Merge tag 'vfio-v4.4-rc1' of git://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:
 - Use kernel interfaces for VPD emulation (Alex Williamson)
 - Platform fix for releasing IRQs (Eric Auger)
 - Type1 IOMMU always advertises PAGE_SIZE support when smaller mapping
   sizes are available (Eric Auger)
 - Platform fixes for incorrectly using copies of structures rather than
   pointers to structures (James Morse)
 - Rework platform reset modules, fix leak, and add AMD xgbe reset
   module (Eric Auger)
 - Fix vfio_device_get_from_name() return value (Joerg Roedel)
 - No-IOMMU interface (Alex Williamson)
 - Fix potential out of bounds array access in PCI config handling (Dan
   Carpenter)

* tag 'vfio-v4.4-rc1' of git://github.com/awilliam/linux-vfio:
  vfio/pci: make an array larger
  vfio: Include No-IOMMU mode
  vfio: Fix bug in vfio_device_get_from_name()
  VFIO: platform: reset: AMD xgbe reset module
  vfio: platform: reset: calxedaxgmac: fix ioaddr leak
  vfio: platform: add dev_info on device reset
  vfio: platform: use list of registered reset function
  vfio: platform: add compat in vfio_platform_device
  vfio: platform: reset: calxedaxgmac: add reset function registration
  vfio: platform: introduce module_vfio_reset_handler macro
  vfio: platform: add capability to register a reset function
  vfio: platform: introduce vfio-platform-base module
  vfio/platform: store mapped memory in region, instead of an on-stack copy
  vfio/type1: handle case where IOMMU does not support PAGE_SIZE size
  VFIO: platform: clear IRQ_NOAUTOEN when de-assigning the IRQ
  vfio/pci: Use kernel VPD access functions
  vfio: Whitelist PCI bridges

drivers/vfio/Kconfig

@@ -31,6 +31,21 @@ menuconfig VFIO
 
 	  If you don't know what to do here, say N.
 
+menuconfig VFIO_NOIOMMU
+	bool "VFIO No-IOMMU support"
+	depends on VFIO
+	help
+	  VFIO is built on the ability to isolate devices using the IOMMU.
+	  Only with an IOMMU can userspace access to DMA capable devices be
+	  considered secure.  VFIO No-IOMMU mode enables IOMMU groups for
+	  devices without IOMMU backing for the purpose of re-using the VFIO
+	  infrastructure in a non-secure mode.  Use of this mode will result
+	  in an unsupportable kernel and will therefore taint the kernel.
+	  Device assignment to virtual machines is also not possible with
+	  this mode since there is no IOMMU to provide DMA translation.
+
+	  If you don't know what to do here, say N.
+
 source "drivers/vfio/pci/Kconfig"
 source "drivers/vfio/platform/Kconfig"
 source "virt/lib/Kconfig"

drivers/vfio/pci/vfio_pci.c

@@ -940,13 +940,13 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL)
 		return -EINVAL;
 
-	group = iommu_group_get(&pdev->dev);
+	group = vfio_iommu_group_get(&pdev->dev);
 	if (!group)
 		return -EINVAL;
 
 	vdev = kzalloc(sizeof(*vdev), GFP_KERNEL);
 	if (!vdev) {
-		iommu_group_put(group);
+		vfio_iommu_group_put(group, &pdev->dev);
 		return -ENOMEM;
 	}
 
@@ -957,7 +957,7 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	ret = vfio_add_group_dev(&pdev->dev, &vfio_pci_ops, vdev);
 	if (ret) {
-		iommu_group_put(group);
+		vfio_iommu_group_put(group, &pdev->dev);
 		kfree(vdev);
 		return ret;
 	}
@@ -993,7 +993,7 @@ static void vfio_pci_remove(struct pci_dev *pdev)
 	if (!vdev)
 		return;
 
-	iommu_group_put(pdev->dev.iommu_group);
+	vfio_iommu_group_put(pdev->dev.iommu_group, &pdev->dev);
 	kfree(vdev);
 
 	if (vfio_pci_is_vga(pdev)) {

drivers/vfio/pci/vfio_pci_config.c

@@ -46,7 +46,7 @@
  *   0: Removed from the user visible capability list
  *   FF: Variable length
  */
-static u8 pci_cap_length[] = {
+static const u8 pci_cap_length[PCI_CAP_ID_MAX + 1] = {
 	[PCI_CAP_ID_BASIC]	= PCI_STD_HEADER_SIZEOF, /* pci config header */
 	[PCI_CAP_ID_PM]		= PCI_PM_SIZEOF,
 	[PCI_CAP_ID_AGP]	= PCI_AGP_SIZEOF,
@@ -74,7 +74,7 @@ static u8 pci_cap_length[] = {
  *   0: Removed or masked from the user visible capabilty list
  *   FF: Variable length
  */
-static u16 pci_ext_cap_length[] = {
+static const u16 pci_ext_cap_length[PCI_EXT_CAP_ID_MAX + 1] = {
 	[PCI_EXT_CAP_ID_ERR]	=	PCI_ERR_ROOT_COMMAND,
 	[PCI_EXT_CAP_ID_VC]	=	0xFF,
 	[PCI_EXT_CAP_ID_DSN]	=	PCI_EXT_CAP_DSN_SIZEOF,
@@ -671,6 +671,73 @@ static int __init init_pci_cap_pm_perm(struct perm_bits *perm)
 	return 0;
 }
 
+static int vfio_vpd_config_write(struct vfio_pci_device *vdev, int pos,
+				 int count, struct perm_bits *perm,
+				 int offset, __le32 val)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	__le16 *paddr = (__le16 *)(vdev->vconfig + pos - offset + PCI_VPD_ADDR);
+	__le32 *pdata = (__le32 *)(vdev->vconfig + pos - offset + PCI_VPD_DATA);
+	u16 addr;
+	u32 data;
+
+	/*
+	 * Write through to emulation.  If the write includes the upper byte
+	 * of PCI_VPD_ADDR, then the PCI_VPD_ADDR_F bit is written and we
+	 * have work to do.
+	 */
+	count = vfio_default_config_write(vdev, pos, count, perm, offset, val);
+	if (count < 0 || offset > PCI_VPD_ADDR + 1 ||
+	    offset + count <= PCI_VPD_ADDR + 1)
+		return count;
+
+	addr = le16_to_cpu(*paddr);
+
+	if (addr & PCI_VPD_ADDR_F) {
+		data = le32_to_cpu(*pdata);
+		if (pci_write_vpd(pdev, addr & ~PCI_VPD_ADDR_F, 4, &data) != 4)
+			return count;
+	} else {
+		if (pci_read_vpd(pdev, addr, 4, &data) != 4)
+			return count;
+		*pdata = cpu_to_le32(data);
+	}
+
+	/*
+	 * Toggle PCI_VPD_ADDR_F in the emulated PCI_VPD_ADDR register to
+	 * signal completion.  If an error occurs above, we assume that not
+	 * toggling this bit will induce a driver timeout.
+	 */
+	addr ^= PCI_VPD_ADDR_F;
+	*paddr = cpu_to_le16(addr);
+
+	return count;
+}
+
+/* Permissions for Vital Product Data capability */
+static int __init init_pci_cap_vpd_perm(struct perm_bits *perm)
+{
+	if (alloc_perm_bits(perm, pci_cap_length[PCI_CAP_ID_VPD]))
+		return -ENOMEM;
+
+	perm->writefn = vfio_vpd_config_write;
+
+	/*
+	 * We always virtualize the next field so we can remove
+	 * capabilities from the chain if we want to.
+	 */
+	p_setb(perm, PCI_CAP_LIST_NEXT, (u8)ALL_VIRT, NO_WRITE);
+
+	/*
+	 * Both the address and data registers are virtualized to
+	 * enable access through the pci_vpd_read/write functions
+	 */
+	p_setw(perm, PCI_VPD_ADDR, (u16)ALL_VIRT, (u16)ALL_WRITE);
+	p_setd(perm, PCI_VPD_DATA, ALL_VIRT, ALL_WRITE);
+
+	return 0;
+}
+
 /* Permissions for PCI-X capability */
 static int __init init_pci_cap_pcix_perm(struct perm_bits *perm)
 {
@@ -790,6 +857,7 @@ void vfio_pci_uninit_perm_bits(void)
 	free_perm_bits(&cap_perms[PCI_CAP_ID_BASIC]);
 
 	free_perm_bits(&cap_perms[PCI_CAP_ID_PM]);
+	free_perm_bits(&cap_perms[PCI_CAP_ID_VPD]);
 	free_perm_bits(&cap_perms[PCI_CAP_ID_PCIX]);
 	free_perm_bits(&cap_perms[PCI_CAP_ID_EXP]);
 	free_perm_bits(&cap_perms[PCI_CAP_ID_AF]);
@@ -807,7 +875,7 @@ int __init vfio_pci_init_perm_bits(void)
 
 	/* Capabilities */
 	ret |= init_pci_cap_pm_perm(&cap_perms[PCI_CAP_ID_PM]);
-	cap_perms[PCI_CAP_ID_VPD].writefn = vfio_raw_config_write;
+	ret |= init_pci_cap_vpd_perm(&cap_perms[PCI_CAP_ID_VPD]);
 	ret |= init_pci_cap_pcix_perm(&cap_perms[PCI_CAP_ID_PCIX]);
 	cap_perms[PCI_CAP_ID_VNDR].writefn = vfio_raw_config_write;
 	ret |= init_pci_cap_exp_perm(&cap_perms[PCI_CAP_ID_EXP]);

drivers/vfio/platform/Makefile

-
-vfio-platform-y := vfio_platform.o vfio_platform_common.o vfio_platform_irq.o
+vfio-platform-base-y := vfio_platform_common.o vfio_platform_irq.o
+vfio-platform-y := vfio_platform.o
 
 obj-$(CONFIG_VFIO_PLATFORM) += vfio-platform.o
+obj-$(CONFIG_VFIO_PLATFORM) += vfio-platform-base.o
 obj-$(CONFIG_VFIO_PLATFORM) += reset/
 
 vfio-amba-y := vfio_amba.o
 
 obj-$(CONFIG_VFIO_AMBA) += vfio-amba.o
+obj-$(CONFIG_VFIO_AMBA) += vfio-platform-base.o
 obj-$(CONFIG_VFIO_AMBA) += reset/

drivers/vfio/platform/reset/Kconfig

@@ -5,3 +5,11 @@ config VFIO_PLATFORM_CALXEDAXGMAC_RESET
 	  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"
+	depends on VFIO_PLATFORM
+	help
+	  Enables the VFIO platform driver to handle reset for AMD XGBE
+
+	  If you don't know what to do here, say N.

drivers/vfio/platform/reset/Makefile

 vfio-platform-calxedaxgmac-y := vfio_platform_calxedaxgmac.o
+vfio-platform-amdxgbe-y := vfio_platform_amdxgbe.o
 
 ccflags-y += -Idrivers/vfio/platform
 
 obj-$(CONFIG_VFIO_PLATFORM_CALXEDAXGMAC_RESET) += vfio-platform-calxedaxgmac.o
+obj-$(CONFIG_VFIO_PLATFORM_AMDXGBE_RESET) += vfio-platform-amdxgbe.o

drivers/vfio/platform/reset/vfio_platform_amdxgbe.c

+/*
+ * 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
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#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 *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 *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));
+}
+
+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;
+
+	if (!xgmac_regs->ioaddr) {
+		xgmac_regs->ioaddr =
+			ioremap_nocache(xgmac_regs->addr, xgmac_regs->size);
+		if (!xgmac_regs->ioaddr)
+			return -ENOMEM;
+	}
+	if (!xpcs_regs->ioaddr) {
+		xpcs_regs->ioaddr =
+			ioremap_nocache(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)
+		pr_warn("%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)
+		pr_warn("%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");

drivers/vfio/platform/reset/vfio_platform_calxedaxgmac.c

@@ -30,8 +30,6 @@
 #define DRIVER_AUTHOR   "Eric Auger <eric.auger@linaro.org>"
 #define DRIVER_DESC     "Reset support for Calxeda xgmac vfio platform device"
 
-#define CALXEDAXGMAC_COMPAT "calxeda,hb-xgmac"
-
 /* XGMAC Register definitions */
 #define XGMAC_CONTROL           0x00000000      /* MAC Configuration */
 
@@ -61,24 +59,25 @@ static inline void xgmac_mac_disable(void __iomem *ioaddr)
 
 int vfio_platform_calxedaxgmac_reset(struct vfio_platform_device *vdev)
 {
-	struct vfio_platform_region reg = vdev->regions[0];
+	struct vfio_platform_region *reg = &vdev->regions[0];
 
-	if (!reg.ioaddr) {
-		reg.ioaddr =
-			ioremap_nocache(reg.addr, reg.size);
-		if (!reg.ioaddr)
+	if (!reg->ioaddr) {
+		reg->ioaddr =
+			ioremap_nocache(reg->addr, reg->size);
+		if (!reg->ioaddr)
 			return -ENOMEM;
 	}
 
 	/* disable IRQ */
-	writel(0, reg.ioaddr + XGMAC_DMA_INTR_ENA);
+	writel(0, reg->ioaddr + XGMAC_DMA_INTR_ENA);
 
 	/* Disable the MAC core */
-	xgmac_mac_disable(reg.ioaddr);
+	xgmac_mac_disable(reg->ioaddr);
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(vfio_platform_calxedaxgmac_reset);
+
+module_vfio_reset_handler("calxeda,hb-xgmac", vfio_platform_calxedaxgmac_reset);
 
 MODULE_VERSION(DRIVER_VERSION);
 MODULE_LICENSE("GPL v2");

drivers/vfio/platform/vfio_amba.c

@@ -67,6 +67,7 @@ static int vfio_amba_probe(struct amba_device *adev, const struct amba_id *id)
 	vdev->flags = VFIO_DEVICE_FLAGS_AMBA;
 	vdev->get_resource = get_amba_resource;
 	vdev->get_irq = get_amba_irq;
+	vdev->parent_module = THIS_MODULE;
 
 	ret = vfio_platform_probe_common(vdev, &adev->dev);
 	if (ret) {

drivers/vfio/platform/vfio_platform.c

@@ -65,6 +65,7 @@ static int vfio_platform_probe(struct platform_device *pdev)
 	vdev->flags = VFIO_DEVICE_FLAGS_PLATFORM;
 	vdev->get_resource = get_platform_resource;
 	vdev->get_irq = get_platform_irq;
+	vdev->parent_module = THIS_MODULE;
 
 	ret = vfio_platform_probe_common(vdev, &pdev->dev);
 	if (ret)

drivers/vfio/platform/vfio_platform_common.c

@@ -23,44 +23,50 @@
 
 #include "vfio_platform_private.h"
 
-static DEFINE_MUTEX(driver_lock);
+#define DRIVER_VERSION  "0.10"
+#define DRIVER_AUTHOR   "Antonios Motakis <a.motakis@virtualopensystems.com>"
+#define DRIVER_DESC     "VFIO platform base module"
 
-static const struct vfio_platform_reset_combo reset_lookup_table[] = {
-	{
-		.compat = "calxeda,hb-xgmac",
-		.reset_function_name = "vfio_platform_calxedaxgmac_reset",
-		.module_name = "vfio-platform-calxedaxgmac",
-	},
-};
+static LIST_HEAD(reset_list);
+static DEFINE_MUTEX(driver_lock);
 
-static void vfio_platform_get_reset(struct vfio_platform_device *vdev,
-				    struct device *dev)
+static vfio_platform_reset_fn_t vfio_platform_lookup_reset(const char *compat,
+					struct module **module)
 {
-	const char *compat;
-	int (*reset)(struct vfio_platform_device *);
-	int ret, i;
-
-	ret = device_property_read_string(dev, "compatible", &compat);
-	if (ret)
-		return;
-
-	for (i = 0 ; i < ARRAY_SIZE(reset_lookup_table); i++) {
-		if (!strcmp(reset_lookup_table[i].compat, compat)) {
-			request_module(reset_lookup_table[i].module_name);
-			reset = __symbol_get(
-				reset_lookup_table[i].reset_function_name);
-			if (reset) {
-				vdev->reset = reset;
-				return;
-			}
+	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->reset;
+			break;
 		}
 	}
+	mutex_unlock(&driver_lock);
+	return reset_fn;
+}
+
+static void vfio_platform_get_reset(struct vfio_platform_device *vdev)
+{
+	char modname[256];
+
+	vdev->reset = vfio_platform_lookup_reset(vdev->compat,
+						&vdev->reset_module);
+	if (!vdev->reset) {
+		snprintf(modname, 256, "vfio-reset:%s", vdev->compat);
+		request_module(modname);
+		vdev->reset = vfio_platform_lookup_reset(vdev->compat,
+							 &vdev->reset_module);
+	}
 }
 
 static void vfio_platform_put_reset(struct vfio_platform_device *vdev)
 {
 	if (vdev->reset)
-		symbol_put_addr(vdev->reset);
+		module_put(vdev->reset_module);
 }
 
 static int vfio_platform_regions_init(struct vfio_platform_device *vdev)
@@ -138,15 +144,19 @@ static void vfio_platform_release(void *device_data)
 	mutex_lock(&driver_lock);
 
 	if (!(--vdev->refcnt)) {
-		if (vdev->reset)
+		if (vdev->reset) {
+			dev_info(vdev->device, "reset\n");
 			vdev->reset(vdev);
+		} else {
+			dev_warn(vdev->device, "no reset function found!\n");
+		}
 		vfio_platform_regions_cleanup(vdev);
 		vfio_platform_irq_cleanup(vdev);
 	}
 
 	mutex_unlock(&driver_lock);
 
-	module_put(THIS_MODULE);
+	module_put(vdev->parent_module);
 }
 
 static int vfio_platform_open(void *device_data)
@@ -154,7 +164,7 @@ static int vfio_platform_open(void *device_data)
 	struct vfio_platform_device *vdev = device_data;
 	int ret;
 
-	if (!try_module_get(THIS_MODULE))
+	if (!try_module_get(vdev->parent_module))
 		return -ENODEV;
 
 	mutex_lock(&driver_lock);
@@ -168,8 +178,12 @@ static int vfio_platform_open(void *device_data)
 		if (ret)
 			goto err_irq;
 
-		if (vdev->reset)
+		if (vdev->reset) {
+			dev_info(vdev->device, "reset\n");
 			vdev->reset(vdev);
+		} else {
+			dev_warn(vdev->device, "no reset function found!\n");
+		}
 	}
 
 	vdev->refcnt++;
@@ -307,17 +321,17 @@ static long vfio_platform_ioctl(void *device_data,
 	return -ENOTTY;
 }
 
-static ssize_t vfio_platform_read_mmio(struct vfio_platform_region reg,
+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 (!reg.ioaddr) {
-		reg.ioaddr =
-			ioremap_nocache(reg.addr, reg.size);
+	if (!reg->ioaddr) {
+		reg->ioaddr =
+			ioremap_nocache(reg->addr, reg->size);
 
-		if (!reg.ioaddr)
+		if (!reg->ioaddr)
 			return -ENOMEM;
 	}
 
@@ -327,7 +341,7 @@ static ssize_t vfio_platform_read_mmio(struct vfio_platform_region reg,
 		if (count >= 4 && !(off % 4)) {
 			u32 val;
 
-			val = ioread32(reg.ioaddr + off);
+			val = ioread32(reg->ioaddr + off);
 			if (copy_to_user(buf, &val, 4))
 				goto err;
 
@@ -335,7 +349,7 @@ static ssize_t vfio_platform_read_mmio(struct vfio_platform_region reg,
 		} else if (count >= 2 && !(off % 2)) {
 			u16 val;
 
-			val = ioread16(reg.ioaddr + off);
+			val = ioread16(reg->ioaddr + off);
 			if (copy_to_user(buf, &val, 2))
 				goto err;
 
@@ -343,7 +357,7 @@ static ssize_t vfio_platform_read_mmio(struct vfio_platform_region reg,
 		} else {
 			u8 val;
 
-			val = ioread8(reg.ioaddr + off);
+			val = ioread8(reg->ioaddr + off);
 			if (copy_to_user(buf, &val, 1))
 				goto err;
 
@@ -376,7 +390,7 @@ static ssize_t vfio_platform_read(void *device_data, char __user *buf,
 		return -EINVAL;
 
 	if (vdev->regions[index].type & VFIO_PLATFORM_REGION_TYPE_MMIO)
-		return vfio_platform_read_mmio(vdev->regions[index],
+		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 */
@@ -384,17 +398,17 @@ static ssize_t vfio_platform_read(void *device_data, char __user *buf,
 	return -EINVAL;
 }
 
-static ssize_t vfio_platform_write_mmio(struct vfio_platform_region reg,
+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 (!reg.ioaddr) {
-		reg.ioaddr =
-			ioremap_nocache(reg.addr, reg.size);
+	if (!reg->ioaddr) {
+		reg->ioaddr =
+			ioremap_nocache(reg->addr, reg->size);
 
-		if (!reg.ioaddr)
+		if (!reg->ioaddr)
 			return -ENOMEM;
 	}
 
@@ -406,7 +420,7 @@ static ssize_t vfio_platform_write_mmio(struct vfio_platform_region reg,
 
 			if (copy_from_user(&val, buf, 4))
 				goto err;
-			iowrite32(val, reg.ioaddr + off);
+			iowrite32(val, reg->ioaddr + off);
 
 			filled = 4;
 		} else if (count >= 2 && !(off % 2)) {
@@ -414,7 +428,7 @@ static ssize_t vfio_platform_write_mmio(struct vfio_platform_region reg,
 
 			if (copy_from_user(&val, buf, 2))
 				goto err;
-			iowrite16(val, reg.ioaddr + off);
+			iowrite16(val, reg->ioaddr + off);
 
 			filled = 2;
 		} else {
@@ -422,7 +436,7 @@ static ssize_t vfio_platform_write_mmio(struct vfio_platform_region reg,
 
 			if (copy_from_user(&val, buf, 1))
 				goto err;
-			iowrite8(val, reg.ioaddr + off);
+			iowrite8(val, reg->ioaddr + off);
 
 			filled = 1;
 		}
@@ -452,7 +466,7 @@ static ssize_t vfio_platform_write(void *device_data, const char __user *buf,
 		return -EINVAL;
 
 	if (vdev->regions[index].type & VFIO_PLATFORM_REGION_TYPE_MMIO)
-		return vfio_platform_write_mmio(vdev->regions[index],
+		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 */
@@ -539,6 +553,14 @@ int vfio_platform_probe_common(struct vfio_platform_device *vdev,
 	if (!vdev)
 		return -EINVAL;
 
+	ret = device_property_read_string(dev, "compatible", &vdev->compat);
+	if (ret) {
+		pr_err("VFIO: cannot retrieve compat for %s\n", vdev->name);
+		return -EINVAL;
+	}
+
+	vdev->device = dev;
+
 	group = iommu_group_get(dev);
 	if (!group) {
 		pr_err("VFIO: No IOMMU group for device %s\n", vdev->name);
@@ -551,7 +573,7 @@ int vfio_platform_probe_common(struct vfio_platform_device *vdev,
 		return ret;
 	}
 
-	vfio_platform_get_reset(vdev, dev);
+	vfio_platform_get_reset(vdev);
 
 	mutex_init(&vdev->igate);
 
@@ -573,3 +595,34 @@ struct vfio_platform_device *vfio_platform_remove_common(struct device *dev)
 	return vdev;
 }
 EXPORT_SYMBOL_GPL(vfio_platform_remove_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->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);

drivers/vfio/platform/vfio_platform_irq.c

@@ -185,6 +185,7 @@ static int vfio_set_trigger(struct vfio_platform_device *vdev, int index,
 	int ret;
 
 	if (irq->trigger) {
+		irq_clear_status_flags(irq->hwirq, IRQ_NOAUTOEN);
 		free_irq(irq->hwirq, irq);
 		kfree(irq->name);
 		eventfd_ctx_put(irq->trigger);

drivers/vfio/platform/vfio_platform_private.h

@@ -56,6 +56,10 @@ struct vfio_platform_device {
 	u32				num_irqs;
 	int				refcnt;
 	struct mutex			igate;
+	struct module			*parent_module;
+	const char			*compat;
+	struct module			*reset_module;
+	struct device			*device;
 
 	/*
 	 * These fields should be filled by the bus specific binder
@@ -70,10 +74,13 @@ struct vfio_platform_device {
 	int	(*reset)(struct vfio_platform_device *vdev);
 };
 
-struct vfio_platform_reset_combo {
-	const char *compat;
-	const char *reset_function_name;
-	const char *module_name;
+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 reset;
 };
 
 extern int vfio_platform_probe_common(struct vfio_platform_device *vdev,
@@ -89,4 +96,29 @@ extern int vfio_platform_set_irqs_ioctl(struct vfio_platform_device *vdev,
 					unsigned start, unsigned count,
 					void *data);
 
+extern void __vfio_platform_register_reset(struct vfio_platform_reset_node *n);
+extern 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,					\
+	.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 */

drivers/vfio/vfio_iommu_type1.c

@@ -403,13 +403,26 @@ static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma)
 static unsigned long vfio_pgsize_bitmap(struct vfio_iommu *iommu)
 {
 	struct vfio_domain *domain;
-	unsigned long bitmap = PAGE_MASK;
+	unsigned long bitmap = ULONG_MAX;
 
 	mutex_lock(&iommu->lock);
 	list_for_each_entry(domain, &iommu->domain_list, next)
 		bitmap &= domain->domain->ops->pgsize_bitmap;
 	mutex_unlock(&iommu->lock);
 
+	/*
+	 * In case the IOMMU supports page sizes smaller than PAGE_SIZE
+	 * we pretend PAGE_SIZE is supported and hide sub-PAGE_SIZE sizes.
+	 * That way the user will be able to map/unmap buffers whose size/
+	 * start address is aligned with PAGE_SIZE. Pinning code uses that
+	 * granularity while iommu driver can use the sub-PAGE_SIZE size
+	 * to map the buffer.
+	 */
+	if (bitmap & ~PAGE_MASK) {
+		bitmap &= PAGE_MASK;
+		bitmap |= PAGE_SIZE;
+	}
+
 	return bitmap;
 }
 

include/linux/vfio.h

@@ -44,6 +44,9 @@ struct vfio_device_ops {
 	void	(*request)(void *device_data, unsigned int count);
 };
 
+extern struct iommu_group *vfio_iommu_group_get(struct device *dev);
+extern void vfio_iommu_group_put(struct iommu_group *group, struct device *dev);
+
 extern int vfio_add_group_dev(struct device *dev,
 			      const struct vfio_device_ops *ops,
 			      void *device_data);

include/uapi/linux/vfio.h

@@ -38,6 +38,13 @@
 
 #define VFIO_SPAPR_TCE_v2_IOMMU		7
 
+/*
+ * The No-IOMMU IOMMU offers no translation or isolation for devices and
+ * supports no ioctls outside of VFIO_CHECK_EXTENSION.  Use of VFIO's No-IOMMU
+ * code will taint the host kernel and should be used with extreme caution.
+ */
+#define VFIO_NOIOMMU_IOMMU		8
+
 /*
  * The IOCTL interface is designed for extensibility by embedding the
  * structure length (argsz) and flags into structures passed between