MIPS: Loongson-3: Add PHYS48_TO_HT40 support

The width of HT-bus is only 40-bit, but Loongson-3 has 48-bit physical
address. This implies only node-0's memory is DMAable because high bits
(Node ID) will lost. Fortunately, by configuring address windows in
firmware, we can extract 2bit Node ID (bit 44~47, only bit 44~45 used
now) from Loongson-3's 48-bit address space and embed it into 40-bit
(bit 37~38). Every NUMA node can do DMA now (however, maximum memory of
each node is reduced to 2^37 = 128GB).

Signed-off-by: Huacai Chen <chenhc@lemote.com>
Cc: John Crispin <john@phrozen.org>
Cc: Steven J. Hill <Steven.Hill@imgtec.com>
Cc: linux-mips@linux-mips.org
Cc: Fuxin Zhang <zhangfx@lemote.com>
Cc: Zhangjin Wu <wuzhangjin@gmail.com>
Patchwork: https://patchwork.linux-mips.org/patch/8321/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>

arch/mips/include/asm/mach-loongson/dma-coherence.h

@@ -23,7 +23,7 @@ static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
 					  size_t size)
 {
 #ifdef CONFIG_CPU_LOONGSON3
-	return virt_to_phys(addr);
+	return phys_to_dma(dev, virt_to_phys(addr));
 #else
 	return virt_to_phys(addr) | 0x80000000;
 #endif
@@ -33,7 +33,7 @@ static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
 					       struct page *page)
 {
 #ifdef CONFIG_CPU_LOONGSON3
-	return page_to_phys(page);
+	return phys_to_dma(dev, page_to_phys(page));
 #else
 	return page_to_phys(page) | 0x80000000;
 #endif
@@ -43,7 +43,7 @@ static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
 	dma_addr_t dma_addr)
 {
 #if defined(CONFIG_CPU_LOONGSON3) && defined(CONFIG_64BIT)
-	return dma_addr;
+	return dma_to_phys(dev, dma_addr);
 #elif defined(CONFIG_CPU_LOONGSON2F) && defined(CONFIG_64BIT)
 	return (dma_addr > 0x8fffffff) ? dma_addr : (dma_addr & 0x0fffffff);
 #else

arch/mips/loongson/Kconfig

@@ -86,6 +86,7 @@ config LOONGSON_MACH3X
 	select LOONGSON_MC146818
 	select ZONE_DMA32
 	select LEFI_FIRMWARE_INTERFACE
+	select PHYS48_TO_HT40
 	help
 		Generic Loongson 3 family machines utilize the 3A/3B revision
 		of Loongson processor and RS780/SBX00 chipset.
@@ -131,6 +132,10 @@ config SWIOTLB
 	select NEED_SG_DMA_LENGTH
 	select NEED_DMA_MAP_STATE
 
+config PHYS48_TO_HT40
+	bool
+	default y if CPU_LOONGSON3
+
 config LOONGSON_MC146818
 	bool
 	default n

arch/mips/loongson/common/dma-swiotlb.c

@@ -105,11 +105,25 @@ static int loongson_dma_set_mask(struct device *dev, u64 mask)
 
 dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
+	long nid;
+#ifdef CONFIG_PHYS48_TO_HT40
+	/* 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 */
+	nid = (paddr >> 44) & 0x3;
+	paddr = ((nid << 44) ^ paddr) | (nid << 37);
+#endif
 	return paddr;
 }
 
 phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 {
+	long nid;
+#ifdef CONFIG_PHYS48_TO_HT40
+	/* 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 */
+	nid = (daddr >> 37) & 0x3;
+	daddr = ((nid << 37) ^ daddr) | (nid << 44);
+#endif
 	return daddr;
 }