virtio_blk: set the zone write granularitygrafted

virtblk_read_zoned_limits() reads the write granularity that the device
reports in virtio_blk_zoned_characteristics and assigns it to the
physical block size and to io_min, but never to the limit that is named
after it. queue_limits.zone_write_granularity is left at zero, so
blk_validate_zoned_limits() raises it to the logical block size:

	if (lim->zone_write_granularity < lim->logical_block_size)
		lim->zone_write_granularity = lim->logical_block_size;

A device that reports a granularity coarser than its logical block size,
which is what the field exists to express, therefore has it silently
reduced. A 512e host managed disk passed through to a guest reports a
logical block size of 512 and a write granularity of 4096, and the guest
ends up with a zone write granularity of 512.

bio_split_alignment() returns lim->zone_write_granularity if it is non-zero
and bio_split_io_at() may split a bio with as per bio_split_alignment().
This can real to the write getting rejected by the host drive, as the write
is not aligned to the physical block size.

zonefs also takes its block size from bdev_zone_write_granularity(), so it
would incorrectly use 512 on a disk that requires 4096.

sd_zbc_read_zones() sets the limit from the physical block size for the
same reason. NVMe ZNS and null_blk leave it unset, but the fallback
gives the right answer for them, as their write granularity is the
logical block size. virtio carries a separate value that may exceed it.

Set the zone write granularity from the value that the device reports.

Fixes: 95bfec41bd3d ("virtio-blk: add support for zoned block devices")
Signed-off-by: Niklas Cassel <cassel@kernel.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Link: https://patch.msgid.link/20260918140641.2031075-2-cassel@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>

12 files changed, 1860 insertions, 0 deletions

diff --git a/drivers/vfio/platform/Kconfig b/drivers/vfio/platform/Kconfig
new file mode 100644
index 000000000..c6be29b2c
--- /dev/null
+++ b/drivers/vfio/platform/Kconfig
@@ -0,0 +1,38 @@
+# SPDX-License-Identifier: GPL-2.0-only
+menu "VFIO support for platform devices"
+	depends on ARM || ARM64 || COMPILE_TEST
+
+config VFIO_PLATFORM_BASE
+	tristate
+	select VFIO_VIRQFD
+
+config VFIO_PLATFORM
+	tristate "Generic VFIO support for any platform device"
+	select VFIO_PLATFORM_BASE
+	help
+	  Support for platform devices with VFIO. This is required to make
+	  use of platform devices present on the system using the VFIO
+	  framework.
+
+	  If you don't know what to do here, say N.
+
+config VFIO_AMBA
+	tristate "VFIO support for AMBA devices (DEPRECATED)"
+	depends on ARM_AMBA || COMPILE_TEST
+	select VFIO_PLATFORM_BASE
+	help
+	  The vfio-amba driver is deprecated and will be removed in a
+	  future kernel release.
+
+	  Support for ARM AMBA devices with VFIO. This is required to make
+	  use of ARM AMBA devices present on the system using the VFIO
+	  framework.
+
+	  If you don't know what to do here, say N.
+
+menu "VFIO platform reset drivers"
+	depends on VFIO_PLATFORM_BASE
+
+source "drivers/vfio/platform/reset/Kconfig"
+endmenu
+endmenu
diff --git a/drivers/vfio/platform/Makefile b/drivers/vfio/platform/Makefile
new file mode 100644
index 000000000..ee4fb6a82
--- /dev/null
+++ b/drivers/vfio/platform/Makefile
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0
+vfio-platform-base-y := vfio_platform_common.o vfio_platform_irq.o
+obj-$(CONFIG_VFIO_PLATFORM_BASE) += vfio-platform-base.o
+obj-$(CONFIG_VFIO_PLATFORM_BASE) += reset/
+
+vfio-platform-y := vfio_platform.o
+obj-$(CONFIG_VFIO_PLATFORM) += vfio-platform.o
+
+vfio-amba-y := vfio_amba.o
+obj-$(CONFIG_VFIO_AMBA) += vfio-amba.o
diff --git a/drivers/vfio/platform/reset/Kconfig b/drivers/vfio/platform/reset/Kconfig
new file mode 100644
index 000000000..70af0dbe2
--- /dev/null
+++ b/drivers/vfio/platform/reset/Kconfig
@@ -0,0 +1,25 @@
+# SPDX-License-Identifier: GPL-2.0-only
+if VFIO_PLATFORM
+config VFIO_PLATFORM_CALXEDAXGMAC_RESET
+	tristate "VFIO support for calxeda xgmac reset (DEPRECATED)"
+	help
+	  Enables the VFIO platform driver to handle reset for Calxeda xgmac
+
+	  If you don't know what to do here, say N.
+
+config VFIO_PLATFORM_AMDXGBE_RESET
+	tristate "VFIO support for AMD XGBE reset (DEPRECATED)"
+	help
+	  Enables the VFIO platform driver to handle reset for AMD XGBE
+
+	  If you don't know what to do here, say N.
+
+config VFIO_PLATFORM_BCMFLEXRM_RESET
+	tristate "VFIO support for Broadcom FlexRM reset (DEPRECATED)"
+	depends on ARCH_BCM_IPROC || COMPILE_TEST
+	default ARCH_BCM_IPROC
+	help
+	  Enables the VFIO platform driver to handle reset for Broadcom FlexRM
+
+	  If you don't know what to do here, say N.
+endif
diff --git a/drivers/vfio/platform/reset/Makefile b/drivers/vfio/platform/reset/Makefile
new file mode 100644
index 000000000..7294c5ea1
--- /dev/null
+++ b/drivers/vfio/platform/reset/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
+vfio-platform-calxedaxgmac-y := vfio_platform_calxedaxgmac.o
+vfio-platform-amdxgbe-y := vfio_platform_amdxgbe.o
+
+obj-$(CONFIG_VFIO_PLATFORM_CALXEDAXGMAC_RESET) += vfio-platform-calxedaxgmac.o
+obj-$(CONFIG_VFIO_PLATFORM_AMDXGBE_RESET) += vfio-platform-amdxgbe.o
+obj-$(CONFIG_VFIO_PLATFORM_BCMFLEXRM_RESET) += vfio_platform_bcmflexrm.o
diff --git a/drivers/vfio/platform/reset/vfio_platform_amdxgbe.c b/drivers/vfio/platform/reset/vfio_platform_amdxgbe.c
new file mode 100644
index 000000000..45f386a04
--- /dev/null
+++ b/drivers/vfio/platform/reset/vfio_platform_amdxgbe.c
@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * VFIO platform driver specialized for AMD xgbe reset
+ * reset code is inherited from AMD xgbe native driver
+ *
+ * Copyright (c) 2015 Linaro Ltd.
+ *              www.linaro.org
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <uapi/linux/mdio.h>
+#include <linux/delay.h>
+
+#include "../vfio_platform_private.h"
+
+#define DMA_MR			0x3000
+#define MAC_VR			0x0110
+#define DMA_ISR			0x3008
+#define MAC_ISR			0x00b0
+#define PCS_MMD_SELECT		0xff
+#define MDIO_AN_INT		0x8002
+#define MDIO_AN_INTMASK		0x8001
+
+static unsigned int xmdio_read(void __iomem *ioaddr, unsigned int mmd,
+			       unsigned int reg)
+{
+	unsigned int mmd_address, value;
+
+	mmd_address = (mmd << 16) | ((reg) & 0xffff);
+	iowrite32(mmd_address >> 8, ioaddr + (PCS_MMD_SELECT << 2));
+	value = ioread32(ioaddr + ((mmd_address & 0xff) << 2));
+	return value;
+}
+
+static void xmdio_write(void __iomem *ioaddr, unsigned int mmd,
+			unsigned int reg, unsigned int value)
+{
+	unsigned int mmd_address;
+
+	mmd_address = (mmd << 16) | ((reg) & 0xffff);
+	iowrite32(mmd_address >> 8, ioaddr + (PCS_MMD_SELECT << 2));
+	iowrite32(value, ioaddr + ((mmd_address & 0xff) << 2));
+}
+
+static int vfio_platform_amdxgbe_reset(struct vfio_platform_device *vdev)
+{
+	struct vfio_platform_region *xgmac_regs = &vdev->regions[0];
+	struct vfio_platform_region *xpcs_regs = &vdev->regions[1];
+	u32 dma_mr_value, pcs_value, value;
+	unsigned int count;
+
+	dev_err_once(vdev->device, "DEPRECATION: VFIO AMD XGBE platform reset is deprecated and will be removed in a future kernel release\n");
+
+	if (!xgmac_regs->ioaddr) {
+		xgmac_regs->ioaddr =
+			ioremap(xgmac_regs->addr, xgmac_regs->size);
+		if (!xgmac_regs->ioaddr)
+			return -ENOMEM;
+	}
+	if (!xpcs_regs->ioaddr) {
+		xpcs_regs->ioaddr =
+			ioremap(xpcs_regs->addr, xpcs_regs->size);
+		if (!xpcs_regs->ioaddr)
+			return -ENOMEM;
+	}
+
+	/* reset the PHY through MDIO*/
+	pcs_value = xmdio_read(xpcs_regs->ioaddr, MDIO_MMD_PCS, MDIO_CTRL1);
+	pcs_value |= MDIO_CTRL1_RESET;
+	xmdio_write(xpcs_regs->ioaddr, MDIO_MMD_PCS, MDIO_CTRL1, pcs_value);
+
+	count = 50;
+	do {
+		msleep(20);
+		pcs_value = xmdio_read(xpcs_regs->ioaddr, MDIO_MMD_PCS,
+					MDIO_CTRL1);
+	} while ((pcs_value & MDIO_CTRL1_RESET) && --count);
+
+	if (pcs_value & MDIO_CTRL1_RESET)
+		dev_warn(vdev->device, "%s: XGBE PHY reset timeout\n",
+			 __func__);
+
+	/* disable auto-negotiation */
+	value = xmdio_read(xpcs_regs->ioaddr, MDIO_MMD_AN, MDIO_CTRL1);
+	value &= ~MDIO_AN_CTRL1_ENABLE;
+	xmdio_write(xpcs_regs->ioaddr, MDIO_MMD_AN, MDIO_CTRL1, value);
+
+	/* disable AN IRQ */
+	xmdio_write(xpcs_regs->ioaddr, MDIO_MMD_AN, MDIO_AN_INTMASK, 0);
+
+	/* clear AN IRQ */
+	xmdio_write(xpcs_regs->ioaddr, MDIO_MMD_AN, MDIO_AN_INT, 0);
+
+	/* MAC software reset */
+	dma_mr_value = ioread32(xgmac_regs->ioaddr + DMA_MR);
+	dma_mr_value |= 0x1;
+	iowrite32(dma_mr_value, xgmac_regs->ioaddr + DMA_MR);
+
+	usleep_range(10, 15);
+
+	count = 2000;
+	while (--count && (ioread32(xgmac_regs->ioaddr + DMA_MR) & 1))
+		usleep_range(500, 600);
+
+	if (!count)
+		dev_warn(vdev->device, "%s: MAC SW reset failed\n", __func__);
+
+	return 0;
+}
+
+module_vfio_reset_handler("amd,xgbe-seattle-v1a", vfio_platform_amdxgbe_reset);
+
+MODULE_VERSION("0.1");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Eric Auger <eric.auger@linaro.org>");
+MODULE_DESCRIPTION("Reset support for AMD xgbe vfio platform device");
diff --git a/drivers/vfio/platform/reset/vfio_platform_bcmflexrm.c b/drivers/vfio/platform/reset/vfio_platform_bcmflexrm.c
new file mode 100644
index 000000000..51c9d156f
--- /dev/null
+++ b/drivers/vfio/platform/reset/vfio_platform_bcmflexrm.c
@@ -0,0 +1,107 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2017 Broadcom
+ */
+
+/*
+ * This driver provides reset support for Broadcom FlexRM ring manager
+ * to VFIO platform.
+ */
+
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include "../vfio_platform_private.h"
+
+/* FlexRM configuration */
+#define RING_REGS_SIZE					0x10000
+#define RING_VER_MAGIC					0x76303031
+
+/* Per-Ring register offsets */
+#define RING_VER					0x000
+#define RING_CONTROL					0x034
+#define RING_FLUSH_DONE					0x038
+
+/* Register RING_CONTROL fields */
+#define CONTROL_FLUSH_SHIFT				5
+
+/* Register RING_FLUSH_DONE fields */
+#define FLUSH_DONE_MASK					0x1
+
+static int vfio_platform_bcmflexrm_shutdown(void __iomem *ring)
+{
+	unsigned int timeout;
+
+	/* Disable/inactivate ring */
+	writel_relaxed(0x0, ring + RING_CONTROL);
+
+	/* Set ring flush state */
+	timeout = 1000; /* timeout of 1s */
+	writel_relaxed(BIT(CONTROL_FLUSH_SHIFT), ring + RING_CONTROL);
+	do {
+		if (readl_relaxed(ring + RING_FLUSH_DONE) &
+		    FLUSH_DONE_MASK)
+			break;
+		mdelay(1);
+	} while (--timeout);
+	if (!timeout)
+		return -ETIMEDOUT;
+
+	/* Clear ring flush state */
+	timeout = 1000; /* timeout of 1s */
+	writel_relaxed(0x0, ring + RING_CONTROL);
+	do {
+		if (!(readl_relaxed(ring + RING_FLUSH_DONE) &
+		      FLUSH_DONE_MASK))
+			break;
+		mdelay(1);
+	} while (--timeout);
+	if (!timeout)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int vfio_platform_bcmflexrm_reset(struct vfio_platform_device *vdev)
+{
+	void __iomem *ring;
+	int rc = 0, ret = 0, ring_num = 0;
+	struct vfio_platform_region *reg = &vdev->regions[0];
+
+	dev_err_once(vdev->device, "DEPRECATION: VFIO Broadcom FlexRM platform reset is deprecated and will be removed in a future kernel release\n");
+
+	/* Map FlexRM ring registers if not mapped */
+	if (!reg->ioaddr) {
+		reg->ioaddr = ioremap(reg->addr, reg->size);
+		if (!reg->ioaddr)
+			return -ENOMEM;
+	}
+
+	/* Discover and shutdown each FlexRM ring */
+	for (ring = reg->ioaddr;
+	     ring < (reg->ioaddr + reg->size); ring += RING_REGS_SIZE) {
+		if (readl_relaxed(ring + RING_VER) == RING_VER_MAGIC) {
+			rc = vfio_platform_bcmflexrm_shutdown(ring);
+			if (rc) {
+				dev_warn(vdev->device,
+					 "FlexRM ring%d shutdown error %d\n",
+					 ring_num, rc);
+				ret |= rc;
+			}
+			ring_num++;
+		}
+	}
+
+	return ret;
+}
+
+module_vfio_reset_handler("brcm,iproc-flexrm-mbox",
+			  vfio_platform_bcmflexrm_reset);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Anup Patel <anup.patel@broadcom.com>");
+MODULE_DESCRIPTION("Reset support for Broadcom FlexRM VFIO platform device");
diff --git a/drivers/vfio/platform/reset/vfio_platform_calxedaxgmac.c b/drivers/vfio/platform/reset/vfio_platform_calxedaxgmac.c
new file mode 100644
index 000000000..a298045a8
--- /dev/null
+++ b/drivers/vfio/platform/reset/vfio_platform_calxedaxgmac.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * VFIO platform driver specialized for Calxeda xgmac reset
+ * reset code is inherited from calxeda xgmac native driver
+ *
+ * Copyright 2010-2011 Calxeda, Inc.
+ * Copyright (c) 2015 Linaro Ltd.
+ *              www.linaro.org
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/io.h>
+
+#include "../vfio_platform_private.h"
+
+#define DRIVER_VERSION  "0.1"
+#define DRIVER_AUTHOR   "Eric Auger <eric.auger@linaro.org>"
+#define DRIVER_DESC     "Reset support for Calxeda xgmac vfio platform device"
+
+/* XGMAC Register definitions */
+#define XGMAC_CONTROL           0x00000000      /* MAC Configuration */
+
+/* DMA Control and Status Registers */
+#define XGMAC_DMA_CONTROL       0x00000f18      /* Ctrl (Operational Mode) */
+#define XGMAC_DMA_INTR_ENA      0x00000f1c      /* Interrupt Enable */
+
+/* DMA Control register defines */
+#define DMA_CONTROL_ST          0x00002000      /* Start/Stop Transmission */
+#define DMA_CONTROL_SR          0x00000002      /* Start/Stop Receive */
+
+/* Common MAC defines */
+#define MAC_ENABLE_TX           0x00000008      /* Transmitter Enable */
+#define MAC_ENABLE_RX           0x00000004      /* Receiver Enable */
+
+static inline void xgmac_mac_disable(void __iomem *ioaddr)
+{
+	u32 value = readl(ioaddr + XGMAC_DMA_CONTROL);
+
+	value &= ~(DMA_CONTROL_ST | DMA_CONTROL_SR);
+	writel(value, ioaddr + XGMAC_DMA_CONTROL);
+
+	value = readl(ioaddr + XGMAC_CONTROL);
+	value &= ~(MAC_ENABLE_TX | MAC_ENABLE_RX);
+	writel(value, ioaddr + XGMAC_CONTROL);
+}
+
+static int vfio_platform_calxedaxgmac_reset(struct vfio_platform_device *vdev)
+{
+	struct vfio_platform_region *reg = &vdev->regions[0];
+
+	dev_err_once(vdev->device, "DEPRECATION: VFIO Calxeda xgmac platform reset is deprecated and will be removed in a future kernel release\n");
+
+	if (!reg->ioaddr) {
+		reg->ioaddr =
+			ioremap(reg->addr, reg->size);
+		if (!reg->ioaddr)
+			return -ENOMEM;
+	}
+
+	/* disable IRQ */
+	writel(0, reg->ioaddr + XGMAC_DMA_INTR_ENA);
+
+	/* Disable the MAC core */
+	xgmac_mac_disable(reg->ioaddr);
+
+	return 0;
+}
+
+module_vfio_reset_handler("calxeda,hb-xgmac", vfio_platform_calxedaxgmac_reset);
+
+MODULE_VERSION(DRIVER_VERSION);
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
diff --git a/drivers/vfio/platform/vfio_amba.c b/drivers/vfio/platform/vfio_amba.c
new file mode 100644
index 000000000..fa754f203
--- /dev/null
+++ b/drivers/vfio/platform/vfio_amba.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2013 - Virtual Open Systems
+ * Author: Antonios Motakis <a.motakis@virtualopensystems.com>
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/vfio.h>
+#include <linux/pm_runtime.h>
+#include <linux/amba/bus.h>
+
+#include "vfio_platform_private.h"
+
+#define DRIVER_VERSION  "0.10"
+#define DRIVER_AUTHOR   "Antonios Motakis <a.motakis@virtualopensystems.com>"
+#define DRIVER_DESC     "VFIO for AMBA devices - User Level meta-driver"
+
+/* probing devices from the AMBA bus */
+
+static struct resource *get_amba_resource(struct vfio_platform_device *vdev,
+					  int i)
+{
+	struct amba_device *adev = (struct amba_device *) vdev->opaque;
+
+	if (i == 0)
+		return &adev->res;
+
+	return NULL;
+}
+
+static int get_amba_irq(struct vfio_platform_device *vdev, int i)
+{
+	struct amba_device *adev = (struct amba_device *) vdev->opaque;
+	int ret = 0;
+
+	if (i < AMBA_NR_IRQS)
+		ret = adev->irq[i];
+
+	/* zero is an unset IRQ for AMBA devices */
+	return ret ? ret : -ENXIO;
+}
+
+static int vfio_amba_init_dev(struct vfio_device *core_vdev)
+{
+	struct vfio_platform_device *vdev =
+		container_of(core_vdev, struct vfio_platform_device, vdev);
+	struct amba_device *adev = to_amba_device(core_vdev->dev);
+	int ret;
+
+	vdev->name = kasprintf(GFP_KERNEL, "vfio-amba-%08x", adev->periphid);
+	if (!vdev->name)
+		return -ENOMEM;
+
+	vdev->opaque = (void *) adev;
+	vdev->flags = VFIO_DEVICE_FLAGS_AMBA;
+	vdev->get_resource = get_amba_resource;
+	vdev->get_irq = get_amba_irq;
+	vdev->reset_required = false;
+
+	ret = vfio_platform_init_common(vdev);
+	if (ret)
+		kfree(vdev->name);
+	return ret;
+}
+
+static const struct vfio_device_ops vfio_amba_ops;
+static int vfio_amba_probe(struct amba_device *adev, const struct amba_id *id)
+{
+	struct vfio_platform_device *vdev;
+	int ret;
+
+	dev_err_once(&adev->dev, "DEPRECATION: vfio-amba is deprecated and will be removed in a future kernel release\n");
+
+	vdev = vfio_alloc_device(vfio_platform_device, vdev, &adev->dev,
+				 &vfio_amba_ops);
+	if (IS_ERR(vdev))
+		return PTR_ERR(vdev);
+
+	ret = vfio_register_group_dev(&vdev->vdev);
+	if (ret)
+		goto out_put_vdev;
+
+	pm_runtime_enable(&adev->dev);
+	dev_set_drvdata(&adev->dev, vdev);
+	return 0;
+
+out_put_vdev:
+	vfio_put_device(&vdev->vdev);
+	return ret;
+}
+
+static void vfio_amba_release_dev(struct vfio_device *core_vdev)
+{
+	struct vfio_platform_device *vdev =
+		container_of(core_vdev, struct vfio_platform_device, vdev);
+
+	vfio_platform_release_common(vdev);
+	kfree(vdev->name);
+}
+
+static void vfio_amba_remove(struct amba_device *adev)
+{
+	struct vfio_platform_device *vdev = dev_get_drvdata(&adev->dev);
+
+	vfio_unregister_group_dev(&vdev->vdev);
+	pm_runtime_disable(vdev->device);
+	vfio_put_device(&vdev->vdev);
+}
+
+static const struct vfio_device_ops vfio_amba_ops = {
+	.name		= "vfio-amba",
+	.init		= vfio_amba_init_dev,
+	.release	= vfio_amba_release_dev,
+	.open_device	= vfio_platform_open_device,
+	.close_device	= vfio_platform_close_device,
+	.ioctl		= vfio_platform_ioctl,
+	.get_region_info_caps = vfio_platform_ioctl_get_region_info,
+	.read		= vfio_platform_read,
+	.write		= vfio_platform_write,
+	.mmap		= vfio_platform_mmap,
+	.bind_iommufd	= vfio_iommufd_physical_bind,
+	.unbind_iommufd	= vfio_iommufd_physical_unbind,
+	.attach_ioas	= vfio_iommufd_physical_attach_ioas,
+	.detach_ioas	= vfio_iommufd_physical_detach_ioas,
+};
+
+static const struct amba_id vfio_amba_ids[] = {
+	{ 0, 0 },
+};
+
+MODULE_DEVICE_TABLE(amba, vfio_amba_ids);
+
+static struct amba_driver vfio_amba_driver = {
+	.probe = vfio_amba_probe,
+	.remove = vfio_amba_remove,
+	.id_table = vfio_amba_ids,
+	.drv = {
+		.name = "vfio-amba",
+	},
+	.driver_managed_dma = true,
+};
+
+module_amba_driver(vfio_amba_driver);
+
+MODULE_VERSION(DRIVER_VERSION);
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
diff --git a/drivers/vfio/platform/vfio_platform.c b/drivers/vfio/platform/vfio_platform.c
new file mode 100644
index 000000000..a4d3ace3e
--- /dev/null
+++ b/drivers/vfio/platform/vfio_platform.c
@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2013 - Virtual Open Systems
+ * Author: Antonios Motakis <a.motakis@virtualopensystems.com>
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/vfio.h>
+#include <linux/pm_runtime.h>
+#include <linux/platform_device.h>
+
+#include "vfio_platform_private.h"
+
+#define DRIVER_VERSION  "0.10"
+#define DRIVER_AUTHOR   "Antonios Motakis <a.motakis@virtualopensystems.com>"
+#define DRIVER_DESC     "VFIO for platform devices - User Level meta-driver"
+
+static bool reset_required = true;
+module_param(reset_required, bool, 0444);
+MODULE_PARM_DESC(reset_required, "override reset requirement (default: 1)");
+
+/* probing devices from the linux platform bus */
+
+static struct resource *get_platform_resource(struct vfio_platform_device *vdev,
+					      int num)
+{
+	struct platform_device *dev = (struct platform_device *) vdev->opaque;
+
+	return platform_get_mem_or_io(dev, num);
+}
+
+static int get_platform_irq(struct vfio_platform_device *vdev, int i)
+{
+	struct platform_device *pdev = (struct platform_device *) vdev->opaque;
+
+	return platform_get_irq_optional(pdev, i);
+}
+
+static int vfio_platform_init_dev(struct vfio_device *core_vdev)
+{
+	struct vfio_platform_device *vdev =
+		container_of(core_vdev, struct vfio_platform_device, vdev);
+	struct platform_device *pdev = to_platform_device(core_vdev->dev);
+
+	vdev->opaque = (void *) pdev;
+	vdev->name = pdev->name;
+	vdev->flags = VFIO_DEVICE_FLAGS_PLATFORM;
+	vdev->get_resource = get_platform_resource;
+	vdev->get_irq = get_platform_irq;
+	vdev->reset_required = reset_required;
+
+	return vfio_platform_init_common(vdev);
+}
+
+static const struct vfio_device_ops vfio_platform_ops;
+static int vfio_platform_probe(struct platform_device *pdev)
+{
+	struct vfio_platform_device *vdev;
+	int ret;
+
+	vdev = vfio_alloc_device(vfio_platform_device, vdev, &pdev->dev,
+				 &vfio_platform_ops);
+	if (IS_ERR(vdev))
+		return PTR_ERR(vdev);
+
+	ret = vfio_register_group_dev(&vdev->vdev);
+	if (ret)
+		goto out_put_vdev;
+
+	pm_runtime_enable(&pdev->dev);
+	dev_set_drvdata(&pdev->dev, vdev);
+	return 0;
+
+out_put_vdev:
+	vfio_put_device(&vdev->vdev);
+	return ret;
+}
+
+static void vfio_platform_release_dev(struct vfio_device *core_vdev)
+{
+	struct vfio_platform_device *vdev =
+		container_of(core_vdev, struct vfio_platform_device, vdev);
+
+	vfio_platform_release_common(vdev);
+}
+
+static void vfio_platform_remove(struct platform_device *pdev)
+{
+	struct vfio_platform_device *vdev = dev_get_drvdata(&pdev->dev);
+
+	vfio_unregister_group_dev(&vdev->vdev);
+	pm_runtime_disable(vdev->device);
+	vfio_put_device(&vdev->vdev);
+}
+
+static const struct vfio_device_ops vfio_platform_ops = {
+	.name		= "vfio-platform",
+	.init		= vfio_platform_init_dev,
+	.release	= vfio_platform_release_dev,
+	.open_device	= vfio_platform_open_device,
+	.close_device	= vfio_platform_close_device,
+	.ioctl		= vfio_platform_ioctl,
+	.get_region_info_caps = vfio_platform_ioctl_get_region_info,
+	.read		= vfio_platform_read,
+	.write		= vfio_platform_write,
+	.mmap		= vfio_platform_mmap,
+	.bind_iommufd	= vfio_iommufd_physical_bind,
+	.unbind_iommufd	= vfio_iommufd_physical_unbind,
+	.attach_ioas	= vfio_iommufd_physical_attach_ioas,
+	.detach_ioas	= vfio_iommufd_physical_detach_ioas,
+};
+
+static struct platform_driver vfio_platform_driver = {
+	.probe		= vfio_platform_probe,
+	.remove		= vfio_platform_remove,
+	.driver	= {
+		.name	= "vfio-platform",
+	},
+	.driver_managed_dma = true,
+};
+
+module_platform_driver(vfio_platform_driver);
+
+MODULE_VERSION(DRIVER_VERSION);
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c
new file mode 100644
index 000000000..c72db5a99
--- /dev/null
+++ b/drivers/vfio/platform/vfio_platform_common.c
@@ -0,0 +1,701 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2013 - Virtual Open Systems
+ * Author: Antonios Motakis <a.motakis@virtualopensystems.com>
+ */
+
+#define dev_fmt(fmt)	"VFIO: " fmt
+
+#include <linux/device.h>
+#include <linux/acpi.h>
+#include <linux/iommu.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/pm_runtime.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/vfio.h>
+
+#include "vfio_platform_private.h"
+
+#define DRIVER_VERSION  "0.10"
+#define DRIVER_AUTHOR   "Antonios Motakis <a.motakis@virtualopensystems.com>"
+#define DRIVER_DESC     "VFIO platform base module"
+
+#define VFIO_PLATFORM_IS_ACPI(vdev) ((vdev)->acpihid != NULL)
+
+static LIST_HEAD(reset_list);
+static DEFINE_MUTEX(driver_lock);
+
+static vfio_platform_reset_fn_t vfio_platform_lookup_reset(const char *compat,
+					struct module **module)
+{
+	struct vfio_platform_reset_node *iter;
+	vfio_platform_reset_fn_t reset_fn = NULL;
+
+	mutex_lock(&driver_lock);
+	list_for_each_entry(iter, &reset_list, link) {
+		if (!strcmp(iter->compat, compat) &&
+			try_module_get(iter->owner)) {
+			*module = iter->owner;
+			reset_fn = iter->of_reset;
+			break;
+		}
+	}
+	mutex_unlock(&driver_lock);
+	return reset_fn;
+}
+
+static int vfio_platform_acpi_probe(struct vfio_platform_device *vdev,
+				    struct device *dev)
+{
+	struct acpi_device *adev;
+
+	if (acpi_disabled)
+		return -ENOENT;
+
+	adev = ACPI_COMPANION(dev);
+	if (!adev) {
+		dev_err(dev, "ACPI companion device not found for %s\n",
+			vdev->name);
+		return -ENODEV;
+	}
+
+#ifdef CONFIG_ACPI
+	vdev->acpihid = acpi_device_hid(adev);
+#endif
+	return WARN_ON(!vdev->acpihid) ? -EINVAL : 0;
+}
+
+static int vfio_platform_acpi_call_reset(struct vfio_platform_device *vdev,
+				  const char **extra_dbg)
+{
+#ifdef CONFIG_ACPI
+	struct device *dev = vdev->device;
+	acpi_handle handle = ACPI_HANDLE(dev);
+	acpi_status acpi_ret;
+
+	acpi_ret = acpi_evaluate_object(handle, "_RST", NULL, NULL);
+	if (ACPI_FAILURE(acpi_ret)) {
+		if (extra_dbg)
+			*extra_dbg = acpi_format_exception(acpi_ret);
+		return -EINVAL;
+	}
+
+	return 0;
+#else
+	return -ENOENT;
+#endif
+}
+
+static bool vfio_platform_acpi_has_reset(struct vfio_platform_device *vdev)
+{
+#ifdef CONFIG_ACPI
+	struct device *dev = vdev->device;
+	acpi_handle handle = ACPI_HANDLE(dev);
+
+	return acpi_has_method(handle, "_RST");
+#else
+	return false;
+#endif
+}
+
+static bool vfio_platform_has_reset(struct vfio_platform_device *vdev)
+{
+	if (VFIO_PLATFORM_IS_ACPI(vdev))
+		return vfio_platform_acpi_has_reset(vdev);
+
+	return vdev->of_reset ? true : false;
+}
+
+static int vfio_platform_get_reset(struct vfio_platform_device *vdev)
+{
+	if (VFIO_PLATFORM_IS_ACPI(vdev))
+		return vfio_platform_acpi_has_reset(vdev) ? 0 : -ENOENT;
+
+	vdev->of_reset = vfio_platform_lookup_reset(vdev->compat,
+						    &vdev->reset_module);
+	if (!vdev->of_reset) {
+		request_module("vfio-reset:%s", vdev->compat);
+		vdev->of_reset = vfio_platform_lookup_reset(vdev->compat,
+							&vdev->reset_module);
+	}
+
+	return vdev->of_reset ? 0 : -ENOENT;
+}
+
+static void vfio_platform_put_reset(struct vfio_platform_device *vdev)
+{
+	if (VFIO_PLATFORM_IS_ACPI(vdev))
+		return;
+
+	if (vdev->of_reset)
+		module_put(vdev->reset_module);
+}
+
+static int vfio_platform_regions_init(struct vfio_platform_device *vdev)
+{
+	int cnt = 0, i;
+
+	while (vdev->get_resource(vdev, cnt))
+		cnt++;
+
+	vdev->regions = kzalloc_objs(struct vfio_platform_region, cnt,
+				     GFP_KERNEL_ACCOUNT);
+	if (!vdev->regions)
+		return -ENOMEM;
+
+	for (i = 0; i < cnt;  i++) {
+		struct resource *res =
+			vdev->get_resource(vdev, i);
+
+		vdev->regions[i].addr = res->start;
+		vdev->regions[i].size = resource_size(res);
+		vdev->regions[i].flags = 0;
+
+		switch (resource_type(res)) {
+		case IORESOURCE_MEM:
+			vdev->regions[i].type = VFIO_PLATFORM_REGION_TYPE_MMIO;
+			vdev->regions[i].flags |= VFIO_REGION_INFO_FLAG_READ;
+			if (!(res->flags & IORESOURCE_READONLY))
+				vdev->regions[i].flags |=
+					VFIO_REGION_INFO_FLAG_WRITE;
+
+			/*
+			 * Only regions addressed with PAGE granularity may be
+			 * MMAPed securely.
+			 */
+			if (!(vdev->regions[i].addr & ~PAGE_MASK) &&
+					!(vdev->regions[i].size & ~PAGE_MASK))
+				vdev->regions[i].flags |=
+					VFIO_REGION_INFO_FLAG_MMAP;
+
+			break;
+		case IORESOURCE_IO:
+			vdev->regions[i].type = VFIO_PLATFORM_REGION_TYPE_PIO;
+			break;
+		default:
+			goto err;
+		}
+	}
+
+	vdev->num_regions = cnt;
+
+	return 0;
+err:
+	kfree(vdev->regions);
+	return -EINVAL;
+}
+
+static void vfio_platform_regions_cleanup(struct vfio_platform_device *vdev)
+{
+	int i;
+
+	for (i = 0; i < vdev->num_regions; i++)
+		iounmap(vdev->regions[i].ioaddr);
+
+	vdev->num_regions = 0;
+	kfree(vdev->regions);
+}
+
+static int vfio_platform_call_reset(struct vfio_platform_device *vdev,
+				    const char **extra_dbg)
+{
+	if (VFIO_PLATFORM_IS_ACPI(vdev)) {
+		dev_info(vdev->device, "reset\n");
+		return vfio_platform_acpi_call_reset(vdev, extra_dbg);
+	} else if (vdev->of_reset) {
+		dev_info(vdev->device, "reset\n");
+		return vdev->of_reset(vdev);
+	}
+
+	dev_warn(vdev->device, "no reset function found!\n");
+	return -EINVAL;
+}
+
+void vfio_platform_close_device(struct vfio_device *core_vdev)
+{
+	struct vfio_platform_device *vdev =
+		container_of(core_vdev, struct vfio_platform_device, vdev);
+	const char *extra_dbg = NULL;
+	int ret;
+
+	ret = vfio_platform_call_reset(vdev, &extra_dbg);
+	if (WARN_ON(ret && vdev->reset_required)) {
+		dev_warn(
+			vdev->device,
+			"reset driver is required and reset call failed in release (%d) %s\n",
+			ret, extra_dbg ? extra_dbg : "");
+	}
+	pm_runtime_put(vdev->device);
+	vfio_platform_regions_cleanup(vdev);
+	vfio_platform_irq_cleanup(vdev);
+}
+EXPORT_SYMBOL_GPL(vfio_platform_close_device);
+
+int vfio_platform_open_device(struct vfio_device *core_vdev)
+{
+	struct vfio_platform_device *vdev =
+		container_of(core_vdev, struct vfio_platform_device, vdev);
+	const char *extra_dbg = NULL;
+	int ret;
+
+	ret = vfio_platform_regions_init(vdev);
+	if (ret)
+		return ret;
+
+	ret = vfio_platform_irq_init(vdev);
+	if (ret)
+		goto err_irq;
+
+	ret = pm_runtime_get_sync(vdev->device);
+	if (ret < 0)
+		goto err_rst;
+
+	ret = vfio_platform_call_reset(vdev, &extra_dbg);
+	if (ret && vdev->reset_required) {
+		dev_warn(
+			vdev->device,
+			"reset driver is required and reset call failed in open (%d) %s\n",
+			ret, extra_dbg ? extra_dbg : "");
+		goto err_rst;
+	}
+	return 0;
+
+err_rst:
+	pm_runtime_put(vdev->device);
+	vfio_platform_irq_cleanup(vdev);
+err_irq:
+	vfio_platform_regions_cleanup(vdev);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(vfio_platform_open_device);
+
+int vfio_platform_ioctl_get_region_info(struct vfio_device *core_vdev,
+					struct vfio_region_info *info,
+					struct vfio_info_cap *caps)
+{
+	struct vfio_platform_device *vdev =
+		container_of(core_vdev, struct vfio_platform_device, vdev);
+
+	if (info->index >= vdev->num_regions)
+		return -EINVAL;
+
+	/* map offset to the physical address  */
+	info->offset = VFIO_PLATFORM_INDEX_TO_OFFSET(info->index);
+	info->size = vdev->regions[info->index].size;
+	info->flags = vdev->regions[info->index].flags;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(vfio_platform_ioctl_get_region_info);
+
+long vfio_platform_ioctl(struct vfio_device *core_vdev,
+			 unsigned int cmd, unsigned long arg)
+{
+	struct vfio_platform_device *vdev =
+		container_of(core_vdev, struct vfio_platform_device, vdev);
+
+	unsigned long minsz;
+
+	if (cmd == VFIO_DEVICE_GET_INFO) {
+		struct vfio_device_info info;
+
+		minsz = offsetofend(struct vfio_device_info, num_irqs);
+
+		if (copy_from_user(&info, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (info.argsz < minsz)
+			return -EINVAL;
+
+		if (vfio_platform_has_reset(vdev))
+			vdev->flags |= VFIO_DEVICE_FLAGS_RESET;
+		info.flags = vdev->flags;
+		info.num_regions = vdev->num_regions;
+		info.num_irqs = vdev->num_irqs;
+
+		return copy_to_user((void __user *)arg, &info, minsz) ?
+			-EFAULT : 0;
+
+	} else if (cmd == VFIO_DEVICE_GET_IRQ_INFO) {
+		struct vfio_irq_info info;
+
+		minsz = offsetofend(struct vfio_irq_info, count);
+
+		if (copy_from_user(&info, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (info.argsz < minsz)
+			return -EINVAL;
+
+		if (info.index >= vdev->num_irqs)
+			return -EINVAL;
+
+		info.flags = vdev->irqs[info.index].flags;
+		info.count = vdev->irqs[info.index].count;
+
+		return copy_to_user((void __user *)arg, &info, minsz) ?
+			-EFAULT : 0;
+
+	} else if (cmd == VFIO_DEVICE_SET_IRQS) {
+		struct vfio_irq_set hdr;
+		u8 *data = NULL;
+		int ret = 0;
+		size_t data_size = 0;
+
+		minsz = offsetofend(struct vfio_irq_set, count);
+
+		if (copy_from_user(&hdr, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		ret = vfio_set_irqs_validate_and_prepare(&hdr, vdev->num_irqs,
+						 vdev->num_irqs, &data_size);
+		if (ret)
+			return ret;
+
+		if (data_size) {
+			data = memdup_user((void __user *)(arg + minsz),
+					    data_size);
+			if (IS_ERR(data))
+				return PTR_ERR(data);
+		}
+
+		mutex_lock(&vdev->igate);
+
+		ret = vfio_platform_set_irqs_ioctl(vdev, hdr.flags, hdr.index,
+						   hdr.start, hdr.count, data);
+		mutex_unlock(&vdev->igate);
+		kfree(data);
+
+		return ret;
+
+	} else if (cmd == VFIO_DEVICE_RESET) {
+		return vfio_platform_call_reset(vdev, NULL);
+	}
+
+	return -ENOTTY;
+}
+EXPORT_SYMBOL_GPL(vfio_platform_ioctl);
+
+static ssize_t vfio_platform_read_mmio(struct vfio_platform_region *reg,
+				       char __user *buf, size_t count,
+				       loff_t off)
+{
+	unsigned int done = 0;
+
+	if (off >= reg->size)
+		return -EINVAL;
+
+	count = min_t(size_t, count, reg->size - off);
+
+	if (!reg->ioaddr) {
+		reg->ioaddr =
+			ioremap(reg->addr, reg->size);
+
+		if (!reg->ioaddr)
+			return -ENOMEM;
+	}
+
+	while (count) {
+		size_t filled;
+
+		if (count >= 4 && !(off % 4)) {
+			u32 val;
+
+			val = ioread32(reg->ioaddr + off);
+			if (copy_to_user(buf, &val, 4))
+				goto err;
+
+			filled = 4;
+		} else if (count >= 2 && !(off % 2)) {
+			u16 val;
+
+			val = ioread16(reg->ioaddr + off);
+			if (copy_to_user(buf, &val, 2))
+				goto err;
+
+			filled = 2;
+		} else {
+			u8 val;
+
+			val = ioread8(reg->ioaddr + off);
+			if (copy_to_user(buf, &val, 1))
+				goto err;
+
+			filled = 1;
+		}
+
+
+		count -= filled;
+		done += filled;
+		off += filled;
+		buf += filled;
+	}
+
+	return done;
+err:
+	return -EFAULT;
+}
+
+ssize_t vfio_platform_read(struct vfio_device *core_vdev,
+			   char __user *buf, size_t count, loff_t *ppos)
+{
+	struct vfio_platform_device *vdev =
+		container_of(core_vdev, struct vfio_platform_device, vdev);
+	unsigned int index = VFIO_PLATFORM_OFFSET_TO_INDEX(*ppos);
+	loff_t off = *ppos & VFIO_PLATFORM_OFFSET_MASK;
+
+	if (index >= vdev->num_regions)
+		return -EINVAL;
+
+	if (!(vdev->regions[index].flags & VFIO_REGION_INFO_FLAG_READ))
+		return -EINVAL;
+
+	if (vdev->regions[index].type & VFIO_PLATFORM_REGION_TYPE_MMIO)
+		return vfio_platform_read_mmio(&vdev->regions[index],
+							buf, count, off);
+	else if (vdev->regions[index].type & VFIO_PLATFORM_REGION_TYPE_PIO)
+		return -EINVAL; /* not implemented */
+
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(vfio_platform_read);
+
+static ssize_t vfio_platform_write_mmio(struct vfio_platform_region *reg,
+					const char __user *buf, size_t count,
+					loff_t off)
+{
+	unsigned int done = 0;
+
+	if (off >= reg->size)
+		return -EINVAL;
+
+	count = min_t(size_t, count, reg->size - off);
+
+	if (!reg->ioaddr) {
+		reg->ioaddr =
+			ioremap(reg->addr, reg->size);
+
+		if (!reg->ioaddr)
+			return -ENOMEM;
+	}
+
+	while (count) {
+		size_t filled;
+
+		if (count >= 4 && !(off % 4)) {
+			u32 val;
+
+			if (copy_from_user(&val, buf, 4))
+				goto err;
+			iowrite32(val, reg->ioaddr + off);
+
+			filled = 4;
+		} else if (count >= 2 && !(off % 2)) {
+			u16 val;
+
+			if (copy_from_user(&val, buf, 2))
+				goto err;
+			iowrite16(val, reg->ioaddr + off);
+
+			filled = 2;
+		} else {
+			u8 val;
+
+			if (copy_from_user(&val, buf, 1))
+				goto err;
+			iowrite8(val, reg->ioaddr + off);
+
+			filled = 1;
+		}
+
+		count -= filled;
+		done += filled;
+		off += filled;
+		buf += filled;
+	}
+
+	return done;
+err:
+	return -EFAULT;
+}
+
+ssize_t vfio_platform_write(struct vfio_device *core_vdev, const char __user *buf,
+			    size_t count, loff_t *ppos)
+{
+	struct vfio_platform_device *vdev =
+		container_of(core_vdev, struct vfio_platform_device, vdev);
+	unsigned int index = VFIO_PLATFORM_OFFSET_TO_INDEX(*ppos);
+	loff_t off = *ppos & VFIO_PLATFORM_OFFSET_MASK;
+
+	if (index >= vdev->num_regions)
+		return -EINVAL;
+
+	if (!(vdev->regions[index].flags & VFIO_REGION_INFO_FLAG_WRITE))
+		return -EINVAL;
+
+	if (vdev->regions[index].type & VFIO_PLATFORM_REGION_TYPE_MMIO)
+		return vfio_platform_write_mmio(&vdev->regions[index],
+							buf, count, off);
+	else if (vdev->regions[index].type & VFIO_PLATFORM_REGION_TYPE_PIO)
+		return -EINVAL; /* not implemented */
+
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(vfio_platform_write);
+
+static int vfio_platform_mmap_mmio(struct vfio_platform_region region,
+				   struct vm_area_struct *vma)
+{
+	u64 req_len, pgoff, req_start;
+
+	req_len = vma->vm_end - vma->vm_start;
+	pgoff = vma->vm_pgoff &
+		((1U << (VFIO_PLATFORM_OFFSET_SHIFT - PAGE_SHIFT)) - 1);
+	req_start = pgoff << PAGE_SHIFT;
+
+	if (region.size < PAGE_SIZE || req_start + req_len > region.size)
+		return -EINVAL;
+
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+	vma->vm_pgoff = (region.addr >> PAGE_SHIFT) + pgoff;
+
+	return remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+			       req_len, vma->vm_page_prot);
+}
+
+int vfio_platform_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma)
+{
+	struct vfio_platform_device *vdev =
+		container_of(core_vdev, struct vfio_platform_device, vdev);
+	unsigned int index;
+
+	index = vma->vm_pgoff >> (VFIO_PLATFORM_OFFSET_SHIFT - PAGE_SHIFT);
+
+	if (vma->vm_end < vma->vm_start)
+		return -EINVAL;
+	if (!(vma->vm_flags & VM_SHARED))
+		return -EINVAL;
+	if (index >= vdev->num_regions)
+		return -EINVAL;
+	if (vma->vm_start & ~PAGE_MASK)
+		return -EINVAL;
+	if (vma->vm_end & ~PAGE_MASK)
+		return -EINVAL;
+
+	if (!(vdev->regions[index].flags & VFIO_REGION_INFO_FLAG_MMAP))
+		return -EINVAL;
+
+	if (!(vdev->regions[index].flags & VFIO_REGION_INFO_FLAG_READ)
+			&& (vma->vm_flags & VM_READ))
+		return -EINVAL;
+
+	if (!(vdev->regions[index].flags & VFIO_REGION_INFO_FLAG_WRITE)
+			&& (vma->vm_flags & VM_WRITE))
+		return -EINVAL;
+
+	vma->vm_private_data = vdev;
+
+	if (vdev->regions[index].type & VFIO_PLATFORM_REGION_TYPE_MMIO)
+		return vfio_platform_mmap_mmio(vdev->regions[index], vma);
+
+	else if (vdev->regions[index].type & VFIO_PLATFORM_REGION_TYPE_PIO)
+		return -EINVAL; /* not implemented */
+
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(vfio_platform_mmap);
+
+static int vfio_platform_of_probe(struct vfio_platform_device *vdev,
+			   struct device *dev)
+{
+	int ret;
+
+	ret = device_property_read_string(dev, "compatible",
+					  &vdev->compat);
+	if (ret)
+		dev_err(dev, "Cannot retrieve compat for %s\n", vdev->name);
+
+	return ret;
+}
+
+/*
+ * There can be two kernel build combinations. One build where
+ * ACPI is not selected in Kconfig and another one with the ACPI Kconfig.
+ *
+ * In the first case, vfio_platform_acpi_probe will return since
+ * acpi_disabled is 1. DT user will not see any kind of messages from
+ * ACPI.
+ *
+ * In the second case, both DT and ACPI is compiled in but the system is
+ * booting with any of these combinations.
+ *
+ * If the firmware is DT type, then acpi_disabled is 1. The ACPI probe routine
+ * terminates immediately without any messages.
+ *
+ * If the firmware is ACPI type, then acpi_disabled is 0. All other checks are
+ * valid checks. We cannot claim that this system is DT.
+ */
+int vfio_platform_init_common(struct vfio_platform_device *vdev)
+{
+	int ret;
+	struct device *dev = vdev->vdev.dev;
+
+	ret = vfio_platform_acpi_probe(vdev, dev);
+	if (ret)
+		ret = vfio_platform_of_probe(vdev, dev);
+
+	if (ret)
+		return ret;
+
+	vdev->device = dev;
+	mutex_init(&vdev->igate);
+
+	ret = vfio_platform_get_reset(vdev);
+	if (ret && vdev->reset_required) {
+		dev_err(dev, "No reset function found for device %s\n",
+			vdev->name);
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(vfio_platform_init_common);
+
+void vfio_platform_release_common(struct vfio_platform_device *vdev)
+{
+	vfio_platform_put_reset(vdev);
+}
+EXPORT_SYMBOL_GPL(vfio_platform_release_common);
+
+void __vfio_platform_register_reset(struct vfio_platform_reset_node *node)
+{
+	mutex_lock(&driver_lock);
+	list_add(&node->link, &reset_list);
+	mutex_unlock(&driver_lock);
+}
+EXPORT_SYMBOL_GPL(__vfio_platform_register_reset);
+
+void vfio_platform_unregister_reset(const char *compat,
+				    vfio_platform_reset_fn_t fn)
+{
+	struct vfio_platform_reset_node *iter, *temp;
+
+	mutex_lock(&driver_lock);
+	list_for_each_entry_safe(iter, temp, &reset_list, link) {
+		if (!strcmp(iter->compat, compat) && (iter->of_reset == fn)) {
+			list_del(&iter->link);
+			break;
+		}
+	}
+
+	mutex_unlock(&driver_lock);
+
+}
+EXPORT_SYMBOL_GPL(vfio_platform_unregister_reset);
+
+MODULE_VERSION(DRIVER_VERSION);
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
diff --git a/drivers/vfio/platform/vfio_platform_irq.c b/drivers/vfio/platform/vfio_platform_irq.c
new file mode 100644
index 000000000..d16596e7f
--- /dev/null
+++ b/drivers/vfio/platform/vfio_platform_irq.c
@@ -0,0 +1,368 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * VFIO platform devices interrupt handling
+ *
+ * Copyright (C) 2013 - Virtual Open Systems
+ * Author: Antonios Motakis <a.motakis@virtualopensystems.com>
+ */
+
+#include <linux/eventfd.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/vfio.h>
+#include <linux/irq.h>
+
+#include "vfio_platform_private.h"
+
+static void vfio_platform_mask(struct vfio_platform_irq *irq_ctx)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&irq_ctx->lock, flags);
+
+	if (!irq_ctx->masked) {
+		disable_irq_nosync(irq_ctx->hwirq);
+		irq_ctx->masked = true;
+	}
+
+	spin_unlock_irqrestore(&irq_ctx->lock, flags);
+}
+
+static int vfio_platform_mask_handler(void *opaque, void *unused)
+{
+	struct vfio_platform_irq *irq_ctx = opaque;
+
+	vfio_platform_mask(irq_ctx);
+
+	return 0;
+}
+
+static int vfio_platform_set_irq_mask(struct vfio_platform_device *vdev,
+				      unsigned index, unsigned start,
+				      unsigned count, uint32_t flags,
+				      void *data)
+{
+	if (start != 0 || count != 1)
+		return -EINVAL;
+
+	if (!(vdev->irqs[index].flags & VFIO_IRQ_INFO_MASKABLE))
+		return -EINVAL;
+
+	if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
+		int32_t fd = *(int32_t *)data;
+
+		if (fd >= 0)
+			return vfio_virqfd_enable((void *) &vdev->irqs[index],
+						  vfio_platform_mask_handler,
+						  NULL, NULL,
+						  &vdev->irqs[index].mask, fd);
+
+		vfio_virqfd_disable(&vdev->irqs[index].mask);
+		return 0;
+	}
+
+	if (flags & VFIO_IRQ_SET_DATA_NONE) {
+		vfio_platform_mask(&vdev->irqs[index]);
+
+	} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
+		uint8_t mask = *(uint8_t *)data;
+
+		if (mask)
+			vfio_platform_mask(&vdev->irqs[index]);
+	}
+
+	return 0;
+}
+
+static void vfio_platform_unmask(struct vfio_platform_irq *irq_ctx)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&irq_ctx->lock, flags);
+
+	if (irq_ctx->masked) {
+		enable_irq(irq_ctx->hwirq);
+		irq_ctx->masked = false;
+	}
+
+	spin_unlock_irqrestore(&irq_ctx->lock, flags);
+}
+
+static int vfio_platform_unmask_handler(void *opaque, void *unused)
+{
+	struct vfio_platform_irq *irq_ctx = opaque;
+
+	vfio_platform_unmask(irq_ctx);
+
+	return 0;
+}
+
+static int vfio_platform_set_irq_unmask(struct vfio_platform_device *vdev,
+					unsigned index, unsigned start,
+					unsigned count, uint32_t flags,
+					void *data)
+{
+	if (start != 0 || count != 1)
+		return -EINVAL;
+
+	if (!(vdev->irqs[index].flags & VFIO_IRQ_INFO_MASKABLE))
+		return -EINVAL;
+
+	if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
+		int32_t fd = *(int32_t *)data;
+
+		if (fd >= 0)
+			return vfio_virqfd_enable((void *) &vdev->irqs[index],
+						  vfio_platform_unmask_handler,
+						  NULL, NULL,
+						  &vdev->irqs[index].unmask,
+						  fd);
+
+		vfio_virqfd_disable(&vdev->irqs[index].unmask);
+		return 0;
+	}
+
+	if (flags & VFIO_IRQ_SET_DATA_NONE) {
+		vfio_platform_unmask(&vdev->irqs[index]);
+
+	} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
+		uint8_t unmask = *(uint8_t *)data;
+
+		if (unmask)
+			vfio_platform_unmask(&vdev->irqs[index]);
+	}
+
+	return 0;
+}
+
+/*
+ * The trigger eventfd is guaranteed valid in the interrupt path
+ * and protected by the igate mutex when triggered via ioctl.
+ */
+static void vfio_send_eventfd(struct vfio_platform_irq *irq_ctx)
+{
+	if (likely(irq_ctx->trigger))
+		eventfd_signal(irq_ctx->trigger);
+}
+
+static irqreturn_t vfio_automasked_irq_handler(int irq, void *dev_id)
+{
+	struct vfio_platform_irq *irq_ctx = dev_id;
+	unsigned long flags;
+	int ret = IRQ_NONE;
+
+	spin_lock_irqsave(&irq_ctx->lock, flags);
+
+	if (!irq_ctx->masked) {
+		ret = IRQ_HANDLED;
+
+		/* automask maskable interrupts */
+		disable_irq_nosync(irq_ctx->hwirq);
+		irq_ctx->masked = true;
+	}
+
+	spin_unlock_irqrestore(&irq_ctx->lock, flags);
+
+	if (ret == IRQ_HANDLED)
+		vfio_send_eventfd(irq_ctx);
+
+	return ret;
+}
+
+static irqreturn_t vfio_irq_handler(int irq, void *dev_id)
+{
+	struct vfio_platform_irq *irq_ctx = dev_id;
+
+	vfio_send_eventfd(irq_ctx);
+
+	return IRQ_HANDLED;
+}
+
+static int vfio_set_trigger(struct vfio_platform_device *vdev, int index,
+			    int fd)
+{
+	struct vfio_platform_irq *irq = &vdev->irqs[index];
+	struct eventfd_ctx *trigger;
+
+	if (irq->trigger) {
+		disable_irq(irq->hwirq);
+		eventfd_ctx_put(irq->trigger);
+		irq->trigger = NULL;
+	}
+
+	if (fd < 0) /* Disable only */
+		return 0;
+
+	trigger = eventfd_ctx_fdget(fd);
+	if (IS_ERR(trigger))
+		return PTR_ERR(trigger);
+
+	irq->trigger = trigger;
+
+	/*
+	 * irq->masked effectively provides nested disables within the overall
+	 * enable relative to trigger.  Specifically request_irq() is called
+	 * with NO_AUTOEN, therefore the IRQ is initially disabled.  The user
+	 * may only further disable the IRQ with a MASK operations because
+	 * irq->masked is initially false.
+	 */
+	enable_irq(irq->hwirq);
+
+	return 0;
+}
+
+static int vfio_platform_set_irq_trigger(struct vfio_platform_device *vdev,
+					 unsigned index, unsigned start,
+					 unsigned count, uint32_t flags,
+					 void *data)
+{
+	struct vfio_platform_irq *irq = &vdev->irqs[index];
+	irq_handler_t handler;
+
+	if (vdev->irqs[index].flags & VFIO_IRQ_INFO_AUTOMASKED)
+		handler = vfio_automasked_irq_handler;
+	else
+		handler = vfio_irq_handler;
+
+	if (!count && (flags & VFIO_IRQ_SET_DATA_NONE))
+		return vfio_set_trigger(vdev, index, -1);
+
+	if (start != 0 || count != 1)
+		return -EINVAL;
+
+	if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
+		int32_t fd = *(int32_t *)data;
+
+		return vfio_set_trigger(vdev, index, fd);
+	}
+
+	if (flags & VFIO_IRQ_SET_DATA_NONE) {
+		handler(irq->hwirq, irq);
+
+	} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
+		uint8_t trigger = *(uint8_t *)data;
+
+		if (trigger)
+			handler(irq->hwirq, irq);
+	}
+
+	return 0;
+}
+
+int vfio_platform_set_irqs_ioctl(struct vfio_platform_device *vdev,
+				 uint32_t flags, unsigned index, unsigned start,
+				 unsigned count, void *data)
+{
+	int (*func)(struct vfio_platform_device *vdev, unsigned index,
+		    unsigned start, unsigned count, uint32_t flags,
+		    void *data) = NULL;
+
+	/*
+	 * For compatibility, errors from request_irq() are local to the
+	 * SET_IRQS path and reflected in the name pointer.  This allows,
+	 * for example, polling mode fallback for an exclusive IRQ failure.
+	 */
+	if (IS_ERR(vdev->irqs[index].name))
+		return PTR_ERR(vdev->irqs[index].name);
+
+	switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) {
+	case VFIO_IRQ_SET_ACTION_MASK:
+		func = vfio_platform_set_irq_mask;
+		break;
+	case VFIO_IRQ_SET_ACTION_UNMASK:
+		func = vfio_platform_set_irq_unmask;
+		break;
+	case VFIO_IRQ_SET_ACTION_TRIGGER:
+		func = vfio_platform_set_irq_trigger;
+		break;
+	}
+
+	if (!func)
+		return -ENOTTY;
+
+	return func(vdev, index, start, count, flags, data);
+}
+
+int vfio_platform_irq_init(struct vfio_platform_device *vdev)
+{
+	int cnt = 0, i, ret = 0;
+
+	while (vdev->get_irq(vdev, cnt) >= 0)
+		cnt++;
+
+	vdev->irqs = kzalloc_objs(struct vfio_platform_irq, cnt,
+				  GFP_KERNEL_ACCOUNT);
+	if (!vdev->irqs)
+		return -ENOMEM;
+
+	for (i = 0; i < cnt; i++) {
+		int hwirq = vdev->get_irq(vdev, i);
+		irq_handler_t handler = vfio_irq_handler;
+
+		if (hwirq < 0) {
+			ret = -EINVAL;
+			goto err;
+		}
+
+		spin_lock_init(&vdev->irqs[i].lock);
+
+		vdev->irqs[i].flags = VFIO_IRQ_INFO_EVENTFD;
+
+		if (irq_get_trigger_type(hwirq) & IRQ_TYPE_LEVEL_MASK) {
+			vdev->irqs[i].flags |= VFIO_IRQ_INFO_MASKABLE
+						| VFIO_IRQ_INFO_AUTOMASKED;
+			handler = vfio_automasked_irq_handler;
+		}
+
+		vdev->irqs[i].count = 1;
+		vdev->irqs[i].hwirq = hwirq;
+		vdev->irqs[i].masked = false;
+		vdev->irqs[i].name = kasprintf(GFP_KERNEL_ACCOUNT,
+					       "vfio-irq[%d](%s)", hwirq,
+					       vdev->name);
+		if (!vdev->irqs[i].name) {
+			ret = -ENOMEM;
+			goto err;
+		}
+
+		ret = request_irq(hwirq, handler, IRQF_NO_AUTOEN,
+				  vdev->irqs[i].name, &vdev->irqs[i]);
+		if (ret) {
+			kfree(vdev->irqs[i].name);
+			vdev->irqs[i].name = ERR_PTR(ret);
+		}
+	}
+
+	vdev->num_irqs = cnt;
+
+	return 0;
+err:
+	for (--i; i >= 0; i--) {
+		if (!IS_ERR(vdev->irqs[i].name)) {
+			free_irq(vdev->irqs[i].hwirq, &vdev->irqs[i]);
+			kfree(vdev->irqs[i].name);
+		}
+	}
+	kfree(vdev->irqs);
+	return ret;
+}
+
+void vfio_platform_irq_cleanup(struct vfio_platform_device *vdev)
+{
+	int i;
+
+	for (i = 0; i < vdev->num_irqs; i++) {
+		vfio_virqfd_disable(&vdev->irqs[i].mask);
+		vfio_virqfd_disable(&vdev->irqs[i].unmask);
+		if (!IS_ERR(vdev->irqs[i].name)) {
+			free_irq(vdev->irqs[i].hwirq, &vdev->irqs[i]);
+			if (vdev->irqs[i].trigger)
+				eventfd_ctx_put(vdev->irqs[i].trigger);
+			kfree(vdev->irqs[i].name);
+		}
+	}
+
+	vdev->num_irqs = 0;
+	kfree(vdev->irqs);
+}
diff --git a/drivers/vfio/platform/vfio_platform_private.h b/drivers/vfio/platform/vfio_platform_private.h
new file mode 100644
index 000000000..05084212a
--- /dev/null
+++ b/drivers/vfio/platform/vfio_platform_private.h
@@ -0,0 +1,132 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2013 - Virtual Open Systems
+ * Author: Antonios Motakis <a.motakis@virtualopensystems.com>
+ */
+
+#ifndef VFIO_PLATFORM_PRIVATE_H
+#define VFIO_PLATFORM_PRIVATE_H
+
+#include <linux/types.h>
+#include <linux/interrupt.h>
+#include <linux/vfio.h>
+
+#define VFIO_PLATFORM_OFFSET_SHIFT   40
+#define VFIO_PLATFORM_OFFSET_MASK (((u64)(1) << VFIO_PLATFORM_OFFSET_SHIFT) - 1)
+
+#define VFIO_PLATFORM_OFFSET_TO_INDEX(off)	\
+	(off >> VFIO_PLATFORM_OFFSET_SHIFT)
+
+#define VFIO_PLATFORM_INDEX_TO_OFFSET(index)	\
+	((u64)(index) << VFIO_PLATFORM_OFFSET_SHIFT)
+
+struct vfio_platform_irq {
+	u32			flags;
+	u32			count;
+	int			hwirq;
+	char			*name;
+	struct eventfd_ctx	*trigger;
+	bool			masked;
+	spinlock_t		lock;
+	struct virqfd		*unmask;
+	struct virqfd		*mask;
+};
+
+struct vfio_platform_region {
+	u64			addr;
+	resource_size_t		size;
+	u32			flags;
+	u32			type;
+#define VFIO_PLATFORM_REGION_TYPE_MMIO	1
+#define VFIO_PLATFORM_REGION_TYPE_PIO	2
+	void __iomem		*ioaddr;
+};
+
+struct vfio_platform_device {
+	struct vfio_device		vdev;
+	struct vfio_platform_region	*regions;
+	u32				num_regions;
+	struct vfio_platform_irq	*irqs;
+	u32				num_irqs;
+	struct mutex			igate;
+	const char			*compat;
+	const char			*acpihid;
+	struct module			*reset_module;
+	struct device			*device;
+
+	/*
+	 * These fields should be filled by the bus specific binder
+	 */
+	void		*opaque;
+	const char	*name;
+	uint32_t	flags;
+	/* callbacks to discover device resources */
+	struct resource*
+		(*get_resource)(struct vfio_platform_device *vdev, int i);
+	int	(*get_irq)(struct vfio_platform_device *vdev, int i);
+	int	(*of_reset)(struct vfio_platform_device *vdev);
+
+	bool				reset_required;
+};
+
+typedef int (*vfio_platform_reset_fn_t)(struct vfio_platform_device *vdev);
+
+struct vfio_platform_reset_node {
+	struct list_head link;
+	char *compat;
+	struct module *owner;
+	vfio_platform_reset_fn_t of_reset;
+};
+
+int vfio_platform_init_common(struct vfio_platform_device *vdev);
+void vfio_platform_release_common(struct vfio_platform_device *vdev);
+
+int vfio_platform_open_device(struct vfio_device *core_vdev);
+void vfio_platform_close_device(struct vfio_device *core_vdev);
+long vfio_platform_ioctl(struct vfio_device *core_vdev,
+			 unsigned int cmd, unsigned long arg);
+int vfio_platform_ioctl_get_region_info(struct vfio_device *core_vdev,
+					struct vfio_region_info *info,
+					struct vfio_info_cap *caps);
+ssize_t vfio_platform_read(struct vfio_device *core_vdev,
+			   char __user *buf, size_t count,
+			   loff_t *ppos);
+ssize_t vfio_platform_write(struct vfio_device *core_vdev,
+			    const char __user *buf,
+			    size_t count, loff_t *ppos);
+int vfio_platform_mmap(struct vfio_device *core_vdev,
+		       struct vm_area_struct *vma);
+
+int vfio_platform_irq_init(struct vfio_platform_device *vdev);
+void vfio_platform_irq_cleanup(struct vfio_platform_device *vdev);
+
+int vfio_platform_set_irqs_ioctl(struct vfio_platform_device *vdev,
+				 uint32_t flags, unsigned index,
+				 unsigned start, unsigned count, void *data);
+
+void __vfio_platform_register_reset(struct vfio_platform_reset_node *n);
+void vfio_platform_unregister_reset(const char *compat,
+				    vfio_platform_reset_fn_t fn);
+#define vfio_platform_register_reset(__compat, __reset)		\
+static struct vfio_platform_reset_node __reset ## _node = {	\
+	.owner = THIS_MODULE,					\
+	.compat = __compat,					\
+	.of_reset = __reset,					\
+};								\
+__vfio_platform_register_reset(&__reset ## _node)
+
+#define module_vfio_reset_handler(compat, reset)		\
+MODULE_ALIAS("vfio-reset:" compat);				\
+static int __init reset ## _module_init(void)			\
+{								\
+	vfio_platform_register_reset(compat, reset);		\
+	return 0;						\
+};								\
+static void __exit reset ## _module_exit(void)			\
+{								\
+	vfio_platform_unregister_reset(compat, reset);		\
+};								\
+module_init(reset ## _module_init);				\
+module_exit(reset ## _module_exit)
+
+#endif /* VFIO_PLATFORM_PRIVATE_H */