211cc1 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c @@ -1913,16 +1913,16 @@ static const char *t4vf_link_down_rc_str(unsigned char link_down_rc) static void t4vf_handle_get_port_info(struct port_info *pi, const struct fw_port_cmd *cmd) { - int action = FW_PORT_CMD_ACTION_G(be32_to_cpu(cmd->action_to_len16)); - struct adapter *adapter = pi->adapter; + fw_port_cap32_t pcaps, acaps, lpacaps, linkattr; struct link_config *lc = &pi->link_cfg; - int link_ok, linkdnrc; - enum fw_port_type port_type; + struct adapter *adapter = pi->adapter; + unsigned int speed, fc, fec, adv_fc; enum fw_port_module_type mod_type; - unsigned int speed, fc, fec; - fw_port_cap32_t pcaps, acaps, lpacaps, linkattr; + int action, link_ok, linkdnrc; + enum fw_port_type port_type; /* Extract the various fields from the Port Information message. */ + action = FW_PORT_CMD_ACTION_G(be32_to_cpu(cmd->action_to_len16)); switch (action) { case FW_PORT_ACTION_GET_PORT_INFO: { u32 lstatus = be32_to_cpu(cmd->u.info.lstatus_to_modtype); @@ -1982,6 +1982,7 @@ static void t4vf_handle_get_port_info(struct port_info *pi, } fec = fwcap_to_cc_fec(acaps); + adv_fc = fwcap_to_cc_pause(acaps); fc = fwcap_to_cc_pause(linkattr); speed = fwcap_to_speed(linkattr); @@ -2012,7 +2013,9 @@ static void t4vf_handle_get_port_info(struct port_info *pi, } if (link_ok != lc->link_ok || speed != lc->speed || - fc != lc->fc || fec != lc->fec) { /* something changed */ + fc != lc->fc || adv_fc != lc->advertised_fc || + fec != lc->fec) { + /* something changed */ if (!link_ok && lc->link_ok) { lc->link_down_rc = linkdnrc; dev_warn_ratelimited(adapter->pdev_dev, @@ -2022,6 +2025,7 @@ static void t4vf_handle_get_port_info(struct port_info *pi, } lc->link_ok = link_ok; lc->speed = speed; + lc->advertised_fc = adv_fc; lc->fc = fc; lc->fec = fec; diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index a60fc3cfc06e..09dbcd819d84 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -1719,7 +1719,7 @@ static struct sk_buff *sg_fd_to_skb(const struct dpaa_priv *priv, int page_offset; unsigned int sz; int *count_ptr; - int i; + int i, j; vaddr = phys_to_virt(addr); WARN_ON(!IS_ALIGNED((unsigned long)vaddr, SMP_CACHE_BYTES)); @@ -1736,14 +1736,14 @@ static struct sk_buff *sg_fd_to_skb(const struct dpaa_priv *priv, WARN_ON(!IS_ALIGNED((unsigned long)sg_vaddr, SMP_CACHE_BYTES)); + dma_unmap_page(priv->rx_dma_dev, sg_addr, + DPAA_BP_RAW_SIZE, DMA_FROM_DEVICE); + /* We may use multiple Rx pools */ dpaa_bp = dpaa_bpid2pool(sgt[i].bpid); if (!dpaa_bp) goto free_buffers; - count_ptr = this_cpu_ptr(dpaa_bp->percpu_count); - dma_unmap_page(priv->rx_dma_dev, sg_addr, - DPAA_BP_RAW_SIZE, DMA_FROM_DEVICE); if (!skb) { sz = dpaa_bp->size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); @@ -1786,7 +1786,9 @@ static struct sk_buff *sg_fd_to_skb(const struct dpaa_priv *priv, skb_add_rx_frag(skb, i - 1, head_page, frag_off, frag_len, dpaa_bp->size); } + /* Update the pool count for the current {cpu x bpool} */ + count_ptr = this_cpu_ptr(dpaa_bp->percpu_count); (*count_ptr)--; if (qm_sg_entry_is_final(&sgt[i])) @@ -1800,26 +1802,25 @@ static struct sk_buff *sg_fd_to_skb(const struct dpaa_priv *priv, return skb; free_buffers: - /* compensate sw bpool counter changes */ - for (i--; i >= 0; i--) { - dpaa_bp = dpaa_bpid2pool(sgt[i].bpid); - if (dpaa_bp) { - count_ptr = this_cpu_ptr(dpaa_bp->percpu_count); - (*count_ptr)++; - } - } /* free all the SG entries */ - for (i = 0; i < DPAA_SGT_MAX_ENTRIES ; i++) { - sg_addr = qm_sg_addr(&sgt[i]); + for (j = 0; j < DPAA_SGT_MAX_ENTRIES ; j++) { + sg_addr = qm_sg_addr(&sgt[j]); sg_vaddr = phys_to_virt(sg_addr); + /* all pages 0..i were unmaped */ + if (j > i) + dma_unmap_page(priv->rx_dma_dev, qm_sg_addr(&sgt[j]), + DPAA_BP_RAW_SIZE, DMA_FROM_DEVICE); free_pages((unsigned long)sg_vaddr, 0); - dpaa_bp = dpaa_bpid2pool(sgt[i].bpid); - if (dpaa_bp) { - count_ptr = this_cpu_ptr(dpaa_bp->percpu_count); - (*count_ptr)--; + /* counters 0..i-1 were decremented */ + if (j >= i) { + dpaa_bp = dpaa_bpid2pool(sgt[j].bpid); + if (dpaa_bp) { + count_ptr = this_cpu_ptr(dpaa_bp->percpu_count); + (*count_ptr)--; + } } - if (qm_sg_entry_is_final(&sgt[i])) + if (qm_sg_entry_is_final(&sgt[j])) break; } /* free the SGT fragment */ diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c index 544344ac4894..79057af4fe99 100644 --- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c +++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c @@ -6,6 +6,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/netlink.h> +#include <linux/vmalloc.h> #include <linux/xz.h> #include "mlxfw_mfa2.h" #include "mlxfw_mfa2_file.h" @@ -548,7 +549,7 @@ mlxfw_mfa2_file_component_get(const struct mlxfw_mfa2_file *mfa2_file, comp_size = be32_to_cpu(comp->size); comp_buf_size = comp_size + mlxfw_mfa2_comp_magic_len; - comp_data = kmalloc(sizeof(*comp_data) + comp_buf_size, GFP_KERNEL); + comp_data = vzalloc(sizeof(*comp_data) + comp_buf_size); if (!comp_data) return ERR_PTR(-ENOMEM); comp_data->comp.data_size = comp_size; @@ -570,7 +571,7 @@ mlxfw_mfa2_file_component_get(const struct mlxfw_mfa2_file *mfa2_file, comp_data->comp.data = comp_data->buff + mlxfw_mfa2_comp_magic_len; return &comp_data->comp; err_out: - kfree(comp_data); + vfree(comp_data); return ERR_PTR(err); } @@ -579,7 +580,7 @@ void mlxfw_mfa2_file_component_put(struct mlxfw_mfa2_component *comp) const struct mlxfw_mfa2_comp_data *comp_data; comp_data = container_of(comp, struct mlxfw_mfa2_comp_data, comp); - kfree(comp_data); + vfree(comp_data); } void mlxfw_mfa2_file_fini(struct mlxfw_mfa2_file *mfa2_file) diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 86a2d575ae73..2b8b4ed6bbef 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -5471,6 +5471,7 @@ enum mlxsw_reg_htgt_trap_group { MLXSW_REG_HTGT_TRAP_GROUP_SP_LBERROR, MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP0, MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP1, + MLXSW_REG_HTGT_TRAP_GROUP_SP_VRRP, __MLXSW_REG_HTGT_TRAP_GROUP_MAX, MLXSW_REG_HTGT_TRAP_GROUP_MAX = __MLXSW_REG_HTGT_TRAP_GROUP_MAX - 1 diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index ea632042e609..fe02ffb1e3a8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4543,8 +4543,8 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = { MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV6, TRAP_TO_CPU, ROUTER_EXP, false), MLXSW_SP_RXL_MARK(IPIP_DECAP_ERROR, TRAP_TO_CPU, ROUTER_EXP, false), MLXSW_SP_RXL_MARK(DECAP_ECN0, TRAP_TO_CPU, ROUTER_EXP, false), - MLXSW_SP_RXL_MARK(IPV4_VRRP, TRAP_TO_CPU, ROUTER_EXP, false), - MLXSW_SP_RXL_MARK(IPV6_VRRP, TRAP_TO_CPU, ROUTER_EXP, false), + MLXSW_SP_RXL_MARK(IPV4_VRRP, TRAP_TO_CPU, VRRP, false), + MLXSW_SP_RXL_MARK(IPV6_VRRP, TRAP_TO_CPU, VRRP, false), /* PKT Sample trap */ MLXSW_RXL(mlxsw_sp_rx_listener_sample_func, PKT_SAMPLE, MIRROR_TO_CPU, false, SP_IP2ME, DISCARD), @@ -4627,6 +4627,10 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core) rate = 19 * 1024; burst_size = 12; break; + case MLXSW_REG_HTGT_TRAP_GROUP_SP_VRRP: + rate = 360; + burst_size = 7; + break; default: continue; } @@ -4666,6 +4670,7 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core) case MLXSW_REG_HTGT_TRAP_GROUP_SP_OSPF: case MLXSW_REG_HTGT_TRAP_GROUP_SP_PIM: case MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP0: + case MLXSW_REG_HTGT_TRAP_GROUP_SP_VRRP: priority = 5; tc = 5; break; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index da1c8342c8f5..7f70aa799064 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -6787,6 +6787,9 @@ static int mlxsw_sp_router_port_check_rif_addr(struct mlxsw_sp *mlxsw_sp, for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) { rif = mlxsw_sp->router->rifs[i]; + if (rif && rif->ops && + rif->ops->type == MLXSW_SP_RIF_TYPE_IPIP_LB) + continue; if (rif && rif->dev && rif->dev != dev && !ether_addr_equal_masked(rif->dev->dev_addr, dev_addr, mlxsw_sp->mac_mask)) { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c index bd6c01004913..0e2fa14f1423 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c @@ -112,6 +112,14 @@ static int meson8b_init_rgmii_tx_clk(struct meson8b_dwmac *dwmac) struct device *dev = dwmac->dev; const char *parent_name, *mux_parent_names[MUX_CLK_NUM_PARENTS]; struct meson8b_dwmac_clk_configs *clk_configs; + static const struct clk_div_table div_table[] = { + { .div = 2, .val = 2, }, + { .div = 3, .val = 3, }, + { .div = 4, .val = 4, }, + { .div = 5, .val = 5, }, + { .div = 6, .val = 6, }, + { .div = 7, .val = 7, }, + }; clk_configs = devm_kzalloc(dev, sizeof(*clk_configs), GFP_KERNEL); if (!clk_configs) @@ -146,9 +154,9 @@ static int meson8b_init_rgmii_tx_clk(struct meson8b_dwmac *dwmac) clk_configs->m250_div.reg = dwmac->regs + PRG_ETH0; clk_configs->m250_div.shift = PRG_ETH0_CLK_M250_DIV_SHIFT; clk_configs->m250_div.width = PRG_ETH0_CLK_M250_DIV_WIDTH; - clk_configs->m250_div.flags = CLK_DIVIDER_ONE_BASED | - CLK_DIVIDER_ALLOW_ZERO | - CLK_DIVIDER_ROUND_CLOSEST; + clk_configs->m250_div.table = div_table; + clk_configs->m250_div.flags = CLK_DIVIDER_ALLOW_ZERO | + CLK_DIVIDER_ROUND_CLOSEST; clk = meson8b_dwmac_register_clk(dwmac, "m250_div", &parent_name, 1, &clk_divider_ops, &clk_configs->m250_div.hw); diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index e5b7d6d2286e..fca471e27f39 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -540,7 +540,7 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev, mtu = dst_mtu(&rt->dst); } - rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu); + rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu, false); if (!skb_is_gso(skb) && (iph->frag_off & htons(IP_DF)) && mtu < ntohs(iph->tot_len)) { diff --git a/drivers/net/phy/aquantia_main.c b/drivers/net/phy/aquantia_main.c index 3b29d381116f..975789d9349d 100644 --- a/drivers/net/phy/aquantia_main.c +++ b/drivers/net/phy/aquantia_main.c @@ -627,6 +627,8 @@ static struct phy_driver aqr_driver[] = { .config_intr = aqr_config_intr, .ack_interrupt = aqr_ack_interrupt, .read_status = aqr_read_status, + .suspend = aqr107_suspend, + .resume = aqr107_resume, }, { PHY_ID_MATCH_MODEL(PHY_ID_AQR106), diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 4f0d91a76dcb..da97a5bab26e 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -166,9 +166,9 @@ static struct posix_clock_operations ptp_clock_ops = { .read = ptp_read, }; -static void delete_ptp_clock(struct posix_clock *pc) +static void ptp_clock_release(struct device *dev) { - struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock); + struct ptp_clock *ptp = container_of(dev, struct ptp_clock, dev); mutex_destroy(&ptp->tsevq_mux); mutex_destroy(&ptp->pincfg_mux); @@ -213,7 +213,6 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, } ptp->clock.ops = ptp_clock_ops; - ptp->clock.release = delete_ptp_clock; ptp->info = info; ptp->devid = MKDEV(major, index); ptp->index = index; @@ -236,15 +235,6 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, if (err) goto no_pin_groups; - /* Create a new device in our class. */ - ptp->dev = device_create_with_groups(ptp_class, parent, ptp->devid, - ptp, ptp->pin_attr_groups, - "ptp%d", ptp->index); - if (IS_ERR(ptp->dev)) { - err = PTR_ERR(ptp->dev); - goto no_device; - } - /* Register a new PPS source. */ if (info->pps) { struct pps_source_info pps; @@ -260,8 +250,18 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, } } - /* Create a posix clock. */ - err = posix_clock_register(&ptp->clock, ptp->devid); + /* Initialize a new device of our class in our clock structure. */ + device_initialize(&ptp->dev); + ptp->dev.devt = ptp->devid; + ptp->dev.class = ptp_class; + ptp->dev.parent = parent; + ptp->dev.groups = ptp->pin_attr_groups; + ptp->dev.release = ptp_clock_release; + dev_set_drvdata(&ptp->dev, ptp); + dev_set_name(&ptp->dev, "ptp%d", ptp->index); + + /* Create a posix clock and link it to the device. */ + err = posix_clock_register(&ptp->clock, &ptp->dev); if (err) { pr_err("failed to create posix clock\n"); goto no_clock; @@ -273,8 +273,6 @@ no_clock: if (ptp->pps_source) pps_unregister_source(ptp->pps_source); no_pps: - device_destroy(ptp_class, ptp->devid); -no_device: ptp_cleanup_pin_groups(ptp); no_pin_groups: if (ptp->kworker) @@ -304,7 +302,6 @@ int ptp_clock_unregister(struct ptp_clock *ptp) if (ptp->pps_source) pps_unregister_source(ptp->pps_source); - device_destroy(ptp_class, ptp->devid); ptp_cleanup_pin_groups(ptp); posix_clock_unregister(&ptp->clock); diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h index 9171d42468fd..6b97155148f1 100644 --- a/drivers/ptp/ptp_private.h +++ b/drivers/ptp/ptp_private.h @@ -28,7 +28,7 @@ struct timestamp_event_queue { struct ptp_clock { struct posix_clock clock; - struct device *dev; + struct device dev; struct ptp_clock_info *info; dev_t devid; int index; /* index into clocks.map */ diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 3be3d13f8d65..c19cc3978e1f 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -2473,50 +2473,46 @@ static int qeth_mpc_initialize(struct qeth_card *card) rc = qeth_cm_enable(card); if (rc) { QETH_CARD_TEXT_(card, 2, "2err%d", rc); - goto out_qdio; + return rc; } rc = qeth_cm_setup(card); if (rc) { QETH_CARD_TEXT_(card, 2, "3err%d", rc); - goto out_qdio; + return rc; } rc = qeth_ulp_enable(card); if (rc) { QETH_CARD_TEXT_(card, 2, "4err%d", rc); - goto out_qdio; + return rc; } rc = qeth_ulp_setup(card); if (rc) { QETH_CARD_TEXT_(card, 2, "5err%d", rc); - goto out_qdio; + return rc; } rc = qeth_alloc_qdio_queues(card); if (rc) { QETH_CARD_TEXT_(card, 2, "5err%d", rc); - goto out_qdio; + return rc; } rc = qeth_qdio_establish(card); if (rc) { QETH_CARD_TEXT_(card, 2, "6err%d", rc); qeth_free_qdio_queues(card); - goto out_qdio; + return rc; } rc = qeth_qdio_activate(card); if (rc) { QETH_CARD_TEXT_(card, 2, "7err%d", rc); - goto out_qdio; + return rc; } rc = qeth_dm_act(card); if (rc) { QETH_CARD_TEXT_(card, 2, "8err%d", rc); - goto out_qdio; + return rc; } return 0; -out_qdio: - qeth_qdio_clear_card(card, !IS_IQD(card)); - qdio_free(CARD_DDEV(card)); - return rc; } void qeth_print_status_message(struct qeth_card *card) @@ -3419,11 +3415,6 @@ int qeth_configure_cq(struct qeth_card *card, enum qeth_cq cq) goto out; } - if (card->state != CARD_STATE_DOWN) { - rc = -1; - goto out; - } - qeth_free_qdio_queues(card); card->options.cq = cq; rc = 0; @@ -5023,10 +5014,8 @@ retriable: } if (qeth_adp_supported(card, IPA_SETADP_SET_DIAG_ASSIST)) { rc = qeth_query_setdiagass(card); - if (rc < 0) { + if (rc) QETH_CARD_TEXT_(card, 2, "8err%d", rc); - goto out; - } } if (!qeth_is_diagass_supported(card, QETH_DIAGS_CMD_TRAP) || diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 69d147c4d2ca..7175b5d8a23c 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -287,12 +287,12 @@ static void qeth_l2_stop_card(struct qeth_card *card) card->state = CARD_STATE_HARDSETUP; } if (card->state == CARD_STATE_HARDSETUP) { - qeth_qdio_clear_card(card, 0); qeth_drain_output_queues(card); qeth_clear_working_pool_list(card); card->state = CARD_STATE_DOWN; } + qeth_qdio_clear_card(card, 0); flush_workqueue(card->event_wq); card->info.mac_bits &= ~QETH_LAYER2_MAC_REGISTERED; card->info.promisc_mode = 0; @@ -1912,8 +1912,7 @@ int qeth_l2_vnicc_get_timeout(struct qeth_card *card, u32 *timeout) /* check if VNICC is currently enabled */ bool qeth_l2_vnicc_is_in_use(struct qeth_card *card) { - /* if everything is turned off, VNICC is not active */ - if (!card->options.vnicc.cur_chars) + if (!card->options.vnicc.sup_chars) return false; /* default values are only OK if rx_bcast was not enabled by user * or the card is offline. @@ -2000,8 +1999,9 @@ static void qeth_l2_vnicc_init(struct qeth_card *card) /* enforce assumed default values and recover settings, if changed */ error |= qeth_l2_vnicc_recover_timeout(card, QETH_VNICC_LEARNING, timeout); - chars_tmp = card->options.vnicc.wanted_chars ^ QETH_VNICC_DEFAULT; - chars_tmp |= QETH_VNICC_BRIDGE_INVISIBLE; + /* Change chars, if necessary */ + chars_tmp = card->options.vnicc.wanted_chars ^ + card->options.vnicc.cur_chars; chars_len = sizeof(card->options.vnicc.wanted_chars) * BITS_PER_BYTE; for_each_set_bit(i, &chars_tmp, chars_len) { vnicc = BIT(i); diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 8a1535ee1467..6c0bffd11138 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -1183,12 +1183,12 @@ static void qeth_l3_stop_card(struct qeth_card *card) card->state = CARD_STATE_HARDSETUP; } if (card->state == CARD_STATE_HARDSETUP) { - qeth_qdio_clear_card(card, 0); qeth_drain_output_queues(card); qeth_clear_working_pool_list(card); card->state = CARD_STATE_DOWN; } + qeth_qdio_clear_card(card, 0); flush_workqueue(card->event_wq); card->info.promisc_mode = 0; } diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c index 96c73965eb68..29f2517d2a31 100644 --- a/drivers/s390/net/qeth_l3_sys.c +++ b/drivers/s390/net/qeth_l3_sys.c @@ -242,21 +242,33 @@ static ssize_t qeth_l3_dev_hsuid_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct qeth_card *card = dev_get_drvdata(dev); + int rc = 0; char *tmp; - int rc; if (!IS_IQD(card)) return -EPERM; - if (card->state != CARD_STATE_DOWN) - return -EPERM; - if (card->options.sniffer) - return -EPERM; - if (card->options.cq == QETH_CQ_NOTAVAILABLE) - return -EPERM; + + mutex_lock(&card->conf_mutex); + if (card->state != CARD_STATE_DOWN) { + rc = -EPERM; + goto out; + } + + if (card->options.sniffer) { + rc = -EPERM; + goto out; + } + + if (card->options.cq == QETH_CQ_NOTAVAILABLE) { + rc = -EPERM; + goto out; + } tmp = strsep((char **)&buf, "\n"); - if (strlen(tmp) > 8) - return -EINVAL; + if (strlen(tmp) > 8) { + rc = -EINVAL; + goto out; + } if (card->options.hsuid[0]) /* delete old ip address */ @@ -267,11 +279,13 @@ static ssize_t qeth_l3_dev_hsuid_store(struct device *dev, card->options.hsuid[0] = '\0'; memcpy(card->dev->perm_addr, card->options.hsuid, 9); qeth_configure_cq(card, QETH_CQ_DISABLED); - return count; + goto out; } - if (qeth_configure_cq(card, QETH_CQ_ENABLED)) - return -EPERM; + if (qeth_configure_cq(card, QETH_CQ_ENABLED)) { + rc = -EPERM; + goto out; + } snprintf(card->options.hsuid, sizeof(card->options.hsuid), "%-8s", tmp); @@ -280,6 +294,8 @@ static ssize_t qeth_l3_dev_hsuid_store(struct device *dev, rc = qeth_l3_modify_hsuid(card, true); +out: + mutex_unlock(&card->conf_mutex); return rc ? rc : count; } diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c index c4e4b0136f86..4bc794d2f51c 100644 --- a/drivers/scsi/cxgbi/libcxgbi.c +++ b/drivers/scsi/cxgbi/libcxgbi.c @@ -121,7 +121,8 @@ static inline void cxgbi_device_destroy(struct cxgbi_device *cdev) "cdev 0x%p, p# %u.\n", cdev, cdev->nports); cxgbi_hbas_remove(cdev); cxgbi_device_portmap_cleanup(cdev); - cxgbi_ppm_release(cdev->cdev2ppm(cdev)); + if (cdev->cdev2ppm) + cxgbi_ppm_release(cdev->cdev2ppm(cdev)); if (cdev->pmap.max_connect) cxgbi_free_big_mem(cdev->pmap.port_csk); kfree(cdev); diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c index 2e6a68d9ea4f..a5ecbce4eda2 100644 --- a/drivers/scsi/lpfc/lpfc_debugfs.c +++ b/drivers/scsi/lpfc/lpfc_debugfs.c @@ -5385,7 +5385,6 @@ static const struct file_operations lpfc_debugfs_ras_log = { .read = lpfc_debugfs_read, .release = lpfc_debugfs_ras_log_release, }; -#endif #undef lpfc_debugfs_op_dumpHBASlim static const struct file_operations lpfc_debugfs_op_dumpHBASlim = { @@ -5557,7 +5556,7 @@ static const struct file_operations lpfc_idiag_op_extAcc = { .write = lpfc_idiag_extacc_write, .release = lpfc_idiag_cmd_release, }; - +#endif /* lpfc_idiag_mbxacc_dump_bsg_mbox - idiag debugfs dump bsg mailbox command * @phba: Pointer to HBA context object. diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 6298b1729098..6a04fdb3fbf2 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -5883,7 +5883,7 @@ void lpfc_sli4_async_event_proc(struct lpfc_hba *phba) break; default: lpfc_printf_log(phba, KERN_ERR, LOG_SLI, - "1804 Invalid asynchrous event code: " + "1804 Invalid asynchronous event code: " "x%x\n", bf_get(lpfc_trailer_code, &cq_event->cqe.mcqe_cmpl)); break; diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index c82b5792da98..625c046ac4ef 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -8555,7 +8555,7 @@ lpfc_sli4_async_mbox_unblock(struct lpfc_hba *phba) psli->sli_flag &= ~LPFC_SLI_ASYNC_MBX_BLK; spin_unlock_irq(&phba->hbalock); - /* wake up worker thread to post asynchronlous mailbox command */ + /* wake up worker thread to post asynchronous mailbox command */ lpfc_worker_wake_up(phba); } @@ -8823,7 +8823,7 @@ lpfc_sli_issue_mbox_s4(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq, return rc; } - /* Now, interrupt mode asynchrous mailbox command */ + /* Now, interrupt mode asynchronous mailbox command */ rc = lpfc_mbox_cmd_check(phba, mboxq); if (rc) { lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_SLI, @@ -13112,11 +13112,11 @@ lpfc_cq_event_setup(struct lpfc_hba *phba, void *entry, int size) } /** - * lpfc_sli4_sp_handle_async_event - Handle an asynchroous event + * lpfc_sli4_sp_handle_async_event - Handle an asynchronous event * @phba: Pointer to HBA context object. * @cqe: Pointer to mailbox completion queue entry. * - * This routine process a mailbox completion queue entry with asynchrous + * This routine process a mailbox completion queue entry with asynchronous * event. * * Return: true if work posted to worker thread, otherwise false. @@ -13270,7 +13270,7 @@ out_no_mqe_complete: * @cqe: Pointer to mailbox completion queue entry. * * This routine process a mailbox completion queue entry, it invokes the - * proper mailbox complete handling or asynchrous event handling routine + * proper mailbox complete handling or asynchronous event handling routine * according to the MCQE's async bit. * * Return: true if work posted to worker thread, otherwise false. diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 848fbec7bda6..45fd8dfb7c40 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -5248,7 +5248,6 @@ _base_allocate_memory_pools(struct MPT3SAS_ADAPTER *ioc) &ct->chain_buffer_dma); if (!ct->chain_buffer) { ioc_err(ioc, "chain_lookup: pci_pool_alloc failed\n"); - _base_release_memory_pools(ioc); goto out; } } diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index 6949ea8bc387..51ffd5c002de 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -646,7 +646,9 @@ iblock_alloc_bip(struct se_cmd *cmd, struct bio *bio, } bip->bip_iter.bi_size = bio_integrity_bytes(bi, bio_sectors(bio)); - bip_set_seed(bip, bio->bi_iter.bi_sector); + /* virtual start sector must be in integrity interval units */ + bip_set_seed(bip, bio->bi_iter.bi_sector >> + (bi->interval_exp - SECTOR_SHIFT)); pr_debug("IBLOCK BIP Size: %u Sector: %llu\n", bip->bip_iter.bi_size, (unsigned long long)bip->bip_iter.bi_sector); diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index ce9bac756c2a..40705e862451 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1693,6 +1693,7 @@ struct cifs_fattr { struct timespec64 cf_atime; struct timespec64 cf_mtime; struct timespec64 cf_ctime; + u32 cf_cifstag; }; static inline void free_dfs_info_param(struct dfs_info3_param *param) diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 3925a7bfc74d..d17587c2c4ab 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -139,6 +139,28 @@ retry: dput(dentry); } +static bool reparse_file_needs_reval(const struct cifs_fattr *fattr) +{ + if (!(fattr->cf_cifsattrs & ATTR_REPARSE)) + return false; + /* + * The DFS tags should be only intepreted by server side as per + * MS-FSCC 2.1.2.1, but let's include them anyway. + * + * Besides, if cf_cifstag is unset (0), then we still need it to be + * revalidated to know exactly what reparse point it is. + */ + switch (fattr->cf_cifstag) { + case IO_REPARSE_TAG_DFS: + case IO_REPARSE_TAG_DFSR: + case IO_REPARSE_TAG_SYMLINK: + case IO_REPARSE_TAG_NFS: + case 0: + return true; + } + return false; +} + static void cifs_fill_common_info(struct cifs_fattr *fattr, struct cifs_sb_info *cifs_sb) { @@ -158,7 +180,7 @@ cifs_fill_common_info(struct cifs_fattr *fattr, struct cifs_sb_info *cifs_sb) * is a symbolic link, DFS referral or a reparse point with a direct * access like junctions, deduplicated files, NFS symlinks. */ - if (fattr->cf_cifsattrs & ATTR_REPARSE) + if (reparse_file_needs_reval(fattr)) fattr->cf_flags |= CIFS_FATTR_NEED_REVAL; /* non-unix readdir doesn't provide nlink */ @@ -194,19 +216,37 @@ cifs_fill_common_info(struct cifs_fattr *fattr, struct cifs_sb_info *cifs_sb) } } +static void __dir_info_to_fattr(struct cifs_fattr *fattr, const void *info) +{ + const FILE_DIRECTORY_INFO *fi = info; + + memset(fattr, 0, sizeof(*fattr)); + fattr->cf_cifsattrs = le32_to_cpu(fi->ExtFileAttributes); + fattr->cf_eof = le64_to_cpu(fi->EndOfFile); + fattr->cf_bytes = le64_to_cpu(fi->AllocationSize); + fattr->cf_createtime = le64_to_cpu(fi->CreationTime); + fattr->cf_atime = cifs_NTtimeToUnix(fi->LastAccessTime); + fattr->cf_ctime = cifs_NTtimeToUnix(fi->ChangeTime); + fattr->cf_mtime = cifs_NTtimeToUnix(fi->LastWriteTime); +} + void cifs_dir_info_to_fattr(struct cifs_fattr *fattr, FILE_DIRECTORY_INFO *info, struct cifs_sb_info *cifs_sb) { - memset(fattr, 0, sizeof(*fattr)); - fattr->cf_cifsattrs = le32_to_cpu(info->ExtFileAttributes); - fattr->cf_eof = le64_to_cpu(info->EndOfFile); - fattr->cf_bytes = le64_to_cpu(info->AllocationSize); - fattr->cf_createtime = le64_to_cpu(info->CreationTime); - fattr->cf_atime = cifs_NTtimeToUnix(info->LastAccessTime); - fattr->cf_ctime = cifs_NTtimeToUnix(info->ChangeTime); - fattr->cf_mtime = cifs_NTtimeToUnix(info->LastWriteTime); + __dir_info_to_fattr(fattr, info); + cifs_fill_common_info(fattr, cifs_sb); +} +static void cifs_fulldir_info_to_fattr(struct cifs_fattr *fattr, + SEARCH_ID_FULL_DIR_INFO *info, + struct cifs_sb_info *cifs_sb) +{ + __dir_info_to_fattr(fattr, info); + + /* See MS-FSCC 2.4.18 FileIdFullDirectoryInformation */ + if (fattr->cf_cifsattrs & ATTR_REPARSE) + fattr->cf_cifstag = le32_to_cpu(info->EaSize); cifs_fill_common_info(fattr, cifs_sb); } @@ -755,6 +795,11 @@ static int cifs_filldir(char *find_entry, struct file *file, (FIND_FILE_STANDARD_INFO *)find_entry, cifs_sb); break; + case SMB_FIND_FILE_ID_FULL_DIR_INFO: + cifs_fulldir_info_to_fattr(&fattr, + (SEARCH_ID_FULL_DIR_INFO *)find_entry, + cifs_sb); + break; default: cifs_dir_info_to_fattr(&fattr, (FILE_DIRECTORY_INFO *)find_entry, diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index 8b0b512c5792..afe1f03aabe3 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -67,7 +67,7 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, goto out; - if (oparms->tcon->use_resilient) { + if (oparms->tcon->use_resilient) { /* default timeout is 0, servers pick default (120 seconds) */ nr_ioctl_req.Timeout = cpu_to_le32(oparms->tcon->handle_timeout); diff --git a/fs/drop_caches.c b/fs/drop_caches.c index d31b6c72b476..dc1a1d5d825b 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -35,11 +35,11 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused) spin_unlock(&inode->i_lock); spin_unlock(&sb->s_inode_list_lock); - cond_resched(); invalidate_mapping_pages(inode->i_mapping, 0, -1); iput(toput_inode); toput_inode = inode; + cond_resched(); spin_lock(&sb->s_inode_list_lock); } spin_unlock(&sb->s_inode_list_lock); diff --git a/fs/inode.c b/fs/inode.c index fef457a42882..96d62d97694e 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -676,6 +676,7 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty) struct inode *inode, *next; LIST_HEAD(dispose); +again: spin_lock(&sb->s_inode_list_lock); list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) { spin_lock(&inode->i_lock); @@ -698,6 +699,12 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty) inode_lru_list_del(inode); spin_unlock(&inode->i_lock); list_add(&inode->i_lru, &dispose); + if (need_resched()) { + spin_unlock(&sb->s_inode_list_lock); + cond_resched(); + dispose_list(&dispose); + goto again; + } } spin_unlock(&sb->s_inode_list_lock); diff --git a/fs/io-wq.c b/fs/io-wq.c index 11e80b7252a8..541c8a3e0bbb 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -92,7 +92,6 @@ struct io_wqe { struct io_wqe_acct acct[2]; struct hlist_nulls_head free_list; - struct hlist_nulls_head busy_list; struct list_head all_list; struct io_wq *wq; @@ -327,7 +326,6 @@ static void __io_worker_busy(struct io_wqe *wqe, struct io_worker *worker, if (worker->flags & IO_WORKER_F_FREE) { worker->flags &= ~IO_WORKER_F_FREE; hlist_nulls_del_init_rcu(&worker->nulls_node); - hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->busy_list); } /* @@ -365,7 +363,6 @@ static bool __io_worker_idle(struct io_wqe *wqe, struct io_worker *worker) { if (!(worker->flags & IO_WORKER_F_FREE)) { worker->flags |= IO_WORKER_F_FREE; - hlist_nulls_del_init_rcu(&worker->nulls_node); hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list); } @@ -432,6 +429,8 @@ next: if (signal_pending(current)) flush_signals(current); + cond_resched(); + spin_lock_irq(&worker->lock); worker->cur_work = work; spin_unlock_irq(&worker->lock); @@ -798,10 +797,6 @@ void io_wq_cancel_all(struct io_wq *wq) set_bit(IO_WQ_BIT_CANCEL, &wq->state); - /* - * Browse both lists, as there's a gap between handing work off - * to a worker and the worker putting itself on the busy_list - */ rcu_read_lock(); for_each_node(node) { struct io_wqe *wqe = wq->wqes[node]; @@ -1049,7 +1044,6 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data) spin_lock_init(&wqe->lock); INIT_WQ_LIST(&wqe->work_list); INIT_HLIST_NULLS_HEAD(&wqe->free_list, 0); - INIT_HLIST_NULLS_HEAD(&wqe->busy_list, 1); INIT_LIST_HEAD(&wqe->all_list); } diff --git a/fs/io_uring.c b/fs/io_uring.c index 6f084e3cf835..562e3a1a1bf9 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -330,6 +330,26 @@ struct io_timeout { struct file *file; u64 addr; int flags; + unsigned count; +}; + +struct io_rw { + /* NOTE: kiocb has the file as the first member, so don't do it here */ + struct kiocb kiocb; + u64 addr; + u64 len; +}; + +struct io_connect { + struct file *file; + struct sockaddr __user *addr; + int addr_len; +}; + +struct io_sr_msg { + struct file *file; + struct user_msghdr __user *msg; + int msg_flags; }; struct io_async_connect { @@ -351,7 +371,6 @@ struct io_async_rw { }; struct io_async_ctx { - struct io_uring_sqe sqe; union { struct io_async_rw rw; struct io_async_msghdr msg; @@ -369,15 +388,16 @@ struct io_async_ctx { struct io_kiocb { union { struct file *file; - struct kiocb rw; + struct io_rw rw; struct io_poll_iocb poll; struct io_accept accept; struct io_sync sync; struct io_cancel cancel; struct io_timeout timeout; + struct io_connect connect; + struct io_sr_msg sr_msg; }; - const struct io_uring_sqe *sqe; struct io_async_ctx *io; struct file *ring_file; int ring_fd; @@ -411,7 +431,6 @@ struct io_kiocb { #define REQ_F_INFLIGHT 16384 /* on inflight list */ #define REQ_F_COMP_LOCKED 32768 /* completion under lock */ #define REQ_F_HARDLINK 65536 /* doesn't sever on completion < 0 */ -#define REQ_F_PREPPED 131072 /* request already opcode prepared */ u64 user_data; u32 result; u32 sequence; @@ -609,33 +628,31 @@ static inline bool io_prep_async_work(struct io_kiocb *req, { bool do_hashed = false; - if (req->sqe) { - switch (req->opcode) { - case IORING_OP_WRITEV: - case IORING_OP_WRITE_FIXED: - /* only regular files should be hashed for writes */ - if (req->flags & REQ_F_ISREG) - do_hashed = true; - /* fall-through */ - case IORING_OP_READV: - case IORING_OP_READ_FIXED: - case IORING_OP_SENDMSG: - case IORING_OP_RECVMSG: - case IORING_OP_ACCEPT: - case IORING_OP_POLL_ADD: - case IORING_OP_CONNECT: - /* - * We know REQ_F_ISREG is not set on some of these - * opcodes, but this enables us to keep the check in - * just one place. - */ - if (!(req->flags & REQ_F_ISREG)) - req->work.flags |= IO_WQ_WORK_UNBOUND; - break; - } - if (io_req_needs_user(req)) - req->work.flags |= IO_WQ_WORK_NEEDS_USER; + switch (req->opcode) { + case IORING_OP_WRITEV: + case IORING_OP_WRITE_FIXED: + /* only regular files should be hashed for writes */ + if (req->flags & REQ_F_ISREG) + do_hashed = true; + /* fall-through */ + case IORING_OP_READV: + case IORING_OP_READ_FIXED: + case IORING_OP_SENDMSG: + case IORING_OP_RECVMSG: + case IORING_OP_ACCEPT: + case IORING_OP_POLL_ADD: + case IORING_OP_CONNECT: + /* + * We know REQ_F_ISREG is not set on some of these + * opcodes, but this enables us to keep the check in + * just one place. + */ + if (!(req->flags & REQ_F_ISREG)) + req->work.flags |= IO_WQ_WORK_UNBOUND; + break; } + if (io_req_needs_user(req)) + req->work.flags |= IO_WQ_WORK_NEEDS_USER; *link = io_prep_linked_timeout(req); return do_hashed; @@ -1180,7 +1197,7 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, ret = 0; list_for_each_entry_safe(req, tmp, &ctx->poll_list, list) { - struct kiocb *kiocb = &req->rw; + struct kiocb *kiocb = &req->rw.kiocb; /* * Move completed entries to our local list. If we find a @@ -1335,7 +1352,7 @@ static inline void req_set_fail_links(struct io_kiocb *req) static void io_complete_rw_common(struct kiocb *kiocb, long res) { - struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); + struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); if (kiocb->ki_flags & IOCB_WRITE) kiocb_end_write(req); @@ -1347,7 +1364,7 @@ static void io_complete_rw_common(struct kiocb *kiocb, long res) static void io_complete_rw(struct kiocb *kiocb, long res, long res2) { - struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); + struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); io_complete_rw_common(kiocb, res); io_put_req(req); @@ -1355,7 +1372,7 @@ static void io_complete_rw(struct kiocb *kiocb, long res, long res2) static struct io_kiocb *__io_complete_rw(struct kiocb *kiocb, long res) { - struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); + struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); struct io_kiocb *nxt = NULL; io_complete_rw_common(kiocb, res); @@ -1366,7 +1383,7 @@ static struct io_kiocb *__io_complete_rw(struct kiocb *kiocb, long res) static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) { - struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); + struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); if (kiocb->ki_flags & IOCB_WRITE) kiocb_end_write(req); @@ -1400,7 +1417,7 @@ static void io_iopoll_req_issued(struct io_kiocb *req) list_req = list_first_entry(&ctx->poll_list, struct io_kiocb, list); - if (list_req->rw.ki_filp != req->rw.ki_filp) + if (list_req->file != req->file) ctx->poll_multi_file = true; } @@ -1471,11 +1488,11 @@ static bool io_file_supports_async(struct file *file) return false; } -static int io_prep_rw(struct io_kiocb *req, bool force_nonblock) +static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, + bool force_nonblock) { - const struct io_uring_sqe *sqe = req->sqe; struct io_ring_ctx *ctx = req->ctx; - struct kiocb *kiocb = &req->rw; + struct kiocb *kiocb = &req->rw.kiocb; unsigned ioprio; int ret; @@ -1524,6 +1541,12 @@ static int io_prep_rw(struct io_kiocb *req, bool force_nonblock) return -EINVAL; kiocb->ki_complete = io_complete_rw; } + + req->rw.addr = READ_ONCE(sqe->addr); + req->rw.len = READ_ONCE(sqe->len); + /* we own ->private, reuse it for the buffer index */ + req->rw.kiocb.private = (void *) (unsigned long) + READ_ONCE(sqe->buf_index); return 0; } @@ -1557,11 +1580,11 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret, struct io_kiocb **nxt, io_rw_done(kiocb, ret); } -static ssize_t io_import_fixed(struct io_ring_ctx *ctx, int rw, - const struct io_uring_sqe *sqe, +static ssize_t io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter) { - size_t len = READ_ONCE(sqe->len); + struct io_ring_ctx *ctx = req->ctx; + size_t len = req->rw.len; struct io_mapped_ubuf *imu; unsigned index, buf_index; size_t offset; @@ -1571,13 +1594,13 @@ static ssize_t io_import_fixed(struct io_ring_ctx *ctx, int rw, if (unlikely(!ctx->user_bufs)) return -EFAULT; - buf_index = READ_ONCE(sqe->buf_index); + buf_index = (unsigned long) req->rw.kiocb.private; if (unlikely(buf_index >= ctx->nr_user_bufs)) return -EFAULT; index = array_index_nospec(buf_index, ctx->nr_user_bufs); imu = &ctx->user_bufs[index]; - buf_addr = READ_ONCE(sqe->addr); + buf_addr = req->rw.addr; /* overflow */ if (buf_addr + len < buf_addr) @@ -1634,25 +1657,20 @@ static ssize_t io_import_fixed(struct io_ring_ctx *ctx, int rw, static ssize_t io_import_iovec(int rw, struct io_kiocb *req, struct iovec **iovec, struct iov_iter *iter) { - const struct io_uring_sqe *sqe = req->sqe; - void __user *buf = u64_to_user_ptr(READ_ONCE(sqe->addr)); - size_t sqe_len = READ_ONCE(sqe->len); + void __user *buf = u64_to_user_ptr(req->rw.addr); + size_t sqe_len = req->rw.len; u8 opcode; - /* - * We're reading ->opcode for the second time, but the first read - * doesn't care whether it's _FIXED or not, so it doesn't matter - * whether ->opcode changes concurrently. The first read does care - * about whether it is a READ or a WRITE, so we don't trust this read - * for that purpose and instead let the caller pass in the read/write - * flag. - */ opcode = req->opcode; if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) { *iovec = NULL; - return io_import_fixed(req->ctx, rw, sqe, iter); + return io_import_fixed(req, rw, iter); } + /* buffer index only valid with fixed read/write */ + if (req->rw.kiocb.private) + return -EINVAL; + if (req->io) { struct io_async_rw *iorw = &req->io->rw; @@ -1750,13 +1768,7 @@ static void io_req_map_rw(struct io_kiocb *req, ssize_t io_size, static int io_alloc_async_ctx(struct io_kiocb *req) { req->io = kmalloc(sizeof(*req->io), GFP_KERNEL); - if (req->io) { - memcpy(&req->io->sqe, req->sqe, sizeof(req->io->sqe)); - req->sqe = &req->io->sqe; - return 0; - } - - return 1; + return req->io == NULL; } static void io_rw_async(struct io_wq_work **workptr) @@ -1782,46 +1794,52 @@ static int io_setup_async_rw(struct io_kiocb *req, ssize_t io_size, return 0; } -static int io_read_prep(struct io_kiocb *req, struct iovec **iovec, - struct iov_iter *iter, bool force_nonblock) +static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, + bool force_nonblock) { + struct io_async_ctx *io; + struct iov_iter iter; ssize_t ret; - ret = io_prep_rw(req, force_nonblock); + ret = io_prep_rw(req, sqe, force_nonblock); if (ret) return ret; if (unlikely(!(req->file->f_mode & FMODE_READ))) return -EBADF; - return io_import_iovec(READ, req, iovec, iter); + if (!req->io) + return 0; + + io = req->io; + io->rw.iov = io->rw.fast_iov; + req->io = NULL; + ret = io_import_iovec(READ, req, &io->rw.iov, &iter); + req->io = io; + if (ret < 0) + return ret; + + io_req_map_rw(req, ret, io->rw.iov, io->rw.fast_iov, &iter); + return 0; } static int io_read(struct io_kiocb *req, struct io_kiocb **nxt, bool force_nonblock) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; - struct kiocb *kiocb = &req->rw; + struct kiocb *kiocb = &req->rw.kiocb; struct iov_iter iter; - struct file *file; size_t iov_count; ssize_t io_size, ret; - if (!req->io) { - ret = io_read_prep(req, &iovec, &iter, force_nonblock); - if (ret < 0) - return ret; - } else { - ret = io_import_iovec(READ, req, &iovec, &iter); - if (ret < 0) - return ret; - } + ret = io_import_iovec(READ, req, &iovec, &iter); + if (ret < 0) + return ret; /* Ensure we clear previously set non-block flag */ if (!force_nonblock) - req->rw.ki_flags &= ~IOCB_NOWAIT; + req->rw.kiocb.ki_flags &= ~IOCB_NOWAIT; - file = req->file; io_size = ret; if (req->flags & REQ_F_LINK) req->result = io_size; @@ -1830,20 +1848,20 @@ static int io_read(struct io_kiocb *req, struct io_kiocb **nxt, * If the file doesn't support async, mark it as REQ_F_MUST_PUNT so * we know to async punt it even if it was opened O_NONBLOCK */ - if (force_nonblock && !io_file_supports_async(file)) { + if (force_nonblock && !io_file_supports_async(req->file)) { req->flags |= REQ_F_MUST_PUNT; goto copy_iov; } iov_count = iov_iter_count(&iter); - ret = rw_verify_area(READ, file, &kiocb->ki_pos, iov_count); + ret = rw_verify_area(READ, req->file, &kiocb->ki_pos, iov_count); if (!ret) { ssize_t ret2; - if (file->f_op->read_iter) - ret2 = call_read_iter(file, kiocb, &iter); + if (req->file->f_op->read_iter) + ret2 = call_read_iter(req->file, kiocb, &iter); else - ret2 = loop_rw_iter(READ, file, kiocb, &iter); + ret2 = loop_rw_iter(READ, req->file, kiocb, &iter); /* * In case of a short read, punt to async. This can happen @@ -1875,46 +1893,52 @@ out_free: return ret; } -static int io_write_prep(struct io_kiocb *req, struct iovec **iovec, - struct iov_iter *iter, bool force_nonblock) +static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, + bool force_nonblock) { + struct io_async_ctx *io; + struct iov_iter iter; ssize_t ret; - ret = io_prep_rw(req, force_nonblock); + ret = io_prep_rw(req, sqe, force_nonblock); if (ret) return ret; if (unlikely(!(req->file->f_mode & FMODE_WRITE))) return -EBADF; - return io_import_iovec(WRITE, req, iovec, iter); + if (!req->io) + return 0; + + io = req->io; + io->rw.iov = io->rw.fast_iov; + req->io = NULL; + ret = io_import_iovec(WRITE, req, &io->rw.iov, &iter); + req->io = io; + if (ret < 0) + return ret; + + io_req_map_rw(req, ret, io->rw.iov, io->rw.fast_iov, &iter); + return 0; } static int io_write(struct io_kiocb *req, struct io_kiocb **nxt, bool force_nonblock) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; - struct kiocb *kiocb = &req->rw; + struct kiocb *kiocb = &req->rw.kiocb; struct iov_iter iter; - struct file *file; size_t iov_count; ssize_t ret, io_size; - if (!req->io) { - ret = io_write_prep(req, &iovec, &iter, force_nonblock); - if (ret < 0) - return ret; - } else { - ret = io_import_iovec(WRITE, req, &iovec, &iter); - if (ret < 0) - return ret; - } + ret = io_import_iovec(WRITE, req, &iovec, &iter); + if (ret < 0) + return ret; /* Ensure we clear previously set non-block flag */ if (!force_nonblock) - req->rw.ki_flags &= ~IOCB_NOWAIT; + req->rw.kiocb.ki_flags &= ~IOCB_NOWAIT; - file = kiocb->ki_filp; io_size = ret; if (req->flags & REQ_F_LINK) req->result = io_size; @@ -1934,7 +1958,7 @@ static int io_write(struct io_kiocb *req, struct io_kiocb **nxt, goto copy_iov; iov_count = iov_iter_count(&iter); - ret = rw_verify_area(WRITE, file, &kiocb->ki_pos, iov_count); + ret = rw_verify_area(WRITE, req->file, &kiocb->ki_pos, iov_count); if (!ret) { ssize_t ret2; @@ -1946,17 +1970,17 @@ static int io_write(struct io_kiocb *req, struct io_kiocb **nxt, * we return to userspace. */ if (req->flags & REQ_F_ISREG) { - __sb_start_write(file_inode(file)->i_sb, + __sb_start_write(file_inode(req->file)->i_sb, SB_FREEZE_WRITE, true); - __sb_writers_release(file_inode(file)->i_sb, + __sb_writers_release(file_inode(req->file)->i_sb, SB_FREEZE_WRITE); } kiocb->ki_flags |= IOCB_WRITE; - if (file->f_op->write_iter) - ret2 = call_write_iter(file, kiocb, &iter); + if (req->file->f_op->write_iter) + ret2 = call_write_iter(req->file, kiocb, &iter); else - ret2 = loop_rw_iter(WRITE, file, kiocb, &iter); + ret2 = loop_rw_iter(WRITE, req->file, kiocb, &iter); if (!force_nonblock || ret2 != -EAGAIN) { kiocb_done(kiocb, ret2, nxt, req->in_async); } else { @@ -1989,13 +2013,10 @@ static int io_nop(struct io_kiocb *req) return 0; } -static int io_prep_fsync(struct io_kiocb *req) +static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - const struct io_uring_sqe *sqe = req->sqe; struct io_ring_ctx *ctx = req->ctx; - if (req->flags & REQ_F_PREPPED) - return 0; if (!req->file) return -EBADF; @@ -2010,7 +2031,6 @@ static int io_prep_fsync(struct io_kiocb *req) req->sync.off = READ_ONCE(sqe->off); req->sync.len = READ_ONCE(sqe->len); - req->flags |= REQ_F_PREPPED; return 0; } @@ -2036,7 +2056,7 @@ static void io_fsync_finish(struct io_wq_work **workptr) if (io_req_cancelled(req)) return; - ret = vfs_fsync_range(req->rw.ki_filp, req->sync.off, + ret = vfs_fsync_range(req->file, req->sync.off, end > 0 ? end : LLONG_MAX, req->sync.flags & IORING_FSYNC_DATASYNC); if (ret < 0) @@ -2051,11 +2071,6 @@ static int io_fsync(struct io_kiocb *req, struct io_kiocb **nxt, bool force_nonblock) { struct io_wq_work *work, *old_work; - int ret; - - ret = io_prep_fsync(req); - if (ret) - return ret; /* fsync always requires a blocking context */ if (force_nonblock) { @@ -2071,13 +2086,10 @@ static int io_fsync(struct io_kiocb *req, struct io_kiocb **nxt, return 0; } -static int io_prep_sfr(struct io_kiocb *req) +static int io_prep_sfr(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - const struct io_uring_sqe *sqe = req->sqe; struct io_ring_ctx *ctx = req->ctx; - if (req->flags & REQ_F_PREPPED) - return 0; if (!req->file) return -EBADF; @@ -2089,7 +2101,6 @@ static int io_prep_sfr(struct io_kiocb *req) req->sync.off = READ_ONCE(sqe->off); req->sync.len = READ_ONCE(sqe->len); req->sync.flags = READ_ONCE(sqe->sync_range_flags); - req->flags |= REQ_F_PREPPED; return 0; } @@ -2102,7 +2113,7 @@ static void io_sync_file_range_finish(struct io_wq_work **workptr) if (io_req_cancelled(req)) return; - ret = sync_file_range(req->rw.ki_filp, req->sync.off, req->sync.len, + ret = sync_file_range(req->file, req->sync.off, req->sync.len, req->sync.flags); if (ret < 0) req_set_fail_links(req); @@ -2116,11 +2127,6 @@ static int io_sync_file_range(struct io_kiocb *req, struct io_kiocb **nxt, bool force_nonblock) { struct io_wq_work *work, *old_work; - int ret; - - ret = io_prep_sfr(req); - if (ret) - return ret; /* sync_file_range always requires a blocking context */ if (force_nonblock) { @@ -2149,19 +2155,23 @@ static void io_sendrecv_async(struct io_wq_work **workptr) } #endif -static int io_sendmsg_prep(struct io_kiocb *req, struct io_async_ctx *io) +static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { #if defined(CONFIG_NET) - const struct io_uring_sqe *sqe = req->sqe; - struct user_msghdr __user *msg; - unsigned flags; + struct io_sr_msg *sr = &req->sr_msg; + struct io_async_ctx *io = req->io; + + sr->msg_flags = READ_ONCE(sqe->msg_flags); + sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr)); + + if (!io) + return 0; - flags = READ_ONCE(sqe->msg_flags); - msg = (struct user_msghdr __user *)(unsigned long) READ_ONCE(sqe->addr); io->msg.iov = io->msg.fast_iov; - return sendmsg_copy_msghdr(&io->msg.msg, msg, flags, &io->msg.iov); + return sendmsg_copy_msghdr(&io->msg.msg, sr->msg, sr->msg_flags, + &io->msg.iov); #else - return 0; + return -EOPNOTSUPP; #endif } @@ -2169,7 +2179,6 @@ static int io_sendmsg(struct io_kiocb *req, struct io_kiocb **nxt, bool force_nonblock) { #if defined(CONFIG_NET) - const struct io_uring_sqe *sqe = req->sqe; struct io_async_msghdr *kmsg = NULL; struct socket *sock; int ret; @@ -2183,12 +2192,6 @@ static int io_sendmsg(struct io_kiocb *req, struct io_kiocb **nxt, struct sockaddr_storage addr; unsigned flags; - flags = READ_ONCE(sqe->msg_flags); - if (flags & MSG_DONTWAIT) - req->flags |= REQ_F_NOWAIT; - else if (force_nonblock) - flags |= MSG_DONTWAIT; - if (req->io) { kmsg = &req->io->msg; kmsg->msg.msg_name = &addr; @@ -2197,13 +2200,24 @@ static int io_sendmsg(struct io_kiocb *req, struct io_kiocb **nxt, kmsg->iov = kmsg->fast_iov; kmsg->msg.msg_iter.iov = kmsg->iov; } else { + struct io_sr_msg *sr = &req->sr_msg; + kmsg = &io.msg; kmsg->msg.msg_name = &addr; - ret = io_sendmsg_prep(req, &io); + + io.msg.iov = io.msg.fast_iov; + ret = sendmsg_copy_msghdr(&io.msg.msg, sr->msg, + sr->msg_flags, &io.msg.iov); if (ret) - goto out; + return ret; } + flags = req->sr_msg.msg_flags; + if (flags & MSG_DONTWAIT) + req->flags |= REQ_F_NOWAIT; + else if (force_nonblock) + flags |= MSG_DONTWAIT; + ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags); if (force_nonblock && ret == -EAGAIN) { if (req->io) @@ -2218,7 +2232,6 @@ static int io_sendmsg(struct io_kiocb *req, struct io_kiocb **nxt, ret = -EINTR; } -out: if (!io_wq_current_is_worker() && kmsg && kmsg->iov != kmsg->fast_iov) kfree(kmsg->iov); io_cqring_add_event(req, ret); @@ -2231,20 +2244,24 @@ out: #endif } -static int io_recvmsg_prep(struct io_kiocb *req, struct io_async_ctx *io) +static int io_recvmsg_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) { #if defined(CONFIG_NET) - const struct io_uring_sqe *sqe = req->sqe; - struct user_msghdr __user *msg; - unsigned flags; + struct io_sr_msg *sr = &req->sr_msg; + struct io_async_ctx *io = req->io; + + sr->msg_flags = READ_ONCE(sqe->msg_flags); + sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr)); + + if (!io) + return 0; - flags = READ_ONCE(sqe->msg_flags); - msg = (struct user_msghdr __user *)(unsigned long) READ_ONCE(sqe->addr); io->msg.iov = io->msg.fast_iov; - return recvmsg_copy_msghdr(&io->msg.msg, msg, flags, &io->msg.uaddr, - &io->msg.iov); + return recvmsg_copy_msghdr(&io->msg.msg, sr->msg, sr->msg_flags, + &io->msg.uaddr, &io->msg.iov); #else - return 0; + return -EOPNOTSUPP; #endif } @@ -2252,7 +2269,6 @@ static int io_recvmsg(struct io_kiocb *req, struct io_kiocb **nxt, bool force_nonblock) { #if defined(CONFIG_NET) - const struct io_uring_sqe *sqe = req->sqe; struct io_async_msghdr *kmsg = NULL; struct socket *sock; int ret; @@ -2262,19 +2278,10 @@ static int io_recvmsg(struct io_kiocb *req, struct io_kiocb **nxt, sock = sock_from_file(req->file, &ret); if (sock) { - struct user_msghdr __user *msg; struct io_async_ctx io; struct sockaddr_storage addr; unsigned flags; - flags = READ_ONCE(sqe->msg_flags); - if (flags & MSG_DONTWAIT) - req->flags |= REQ_F_NOWAIT; - else if (force_nonblock) - flags |= MSG_DONTWAIT; - - msg = (struct user_msghdr __user *) (unsigned long) - READ_ONCE(sqe->addr); if (req->io) { kmsg = &req->io->msg; kmsg->msg.msg_name = &addr; @@ -2283,14 +2290,27 @@ static int io_recvmsg(struct io_kiocb *req, struct io_kiocb **nxt, kmsg->iov = kmsg->fast_iov; kmsg->msg.msg_iter.iov = kmsg->iov; } else { + struct io_sr_msg *sr = &req->sr_msg; + kmsg = &io.msg; kmsg->msg.msg_name = &addr; - ret = io_recvmsg_prep(req, &io); + + io.msg.iov = io.msg.fast_iov; + ret = recvmsg_copy_msghdr(&io.msg.msg, sr->msg, + sr->msg_flags, &io.msg.uaddr, + &io.msg.iov); if (ret) - goto out; + return ret; } - ret = __sys_recvmsg_sock(sock, &kmsg->msg, msg, kmsg->uaddr, flags); + flags = req->sr_msg.msg_flags; + if (flags & MSG_DONTWAIT) + req->flags |= REQ_F_NOWAIT; + else if (force_nonblock) + flags |= MSG_DONTWAIT; + + ret = __sys_recvmsg_sock(sock, &kmsg->msg, req->sr_msg.msg, + kmsg->uaddr, flags); if (force_nonblock && ret == -EAGAIN) { if (req->io) return -EAGAIN; @@ -2304,7 +2324,6 @@ static int io_recvmsg(struct io_kiocb *req, struct io_kiocb **nxt, ret = -EINTR; } -out: if (!io_wq_current_is_worker() && kmsg && kmsg->iov != kmsg->fast_iov) kfree(kmsg->iov); io_cqring_add_event(req, ret); @@ -2317,25 +2336,19 @@ out: #endif } -static int io_accept_prep(struct io_kiocb *req) +static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { #if defined(CONFIG_NET) - const struct io_uring_sqe *sqe = req->sqe; struct io_accept *accept = &req->accept; - if (req->flags & REQ_F_PREPPED) - return 0; - if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) return -EINVAL; if (sqe->ioprio || sqe->len || sqe->buf_index) return -EINVAL; - accept->addr = (struct sockaddr __user *) - (unsigned long) READ_ONCE(sqe->addr); - accept->addr_len = (int __user *) (unsigned long) READ_ONCE(sqe->addr2); + accept->addr = u64_to_user_ptr(READ_ONCE(sqe->addr)); + accept->addr_len = u64_to_user_ptr(READ_ONCE(sqe->addr2)); accept->flags = READ_ONCE(sqe->accept_flags); - req->flags |= REQ_F_PREPPED; return 0; #else return -EOPNOTSUPP; @@ -2383,10 +2396,6 @@ static int io_accept(struct io_kiocb *req, struct io_kiocb **nxt, #if defined(CONFIG_NET) int ret; - ret = io_accept_prep(req); - if (ret) - return ret; - ret = __io_accept(req, nxt, force_nonblock); if (ret == -EAGAIN && force_nonblock) { req->work.func = io_accept_finish; @@ -2400,18 +2409,27 @@ static int io_accept(struct io_kiocb *req, struct io_kiocb **nxt, #endif } -static int io_connect_prep(struct io_kiocb *req, struct io_async_ctx *io) +static int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { #if defined(CONFIG_NET) - const struct io_uring_sqe *sqe = req->sqe; - struct sockaddr __user *addr; - int addr_len; + struct io_connect *conn = &req->connect; + struct io_async_ctx *io = req->io; + + if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) + return -EINVAL; + if (sqe->ioprio || sqe->len || sqe->buf_index || sqe->rw_flags) + return -EINVAL; - addr = (struct sockaddr __user *) (unsigned long) READ_ONCE(sqe->addr); - addr_len = READ_ONCE(sqe->addr2); - return move_addr_to_kernel(addr, addr_len, &io->connect.address); + conn->addr = u64_to_user_ptr(READ_ONCE(sqe->addr)); + conn->addr_len = READ_ONCE(sqe->addr2); + + if (!io) + return 0; + + return move_addr_to_kernel(conn->addr, conn->addr_len, + &io->connect.address); #else - return 0; + return -EOPNOTSUPP; #endif } @@ -2419,30 +2437,25 @@ static int io_connect(struct io_kiocb *req, struct io_kiocb **nxt, bool force_nonblock) { #if defined(CONFIG_NET) - const struct io_uring_sqe *sqe = req->sqe; struct io_async_ctx __io, *io; unsigned file_flags; - int addr_len, ret; - - if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) - return -EINVAL; - if (sqe->ioprio || sqe->len || sqe->buf_index || sqe->rw_flags) - return -EINVAL; - - addr_len = READ_ONCE(sqe->addr2); - file_flags = force_nonblock ? O_NONBLOCK : 0; + int ret; if (req->io) { io = req->io; } else { - ret = io_connect_prep(req, &__io); + ret = move_addr_to_kernel(req->connect.addr, + req->connect.addr_len, + &__io.connect.address); if (ret) goto out; io = &__io; } - ret = __sys_connect_file(req->file, &io->connect.address, addr_len, - file_flags); + file_flags = force_nonblock ? O_NONBLOCK : 0; + + ret = __sys_connect_file(req->file, &io->connect.address, + req->connect.addr_len, file_flags); if ((ret == -EAGAIN || ret == -EINPROGRESS) && force_nonblock) { if (req->io) return -EAGAIN; @@ -2513,12 +2526,9 @@ static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr) return -ENOENT; } -static int io_poll_remove_prep(struct io_kiocb *req) +static int io_poll_remove_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) { - const struct io_uring_sqe *sqe = req->sqe; - - if (req->flags & REQ_F_PREPPED) - return 0; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->ioprio || sqe->off || sqe->len || sqe->buf_index || @@ -2526,7 +2536,6 @@ static int io_poll_remove_prep(struct io_kiocb *req) return -EINVAL; req->poll.addr = READ_ONCE(sqe->addr); - req->flags |= REQ_F_PREPPED; return 0; } @@ -2540,10 +2549,6 @@ static int io_poll_remove(struct io_kiocb *req) u64 addr; int ret; - ret = io_poll_remove_prep(req); - if (ret) - return ret; - addr = req->poll.addr; spin_lock_irq(&ctx->completion_lock); ret = io_poll_cancel(ctx, addr); @@ -2681,14 +2686,11 @@ static void io_poll_req_insert(struct io_kiocb *req) hlist_add_head(&req->hash_node, list); } -static int io_poll_add_prep(struct io_kiocb *req) +static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - const struct io_uring_sqe *sqe = req->sqe; struct io_poll_iocb *poll = &req->poll; u16 events; - if (req->flags & REQ_F_PREPPED) - return 0; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->addr || sqe->ioprio || sqe->off || sqe->len || sqe->buf_index) @@ -2696,7 +2698,6 @@ static int io_poll_add_prep(struct io_kiocb *req) if (!poll->file) return -EBADF; - req->flags |= REQ_F_PREPPED; events = READ_ONCE(sqe->poll_events); poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP; return 0; @@ -2709,11 +2710,6 @@ static int io_poll_add(struct io_kiocb *req, struct io_kiocb **nxt) struct io_poll_table ipt; bool cancel = false; __poll_t mask; - int ret; - - ret = io_poll_add_prep(req); - if (ret) - return ret; INIT_IO_WORK(&req->work, io_poll_complete_work); INIT_HLIST_NODE(&req->hash_node); @@ -2832,12 +2828,9 @@ static int io_timeout_cancel(struct io_ring_ctx *ctx, __u64 user_data) return 0; } -static int io_timeout_remove_prep(struct io_kiocb *req) +static int io_timeout_remove_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) { - const struct io_uring_sqe *sqe = req->sqe; - - if (req->flags & REQ_F_PREPPED) - return 0; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->flags || sqe->ioprio || sqe->buf_index || sqe->len) @@ -2848,7 +2841,6 @@ static int io_timeout_remove_prep(struct io_kiocb *req) if (req->timeout.flags) return -EINVAL; - req->flags |= REQ_F_PREPPED; return 0; } @@ -2860,10 +2852,6 @@ static int io_timeout_remove(struct io_kiocb *req) struct io_ring_ctx *ctx = req->ctx; int ret; - ret = io_timeout_remove_prep(req); - if (ret) - return ret; - spin_lock_irq(&ctx->completion_lock); ret = io_timeout_cancel(ctx, req->timeout.addr); @@ -2877,10 +2865,9 @@ static int io_timeout_remove(struct io_kiocb *req) return 0; } -static int io_timeout_prep(struct io_kiocb *req, struct io_async_ctx *io, +static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, bool is_timeout_link) { - const struct io_uring_sqe *sqe = req->sqe; struct io_timeout_data *data; unsigned flags; @@ -2894,7 +2881,12 @@ static int io_timeout_prep(struct io_kiocb *req, struct io_async_ctx *io, if (flags & ~IORING_TIMEOUT_ABS) return -EINVAL; - data = &io->timeout; + req->timeout.count = READ_ONCE(sqe->off); + + if (!req->io && io_alloc_async_ctx(req)) + return -ENOMEM; + + data = &req->io->timeout; data->req = req; req->flags |= REQ_F_TIMEOUT; @@ -2912,21 +2904,12 @@ static int io_timeout_prep(struct io_kiocb *req, struct io_async_ctx *io, static int io_timeout(struct io_kiocb *req) { - const struct io_uring_sqe *sqe = req->sqe; unsigned count; struct io_ring_ctx *ctx = req->ctx; struct io_timeout_data *data; struct list_head *entry; unsigned span = 0; - int ret; - if (!req->io) { - if (io_alloc_async_ctx(req)) - return -ENOMEM; - ret = io_timeout_prep(req, req->io, false); - if (ret) - return ret; - } data = &req->io->timeout; /* @@ -2934,7 +2917,7 @@ static int io_timeout(struct io_kiocb *req) * timeout event to be satisfied. If it isn't set, then this is * a pure timeout request, sequence isn't used. */ - count = READ_ONCE(sqe->off); + count = req->timeout.count; if (!count) { req->flags |= REQ_F_TIMEOUT_NOSEQ; spin_lock_irq(&ctx->completion_lock); @@ -3052,19 +3035,15 @@ done: io_put_req_find_next(req, nxt); } -static int io_async_cancel_prep(struct io_kiocb *req) +static int io_async_cancel_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) { - const struct io_uring_sqe *sqe = req->sqe; - - if (req->flags & REQ_F_PREPPED) - return 0; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->flags || sqe->ioprio || sqe->off || sqe->len || sqe->cancel_flags) return -EINVAL; - req->flags |= REQ_F_PREPPED; req->cancel.addr = READ_ONCE(sqe->addr); return 0; } @@ -3072,21 +3051,14 @@ static int io_async_cancel_prep(struct io_kiocb *req) static int io_async_cancel(struct io_kiocb *req, struct io_kiocb **nxt) { struct io_ring_ctx *ctx = req->ctx; - int ret; - - ret = io_async_cancel_prep(req); - if (ret) - return ret; io_async_find_and_cancel(ctx, req, req->cancel.addr, nxt, 0); return 0; } -static int io_req_defer_prep(struct io_kiocb *req) +static int io_req_defer_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) { - struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; - struct io_async_ctx *io = req->io; - struct iov_iter iter; ssize_t ret = 0; switch (req->opcode) { @@ -3094,61 +3066,47 @@ static int io_req_defer_prep(struct io_kiocb *req) break; case IORING_OP_READV: case IORING_OP_READ_FIXED: - /* ensure prep does right import */ - req->io = NULL; - ret = io_read_prep(req, &iovec, &iter, true); - req->io = io; - if (ret < 0) - break; - io_req_map_rw(req, ret, iovec, inline_vecs, &iter); - ret = 0; + ret = io_read_prep(req, sqe, true); break; case IORING_OP_WRITEV: case IORING_OP_WRITE_FIXED: - /* ensure prep does right import */ - req->io = NULL; - ret = io_write_prep(req, &iovec, &iter, true); - req->io = io; - if (ret < 0) - break; - io_req_map_rw(req, ret, iovec, inline_vecs, &iter); - ret = 0; + ret = io_write_prep(req, sqe, true); break; case IORING_OP_POLL_ADD: - ret = io_poll_add_prep(req); + ret = io_poll_add_prep(req, sqe); break; case IORING_OP_POLL_REMOVE: - ret = io_poll_remove_prep(req); + ret = io_poll_remove_prep(req, sqe); break; case IORING_OP_FSYNC: - ret = io_prep_fsync(req); + ret = io_prep_fsync(req, sqe); break; case IORING_OP_SYNC_FILE_RANGE: - ret = io_prep_sfr(req); + ret = io_prep_sfr(req, sqe); break; case IORING_OP_SENDMSG: - ret = io_sendmsg_prep(req, io); + ret = io_sendmsg_prep(req, sqe); break; case IORING_OP_RECVMSG: - ret = io_recvmsg_prep(req, io); + ret = io_recvmsg_prep(req, sqe); break; case IORING_OP_CONNECT: - ret = io_connect_prep(req, io); + ret = io_connect_prep(req, sqe); break; case IORING_OP_TIMEOUT: - ret = io_timeout_prep(req, io, false); + ret = io_timeout_prep(req, sqe, false); break; case IORING_OP_TIMEOUT_REMOVE: - ret = io_timeout_remove_prep(req); + ret = io_timeout_remove_prep(req, sqe); break; case IORING_OP_ASYNC_CANCEL: - ret = io_async_cancel_prep(req); + ret = io_async_cancel_prep(req, sqe); break; case IORING_OP_LINK_TIMEOUT: - ret = io_timeout_prep(req, io, true); + ret = io_timeout_prep(req, sqe, true); break; case IORING_OP_ACCEPT: - ret = io_accept_prep(req); + ret = io_accept_prep(req, sqe); break; default: printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n", @@ -3160,7 +3118,7 @@ static int io_req_defer_prep(struct io_kiocb *req) return ret; } -static int io_req_defer(struct io_kiocb *req) +static int io_req_defer(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_ring_ctx *ctx = req->ctx; int ret; @@ -3169,10 +3127,10 @@ static int io_req_defer(struct io_kiocb *req) if (!req_need_defer(req) && list_empty(&ctx->defer_list)) return 0; - if (io_alloc_async_ctx(req)) + if (!req->io && io_alloc_async_ctx(req)) return -EAGAIN; - ret = io_req_defer_prep(req); + ret = io_req_defer_prep(req, sqe); if (ret < 0) return ret; @@ -3188,9 +3146,8 @@ static int io_req_defer(struct io_kiocb *req) return -EIOCBQUEUED; } -__attribute__((nonnull)) -static int io_issue_sqe(struct io_kiocb *req, struct io_kiocb **nxt, - bool force_nonblock) +static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, + struct io_kiocb **nxt, bool force_nonblock) { struct io_ring_ctx *ctx = req->ctx; int ret; @@ -3200,52 +3157,109 @@ static int io_issue_sqe(struct io_kiocb *req, struct io_kiocb **nxt, ret = io_nop(req); break; case IORING_OP_READV: - if (unlikely(req->sqe->buf_index)) - return -EINVAL; - ret = io_read(req, nxt, force_nonblock); - break; - case IORING_OP_WRITEV: - if (unlikely(req->sqe->buf_index)) - return -EINVAL; - ret = io_write(req, nxt, force_nonblock); - break; case IORING_OP_READ_FIXED: + if (sqe) { + ret = io_read_prep(req, sqe, force_nonblock); + if (ret < 0) + break; + } ret = io_read(req, nxt, force_nonblock); break; + case IORING_OP_WRITEV: case IORING_OP_WRITE_FIXED: + if (sqe) { + ret = io_write_prep(req, sqe, force_nonblock); + if (ret < 0) + break; + } ret = io_write(req, nxt, force_nonblock); break; case IORING_OP_FSYNC: + if (sqe) { + ret = io_prep_fsync(req, sqe); + if (ret < 0) + break; + } ret = io_fsync(req, nxt, force_nonblock); break; case IORING_OP_POLL_ADD: + if (sqe) { + ret = io_poll_add_prep(req, sqe); + if (ret) + break; + } ret = io_poll_add(req, nxt); break; case IORING_OP_POLL_REMOVE: + if (sqe) { + ret = io_poll_remove_prep(req, sqe); + if (ret < 0) + break; + } ret = io_poll_remove(req); break; case IORING_OP_SYNC_FILE_RANGE: + if (sqe) { + ret = io_prep_sfr(req, sqe); + if (ret < 0) + break; + } ret = io_sync_file_range(req, nxt, force_nonblock); break; case IORING_OP_SENDMSG: + if (sqe) { + ret = io_sendmsg_prep(req, sqe); + if (ret < 0) + break; + } ret = io_sendmsg(req, nxt, force_nonblock); break; case IORING_OP_RECVMSG: + if (sqe) { + ret = io_recvmsg_prep(req, sqe); + if (ret) + break; + } ret = io_recvmsg(req, nxt, force_nonblock); break; case IORING_OP_TIMEOUT: + if (sqe) { + ret = io_timeout_prep(req, sqe, false); + if (ret) + break; + } ret = io_timeout(req); break; case IORING_OP_TIMEOUT_REMOVE: + if (sqe) { + ret = io_timeout_remove_prep(req, sqe); + if (ret) + break; + } ret = io_timeout_remove(req); break; case IORING_OP_ACCEPT: + if (sqe) { + ret = io_accept_prep(req, sqe); + if (ret) + break; + } ret = io_accept(req, nxt, force_nonblock); break; case IORING_OP_CONNECT: + if (sqe) { + ret = io_connect_prep(req, sqe); + if (ret) + break; + } ret = io_connect(req, nxt, force_nonblock); break; case IORING_OP_ASYNC_CANCEL: + if (sqe) { + ret = io_async_cancel_prep(req, sqe); + if (ret) + break; + } ret = io_async_cancel(req, nxt); break; default: @@ -3289,7 +3303,7 @@ static void io_wq_submit_work(struct io_wq_work **workptr) req->has_user = (work->flags & IO_WQ_WORK_HAS_MM) != 0; req->in_async = true; do { - ret = io_issue_sqe(req, &nxt, false); + ret = io_issue_sqe(req, NULL, &nxt, false); /* * We can get EAGAIN for polled IO even though we're * forcing a sync submission from here, since we can't @@ -3355,14 +3369,15 @@ static inline struct file *io_file_from_index(struct io_ring_ctx *ctx, return table->files[index & IORING_FILE_TABLE_MASK]; } -static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req) +static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req, + const struct io_uring_sqe *sqe) { struct io_ring_ctx *ctx = req->ctx; unsigned flags; int fd, ret; - flags = READ_ONCE(req->sqe->flags); - fd = READ_ONCE(req->sqe->fd); + flags = READ_ONCE(sqe->flags); + fd = READ_ONCE(sqe->fd); if (flags & IOSQE_IO_DRAIN) req->flags |= REQ_F_IO_DRAIN; @@ -3494,7 +3509,7 @@ static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req) return nxt; } -static void __io_queue_sqe(struct io_kiocb *req) +static void __io_queue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_kiocb *linked_timeout; struct io_kiocb *nxt = NULL; @@ -3503,7 +3518,7 @@ static void __io_queue_sqe(struct io_kiocb *req) again: linked_timeout = io_prep_linked_timeout(req); - ret = io_issue_sqe(req, &nxt, true); + ret = io_issue_sqe(req, sqe, &nxt, true); /* * We async punt it if the file wasn't marked NOWAIT, or if the file @@ -3550,7 +3565,7 @@ done_req: } } -static void io_queue_sqe(struct io_kiocb *req) +static void io_queue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe) { int ret; @@ -3560,7 +3575,7 @@ static void io_queue_sqe(struct io_kiocb *req) } req->ctx->drain_next = (req->flags & REQ_F_DRAIN_LINK); - ret = io_req_defer(req); + ret = io_req_defer(req, sqe); if (ret) { if (ret != -EIOCBQUEUED) { io_cqring_add_event(req, ret); @@ -3568,7 +3583,7 @@ static void io_queue_sqe(struct io_kiocb *req) io_double_put_req(req); } } else - __io_queue_sqe(req); + __io_queue_sqe(req, sqe); } static inline void io_queue_link_head(struct io_kiocb *req) @@ -3577,25 +3592,25 @@ static inline void io_queue_link_head(struct io_kiocb *req) io_cqring_add_event(req, -ECANCELED); io_double_put_req(req); } else - io_queue_sqe(req); + io_queue_sqe(req, NULL); } #define SQE_VALID_FLAGS (IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK| \ IOSQE_IO_HARDLINK) -static bool io_submit_sqe(struct io_kiocb *req, struct io_submit_state *state, - struct io_kiocb **link) +static bool io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, + struct io_submit_state *state, struct io_kiocb **link) { struct io_ring_ctx *ctx = req->ctx; int ret; /* enforce forwards compatibility on users */ - if (unlikely(req->sqe->flags & ~SQE_VALID_FLAGS)) { + if (unlikely(sqe->flags & ~SQE_VALID_FLAGS)) { ret = -EINVAL; goto err_req; } - ret = io_req_set_file(state, req); + ret = io_req_set_file(state, req, sqe); if (unlikely(ret)) { err_req: io_cqring_add_event(req, ret); @@ -3613,10 +3628,10 @@ err_req: if (*link) { struct io_kiocb *prev = *link; - if (req->sqe->flags & IOSQE_IO_DRAIN) + if (sqe->flags & IOSQE_IO_DRAIN) (*link)->flags |= REQ_F_DRAIN_LINK | REQ_F_IO_DRAIN; - if (req->sqe->flags & IOSQE_IO_HARDLINK) + if (sqe->flags & IOSQE_IO_HARDLINK) req->flags |= REQ_F_HARDLINK; if (io_alloc_async_ctx(req)) { @@ -3624,7 +3639,7 @@ err_req: goto err_req; } - ret = io_req_defer_prep(req); + ret = io_req_defer_prep(req, sqe); if (ret) { /* fail even hard links since we don't submit */ prev->flags |= REQ_F_FAIL_LINK; @@ -3632,15 +3647,18 @@ err_req: } trace_io_uring_link(ctx, req, prev); list_add_tail(&req->link_list, &prev->link_list); - } else if (req->sqe->flags & (IOSQE_IO_LINK|IOSQE_IO_HARDLINK)) { + } else if (sqe->flags & (IOSQE_IO_LINK|IOSQE_IO_HARDLINK)) { req->flags |= REQ_F_LINK; - if (req->sqe->flags & IOSQE_IO_HARDLINK) + if (sqe->flags & IOSQE_IO_HARDLINK) req->flags |= REQ_F_HARDLINK; INIT_LIST_HEAD(&req->link_list); + ret = io_req_defer_prep(req, sqe); + if (ret) + req->flags |= REQ_F_FAIL_LINK; *link = req; } else { - io_queue_sqe(req); + io_queue_sqe(req, sqe); } return true; @@ -3685,14 +3703,15 @@ static void io_commit_sqring(struct io_ring_ctx *ctx) } /* - * Fetch an sqe, if one is available. Note that req->sqe will point to memory + * Fetch an sqe, if one is available. Note that sqe_ptr will point to memory * that is mapped by userspace. This means that care needs to be taken to * ensure that reads are stable, as we cannot rely on userspace always * being a good citizen. If members of the sqe are validated and then later * used, it's important that those reads are done through READ_ONCE() to * prevent a re-load down the line. */ -static bool io_get_sqring(struct io_ring_ctx *ctx, struct io_kiocb *req) +static bool io_get_sqring(struct io_ring_ctx *ctx, struct io_kiocb *req, + const struct io_uring_sqe **sqe_ptr) { struct io_rings *rings = ctx->rings; u32 *sq_array = ctx->sq_array; @@ -3719,9 +3738,9 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct io_kiocb *req) * link list. */ req->sequence = ctx->cached_sq_head; - req->sqe = &ctx->sq_sqes[head]; - req->opcode = READ_ONCE(req->sqe->opcode); - req->user_data = READ_ONCE(req->sqe->user_data); + *sqe_ptr = &ctx->sq_sqes[head]; + req->opcode = READ_ONCE((*sqe_ptr)->opcode); + req->user_data = READ_ONCE((*sqe_ptr)->user_data); ctx->cached_sq_head++; return true; } @@ -3753,6 +3772,7 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, } for (i = 0; i < nr; i++) { + const struct io_uring_sqe *sqe; struct io_kiocb *req; unsigned int sqe_flags; @@ -3762,7 +3782,7 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, submitted = -EAGAIN; break; } - if (!io_get_sqring(ctx, req)) { + if (!io_get_sqring(ctx, req, &sqe)) { __io_free_req(req); break; } @@ -3776,7 +3796,7 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, } submitted++; - sqe_flags = req->sqe->flags; + sqe_flags = sqe->flags; req->ring_file = ring_file; req->ring_fd = ring_fd; @@ -3784,7 +3804,7 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, req->in_async = async; req->needs_fixed_file = async; trace_io_uring_submit_sqe(ctx, req->user_data, true, async); - if (!io_submit_sqe(req, statep, &link)) + if (!io_submit_sqe(req, sqe, statep, &link)) break; /* * If previous wasn't linked and we have a linked command, @@ -4702,7 +4722,7 @@ static int io_copy_iov(struct io_ring_ctx *ctx, struct iovec *dst, if (copy_from_user(&ciov, &ciovs[index], sizeof(ciov))) return -EFAULT; - dst->iov_base = (void __user *) (unsigned long) ciov.iov_base; + dst->iov_base = u64_to_user_ptr((u64)ciov.iov_base); dst->iov_len = ciov.iov_len; return 0; } diff --git a/fs/locks.c b/fs/locks.c index 6970f55daf54..44b6da032842 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2853,7 +2853,7 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl, } if (inode) { /* userspace relies on this representation of dev_t */ - seq_printf(f, "%d %02x:%02x:%ld ", fl_pid, + seq_printf(f, "%d %02x:%02x:%lu ", fl_pid, MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino); } else { diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 3e77b728a22b..46f225580009 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -57,6 +57,9 @@ static void fsnotify_unmount_inodes(struct super_block *sb) * doing an __iget/iput with SB_ACTIVE clear would actually * evict all inodes with zero i_count from icache which is * unnecessarily violent and may in fact be illegal to do. + * However, we should have been called /after/ evict_inodes + * removed all zero refcount inodes, in any case. Test to + * be sure. */ if (!atomic_read(&inode->i_count)) { spin_unlock(&inode->i_lock); @@ -77,6 +80,7 @@ static void fsnotify_unmount_inodes(struct super_block *sb) iput_inode = inode; + cond_resched(); spin_lock(&sb->s_inode_list_lock); } spin_unlock(&sb->s_inode_list_lock); diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index b0688c02dc90..b6a4f692d345 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -984,6 +984,7 @@ static int add_dquot_ref(struct super_block *sb, int type) * later. */ old_inode = inode; + cond_resched(); spin_lock(&sb->s_inode_list_lock); } spin_unlock(&sb->s_inode_list_lock); diff --git a/fs/super.c b/fs/super.c index cfadab2cbf35..cd352530eca9 100644 --- a/fs/super.c +++ b/fs/super.c @@ -448,10 +448,12 @@ void generic_shutdown_super(struct super_block *sb) sync_filesystem(sb); sb->s_flags &= ~SB_ACTIVE; - fsnotify_sb_delete(sb); cgroup_writeback_umount(); + /* evict all inodes with zero refcount */ evict_inodes(sb); + /* only nonzero refcount inodes can have marks */ + fsnotify_sb_delete(sb); if (sb->s_dio_done_wq) { destroy_workqueue(sb->s_dio_done_wq); diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h index 6782f0d45ebe..49e5383d4222 100644 --- a/include/linux/ahci_platform.h +++ b/include/linux/ahci_platform.h @@ -19,6 +19,8 @@ struct ahci_host_priv; struct platform_device; struct scsi_host_template; +int ahci_platform_enable_phys(struct ahci_host_priv *hpriv); +void ahci_platform_disable_phys(struct ahci_host_priv *hpriv); int ahci_platform_enable_clks(struct ahci_host_priv *hpriv); void ahci_platform_disable_clks(struct ahci_host_priv *hpriv); int ahci_platform_enable_regulators(struct ahci_host_priv *hpriv); diff --git a/include/linux/libata.h b/include/linux/libata.h index d3bbfddf616a..2dbde119721d 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1175,6 +1175,7 @@ extern unsigned int ata_do_dev_read_id(struct ata_device *dev, struct ata_taskfile *tf, u16 *id); extern void ata_qc_complete(struct ata_queued_cmd *qc); extern int ata_qc_complete_multiple(struct ata_port *ap, u64 qc_active); +extern u64 ata_qc_get_active(struct ata_port *ap); extern void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd); extern int ata_std_bios_param(struct scsi_device *sdev, struct block_device *bdev, diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 79bc82e30c02..491a2b7e77c1 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -55,7 +55,7 @@ static inline int of_mdio_parse_addr(struct device *dev, } #else /* CONFIG_OF_MDIO */ -static bool of_mdiobus_child_is_phy(struct device_node *child) +static inline bool of_mdiobus_child_is_phy(struct device_node *child) { return false; } diff --git a/include/linux/posix-clock.h b/include/linux/posix-clock.h index fe6cfdcfbc26..468328b1e1dd 100644 --- a/include/linux/posix-clock.h +++ b/include/linux/posix-clock.h @@ -69,29 +69,32 @@ struct posix_clock_operations { * * @ops: Functional interface to the clock * @cdev: Character device instance for this clock - * @kref: Reference count. + * @dev: Pointer to the clock's device. * @rwsem: Protects the 'zombie' field from concurrent access. * @zombie: If 'zombie' is true, then the hardware has disappeared. - * @release: A function to free the structure when the reference count reaches - * zero. May be NULL if structure is statically allocated. * * Drivers should embed their struct posix_clock within a private * structure, obtaining a reference to it during callbacks using * container_of(). + * + * Drivers should supply an initialized but not exposed struct device + * to posix_clock_register(). It is used to manage lifetime of the + * driver's private structure. It's 'release' field should be set to + * a release function for this private structure. */ struct posix_clock { struct posix_clock_operations ops; struct cdev cdev; - struct kref kref; + struct device *dev; struct rw_semaphore rwsem; bool zombie; - void (*release)(struct posix_clock *clk); }; /** * posix_clock_register() - register a new clock - * @clk: Pointer to the clock. Caller must provide 'ops' and 'release' - * @devid: Allocated device id + * @clk: Pointer to the clock. Caller must provide 'ops' field + * @dev: Pointer to the initialized device. Caller must provide + * 'release' field * * A clock driver calls this function to register itself with the * clock device subsystem. If 'clk' points to dynamically allocated @@ -100,7 +103,7 @@ struct posix_clock { * * Returns zero on success, non-zero otherwise. */ -int posix_clock_register(struct posix_clock *clk, dev_t devid); +int posix_clock_register(struct posix_clock *clk, struct device *dev); /** * posix_clock_unregister() - unregister a clock diff --git a/include/net/dst.h b/include/net/dst.h index 8224dad2ae94..3448cf865ede 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -516,7 +516,16 @@ static inline void skb_dst_update_pmtu(struct sk_buff *skb, u32 mtu) struct dst_entry *dst = skb_dst(skb); if (dst && dst->ops->update_pmtu) - dst->ops->update_pmtu(dst, NULL, skb, mtu); + dst->ops->update_pmtu(dst, NULL, skb, mtu, true); +} + +/* update dst pmtu but not do neighbor confirm */ +static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu) +{ + struct dst_entry *dst = skb_dst(skb); + + if (dst && dst->ops->update_pmtu) + dst->ops->update_pmtu(dst, NULL, skb, mtu, false); } static inline void skb_tunnel_check_pmtu(struct sk_buff *skb, @@ -526,7 +535,7 @@ static inline void skb_tunnel_check_pmtu(struct sk_buff *skb, u32 encap_mtu = dst_mtu(encap_dst); if (skb->len > encap_mtu - headroom) - skb_dst_update_pmtu(skb, encap_mtu - headroom); + skb_dst_update_pmtu_no_confirm(skb, encap_mtu - headroom); } #endif /* _NET_DST_H */ diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 5ec645f27ee3..443863c7b8da 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -27,7 +27,8 @@ struct dst_ops { struct dst_entry * (*negative_advice)(struct dst_entry *); void (*link_failure)(struct sk_buff *); void (*update_pmtu)(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu); + struct sk_buff *skb, u32 mtu, + bool confirm_neigh); void (*redirect)(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); int (*local_out)(struct net *net, struct sock *sk, struct sk_buff *skb); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 144f264ea394..fceddf89592a 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -308,6 +308,7 @@ struct tcf_proto_ops { int (*delete)(struct tcf_proto *tp, void *arg, bool *last, bool rtnl_held, struct netlink_ext_ack *); + bool (*delete_empty)(struct tcf_proto *tp); void (*walk)(struct tcf_proto *tp, struct tcf_walker *arg, bool rtnl_held); int (*reoffload)(struct tcf_proto *tp, bool add, @@ -336,6 +337,10 @@ struct tcf_proto_ops { int flags; }; +/* Classifiers setting TCF_PROTO_OPS_DOIT_UNLOCKED in tcf_proto_ops->flags + * are expected to implement tcf_proto_ops->delete_empty(), otherwise race + * conditions can occur when filters are inserted/deleted simultaneously. + */ enum tcf_proto_ops_flags { TCF_PROTO_OPS_DOIT_UNLOCKED = 1, }; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 4983940cbdca..6f63ae7a370c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -907,7 +907,8 @@ static const int caller_saved[CALLER_SAVED_REGS] = { BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5 }; -static void __mark_reg_not_init(struct bpf_reg_state *reg); +static void __mark_reg_not_init(const struct bpf_verifier_env *env, + struct bpf_reg_state *reg); /* Mark the unknown part of a register (variable offset or scalar value) as * known to have the value @imm. @@ -945,7 +946,7 @@ static void mark_reg_known_zero(struct bpf_verifier_env *env, verbose(env, "mark_reg_known_zero(regs, %u)\n", regno); /* Something bad happened, let's kill all regs */ for (regno = 0; regno < MAX_BPF_REG; regno++) - __mark_reg_not_init(regs + regno); + __mark_reg_not_init(env, regs + regno); return; } __mark_reg_known_zero(regs + regno); @@ -1054,7 +1055,8 @@ static void __mark_reg_unbounded(struct bpf_reg_state *reg) } /* Mark a register as having a completely unknown (scalar) value. */ -static void __mark_reg_unknown(struct bpf_reg_state *reg) +static void __mark_reg_unknown(const struct bpf_verifier_env *env, + struct bpf_reg_state *reg) { /* * Clear type, id, off, and union(map_ptr, range) and @@ -1064,6 +1066,8 @@ static void __mark_reg_unknown(struct bpf_reg_state *reg) reg->type = SCALAR_VALUE; reg->var_off = tnum_unknown; reg->frameno = 0; + reg->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks ? + true : false; __mark_reg_unbounded(reg); } @@ -1074,19 +1078,16 @@ static void mark_reg_unknown(struct bpf_verifier_env *env, verbose(env, "mark_reg_unknown(regs, %u)\n", regno); /* Something bad happened, let's kill all regs except FP */ for (regno = 0; regno < BPF_REG_FP; regno++) - __mark_reg_not_init(regs + regno); + __mark_reg_not_init(env, regs + regno); return; } - regs += regno; - __mark_reg_unknown(regs); - /* constant backtracking is enabled for root without bpf2bpf calls */ - regs->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks ? - true : false; + __mark_reg_unknown(env, regs + regno); } -static void __mark_reg_not_init(struct bpf_reg_state *reg) +static void __mark_reg_not_init(const struct bpf_verifier_env *env, + struct bpf_reg_state *reg) { - __mark_reg_unknown(reg); + __mark_reg_unknown(env, reg); reg->type = NOT_INIT; } @@ -1097,10 +1098,10 @@ static void mark_reg_not_init(struct bpf_verifier_env *env, verbose(env, "mark_reg_not_init(regs, %u)\n", regno); /* Something bad happened, let's kill all regs except FP */ for (regno = 0; regno < BPF_REG_FP; regno++) - __mark_reg_not_init(regs + regno); + __mark_reg_not_init(env, regs + regno); return; } - __mark_reg_not_init(regs + regno); + __mark_reg_not_init(env, regs + regno); } #define DEF_NOT_SUBREG (0) @@ -3234,7 +3235,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, } if (state->stack[spi].slot_type[0] == STACK_SPILL && state->stack[spi].spilled_ptr.type == SCALAR_VALUE) { - __mark_reg_unknown(&state->stack[spi].spilled_ptr); + __mark_reg_unknown(env, &state->stack[spi].spilled_ptr); for (j = 0; j < BPF_REG_SIZE; j++) state->stack[spi].slot_type[j] = STACK_MISC; goto mark; @@ -3892,7 +3893,7 @@ static void __clear_all_pkt_pointers(struct bpf_verifier_env *env, if (!reg) continue; if (reg_is_pkt_pointer_any(reg)) - __mark_reg_unknown(reg); + __mark_reg_unknown(env, reg); } } @@ -3920,7 +3921,7 @@ static void release_reg_references(struct bpf_verifier_env *env, if (!reg) continue; if (reg->ref_obj_id == ref_obj_id) - __mark_reg_unknown(reg); + __mark_reg_unknown(env, reg); } } @@ -4582,7 +4583,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, /* Taint dst register if offset had invalid bounds derived from * e.g. dead branches. */ - __mark_reg_unknown(dst_reg); + __mark_reg_unknown(env, dst_reg); return 0; } @@ -4834,13 +4835,13 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, /* Taint dst register if offset had invalid bounds derived from * e.g. dead branches. */ - __mark_reg_unknown(dst_reg); + __mark_reg_unknown(env, dst_reg); return 0; } if (!src_known && opcode != BPF_ADD && opcode != BPF_SUB && opcode != BPF_AND) { - __mark_reg_unknown(dst_reg); + __mark_reg_unknown(env, dst_reg); return 0; } @@ -6982,7 +6983,7 @@ static void clean_func_state(struct bpf_verifier_env *env, /* since the register is unused, clear its state * to make further comparison simpler */ - __mark_reg_not_init(&st->regs[i]); + __mark_reg_not_init(env, &st->regs[i]); } for (i = 0; i < st->allocated_stack / BPF_REG_SIZE; i++) { @@ -6990,7 +6991,7 @@ static void clean_func_state(struct bpf_verifier_env *env, /* liveness must not touch this stack slot anymore */ st->stack[i].spilled_ptr.live |= REG_LIVE_DONE; if (!(live & REG_LIVE_READ)) { - __mark_reg_not_init(&st->stack[i].spilled_ptr); + __mark_reg_not_init(env, &st->stack[i].spilled_ptr); for (j = 0; j < BPF_REG_SIZE; j++) st->stack[i].slot_type[j] = STACK_INVALID; } diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c index ec960bb939fd..200fb2d3be99 100644 --- a/kernel/time/posix-clock.c +++ b/kernel/time/posix-clock.c @@ -14,8 +14,6 @@ #include "posix-timers.h" -static void delete_clock(struct kref *kref); - /* * Returns NULL if the posix_clock instance attached to 'fp' is old and stale. */ @@ -125,7 +123,7 @@ static int posix_clock_open(struct inode *inode, struct file *fp) err = 0; if (!err) { - kref_get(&clk->kref); + get_device(clk->dev); fp->private_data = clk; } out: @@ -141,7 +139,7 @@ static int posix_clock_release(struct inode *inode, struct file *fp) if (clk->ops.release) err = clk->ops.release(clk); - kref_put(&clk->kref, delete_clock); + put_device(clk->dev); fp->private_data = NULL; @@ -161,38 +159,35 @@ static const struct file_operations posix_clock_file_operations = { #endif }; -int posix_clock_register(struct posix_clock *clk, dev_t devid) +int posix_clock_register(struct posix_clock *clk, struct device *dev) { int err; - kref_init(&clk->kref); init_rwsem(&clk->rwsem); cdev_init(&clk->cdev, &posix_clock_file_operations); + err = cdev_device_add(&clk->cdev, dev); + if (err) { + pr_err("%s unable to add device %d:%d\n", + dev_name(dev), MAJOR(dev->devt), MINOR(dev->devt)); + return err; + } clk->cdev.owner = clk->ops.owner; - err = cdev_add(&clk->cdev, devid, 1); + clk->dev = dev; - return err; + return 0; } EXPORT_SYMBOL_GPL(posix_clock_register); -static void delete_clock(struct kref *kref) -{ - struct posix_clock *clk = container_of(kref, struct posix_clock, kref); - - if (clk->release) - clk->release(clk); -} - void posix_clock_unregister(struct posix_clock *clk) { - cdev_del(&clk->cdev); + cdev_device_del(&clk->cdev, clk->dev); down_write(&clk->rwsem); clk->zombie = true; up_write(&clk->rwsem); - kref_put(&clk->kref, delete_clock); + put_device(clk->dev); } EXPORT_SYMBOL_GPL(posix_clock_unregister); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index fb29c02c6a3c..51595bf3af85 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1222,11 +1222,12 @@ EXPORT_SYMBOL(iov_iter_discard); unsigned long iov_iter_alignment(const struct iov_iter *i) { - unsigned int p_mask = i->pipe->ring_size - 1; unsigned long res = 0; size_t size = i->count; if (unlikely(iov_iter_is_pipe(i))) { + unsigned int p_mask = i->pipe->ring_size - 1; + if (size && i->iov_offset && allocated(&i->pipe->bufs[i->head & p_mask])) return size | i->iov_offset; return size; diff --git a/net/bridge/br_nf_core.c b/net/bridge/br_nf_core.c index 2cdfc5d6c25d..8c69f0c95a8e 100644 --- a/net/bridge/br_nf_core.c +++ b/net/bridge/br_nf_core.c @@ -22,7 +22,8 @@ #endif static void fake_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { } diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 4096d8a74a2b..e1256e03a9a8 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1867,7 +1867,7 @@ static int ebt_buf_count(struct ebt_entries_buf_state *state, unsigned int sz) } static int ebt_buf_add(struct ebt_entries_buf_state *state, - void *data, unsigned int sz) + const void *data, unsigned int sz) { if (state->buf_kern_start == NULL) goto count_only; @@ -1901,7 +1901,7 @@ enum compat_mwt { EBT_COMPAT_TARGET, }; -static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, +static int compat_mtw_from_user(const struct compat_ebt_entry_mwt *mwt, enum compat_mwt compat_mwt, struct ebt_entries_buf_state *state, const unsigned char *base) @@ -1979,22 +1979,23 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, /* return size of all matches, watchers or target, including necessary * alignment and padding. */ -static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32, +static int ebt_size_mwt(const struct compat_ebt_entry_mwt *match32, unsigned int size_left, enum compat_mwt type, struct ebt_entries_buf_state *state, const void *base) { + const char *buf = (const char *)match32; int growth = 0; - char *buf; if (size_left == 0) return 0; - buf = (char *) match32; - - while (size_left >= sizeof(*match32)) { + do { struct ebt_entry_match *match_kern; int ret; + if (size_left < sizeof(*match32)) + return -EINVAL; + match_kern = (struct ebt_entry_match *) state->buf_kern_start; if (match_kern) { char *tmp; @@ -2031,22 +2032,18 @@ static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32, if (match_kern) match_kern->match_size = ret; - /* rule should have no remaining data after target */ - if (type == EBT_COMPAT_TARGET && size_left) - return -EINVAL; - match32 = (struct compat_ebt_entry_mwt *) buf; - } + } while (size_left); return growth; } /* called for all ebt_entry structures. */ -static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base, +static int size_entry_mwt(const struct ebt_entry *entry, const unsigned char *base, unsigned int *total, struct ebt_entries_buf_state *state) { - unsigned int i, j, startoff, new_offset = 0; + unsigned int i, j, startoff, next_expected_off, new_offset = 0; /* stores match/watchers/targets & offset of next struct ebt_entry: */ unsigned int offsets[4]; unsigned int *offsets_update = NULL; @@ -2132,11 +2129,13 @@ static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base, return ret; } - startoff = state->buf_user_offset - startoff; + next_expected_off = state->buf_user_offset - startoff; + if (next_expected_off != entry->next_offset) + return -EINVAL; - if (WARN_ON(*total < startoff)) + if (*total < entry->next_offset) return -EINVAL; - *total -= startoff; + *total -= entry->next_offset; return 0; } diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index aea918135ec3..08c3dc45f1a4 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -110,7 +110,8 @@ static void dn_dst_ifdown(struct dst_entry *, struct net_device *dev, int how); static struct dst_entry *dn_dst_negative_advice(struct dst_entry *); static void dn_dst_link_failure(struct sk_buff *); static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb , u32 mtu); + struct sk_buff *skb , u32 mtu, + bool confirm_neigh); static void dn_dst_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst, @@ -251,7 +252,8 @@ static int dn_dst_gc(struct dst_ops *ops) * advertise to the other end). */ static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { struct dn_route *rt = (struct dn_route *) dst; struct neighbour *n = rt->n; diff --git a/net/hsr/hsr_debugfs.c b/net/hsr/hsr_debugfs.c index 94447974a3c0..d5f709b940ff 100644 --- a/net/hsr/hsr_debugfs.c +++ b/net/hsr/hsr_debugfs.c @@ -20,6 +20,8 @@ #include "hsr_main.h" #include "hsr_framereg.h" +static struct dentry *hsr_debugfs_root_dir; + static void print_mac_address(struct seq_file *sfp, unsigned char *mac) { seq_printf(sfp, "%02x:%02x:%02x:%02x:%02x:%02x:", @@ -63,8 +65,20 @@ hsr_node_table_open(struct inode *inode, struct file *filp) return single_open(filp, hsr_node_table_show, inode->i_private); } +void hsr_debugfs_rename(struct net_device *dev) +{ + struct hsr_priv *priv = netdev_priv(dev); + struct dentry *d; + + d = debugfs_rename(hsr_debugfs_root_dir, priv->node_tbl_root, + hsr_debugfs_root_dir, dev->name); + if (IS_ERR(d)) + netdev_warn(dev, "failed to rename\n"); + else + priv->node_tbl_root = d; +} + static const struct file_operations hsr_fops = { - .owner = THIS_MODULE, .open = hsr_node_table_open, .read = seq_read, .llseek = seq_lseek, @@ -78,15 +92,14 @@ static const struct file_operations hsr_fops = { * When debugfs is configured this routine sets up the node_table file per * hsr device for dumping the node_table entries */ -int hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev) +void hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev) { - int rc = -1; struct dentry *de = NULL; - de = debugfs_create_dir(hsr_dev->name, NULL); - if (!de) { - pr_err("Cannot create hsr debugfs root\n"); - return rc; + de = debugfs_create_dir(hsr_dev->name, hsr_debugfs_root_dir); + if (IS_ERR(de)) { + pr_err("Cannot create hsr debugfs directory\n"); + return; } priv->node_tbl_root = de; @@ -94,13 +107,13 @@ int hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev) de = debugfs_create_file("node_table", S_IFREG | 0444, priv->node_tbl_root, priv, &hsr_fops); - if (!de) { - pr_err("Cannot create hsr node_table directory\n"); - return rc; + if (IS_ERR(de)) { + pr_err("Cannot create hsr node_table file\n"); + debugfs_remove(priv->node_tbl_root); + priv->node_tbl_root = NULL; + return; } priv->node_tbl_file = de; - - return 0; } /* hsr_debugfs_term - Tear down debugfs intrastructure @@ -117,3 +130,18 @@ hsr_debugfs_term(struct hsr_priv *priv) debugfs_remove(priv->node_tbl_root); priv->node_tbl_root = NULL; } + +void hsr_debugfs_create_root(void) +{ + hsr_debugfs_root_dir = debugfs_create_dir("hsr", NULL); + if (IS_ERR(hsr_debugfs_root_dir)) { + pr_err("Cannot create hsr debugfs root directory\n"); + hsr_debugfs_root_dir = NULL; + } +} + +void hsr_debugfs_remove_root(void) +{ + /* debugfs_remove() internally checks NULL and ERROR */ + debugfs_remove(hsr_debugfs_root_dir); +} diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index b01e1bae4ddc..c7bd6c49fadf 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -272,6 +272,8 @@ static void send_hsr_supervision_frame(struct hsr_port *master, skb->dev->dev_addr, skb->len) <= 0) goto out; skb_reset_mac_header(skb); + skb_reset_network_header(skb); + skb_reset_transport_header(skb); if (hsr_ver > 0) { hsr_tag = skb_put(skb, sizeof(struct hsr_tag)); @@ -368,7 +370,7 @@ static void hsr_dev_destroy(struct net_device *hsr_dev) del_timer_sync(&hsr->prune_timer); del_timer_sync(&hsr->announce_timer); - hsr_del_self_node(&hsr->self_node_db); + hsr_del_self_node(hsr); hsr_del_nodes(&hsr->node_db); } @@ -440,11 +442,12 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], INIT_LIST_HEAD(&hsr->ports); INIT_LIST_HEAD(&hsr->node_db); INIT_LIST_HEAD(&hsr->self_node_db); + spin_lock_init(&hsr->list_lock); ether_addr_copy(hsr_dev->dev_addr, slave[0]->dev_addr); /* Make sure we recognize frames from ourselves in hsr_rcv() */ - res = hsr_create_self_node(&hsr->self_node_db, hsr_dev->dev_addr, + res = hsr_create_self_node(hsr, hsr_dev->dev_addr, slave[1]->dev_addr); if (res < 0) return res; @@ -477,31 +480,32 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], res = hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER); if (res) - goto err_add_port; + goto err_add_master; res = register_netdevice(hsr_dev); if (res) - goto fail; + goto err_unregister; res = hsr_add_port(hsr, slave[0], HSR_PT_SLAVE_A); if (res) - goto fail; + goto err_add_slaves; + res = hsr_add_port(hsr, slave[1], HSR_PT_SLAVE_B); if (res) - goto fail; + goto err_add_slaves; + hsr_debugfs_init(hsr, hsr_dev); mod_timer(&hsr->prune_timer, jiffies + msecs_to_jiffies(PRUNE_PERIOD)); - res = hsr_debugfs_init(hsr, hsr_dev); - if (res) - goto fail; return 0; -fail: +err_add_slaves: + unregister_netdevice(hsr_dev); +err_unregister: list_for_each_entry_safe(port, tmp, &hsr->ports, port_list) hsr_del_port(port); -err_add_port: - hsr_del_self_node(&hsr->self_node_db); +err_add_master: + hsr_del_self_node(hsr); return res; } diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 292be446007b..27dc65d7de67 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -75,10 +75,11 @@ static struct hsr_node *find_node_by_addr_A(struct list_head *node_db, /* Helper for device init; the self_node_db is used in hsr_rcv() to recognize * frames from self that's been looped over the HSR ring. */ -int hsr_create_self_node(struct list_head *self_node_db, +int hsr_create_self_node(struct hsr_priv *hsr, unsigned char addr_a[ETH_ALEN], unsigned char addr_b[ETH_ALEN]) { + struct list_head *self_node_db = &hsr->self_node_db; struct hsr_node *node, *oldnode; node = kmalloc(sizeof(*node), GFP_KERNEL); @@ -88,33 +89,33 @@ int hsr_create_self_node(struct list_head *self_node_db, ether_addr_copy(node->macaddress_A, addr_a); ether_addr_copy(node->macaddress_B, addr_b); - rcu_read_lock(); + spin_lock_bh(&hsr->list_lock); oldnode = list_first_or_null_rcu(self_node_db, struct hsr_node, mac_list); if (oldnode) { list_replace_rcu(&oldnode->mac_list, &node->mac_list); - rcu_read_unlock(); - synchronize_rcu(); - kfree(oldnode); + spin_unlock_bh(&hsr->list_lock); + kfree_rcu(oldnode, rcu_head); } else { - rcu_read_unlock(); list_add_tail_rcu(&node->mac_list, self_node_db); + spin_unlock_bh(&hsr->list_lock); } return 0; } -void hsr_del_self_node(struct list_head *self_node_db) +void hsr_del_self_node(struct hsr_priv *hsr) { + struct list_head *self_node_db = &hsr->self_node_db; struct hsr_node *node; - rcu_read_lock(); + spin_lock_bh(&hsr->list_lock); node = list_first_or_null_rcu(self_node_db, struct hsr_node, mac_list); - rcu_read_unlock(); if (node) { list_del_rcu(&node->mac_list); - kfree(node); + kfree_rcu(node, rcu_head); } + spin_unlock_bh(&hsr->list_lock); } void hsr_del_nodes(struct list_head *node_db) @@ -130,30 +131,43 @@ void hsr_del_nodes(struct list_head *node_db) * seq_out is used to initialize filtering of outgoing duplicate frames * originating from the newly added node. */ -struct hsr_node *hsr_add_node(struct list_head *node_db, unsigned char addr[], - u16 seq_out) +static struct hsr_node *hsr_add_node(struct hsr_priv *hsr, + struct list_head *node_db, + unsigned char addr[], + u16 seq_out) { - struct hsr_node *node; + struct hsr_node *new_node, *node; unsigned long now; int i; - node = kzalloc(sizeof(*node), GFP_ATOMIC); - if (!node) + new_node = kzalloc(sizeof(*new_node), GFP_ATOMIC); + if (!new_node) return NULL; - ether_addr_copy(node->macaddress_A, addr); + ether_addr_copy(new_node->macaddress_A, addr); /* We are only interested in time diffs here, so use current jiffies * as initialization. (0 could trigger an spurious ring error warning). */ now = jiffies; for (i = 0; i < HSR_PT_PORTS; i++) - node->time_in[i] = now; + new_node->time_in[i] = now; for (i = 0; i < HSR_PT_PORTS; i++) - node->seq_out[i] = seq_out; - - list_add_tail_rcu(&node->mac_list, node_db); + new_node->seq_out[i] = seq_out; + spin_lock_bh(&hsr->list_lock); + list_for_each_entry_rcu(node, node_db, mac_list) { + if (ether_addr_equal(node->macaddress_A, addr)) + goto out; + if (ether_addr_equal(node->macaddress_B, addr)) + goto out; + } + list_add_tail_rcu(&new_node->mac_list, node_db); + spin_unlock_bh(&hsr->list_lock); + return new_node; +out: + spin_unlock_bh(&hsr->list_lock); + kfree(new_node); return node; } @@ -163,6 +177,7 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb, bool is_sup) { struct list_head *node_db = &port->hsr->node_db; + struct hsr_priv *hsr = port->hsr; struct hsr_node *node; struct ethhdr *ethhdr; u16 seq_out; @@ -196,7 +211,7 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb, seq_out = HSR_SEQNR_START; } - return hsr_add_node(node_db, ethhdr->h_source, seq_out); + return hsr_add_node(hsr, node_db, ethhdr->h_source, seq_out); } /* Use the Supervision frame's info about an eventual macaddress_B for merging @@ -206,10 +221,11 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb, void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr, struct hsr_port *port_rcv) { - struct ethhdr *ethhdr; - struct hsr_node *node_real; + struct hsr_priv *hsr = port_rcv->hsr; struct hsr_sup_payload *hsr_sp; + struct hsr_node *node_real; struct list_head *node_db; + struct ethhdr *ethhdr; int i; ethhdr = (struct ethhdr *)skb_mac_header(skb); @@ -231,7 +247,7 @@ void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr, node_real = find_node_by_addr_A(node_db, hsr_sp->macaddress_A); if (!node_real) /* No frame received from AddrA of this node yet */ - node_real = hsr_add_node(node_db, hsr_sp->macaddress_A, + node_real = hsr_add_node(hsr, node_db, hsr_sp->macaddress_A, HSR_SEQNR_START - 1); if (!node_real) goto done; /* No mem */ @@ -252,7 +268,9 @@ void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr, } node_real->addr_B_port = port_rcv->type; + spin_lock_bh(&hsr->list_lock); list_del_rcu(&node_curr->mac_list); + spin_unlock_bh(&hsr->list_lock); kfree_rcu(node_curr, rcu_head); done: @@ -368,12 +386,13 @@ void hsr_prune_nodes(struct timer_list *t) { struct hsr_priv *hsr = from_timer(hsr, t, prune_timer); struct hsr_node *node; + struct hsr_node *tmp; struct hsr_port *port; unsigned long timestamp; unsigned long time_a, time_b; - rcu_read_lock(); - list_for_each_entry_rcu(node, &hsr->node_db, mac_list) { + spin_lock_bh(&hsr->list_lock); + list_for_each_entry_safe(node, tmp, &hsr->node_db, mac_list) { /* Don't prune own node. Neither time_in[HSR_PT_SLAVE_A] * nor time_in[HSR_PT_SLAVE_B], will ever be updated for * the master port. Thus the master node will be repeatedly @@ -421,7 +440,7 @@ void hsr_prune_nodes(struct timer_list *t) kfree_rcu(node, rcu_head); } } - rcu_read_unlock(); + spin_unlock_bh(&hsr->list_lock); /* Restart timer */ mod_timer(&hsr->prune_timer, diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h index 89a3ce38151d..0f0fa12b4329 100644 --- a/net/hsr/hsr_framereg.h +++ b/net/hsr/hsr_framereg.h @@ -12,10 +12,8 @@ struct hsr_node; -void hsr_del_self_node(struct list_head *self_node_db); +void hsr_del_self_node(struct hsr_priv *hsr); void hsr_del_nodes(struct list_head *node_db); -struct hsr_node *hsr_add_node(struct list_head *node_db, unsigned char addr[], - u16 seq_out); struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb, bool is_sup); void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr, @@ -33,7 +31,7 @@ int hsr_register_frame_out(struct hsr_port *port, struct hsr_node *node, void hsr_prune_nodes(struct timer_list *t); -int hsr_create_self_node(struct list_head *self_node_db, +int hsr_create_self_node(struct hsr_priv *hsr, unsigned char addr_a[ETH_ALEN], unsigned char addr_b[ETH_ALEN]); diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c index b9988a662ee1..9e389accbfc7 100644 --- a/net/hsr/hsr_main.c +++ b/net/hsr/hsr_main.c @@ -45,6 +45,10 @@ static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event, case NETDEV_CHANGE: /* Link (carrier) state changes */ hsr_check_carrier_and_operstate(hsr); break; + case NETDEV_CHANGENAME: + if (is_hsr_master(dev)) + hsr_debugfs_rename(dev); + break; case NETDEV_CHANGEADDR: if (port->type == HSR_PT_MASTER) { /* This should not happen since there's no @@ -64,7 +68,7 @@ static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event, /* Make sure we recognize frames from ourselves in hsr_rcv() */ port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); - res = hsr_create_self_node(&hsr->self_node_db, + res = hsr_create_self_node(hsr, master->dev->dev_addr, port ? port->dev->dev_addr : @@ -123,6 +127,7 @@ static void __exit hsr_exit(void) { unregister_netdevice_notifier(&hsr_nb); hsr_netlink_exit(); + hsr_debugfs_remove_root(); } module_init(hsr_init); diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index 96fac696a1e1..d40de84a637f 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -160,8 +160,9 @@ struct hsr_priv { int announce_count; u16 sequence_nr; u16 sup_sequence_nr; /* For HSRv1 separate seq_nr for supervision */ - u8 prot_version; /* Indicate if HSRv0 or HSRv1. */ - spinlock_t seqnr_lock; /* locking for sequence_nr */ + u8 prot_version; /* Indicate if HSRv0 or HSRv1. */ + spinlock_t seqnr_lock; /* locking for sequence_nr */ + spinlock_t list_lock; /* locking for node list */ unsigned char sup_multicast_addr[ETH_ALEN]; #ifdef CONFIG_DEBUG_FS struct dentry *node_tbl_root; @@ -184,17 +185,24 @@ static inline u16 hsr_get_skb_sequence_nr(struct sk_buff *skb) } #if IS_ENABLED(CONFIG_DEBUG_FS) -int hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev); +void hsr_debugfs_rename(struct net_device *dev); +void hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev); void hsr_debugfs_term(struct hsr_priv *priv); +void hsr_debugfs_create_root(void); +void hsr_debugfs_remove_root(void); #else -static inline int hsr_debugfs_init(struct hsr_priv *priv, - struct net_device *hsr_dev) +static inline void void hsr_debugfs_rename(struct net_device *dev) { - return 0; } - +static inline void hsr_debugfs_init(struct hsr_priv *priv, + struct net_device *hsr_dev) +{} static inline void hsr_debugfs_term(struct hsr_priv *priv) {} +static inline void hsr_debugfs_create_root(void) +{} +static inline void hsr_debugfs_remove_root(void) +{} #endif #endif /* __HSR_PRIVATE_H */ diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index 8f8337f893ba..8dc0547f01d0 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -476,6 +476,7 @@ int __init hsr_netlink_init(void) if (rc) goto fail_genl_register_family; + hsr_debugfs_create_root(); return 0; fail_genl_register_family: diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index e4c6e8b40490..18c0d5bffe12 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1086,7 +1086,7 @@ struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu) if (!dst) goto out; } - dst->ops->update_pmtu(dst, sk, NULL, mtu); + dst->ops->update_pmtu(dst, sk, NULL, mtu, true); dst = __sk_dst_check(sk, 0); if (!dst) diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 38c02bb62e2c..0fe2a5d3e258 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -505,7 +505,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; if (skb_valid_dst(skb)) - skb_dst_update_pmtu(skb, mtu); + skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { if (!skb_is_gso(skb) && diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 9b153c7fcbb4..e90b600c7a25 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -214,7 +214,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, mtu = dst_mtu(dst); if (skb->len > mtu) { - skb_dst_update_pmtu(skb, mtu); + skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index f88c93c38f11..87e979f2b74a 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -139,7 +139,8 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst); static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu); + struct sk_buff *skb, u32 mtu, + bool confirm_neigh); static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static void ipv4_dst_destroy(struct dst_entry *dst); @@ -1043,7 +1044,8 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) } static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { struct rtable *rt = (struct rtable *) dst; struct flowi4 fl4; @@ -2687,7 +2689,8 @@ static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst) } static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 1f7735ca8f22..58c92a7d671c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -72,6 +72,9 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) __skb_unlink(skb, &sk->sk_write_queue); tcp_rbtree_insert(&sk->tcp_rtx_queue, skb); + if (tp->highest_sack == NULL) + tp->highest_sack = skb; + tp->packets_out += tcp_skb_pcount(skb); if (!prior_packets || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) tcp_rearm_rto(sk); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 4da5758cc718..93a355b6b092 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1475,7 +1475,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) * queue contains some other skb */ rmem = atomic_add_return(size, &sk->sk_rmem_alloc); - if (rmem > (size + sk->sk_rcvbuf)) + if (rmem > (size + (unsigned int)sk->sk_rcvbuf)) goto uncharge_drop; spin_lock(&list->lock); diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 35b84b52b702..9ebd54752e03 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -100,12 +100,13 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, } static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; - path->ops->update_pmtu(path, sk, skb, mtu); + path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh); } static void xfrm4_redirect(struct dst_entry *dst, struct sock *sk, diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index fe9cb8d1adca..e315526fa244 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -146,7 +146,7 @@ struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu) if (IS_ERR(dst)) return NULL; - dst->ops->update_pmtu(dst, sk, NULL, mtu); + dst->ops->update_pmtu(dst, sk, NULL, mtu, true); dst = inet6_csk_route_socket(sk, &fl6); return IS_ERR(dst) ? NULL : dst; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 9d0965252ddf..ee968d980746 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1040,7 +1040,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, /* TooBig packet may have updated dst->dev's mtu */ if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu) - dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu); + dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu, false); err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, NEXTHDR_GRE); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 754a484d35df..2f376dbc37d5 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -640,7 +640,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (rel_info > dst_mtu(skb_dst(skb2))) goto out; - skb_dst_update_pmtu(skb2, rel_info); + skb_dst_update_pmtu_no_confirm(skb2, rel_info); } icmp_send(skb2, rel_type, rel_code, htonl(rel_info)); @@ -1132,7 +1132,7 @@ route_lookup: mtu = max(mtu, skb->protocol == htons(ETH_P_IPV6) ? IPV6_MIN_MTU : IPV4_MIN_MTU); - skb_dst_update_pmtu(skb, mtu); + skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) { *pmtu = mtu; err = -EMSGSIZE; diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 024db17386d2..6f08b760c2a7 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -479,7 +479,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) mtu = dst_mtu(dst); if (skb->len > mtu) { - skb_dst_update_pmtu(skb, mtu); + skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IPV6)) { if (mtu < IPV6_MIN_MTU) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 4b8659e077d3..0253b702afb7 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -95,7 +95,8 @@ static int ip6_pkt_prohibit(struct sk_buff *skb); static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb); static void ip6_link_failure(struct sk_buff *skb); static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu); + struct sk_buff *skb, u32 mtu, + bool confirm_neigh); static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static int rt6_score_route(const struct fib6_nh *nh, u32 fib6_flags, int oif, @@ -264,7 +265,8 @@ static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst) } static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { } @@ -2692,7 +2694,8 @@ static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt) } static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, - const struct ipv6hdr *iph, u32 mtu) + const struct ipv6hdr *iph, u32 mtu, + bool confirm_neigh) { const struct in6_addr *daddr, *saddr; struct rt6_info *rt6 = (struct rt6_info *)dst; @@ -2710,7 +2713,10 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, daddr = NULL; saddr = NULL; } - dst_confirm_neigh(dst, daddr); + + if (confirm_neigh) + dst_confirm_neigh(dst, daddr); + mtu = max_t(u32, mtu, IPV6_MIN_MTU); if (mtu >= dst_mtu(dst)) return; @@ -2764,9 +2770,11 @@ out_unlock: } static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { - __ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu); + __ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu, + confirm_neigh); } void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, @@ -2785,7 +2793,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, dst = ip6_route_output(net, NULL, &fl6); if (!dst->error) - __ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu)); + __ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu), true); dst_release(dst); } EXPORT_SYMBOL_GPL(ip6_update_pmtu); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index b2ccbc473127..98954830c40b 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -944,7 +944,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, } if (tunnel->parms.iph.daddr) - skb_dst_update_pmtu(skb, mtu); + skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->len > mtu && !skb_is_gso(skb)) { icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 699e0730ce8e..af7a4b8b1e9c 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -98,12 +98,13 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, } static void xfrm6_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; - path->ops->update_pmtu(path, sk, skb, mtu); + path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh); } static void xfrm6_redirect(struct dst_entry *dst, struct sock *sk, diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index b1e300f8881b..b00866d777fe 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -208,7 +208,7 @@ static inline void maybe_update_pmtu(int skb_af, struct sk_buff *skb, int mtu) struct rtable *ort = skb_rtable(skb); if (!skb->dev && sk && sk_fullsock(sk)) - ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu); + ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu, true); } static inline bool ensure_mtu_is_adequate(struct netns_ipvs *ipvs, int skb_af, diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index de7a0d1e15c8..0d72e5ccb47b 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -88,7 +88,7 @@ static int nf_flow_rule_match(struct nf_flow_match *match, switch (tuple->l4proto) { case IPPROTO_TCP: key->tcp.flags = 0; - mask->tcp.flags = TCP_FLAG_RST | TCP_FLAG_FIN; + mask->tcp.flags = cpu_to_be16(be32_to_cpu(TCP_FLAG_RST | TCP_FLAG_FIN) >> 16); match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_TCP); break; case IPPROTO_UDP: diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index 4c33dfc9dab5..d67f83a0958d 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -50,7 +50,7 @@ static void nft_tproxy_eval_v4(const struct nft_expr *expr, taddr = nf_tproxy_laddr4(skb, taddr, iph->daddr); if (priv->sreg_port) - tport = regs->data[priv->sreg_port]; + tport = nft_reg_load16(®s->data[priv->sreg_port]); if (!tport) tport = hp->dest; @@ -117,7 +117,7 @@ static void nft_tproxy_eval_v6(const struct nft_expr *expr, taddr = *nf_tproxy_laddr6(skb, &taddr, &iph->daddr); if (priv->sreg_port) - tport = regs->data[priv->sreg_port]; + tport = nft_reg_load16(®s->data[priv->sreg_port]); if (!tport) tport = hp->dest; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 7c7d10f2e0c1..5e99df80e80a 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -209,6 +209,7 @@ struct rxrpc_skb_priv { struct rxrpc_security { const char *name; /* name of this service */ u8 security_index; /* security type provided */ + u32 no_key_abort; /* Abort code indicating no key */ /* Initialise a security service */ int (*init)(void); @@ -977,8 +978,9 @@ static inline void rxrpc_reduce_conn_timer(struct rxrpc_connection *conn, struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *, struct sk_buff *); struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *, gfp_t); -void rxrpc_new_incoming_connection(struct rxrpc_sock *, - struct rxrpc_connection *, struct sk_buff *); +void rxrpc_new_incoming_connection(struct rxrpc_sock *, struct rxrpc_connection *, + const struct rxrpc_security *, struct key *, + struct sk_buff *); void rxrpc_unpublish_service_conn(struct rxrpc_connection *); /* @@ -1103,7 +1105,9 @@ extern const struct rxrpc_security rxkad; int __init rxrpc_init_security(void); void rxrpc_exit_security(void); int rxrpc_init_client_conn_security(struct rxrpc_connection *); -int rxrpc_init_server_conn_security(struct rxrpc_connection *); +bool rxrpc_look_up_server_security(struct rxrpc_local *, struct rxrpc_sock *, + const struct rxrpc_security **, struct key **, + struct sk_buff *); /* * sendmsg.c diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 135bf5cd8dd5..70e44abf106c 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -240,6 +240,22 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) } /* + * Ping the other end to fill our RTT cache and to retrieve the rwind + * and MTU parameters. + */ +static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + ktime_t now = skb->tstamp; + + if (call->peer->rtt_usage < 3 || + ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), now)) + rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, + true, true, + rxrpc_propose_ack_ping_for_params); +} + +/* * Allocate a new incoming call from the prealloc pool, along with a connection * and a peer as necessary. */ @@ -247,6 +263,8 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, struct rxrpc_local *local, struct rxrpc_peer *peer, struct rxrpc_connection *conn, + const struct rxrpc_security *sec, + struct key *key, struct sk_buff *skb) { struct rxrpc_backlog *b = rx->backlog; @@ -294,7 +312,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, conn->params.local = rxrpc_get_local(local); conn->params.peer = peer; rxrpc_see_connection(conn); - rxrpc_new_incoming_connection(rx, conn, skb); + rxrpc_new_incoming_connection(rx, conn, sec, key, skb); } else { rxrpc_get_connection(conn); } @@ -333,9 +351,11 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + const struct rxrpc_security *sec = NULL; struct rxrpc_connection *conn; struct rxrpc_peer *peer = NULL; - struct rxrpc_call *call; + struct rxrpc_call *call = NULL; + struct key *key = NULL; _enter(""); @@ -346,9 +366,7 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, sp->hdr.seq, RX_INVALID_OPERATION, ESHUTDOWN); skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; skb->priority = RX_INVALID_OPERATION; - _leave(" = NULL [close]"); - call = NULL; - goto out; + goto no_call; } /* The peer, connection and call may all have sprung into existence due @@ -358,29 +376,19 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, */ conn = rxrpc_find_connection_rcu(local, skb, &peer); - call = rxrpc_alloc_incoming_call(rx, local, peer, conn, skb); + if (!conn && !rxrpc_look_up_server_security(local, rx, &sec, &key, skb)) + goto no_call; + + call = rxrpc_alloc_incoming_call(rx, local, peer, conn, sec, key, skb); + key_put(key); if (!call) { skb->mark = RXRPC_SKB_MARK_REJECT_BUSY; - _leave(" = NULL [busy]"); - call = NULL; - goto out; + goto no_call; } trace_rxrpc_receive(call, rxrpc_receive_incoming, sp->hdr.serial, sp->hdr.seq); - /* Lock the call to prevent rxrpc_kernel_send/recv_data() and - * sendmsg()/recvmsg() inconveniently stealing the mutex once the - * notification is generated. - * - * The BUG should never happen because the kernel should be well - * behaved enough not to access the call before the first notification - * event and userspace is prevented from doing so until the state is - * appropriate. - */ - if (!mutex_trylock(&call->user_mutex)) - BUG(); - /* Make the call live. */ rxrpc_incoming_call(rx, call, skb); conn = call->conn; @@ -421,6 +429,9 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, BUG(); } spin_unlock(&conn->state_lock); + spin_unlock(&rx->incoming_lock); + + rxrpc_send_ping(call, skb); if (call->state == RXRPC_CALL_SERVER_ACCEPTING) rxrpc_notify_socket(call); @@ -433,9 +444,12 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, rxrpc_put_call(call, rxrpc_call_put); _leave(" = %p{%d}", call, call->debug_id); -out: - spin_unlock(&rx->incoming_lock); return call; + +no_call: + spin_unlock(&rx->incoming_lock); + _leave(" = NULL [%u]", skb->mark); + return NULL; } /* diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index a1ceef4f5cd0..808a4723f868 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -376,21 +376,7 @@ static void rxrpc_secure_connection(struct rxrpc_connection *conn) _enter("{%d}", conn->debug_id); ASSERT(conn->security_ix != 0); - - if (!conn->params.key) { - _debug("set up security"); - ret = rxrpc_init_server_conn_security(conn); - switch (ret) { - case 0: - break; - case -ENOENT: - abort_code = RX_CALL_DEAD; - goto abort; - default: - abort_code = RXKADNOAUTH; - goto abort; - } - } + ASSERT(conn->server_key); if (conn->security->issue_challenge(conn) < 0) { abort_code = RX_CALL_DEAD; diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index 123d6ceab15c..21da48e3d2e5 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -148,6 +148,8 @@ struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxn */ void rxrpc_new_incoming_connection(struct rxrpc_sock *rx, struct rxrpc_connection *conn, + const struct rxrpc_security *sec, + struct key *key, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); @@ -160,6 +162,8 @@ void rxrpc_new_incoming_connection(struct rxrpc_sock *rx, conn->service_id = sp->hdr.serviceId; conn->security_ix = sp->hdr.securityIndex; conn->out_clientflag = 0; + conn->security = sec; + conn->server_key = key_get(key); if (conn->security_ix) conn->state = RXRPC_CONN_SERVICE_UNSECURED; else diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 157be1ff8697..86bd133b4fa0 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -193,22 +193,6 @@ send_extra_data: } /* - * Ping the other end to fill our RTT cache and to retrieve the rwind - * and MTU parameters. - */ -static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb) -{ - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - ktime_t now = skb->tstamp; - - if (call->peer->rtt_usage < 3 || - ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), now)) - rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, - true, true, - rxrpc_propose_ack_ping_for_params); -} - -/* * Apply a hard ACK by advancing the Tx window. */ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, @@ -1396,8 +1380,6 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) call = rxrpc_new_incoming_call(local, rx, skb); if (!call) goto reject_packet; - rxrpc_send_ping(call, skb); - mutex_unlock(&call->user_mutex); } /* Process a call packet; this either discards or passes on the ref diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 8d8aa3c230b5..098f1f9ec53b 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -648,9 +648,9 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn) u32 serial; int ret; - _enter("{%d,%x}", conn->debug_id, key_serial(conn->params.key)); + _enter("{%d,%x}", conn->debug_id, key_serial(conn->server_key)); - ret = key_validate(conn->params.key); + ret = key_validate(conn->server_key); if (ret < 0) return ret; @@ -1293,6 +1293,7 @@ static void rxkad_exit(void) const struct rxrpc_security rxkad = { .name = "rxkad", .security_index = RXRPC_SECURITY_RXKAD, + .no_key_abort = RXKADUNKNOWNKEY, .init = rxkad_init, .exit = rxkad_exit, .init_connection_security = rxkad_init_connection_security, diff --git a/net/rxrpc/security.c b/net/rxrpc/security.c index a4c47d2b7054..9b1fb9ed0717 100644 --- a/net/rxrpc/security.c +++ b/net/rxrpc/security.c @@ -101,62 +101,58 @@ int rxrpc_init_client_conn_security(struct rxrpc_connection *conn) } /* - * initialise the security on a server connection + * Find the security key for a server connection. */ -int rxrpc_init_server_conn_security(struct rxrpc_connection *conn) +bool rxrpc_look_up_server_security(struct rxrpc_local *local, struct rxrpc_sock *rx, + const struct rxrpc_security **_sec, + struct key **_key, + struct sk_buff *skb) { const struct rxrpc_security *sec; - struct rxrpc_local *local = conn->params.local; - struct rxrpc_sock *rx; - struct key *key; - key_ref_t kref; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + key_ref_t kref = NULL; char kdesc[5 + 1 + 3 + 1]; _enter(""); - sprintf(kdesc, "%u:%u", conn->service_id, conn->security_ix); + sprintf(kdesc, "%u:%u", sp->hdr.serviceId, sp->hdr.securityIndex); - sec = rxrpc_security_lookup(conn->security_ix); + sec = rxrpc_security_lookup(sp->hdr.securityIndex); if (!sec) { - _leave(" = -ENOKEY [lookup]"); - return -ENOKEY; + trace_rxrpc_abort(0, "SVS", + sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, + RX_INVALID_OPERATION, EKEYREJECTED); + skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; + skb->priority = RX_INVALID_OPERATION; + return false; } - /* find the service */ - read_lock(&local->services_lock); - rx = rcu_dereference_protected(local->service, - lockdep_is_held(&local->services_lock)); - if (rx && (rx->srx.srx_service == conn->service_id || - rx->second_service == conn->service_id)) - goto found_service; + if (sp->hdr.securityIndex == RXRPC_SECURITY_NONE) + goto out; - /* the service appears to have died */ - read_unlock(&local->services_lock); - _leave(" = -ENOENT"); - return -ENOENT; - -found_service: if (!rx->securities) { - read_unlock(&local->services_lock); - _leave(" = -ENOKEY"); - return -ENOKEY; + trace_rxrpc_abort(0, "SVR", + sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, + RX_INVALID_OPERATION, EKEYREJECTED); + skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; + skb->priority = RX_INVALID_OPERATION; + return false; } /* look through the service's keyring */ kref = keyring_search(make_key_ref(rx->securities, 1UL), &key_type_rxrpc_s, kdesc, true); if (IS_ERR(kref)) { - read_unlock(&local->services_lock); - _leave(" = %ld [search]", PTR_ERR(kref)); - return PTR_ERR(kref); + trace_rxrpc_abort(0, "SVK", + sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, + sec->no_key_abort, EKEYREJECTED); + skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; + skb->priority = sec->no_key_abort; + return false; } - key = key_ref_to_ptr(kref); - read_unlock(&local->services_lock); - - conn->server_key = key; - conn->security = sec; - - _leave(" = 0"); - return 0; +out: + *_sec = sec; + *_key = key_ref_to_ptr(kref); + return true; } diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 1e3eb3a97532..1ad300e6dbc0 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -219,8 +219,10 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, bool use_reinsert; bool want_ingress; bool is_redirect; + bool expects_nh; int m_eaction; int mac_len; + bool at_nh; rec_level = __this_cpu_inc_return(mirred_rec_level); if (unlikely(rec_level > MIRRED_RECURSION_LIMIT)) { @@ -261,19 +263,19 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, goto out; } - /* If action's target direction differs than filter's direction, - * and devices expect a mac header on xmit, then mac push/pull is - * needed. - */ want_ingress = tcf_mirred_act_wants_ingress(m_eaction); - if (skb_at_tc_ingress(skb) != want_ingress && m_mac_header_xmit) { - if (!skb_at_tc_ingress(skb)) { - /* caught at egress, act ingress: pull mac */ - mac_len = skb_network_header(skb) - skb_mac_header(skb); + + expects_nh = want_ingress || !m_mac_header_xmit; + at_nh = skb->data == skb_network_header(skb); + if (at_nh != expects_nh) { + mac_len = skb_at_tc_ingress(skb) ? skb->mac_len : + skb_network_header(skb) - skb_mac_header(skb); + if (expects_nh) { + /* target device/action expect data at nh */ skb_pull_rcsum(skb2, mac_len); } else { - /* caught at ingress, act egress: push mac */ - skb_push_rcsum(skb2, skb->mac_len); + /* target device/action expect data at mac */ + skb_push_rcsum(skb2, mac_len); } } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 6a0eacafdb19..76e0d122616a 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -308,33 +308,12 @@ static void tcf_proto_put(struct tcf_proto *tp, bool rtnl_held, tcf_proto_destroy(tp, rtnl_held, true, extack); } -static int walker_check_empty(struct tcf_proto *tp, void *fh, - struct tcf_walker *arg) +static bool tcf_proto_check_delete(struct tcf_proto *tp) { - if (fh) { - arg->nonempty = true; - return -1; - } - return 0; -} - -static bool tcf_proto_is_empty(struct tcf_proto *tp, bool rtnl_held) -{ - struct tcf_walker walker = { .fn = walker_check_empty, }; - - if (tp->ops->walk) { - tp->ops->walk(tp, &walker, rtnl_held); - return !walker.nonempty; - } - return true; -} + if (tp->ops->delete_empty) + return tp->ops->delete_empty(tp); -static bool tcf_proto_check_delete(struct tcf_proto *tp, bool rtnl_held) -{ - spin_lock(&tp->lock); - if (tcf_proto_is_empty(tp, rtnl_held)) - tp->deleting = true; - spin_unlock(&tp->lock); + tp->deleting = true; return tp->deleting; } @@ -1751,7 +1730,7 @@ static void tcf_chain_tp_delete_empty(struct tcf_chain *chain, * concurrently. * Mark tp for deletion if it is empty. */ - if (!tp_iter || !tcf_proto_check_delete(tp, rtnl_held)) { + if (!tp_iter || !tcf_proto_check_delete(tp)) { mutex_unlock(&chain->filter_chain_lock); return; } diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 0d125de54285..b0f42e62dd76 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -2773,6 +2773,17 @@ static void fl_bind_class(void *fh, u32 classid, unsigned long cl) f->res.class = cl; } +static bool fl_delete_empty(struct tcf_proto *tp) +{ + struct cls_fl_head *head = fl_head_dereference(tp); + + spin_lock(&tp->lock); + tp->deleting = idr_is_empty(&head->handle_idr); + spin_unlock(&tp->lock); + + return tp->deleting; +} + static struct tcf_proto_ops cls_fl_ops __read_mostly = { .kind = "flower", .classify = fl_classify, @@ -2782,6 +2793,7 @@ static struct tcf_proto_ops cls_fl_ops __read_mostly = { .put = fl_put, .change = fl_change, .delete = fl_delete, + .delete_empty = fl_delete_empty, .walk = fl_walk, .reoffload = fl_reoffload, .hw_add = fl_hw_add, diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 66c6bcec16cb..a0e6fac613de 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -1108,33 +1108,10 @@ erridr: return err; } -static bool u32_hnode_empty(struct tc_u_hnode *ht, bool *non_root_ht) -{ - int i; - - if (!ht) - return true; - if (!ht->is_root) { - *non_root_ht = true; - return false; - } - if (*non_root_ht) - return false; - if (ht->refcnt < 2) - return true; - - for (i = 0; i <= ht->divisor; i++) { - if (rtnl_dereference(ht->ht[i])) - return false; - } - return true; -} - static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg, bool rtnl_held) { struct tc_u_common *tp_c = tp->data; - bool non_root_ht = false; struct tc_u_hnode *ht; struct tc_u_knode *n; unsigned int h; @@ -1147,8 +1124,6 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg, ht = rtnl_dereference(ht->next)) { if (ht->prio != tp->prio) continue; - if (u32_hnode_empty(ht, &non_root_ht)) - return; if (arg->count >= arg->skip) { if (arg->fn(tp, ht, arg) < 0) { arg->stop = 1; diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index b1c7e726ce5d..ff4c5e9d0d77 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -301,6 +301,9 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) f->socket_hash != sk->sk_hash)) { f->credit = q->initial_quantum; f->socket_hash = sk->sk_hash; + if (q->rate_enable) + smp_store_release(&sk->sk_pacing_status, + SK_PACING_FQ); if (fq_flow_is_throttled(f)) fq_flow_unset_throttled(q, f); f->time_next_packet = 0ULL; @@ -322,8 +325,12 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) fq_flow_set_detached(f); f->sk = sk; - if (skb->sk == sk) + if (skb->sk == sk) { f->socket_hash = sk->sk_hash; + if (q->rate_enable) + smp_store_release(&sk->sk_pacing_status, + SK_PACING_FQ); + } f->credit = q->initial_quantum; rb_link_node(&f->fq_node, parent, p); @@ -428,17 +435,9 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, f->qlen++; qdisc_qstats_backlog_inc(sch, skb); if (fq_flow_is_detached(f)) { - struct sock *sk = skb->sk; - fq_flow_add_tail(&q->new_flows, f); if (time_after(jiffies, f->age + q->flow_refill_delay)) f->credit = max_t(u32, f->credit, q->quantum); - if (sk && q->rate_enable) { - if (unlikely(smp_load_acquire(&sk->sk_pacing_status) != - SK_PACING_FQ)) - smp_store_release(&sk->sk_pacing_status, - SK_PACING_FQ); - } q->inactive_flows--; } diff --git a/net/sctp/stream.c b/net/sctp/stream.c index e0b01bf912b3..67f7e71f9129 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -84,10 +84,8 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, return 0; ret = genradix_prealloc(&stream->out, outcnt, gfp); - if (ret) { - genradix_free(&stream->out); + if (ret) return ret; - } stream->outcnt = outcnt; return 0; @@ -102,10 +100,8 @@ static int sctp_stream_alloc_in(struct sctp_stream *stream, __u16 incnt, return 0; ret = genradix_prealloc(&stream->in, incnt, gfp); - if (ret) { - genradix_free(&stream->in); + if (ret) return ret; - } stream->incnt = incnt; return 0; @@ -123,7 +119,7 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, * a new one with new outcnt to save memory if needed. */ if (outcnt == stream->outcnt) - goto in; + goto handle_in; /* Filter out chunks queued on streams that won't exist anymore */ sched->unsched_all(stream); @@ -132,24 +128,28 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, ret = sctp_stream_alloc_out(stream, outcnt, gfp); if (ret) - goto out; + goto out_err; for (i = 0; i < stream->outcnt; i++) SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN; -in: +handle_in: sctp_stream_interleave_init(stream); if (!incnt) goto out; ret = sctp_stream_alloc_in(stream, incnt, gfp); - if (ret) { - sched->free(stream); - genradix_free(&stream->out); - stream->outcnt = 0; - goto out; - } + if (ret) + goto in_err; + + goto out; +in_err: + sched->free(stream); + genradix_free(&stream->in); +out_err: + genradix_free(&stream->out); + stream->outcnt = 0; out: return ret; } diff --git a/net/sctp/transport.c b/net/sctp/transport.c index f4de064598f8..806af58f4375 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -263,7 +263,7 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) pf->af->from_sk(&addr, sk); pf->to_sk_daddr(&t->ipaddr, sk); - dst->ops->update_pmtu(dst, sk, NULL, pmtu); + dst->ops->update_pmtu(dst, sk, NULL, pmtu, true); pf->to_sk_daddr(&addr, sk); dst = sctp_transport_dst_check(t); diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c index dd3d5942e669..c36bafbcd77e 100644 --- a/security/tomoyo/common.c +++ b/security/tomoyo/common.c @@ -951,7 +951,8 @@ static bool tomoyo_manager(void) exe = tomoyo_get_exe(); if (!exe) return false; - list_for_each_entry_rcu(ptr, &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER], head.list) { + list_for_each_entry_rcu(ptr, &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER], head.list, + srcu_read_lock_held(&tomoyo_ss)) { if (!ptr->head.is_deleted && (!tomoyo_pathcmp(domainname, ptr->manager) || !strcmp(exe, ptr->manager->name))) { @@ -1095,7 +1096,8 @@ static int tomoyo_delete_domain(char *domainname) if (mutex_lock_interruptible(&tomoyo_policy_lock)) return -EINTR; /* Is there an active domain? */ - list_for_each_entry_rcu(domain, &tomoyo_domain_list, list) { + list_for_each_entry_rcu(domain, &tomoyo_domain_list, list, + srcu_read_lock_held(&tomoyo_ss)) { /* Never delete tomoyo_kernel_domain */ if (domain == &tomoyo_kernel_domain) continue; @@ -2778,7 +2780,8 @@ void tomoyo_check_profile(void) tomoyo_policy_loaded = true; pr_info("TOMOYO: 2.6.0\n"); - list_for_each_entry_rcu(domain, &tomoyo_domain_list, list) { + list_for_each_entry_rcu(domain, &tomoyo_domain_list, list, + srcu_read_lock_held(&tomoyo_ss)) { const u8 profile = domain->profile; struct tomoyo_policy_namespace *ns = domain->ns; diff --git a/security/tomoyo/domain.c b/security/tomoyo/domain.c index 8526a0a74023..7869d6a9980b 100644 --- a/security/tomoyo/domain.c +++ b/security/tomoyo/domain.c @@ -41,7 +41,8 @@ int tomoyo_update_policy(struct tomoyo_acl_head *new_entry, const int size, if (mutex_lock_interruptible(&tomoyo_policy_lock)) return -ENOMEM; - list_for_each_entry_rcu(entry, list, list) { + list_for_each_entry_rcu(entry, list, list, + srcu_read_lock_held(&tomoyo_ss)) { if (entry->is_deleted == TOMOYO_GC_IN_PROGRESS) continue; if (!check_duplicate(entry, new_entry)) @@ -119,7 +120,8 @@ int tomoyo_update_domain(struct tomoyo_acl_info *new_entry, const int size, } if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; - list_for_each_entry_rcu(entry, list, list) { + list_for_each_entry_rcu(entry, list, list, + srcu_read_lock_held(&tomoyo_ss)) { if (entry->is_deleted == TOMOYO_GC_IN_PROGRESS) continue; if (!tomoyo_same_acl_head(entry, new_entry) || @@ -166,7 +168,8 @@ void tomoyo_check_acl(struct tomoyo_request_info *r, u16 i = 0; retry: - list_for_each_entry_rcu(ptr, list, list) { + list_for_each_entry_rcu(ptr, list, list, + srcu_read_lock_held(&tomoyo_ss)) { if (ptr->is_deleted || ptr->type != r->param_type) continue; if (!check_entry(r, ptr)) @@ -298,7 +301,8 @@ static inline bool tomoyo_scan_transition { const struct tomoyo_transition_control *ptr; - list_for_each_entry_rcu(ptr, list, head.list) { + list_for_each_entry_rcu(ptr, list, head.list, + srcu_read_lock_held(&tomoyo_ss)) { if (ptr->head.is_deleted || ptr->type != type) continue; if (ptr->domainname) { @@ -735,7 +739,8 @@ retry: /* Check 'aggregator' directive. */ candidate = &exename; - list_for_each_entry_rcu(ptr, list, head.list) { + list_for_each_entry_rcu(ptr, list, head.list, + srcu_read_lock_held(&tomoyo_ss)) { if (ptr->head.is_deleted || !tomoyo_path_matches_pattern(&exename, ptr->original_name)) diff --git a/security/tomoyo/group.c b/security/tomoyo/group.c index a37c7dc66e44..1cecdd797597 100644 --- a/security/tomoyo/group.c +++ b/security/tomoyo/group.c @@ -133,7 +133,8 @@ tomoyo_path_matches_group(const struct tomoyo_path_info *pathname, { struct tomoyo_path_group *member; - list_for_each_entry_rcu(member, &group->member_list, head.list) { + list_for_each_entry_rcu(member, &group->member_list, head.list, + srcu_read_lock_held(&tomoyo_ss)) { if (member->head.is_deleted) continue; if (!tomoyo_path_matches_pattern(pathname, member->member_name)) @@ -161,7 +162,8 @@ bool tomoyo_number_matches_group(const unsigned long min, struct tomoyo_number_group *member; bool matched = false; - list_for_each_entry_rcu(member, &group->member_list, head.list) { + list_for_each_entry_rcu(member, &group->member_list, head.list, + srcu_read_lock_held(&tomoyo_ss)) { if (member->head.is_deleted) continue; if (min > member->number.values[1] || @@ -191,7 +193,8 @@ bool tomoyo_address_matches_group(const bool is_ipv6, const __be32 *address, bool matched = false; const u8 size = is_ipv6 ? 16 : 4; - list_for_each_entry_rcu(member, &group->member_list, head.list) { + list_for_each_entry_rcu(member, &group->member_list, head.list, + srcu_read_lock_held(&tomoyo_ss)) { if (member->head.is_deleted) continue; if (member->address.is_ipv6 != is_ipv6) diff --git a/security/tomoyo/realpath.c b/security/tomoyo/realpath.c index e7832448d721..bf38fc1b59b2 100644 --- a/security/tomoyo/realpath.c +++ b/security/tomoyo/realpath.c @@ -218,31 +218,6 @@ out: } /** - * tomoyo_get_socket_name - Get the name of a socket. - * - * @path: Pointer to "struct path". - * @buffer: Pointer to buffer to return value in. - * @buflen: Sizeof @buffer. - * - * Returns the buffer. - */ -static char *tomoyo_get_socket_name(const struct path *path, char * const buffer, - const int buflen) -{ - struct inode *inode = d_backing_inode(path->dentry); - struct socket *sock = inode ? SOCKET_I(inode) : NULL; - struct sock *sk = sock ? sock->sk : NULL; - - if (sk) { - snprintf(buffer, buflen, "socket:[family=%u:type=%u:protocol=%u]", - sk->sk_family, sk->sk_type, sk->sk_protocol); - } else { - snprintf(buffer, buflen, "socket:[unknown]"); - } - return buffer; -} - -/** * tomoyo_realpath_from_path - Returns realpath(3) of the given pathname but ignores chroot'ed root. * * @path: Pointer to "struct path". @@ -279,12 +254,7 @@ char *tomoyo_realpath_from_path(const struct path *path) break; /* To make sure that pos is '\0' terminated. */ buf[buf_len - 1] = '\0'; - /* Get better name for socket. */ - if (sb->s_magic == SOCKFS_MAGIC) { - pos = tomoyo_get_socket_name(path, buf, buf_len - 1); - goto encode; - } - /* For "pipe:[\$]". */ + /* For "pipe:[\$]" and "socket:[\$]". */ if (dentry->d_op && dentry->d_op->d_dname) { pos = dentry->d_op->d_dname(dentry, buf, buf_len - 1); goto encode; diff --git a/security/tomoyo/util.c b/security/tomoyo/util.c index 52752e1a84ed..eba0b3395851 100644 --- a/security/tomoyo/util.c +++ b/security/tomoyo/util.c @@ -594,7 +594,8 @@ struct tomoyo_domain_info *tomoyo_find_domain(const char *domainname) name.name = domainname; tomoyo_fill_path_info(&name); - list_for_each_entry_rcu(domain, &tomoyo_domain_list, list) { + list_for_each_entry_rcu(domain, &tomoyo_domain_list, list, + srcu_read_lock_held(&tomoyo_ss)) { if (!domain->is_deleted && !tomoyo_pathcmp(&name, domain->domainname)) return domain; @@ -1028,7 +1029,8 @@ bool tomoyo_domain_quota_is_ok(struct tomoyo_request_info *r) return false; if (!domain) return true; - list_for_each_entry_rcu(ptr, &domain->acl_info_list, list) { + list_for_each_entry_rcu(ptr, &domain->acl_info_list, list, + srcu_read_lock_held(&tomoyo_ss)) { u16 perm; u8 i; diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index d4790121adf4..d87830e7ea63 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -138,6 +138,7 @@ STATIC_OBJDIR := $(OUTPUT)staticobjs/ BPF_IN_SHARED := $(SHARED_OBJDIR)libbpf-in.o BPF_IN_STATIC := $(STATIC_OBJDIR)libbpf-in.o VERSION_SCRIPT := libbpf.map +BPF_HELPER_DEFS := $(OUTPUT)bpf_helper_defs.h LIB_TARGET := $(addprefix $(OUTPUT),$(LIB_TARGET)) LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE)) @@ -160,7 +161,7 @@ all: fixdep all_cmd: $(CMD_TARGETS) check -$(BPF_IN_SHARED): force elfdep zdep bpfdep bpf_helper_defs.h +$(BPF_IN_SHARED): force elfdep zdep bpfdep $(BPF_HELPER_DEFS) @(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \ (diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \ echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'" >&2 )) || true @@ -178,12 +179,12 @@ $(BPF_IN_SHARED): force elfdep zdep bpfdep bpf_helper_defs.h echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)" -$(BPF_IN_STATIC): force elfdep zdep bpfdep bpf_helper_defs.h +$(BPF_IN_STATIC): force elfdep zdep bpfdep $(BPF_HELPER_DEFS) $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR) -bpf_helper_defs.h: $(srctree)/tools/include/uapi/linux/bpf.h +$(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h $(Q)$(srctree)/scripts/bpf_helpers_doc.py --header \ - --file $(srctree)/tools/include/uapi/linux/bpf.h > bpf_helper_defs.h + --file $(srctree)/tools/include/uapi/linux/bpf.h > $(BPF_HELPER_DEFS) $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION) @@ -245,7 +246,7 @@ install_lib: all_cmd $(call do_install_mkdir,$(libdir_SQ)); \ cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ) -install_headers: bpf_helper_defs.h +install_headers: $(BPF_HELPER_DEFS) $(call QUIET_INSTALL, headers) \ $(call do_install,bpf.h,$(prefix)/include/bpf,644); \ $(call do_install,libbpf.h,$(prefix)/include/bpf,644); \ @@ -254,7 +255,7 @@ install_headers: bpf_helper_defs.h $(call do_install,libbpf_common.h,$(prefix)/include/bpf,644); \ $(call do_install,xsk.h,$(prefix)/include/bpf,644); \ $(call do_install,bpf_helpers.h,$(prefix)/include/bpf,644); \ - $(call do_install,bpf_helper_defs.h,$(prefix)/include/bpf,644); \ + $(call do_install,$(BPF_HELPER_DEFS),$(prefix)/include/bpf,644); \ $(call do_install,bpf_tracing.h,$(prefix)/include/bpf,644); \ $(call do_install,bpf_endian.h,$(prefix)/include/bpf,644); \ $(call do_install,bpf_core_read.h,$(prefix)/include/bpf,644); @@ -274,7 +275,7 @@ config-clean: clean: $(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS) \ *.o *~ *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) .*.d .*.cmd \ - *.pc LIBBPF-CFLAGS bpf_helper_defs.h \ + *.pc LIBBPF-CFLAGS $(BPF_HELPER_DEFS) \ $(SHARED_OBJDIR) $(STATIC_OBJDIR) $(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index efe06d621983..e59eb9e7f923 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -31,15 +31,12 @@ class KunitStatus(Enum): TEST_FAILURE = auto() def create_default_kunitconfig(): - if not os.path.exists(kunit_kernel.KUNITCONFIG_PATH): + if not os.path.exists(kunit_kernel.kunitconfig_path): shutil.copyfile('arch/um/configs/kunit_defconfig', - kunit_kernel.KUNITCONFIG_PATH) + kunit_kernel.kunitconfig_path) def run_tests(linux: kunit_kernel.LinuxSourceTree, request: KunitRequest) -> KunitResult: - if request.defconfig: - create_default_kunitconfig() - config_start = time.time() success = linux.build_reconfig(request.build_dir) config_end = time.time() @@ -108,15 +105,22 @@ def main(argv, linux=None): run_parser.add_argument('--build_dir', help='As in the make command, it specifies the build ' 'directory.', - type=str, default=None, metavar='build_dir') + type=str, default='', metavar='build_dir') run_parser.add_argument('--defconfig', - help='Uses a default kunitconfig.', + help='Uses a default .kunitconfig.', action='store_true') cli_args = parser.parse_args(argv) if cli_args.subcommand == 'run': + if cli_args.build_dir: + if not os.path.exists(cli_args.build_dir): + os.mkdir(cli_args.build_dir) + kunit_kernel.kunitconfig_path = os.path.join( + cli_args.build_dir, + kunit_kernel.kunitconfig_path) + if cli_args.defconfig: create_default_kunitconfig() diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index bf3876835331..cc5d844ecca1 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -14,7 +14,7 @@ import os import kunit_config KCONFIG_PATH = '.config' -KUNITCONFIG_PATH = 'kunitconfig' +kunitconfig_path = '.kunitconfig' class ConfigError(Exception): """Represents an error trying to configure the Linux kernel.""" @@ -82,7 +82,7 @@ class LinuxSourceTree(object): def __init__(self): self._kconfig = kunit_config.Kconfig() - self._kconfig.read_from_file(KUNITCONFIG_PATH) + self._kconfig.read_from_file(kunitconfig_path) self._ops = LinuxSourceTreeOperations() def clean(self): @@ -111,7 +111,7 @@ class LinuxSourceTree(object): return True def build_reconfig(self, build_dir): - """Creates a new .config if it is not a subset of the kunitconfig.""" + """Creates a new .config if it is not a subset of the .kunitconfig.""" kconfig_path = get_kconfig_path(build_dir) if os.path.exists(kconfig_path): existing_kconfig = kunit_config.Kconfig() @@ -140,10 +140,10 @@ class LinuxSourceTree(object): return False return True - def run_kernel(self, args=[], timeout=None, build_dir=None): + def run_kernel(self, args=[], timeout=None, build_dir=''): args.extend(['mem=256M']) process = self._ops.linux_bin(args, timeout, build_dir) - with open('test.log', 'w') as f: + with open(os.path.join(build_dir, 'test.log'), 'w') as f: for line in process.stdout: f.write(line.rstrip().decode('ascii') + '\n') yield line.rstrip().decode('ascii') diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index a2a8ea6beae3..cba97756ac4a 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -174,6 +174,7 @@ class KUnitMainTest(unittest.TestCase): kunit.main(['run'], self.linux_source_mock) assert self.linux_source_mock.build_reconfig.call_count == 1 assert self.linux_source_mock.run_kernel.call_count == 1 + self.linux_source_mock.run_kernel.assert_called_once_with(build_dir='', timeout=300) self.print_mock.assert_any_call(StrContains('Testing complete.')) def test_run_passes_args_fail(self): @@ -199,7 +200,14 @@ class KUnitMainTest(unittest.TestCase): timeout = 3453 kunit.main(['run', '--timeout', str(timeout)], self.linux_source_mock) assert self.linux_source_mock.build_reconfig.call_count == 1 - self.linux_source_mock.run_kernel.assert_called_once_with(build_dir=None, timeout=timeout) + self.linux_source_mock.run_kernel.assert_called_once_with(build_dir='', timeout=timeout) + self.print_mock.assert_any_call(StrContains('Testing complete.')) + + def test_run_builddir(self): + build_dir = '.kunit' + kunit.main(['run', '--build_dir', build_dir], self.linux_source_mock) + assert self.linux_source_mock.build_reconfig.call_count == 1 + self.linux_source_mock.run_kernel.assert_called_once_with(build_dir=build_dir, timeout=300) self.print_mock.assert_any_call(StrContains('Testing complete.')) if __name__ == '__main__': diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index b139b3d75ebb..301ac12d5d69 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -41,3 +41,4 @@ test_cpp /no_alu32 /bpf_gcc /tools +bpf_helper_defs.h diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 41691fb067da..f1f949cd8ed9 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -151,9 +151,9 @@ $(DEFAULT_BPFTOOL): force $(BPFOBJ): force $(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/ -BPF_HELPERS := $(BPFDIR)/bpf_helper_defs.h $(wildcard $(BPFDIR)/bpf_*.h) -$(BPFDIR)/bpf_helper_defs.h: - $(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/ bpf_helper_defs.h +BPF_HELPERS := $(OUTPUT)/bpf_helper_defs.h $(wildcard $(BPFDIR)/bpf_*.h) +$(OUTPUT)/bpf_helper_defs.h: + $(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/ $(OUTPUT)/bpf_helper_defs.h # Get Clang's default includes on this system, as opposed to those seen by # '-target bpf'. This fixes "missing" files on some architectures/distros, diff --git a/tools/testing/selftests/filesystems/epoll/Makefile b/tools/testing/selftests/filesystems/epoll/Makefile index e62f3d4f68da..78ae4aaf7141 100644 --- a/tools/testing/selftests/filesystems/epoll/Makefile +++ b/tools/testing/selftests/filesystems/epoll/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += -I../../../../../usr/include/ -LDFLAGS += -lpthread +LDLIBS += -lpthread TEST_GEN_PROGS := epoll_wakeup_test include ../../lib.mk diff --git a/tools/testing/selftests/firmware/fw_lib.sh b/tools/testing/selftests/firmware/fw_lib.sh index b879305a766d..5b8c0fedee76 100755 --- a/tools/testing/selftests/firmware/fw_lib.sh +++ b/tools/testing/selftests/firmware/fw_lib.sh @@ -34,6 +34,12 @@ test_modprobe() check_mods() { + local uid=$(id -u) + if [ $uid -ne 0 ]; then + echo "skip all tests: must be run as root" >&2 + exit $ksft_skip + fi + trap "test_modprobe" EXIT if [ ! -d $DIR ]; then modprobe test_firmware diff --git a/tools/testing/selftests/livepatch/functions.sh b/tools/testing/selftests/livepatch/functions.sh index 31eb09e38729..a6e3d5517a6f 100644 --- a/tools/testing/selftests/livepatch/functions.sh +++ b/tools/testing/selftests/livepatch/functions.sh @@ -7,6 +7,9 @@ MAX_RETRIES=600 RETRY_INTERVAL=".1" # seconds +# Kselftest framework requirement - SKIP code is 4 +ksft_skip=4 + # log(msg) - write message to kernel log # msg - insightful words function log() { @@ -18,7 +21,16 @@ function log() { function skip() { log "SKIP: $1" echo "SKIP: $1" >&2 - exit 4 + exit $ksft_skip +} + +# root test +function is_root() { + uid=$(id -u) + if [ $uid -ne 0 ]; then + echo "skip all tests: must be run as root" >&2 + exit $ksft_skip + fi } # die(msg) - game over, man @@ -62,6 +74,7 @@ function set_ftrace_enabled() { # for verbose livepatching output and turn on # the ftrace_enabled sysctl. function setup_config() { + is_root push_config set_dynamic_debug set_ftrace_enabled 1 diff --git a/tools/testing/selftests/livepatch/test-state.sh b/tools/testing/selftests/livepatch/test-state.sh index dc2908c22c26..a08212708115 100755 --- a/tools/testing/selftests/livepatch/test-state.sh +++ b/tools/testing/selftests/livepatch/test-state.sh @@ -8,8 +8,7 @@ MOD_LIVEPATCH=test_klp_state MOD_LIVEPATCH2=test_klp_state2 MOD_LIVEPATCH3=test_klp_state3 -set_dynamic_debug - +setup_config # TEST: Loading and removing a module that modifies the system state diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh index 16571ac1dab4..d3e0809ab368 100755 --- a/tools/testing/selftests/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/netfilter/nft_flowtable.sh @@ -226,17 +226,19 @@ check_transfer() return 0 } -test_tcp_forwarding() +test_tcp_forwarding_ip() { local nsa=$1 local nsb=$2 + local dstip=$3 + local dstport=$4 local lret=0 ip netns exec $nsb nc -w 5 -l -p 12345 < "$ns2in" > "$ns2out" & lpid=$! sleep 1 - ip netns exec $nsa nc -w 4 10.0.2.99 12345 < "$ns1in" > "$ns1out" & + ip netns exec $nsa nc -w 4 "$dstip" "$dstport" < "$ns1in" > "$ns1out" & cpid=$! sleep 3 @@ -258,6 +260,28 @@ test_tcp_forwarding() return $lret } +test_tcp_forwarding() +{ + test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345 + + return $? +} + +test_tcp_forwarding_nat() +{ + local lret + + test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345 + lret=$? + + if [ $lret -eq 0 ] ; then + test_tcp_forwarding_ip "$1" "$2" 10.6.6.6 1666 + lret=$? + fi + + return $lret +} + make_file "$ns1in" "ns1" make_file "$ns2in" "ns2" @@ -283,14 +307,19 @@ ip -net ns2 route add 192.168.10.1 via 10.0.2.1 # Same, but with NAT enabled. ip netns exec nsr1 nft -f - <<EOF table ip nat { + chain prerouting { + type nat hook prerouting priority 0; policy accept; + meta iif "veth0" ip daddr 10.6.6.6 tcp dport 1666 counter dnat ip to 10.0.2.99:12345 + } + chain postrouting { type nat hook postrouting priority 0; policy accept; - meta oifname "veth1" masquerade + meta oifname "veth1" counter masquerade } } EOF -test_tcp_forwarding ns1 ns2 +test_tcp_forwarding_nat ns1 ns2 if [ $? -eq 0 ] ;then echo "PASS: flow offloaded for ns1/ns2 with NAT" @@ -313,7 +342,7 @@ fi ip netns exec ns1 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null ip netns exec ns2 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null -test_tcp_forwarding ns1 ns2 +test_tcp_forwarding_nat ns1 ns2 if [ $? -eq 0 ] ;then echo "PASS: flow offloaded for ns1/ns2 with NAT and pmtu discovery" else diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c index eec2663261f2..e8a657a5f48a 100644 --- a/tools/testing/selftests/rseq/param_test.c +++ b/tools/testing/selftests/rseq/param_test.c @@ -15,7 +15,7 @@ #include <errno.h> #include <stddef.h> -static inline pid_t gettid(void) +static inline pid_t rseq_gettid(void) { return syscall(__NR_gettid); } @@ -373,11 +373,12 @@ void *test_percpu_spinlock_thread(void *arg) rseq_percpu_unlock(&data->lock, cpu); #ifndef BENCHMARK if (i != 0 && !(i % (reps / 10))) - printf_verbose("tid %d: count %lld\n", (int) gettid(), i); + printf_verbose("tid %d: count %lld\n", + (int) rseq_gettid(), i); #endif } printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n", - (int) gettid(), nr_abort, signals_delivered); + (int) rseq_gettid(), nr_abort, signals_delivered); if (!opt_disable_rseq && thread_data->reg && rseq_unregister_current_thread()) abort(); @@ -454,11 +455,12 @@ void *test_percpu_inc_thread(void *arg) } while (rseq_unlikely(ret)); #ifndef BENCHMARK if (i != 0 && !(i % (reps / 10))) - printf_verbose("tid %d: count %lld\n", (int) gettid(), i); + printf_verbose("tid %d: count %lld\n", + (int) rseq_gettid(), i); #endif } printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n", - (int) gettid(), nr_abort, signals_delivered); + (int) rseq_gettid(), nr_abort, signals_delivered); if (!opt_disable_rseq && thread_data->reg && rseq_unregister_current_thread()) abort(); @@ -605,7 +607,7 @@ void *test_percpu_list_thread(void *arg) } printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n", - (int) gettid(), nr_abort, signals_delivered); + (int) rseq_gettid(), nr_abort, signals_delivered); if (!opt_disable_rseq && rseq_unregister_current_thread()) abort(); @@ -796,7 +798,7 @@ void *test_percpu_buffer_thread(void *arg) } printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n", - (int) gettid(), nr_abort, signals_delivered); + (int) rseq_gettid(), nr_abort, signals_delivered); if (!opt_disable_rseq && rseq_unregister_current_thread()) abort(); @@ -1011,7 +1013,7 @@ void *test_percpu_memcpy_buffer_thread(void *arg) } printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n", - (int) gettid(), nr_abort, signals_delivered); + (int) rseq_gettid(), nr_abort, signals_delivered); if (!opt_disable_rseq && rseq_unregister_current_thread()) abort(); diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h index d40d60e7499e..3f63eb362b92 100644 --- a/tools/testing/selftests/rseq/rseq.h +++ b/tools/testing/selftests/rseq/rseq.h @@ -149,11 +149,13 @@ static inline void rseq_clear_rseq_cs(void) /* * rseq_prepare_unload() should be invoked by each thread executing a rseq * critical section at least once between their last critical section and - * library unload of the library defining the rseq critical section - * (struct rseq_cs). This also applies to use of rseq in code generated by - * JIT: rseq_prepare_unload() should be invoked at least once by each - * thread executing a rseq critical section before reclaim of the memory - * holding the struct rseq_cs. + * library unload of the library defining the rseq critical section (struct + * rseq_cs) or the code referred to by the struct rseq_cs start_ip and + * post_commit_offset fields. This also applies to use of rseq in code + * generated by JIT: rseq_prepare_unload() should be invoked at least once by + * each thread executing a rseq critical section before reclaim of the memory + * holding the struct rseq_cs or reclaim of the code pointed to by struct + * rseq_cs start_ip and post_commit_offset fields. */ static inline void rseq_prepare_unload(void) { diff --git a/tools/testing/selftests/rseq/settings b/tools/testing/selftests/rseq/settings new file mode 100644 index 000000000000..e7b9417537fb --- /dev/null +++ b/tools/testing/selftests/rseq/settings @@ -0,0 +1 @@ +timeout=0 |