[RFC PATCH 1/2] iommu: Add iommu_map_sgtable_dma()

[Karl Mehltretter]

DMA-BUF attachments provide DMA addresses, not CPU-side pages.
iommu_map_sgtable() needs those pages, so private-domain importers such
as Rockchip cannot use it with strict DMABUF_DEBUG.

Add an iommu-dma helper to map a live attachment into another domain by
translating through the device's default DMA domain. Roll back target
mappings on error. This still recovers physical addresses internally.

Only non-bounced iommu-dma mappings are supported. Other DMA backends,
marked bus addresses and zero translations return -EOPNOTSUPP, as does
the IOMMU_DMA=n stub. A zero lookup cannot distinguish a hole from PA0.
Reject bounce slots because a second mapping cannot keep them in sync
with writes to the original buffer.

DMABUF_DEBUG currently drops DMA flags from its copy, so the bus-address
check depends on the input retaining that mark.

Assisted-by: LLM
Signed-off-by: Karl Mehltretter <kmehltretter@xxxxxxxxx>
---
 drivers/iommu/dma-iommu.c | 131 ++++++++++++++++++++++++++++++++++++++
 include/linux/iommu.h     |  12 ++++
 2 files changed, 143 insertions(+)

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 58c624513cd4..b9a1f91ec5db 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -38,6 +38,137 @@
 #include "dma-iommu.h"
 #include "iommu-pages.h"
 
+/**
+ * iommu_map_sgtable_dma - map the DMA side of an sg_table into a domain
+ * @domain: domain to map into
+ * @iova: IOVA of the first byte
+ * @dev: device for which @sgt is mapped
+ * @sgt: live DMA-API mapping for @dev, backed by non-bounced RAM
+ * @prot: IOMMU protection flags
+ *
+ * Translate the DMA addresses through @dev's default iommu-dma domain and
+ * map the backing memory into @domain without reading the CPU side of @sgt.
+ * Direct DMA and other DMA backends are not supported. Entries marked as
+ * PCI P2P bus addresses and SWIOTLB bounce buffers are also not supported.
+ *
+ * The caller must keep the source mapping, DMA backend and default domain
+ * unchanged until the target mapping is removed. This function may sleep.
+ * DMA addresses and lengths must be aligned to the smaller of the source
+ * and target domains' minimum page sizes. @iova and the total length must
+ * be aligned to the target domain's minimum page size.
+ *
+ * A zero reverse translation is unsupported: iommu_iova_to_phys() cannot
+ * distinguish an absent mapping from a mapping to physical address zero.
+ *
+ * Return: the number of bytes mapped, -EOPNOTSUPP for unsupported source
+ * mappings or source alignment, or another negative errno on error. Any
+ * target mappings installed by this call are removed on error.
+ */
+ssize_t iommu_map_sgtable_dma(struct iommu_domain *domain, unsigned long iova,
+			      struct device *dev, struct sg_table *sgt,
+			      int prot)
+{
+	struct iommu_domain *dma_domain;
+	size_t len = 0, mapped = 0, total = 0;
+	struct scatterlist *sg;
+	size_t granule, target_granule;
+	phys_addr_t start = 0;
+	unsigned long last_iova;
+	unsigned int i;
+	int ret;
+
+	if (!domain->pgsize_bitmap)
+		return -EINVAL;
+
+	target_granule = 1UL << __ffs(domain->pgsize_bitmap);
+	if (!use_dma_iommu(dev))
+		return -EOPNOTSUPP;
+	dma_domain = iommu_get_dma_domain(dev);
+	if (!dma_domain || !dma_domain->pgsize_bitmap)
+		return -EOPNOTSUPP;
+	granule = min(target_granule,
+		      1UL << __ffs(dma_domain->pgsize_bitmap));
+
+	for_each_sgtable_dma_sg(sgt, sg, i) {
+		dma_addr_t last_dma;
+		size_t dma_len = sg_dma_len(sg);
+
+		if (sg_dma_is_bus_address(sg))
+			return -EOPNOTSUPP;
+		if (!dma_len || !IS_ALIGNED(sg_dma_address(sg), granule) ||
+		    !IS_ALIGNED(dma_len, granule))
+			return -EOPNOTSUPP;
+		if (check_add_overflow(sg_dma_address(sg), dma_len - 1,
+				       &last_dma) ||
+		    check_add_overflow(total, dma_len, &total))
+			return -EOVERFLOW;
+	}
+	if (!total)
+		return 0;
+	if (total > SSIZE_MAX || !IS_ALIGNED(iova, target_granule) ||
+	    !IS_ALIGNED(total, target_granule))
+		return -EINVAL;
+	if (check_add_overflow(iova, total - 1, &last_iova))
+		return -EOVERFLOW;
+
+	for_each_sgtable_dma_sg(sgt, sg, i) {
+		dma_addr_t dma_addr = sg_dma_address(sg);
+		size_t dma_len = sg_dma_len(sg);
+
+		while (dma_len) {
+			phys_addr_t next;
+			phys_addr_t phys;
+
+			phys = iommu_iova_to_phys(dma_domain, dma_addr);
+			if (!phys || swiotlb_find_pool(dev, phys)) {
+				ret = -EOPNOTSUPP;
+				goto out_err;
+			}
+
+			if (len && check_add_overflow(start, len, &next)) {
+				ret = -EOVERFLOW;
+				goto out_err;
+			}
+			if (len && phys != next) {
+				ret = iommu_map_nosync(domain, iova + mapped,
+						       start, len, prot,
+						       GFP_KERNEL);
+				if (ret)
+					goto out_err;
+				mapped += len;
+				len = 0;
+			}
+			if (!len)
+				start = phys;
+			if (check_add_overflow(len, granule, &len)) {
+				ret = -EOVERFLOW;
+				goto out_err;
+			}
+			dma_addr += granule;
+			dma_len -= granule;
+		}
+	}
+
+	if (len) {
+		ret = iommu_map_nosync(domain, iova + mapped, start, len, prot,
+				       GFP_KERNEL);
+		if (ret)
+			goto out_err;
+		mapped += len;
+	}
+
+	ret = iommu_sync_map(domain, iova, mapped);
+	if (ret)
+		goto out_err;
+
+	return mapped;
+
+out_err:
+	iommu_unmap(domain, iova, mapped);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_map_sgtable_dma);
+
 struct iommu_dma_msi_page {
 	struct list_head	list;
 	dma_addr_t		iova;
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index ac43b8b93f14..95d90c7f953b 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -1604,8 +1604,20 @@ static inline void iommu_debugfs_setup(void) {}
 #endif
 
 #ifdef CONFIG_IOMMU_DMA
+ssize_t iommu_map_sgtable_dma(struct iommu_domain *domain, unsigned long iova,
+			      struct device *dev, struct sg_table *sgt,
+			      int prot);
 int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base);
 #else /* CONFIG_IOMMU_DMA */
+static inline ssize_t iommu_map_sgtable_dma(struct iommu_domain *domain,
+					    unsigned long iova,
+					    struct device *dev,
+					    struct sg_table *sgt,
+					    int prot)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base)
 {
 	return -ENODEV;
-- 
2.53.0