[v3,03/15] iommupt: Add the basic structure of the iommu implementation

diff --git a/drivers/iommu/generic_pt/Kconfig b/drivers/iommu/generic_pt/Kconfig
index 775a3afb563f72..73b7a54375f9bd 100644
--- a/drivers/iommu/generic_pt/Kconfig
+++ b/drivers/iommu/generic_pt/Kconfig
@@ -19,4 +19,17 @@  config DEBUG_GENERIC_PT
 	  kernels.
 
 	  The kunit tests require this to be enabled to get full coverage.
+
+config IOMMU_PT
+	tristate "IOMMU Page Tables"
+	select IOMMU_API
+	depends on IOMMU_SUPPORT
+	depends on GENERIC_PT
+	default n
+	help
+	  Generic library for building IOMMU page tables
+
+	  IOMMU_PT provides an implementation of the page table operations
+	  related struct iommu_domain using GENERIC_PT to abstract the page
+	  table format.
 endif
diff --git a/drivers/iommu/generic_pt/fmt/iommu_template.h b/drivers/iommu/generic_pt/fmt/iommu_template.h
new file mode 100644
index 00000000000000..5b631bc07cbc16
--- /dev/null
+++ b/drivers/iommu/generic_pt/fmt/iommu_template.h
@@ -0,0 +1,39 @@ 
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2024-2025, NVIDIA CORPORATION & AFFILIATES
+ *
+ * Template to build the iommu module and kunit from the format and
+ * implementation headers.
+ *
+ * The format should have:
+ *  #define PT_FMT <name>
+ *  #define PT_SUPPORTED_FEATURES (BIT(PT_FEAT_xx) | BIT(PT_FEAT_yy))
+ * And optionally:
+ *  #define PT_FORCE_ENABLED_FEATURES ..
+ *  #define PT_FMT_VARIANT <suffix>
+ */
+#include <linux/args.h>
+#include <linux/stringify.h>
+
+#ifdef PT_FMT_VARIANT
+#define PTPFX_RAW \
+	CONCATENATE(CONCATENATE(PT_FMT, _), PT_FMT_VARIANT)
+#else
+#define PTPFX_RAW PT_FMT
+#endif
+
+#define PTPFX CONCATENATE(PTPFX_RAW, _)
+
+#define _PT_FMT_H PT_FMT.h
+#define PT_FMT_H __stringify(_PT_FMT_H)
+
+#define _PT_DEFS_H CONCATENATE(defs_, _PT_FMT_H)
+#define PT_DEFS_H __stringify(_PT_DEFS_H)
+
+#include <linux/generic_pt/common.h>
+#include PT_DEFS_H
+#include "../pt_defs.h"
+#include PT_FMT_H
+#include "../pt_common.h"
+
+#include "../iommu_pt.h"
diff --git a/drivers/iommu/generic_pt/iommu_pt.h b/drivers/iommu/generic_pt/iommu_pt.h
new file mode 100644
index 00000000000000..205c232bda68b5
--- /dev/null
+++ b/drivers/iommu/generic_pt/iommu_pt.h
@@ -0,0 +1,268 @@ 
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2024-2025, NVIDIA CORPORATION & AFFILIATES
+ *
+ * "Templated C code" for implementing the iommu operations for page tables.
+ * This is compiled multiple times, over all the page table formats to pick up
+ * the per-format definitions.
+ */
+#ifndef __GENERIC_PT_IOMMU_PT_H
+#define __GENERIC_PT_IOMMU_PT_H
+
+#include "pt_iter.h"
+
+#include <linux/iommu.h>
+#include "../iommu-pages.h"
+#include <linux/export.h>
+
+#define DOMAIN_NS(op) CONCATENATE(CONCATENATE(pt_iommu_, PTPFX), op)
+
+struct pt_iommu_collect_args {
+	struct iommu_pages_list free_list;
+	u8 ignore_mapped : 1;
+};
+
+static int __collect_tables(struct pt_range *range, void *arg,
+			    unsigned int level, struct pt_table_p *table)
+{
+	struct pt_state pts = pt_init(range, level, table);
+	struct pt_iommu_collect_args *collect = arg;
+	int ret;
+
+	if (collect->ignore_mapped && !pt_can_have_table(&pts))
+		return 0;
+
+	for_each_pt_level_entry(&pts) {
+		if (pts.type == PT_ENTRY_TABLE) {
+			iommu_pages_list_add(&collect->free_list, pts.table_lower);
+			ret = pt_descend(&pts, arg, __collect_tables);
+			if (ret)
+				return ret;
+			continue;
+		}
+		if (pts.type == PT_ENTRY_OA && !collect->ignore_mapped)
+			return -EADDRINUSE;
+	}
+	return 0;
+}
+
+static inline struct pt_table_p *table_alloc_top(struct pt_common *common,
+						 uintptr_t top_of_table,
+						 gfp_t gfp)
+{
+	struct pt_iommu *iommu_table = iommu_from_common(common);
+
+	/*
+	 * Top doesn't need the free list or otherwise, so it technically
+	 * doesn't need to use iommu pages. Use the API anyhow as the top is
+	 * usually not smaller than PAGE_SIZE to keep things simple.
+	 */
+	return iommu_alloc_pages_node_sz(
+		iommu_table->nid, gfp,
+		log2_to_int(pt_top_memsize_lg2(common, top_of_table)));
+}
+
+static void NS(get_info)(struct pt_iommu *iommu_table,
+			 struct pt_iommu_info *info)
+{
+	struct pt_common *common = common_from_iommu(iommu_table);
+	struct pt_range range = pt_top_range(common);
+	struct pt_state pts = pt_init_top(&range);
+	pt_vaddr_t pgsize_bitmap = 0;
+
+	if (pt_feature(common, PT_FEAT_DYNAMIC_TOP)) {
+		for (pts.level = 0; pts.level <= PT_MAX_TOP_LEVEL;
+		     pts.level++) {
+			if (pt_table_item_lg2sz(&pts) >= common->max_vasz_lg2)
+				break;
+			pgsize_bitmap |= pt_possible_sizes(&pts);
+		}
+	} else {
+		for (pts.level = 0; pts.level <= range.top_level; pts.level++)
+			pgsize_bitmap |= pt_possible_sizes(&pts);
+	}
+
+	/* Hide page sizes larger than the maximum OA */
+	info->pgsize_bitmap = oalog2_mod(pgsize_bitmap, common->max_oasz_lg2);
+}
+
+static void NS(deinit)(struct pt_iommu *iommu_table)
+{
+	struct pt_common *common = common_from_iommu(iommu_table);
+	struct pt_range range = pt_all_range(common);
+	struct pt_iommu_collect_args collect = {
+		.free_list = IOMMU_PAGES_LIST_INIT(collect.free_list),
+		.ignore_mapped = true,
+	};
+
+	iommu_pages_list_add(&collect.free_list, range.top_table);
+	pt_walk_range(&range, __collect_tables, &collect);
+
+	/*
+	 * The driver has to already have fenced the HW access to the page table
+	 * and invalidated any caching referring to this memory.
+	 */
+	iommu_put_pages_list(&collect.free_list);
+}
+
+static const struct pt_iommu_ops NS(ops) = {
+	.get_info = NS(get_info),
+	.deinit = NS(deinit),
+};
+
+static int pt_init_common(struct pt_common *common)
+{
+	struct pt_range top_range = pt_top_range(common);
+
+	if (PT_WARN_ON(top_range.top_level > PT_MAX_TOP_LEVEL))
+		return -EINVAL;
+
+	if (top_range.top_level == PT_MAX_TOP_LEVEL ||
+	    common->max_vasz_lg2 == top_range.max_vasz_lg2)
+		common->features &= ~BIT(PT_FEAT_DYNAMIC_TOP);
+
+	if (top_range.max_vasz_lg2 == PT_VADDR_MAX_LG2)
+		common->features |= BIT(PT_FEAT_FULL_VA);
+
+	/* Requested features must match features compiled into this format */
+	if ((common->features & ~(unsigned int)PT_SUPPORTED_FEATURES) ||
+	    (!IS_ENABLED(CONFIG_DEBUG_GENERIC_PT) &&
+	     (common->features & PT_FORCE_ENABLED_FEATURES) !=
+		     PT_FORCE_ENABLED_FEATURES))
+		return -EOPNOTSUPP;
+
+	if (common->max_oasz_lg2 == 0)
+		common->max_oasz_lg2 = pt_max_output_address_lg2(common);
+	else
+		common->max_oasz_lg2 = min(common->max_oasz_lg2,
+					   pt_max_output_address_lg2(common));
+	return 0;
+}
+
+static int pt_iommu_init_domain(struct pt_iommu *iommu_table,
+				struct iommu_domain *domain)
+{
+	struct pt_common *common = common_from_iommu(iommu_table);
+	struct pt_iommu_info info;
+	struct pt_range range;
+
+	NS(get_info)(iommu_table, &info);
+
+	domain->type = __IOMMU_DOMAIN_PAGING;
+	domain->pgsize_bitmap = info.pgsize_bitmap;
+
+	if (pt_feature(common, PT_FEAT_DYNAMIC_TOP))
+		range = _pt_top_range(common,
+				      _pt_top_set(NULL, PT_MAX_TOP_LEVEL));
+	else
+		range = pt_top_range(common);
+
+	/*
+	 * A 64 bit high address space table on a 32 bit system cannot work.
+	 */
+	domain->geometry.aperture_start = (unsigned long)range.va;
+	if ((pt_vaddr_t)domain->geometry.aperture_start != range.va ||
+	    range.va > ULONG_MAX)
+		return -EOVERFLOW;
+
+	/*
+	 * The aperture is limited to what the API can do after considering all
+	 * the different types dma_addr_t/unsigned long/pt_vaddr_t that are used
+	 * to store a VA. Set the aperture to something that is valid for all
+	 * cases. Saturate instead of truncate the end if the types are smaller
+	 * than the top range. aperture_end is a last.
+	 */
+	domain->geometry.aperture_end = (unsigned long)range.last_va;
+	if ((pt_vaddr_t)domain->geometry.aperture_end != range.last_va) {
+		domain->geometry.aperture_end = ULONG_MAX;
+		domain->pgsize_bitmap &= ULONG_MAX;
+	}
+	domain->geometry.force_aperture = true;
+
+	return 0;
+}
+
+static void pt_iommu_zero(struct pt_iommu_table *fmt_table)
+{
+	struct pt_iommu *iommu_table = &fmt_table->iommu;
+	struct pt_iommu cfg = *iommu_table;
+
+	static_assert(offsetof(struct pt_iommu_table, iommu.domain) == 0);
+	memset_after(fmt_table, 0, iommu.domain);
+
+	/* The caller can initialize some of these values */
+	iommu_table->nid = cfg.nid;
+}
+
+#define pt_iommu_table_cfg CONCATENATE(pt_iommu_table, _cfg)
+#define pt_iommu_init CONCATENATE(CONCATENATE(pt_iommu_, PTPFX), init)
+int pt_iommu_init(struct pt_iommu_table *fmt_table,
+		  const struct pt_iommu_table_cfg *cfg, gfp_t gfp)
+{
+	struct pt_iommu *iommu_table = &fmt_table->iommu;
+	struct pt_common *common = common_from_iommu(iommu_table);
+	struct pt_table_p *table_mem;
+	int ret;
+
+	if (cfg->common.hw_max_vasz_lg2 > PT_MAX_VA_ADDRESS_LG2 ||
+	    !cfg->common.hw_max_vasz_lg2 || !cfg->common.hw_max_oasz_lg2)
+		return -EINVAL;
+
+	pt_iommu_zero(fmt_table);
+	common->features = cfg->common.features;
+	common->max_vasz_lg2 = cfg->common.hw_max_vasz_lg2;
+	common->max_oasz_lg2 = cfg->common.hw_max_oasz_lg2;
+#ifdef PT_FIXED_TOP_LEVEL
+	pt_top_set_level(common, PT_FIXED_TOP_LEVEL);
+#endif
+	ret = pt_iommu_fmt_init(fmt_table, cfg);
+	if (ret)
+		return ret;
+
+	if (cfg->common.hw_max_oasz_lg2 > pt_max_output_address_lg2(common))
+		return -EINVAL;
+
+	ret = pt_init_common(common);
+	if (ret)
+		return ret;
+
+	if (pt_feature(common, PT_FEAT_SIGN_EXTEND) &&
+	    (pt_feature(common, PT_FEAT_FULL_VA) ||
+	     pt_feature(common, PT_FEAT_DYNAMIC_TOP)))
+		return -EINVAL;
+
+	ret = pt_iommu_init_domain(iommu_table, &iommu_table->domain);
+	if (ret)
+		return ret;
+
+	table_mem = table_alloc_top(common, common->top_of_table, gfp);
+	if (IS_ERR(table_mem))
+		return PTR_ERR(table_mem);
+	pt_top_set(common, table_mem, pt_top_get_level(common));
+
+	/* Must be last, see pt_iommu_deinit() */
+	iommu_table->ops = &NS(ops);
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(pt_iommu_init, "GENERIC_PT_IOMMU");
+
+#ifdef pt_iommu_fmt_hw_info
+#define pt_iommu_table_hw_info CONCATENATE(pt_iommu_table, _hw_info)
+#define pt_iommu_hw_info CONCATENATE(CONCATENATE(pt_iommu_, PTPFX), hw_info)
+void pt_iommu_hw_info(struct pt_iommu_table *fmt_table,
+		      struct pt_iommu_table_hw_info *info)
+{
+	struct pt_iommu *iommu_table = &fmt_table->iommu;
+	struct pt_common *common = common_from_iommu(iommu_table);
+	struct pt_range top_range = pt_top_range(common);
+
+	pt_iommu_fmt_hw_info(fmt_table, &top_range, info);
+}
+EXPORT_SYMBOL_NS_GPL(pt_iommu_hw_info, "GENERIC_PT_IOMMU");
+#endif
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("IOMMU Pagetable implementation for " __stringify(PTPFX_RAW));
+MODULE_IMPORT_NS("GENERIC_PT");
+
+#endif
diff --git a/include/linux/generic_pt/iommu.h b/include/linux/generic_pt/iommu.h
new file mode 100644
index 00000000000000..9d2152bc64c0d6
--- /dev/null
+++ b/include/linux/generic_pt/iommu.h
@@ -0,0 +1,118 @@ 
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2024-2025, NVIDIA CORPORATION & AFFILIATES
+ */
+#ifndef __GENERIC_PT_IOMMU_H
+#define __GENERIC_PT_IOMMU_H
+
+#include <linux/generic_pt/common.h>
+#include <linux/iommu.h>
+#include <linux/mm_types.h>
+
+struct pt_iommu_ops;
+
+/**
+ * DOC: IOMMU Radix Page Table
+ *
+ * The iommu implementation of the Generic Page Table provides an ops struct
+ * that is useful to go with an iommu_domain to serve the DMA API, IOMMUFD and
+ * the generic map/unmap interface.
+ *
+ * This interface uses a caller provided locking approach. The caller must have
+ * a VA range lock concept that prevents concurrent threads from calling ops on
+ * the same VA. Generally the range lock must be at least as large as a single
+ * map call.
+ */
+
+/**
+ * struct pt_iommu - Base structure for iommu page tables
+ *
+ * The format specific struct will include this as the first member.
+ */
+struct pt_iommu {
+	/**
+	 * @domain - The core iommu domain. The driver should use a union to
+	 * overlay this memory with its previously existing domain struct to
+	 * create an alias.
+	 */
+	struct iommu_domain domain;
+
+	/**
+	 * @ops - Function pointers to access the API
+	 */
+	const struct pt_iommu_ops *ops;
+
+	/**
+	 * @nid - Node ID to use for table memory allocations. The iommu driver
+	 * may want to set the NID to the device's NID, if there are multiple
+	 * table walkers.
+	 */
+	int nid;
+};
+
+/**
+ * struct pt_iommu_info - Details about the iommu page table
+ *
+ * Returned from pt_iommu_ops->get_info()
+ */
+struct pt_iommu_info {
+	/**
+	 * @pgsize_bitmap - A bitmask where each set bit indicates
+	 * a page size that can be natively stored in the page table.
+	 */
+	u64 pgsize_bitmap;
+};
+
+struct pt_iommu_ops {
+	/**
+	 * get_info() - Return the pt_iommu_info structure
+	 * @iommu_table: Table to query
+	 *
+	 * Return some basic static information about the page table.
+	 */
+	void (*get_info)(struct pt_iommu *iommu_table,
+			 struct pt_iommu_info *info);
+
+	/**
+	 * deinit() - Undo a format specific init operation
+	 * @iommu_table: Table to destroy
+	 *
+	 * Release all of the memory. The caller must have already removed the
+	 * table from all HW access and all caches.
+	 */
+	void (*deinit)(struct pt_iommu *iommu_table);
+};
+
+static inline void pt_iommu_deinit(struct pt_iommu *iommu_table)
+{
+	/*
+	 * It is safe to call pt_iommu_deinit() before an init, or if init
+	 * fails. The ops pointer will only become non-NUL if deinit needs to be
+	 * run.
+	 */
+	if (iommu_table->ops)
+		iommu_table->ops->deinit(iommu_table);
+}
+
+/**
+ * struct pt_iommu_cfg - Common configuration values for all formats
+ */
+struct pt_iommu_cfg {
+	/**
+	 * @features - Features required. Only these features will be turned on.
+	 * The feature list should reflect what the IOMMU HW is capable of.
+	 */
+	unsigned int features;
+	/**
+	 * @hw_max_vasz_lg2 - Maximum VA the IOMMU HW can support. This will
+	 * imply the top level of the table.
+	 */
+	u8 hw_max_vasz_lg2;
+	/**
+	 * @hw_max_oasz_lg2 - Maximum OA the IOMMU HW can support. The format
+	 * might select a lower maximum OA.
+	 */
+	u8 hw_max_oasz_lg2;
+};
+
+#endif