MIPS: Loongson-3: Introduce CONFIG_LOONGSON3_ENHANCEMENT

New Loongson 3 CPU (since Loongson-3A R2, as opposed to Loongson-3A R1,
Loongson-3B R1 and Loongson-3B R2) has many enhancements, such as FTLB,
L1-VCache, EI/DI/Wait/Prefetch instruction, DSP/DSPv2 ASE, User Local
register, Read-Inhibit/Execute-Inhibit, SFB (Store Fill Buffer), Fast
TLB refill support, etc.

This patch introduce a config option, CONFIG_LOONGSON3_ENHANCEMENT, to
enable those enhancements which are not probed at run time. If you want
a generic kernel to run on all Loongson 3 machines, please say 'N'
here. If you want a high-performance kernel to run on new Loongson 3
machines only, please say 'Y' here.

Some additional explanations:
1) SFB locates between core and L1 cache, it causes memory access out
   of order, so writel/outl (and other similar functions) need a I/O
   reorder barrier.
2) Loongson 3 has a bug that di instruction can not save the irqflag,
   so arch_local_irq_save() is modified. Since CPU_MIPSR2 is selected
   by CONFIG_LOONGSON3_ENHANCEMENT, generic kernel doesn't use ei/di
   at all.
3) CPU_HAS_PREFETCH is selected by CONFIG_LOONGSON3_ENHANCEMENT, so
   MIPS_CPU_PREFETCH (used by uasm) probing is also put in this patch.

Signed-off-by: Huacai Chen <chenhc@lemote.com>
Cc: Aurelien Jarno <aurelien@aurel32.net>
Cc: Steven J . Hill <sjhill@realitydiluted.com>
Cc: Fuxin Zhang <zhangfx@lemote.com>
Cc: Zhangjin Wu <wuzhangjin@gmail.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/12755/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>

arch/mips/Kconfig

@@ -1360,6 +1360,24 @@ config CPU_LOONGSON3
 		The Loongson 3 processor implements the MIPS64R2 instruction
 		set with many extensions.
 
+config LOONGSON3_ENHANCEMENT
+	bool "New Loongson 3 CPU Enhancements"
+	default n
+	select CPU_MIPSR2
+	select CPU_HAS_PREFETCH
+	depends on CPU_LOONGSON3
+	help
+	  New Loongson 3 CPU (since Loongson-3A R2, as opposed to Loongson-3A
+	  R1, Loongson-3B R1 and Loongson-3B R2) has many enhancements, such as
+	  FTLB, L1-VCache, EI/DI/Wait/Prefetch instruction, DSP/DSPv2 ASE, User
+	  Local register, Read-Inhibit/Execute-Inhibit, SFB (Store Fill Buffer),
+	  Fast TLB refill support, etc.
+
+	  This option enable those enhancements which are not probed at run
+	  time. If you want a generic kernel to run on all Loongson 3 machines,
+	  please say 'N' here. If you want a high-performance kernel to run on
+	  new Loongson 3 machines only, please say 'Y' here.
+
 config CPU_LOONGSON2E
 	bool "Loongson 2E"
 	depends on SYS_HAS_CPU_LOONGSON2E

arch/mips/include/asm/hazards.h

@@ -22,7 +22,8 @@
 /*
  * TLB hazards
  */
-#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) && !defined(CONFIG_CPU_CAVIUM_OCTEON)
+#if (defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)) && \
+	!defined(CONFIG_CPU_CAVIUM_OCTEON) && !defined(CONFIG_LOONGSON3_ENHANCEMENT)
 
 /*
  * MIPSR2 defines ehb for hazard avoidance
@@ -155,8 +156,8 @@ do {									\
 } while (0)
 
 #elif defined(CONFIG_MIPS_ALCHEMY) || defined(CONFIG_CPU_CAVIUM_OCTEON) || \
-	defined(CONFIG_CPU_LOONGSON2) || defined(CONFIG_CPU_R10000) || \
-	defined(CONFIG_CPU_R5500) || defined(CONFIG_CPU_XLR)
+	defined(CONFIG_CPU_LOONGSON2) || defined(CONFIG_LOONGSON3_ENHANCEMENT) || \
+	defined(CONFIG_CPU_R10000) || defined(CONFIG_CPU_R5500) || defined(CONFIG_CPU_XLR)
 
 /*
  * R10000 rocks - all hazards handled in hardware, so this becomes a nobrainer.

arch/mips/include/asm/io.h

@@ -304,10 +304,10 @@ static inline void iounmap(const volatile void __iomem *addr)
 #undef __IS_KSEG1
 }
 
-#ifdef CONFIG_CPU_CAVIUM_OCTEON
-#define war_octeon_io_reorder_wmb()		wmb()
+#if defined(CONFIG_CPU_CAVIUM_OCTEON) || defined(CONFIG_LOONGSON3_ENHANCEMENT)
+#define war_io_reorder_wmb()		wmb()
 #else
-#define war_octeon_io_reorder_wmb()		do { } while (0)
+#define war_io_reorder_wmb()		do { } while (0)
 #endif
 
 #define __BUILD_MEMORY_SINGLE(pfx, bwlq, type, irq)			\
@@ -318,7 +318,7 @@ static inline void pfx##write##bwlq(type val,				\
 	volatile type *__mem;						\
 	type __val;							\
 									\
-	war_octeon_io_reorder_wmb();					\
+	war_io_reorder_wmb();					\
 									\
 	__mem = (void *)__swizzle_addr_##bwlq((unsigned long)(mem));	\
 									\
@@ -387,7 +387,7 @@ static inline void pfx##out##bwlq##p(type val, unsigned long port)	\
 	volatile type *__addr;						\
 	type __val;							\
 									\
-	war_octeon_io_reorder_wmb();					\
+	war_io_reorder_wmb();					\
 									\
 	__addr = (void *)__swizzle_addr_##bwlq(mips_io_port_base + port); \
 									\

arch/mips/include/asm/irqflags.h

@@ -41,7 +41,12 @@ static inline unsigned long arch_local_irq_save(void)
 	"	.set	push						\n"
 	"	.set	reorder						\n"
 	"	.set	noat						\n"
+#if defined(CONFIG_CPU_LOONGSON3)
+	"	mfc0	%[flags], $12					\n"
+	"	di							\n"
+#else
 	"	di	%[flags]					\n"
+#endif
 	"	andi	%[flags], 1					\n"
 	"	" __stringify(__irq_disable_hazard) "			\n"
 	"	.set	pop						\n"

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

@@ -26,6 +26,12 @@
 	mfc0	t0, $5, 1
 	or	t0, (0x1 << 29)
 	mtc0	t0, $5, 1
+#ifdef CONFIG_LOONGSON3_ENHANCEMENT
+	/* Enable STFill Buffer */
+	mfc0	t0, $16, 6
+	or	t0, 0x100
+	mtc0	t0, $16, 6
+#endif
 	_ehb
 	.set	pop
 #endif
@@ -46,6 +52,12 @@
 	mfc0	t0, $5, 1
 	or	t0, (0x1 << 29)
 	mtc0	t0, $5, 1
+#ifdef CONFIG_LOONGSON3_ENHANCEMENT
+	/* Enable STFill Buffer */
+	mfc0	t0, $16, 6
+	or	t0, 0x100
+	mtc0	t0, $16, 6
+#endif
 	_ehb
 	.set	pop
 #endif

arch/mips/mm/c-r4k.c

@@ -1161,6 +1161,8 @@ static void probe_pcache(void)
 					  c->dcache.ways *
 					  c->dcache.linesz;
 		c->dcache.waybit = 0;
+		if ((prid & PRID_REV_MASK) >= PRID_REV_LOONGSON3A_R2)
+			c->options |= MIPS_CPU_PREFETCH;
 		break;
 
 	case CPU_CAVIUM_OCTEON3:

arch/mips/mm/page.c

@@ -188,6 +188,15 @@ static void set_prefetch_parameters(void)
 			}
 			break;
 
+		case CPU_LOONGSON3:
+			/* Loongson-3 only support the Pref_Load/Pref_Store. */
+			pref_bias_clear_store = 128;
+			pref_bias_copy_load = 128;
+			pref_bias_copy_store = 128;
+			pref_src_mode = Pref_Load;
+			pref_dst_mode = Pref_Store;
+			break;
+
 		default:
 			pref_bias_clear_store = 128;
 			pref_bias_copy_load = 256;