Merge tag 'dma-mapping-5.3-1' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping fixes from Christoph Hellwig:
 "Fix various regressions:

   - force unencrypted dma-coherent buffers if encryption bit can't fit
     into the dma coherent mask (Tom Lendacky)

   - avoid limiting request size if swiotlb is not used (me)

   - fix swiotlb handling in dma_direct_sync_sg_for_cpu/device (Fugang
     Duan)"

* tag 'dma-mapping-5.3-1' of git://git.infradead.org/users/hch/dma-mapping:
  dma-direct: correct the physical addr in dma_direct_sync_sg_for_cpu/device
  dma-direct: only limit the mapping size if swiotlb could be used
  dma-mapping: add a dma_addressing_limited helper
  dma-direct: Force unencrypted DMA under SME for certain DMA masks

8 files changed, 83 insertions, 26 deletions

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 5d8570ed6cab..a4ad2733eedf 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -189,6 +189,7 @@ config S390
 	select VIRT_CPU_ACCOUNTING
 	select ARCH_HAS_SCALED_CPUTIME
 	select HAVE_NMI
+	select ARCH_HAS_FORCE_DMA_UNENCRYPTED
 	select SWIOTLB
 	select GENERIC_ALLOCATOR
 
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 4e5bbe328594..20340a03ad90 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -30,7 +30,7 @@
 #include <linux/export.h>
 #include <linux/cma.h>
 #include <linux/gfp.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-direct.h>
 #include <asm/processor.h>
 #include <linux/uaccess.h>
 #include <asm/pgtable.h>
@@ -161,6 +161,11 @@ bool sev_active(void)
 	return is_prot_virt_guest();
 }
 
+bool force_dma_unencrypted(struct device *dev)
+{
+	return sev_active();
+}
+
 /* protected virtualization */
 static void pv_init(void)
 {
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 78772870facd..222855cc0158 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1526,6 +1526,7 @@ config AMD_MEM_ENCRYPT
 	depends on X86_64 && CPU_SUP_AMD
 	select DYNAMIC_PHYSICAL_MASK
 	select ARCH_USE_MEMREMAP_PROT
+	select ARCH_HAS_FORCE_DMA_UNENCRYPTED
 	---help---
 	  Say yes to enable support for the encryption of system memory.
 	  This requires an AMD processor that supports Secure Memory
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index e94e0a62ba92..fece30ca8b0c 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -15,6 +15,10 @@
 #include <linux/dma-direct.h>
 #include <linux/swiotlb.h>
 #include <linux/mem_encrypt.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <linux/dma-mapping.h>
 
 #include <asm/tlbflush.h>
 #include <asm/fixmap.h>
@@ -348,6 +352,32 @@ bool sev_active(void)
 }
 EXPORT_SYMBOL(sev_active);
 
+/* Override for DMA direct allocation check - ARCH_HAS_FORCE_DMA_UNENCRYPTED */
+bool force_dma_unencrypted(struct device *dev)
+{
+	/*
+	 * For SEV, all DMA must be to unencrypted addresses.
+	 */
+	if (sev_active())
+		return true;
+
+	/*
+	 * For SME, all DMA must be to unencrypted addresses if the
+	 * device does not support DMA to addresses that include the
+	 * encryption mask.
+	 */
+	if (sme_active()) {
+		u64 dma_enc_mask = DMA_BIT_MASK(__ffs64(sme_me_mask));
+		u64 dma_dev_mask = min_not_zero(dev->coherent_dma_mask,
+						dev->bus_dma_mask);
+
+		if (dma_dev_mask <= dma_enc_mask)
+			return true;
+	}
+
+	return false;
+}
+
 /* Architecture __weak replacement functions */
 void __init mem_encrypt_free_decrypted_mem(void)
 {
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index b7338702592a..adf993a3bd58 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -32,6 +32,15 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
 }
 #endif /* !CONFIG_ARCH_HAS_PHYS_TO_DMA */
 
+#ifdef CONFIG_ARCH_HAS_FORCE_DMA_UNENCRYPTED
+bool force_dma_unencrypted(struct device *dev);
+#else
+static inline bool force_dma_unencrypted(struct device *dev)
+{
+	return false;
+}
+#endif /* CONFIG_ARCH_HAS_FORCE_DMA_UNENCRYPTED */
+
 /*
  * If memory encryption is supported, phys_to_dma will set the memory encryption
  * bit in the DMA address, and dma_to_phys will clear it.  The raw __phys_to_dma
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 8d13e28a8e07..e11b115dd0e4 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -679,6 +679,20 @@ static inline int dma_coerce_mask_and_coherent(struct device *dev, u64 mask)
 	return dma_set_mask_and_coherent(dev, mask);
 }
 
+/**
+ * dma_addressing_limited - return if the device is addressing limited
+ * @dev:	device to check
+ *
+ * Return %true if the devices DMA mask is too small to address all memory in
+ * the system, else %false.  Lack of addressing bits is the prime reason for
+ * bounce buffering, but might not be the only one.
+ */
+static inline bool dma_addressing_limited(struct device *dev)
+{
+	return min_not_zero(*dev->dma_mask, dev->bus_dma_mask) <
+		dma_get_required_mask(dev);
+}
+
 #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 		const struct iommu_ops *iommu, bool coherent);
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index 70f8f8d9200e..9decbba255fc 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -48,6 +48,9 @@ config ARCH_HAS_DMA_COHERENT_TO_PFN
 config ARCH_HAS_DMA_MMAP_PGPROT
 	bool
 
+config ARCH_HAS_FORCE_DMA_UNENCRYPTED
+	bool
+
 config DMA_NONCOHERENT_CACHE_SYNC
 	bool
 
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index b90e1aede743..59bdceea3737 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -23,14 +23,6 @@
 #define ARCH_ZONE_DMA_BITS 24
 #endif
 
-/*
- * For AMD SEV all DMA must be to unencrypted addresses.
- */
-static inline bool force_dma_unencrypted(void)
-{
-	return sev_active();
-}
-
 static void report_addr(struct device *dev, dma_addr_t dma_addr, size_t size)
 {
 	if (!dev->dma_mask) {
@@ -46,7 +38,7 @@ static void report_addr(struct device *dev, dma_addr_t dma_addr, size_t size)
 static inline dma_addr_t phys_to_dma_direct(struct device *dev,
 		phys_addr_t phys)
 {
-	if (force_dma_unencrypted())
+	if (force_dma_unencrypted(dev))
 		return __phys_to_dma(dev, phys);
 	return phys_to_dma(dev, phys);
 }
@@ -67,7 +59,7 @@ static gfp_t __dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 	if (dev->bus_dma_mask && dev->bus_dma_mask < dma_mask)
 		dma_mask = dev->bus_dma_mask;
 
-	if (force_dma_unencrypted())
+	if (force_dma_unencrypted(dev))
 		*phys_mask = __dma_to_phys(dev, dma_mask);
 	else
 		*phys_mask = dma_to_phys(dev, dma_mask);
@@ -159,7 +151,7 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 	}
 
 	ret = page_address(page);
-	if (force_dma_unencrypted()) {
+	if (force_dma_unencrypted(dev)) {
 		set_memory_decrypted((unsigned long)ret, 1 << get_order(size));
 		*dma_handle = __phys_to_dma(dev, page_to_phys(page));
 	} else {
@@ -192,7 +184,7 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
 		return;
 	}
 
-	if (force_dma_unencrypted())
+	if (force_dma_unencrypted(dev))
 		set_memory_encrypted((unsigned long)cpu_addr, 1 << page_order);
 
 	if (IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) &&
@@ -242,12 +234,14 @@ void dma_direct_sync_sg_for_device(struct device *dev,
 	int i;
 
 	for_each_sg(sgl, sg, nents, i) {
-		if (unlikely(is_swiotlb_buffer(sg_phys(sg))))
-			swiotlb_tbl_sync_single(dev, sg_phys(sg), sg->length,
+		phys_addr_t paddr = dma_to_phys(dev, sg_dma_address(sg));
+
+		if (unlikely(is_swiotlb_buffer(paddr)))
+			swiotlb_tbl_sync_single(dev, paddr, sg->length,
 					dir, SYNC_FOR_DEVICE);
 
 		if (!dev_is_dma_coherent(dev))
-			arch_sync_dma_for_device(dev, sg_phys(sg), sg->length,
+			arch_sync_dma_for_device(dev, paddr, sg->length,
 					dir);
 	}
 }
@@ -279,11 +273,13 @@ void dma_direct_sync_sg_for_cpu(struct device *dev,
 	int i;
 
 	for_each_sg(sgl, sg, nents, i) {
+		phys_addr_t paddr = dma_to_phys(dev, sg_dma_address(sg));
+
 		if (!dev_is_dma_coherent(dev))
-			arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
-	
-		if (unlikely(is_swiotlb_buffer(sg_phys(sg))))
-			swiotlb_tbl_sync_single(dev, sg_phys(sg), sg->length, dir,
+			arch_sync_dma_for_cpu(dev, paddr, sg->length, dir);
+
+		if (unlikely(is_swiotlb_buffer(paddr)))
+			swiotlb_tbl_sync_single(dev, paddr, sg->length, dir,
 					SYNC_FOR_CPU);
 	}
 
@@ -407,11 +403,9 @@ int dma_direct_supported(struct device *dev, u64 mask)
 
 size_t dma_direct_max_mapping_size(struct device *dev)
 {
-	size_t size = SIZE_MAX;
-
 	/* If SWIOTLB is active, use its maximum mapping size */
-	if (is_swiotlb_active())
-		size = swiotlb_max_mapping_size(dev);
-
-	return size;
+	if (is_swiotlb_active() &&
+	    (dma_addressing_limited(dev) || swiotlb_force == SWIOTLB_FORCE))
+		return swiotlb_max_mapping_size(dev);
+	return SIZE_MAX;
 }