[PATCH v3 2/3] MIPS: Loongson: Add DMA support for 7A1000

[Tiezhu Yang]

In the current market, the most used bridge chip on the Loongson platform
are AMD RS780E and Loongson 7A1000, the AMD RS780E is already supported by
the mainline kernel.

If use the default implementation of __phys_to_dma() and __dma_to_phys()
in dma-direct.h when CONFIG_ARCH_HAS_PHYS_TO_DMA is not set, it works
well used with 7A1000 on the Loongson single-way and multi-way platform,
and also works well used with RS780E on the Loongson single-way platform,
but the DMA address will be wrong on the non-node0 used with RS780E on
the Loongson multi-way platform.

Just as the description in the code comment, the devices get node id from
40 bit of HyperTransport bus, so we extract 2 bit node id (bit 44~45) from
48 bit address space of Loongson CPU and embed it into HyperTransport bus
(bit 37-38), this operation can be done only at the software level used
with RS780E on the Loongson multi-way platform, because it has no hardware
function to translate address of node id, this is a hardware compatibility
problem.

Device
    |
    | DMA address
    |
Host Bridge
    |
    | HT bus address (40 bit)
    |
   CPU
    |
    | physical address (48 bit)
    |
   RAM

The Loongson 7A1000 has dma_node_id_offset field in the DMA route config
register, the hardware can use the dma_node_id_offset to translate address
of node id automatically, so we can get correct address when just use the
dma_pfn_offset field in struct device.

For the above reasons, in order to maintain downward compatibility to
support the AMD RS780E bridge chip, it is better to use the platform
dependent implementation of __phys_to_dma() and __dma_to_phys().

Signed-off-by: Tiezhu Yang <yangtiezhu@xxxxxxxxxxx>
---

v3:
  - Modify the macro definition NODE_ID_OFFSET_ADDR to
    make it easy to read
  - update the commit message

 arch/mips/include/asm/mach-loongson64/boot_param.h |  5 +++++
 arch/mips/loongson64/dma.c                         |  9 ++++++---
 arch/mips/loongson64/env.c                         |  2 ++
 arch/mips/loongson64/init.c                        | 17 +++++++++++++++++
 4 files changed, 30 insertions(+), 3 deletions(-)

diff --git a/arch/mips/include/asm/mach-loongson64/boot_param.h b/arch/mips/include/asm/mach-loongson64/boot_param.h
index a272427..a36d3dc 100644
--- a/arch/mips/include/asm/mach-loongson64/boot_param.h
+++ b/arch/mips/include/asm/mach-loongson64/boot_param.h
@@ -221,9 +221,14 @@ struct loongson_system_configuration {
 	u32 nr_sensors;
 	struct sensor_device sensors[MAX_SENSORS];
 	u64 workarounds;
+	void (*early_config)(void);
 };
 
 extern struct efi_memory_map_loongson *loongson_memmap;
 extern struct loongson_system_configuration loongson_sysconf;
 
+extern u32 node_id_offset;
+extern void rs780e_early_config(void);
+extern void ls7a1000_early_config(void);
+
 #endif
diff --git a/arch/mips/loongson64/dma.c b/arch/mips/loongson64/dma.c
index 5e86635..dbfe6e8 100644
--- a/arch/mips/loongson64/dma.c
+++ b/arch/mips/loongson64/dma.c
@@ -2,21 +2,24 @@
 #include <linux/dma-direct.h>
 #include <linux/init.h>
 #include <linux/swiotlb.h>
+#include <boot_param.h>
 
 dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	/* 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 */
 	long nid = (paddr >> 44) & 0x3;
-	return ((nid << 44) ^ paddr) | (nid << 37);
+
+	return ((nid << 44) ^ paddr) | (nid << node_id_offset);
 }
 
 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 */
-	long nid = (daddr >> 37) & 0x3;
-	return ((nid << 37) ^ daddr) | (nid << 44);
+	long nid = (daddr >> node_id_offset) & 0x3;
+
+	return ((nid << node_id_offset) ^ daddr) | (nid << 44);
 }
 
 void __init plat_swiotlb_setup(void)
diff --git a/arch/mips/loongson64/env.c b/arch/mips/loongson64/env.c
index 257a9b6..8b8d6f6 100644
--- a/arch/mips/loongson64/env.c
+++ b/arch/mips/loongson64/env.c
@@ -192,8 +192,10 @@ void __init prom_init_env(void)
 	if (vendor == PCI_VENDOR_ID_LOONGSON && device == 0x7a00) {
 		pr_info("The bridge chip is Loongson 7A1000\n");
 		loongson_sysconf.bridgetype = LS7A1000;
+		loongson_sysconf.early_config = ls7a1000_early_config;
 	} else {
 		pr_info("The bridge chip is AMD RS780E or SR5690\n");
 		loongson_sysconf.bridgetype = RS780E;
+		loongson_sysconf.early_config = rs780e_early_config;
 	}
 }
diff --git a/arch/mips/loongson64/init.c b/arch/mips/loongson64/init.c
index da38944..8ee010f3 100644
--- a/arch/mips/loongson64/init.c
+++ b/arch/mips/loongson64/init.c
@@ -13,6 +13,11 @@
 #include <asm/fw/fw.h>
 
 #include <loongson.h>
+#include <boot_param.h>
+
+#define NODE_ID_OFFSET_ADDR	((void __iomem *)TO_UNCAC(0x1001041c))
+
+u32 node_id_offset;
 
 static void __init mips_nmi_setup(void)
 {
@@ -24,6 +29,16 @@ static void __init mips_nmi_setup(void)
 	flush_icache_range((unsigned long)base, (unsigned long)base + 0x80);
 }
 
+void rs780e_early_config(void)
+{
+	node_id_offset = 37;
+}
+
+void ls7a1000_early_config(void)
+{
+	node_id_offset = ((readl(NODE_ID_OFFSET_ADDR) >> 8) & 0x1f) + 36;
+}
+
 void __init prom_init(void)
 {
 	fw_init_cmdline();
@@ -33,6 +48,8 @@ void __init prom_init(void)
 	set_io_port_base((unsigned long)
 		ioremap(LOONGSON_PCIIO_BASE, LOONGSON_PCIIO_SIZE));
 
+	loongson_sysconf.early_config();
+
 	prom_init_numa_memory();
 
 	/* Hardcode to CPU UART 0 */
-- 
2.1.0