[PATCH v7 08/15] iommupt: Add read_and_clear_dirty op

[Jason Gunthorpe]

IOMMU HW now supports updating a dirty bit in an entry when a DMA writes
to the entry's VA range. iommufd has a uAPI to read and clear the dirty
bits from the tables.

This is a trivial recursive descent algorithm to read and optionally clear
the dirty bits. The format needs a function to tell if a contiguous entry
is dirty, and a function to clear a contiguous entry back to clean.

Tested-by: Alejandro Jimenez <alejandro.j.jimenez at oracle.com>
Reviewed-by: Kevin Tian <kevin.tian at intel.com>
Signed-off-by: Jason Gunthorpe <jgg at nvidia.com>
---
 drivers/iommu/generic_pt/iommu_pt.h | 104 ++++++++++++++++++++++++++++
 include/linux/generic_pt/iommu.h    |   6 ++
 2 files changed, 110 insertions(+)

diff --git a/drivers/iommu/generic_pt/iommu_pt.h b/drivers/iommu/generic_pt/iommu_pt.h
index f32e81509f4f09..448c5796d4a861 100644
--- a/drivers/iommu/generic_pt/iommu_pt.h
+++ b/drivers/iommu/generic_pt/iommu_pt.h
@@ -162,6 +162,108 @@ phys_addr_t DOMAIN_NS(iova_to_phys)(struct iommu_domain *domain,
 }
 EXPORT_SYMBOL_NS_GPL(DOMAIN_NS(iova_to_phys), "GENERIC_PT_IOMMU");
 
+struct pt_iommu_dirty_args {
+	struct iommu_dirty_bitmap *dirty;
+	unsigned int flags;
+};
+
+static void record_dirty(struct pt_state *pts,
+			 struct pt_iommu_dirty_args *dirty,
+			 unsigned int num_contig_lg2)
+{
+	pt_vaddr_t dirty_len;
+
+	if (num_contig_lg2 != ilog2(1)) {
+		unsigned int index = pts->index;
+		unsigned int end_index = log2_set_mod_max_t(
+			unsigned int, pts->index, num_contig_lg2);
+
+		/* Adjust for being contained inside a contiguous page */
+		end_index = min(end_index, pts->end_index);
+		dirty_len = (end_index - index) *
+				log2_to_int(pt_table_item_lg2sz(pts));
+	} else {
+		dirty_len = log2_to_int(pt_table_item_lg2sz(pts));
+	}
+
+	if (dirty->dirty->bitmap)
+		iova_bitmap_set(dirty->dirty->bitmap, pts->range->va,
+				dirty_len);
+
+	if (!(dirty->flags & IOMMU_DIRTY_NO_CLEAR)) {
+		pt_entry_make_write_clean(pts);
+		iommu_iotlb_gather_add_range(dirty->dirty->gather,
+					     pts->range->va, dirty_len);
+	}
+}
+
+static inline int __read_and_clear_dirty(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_dirty_args *dirty = arg;
+	int ret;
+
+	for_each_pt_level_entry(&pts) {
+		if (pts.type == PT_ENTRY_TABLE) {
+			ret = pt_descend(&pts, arg, __read_and_clear_dirty);
+			if (ret)
+				return ret;
+			continue;
+		}
+		if (pts.type == PT_ENTRY_OA && pt_entry_is_write_dirty(&pts))
+			record_dirty(&pts, dirty,
+				     pt_entry_num_contig_lg2(&pts));
+	}
+	return 0;
+}
+
+/**
+ * read_and_clear_dirty() - Manipulate the HW set write dirty state
+ * @domain: Domain to manipulate
+ * @iova: IO virtual address to start
+ * @size: Length of the IOVA
+ * @flags: A bitmap of IOMMU_DIRTY_NO_CLEAR
+ * @dirty: Place to store the dirty bits
+ *
+ * Iterate over all the entries in the mapped range and record their write dirty
+ * status in iommu_dirty_bitmap. If IOMMU_DIRTY_NO_CLEAR is not specified then
+ * the entries will be left dirty, otherwise they are returned to being not
+ * write dirty.
+ *
+ * Context: The caller must hold a read range lock that includes @iova.
+ *
+ * Returns: -ERRNO on failure, 0 on success.
+ */
+int DOMAIN_NS(read_and_clear_dirty)(struct iommu_domain *domain,
+				    unsigned long iova, size_t size,
+				    unsigned long flags,
+				    struct iommu_dirty_bitmap *dirty)
+{
+	struct pt_iommu *iommu_table =
+		container_of(domain, struct pt_iommu, domain);
+	struct pt_iommu_dirty_args dirty_args = {
+		.dirty = dirty,
+		.flags = flags,
+	};
+	struct pt_range range;
+	int ret;
+
+#if !IS_ENABLED(CONFIG_IOMMUFD_DRIVER) || !defined(pt_entry_is_write_dirty)
+	return -EOPNOTSUPP;
+#endif
+
+	ret = make_range(common_from_iommu(iommu_table), &range, iova, size);
+	if (ret)
+		return ret;
+
+	ret = pt_walk_range(&range, __read_and_clear_dirty, &dirty_args);
+	PT_WARN_ON(ret);
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(DOMAIN_NS(read_and_clear_dirty), "GENERIC_PT_IOMMU");
+
 struct pt_iommu_collect_args {
 	struct iommu_pages_list free_list;
 	/* Fail if any OAs are within the range */
@@ -1015,5 +1117,7 @@ EXPORT_SYMBOL_NS_GPL(pt_iommu_hw_info, "GENERIC_PT_IOMMU");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("IOMMU Page table implementation for " __stringify(PTPFX_RAW));
 MODULE_IMPORT_NS("GENERIC_PT");
+/* For iommu_dirty_bitmap_record() */
+MODULE_IMPORT_NS("IOMMUFD");
 
 #endif  /* __GENERIC_PT_IOMMU_PT_H */
diff --git a/include/linux/generic_pt/iommu.h b/include/linux/generic_pt/iommu.h
index 0d59423024d57f..03a906fbe12a83 100644
--- a/include/linux/generic_pt/iommu.h
+++ b/include/linux/generic_pt/iommu.h
@@ -12,6 +12,7 @@
 struct iommu_iotlb_gather;
 struct pt_iommu_ops;
 struct pt_iommu_driver_ops;
+struct iommu_dirty_bitmap;
 
 /**
  * DOC: IOMMU Radix Page Table
@@ -182,6 +183,9 @@ struct pt_iommu_cfg {
 		struct iommu_domain *domain, unsigned long iova,               \
 		size_t pgsize, size_t pgcount,                                 \
 		struct iommu_iotlb_gather *iotlb_gather);                      \
+	int pt_iommu_##fmt##_read_and_clear_dirty(                             \
+		struct iommu_domain *domain, unsigned long iova, size_t size,  \
+		unsigned long flags, struct iommu_dirty_bitmap *dirty);        \
 	int pt_iommu_##fmt##_init(struct pt_iommu_##fmt *table,                \
 				  const struct pt_iommu_##fmt##_cfg *cfg,      \
 				  gfp_t gfp);                                  \
@@ -202,6 +206,8 @@ struct pt_iommu_cfg {
 	.iova_to_phys = &pt_iommu_##fmt##_iova_to_phys, \
 	.map_pages = &pt_iommu_##fmt##_map_pages,       \
 	.unmap_pages = &pt_iommu_##fmt##_unmap_pages
+#define IOMMU_PT_DIRTY_OPS(fmt) \
+	.read_and_clear_dirty = &pt_iommu_##fmt##_read_and_clear_dirty
 
 /*
  * The driver should setup its domain struct like
-- 
2.43.0