MIPS: clean up CONFIG_MIPS_PGD_C0_CONTEXT handling

+. LOONGSON64 use 0x98xx_xxxx_xxxx_xxxx as xphys cached, instread of
0xa8xx_xxxx_xxxx_xxxx

+. let CONFIG_MIPS_PGD_C0_CONTEXT depend on 64bit

+. cast CAC_BASE into u64 to silence warning on MIPS32

CP0 Context has enough room for wraping pgd into its 41-bit PTEBase field.

+. For XPHYS, the trick is that pgd is 4kB aligned, and the PABITS <= 53,
only save 53 - 12 = 41 bits, aka :

   bit[63:59] | 0000 00 |  bit[53:12] | 0000 0000 0000

+. for CKSEG0, only save 29 - 12 = 17 bits

when switching pgd, only need to save bit[53:12] or bit[28:12] into
CP0 Context's bit[63:23], see folling asm generated at run time

tlbmiss_handler_setup_pgd:
	.set	push
	.set	noreorder

	dsra	a2, a0, 29
	move	a3, a0
	dins	a0, zero, 29, 35
	daddiu	a2, a2, 4	//for CKSEG0, a2 from 0xfffffffffffffffc
				//into 0

	movn	a0, a3, a2
	dsll	a0, a0, 11
	jr	ra
	dmtc0	a0, CP0_CONTEXT

	.set	pop

when using it on page walking

	dmfc0	k0, CP0_CONTEXT
	dins	k0, zero, 0, 23	         // zero badv2
	ori	k0, k0, (CAC_BASE >> 53) // *prefix* with bit[63:59]
	drotr	k0, k0, 11		 // kick it in the right place
Signed-off-by: Huang Pei <huangpei@loongson.cn>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>

arch/mips/Kconfig

@@ -2188,7 +2188,8 @@ config CPU_SUPPORTS_HUGEPAGES
 	depends on !(32BIT && (ARCH_PHYS_ADDR_T_64BIT || EVA))
 config MIPS_PGD_C0_CONTEXT
 	bool
-	default y if 64BIT && (CPU_MIPSR2 || CPU_MIPSR6) && !CPU_XLP
+	depends on 64BIT
+	default y if (CPU_MIPSR2 || CPU_MIPSR6) && !CPU_XLP
 
 #
 # Set to y for ptrace access to watch registers.

arch/mips/mm/tlbex.c

@@ -849,8 +849,8 @@ void build_get_pmde64(u32 **p, struct uasm_label **l, struct uasm_reloc **r,
 		/* Clear lower 23 bits of context. */
 		uasm_i_dins(p, ptr, 0, 0, 23);
 
-		/* 1 0	1 0 1  << 6  xkphys cached */
-		uasm_i_ori(p, ptr, ptr, 0x540);
+		/* insert bit[63:59] of CAC_BASE into bit[11:6] of ptr */
+		uasm_i_ori(p, ptr, ptr, ((u64)(CAC_BASE) >> 53));
 		uasm_i_drotr(p, ptr, ptr, 11);
 #elif defined(CONFIG_SMP)
 		UASM_i_CPUID_MFC0(p, ptr, SMP_CPUID_REG);
@@ -1165,8 +1165,9 @@ build_fast_tlb_refill_handler (u32 **p, struct uasm_label **l,
 
 	if (pgd_reg == -1) {
 		vmalloc_branch_delay_filled = 1;
-		/* 1 0	1 0 1  << 6  xkphys cached */
-		uasm_i_ori(p, ptr, ptr, 0x540);
+		/* insert bit[63:59] of CAC_BASE into bit[11:6] of ptr */
+		uasm_i_ori(p, ptr, ptr, ((u64)(CAC_BASE) >> 53));
+
 		uasm_i_drotr(p, ptr, ptr, 11);
 	}