dma-mapping: introduce DMA_ATTR_CC_SHARED for shared memory

Current CC designs don't place a vIOMMU in front of untrusted devices.
Instead, the DMA API forces all untrusted device DMA through swiotlb
bounce buffers (is_swiotlb_force_bounce()) which copies data into
shared memory on behalf of the device.

When a caller has already arranged for the memory to be shared
via set_memory_decrypted(), the DMA API needs to know so it can map
directly using the unencrypted physical address rather than bounce
buffering. Following the pattern of DMA_ATTR_MMIO, add
DMA_ATTR_CC_SHARED for this purpose. Like the MMIO case, only the
caller knows what kind of memory it has and must inform the DMA API
for it to work correctly.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Acked-by: Sumit Semwal <sumit.semwal@linaro.org>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20260325192352.437608-2-jiri@resnulli.us

4 files changed, 34 insertions, 6 deletions

diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 677c51ab7510..db8ab24a54f4 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -92,6 +92,16 @@
  * flushing.
  */
 #define DMA_ATTR_REQUIRE_COHERENT	(1UL << 12)
+/*
+ * DMA_ATTR_CC_SHARED: Indicates the DMA mapping is shared (decrypted) for
+ * confidential computing guests. For normal system memory the caller must have
+ * called set_memory_decrypted(), and pgprot_decrypted must be used when
+ * creating CPU PTEs for the mapping. The same shared semantic may be passed
+ * to the vIOMMU when it sets up the IOPTE. For MMIO use together with
+ * DMA_ATTR_MMIO to indicate shared MMIO. Unless DMA_ATTR_MMIO is provided
+ * a struct page is required.
+ */
+#define DMA_ATTR_CC_SHARED	(1UL << 13)
 
 /*
  * A dma_addr_t can hold any valid DMA or bus address for the platform.  It can
diff --git a/include/trace/events/dma.h b/include/trace/events/dma.h
index 63597b004424..31c9ddf72c9d 100644
--- a/include/trace/events/dma.h
+++ b/include/trace/events/dma.h
@@ -34,7 +34,8 @@ TRACE_DEFINE_ENUM(DMA_NONE);
 		{ DMA_ATTR_PRIVILEGED, "PRIVILEGED" }, \
 		{ DMA_ATTR_MMIO, "MMIO" }, \
 		{ DMA_ATTR_DEBUGGING_IGNORE_CACHELINES, "CACHELINES_OVERLAP" }, \
-		{ DMA_ATTR_REQUIRE_COHERENT, "REQUIRE_COHERENT" })
+		{ DMA_ATTR_REQUIRE_COHERENT, "REQUIRE_COHERENT" }, \
+		{ DMA_ATTR_CC_SHARED, "CC_SHARED" })
 
 DECLARE_EVENT_CLASS(dma_map,
 	TP_PROTO(struct device *dev, phys_addr_t phys_addr, dma_addr_t dma_addr,
diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
index b86ff65496fc..7140c208c123 100644
--- a/kernel/dma/direct.h
+++ b/kernel/dma/direct.h
@@ -89,16 +89,24 @@ static inline dma_addr_t dma_direct_map_phys(struct device *dev,
 	dma_addr_t dma_addr;
 
 	if (is_swiotlb_force_bounce(dev)) {
-		if (attrs & (DMA_ATTR_MMIO | DMA_ATTR_REQUIRE_COHERENT))
-			return DMA_MAPPING_ERROR;
+		if (!(attrs & DMA_ATTR_CC_SHARED)) {
+			if (attrs & (DMA_ATTR_MMIO | DMA_ATTR_REQUIRE_COHERENT))
+				return DMA_MAPPING_ERROR;
 
-		return swiotlb_map(dev, phys, size, dir, attrs);
+			return swiotlb_map(dev, phys, size, dir, attrs);
+		}
+	} else if (attrs & DMA_ATTR_CC_SHARED) {
+		return DMA_MAPPING_ERROR;
 	}
 
 	if (attrs & DMA_ATTR_MMIO) {
 		dma_addr = phys;
 		if (unlikely(!dma_capable(dev, dma_addr, size, false)))
 			goto err_overflow;
+	} else if (attrs & DMA_ATTR_CC_SHARED) {
+		dma_addr = phys_to_dma_unencrypted(dev, phys);
+		if (unlikely(!dma_capable(dev, dma_addr, size, false)))
+			goto err_overflow;
 	} else {
 		dma_addr = phys_to_dma(dev, phys);
 		if (unlikely(!dma_capable(dev, dma_addr, size, true)) ||
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index df3eccc7d4ca..23ed8eb9233e 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -157,6 +157,7 @@ dma_addr_t dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 	bool is_mmio = attrs & DMA_ATTR_MMIO;
+	bool is_cc_shared = attrs & DMA_ATTR_CC_SHARED;
 	dma_addr_t addr = DMA_MAPPING_ERROR;
 
 	BUG_ON(!valid_dma_direction(dir));
@@ -168,8 +169,11 @@ dma_addr_t dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
 		return DMA_MAPPING_ERROR;
 
 	if (dma_map_direct(dev, ops) ||
-	    (!is_mmio && arch_dma_map_phys_direct(dev, phys + size)))
+	    (!is_mmio && !is_cc_shared &&
+	     arch_dma_map_phys_direct(dev, phys + size)))
 		addr = dma_direct_map_phys(dev, phys, size, dir, attrs, true);
+	else if (is_cc_shared)
+		return DMA_MAPPING_ERROR;
 	else if (use_dma_iommu(dev))
 		addr = iommu_dma_map_phys(dev, phys, size, dir, attrs);
 	else if (ops->map_phys)
@@ -206,11 +210,16 @@ void dma_unmap_phys(struct device *dev, dma_addr_t addr, size_t size,
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 	bool is_mmio = attrs & DMA_ATTR_MMIO;
+	bool is_cc_shared = attrs & DMA_ATTR_CC_SHARED;
 
 	BUG_ON(!valid_dma_direction(dir));
+
 	if (dma_map_direct(dev, ops) ||
-	    (!is_mmio && arch_dma_unmap_phys_direct(dev, addr + size)))
+	    (!is_mmio && !is_cc_shared &&
+	     arch_dma_unmap_phys_direct(dev, addr + size)))
 		dma_direct_unmap_phys(dev, addr, size, dir, attrs, true);
+	else if (is_cc_shared)
+		return;
 	else if (use_dma_iommu(dev))
 		iommu_dma_unmap_phys(dev, addr, size, dir, attrs);
 	else if (ops->unmap_phys)