iommupt: Add the basic structure of the iommu implementation

The existing IOMMU page table implementations duplicate all of the working
algorithms for each format. By using the generic page table API a single C
version of the IOMMU algorithms can be created and re-used for all of the
different formats used in the drivers. The implementation will provide a
single C version of the iommu domain operations: iova_to_phys, map, unmap,
and read_and_clear_dirty.

Further, adding new algorithms and techniques becomes easy to do across
the entire fleet of drivers and formats.

The C functions are drop in compatible with the existing iommu_domain_ops
using the IOMMU_PT_DOMAIN_OPS() macro. Each per-format implementation
compilation unit will produce exported symbols following the pattern
pt_iommu_FMT_map_pages() which the macro directly maps to the
iommu_domain_ops members. This avoids the additional function pointer
indirection like io-pgtable has.

The top level struct used by the drivers is pt_iommu_table_FMT. It
contains the other structs to allow container_of() to move between the
driver, iommu page table, generic page table, and generic format layers.

   struct pt_iommu_table_amdv1 {
       struct pt_iommu {
	      struct iommu_domain domain;
       } iommu;
       struct pt_amdv1 {
	      struct pt_common common;
       } amdpt;
   };

The driver is expected to union the pt_iommu_table_FMT with its own
existing domain struct:

   struct driver_domain {
       union {
	       struct iommu_domain domain;
	       struct pt_iommu_table_amdv1 amdv1;
       };
   };
   PT_IOMMU_CHECK_DOMAIN(struct driver_domain, amdv1, domain);

To create an alias to avoid renaming 'domain' in a lot of driver code.

This allows all the layers to access all the necessary functions to
implement their different roles with no change to any of the existing
iommu core code.

Implement the basic starting point: pt_iommu_init(), get_info() and
deinit().

Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Reviewed-by: Samiullah Khawaja <skhawaja@google.com>
Tested-by: Alejandro Jimenez <alejandro.j.jimenez@oracle.com>
Tested-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>

1 files changed, 150 insertions, 0 deletions

diff --git a/include/linux/generic_pt/iommu.h b/include/linux/generic_pt/iommu.h
new file mode 100644
index 000000000000..defa96abc497
--- /dev/null
+++ b/include/linux/generic_pt/iommu.h
@@ -0,0 +1,150 @@
+/* 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-NULL 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;
+};
+
+/* Generate the exported function signatures from iommu_pt.h */
+#define IOMMU_PROTOTYPES(fmt)                                             \
+	int pt_iommu_##fmt##_init(struct pt_iommu_##fmt *table,           \
+				  const struct pt_iommu_##fmt##_cfg *cfg, \
+				  gfp_t gfp);                             \
+	void pt_iommu_##fmt##_hw_info(struct pt_iommu_##fmt *table,       \
+				      struct pt_iommu_##fmt##_hw_info *info)
+#define IOMMU_FORMAT(fmt, member)       \
+	struct pt_iommu_##fmt {         \
+		struct pt_iommu iommu;  \
+		struct pt_##fmt member; \
+	};                              \
+	IOMMU_PROTOTYPES(fmt)
+
+/*
+ * The driver should setup its domain struct like
+ *	union {
+ *		struct iommu_domain domain;
+ *		struct pt_iommu_xxx xx;
+ *	};
+ * PT_IOMMU_CHECK_DOMAIN(struct mock_iommu_domain, xx.iommu, domain);
+ *
+ * Which creates an alias between driver_domain.domain and
+ * driver_domain.xx.iommu.domain. This is to avoid a mass rename of existing
+ * driver_domain.domain users.
+ */
+#define PT_IOMMU_CHECK_DOMAIN(s, pt_iommu_memb, domain_memb) \
+	static_assert(offsetof(s, pt_iommu_memb.domain) ==   \
+		      offsetof(s, domain_memb))
+
+#undef IOMMU_PROTOTYPES
+#undef IOMMU_FORMAT
+#endif