Merge tag 'iommu-updates-v5.1' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull IOMMU updates from Joerg Roedel:

 - A big cleanup and optimization patch-set for the Tegra GART driver

 - Documentation updates and fixes for the IOMMU-API

 - Support for page request in Intel VT-d scalable mode

 - Intel VT-d dma_[un]map_resource() support

 - Updates to the ATS enabling code for PCI (acked by Bjorn) and Intel
   VT-d to align with the latest version of the ATS spec

 - Relaxed IRQ source checking in the Intel VT-d driver for some aliased
   devices, needed for future devices which send IRQ messages from more
   than on request-ID

 - IRQ remapping driver for Hyper-V

 - Patches to make generic IOVA and IO-Page-Table code usable outside of
   the IOMMU code

 - Various other small fixes and cleanups

* tag 'iommu-updates-v5.1' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (60 commits)
  iommu/vt-d: Get domain ID before clear pasid entry
  iommu/vt-d: Fix NULL pointer reference in intel_svm_bind_mm()
  iommu/vt-d: Set context field after value initialized
  iommu/vt-d: Disable ATS support on untrusted devices
  iommu/mediatek: Fix semicolon code style issue
  MAINTAINERS: Add Hyper-V IOMMU driver into Hyper-V CORE AND DRIVERS scope
  iommu/hyper-v: Add Hyper-V stub IOMMU driver
  x86/Hyper-V: Set x2apic destination mode to physical when x2apic is available
  PCI/ATS: Add inline to pci_prg_resp_pasid_required()
  iommu/vt-d: Check identity map for hot-added devices
  iommu: Fix IOMMU debugfs fallout
  iommu: Document iommu_ops.is_attach_deferred()
  iommu: Document iommu_ops.iotlb_sync_map()
  iommu/vt-d: Enable ATS only if the device uses page aligned address.
  PCI/ATS: Add pci_ats_page_aligned() interface
  iommu/vt-d: Fix PRI/PASID dependency issue.
  PCI/ATS: Add pci_prg_resp_pasid_required() interface.
  iommu/vt-d: Allow interrupts from the entire bus for aliased devices
  iommu/vt-d: Add helper to set an IRTE to verify only the bus number
  iommu: Fix flush_tlb_all typo
  ...

44 files changed, 838 insertions, 611 deletions

diff --git a/Documentation/devicetree/bindings/iommu/nvidia,tegra20-gart.txt b/Documentation/devicetree/bindings/iommu/nvidia,tegra20-gart.txt
deleted file mode 100644
index 099d9362ebc1..000000000000
--- a/Documentation/devicetree/bindings/iommu/nvidia,tegra20-gart.txt
+++ /dev/null
@@ -1,14 +0,0 @@
-NVIDIA Tegra 20 GART
-
-Required properties:
-- compatible: "nvidia,tegra20-gart"
-- reg: Two pairs of cells specifying the physical address and size of
-  the memory controller registers and the GART aperture respectively.
-
-Example:
-
-	gart {
-		compatible = "nvidia,tegra20-gart";
-		reg = <0x7000f024 0x00000018	/* controller registers */
-		       0x58000000 0x02000000>;	/* GART aperture */
-	};
diff --git a/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra20-mc.txt b/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra20-mc.txt
index 7d60a50a4fa1..e55328237df4 100644
--- a/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra20-mc.txt
+++ b/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra20-mc.txt
@@ -1,26 +1,37 @@
 NVIDIA Tegra20 MC(Memory Controller)
 
 Required properties:
-- compatible : "nvidia,tegra20-mc"
-- reg : Should contain 2 register ranges(address and length); see the
-  example below. Note that the MC registers are interleaved with the
-  GART registers, and hence must be represented as multiple ranges.
+- compatible : "nvidia,tegra20-mc-gart"
+- reg : Should contain 2 register ranges: physical base address and length of
+  the controller's registers and the GART aperture respectively.
+- clocks: Must contain an entry for each entry in clock-names.
+  See ../clocks/clock-bindings.txt for details.
+- clock-names: Must include the following entries:
+  - mc: the module's clock input
 - interrupts : Should contain MC General interrupt.
 - #reset-cells : Should be 1. This cell represents memory client module ID.
   The assignments may be found in header file <dt-bindings/memory/tegra20-mc.h>
   or in the TRM documentation.
+- #iommu-cells: Should be 0. This cell represents the number of cells in an
+  IOMMU specifier needed to encode an address. GART supports only a single
+  address space that is shared by all devices, therefore no additional
+  information needed for the address encoding.
 
 Example:
 	mc: memory-controller@7000f000 {
-		compatible = "nvidia,tegra20-mc";
-		reg = <0x7000f000 0x024
-		       0x7000f03c 0x3c4>;
-		interrupts = <0 77 0x04>;
+		compatible = "nvidia,tegra20-mc-gart";
+		reg = <0x7000f000 0x400		/* controller registers */
+		       0x58000000 0x02000000>;	/* GART aperture */
+		clocks = <&tegra_car TEGRA20_CLK_MC>;
+		clock-names = "mc";
+		interrupts = <GIC_SPI 77 0x04>;
 		#reset-cells = <1>;
+		#iommu-cells = <0>;
 	};
 
 	video-codec@6001a000 {
 		compatible = "nvidia,tegra20-vde";
 		...
 		resets = <&mc TEGRA20_MC_RESET_VDE>;
+		iommus = <&mc>;
 	};
diff --git a/MAINTAINERS b/MAINTAINERS
index b5bffd2d7f8c..08995da6e16a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7170,6 +7170,7 @@ F:	drivers/net/hyperv/
 F:	drivers/scsi/storvsc_drv.c
 F:	drivers/uio/uio_hv_generic.c
 F:	drivers/video/fbdev/hyperv_fb.c
+F:	drivers/iommu/hyperv_iommu.c
 F:	net/vmw_vsock/hyperv_transport.c
 F:	include/linux/hyperv.h
 F:	include/uapi/linux/hyperv.h
diff --git a/arch/arm/boot/dts/tegra20.dtsi b/arch/arm/boot/dts/tegra20.dtsi
index dcad6d6128cf..8c942e60703e 100644
--- a/arch/arm/boot/dts/tegra20.dtsi
+++ b/arch/arm/boot/dts/tegra20.dtsi
@@ -616,17 +616,14 @@
 	};
 
 	mc: memory-controller@7000f000 {
-		compatible = "nvidia,tegra20-mc";
-		reg = <0x7000f000 0x024
-		       0x7000f03c 0x3c4>;
+		compatible = "nvidia,tegra20-mc-gart";
+		reg = <0x7000f000 0x400		/* controller registers */
+		       0x58000000 0x02000000>;	/* GART aperture */
+		clocks = <&tegra_car TEGRA20_CLK_MC>;
+		clock-names = "mc";
 		interrupts = <GIC_SPI 77 IRQ_TYPE_LEVEL_HIGH>;
 		#reset-cells = <1>;
-	};
-
-	iommu@7000f024 {
-		compatible = "nvidia,tegra20-gart";
-		reg = <0x7000f024 0x00000018	/* controller registers */
-		       0x58000000 0x02000000>;	/* GART aperture */
+		#iommu-cells = <0>;
 	};
 
 	memory-controller@7000f400 {
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index e81a2db42df7..3fa238a137d2 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -328,6 +328,18 @@ static void __init ms_hyperv_init_platform(void)
 # ifdef CONFIG_SMP
 	smp_ops.smp_prepare_boot_cpu = hv_smp_prepare_boot_cpu;
 # endif
+
+	/*
+	 * Hyper-V doesn't provide irq remapping for IO-APIC. To enable x2apic,
+	 * set x2apic destination mode to physcial mode when x2apic is available
+	 * and Hyper-V IOMMU driver makes sure cpus assigned with IO-APIC irqs
+	 * have 8-bit APIC id.
+	 */
+# ifdef CONFIG_X86_X2APIC
+	if (x2apic_supported())
+		x2apic_phys = 1;
+# endif
+
 #endif
 }
 
diff --git a/drivers/Makefile b/drivers/Makefile
index bb15b9d0e793..c61cde554340 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -56,7 +56,7 @@ obj-y				+= tty/
 obj-y				+= char/
 
 # iommu/ comes before gpu as gpu are using iommu controllers
-obj-$(CONFIG_IOMMU_SUPPORT)	+= iommu/
+obj-y				+= iommu/
 
 # gpu/ comes after char for AGP vs DRM startup and after iommu
 obj-y				+= gpu/
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index d9a25715650e..6f07f3b21816 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -1,3 +1,7 @@
+# The IOVA library may also be used by non-IOMMU_API users
+config IOMMU_IOVA
+	tristate
+
 # IOMMU_API always gets selected by whoever wants it.
 config IOMMU_API
 	bool
@@ -81,9 +85,6 @@ config IOMMU_DEFAULT_PASSTHROUGH
 
 	  If unsure, say N here.
 
-config IOMMU_IOVA
-	tristate
-
 config OF_IOMMU
        def_bool y
        depends on OF && IOMMU_API
@@ -282,6 +283,7 @@ config ROCKCHIP_IOMMU
 config TEGRA_IOMMU_GART
 	bool "Tegra GART IOMMU Support"
 	depends on ARCH_TEGRA_2x_SOC
+	depends on TEGRA_MC
 	select IOMMU_API
 	help
 	  Enables support for remapping discontiguous physical memory
@@ -435,4 +437,13 @@ config QCOM_IOMMU
 	help
 	  Support for IOMMU on certain Qualcomm SoCs.
 
+config HYPERV_IOMMU
+	bool "Hyper-V x2APIC IRQ Handling"
+	depends on HYPERV
+	select IOMMU_API
+	default HYPERV
+	help
+	  Stub IOMMU driver to handle IRQs as to allow Hyper-V Linux
+	  guests to run with x2APIC mode enabled.
+
 endif # IOMMU_SUPPORT
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index a158a68c8ea8..8c71a15e986b 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -32,3 +32,4 @@ obj-$(CONFIG_EXYNOS_IOMMU) += exynos-iommu.o
 obj-$(CONFIG_FSL_PAMU) += fsl_pamu.o fsl_pamu_domain.o
 obj-$(CONFIG_S390_IOMMU) += s390-iommu.o
 obj-$(CONFIG_QCOM_IOMMU) += qcom_iommu.o
+obj-$(CONFIG_HYPERV_IOMMU) += hyperv-iommu.o
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 2a7b78bb98b4..6b0760dafb3e 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -18,6 +18,7 @@
  */
 
 #define pr_fmt(fmt)     "AMD-Vi: " fmt
+#define dev_fmt(fmt)    pr_fmt(fmt)
 
 #include <linux/ratelimit.h>
 #include <linux/pci.h>
@@ -279,10 +280,10 @@ static u16 get_alias(struct device *dev)
 		return pci_alias;
 	}
 
-	pr_info("Using IVRS reported alias %02x:%02x.%d "
-		"for device %s[%04x:%04x], kernel reported alias "
+	pci_info(pdev, "Using IVRS reported alias %02x:%02x.%d "
+		"for device [%04x:%04x], kernel reported alias "
 		"%02x:%02x.%d\n", PCI_BUS_NUM(ivrs_alias), PCI_SLOT(ivrs_alias),
-		PCI_FUNC(ivrs_alias), dev_name(dev), pdev->vendor, pdev->device,
+		PCI_FUNC(ivrs_alias), pdev->vendor, pdev->device,
 		PCI_BUS_NUM(pci_alias), PCI_SLOT(pci_alias),
 		PCI_FUNC(pci_alias));
 
@@ -293,9 +294,8 @@ static u16 get_alias(struct device *dev)
 	if (pci_alias == devid &&
 	    PCI_BUS_NUM(ivrs_alias) == pdev->bus->number) {
 		pci_add_dma_alias(pdev, ivrs_alias & 0xff);
-		pr_info("Added PCI DMA alias %02x.%d for %s\n",
-			PCI_SLOT(ivrs_alias), PCI_FUNC(ivrs_alias),
-			dev_name(dev));
+		pci_info(pdev, "Added PCI DMA alias %02x.%d\n",
+			PCI_SLOT(ivrs_alias), PCI_FUNC(ivrs_alias));
 	}
 
 	return ivrs_alias;
@@ -545,7 +545,7 @@ static void amd_iommu_report_page_fault(u16 devid, u16 domain_id,
 		dev_data = get_dev_data(&pdev->dev);
 
 	if (dev_data && __ratelimit(&dev_data->rs)) {
-		dev_err(&pdev->dev, "Event logged [IO_PAGE_FAULT domain=0x%04x address=0x%llx flags=0x%04x]\n",
+		pci_err(pdev, "Event logged [IO_PAGE_FAULT domain=0x%04x address=0x%llx flags=0x%04x]\n",
 			domain_id, address, flags);
 	} else if (printk_ratelimit()) {
 		pr_err("Event logged [IO_PAGE_FAULT device=%02x:%02x.%x domain=0x%04x address=0x%llx flags=0x%04x]\n",
@@ -2258,8 +2258,7 @@ static int amd_iommu_add_device(struct device *dev)
 	ret = iommu_init_device(dev);
 	if (ret) {
 		if (ret != -ENOTSUPP)
-			pr_err("Failed to initialize device %s - trying to proceed anyway\n",
-				dev_name(dev));
+			dev_err(dev, "Failed to initialize - trying to proceed anyway\n");
 
 		iommu_ignore_device(dev);
 		dev->dma_ops = NULL;
@@ -2569,6 +2568,7 @@ static int map_sg(struct device *dev, struct scatterlist *sglist,
 	struct scatterlist *s;
 	unsigned long address;
 	u64 dma_mask;
+	int ret;
 
 	domain = get_domain(dev);
 	if (IS_ERR(domain))
@@ -2591,7 +2591,6 @@ static int map_sg(struct device *dev, struct scatterlist *sglist,
 
 		for (j = 0; j < pages; ++j) {
 			unsigned long bus_addr, phys_addr;
-			int ret;
 
 			bus_addr  = address + s->dma_address + (j << PAGE_SHIFT);
 			phys_addr = (sg_phys(s) & PAGE_MASK) + (j << PAGE_SHIFT);
@@ -2612,8 +2611,8 @@ static int map_sg(struct device *dev, struct scatterlist *sglist,
 	return nelems;
 
 out_unmap:
-	pr_err("%s: IOMMU mapping error in map_sg (io-pages: %d)\n",
-	       dev_name(dev), npages);
+	dev_err(dev, "IOMMU mapping error in map_sg (io-pages: %d reason: %d)\n",
+		npages, ret);
 
 	for_each_sg(sglist, s, nelems, i) {
 		int j, pages = iommu_num_pages(sg_phys(s), s->length, PAGE_SIZE);
@@ -2807,7 +2806,7 @@ static int init_reserved_iova_ranges(void)
 					   IOVA_PFN(r->start),
 					   IOVA_PFN(r->end));
 			if (!val) {
-				pr_err("Reserve pci-resource range failed\n");
+				pci_err(pdev, "Reserve pci-resource range %pR failed\n", r);
 				return -ENOMEM;
 			}
 		}
@@ -3177,8 +3176,7 @@ static void amd_iommu_get_resv_regions(struct device *dev,
 						 length, prot,
 						 IOMMU_RESV_DIRECT);
 		if (!region) {
-			pr_err("Out of memory allocating dm-regions for %s\n",
-				dev_name(dev));
+			dev_err(dev, "Out of memory allocating dm-regions\n");
 			return;
 		}
 		list_add_tail(&region->list, head);
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 66123b911ec8..f773792d77fd 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -18,6 +18,7 @@
  */
 
 #define pr_fmt(fmt)     "AMD-Vi: " fmt
+#define dev_fmt(fmt)    pr_fmt(fmt)
 
 #include <linux/pci.h>
 #include <linux/acpi.h>
@@ -1457,8 +1458,7 @@ static void amd_iommu_erratum_746_workaround(struct amd_iommu *iommu)
 	pci_write_config_dword(iommu->dev, 0xf0, 0x90 | (1 << 8));
 
 	pci_write_config_dword(iommu->dev, 0xf4, value | 0x4);
-	pr_info("Applying erratum 746 workaround for IOMMU at %s\n",
-		dev_name(&iommu->dev->dev));
+	pci_info(iommu->dev, "Applying erratum 746 workaround\n");
 
 	/* Clear the enable writing bit */
 	pci_write_config_dword(iommu->dev, 0xf0, 0x90);
@@ -1488,8 +1488,7 @@ static void amd_iommu_ats_write_check_workaround(struct amd_iommu *iommu)
 	/* Set L2_DEBUG_3[AtsIgnoreIWDis] = 1 */
 	iommu_write_l2(iommu, 0x47, value | BIT(0));
 
-	pr_info("Applying ATS write check workaround for IOMMU at %s\n",
-		dev_name(&iommu->dev->dev));
+	pci_info(iommu->dev, "Applying ATS write check workaround\n");
 }
 
 /*
@@ -1665,6 +1664,7 @@ static int iommu_pc_get_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
 
 static void init_iommu_perf_ctr(struct amd_iommu *iommu)
 {
+	struct pci_dev *pdev = iommu->dev;
 	u64 val = 0xabcd, val2 = 0;
 
 	if (!iommu_feature(iommu, FEATURE_PC))
@@ -1676,12 +1676,12 @@ static void init_iommu_perf_ctr(struct amd_iommu *iommu)
 	if ((iommu_pc_get_set_reg(iommu, 0, 0, 0, &val, true)) ||
 	    (iommu_pc_get_set_reg(iommu, 0, 0, 0, &val2, false)) ||
 	    (val != val2)) {
-		pr_err("Unable to write to IOMMU perf counter.\n");
+		pci_err(pdev, "Unable to write to IOMMU perf counter.\n");
 		amd_iommu_pc_present = false;
 		return;
 	}
 
-	pr_info("IOMMU performance counters supported\n");
+	pci_info(pdev, "IOMMU performance counters supported\n");
 
 	val = readl(iommu->mmio_base + MMIO_CNTR_CONF_OFFSET);
 	iommu->max_banks = (u8) ((val >> 12) & 0x3f);
@@ -1840,14 +1840,14 @@ static void print_iommu_info(void)
 	struct amd_iommu *iommu;
 
 	for_each_iommu(iommu) {
+		struct pci_dev *pdev = iommu->dev;
 		int i;
 
-		pr_info("Found IOMMU at %s cap 0x%hx\n",
-			dev_name(&iommu->dev->dev), iommu->cap_ptr);
+		pci_info(pdev, "Found IOMMU cap 0x%hx\n", iommu->cap_ptr);
 
 		if (iommu->cap & (1 << IOMMU_CAP_EFR)) {
-			pr_info("Extended features (%#llx):\n",
-				iommu->features);
+			pci_info(pdev, "Extended features (%#llx):\n",
+				 iommu->features);
 			for (i = 0; i < ARRAY_SIZE(feat_str); ++i) {
 				if (iommu_feature(iommu, (1ULL << i)))
 					pr_cont(" %s", feat_str[i]);
diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c
index 23dae9348ace..5d7ef750e4a0 100644
--- a/drivers/iommu/amd_iommu_v2.c
+++ b/drivers/iommu/amd_iommu_v2.c
@@ -370,29 +370,6 @@ static struct pasid_state *mn_to_state(struct mmu_notifier *mn)
 	return container_of(mn, struct pasid_state, mn);
 }
 
-static void __mn_flush_page(struct mmu_notifier *mn,
-			    unsigned long address)
-{
-	struct pasid_state *pasid_state;
-	struct device_state *dev_state;
-
-	pasid_state = mn_to_state(mn);
-	dev_state   = pasid_state->device_state;
-
-	amd_iommu_flush_page(dev_state->domain, pasid_state->pasid, address);
-}
-
-static int mn_clear_flush_young(struct mmu_notifier *mn,
-				struct mm_struct *mm,
-				unsigned long start,
-				unsigned long end)
-{
-	for (; start < end; start += PAGE_SIZE)
-		__mn_flush_page(mn, start);
-
-	return 0;
-}
-
 static void mn_invalidate_range(struct mmu_notifier *mn,
 				struct mm_struct *mm,
 				unsigned long start, unsigned long end)
@@ -430,7 +407,6 @@ static void mn_release(struct mmu_notifier *mn, struct mm_struct *mm)
 
 static const struct mmu_notifier_ops iommu_mn = {
 	.release		= mn_release,
-	.clear_flush_young      = mn_clear_flush_young,
 	.invalidate_range       = mn_invalidate_range,
 };
 
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 0d284029dc73..d3880010c6cf 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -18,6 +18,7 @@
 #include <linux/dma-iommu.h>
 #include <linux/err.h>
 #include <linux/interrupt.h>
+#include <linux/io-pgtable.h>
 #include <linux/iommu.h>
 #include <linux/iopoll.h>
 #include <linux/init.h>
@@ -32,8 +33,6 @@
 
 #include <linux/amba/bus.h>
 
-#include "io-pgtable.h"
-
 /* MMIO registers */
 #define ARM_SMMU_IDR0			0x0
 #define IDR0_ST_LVL			GENMASK(28, 27)
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index af18a7e7f917..045d93884164 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -39,6 +39,7 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/io-64-nonatomic-hi-lo.h>
+#include <linux/io-pgtable.h>
 #include <linux/iommu.h>
 #include <linux/iopoll.h>
 #include <linux/init.h>
@@ -56,7 +57,6 @@
 #include <linux/amba/bus.h>
 #include <linux/fsl/mc.h>
 
-#include "io-pgtable.h"
 #include "arm-smmu-regs.h"
 
 #define ARM_MMU500_ACTLR_CPRE		(1 << 1)
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index d19f3d6b43c1..77aabe637a60 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -289,7 +289,7 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 {
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	struct iova_domain *iovad = &cookie->iovad;
-	unsigned long order, base_pfn, end_pfn;
+	unsigned long order, base_pfn;
 	int attr;
 
 	if (!cookie || cookie->type != IOMMU_DMA_IOVA_COOKIE)
@@ -298,7 +298,6 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 	/* Use the smallest supported page size for IOVA granularity */
 	order = __ffs(domain->pgsize_bitmap);
 	base_pfn = max_t(unsigned long, 1, base >> order);
-	end_pfn = (base + size - 1) >> order;
 
 	/* Check the domain allows at least some access to the device... */
 	if (domain->geometry.force_aperture) {
diff --git a/drivers/iommu/hyperv-iommu.c b/drivers/iommu/hyperv-iommu.c
new file mode 100644
index 000000000000..a386b83e0e34
--- /dev/null
+++ b/drivers/iommu/hyperv-iommu.c
@@ -0,0 +1,196 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Hyper-V stub IOMMU driver.
+ *
+ * Copyright (C) 2019, Microsoft, Inc.
+ *
+ * Author : Lan Tianyu <Tianyu.Lan@microsoft.com>
+ */
+
+#include <linux/types.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/iommu.h>
+#include <linux/module.h>
+
+#include <asm/apic.h>
+#include <asm/cpu.h>
+#include <asm/hw_irq.h>
+#include <asm/io_apic.h>
+#include <asm/irq_remapping.h>
+#include <asm/hypervisor.h>
+
+#include "irq_remapping.h"
+
+#ifdef CONFIG_IRQ_REMAP
+
+/*
+ * According 82093AA IO-APIC spec , IO APIC has a 24-entry Interrupt
+ * Redirection Table. Hyper-V exposes one single IO-APIC and so define
+ * 24 IO APIC remmapping entries.
+ */
+#define IOAPIC_REMAPPING_ENTRY 24
+
+static cpumask_t ioapic_max_cpumask = { CPU_BITS_NONE };
+static struct irq_domain *ioapic_ir_domain;
+
+static int hyperv_ir_set_affinity(struct irq_data *data,
+		const struct cpumask *mask, bool force)
+{
+	struct irq_data *parent = data->parent_data;
+	struct irq_cfg *cfg = irqd_cfg(data);
+	struct IO_APIC_route_entry *entry;
+	int ret;
+
+	/* Return error If new irq affinity is out of ioapic_max_cpumask. */
+	if (!cpumask_subset(mask, &ioapic_max_cpumask))
+		return -EINVAL;
+
+	ret = parent->chip->irq_set_affinity(parent, mask, force);
+	if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
+		return ret;
+
+	entry = data->chip_data;
+	entry->dest = cfg->dest_apicid;
+	entry->vector = cfg->vector;
+	send_cleanup_vector(cfg);
+
+	return 0;
+}
+
+static struct irq_chip hyperv_ir_chip = {
+	.name			= "HYPERV-IR",
+	.irq_ack		= apic_ack_irq,
+	.irq_set_affinity	= hyperv_ir_set_affinity,
+};
+
+static int hyperv_irq_remapping_alloc(struct irq_domain *domain,
+				     unsigned int virq, unsigned int nr_irqs,
+				     void *arg)
+{
+	struct irq_alloc_info *info = arg;
+	struct irq_data *irq_data;
+	struct irq_desc *desc;
+	int ret = 0;
+
+	if (!info || info->type != X86_IRQ_ALLOC_TYPE_IOAPIC || nr_irqs > 1)
+		return -EINVAL;
+
+	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
+	if (ret < 0)
+		return ret;
+
+	irq_data = irq_domain_get_irq_data(domain, virq);
+	if (!irq_data) {
+		irq_domain_free_irqs_common(domain, virq, nr_irqs);
+		return -EINVAL;
+	}
+
+	irq_data->chip = &hyperv_ir_chip;
+
+	/*
+	 * If there is interrupt remapping function of IOMMU, setting irq
+	 * affinity only needs to change IRTE of IOMMU. But Hyper-V doesn't
+	 * support interrupt remapping function, setting irq affinity of IO-APIC
+	 * interrupts still needs to change IO-APIC registers. But ioapic_
+	 * configure_entry() will ignore value of cfg->vector and cfg->
+	 * dest_apicid when IO-APIC's parent irq domain is not the vector
+	 * domain.(See ioapic_configure_entry()) In order to setting vector
+	 * and dest_apicid to IO-APIC register, IO-APIC entry pointer is saved
+	 * in the chip_data and hyperv_irq_remapping_activate()/hyperv_ir_set_
+	 * affinity() set vector and dest_apicid directly into IO-APIC entry.
+	 */
+	irq_data->chip_data = info->ioapic_entry;
+
+	/*
+	 * Hypver-V IO APIC irq affinity should be in the scope of
+	 * ioapic_max_cpumask because no irq remapping support.
+	 */
+	desc = irq_data_to_desc(irq_data);
+	cpumask_copy(desc->irq_common_data.affinity, &ioapic_max_cpumask);
+
+	return 0;
+}
+
+static void hyperv_irq_remapping_free(struct irq_domain *domain,
+				 unsigned int virq, unsigned int nr_irqs)
+{
+	irq_domain_free_irqs_common(domain, virq, nr_irqs);
+}
+
+static int hyperv_irq_remapping_activate(struct irq_domain *domain,
+			  struct irq_data *irq_data, bool reserve)
+{
+	struct irq_cfg *cfg = irqd_cfg(irq_data);
+	struct IO_APIC_route_entry *entry = irq_data->chip_data;
+
+	entry->dest = cfg->dest_apicid;
+	entry->vector = cfg->vector;
+
+	return 0;
+}
+
+static struct irq_domain_ops hyperv_ir_domain_ops = {
+	.alloc = hyperv_irq_remapping_alloc,
+	.free = hyperv_irq_remapping_free,
+	.activate = hyperv_irq_remapping_activate,
+};
+
+static int __init hyperv_prepare_irq_remapping(void)
+{
+	struct fwnode_handle *fn;
+	int i;
+
+	if (!hypervisor_is_type(X86_HYPER_MS_HYPERV) ||
+	    !x2apic_supported())
+		return -ENODEV;
+
+	fn = irq_domain_alloc_named_id_fwnode("HYPERV-IR", 0);
+	if (!fn)
+		return -ENOMEM;
+
+	ioapic_ir_domain =
+		irq_domain_create_hierarchy(arch_get_ir_parent_domain(),
+				0, IOAPIC_REMAPPING_ENTRY, fn,
+				&hyperv_ir_domain_ops, NU