diff --git a/Documentation/dev-tools/kunit/start.rst b/Documentation/dev-tools/kunit/start.rst
index 9d6db89..4e1d24d 100644
--- a/Documentation/dev-tools/kunit/start.rst
+++ b/Documentation/dev-tools/kunit/start.rst
@@ -24,19 +24,16 @@
 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 @@
 
 	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/MAINTAINERS b/MAINTAINERS
index ffa3371..e09bd92 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7034,6 +7034,7 @@
 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>
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index 6ca015f..3ed7a0f 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 @@
 	 * 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 @@
 	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 f41744b..66a570d 100644
--- a/drivers/ata/ahci_brcm.c
+++ b/drivers/ata/ahci_brcm.c
@@ -76,8 +76,7 @@
 };
 
 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 @@
 			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 @@
 	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 @@
 	/* 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 @@
 	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 @@
 	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 @@
 	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;
-		priv->quirks |= BRCM_AHCI_QUIRK_SKIP_PHY_ENABLE;
+	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 @@
 	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 8befce0..129556f 100644
--- a/drivers/ata/libahci_platform.c
+++ b/drivers/ata/libahci_platform.c
@@ -43,7 +43,7 @@
  * 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 @@
 	}
 	return rc;
 }
+EXPORT_SYMBOL_GPL(ahci_platform_enable_phys);
 
 /**
  * ahci_platform_disable_phys - Disable PHYs
@@ -81,7 +82,7 @@
  *
  * 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 @@
 		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 e9017c5..6f4ab5c 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -5329,6 +5329,30 @@
 }
 
 /**
+ *	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 9239615..d55ee24 100644
--- a/drivers/ata/sata_fsl.c
+++ b/drivers/ata/sata_fsl.c
@@ -1280,7 +1280,7 @@
 				     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 277f119..d7228f8 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -2829,7 +2829,7 @@
 	}
 
 	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 f3e62f5..eb9dc14e 100644
--- a/drivers/ata/sata_nv.c
+++ b/drivers/ata/sata_nv.c
@@ -984,7 +984,7 @@
 					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 ee67bf9..861fc65 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2707,7 +2707,7 @@
 	.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 defe1d4..3553583 100644
--- a/drivers/devfreq/Kconfig
+++ b/drivers/devfreq/Kconfig
@@ -83,7 +83,6 @@
 	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 @@
 		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 @@
 	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 @@
 	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 8adffd4..6ab25fe 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -553,8 +553,8 @@
 
 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 7e99860..8319812 100644
--- a/drivers/gpio/gpio-aspeed-sgpio.c
+++ b/drivers/gpio/gpio-aspeed-sgpio.c
@@ -107,7 +107,7 @@
 		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 56d647a..c4fdc19 100644
--- a/drivers/gpio/gpio-mockup.c
+++ b/drivers/gpio/gpio-mockup.c
@@ -226,7 +226,7 @@
 	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 @@
 	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 @@
 	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 f1e164c..5ae30de 100644
--- a/drivers/gpio/gpio-mpc8xxx.c
+++ b/drivers/gpio/gpio-mpc8xxx.c
@@ -346,6 +346,7 @@
 		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 6652bee..9853547 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -568,16 +568,18 @@
 {
 	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 @@
 {
 	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 @@
 		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 @@
 {
 	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 773e5c2..b21c2e4 100644
--- a/drivers/gpio/gpio-xgs-iproc.c
+++ b/drivers/gpio/gpio-xgs-iproc.c
@@ -280,7 +280,7 @@
 	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 08d7c3b..c8af34a 100644
--- a/drivers/gpio/gpio-xtensa.c
+++ b/drivers/gpio/gpio-xtensa.c
@@ -44,15 +44,14 @@
 	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 9913886..78a16e4 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -220,6 +220,14 @@
 	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 @@
 
 		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 6f5e3bd..effc425 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -15112,7 +15112,7 @@
 		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 84b164f..6cb02c9 100644
--- a/drivers/gpu/drm/i915/display/intel_frontbuffer.c
+++ b/drivers/gpu/drm/i915/display/intel_frontbuffer.c
@@ -229,11 +229,11 @@
 		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 @@
 	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 @@
 			 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 adc64d6..6d41f53 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 @@
 	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(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 @@
 			     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 848ce07..8a98a1a 100644
--- a/drivers/gpu/drm/i915/display/intel_overlay.c
+++ b/drivers/gpu/drm/i915/display/intel_overlay.c
@@ -279,12 +279,21 @@
 				       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 @@
 		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 b9f504b..18ee708 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 @@
 {
 	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 9937b4c..f86400a 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_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 @@
 	}
 
 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 a50296c..a596548 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 @@
 		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 @@
 	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 458cd51..4b93591 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 @@
 				  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 96008374..e3f3944 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 @@
 	 */
 	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 a459a42..7e64b7d 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 @@
 		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 d034fa41..905890e3 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -161,7 +161,7 @@
 	 * 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 @@
 	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 @@
 		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 @@
 		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 @@
 		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 2814218..6f09aa0 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -144,61 +144,40 @@
 	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 @@
 	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 void park_rc6(struct drm_i915_private *i915) {}
-static void unpark_rc6(struct drm_i915_private *i915) {}
 
 #endif
 
@@ -281,8 +250,6 @@
 	 */
 	__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 bf52e39..6c1647c 100644
--- a/drivers/gpu/drm/i915/i915_pmu.h
+++ b/drivers/gpu/drm/i915/i915_pmu.h
@@ -18,7 +18,7 @@
 	__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 e5512f2..01c8222 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -1104,8 +1104,14 @@
 		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/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c
index c4e4b01..4bc794d 100644
--- a/drivers/scsi/cxgbi/libcxgbi.c
+++ b/drivers/scsi/cxgbi/libcxgbi.c
@@ -121,7 +121,8 @@
 		"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 2e6a68d..a5ecbce 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -5385,7 +5385,6 @@
 	.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 @@
 	.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 6298b17..6a04fdb 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -5883,7 +5883,7 @@
 			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 c82b579..625c046 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -8555,7 +8555,7 @@
 	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 @@
 		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_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 @@
  * @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 848fbec..45fd8df 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -5248,7 +5248,6 @@
 					&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 6949ea8..51ffd5c 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -646,7 +646,9 @@
 	}
 
 	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 ce9bac7..40705e8 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -1693,6 +1693,7 @@
 	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 3925a7b..d17587c 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -139,6 +139,28 @@
 	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 @@
 	 * 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 @@
 	}
 }
 
+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 @@
 				       (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 8b0b512..afe1f03 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -67,7 +67,7 @@
 		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/io-wq.c b/fs/io-wq.c
index 11e80b7..541c8a3 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -92,7 +92,6 @@
 	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 @@
 	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 @@
 {
 	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 @@
 		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 @@
 
 	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 @@
 		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 6f084e3..562e3a1 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -330,6 +330,26 @@
 	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_ctx {
-	struct io_uring_sqe		sqe;
 	union {
 		struct io_async_rw	rw;
 		struct io_async_msghdr	msg;
@@ -369,15 +388,16 @@
 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 @@
 #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 @@
 {
 	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 @@
 
 	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 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(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 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 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 @@
 
 		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 @@
 	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 @@
 			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 @@
 		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 @@
 	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_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 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 @@
 	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 @@
 	 * 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 @@
 	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 @@
 		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 @@
 		 * 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 @@
 	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 @@
 
 	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 @@
 	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 @@
 		    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 @@
 	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 @@
 	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 @@
 	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 @@
 			      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 @@
 }
 #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;
 
-	flags = READ_ONCE(sqe->msg_flags);
-	msg = (struct user_msghdr __user *)(unsigned long) READ_ONCE(sqe->addr);
+	sr->msg_flags = READ_ONCE(sqe->msg_flags);
+	sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr));
+
+	if (!io)
+		return 0;
+
 	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 @@
 		      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 @@
 		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 @@
 				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 @@
 			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 @@
 #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;
 
-	flags = READ_ONCE(sqe->msg_flags);
-	msg = (struct user_msghdr __user *)(unsigned long) READ_ONCE(sqe->addr);
+	sr->msg_flags = READ_ONCE(sqe->msg_flags);
+	sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr));
+
+	if (!io)
+		return 0;
+
 	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 @@
 		      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 @@
 
 	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 @@
 				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 @@
 			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 @@
 #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 @@
 #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 @@
 #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;
 
-	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);
+	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;
+
+	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 @@
 		      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 @@
 	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 @@
 		return -EINVAL;
 
 	req->poll.addr = READ_ONCE(sqe->addr);
-	req->flags |= REQ_F_PREPPED;
 	return 0;
 }
 
@@ -2540,10 +2549,6 @@
 	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 @@
 	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 @@
 	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 @@
 	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 @@
 	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 @@
 	if (req->timeout.flags)
 		return -EINVAL;
 
-	req->flags |= REQ_F_PREPPED;
 	return 0;
 }
 
@@ -2860,10 +2852,6 @@
 	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 @@
 	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 @@
 	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(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 @@
 	 * 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 @@
 	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(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 @@
 		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 @@
 	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 @@
 	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 @@
 	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 @@
 		ret = io_nop(req);
 		break;
 	case IORING_OP_READV:
-		if (unlikely(req->sqe->buf_index))
-			return -EINVAL;
+	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:
-		if (unlikely(req->sqe->buf_index))
-			return -EINVAL;
-		ret = io_write(req, nxt, force_nonblock);
-		break;
-	case IORING_OP_READ_FIXED:
-		ret = io_read(req, nxt, force_nonblock);
-		break;
 	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 @@
 		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 @@
 	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 @@
 	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 @@
 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 @@
 	}
 }
 
-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 @@
 	}
 	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 @@
 			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 @@
 		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 @@
 	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 @@
 			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 @@
 		}
 		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 @@
 }
 
 /*
- * 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 @@
 		 * 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 @@
 	}
 
 	for (i = 0; i < nr; i++) {
+		const struct io_uring_sqe *sqe;
 		struct io_kiocb *req;
 		unsigned int sqe_flags;
 
@@ -3762,7 +3782,7 @@
 				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 @@
 		}
 
 		submitted++;
-		sqe_flags = req->sqe->flags;
+		sqe_flags = sqe->flags;
 
 		req->ring_file = ring_file;
 		req->ring_fd = ring_fd;
@@ -3784,7 +3804,7 @@
 		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 @@
 		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 6970f55..44b6da0 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -2853,7 +2853,7 @@
 	}
 	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/include/linux/ahci_platform.h b/include/linux/ahci_platform.h
index 6782f0d..49e5383 100644
--- a/include/linux/ahci_platform.h
+++ b/include/linux/ahci_platform.h
@@ -19,6 +19,8 @@
 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 d3bbfdd..2dbde11 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1175,6 +1175,7 @@
 					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/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py
index efe06d6..e59eb9e 100755
--- a/tools/testing/kunit/kunit.py
+++ b/tools/testing/kunit/kunit.py
@@ -31,15 +31,12 @@
 	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 @@
 	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 bf38768..cc5d844 100644
--- a/tools/testing/kunit/kunit_kernel.py
+++ b/tools/testing/kunit/kunit_kernel.py
@@ -14,7 +14,7 @@
 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 @@
 
 	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 @@
 		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 @@
 			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 a2a8ea6..cba9775 100755
--- a/tools/testing/kunit/kunit_tool_test.py
+++ b/tools/testing/kunit/kunit_tool_test.py
@@ -174,6 +174,7 @@
 		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 @@
 		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/filesystems/epoll/Makefile b/tools/testing/selftests/filesystems/epoll/Makefile
index e62f3d4..78ae4aa 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 b879305..5b8c0fe 100755
--- a/tools/testing/selftests/firmware/fw_lib.sh
+++ b/tools/testing/selftests/firmware/fw_lib.sh
@@ -34,6 +34,12 @@
 
 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 31eb09e..a6e3d55 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 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 @@
 #		 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 dc2908c..a082127 100755
--- a/tools/testing/selftests/livepatch/test-state.sh
+++ b/tools/testing/selftests/livepatch/test-state.sh
@@ -8,8 +8,7 @@
 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/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c
index eec2663..e8a657a 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 @@
 		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 @@
 		} 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 @@
 	}
 
 	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 @@
 	}
 
 	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 @@
 	}
 
 	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 d40d60e..3f63eb3 100644
--- a/tools/testing/selftests/rseq/rseq.h
+++ b/tools/testing/selftests/rseq/rseq.h
@@ -149,11 +149,13 @@
 /*
  * 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 0000000..e7b9417
--- /dev/null
+++ b/tools/testing/selftests/rseq/settings
@@ -0,0 +1 @@
+timeout=0