dma-direct: remove __dma_to_phys

There is no harm in just always clearing the SME encryption bit, while
significantly simplifying the interface.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>

arch/arm/include/asm/dma-direct.h

@@ -8,7 +8,7 @@ static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return pfn_to_dma(dev, __phys_to_pfn(paddr)) + offset;
 }
 
-static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dev_addr)
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
 {
 	unsigned int offset = dev_addr & ~PAGE_MASK;
 	return __pfn_to_phys(dma_to_pfn(dev, dev_addr)) + offset;

arch/mips/bmips/dma.c

@@ -52,7 +52,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t pa)
 	return pa;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	struct bmips_dma_range *r;
 

arch/mips/cavium-octeon/dma-octeon.c

@@ -177,7 +177,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return paddr;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 {
 #ifdef CONFIG_PCI
 	if (dev && dev_is_pci(dev))

arch/mips/include/asm/dma-direct.h

@@ -3,6 +3,6 @@
 #define _MIPS_DMA_DIRECT_H 1
 
 dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr);
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr);
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr);
 
 #endif /* _MIPS_DMA_DIRECT_H */

arch/mips/loongson2ef/fuloong-2e/dma.c

@@ -6,7 +6,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return paddr | 0x80000000;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	return dma_addr & 0x7fffffff;
 }

arch/mips/loongson2ef/lemote-2f/dma.c

@@ -6,7 +6,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return paddr | 0x80000000;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	if (dma_addr > 0x8fffffff)
 		return dma_addr;

arch/mips/loongson64/dma.c

@@ -13,7 +13,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return ((nid << 44) ^ paddr) | (nid << node_id_offset);
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 {
 	/* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from
 	 * Loongson-3's 48bit address space and embed it into 40bit */

arch/mips/pci/pci-ar2315.c

@@ -175,7 +175,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return paddr + ar2315_dev_offset(dev);
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	return dma_addr - ar2315_dev_offset(dev);
 }

arch/mips/pci/pci-xtalk-bridge.c

@@ -33,7 +33,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return bc->baddr + paddr;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	return dma_addr & ~(0xffUL << 56);
 }

arch/mips/sgi-ip32/ip32-dma.c

@@ -27,7 +27,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return dma_addr;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	phys_addr_t paddr = dma_addr & RAM_OFFSET_MASK;
 

arch/powerpc/include/asm/dma-direct.h

@@ -7,7 +7,7 @@ static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return paddr + dev->archdata.dma_offset;
 }
 
-static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 {
 	return daddr - dev->archdata.dma_offset;
 }

include/linux/dma-direct.h

@@ -24,11 +24,12 @@ static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return dev_addr - ((dma_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
 }
 
-static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dev_addr)
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
 {
-	phys_addr_t paddr = (phys_addr_t)dev_addr;
+	phys_addr_t paddr = (phys_addr_t)dev_addr +
+		((phys_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
 
-	return paddr + ((phys_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
+	return __sme_clr(paddr);
 }
 #endif /* !CONFIG_ARCH_HAS_PHYS_TO_DMA */
 
@@ -44,7 +45,7 @@ static inline bool force_dma_unencrypted(struct device *dev)
 /*
  * 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
- * and __dma_to_phys versions should only be used on non-encrypted memory for
+ * version should only be used on non-encrypted memory for
  * special occasions like DMA coherent buffers.
  */
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
@@ -52,11 +53,6 @@ static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return __sme_set(__phys_to_dma(dev, paddr));
 }
 
-static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
-{
-	return __sme_clr(__dma_to_phys(dev, daddr));
-}
-
 static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size,
 		bool is_ram)
 {

kernel/dma/direct.c

@@ -48,11 +48,6 @@ static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 {
 	u64 dma_limit = min_not_zero(dma_mask, dev->bus_dma_limit);
 
-	if (force_dma_unencrypted(dev))
-		*phys_limit = __dma_to_phys(dev, dma_limit);
-	else
-		*phys_limit = dma_to_phys(dev, dma_limit);
-
 	/*
 	 * Optimistically try the zone that the physical address mask falls
 	 * into first.  If that returns memory that isn't actually addressable
@@ -61,6 +56,7 @@ static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 	 * Note that GFP_DMA32 and GFP_DMA are no ops without the corresponding
 	 * zones.
 	 */
+	*phys_limit = dma_to_phys(dev, dma_limit);
 	if (*phys_limit <= DMA_BIT_MASK(zone_dma_bits))
 		return GFP_DMA;
 	if (*phys_limit <= DMA_BIT_MASK(32))