MIPS: Optimise TLB handlers for MIPS32/64 R2 cores.

The EXT and INS instructions can be used to decrease code size and
thus speed up TLB handlers on MIPS32R2 and MIPS64R2 cores.
Signed-off-by: NSteven J. Hill <sjhill@mips.com>

arch/mips/mm/tlbex.c

@@ -933,6 +933,13 @@ build_get_pgde32(u32 **p, unsigned int tmp, unsigned int ptr)
 #endif
 	uasm_i_mfc0(p, tmp, C0_BADVADDR); /* get faulting address */
 	uasm_i_lw(p, ptr, uasm_rel_lo(pgdc), ptr);
+
+	if (cpu_has_mips_r2) {
+		uasm_i_ext(p, tmp, tmp, PGDIR_SHIFT, (32 - PGDIR_SHIFT));
+		uasm_i_ins(p, ptr, tmp, PGD_T_LOG2, (32 - PGDIR_SHIFT));
+		return;
+	}
+
 	uasm_i_srl(p, tmp, tmp, PGDIR_SHIFT); /* get pgd only bits */
 	uasm_i_sll(p, tmp, tmp, PGD_T_LOG2);
 	uasm_i_addu(p, ptr, ptr, tmp); /* add in pgd offset */
@@ -968,6 +975,15 @@ static void __cpuinit build_adjust_context(u32 **p, unsigned int ctx)
 
 static void __cpuinit build_get_ptep(u32 **p, unsigned int tmp, unsigned int ptr)
 {
+	if (cpu_has_mips_r2) {
+		/* PTE ptr offset is obtained from BadVAddr */
+		UASM_i_MFC0(p, tmp, C0_BADVADDR);
+		UASM_i_LW(p, ptr, 0, ptr);
+		uasm_i_ext(p, tmp, tmp, PAGE_SHIFT+1, PGDIR_SHIFT-PAGE_SHIFT-1);
+		uasm_i_ins(p, ptr, tmp, PTE_T_LOG2+1, PGDIR_SHIFT-PAGE_SHIFT-1);
+		return;
+	}
+
 	/*
 	 * Bug workaround for the Nevada. It seems as if under certain
 	 * circumstances the move from cp0_context might produce a