MIPS: Loongson-3: Enable Store Fill Buffer at runtime

New Loongson-3 (Loongson-3A R2, Loongson-3A R3, and newer) has SFB
(Store Fill Buffer) which can improve the performance of memory access.
Now, SFB enablement is controlled by CONFIG_LOONGSON3_ENHANCEMENT, and
the generic kernel has no benefit from SFB (even it is running on a new
Loongson-3 machine). With this patch, we can enable SFB at runtime by
detecting the CPU type (the expense is war_io_reorder_wmb() will always
be a 'sync', which will hurt the performance of old Loongson-3).

[paul.burton@mips.com: Further info from Huacai:
  In practise, I found that sometimes there are boot failures if I
  enable SFB/LPA in cpu_probe(). I don't know why because processor
  designers also haven't give me an explaination, but I think this may
  have some relationships to speculative execution.]

Signed-off-by: Huacai Chen <chenhc@lemote.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/20426/
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: linux-mips@linux-mips.org
Cc: Fuxin Zhang <zhangfx@lemote.com>
Cc: Zhangjin Wu <wuzhangjin@gmail.com>
Cc: Huacai Chen <chenhuacai@gmail.com>

arch/mips/include/asm/io.h

@@ -289,7 +289,7 @@ static inline void iounmap(const volatile void __iomem *addr)
 #undef __IS_KSEG1
 }
 
-#if defined(CONFIG_CPU_CAVIUM_OCTEON) || defined(CONFIG_LOONGSON3_ENHANCEMENT)
+#if defined(CONFIG_CPU_CAVIUM_OCTEON) || defined(CONFIG_CPU_LOONGSON3)
 #define war_io_reorder_wmb()		wmb()
 #else
 #define war_io_reorder_wmb()		barrier()

arch/mips/include/asm/mach-loongson64/kernel-entry-init.h

@@ -11,6 +11,8 @@
 #ifndef __ASM_MACH_LOONGSON64_KERNEL_ENTRY_H
 #define __ASM_MACH_LOONGSON64_KERNEL_ENTRY_H
 
+#include <asm/cpu.h>
+
 /*
  * Override macros used in arch/mips/kernel/head.S.
  */
@@ -26,12 +28,15 @@
 	mfc0	t0, CP0_PAGEGRAIN
 	or	t0, (0x1 << 29)
 	mtc0	t0, CP0_PAGEGRAIN
-#ifdef CONFIG_LOONGSON3_ENHANCEMENT
 	/* Enable STFill Buffer */
+	mfc0	t0, CP0_PRID
+	andi	t0, (PRID_IMP_MASK | PRID_REV_MASK)
+	slti	t0, (PRID_IMP_LOONGSON_64 | PRID_REV_LOONGSON3A_R2)
+	bnez	t0, 1f
 	mfc0	t0, CP0_CONFIG6
 	or	t0, 0x100
 	mtc0	t0, CP0_CONFIG6
-#endif
+1:
 	_ehb
 	.set	pop
 #endif
@@ -52,12 +57,15 @@
 	mfc0	t0, CP0_PAGEGRAIN
 	or	t0, (0x1 << 29)
 	mtc0	t0, CP0_PAGEGRAIN
-#ifdef CONFIG_LOONGSON3_ENHANCEMENT
 	/* Enable STFill Buffer */
+	mfc0	t0, CP0_PRID
+	andi	t0, (PRID_IMP_MASK | PRID_REV_MASK)
+	slti	t0, (PRID_IMP_LOONGSON_64 | PRID_REV_LOONGSON3A_R2)
+	bnez	t0, 1f
 	mfc0	t0, CP0_CONFIG6
 	or	t0, 0x100
 	mtc0	t0, CP0_CONFIG6
-#endif
+1:
 	_ehb
 	.set	pop
 #endif