MIPS: Loongson: Add swiotlb to support All-Memory DMA

Loongson doesn't support DMA address above 4GB traditionally. If memory
is more than 4GB, CONFIG_SWIOTLB and ZONE_DMA32 should be selected. In
this way, DMA pages are allocated below 4GB preferably. However, if low
memory is not enough, high pages are allocated and swiotlb is used for
bouncing.

Moreover, we provide a platform-specific dma_map_ops::set_dma_mask() to
set a device's dma_mask and coherent_dma_mask. We use these masks to
distinguishes an allocated page can be used for DMA directly, or need
swiotlb to bounce.

Recently, we found that 32-bit DMA isn't a hardware bug, but a hardware
configuration issue. So, latest firmware has enable the DMA support as
high as 40-bit. To support all-memory DMA for all devices (besides the
Loongson platform limit, there are still some devices have their own
DMA32 limit), and also to be compatible with old firmware, we keep use
swiotlb.

Signed-off-by: Huacai Chen <chenhc@lemote.com>
Signed-off-by: Hongliang Tao <taohl@lemote.com>
Signed-off-by: Hua Yan <yanh@lemote.com>
Tested-by: Alex Smith <alex.smith@imgtec.com>
Reviewed-by: Alex Smith <alex.smith@imgtec.com>
Cc: John Crispin <john@phrozen.org>
Cc: Steven J. Hill <Steven.Hill@imgtec.com>
Cc: Aurelien Jarno <aurelien@aurel32.net>
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/6636
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>

2 files changed, 141 insertions, 0 deletions

diff --git a/arch/mips/loongson/common/Makefile b/arch/mips/loongson/common/Makefile
index 9e4484ccbb03..0bb9cc9dc621 100644
--- a/arch/mips/loongson/common/Makefile
+++ b/arch/mips/loongson/common/Makefile
@@ -26,3 +26,8 @@ obj-$(CONFIG_CS5536) += cs5536/
 #
 
 obj-$(CONFIG_LOONGSON_SUSPEND) += pm.o
+
+#
+# Big Memory (SWIOTLB) Support
+#
+obj-$(CONFIG_SWIOTLB) += dma-swiotlb.o
diff --git a/arch/mips/loongson/common/dma-swiotlb.c b/arch/mips/loongson/common/dma-swiotlb.c
new file mode 100644
index 000000000000..c2be01f91575
--- /dev/null
+++ b/arch/mips/loongson/common/dma-swiotlb.c
@@ -0,0 +1,136 @@
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/dma-mapping.h>
+#include <linux/scatterlist.h>
+#include <linux/swiotlb.h>
+#include <linux/bootmem.h>
+
+#include <asm/bootinfo.h>
+#include <boot_param.h>
+#include <dma-coherence.h>
+
+static void *loongson_dma_alloc_coherent(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp, struct dma_attrs *attrs)
+{
+	void *ret;
+
+	if (dma_alloc_from_coherent(dev, size, dma_handle, &ret))
+		return ret;
+
+	/* ignore region specifiers */
+	gfp &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM);
+
+#ifdef CONFIG_ISA
+	if (dev == NULL)
+		gfp |= __GFP_DMA;
+	else
+#endif
+#ifdef CONFIG_ZONE_DMA
+	if (dev->coherent_dma_mask < DMA_BIT_MASK(32))
+		gfp |= __GFP_DMA;
+	else
+#endif
+#ifdef CONFIG_ZONE_DMA32
+	if (dev->coherent_dma_mask < DMA_BIT_MASK(40))
+		gfp |= __GFP_DMA32;
+	else
+#endif
+	;
+	gfp |= __GFP_NORETRY;
+
+	ret = swiotlb_alloc_coherent(dev, size, dma_handle, gfp);
+	mb();
+	return ret;
+}
+
+static void loongson_dma_free_coherent(struct device *dev, size_t size,
+		void *vaddr, dma_addr_t dma_handle, struct dma_attrs *attrs)
+{
+	int order = get_order(size);
+
+	if (dma_release_from_coherent(dev, order, vaddr))
+		return;
+
+	swiotlb_free_coherent(dev, size, vaddr, dma_handle);
+}
+
+static dma_addr_t loongson_dma_map_page(struct device *dev, struct page *page,
+				unsigned long offset, size_t size,
+				enum dma_data_direction dir,
+				struct dma_attrs *attrs)
+{
+	dma_addr_t daddr = swiotlb_map_page(dev, page, offset, size,
+					dir, attrs);
+	mb();
+	return daddr;
+}
+
+static int loongson_dma_map_sg(struct device *dev, struct scatterlist *sg,
+				int nents, enum dma_data_direction dir,
+				struct dma_attrs *attrs)
+{
+	int r = swiotlb_map_sg_attrs(dev, sg, nents, dir, NULL);
+	mb();
+
+	return r;
+}
+
+static void loongson_dma_sync_single_for_device(struct device *dev,
+				dma_addr_t dma_handle, size_t size,
+				enum dma_data_direction dir)
+{
+	swiotlb_sync_single_for_device(dev, dma_handle, size, dir);
+	mb();
+}
+
+static void loongson_dma_sync_sg_for_device(struct device *dev,
+				struct scatterlist *sg, int nents,
+				enum dma_data_direction dir)
+{
+	swiotlb_sync_sg_for_device(dev, sg, nents, dir);
+	mb();
+}
+
+static int loongson_dma_set_mask(struct device *dev, u64 mask)
+{
+	if (mask > DMA_BIT_MASK(loongson_sysconf.dma_mask_bits)) {
+		*dev->dma_mask = DMA_BIT_MASK(loongson_sysconf.dma_mask_bits);
+		return -EIO;
+	}
+
+	*dev->dma_mask = mask;
+
+	return 0;
+}
+
+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)
+{
+	return daddr;
+}
+
+static struct dma_map_ops loongson_dma_map_ops = {
+	.alloc = loongson_dma_alloc_coherent,
+	.free = loongson_dma_free_coherent,
+	.map_page = loongson_dma_map_page,
+	.unmap_page = swiotlb_unmap_page,
+	.map_sg = loongson_dma_map_sg,
+	.unmap_sg = swiotlb_unmap_sg_attrs,
+	.sync_single_for_cpu = swiotlb_sync_single_for_cpu,
+	.sync_single_for_device = loongson_dma_sync_single_for_device,
+	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
+	.sync_sg_for_device = loongson_dma_sync_sg_for_device,
+	.mapping_error = swiotlb_dma_mapping_error,
+	.dma_supported = swiotlb_dma_supported,
+	.set_dma_mask = loongson_dma_set_mask
+};
+
+void __init plat_swiotlb_setup(void)
+{
+	swiotlb_init(1);
+	mips_dma_map_ops = &loongson_dma_map_ops;
+}