Merge tag 'iommu-updates-v7.0' of git://git.kernel.org/pub/scm/linux/kernel/git/iommu/linux

Pull iommu updates from Joerg Roedel:
 "Core changes:
   - Rust bindings for IO-pgtable code
   - IOMMU page allocation debugging support
   - Disable ATS during PCI resets

  Intel VT-d changes:
   - Skip dev-iotlb flush for inaccessible PCIe device
   - Flush cache for PASID table before using it
   - Use right invalidation method for SVA and NESTED domains
   - Ensure atomicity in context and PASID entry updates

  AMD-Vi changes:
   - Support for nested translations
   - Other minor improvements

  ARM-SMMU-v2 changes:
   - Configure SoC-specific prefetcher settings for Qualcomm's "MDSS"

  ARM-SMMU-v3 changes:
   - Improve CMDQ locking fairness for pathetically small queue sizes
   - Remove tracking of the IAS as this is only relevant for AArch32 and
     was causing C_BAD_STE errors
   - Add device-tree support for NVIDIA's CMDQV extension
   - Allow some hitless transitions for the 'MEV' and 'EATS' STE fields
   - Don't disable ATS for nested S1-bypass nested domains
   - Additions to the kunit selftests"

* tag 'iommu-updates-v7.0' of git://git.kernel.org/pub/scm/linux/kernel/git/iommu/linux: (54 commits)
  iommupt: Always add IOVA range to iotlb_gather in gather_range_pages()
  iommu/amd: serialize sequence allocation under concurrent TLB invalidations
  iommu/amd: Fix type of type parameter to amd_iommufd_hw_info()
  iommu/arm-smmu-v3: Do not set disable_ats unless vSTE is Translate
  iommu/arm-smmu-v3-test: Add nested s1bypass/s1dssbypass coverage
  iommu/arm-smmu-v3: Mark EATS_TRANS safe when computing the update sequence
  iommu/arm-smmu-v3: Mark STE MEV safe when computing the update sequence
  iommu/arm-smmu-v3: Add update_safe bits to fix STE update sequence
  iommu/arm-smmu-v3: Add device-tree support for CMDQV driver
  iommu/tegra241-cmdqv: Decouple driver from ACPI
  iommu/arm-smmu-qcom: Restore ACTLR settings for MDSS on sa8775p
  iommu/vt-d: Fix race condition during PASID entry replacement
  iommu/vt-d: Clear Present bit before tearing down context entry
  iommu/vt-d: Clear Present bit before tearing down PASID entry
  iommu/vt-d: Flush piotlb for SVM and Nested domain
  iommu/vt-d: Flush cache for PASID table before using it
  iommu/vt-d: Flush dev-IOTLB only when PCIe device is accessible in scalable mode
  iommu/vt-d: Skip dev-iotlb flush for inaccessible PCIe device without scalable mode
  rust: iommu: fix `srctree` link warning
  rust: iommu: fix Rust formatting
  ...

6 files changed, 100 insertions, 0 deletions

diff --git a/include/linux/iommu-debug-pagealloc.h b/include/linux/iommu-debug-pagealloc.h
new file mode 100644
index 000000000000..46c3c1f70150
--- /dev/null
+++ b/include/linux/iommu-debug-pagealloc.h
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2025 - Google Inc
+ * Author: Mostafa Saleh <smostafa@google.com>
+ * IOMMU API debug page alloc sanitizer
+ */
+
+#ifndef __LINUX_IOMMU_DEBUG_PAGEALLOC_H
+#define __LINUX_IOMMU_DEBUG_PAGEALLOC_H
+
+#ifdef CONFIG_IOMMU_DEBUG_PAGEALLOC
+DECLARE_STATIC_KEY_FALSE(iommu_debug_initialized);
+
+extern struct page_ext_operations page_iommu_debug_ops;
+
+void __iommu_debug_check_unmapped(const struct page *page, int numpages);
+
+static inline void iommu_debug_check_unmapped(const struct page *page, int numpages)
+{
+	if (static_branch_unlikely(&iommu_debug_initialized))
+		__iommu_debug_check_unmapped(page, numpages);
+}
+
+#else
+static inline void iommu_debug_check_unmapped(const struct page *page,
+					      int numpages)
+{
+}
+
+#endif /* CONFIG_IOMMU_DEBUG_PAGEALLOC */
+
+#endif /* __LINUX_IOMMU_DEBUG_PAGEALLOC_H */
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 8c66284a91a8..54b8b48c762e 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -910,6 +910,7 @@ extern int iommu_attach_device(struct iommu_domain *domain,
 extern void iommu_detach_device(struct iommu_domain *domain,
 				struct device *dev);
 extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev);
+struct iommu_domain *iommu_driver_get_domain_for_dev(struct device *dev);
 extern struct iommu_domain *iommu_get_dma_domain(struct device *dev);
 extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
 		     phys_addr_t paddr, size_t size, int prot, gfp_t gfp);
@@ -1187,6 +1188,10 @@ void iommu_detach_device_pasid(struct iommu_domain *domain,
 			       struct device *dev, ioasid_t pasid);
 ioasid_t iommu_alloc_global_pasid(struct device *dev);
 void iommu_free_global_pasid(ioasid_t pasid);
+
+/* PCI device reset functions */
+int pci_dev_reset_iommu_prepare(struct pci_dev *pdev);
+void pci_dev_reset_iommu_done(struct pci_dev *pdev);
 #else /* CONFIG_IOMMU_API */
 
 struct iommu_ops {};
@@ -1510,6 +1515,15 @@ static inline ioasid_t iommu_alloc_global_pasid(struct device *dev)
 }
 
 static inline void iommu_free_global_pasid(ioasid_t pasid) {}
+
+static inline int pci_dev_reset_iommu_prepare(struct pci_dev *pdev)
+{
+	return 0;
+}
+
+static inline void pci_dev_reset_iommu_done(struct pci_dev *pdev)
+{
+}
 #endif /* CONFIG_IOMMU_API */
 
 #ifdef CONFIG_IRQ_MSI_IOMMU
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 73d3500d388e..6c5d06e27230 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -36,6 +36,7 @@
 #include <linux/rcuwait.h>
 #include <linux/bitmap.h>
 #include <linux/bitops.h>
+#include <linux/iommu-debug-pagealloc.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -4114,12 +4115,16 @@ extern void __kernel_map_pages(struct page *page, int numpages, int enable);
 #ifdef CONFIG_DEBUG_PAGEALLOC
 static inline void debug_pagealloc_map_pages(struct page *page, int numpages)
 {
+	iommu_debug_check_unmapped(page, numpages);
+
 	if (debug_pagealloc_enabled_static())
 		__kernel_map_pages(page, numpages, 1);
 }
 
 static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages)
 {
+	iommu_debug_check_unmapped(page, numpages);
+
 	if (debug_pagealloc_enabled_static())
 		__kernel_map_pages(page, numpages, 0);
 }
diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h
index 76c817162d2f..61e876e255e8 100644
--- a/include/linux/page_ext.h
+++ b/include/linux/page_ext.h
@@ -93,6 +93,7 @@ static inline bool page_ext_iter_next_fast_possible(unsigned long next_pfn)
 #endif
 
 extern struct page_ext *page_ext_get(const struct page *page);
+extern struct page_ext *page_ext_from_phys(phys_addr_t phys);
 extern void page_ext_put(struct page_ext *page_ext);
 extern struct page_ext *page_ext_lookup(unsigned long pfn);
 
@@ -215,6 +216,11 @@ static inline struct page_ext *page_ext_get(const struct page *page)
 	return NULL;
 }
 
+static inline struct page_ext *page_ext_from_phys(phys_addr_t phys)
+{
+	return NULL;
+}
+
 static inline void page_ext_put(struct page_ext *page_ext)
 {
 }
diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h
index 2c41920b641d..1dafbc552d37 100644
--- a/include/uapi/linux/iommufd.h
+++ b/include/uapi/linux/iommufd.h
@@ -466,15 +466,26 @@ struct iommu_hwpt_arm_smmuv3 {
 };
 
 /**
+ * struct iommu_hwpt_amd_guest - AMD IOMMU guest I/O page table data
+ *				 (IOMMU_HWPT_DATA_AMD_GUEST)
+ * @dte: Guest Device Table Entry (DTE)
+ */
+struct iommu_hwpt_amd_guest {
+	__aligned_u64 dte[4];
+};
+
+/**
  * enum iommu_hwpt_data_type - IOMMU HWPT Data Type
  * @IOMMU_HWPT_DATA_NONE: no data
  * @IOMMU_HWPT_DATA_VTD_S1: Intel VT-d stage-1 page table
  * @IOMMU_HWPT_DATA_ARM_SMMUV3: ARM SMMUv3 Context Descriptor Table
+ * @IOMMU_HWPT_DATA_AMD_GUEST: AMD IOMMU guest page table
  */
 enum iommu_hwpt_data_type {
 	IOMMU_HWPT_DATA_NONE = 0,
 	IOMMU_HWPT_DATA_VTD_S1 = 1,
 	IOMMU_HWPT_DATA_ARM_SMMUV3 = 2,
+	IOMMU_HWPT_DATA_AMD_GUEST = 3,
 };
 
 /**
@@ -624,6 +635,32 @@ struct iommu_hw_info_tegra241_cmdqv {
 };
 
 /**
+ * struct iommu_hw_info_amd - AMD IOMMU device info
+ *
+ * @efr : Value of AMD IOMMU Extended Feature Register (EFR)
+ * @efr2: Value of AMD IOMMU Extended Feature 2 Register (EFR2)
+ *
+ * Please See description of these registers in the following sections of
+ * the AMD I/O Virtualization Technology (IOMMU) Specification.
+ * (https://docs.amd.com/v/u/en-US/48882_3.10_PUB)
+ *
+ * - MMIO Offset 0030h IOMMU Extended Feature Register
+ * - MMIO Offset 01A0h IOMMU Extended Feature 2 Register
+ *
+ * Note: The EFR and EFR2 are raw values reported by hardware.
+ * VMM is responsible to determine the appropriate flags to be exposed to
+ * the VM since cetertain features are not currently supported by the kernel
+ * for HW-vIOMMU.
+ *
+ * Current VMM-allowed list of feature flags are:
+ * - EFR[GTSup, GASup, GioSup, PPRSup, EPHSup, GATS, GLX, PASmax]
+ */
+struct iommu_hw_info_amd {
+	__aligned_u64 efr;
+	__aligned_u64 efr2;
+};
+
+/**
  * enum iommu_hw_info_type - IOMMU Hardware Info Types
  * @IOMMU_HW_INFO_TYPE_NONE: Output by the drivers that do not report hardware
  *                           info
@@ -632,6 +669,7 @@ struct iommu_hw_info_tegra241_cmdqv {
  * @IOMMU_HW_INFO_TYPE_ARM_SMMUV3: ARM SMMUv3 iommu info type
  * @IOMMU_HW_INFO_TYPE_TEGRA241_CMDQV: NVIDIA Tegra241 CMDQV (extension for ARM
  *                                     SMMUv3) info type
+ * @IOMMU_HW_INFO_TYPE_AMD: AMD IOMMU info type
  */
 enum iommu_hw_info_type {
 	IOMMU_HW_INFO_TYPE_NONE = 0,
@@ -639,6 +677,7 @@ enum iommu_hw_info_type {
 	IOMMU_HW_INFO_TYPE_INTEL_VTD = 1,
 	IOMMU_HW_INFO_TYPE_ARM_SMMUV3 = 2,
 	IOMMU_HW_INFO_TYPE_TEGRA241_CMDQV = 3,
+	IOMMU_HW_INFO_TYPE_AMD = 4,
 };
 
 /**
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index ac2329f24141..bb7b89330d35 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -964,6 +964,10 @@ struct vfio_device_bind_iommufd {
  * hwpt corresponding to the given pt_id.
  *
  * Return: 0 on success, -errno on failure.
+ *
+ * When a device is resetting, -EBUSY will be returned to reject any concurrent
+ * attachment to the resetting device itself or any sibling device in the IOMMU
+ * group having the resetting device.
  */
 struct vfio_device_attach_iommufd_pt {
 	__u32	argsz;